diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 197 |
1 files changed, 149 insertions, 48 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 271e4432734c..a8c3087089d8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -40,6 +40,11 @@ int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; +/* + * Minimum page order among possible hugepage sizes, set to a proper value + * at boot time. + */ +static unsigned int minimum_order __read_mostly = UINT_MAX; __initdata LIST_HEAD(huge_boot_pages); @@ -212,8 +217,20 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * - * The region data structures are embedded into a resv_map and - * protected by a resv_map's lock + * The region data structures are embedded into a resv_map and protected + * by a resv_map's lock. The set of regions within the resv_map represent + * reservations for huge pages, or huge pages that have already been + * instantiated within the map. The from and to elements are huge page + * indicies into the associated mapping. from indicates the starting index + * of the region. to represents the first index past the end of the region. + * + * For example, a file region structure with from == 0 and to == 4 represents + * four huge pages in a mapping. It is important to note that the to element + * represents the first element past the end of the region. This is used in + * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. + * + * Interval notation of the form [from, to) will be used to indicate that + * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; @@ -221,10 +238,22 @@ struct file_region { long to; }; +/* + * Add the huge page range represented by [f, t) to the reserve + * map. Existing regions will be expanded to accommodate the + * specified range. We know only existing regions need to be + * expanded, because region_add is only called after region_chg + * with the same range. If a new file_region structure must + * be allocated, it is done in region_chg. + * + * Return the number of new huge pages added to the map. This + * number is greater than or equal to zero. + */ static long region_add(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *nrg, *trg; + long add = 0; spin_lock(&resv->lock); /* Locate the region we are either in or before. */ @@ -250,16 +279,45 @@ static long region_add(struct resv_map *resv, long f, long t) if (rg->to > t) t = rg->to; if (rg != nrg) { + /* Decrement return value by the deleted range. + * Another range will span this area so that by + * end of routine add will be >= zero + */ + add -= (rg->to - rg->from); list_del(&rg->link); kfree(rg); } } + + add += (nrg->from - f); /* Added to beginning of region */ nrg->from = f; + add += t - nrg->to; /* Added to end of region */ nrg->to = t; + spin_unlock(&resv->lock); - return 0; + VM_BUG_ON(add < 0); + return add; } +/* + * Examine the existing reserve map and determine how many + * huge pages in the specified range [f, t) are NOT currently + * represented. This routine is called before a subsequent + * call to region_add that will actually modify the reserve + * map to add the specified range [f, t). region_chg does + * not change the number of huge pages represented by the + * map. However, if the existing regions in the map can not + * be expanded to represent the new range, a new file_region + * structure is added to the map as a placeholder. This is + * so that the subsequent region_add call will have all the + * regions it needs and will not fail. + * + * Returns the number of huge pages that need to be added + * to the existing reservation map for the range [f, t). + * This number is greater or equal to zero. -ENOMEM is + * returned if a new file_region structure is needed and can + * not be allocated. + */ static long region_chg(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; @@ -326,6 +384,11 @@ out_nrg: return chg; } +/* + * Truncate the reserve map at index 'end'. Modify/truncate any + * region which contains end. Delete any regions past end. + * Return the number of huge pages removed from the map. + */ static long region_truncate(struct resv_map *resv, long end) { struct list_head *head = &resv->regions; @@ -361,6 +424,10 @@ out: return chg; } +/* + * Count and return the number of huge pages in the reserve map + * that intersect with the range [f, t). + */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; @@ -908,7 +975,6 @@ static void update_and_free_page(struct hstate *h, struct page *page) destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { - arch_release_hugepage(page); __free_pages(page, huge_page_order(h)); } } @@ -1093,10 +1159,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { - if (arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - return NULL; - } prep_new_huge_page(h, page, nid); } @@ -1188,19 +1250,13 @@ static void dissolve_free_huge_page(struct page *page) */ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { - unsigned int order = 8 * sizeof(void *); unsigned long pfn; - struct hstate *h; if (!hugepages_supported()) return; - /* Set scan step to minimum hugepage size */ - for_each_hstate(h) - if (order > huge_page_order(h)) - order = huge_page_order(h); - VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order)); - for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) + VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order)); + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) dissolve_free_huge_page(pfn_to_page(pfn)); } @@ -1254,11 +1310,6 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); - if (page && arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - page = NULL; - } - spin_lock(&hugetlb_lock); if (page) { INIT_LIST_HEAD(&page->lru); @@ -1423,46 +1474,56 @@ static void return_unused_surplus_pages(struct hstate *h, } /* - * 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 subpool usage 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 allocated from the subpool and instantiated the change should - * be committed via vma_commit_reservation. No action is required on - * failure. + * vma_needs_reservation and vma_commit_reservation are used by the huge + * page allocation routines to manage reservations. + * + * vma_needs_reservation is called to determine if the huge page at addr + * within the vma has an associated reservation. If a reservation is + * needed, the value 1 is returned. The caller is then responsible for + * managing the global reservation and subpool usage counts. After + * the huge page has been allocated, vma_commit_reservation is called + * to add the page to the reservation map. + * + * In the normal case, vma_commit_reservation returns the same value + * as the preceding vma_needs_reservation call. The only time this + * is not the case is if a reserve map was changed between calls. It + * is the responsibility of the caller to notice the difference and + * take appropriate action. */ -static long vma_needs_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) +static long __vma_reservation_common(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr, + bool commit) { struct resv_map *resv; pgoff_t idx; - long chg; + long ret; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); - chg = region_chg(resv, idx, idx + 1); + if (commit) + ret = region_add(resv, idx, idx + 1); + else + ret = region_chg(resv, idx, idx + 1); if (vma->vm_flags & VM_MAYSHARE) - return chg; + return ret; else - return chg < 0 ? chg : 0; + return ret < 0 ? ret : 0; } -static void vma_commit_reservation(struct hstate *h, + +static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct resv_map *resv; - pgoff_t idx; - - resv = vma_resv_map(vma); - if (!resv) - return; + return __vma_reservation_common(h, vma, addr, false); +} - idx = vma_hugecache_offset(h, vma, addr); - region_add(resv, idx, idx + 1); +static long vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, true); } static struct page *alloc_huge_page(struct vm_area_struct *vma, @@ -1471,7 +1532,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; - long chg; + long chg, commit; int ret, idx; struct hugetlb_cgroup *h_cg; @@ -1512,7 +1573,22 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_private(page, (unsigned long)spool); - vma_commit_reservation(h, vma, addr); + commit = vma_commit_reservation(h, vma, addr); + if (unlikely(chg > commit)) { + /* + * The page was added to the reservation map between + * vma_needs_reservation and vma_commit_reservation. + * This indicates a race with hugetlb_reserve_pages. + * Adjust for the subpool count incremented above AND + * in hugetlb_reserve_pages for the same page. Also, + * the reservation count added in hugetlb_reserve_pages + * no longer applies. + */ + long rsv_adjust; + + rsv_adjust = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -rsv_adjust); + } return page; out_uncharge_cgroup: @@ -1627,10 +1703,14 @@ static void __init hugetlb_init_hstates(void) struct hstate *h; for_each_hstate(h) { + if (minimum_order > huge_page_order(h)) + minimum_order = huge_page_order(h); + /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } + VM_BUG_ON(minimum_order == UINT_MAX); } static char * __init memfmt(char *buf, unsigned long n) @@ -3626,8 +3706,24 @@ int hugetlb_reserve_pages(struct inode *inode, * 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(resv_map, from, to); + if (!vma || vma->vm_flags & VM_MAYSHARE) { + long add = region_add(resv_map, from, to); + + if (unlikely(chg > add)) { + /* + * pages in this range were added to the reserve + * map between region_chg and region_add. This + * indicates a race with alloc_huge_page. Adjust + * the subpool and reserve counts modified above + * based on the difference. + */ + long rsv_adjust; + + rsv_adjust = hugepage_subpool_put_pages(spool, + chg - add); + hugetlb_acct_memory(h, -rsv_adjust); + } + } return 0; out_err: if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) @@ -3789,6 +3885,11 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { return NULL; } + +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + return 0; +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ |