summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c288
1 files changed, 91 insertions, 197 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b45a95363a84..ac65bb5e38ac 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -244,16 +244,66 @@ struct file_region {
long to;
};
+/* Must be called with resv->lock held. Calling this with count_only == true
+ * will count the number of pages to be added but will not modify the linked
+ * list.
+ */
+static long add_reservation_in_range(struct resv_map *resv, long f, long t,
+ bool count_only)
+{
+ long chg = 0;
+ struct list_head *head = &resv->regions;
+ struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+
+ /* Locate the region we are before or in. */
+ list_for_each_entry(rg, head, link)
+ if (f <= rg->to)
+ break;
+
+ /* Round our left edge to the current segment if it encloses us. */
+ if (f > rg->from)
+ f = rg->from;
+
+ chg = t - f;
+
+ /* Check for and consume any regions we now overlap with. */
+ nrg = rg;
+ list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ if (rg->from > t)
+ break;
+
+ /* We overlap with this area, if it extends further than
+ * us then we must extend ourselves. Account for its
+ * existing reservation.
+ */
+ if (rg->to > t) {
+ chg += rg->to - t;
+ t = rg->to;
+ }
+ chg -= rg->to - rg->from;
+
+ if (!count_only && rg != nrg) {
+ list_del(&rg->link);
+ kfree(rg);
+ }
+ }
+
+ if (!count_only) {
+ nrg->from = f;
+ nrg->to = t;
+ }
+
+ return chg;
+}
+
/*
* Add the huge page range represented by [f, t) to the reserve
- * map. In the normal case, existing regions will be expanded
- * to accommodate the specified range. Sufficient regions should
- * exist for expansion due to the previous call to region_chg
- * with the same range. However, it is possible that region_del
- * could have been called after region_chg and modifed the map
- * in such a way that no region exists to be expanded. In this
- * case, pull a region descriptor from the cache associated with
- * the map and use that for the new range.
+ * map. Existing regions will be expanded to accommodate the specified
+ * range, or a region will be taken from the cache. Sufficient regions
+ * must exist in the cache due to the previous call to region_chg with
+ * the same range.
*
* Return the number of new huge pages added to the map. This
* number is greater than or equal to zero.
@@ -261,7 +311,7 @@ struct file_region {
static long region_add(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
- struct file_region *rg, *nrg, *trg;
+ struct file_region *rg, *nrg;
long add = 0;
spin_lock(&resv->lock);
@@ -272,9 +322,8 @@ static long region_add(struct resv_map *resv, long f, long t)
/*
* If no region exists which can be expanded to include the
- * specified range, the list must have been modified by an
- * interleving call to region_del(). Pull a region descriptor
- * from the cache and use it for this range.
+ * specified range, pull a region descriptor from the cache
+ * and use it for this range.
*/
if (&rg->link == head || t < rg->from) {
VM_BUG_ON(resv->region_cache_count <= 0);
@@ -292,38 +341,7 @@ static long region_add(struct resv_map *resv, long f, long t)
goto out_locked;
}
- /* Round our left edge to the current segment if it encloses us. */
- if (f > rg->from)
- f = rg->from;
-
- /* Check for and consume any regions we now overlap with. */
- nrg = rg;
- list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
- if (&rg->link == head)
- break;
- if (rg->from > t)
- break;
-
- /* If this area reaches higher then extend our area to
- * include it completely. If this is not the first area
- * which we intend to reuse, free it. */
- 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;
+ add = add_reservation_in_range(resv, f, t, false);
out_locked:
resv->adds_in_progress--;
@@ -339,15 +357,9 @@ out_locked:
* 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.
- *
- * Upon entry, region_chg will also examine the cache of region descriptors
- * associated with the map. If there are not enough descriptors cached, one
- * will be allocated for the in progress add operation.
+ * map. A new file_region structure is added to the cache
+ * as a placeholder, 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
@@ -356,11 +368,8 @@ out_locked:
*/
static long region_chg(struct resv_map *resv, long f, long t)
{
- struct list_head *head = &resv->regions;
- struct file_region *rg, *nrg = NULL;
long chg = 0;
-retry:
spin_lock(&resv->lock);
retry_locked:
resv->adds_in_progress++;
@@ -378,10 +387,8 @@ retry_locked:
spin_unlock(&resv->lock);
trg = kmalloc(sizeof(*trg), GFP_KERNEL);
- if (!trg) {
- kfree(nrg);
+ if (!trg)
return -ENOMEM;
- }
spin_lock(&resv->lock);
list_add(&trg->link, &resv->region_cache);
@@ -389,61 +396,8 @@ retry_locked:
goto retry_locked;
}
- /* Locate the region we are before or in. */
- list_for_each_entry(rg, head, link)
- if (f <= rg->to)
- break;
+ chg = add_reservation_in_range(resv, f, t, true);
- /* If we are below the current region then a new region is required.
- * Subtle, allocate a new region at the position but make it zero
- * size such that we can guarantee to record the reservation. */
- if (&rg->link == head || t < rg->from) {
- if (!nrg) {
- resv->adds_in_progress--;
- spin_unlock(&resv->lock);
- nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
- if (!nrg)
- return -ENOMEM;
-
- nrg->from = f;
- nrg->to = f;
- INIT_LIST_HEAD(&nrg->link);
- goto retry;
- }
-
- list_add(&nrg->link, rg->link.prev);
- chg = t - f;
- goto out_nrg;
- }
-
- /* Round our left edge to the current segment if it encloses us. */
- if (f > rg->from)
- f = rg->from;
- chg = t - f;
-
- /* Check for and consume any regions we now overlap with. */
- list_for_each_entry(rg, rg->link.prev, link) {
- if (&rg->link == head)
- break;
- if (rg->from > t)
- goto out;
-
- /* We overlap with this area, if it extends further than
- * us then we must extend ourselves. Account for its
- * existing reservation. */
- if (rg->to > t) {
- chg += rg->to - t;
- t = rg->to;
- }
- chg -= rg->to - rg->from;
- }
-
-out:
- spin_unlock(&resv->lock);
- /* We already know we raced and no longer need the new region */
- kfree(nrg);
- return chg;
-out_nrg:
spin_unlock(&resv->lock);
return chg;
}
@@ -1069,85 +1023,12 @@ static void free_gigantic_page(struct page *page, unsigned int order)
}
#ifdef CONFIG_CONTIG_ALLOC
-static int __alloc_gigantic_page(unsigned long start_pfn,
- unsigned long nr_pages, gfp_t gfp_mask)
-{
- unsigned long end_pfn = start_pfn + nr_pages;
- return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
- gfp_mask);
-}
-
-static bool pfn_range_valid_gigantic(struct zone *z,
- unsigned long start_pfn, unsigned long nr_pages)
-{
- unsigned long i, end_pfn = start_pfn + nr_pages;
- struct page *page;
-
- for (i = start_pfn; i < end_pfn; i++) {
- page = pfn_to_online_page(i);
- if (!page)
- return false;
-
- if (page_zone(page) != z)
- return false;
-
- if (PageReserved(page))
- return false;
-
- if (page_count(page) > 0)
- return false;
-
- if (PageHuge(page))
- return false;
- }
-
- return true;
-}
-
-static bool zone_spans_last_pfn(const struct zone *zone,
- unsigned long start_pfn, unsigned long nr_pages)
-{
- unsigned long last_pfn = start_pfn + nr_pages - 1;
- return zone_spans_pfn(zone, last_pfn);
-}
-
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask)
{
- unsigned int order = huge_page_order(h);
- unsigned long nr_pages = 1 << order;
- unsigned long ret, pfn, flags;
- struct zonelist *zonelist;
- struct zone *zone;
- struct zoneref *z;
+ unsigned long nr_pages = 1UL << huge_page_order(h);
- zonelist = node_zonelist(nid, gfp_mask);
- for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) {
- spin_lock_irqsave(&zone->lock, flags);
-
- pfn = ALIGN(zone->zone_start_pfn, nr_pages);
- while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
- if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) {
- /*
- * We release the zone lock here because
- * alloc_contig_range() will also lock the zone
- * at some point. If there's an allocation
- * spinning on this lock, it may win the race
- * and cause alloc_contig_range() to fail...
- */
- spin_unlock_irqrestore(&zone->lock, flags);
- ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask);
- if (!ret)
- return pfn_to_page(pfn);
- spin_lock_irqsave(&zone->lock, flags);
- }
- pfn += nr_pages;
- }
-
- spin_unlock_irqrestore(&zone->lock, flags);
- }
-
- return NULL;
+ return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
}
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
@@ -3915,7 +3796,7 @@ retry:
* handling userfault. Reacquire after handling
* fault to make calling code simpler.
*/
- hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
+ hash = hugetlb_fault_mutex_hash(mapping, idx);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
ret = handle_userfault(&vmf, VM_UFFD_MISSING);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -4042,8 +3923,7 @@ backout_unlocked:
}
#ifdef CONFIG_SMP
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
- pgoff_t idx, unsigned long address)
+u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
{
unsigned long key[2];
u32 hash;
@@ -4051,7 +3931,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
key[0] = (unsigned long) mapping;
key[1] = idx;
- hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
+ hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0);
return hash & (num_fault_mutexes - 1);
}
@@ -4060,8 +3940,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
* For uniprocesor systems we always use a single mutex, so just
* return 0 and avoid the hashing overhead.
*/
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
- pgoff_t idx, unsigned long address)
+u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
{
return 0;
}
@@ -4105,7 +3984,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
* get spurious allocation failures if two CPUs race to instantiate
* the same page in the page cache.
*/
- hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
+ hash = hugetlb_fault_mutex_hash(mapping, idx);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
entry = huge_ptep_get(ptep);
@@ -4459,6 +4338,21 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
break;
}
}
+
+ /*
+ * If subpage information not requested, update counters
+ * and skip the same_page loop below.
+ */
+ if (!pages && !vmas && !pfn_offset &&
+ (vaddr + huge_page_size(h) < vma->vm_end) &&
+ (remainder >= pages_per_huge_page(h))) {
+ vaddr += huge_page_size(h);
+ remainder -= pages_per_huge_page(h);
+ i += pages_per_huge_page(h);
+ spin_unlock(ptl);
+ continue;
+ }
+
same_page:
if (pages) {
pages[i] = mem_map_offset(page, pfn_offset);
@@ -4842,7 +4736,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (!vma_shareable(vma, addr))
return (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
if (svma == vma)
continue;
@@ -4872,7 +4766,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
spin_unlock(ptl);
out:
pte = (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
return pte;
}