diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/filemap.c | 5 | ||||
| -rw-r--r-- | mm/gup.c | 14 | ||||
| -rw-r--r-- | mm/hugetlb.c | 37 | ||||
| -rw-r--r-- | mm/ksm.c | 3 | ||||
| -rw-r--r-- | mm/list_lru.c | 2 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/shmem.c | 2 | ||||
| -rw-r--r-- | mm/vmscan.c | 14 |
8 files changed, 62 insertions, 17 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index 1ffef05f1c1f..fc5165c744a8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1485,6 +1485,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, cond_resched(); find_page: + if (fatal_signal_pending(current)) { + error = -EINTR; + goto out; + } + page = find_get_page(mapping, index); if (!page) { page_cache_sync_readahead(mapping, @@ -32,6 +32,16 @@ static struct page *no_page_table(struct vm_area_struct *vma, return NULL; } +/* + * FOLL_FORCE can write to even unwritable pte's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +{ + return pte_write(pte) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); +} + static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { @@ -66,7 +76,7 @@ retry: } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) { + if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { pte_unmap_unlock(ptep, ptl); return NULL; } @@ -315,7 +325,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, * reCOWed by userspace write). */ if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags &= ~FOLL_WRITE; + *flags |= FOLL_COW; return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 88b472bec71d..2f47f0332a2c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1387,23 +1387,32 @@ 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. + * This routine has two main purposes: + * 1) Decrement the reservation count (resv_huge_pages) by the value passed + * in unused_resv_pages. This corresponds to the prior adjustments made + * to the associated reservation map. + * 2) Free any unused surplus pages that may have been allocated to satisfy + * the reservation. As many as unused_resv_pages may be freed. + * + * Called with hugetlb_lock held. However, the lock could be dropped (and + * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, + * we must make sure nobody else can claim pages we are in the process of + * freeing. Do this by ensuring resv_huge_page always is greater than the + * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; - /* Uncommit the reservation */ - h->resv_huge_pages -= unused_resv_pages; - /* Cannot return gigantic pages currently */ if (hstate_is_gigantic(h)) - return; + goto out; + /* + * Part (or even all) of the reservation could have been backed + * by pre-allocated pages. Only free surplus pages. + */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* @@ -1413,12 +1422,22 @@ static void return_unused_surplus_pages(struct hstate *h, * 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. + * + * Note that we decrement resv_huge_pages as we free the pages. If + * we drop the lock, resv_huge_pages will still be sufficiently large + * to cover subsequent pages we may free. */ while (nr_pages--) { + h->resv_huge_pages--; + unused_resv_pages--; if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) - break; + goto out; cond_resched_lock(&hugetlb_lock); } + +out: + /* Fully uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; } /* @@ -283,7 +283,8 @@ static inline struct rmap_item *alloc_rmap_item(void) { struct rmap_item *rmap_item; - rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL); + rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | + __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; diff --git a/mm/list_lru.c b/mm/list_lru.c index 909eca2c820e..84b4c21d78d7 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -532,6 +532,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, err = memcg_init_list_lru(lru, memcg_aware); if (err) { kfree(lru->node); + /* Do this so a list_lru_destroy() doesn't crash: */ + lru->node = NULL; goto out; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 99d4c1d0b858..18c63b754e49 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2009,8 +2009,8 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); zl = policy_zonelist(gfp, pol, node); - mpol_cond_put(pol); page = __alloc_pages_nodemask(gfp, order, zl, nmask); + mpol_cond_put(pol); out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; diff --git a/mm/shmem.c b/mm/shmem.c index 46511ad90bc5..feaaf6ea1b86 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -548,7 +548,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) struct shmem_inode_info *info = SHMEM_I(inode); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/mm/vmscan.c b/mm/vmscan.c index e1a95dbcd5f8..f16e330e1096 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -246,6 +246,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; + long scanned = 0, next_deferred; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0) @@ -267,7 +268,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); total_scan = freeable; - } + next_deferred = nr; + } else + next_deferred = total_scan; /* * We need to avoid excessive windup on filesystem shrinkers @@ -324,17 +327,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, count_vm_events(SLABS_SCANNED, nr_to_scan); total_scan -= nr_to_scan; + scanned += nr_to_scan; cond_resched(); } + if (next_deferred >= scanned) + next_deferred -= scanned; + else + next_deferred = 0; /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. If we exhausted the * scan, there is no need to do an update. */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, + if (next_deferred > 0) + new_nr = atomic_long_add_return(next_deferred, &shrinker->nr_deferred[nid]); else new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); |