From 3dbb95f7895e378514ffefa93cc887fb1bc9df94 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Wed, 11 Sep 2013 14:20:25 -0700 Subject: mm: replace strict_strtoul() with kstrtoul() The use of strict_strtoul() is not preferred, because strict_strtoul() is obsolete. Thus, kstrtoul() should be used. Signed-off-by: Jingoo Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b60f33080a28..6e514831bda5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1526,7 +1526,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h; NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); - err = strict_strtoul(buf, 10, &count); + err = kstrtoul(buf, 10, &count); if (err) goto out; @@ -1617,7 +1617,7 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, if (h->order >= MAX_ORDER) return -EINVAL; - err = strict_strtoul(buf, 10, &input); + err = kstrtoul(buf, 10, &input); if (err) return err; -- cgit v1.2.3 From 9966c4bbb110003ee218c5c4df583041b57027c4 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:20:50 -0700 Subject: mm, hugetlb: move up the code which check availability of free huge page In this time we are holding a hugetlb_lock, so hstate values can't be changed. If we don't have any usable free huge page in this time, we don't need to proceed with the processing. So move this code up. Signed-off-by: Joonsoo Kim Acked-by: Michal Hocko Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Cc: Aneesh Kumar K.V Acked-by: Hillf Danton Cc: Naoya Horiguchi Cc: Rik van Riel Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6e514831bda5..a87903578810 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -539,10 +539,6 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, struct zoneref *z; unsigned int cpuset_mems_cookie; -retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); - zonelist = huge_zonelist(vma, address, - htlb_alloc_mask, &mpol, &nodemask); /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are @@ -556,6 +552,11 @@ retry_cpuset: if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) goto err; +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + zonelist = huge_zonelist(vma, address, + htlb_alloc_mask, &mpol, &nodemask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { @@ -574,7 +575,6 @@ retry_cpuset: return page; err: - mpol_cond_put(mpol); return NULL; } -- cgit v1.2.3 From c748c26294600d7e4f0d1f2f61449d3a740f102f Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:20:57 -0700 Subject: mm, hugetlb: trivial commenting fix The name of the mutex written in comment is wrong. Fix it. Signed-off-by: Joonsoo Kim Acked-by: Michal Hocko Acked-by: Hillf Danton Reviewed-by: Aneesh Kumar K.V Cc: Aneesh Kumar K.V Cc: Naoya Horiguchi Cc: Wanpeng Li Cc: Rik van Riel Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a87903578810..bfca1b00b09b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -135,9 +135,9 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) * 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 + * and the hugetlb_instantiation_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: + * the hugetlb_instantiation_mutex: * * down_write(&mm->mmap_sem); * or -- cgit v1.2.3 From 81a6fcae3ff3f6af1c9d7e31499e68fda2b3f58d Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:20:58 -0700 Subject: mm, hugetlb: clean-up alloc_huge_page() Unify successful allocation paths to make the code more readable. There are no functional changes. Signed-off-by: Joonsoo Kim Acked-by: Michal Hocko Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Cc: Hillf Danton Cc: Naoya Horiguchi Cc: Wanpeng Li Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bfca1b00b09b..a698d40d1c3e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1166,12 +1166,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, } spin_lock(&hugetlb_lock); page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); - if (page) { - /* update page cgroup details */ - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), - h_cg, page); - spin_unlock(&hugetlb_lock); - } else { + if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { @@ -1182,11 +1177,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); - hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), - h_cg, page); list_move(&page->lru, &h->hugepage_activelist); - spin_unlock(&hugetlb_lock); + /* Fall through */ } + hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); + spin_unlock(&hugetlb_lock); set_page_private(page, (unsigned long)spool); -- cgit v1.2.3 From b2261026825ed34066b24069359d118098bb1876 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:00 -0700 Subject: mm, hugetlb: fix and clean-up node iteration code to alloc or free Current node iteration code have a minor problem which do one more node rotation if we can't succeed to allocate. For example, if we start to allocate at node 0, we stop to iterate at node 0. Then we start to allocate at node 1 for next allocation. I introduce new macros "for_each_node_mask_to_[alloc|free]" and fix and clean-up node iteration code to alloc or free. This makes code more understandable. Signed-off-by: Joonsoo Kim Reviewed-by: Aneesh Kumar K.V Acked-by: Hillf Danton Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Wanpeng Li Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 143 +++++++++++++++++++++++++---------------------------------- 1 file changed, 61 insertions(+), 82 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a698d40d1c3e..08b7595fe3c1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -772,33 +772,6 @@ static int hstate_next_node_to_alloc(struct hstate *h, 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 = hstate_next_node_to_alloc(h, nodes_allowed); - next_nid = start_nid; - - do { - page = alloc_fresh_huge_page_node(h, next_nid); - if (page) { - ret = 1; - break; - } - next_nid = hstate_next_node_to_alloc(h, nodes_allowed); - } while (next_nid != start_nid); - - if (ret) - count_vm_event(HTLB_BUDDY_PGALLOC); - else - count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); - - return ret; -} - /* * helper for free_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the @@ -817,6 +790,40 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) return nid; } +#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ + nr_nodes--) + +#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ + for (nr_nodes = nodes_weight(*mask); \ + nr_nodes > 0 && \ + ((node = hstate_next_node_to_free(hs, mask)) || 1); \ + nr_nodes--) + +static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed) +{ + struct page *page; + int nr_nodes, node; + int ret = 0; + + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + page = alloc_fresh_huge_page_node(h, node); + if (page) { + ret = 1; + break; + } + } + + if (ret) + count_vm_event(HTLB_BUDDY_PGALLOC); + else + count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); + + return ret; +} + /* * Free huge page from pool from next node to free. * Attempt to keep persistent huge pages more or less @@ -826,36 +833,31 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { - int start_nid; - int next_nid; + int nr_nodes, node; int ret = 0; - start_nid = hstate_next_node_to_free(h, nodes_allowed); - next_nid = start_nid; - - do { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * 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])) { + if ((!acct_surplus || h->surplus_huge_pages_node[node]) && + !list_empty(&h->hugepage_freelists[node])) { struct page *page = - list_entry(h->hugepage_freelists[next_nid].next, + list_entry(h->hugepage_freelists[node].next, struct page, lru); list_del(&page->lru); h->free_huge_pages--; - h->free_huge_pages_node[next_nid]--; + h->free_huge_pages_node[node]--; if (acct_surplus) { h->surplus_huge_pages--; - h->surplus_huge_pages_node[next_nid]--; + h->surplus_huge_pages_node[node]--; } 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; } @@ -1192,14 +1194,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, int __weak alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; - int nr_nodes = nodes_weight(node_states[N_MEMORY]); + int nr_nodes, node; - while (nr_nodes) { + for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = __alloc_bootmem_node_nopanic( - NODE_DATA(hstate_next_node_to_alloc(h, - &node_states[N_MEMORY])), + addr = __alloc_bootmem_node_nopanic(NODE_DATA(node), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -1211,7 +1211,6 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) m = addr; goto found; } - nr_nodes--; } return 0; @@ -1350,48 +1349,28 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count, static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { - int start_nid, next_nid; - int ret = 0; + int nr_nodes, node; 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) { + for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node]) + goto found; } - 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; - } + } else { + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + if (h->surplus_huge_pages_node[node] < + h->nr_huge_pages_node[node]) + goto found; } + } + return 0; - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (next_nid != start_nid); - - return ret; +found: + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[node] += delta; + return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) -- cgit v1.2.3 From c0d934ba278935fa751057091fe4a7c02d814f68 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:02 -0700 Subject: mm, hugetlb: remove redundant list_empty check in gather_surplus_pages() If list is empty, list_for_each_entry_safe() doesn't do anything. So, this check is redundant. Remove it. Signed-off-by: Joonsoo Kim Acked-by: Michal Hocko Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Acked-by: Hillf Danton Cc: Naoya Horiguchi Cc: Wanpeng Li Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 08b7595fe3c1..a13be48b818b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1037,11 +1037,8 @@ free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ - if (!list_empty(&surplus_list)) { - list_for_each_entry_safe(page, tmp, &surplus_list, lru) { - put_page(page); - } - } + list_for_each_entry_safe(page, tmp, &surplus_list, lru) + put_page(page); spin_lock(&hugetlb_lock); return ret; -- cgit v1.2.3 From 37a2140dc2145a6f154172286944a1861e978dfd Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:04 -0700 Subject: mm, hugetlb: do not use a page in page cache for cow optimization Currently, we use a page with mapped count 1 in page cache for cow optimization. If we find this condition, we don't allocate a new page and copy contents. Instead, we map this page directly. This may introduce a problem that writting to private mapping overwrite hugetlb file directly. You can find this situation with following code. size = 20 * MB; flag = MAP_SHARED; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); return -1; } p[0] = 's'; fprintf(stdout, "BEFORE STEAL PRIVATE WRITE: %c\n", p[0]); munmap(p, size); flag = MAP_PRIVATE; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); } p[0] = 'c'; munmap(p, size); flag = MAP_SHARED; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); return -1; } fprintf(stdout, "AFTER STEAL PRIVATE WRITE: %c\n", p[0]); munmap(p, size); We can see that "AFTER STEAL PRIVATE WRITE: c", not "AFTER STEAL PRIVATE WRITE: s". If we turn off this optimization to a page in page cache, the problem is disappeared. So, I change the trigger condition of optimization. If this page is not AnonPage, we don't do optimization. This makes this optimization turning off for a page cache. Signed-off-by: Joonsoo Kim Acked-by: Michal Hocko Reviewed-by: Wanpeng Li Reviewed-by: Naoya Horiguchi Cc: Aneesh Kumar K.V Acked-by: Hillf Danton Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a13be48b818b..da027a3307af 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2528,7 +2528,6 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, { struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; - int avoidcopy; int outside_reserve = 0; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ @@ -2538,10 +2537,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ - avoidcopy = (page_mapcount(old_page) == 1); - if (avoidcopy) { - if (PageAnon(old_page)) - page_move_anon_rmap(old_page, vma, address); + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { + page_move_anon_rmap(old_page, vma, address); set_huge_ptep_writable(vma, address, ptep); return 0; } -- cgit v1.2.3 From 72231b03ccf126ca04fba8359998ef7dfd195577 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:06 -0700 Subject: mm, hugetlb: add VM_NORESERVE check in vma_has_reserves() If we map the region with MAP_NORESERVE and MAP_SHARED, we can skip to check reserve counting and eventually we cannot be ensured to allocate a huge page in fault time. With following example code, you can easily find this situation. Assume 2MB, nr_hugepages = 100 fd = hugetlbfs_unlinked_fd(); if (fd < 0) return 1; size = 200 * MB; flag = MAP_SHARED; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); return -1; } size = 2 * MB; flag = MAP_ANONYMOUS | MAP_SHARED | MAP_HUGETLB | MAP_NORESERVE; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, -1, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); } p[0] = '0'; sleep(10); During executing sleep(10), run 'cat /proc/meminfo' on another process. HugePages_Free: 99 HugePages_Rsvd: 100 Number of free should be higher or equal than number of reserve, but this aren't. This represent that non reserved shared mapping steal a reserved page. Non reserved shared mapping should not eat into reserve space. If we consider VM_NORESERVE in vma_has_reserve() and return 0 which mean that we don't have reserved pages, then we check that we have enough free pages in dequeue_huge_page_vma(). This prevent to steal a reserved page. With this change, above test generate a SIGBUG which is correct, because all free pages are reserved and non reserved shared mapping can't get a free page. Signed-off-by: Joonsoo Kim Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Acked-by: Hillf Danton Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index da027a3307af..cb134e6a9fee 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -464,6 +464,8 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) /* Returns true if the VMA has associated reserve pages */ static int vma_has_reserves(struct vm_area_struct *vma) { + if (vma->vm_flags & VM_NORESERVE) + return 0; if (vma->vm_flags & VM_MAYSHARE) return 1; if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) -- cgit v1.2.3 From a63884e921cb33a6beb260fa88bcbf1712d98a9a Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:07 -0700 Subject: mm, hugetlb: remove decrement_hugepage_resv_vma() Now, Checking condition of decrement_hugepage_resv_vma() and vma_has_reserves() is same, so we can clean-up this function with vma_has_reserves(). Additionally, decrement_hugepage_resv_vma() has only one call site, so we can remove function and embed it into dequeue_huge_page_vma() directly. This patch implement it. Signed-off-by: Joonsoo Kim Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Acked-by: Hillf Danton Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 31 ++++++++++--------------------- 1 file changed, 10 insertions(+), 21 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cb134e6a9fee..dacf0d2256d9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -434,25 +434,6 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) return (get_vma_private_data(vma) & flag) != 0; } -/* Decrement the reserved pages in the hugepage pool by one */ -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_MAYSHARE) { - /* Shared mappings always use reserves */ - 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. - */ - h->resv_huge_pages--; - } -} - /* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { @@ -466,10 +447,18 @@ static int vma_has_reserves(struct vm_area_struct *vma) { if (vma->vm_flags & VM_NORESERVE) return 0; + + /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) return 1; + + /* + * Only the process that called mmap() has reserves for + * private mappings. + */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; + return 0; } @@ -564,8 +553,8 @@ retry_cpuset: if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { - if (!avoid_reserve) - decrement_hugepage_resv_vma(h, vma); + if (!avoid_reserve && vma_has_reserves(vma)) + h->resv_huge_pages--; break; } } -- cgit v1.2.3 From af0ed73e699bb0453603b1d1a4727377641b2096 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:18 -0700 Subject: mm, hugetlb: decrement reserve count if VM_NORESERVE alloc page cache If a vma with VM_NORESERVE allocate a new page for page cache, we should check whether this area is reserved or not. If this address is already reserved by other process(in case of chg == 0), we should decrement reserve count, because this allocated page will go into page cache and currently, there is no way to know that this page comes from reserved pool or not when releasing inode. This may introduce over-counting problem to reserved count. With following example code, you can easily reproduce this situation. Assume 2MB, nr_hugepages = 100 size = 20 * MB; flag = MAP_SHARED; p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (p == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); return -1; } flag = MAP_SHARED | MAP_NORESERVE; q = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); if (q == MAP_FAILED) { fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); } q[0] = 'c'; After finish the program, run 'cat /proc/meminfo'. You can see below result. HugePages_Free: 100 HugePages_Rsvd: 1 To fix this, we should check our mapping type and tracked region. If our mapping is VM_NORESERVE, VM_MAYSHARE and chg is 0, this imply that current allocated page will go into page cache which is already reserved region when mapping is created. In this case, we should decrease reserve count. As implementing above, this patch solve the problem. [akpm@linux-foundation.org: fix spelling in comment] Signed-off-by: Joonsoo Kim Reviewed-by: Wanpeng Li Reviewed-by: Aneesh Kumar K.V Acked-by: Hillf Danton Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Rik van Riel Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Davidlohr Bueso Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dacf0d2256d9..5b084c7b34c6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -443,10 +443,23 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) } /* Returns true if the VMA has associated reserve pages */ -static int vma_has_reserves(struct vm_area_struct *vma) +static int vma_has_reserves(struct vm_area_struct *vma, long chg) { - if (vma->vm_flags & VM_NORESERVE) - return 0; + if (vma->vm_flags & VM_NORESERVE) { + /* + * This address is already reserved by other process(chg == 0), + * so, we should decrement reserved count. Without decrementing, + * reserve count remains after releasing inode, because this + * allocated page will go into page cache and is regarded as + * coming from reserved pool in releasing step. Currently, we + * don't have any other solution to deal with this situation + * properly, so add work-around here. + */ + if (vma->vm_flags & VM_MAYSHARE && chg == 0) + return 1; + else + return 0; + } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) @@ -520,7 +533,8 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve) + unsigned long address, int avoid_reserve, + long chg) { struct page *page = NULL; struct mempolicy *mpol; @@ -535,7 +549,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ - if (!vma_has_reserves(vma) && + if (!vma_has_reserves(vma, chg) && h->free_huge_pages - h->resv_huge_pages == 0) goto err; @@ -553,8 +567,12 @@ retry_cpuset: if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { - if (!avoid_reserve && vma_has_reserves(vma)) - h->resv_huge_pages--; + if (avoid_reserve) + break; + if (!vma_has_reserves(vma, chg)) + break; + + h->resv_huge_pages--; break; } } @@ -1155,7 +1173,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg); if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page(h, NUMA_NO_NODE); -- cgit v1.2.3 From 4ef91848043679b272a1a5b8e2879acf696ba9e2 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:51 -0700 Subject: mm, hugetlb: protect reserved pages when soft offlining a hugepage Don't use the reserve pool when soft offlining a hugepage. Check we have free pages outside the reserve pool before we dequeue the huge page. Otherwise, we can steal other's reserve page. Signed-off-by: Joonsoo Kim Reviewed-by: Aneesh Kumar Cc: Naoya Horiguchi Reviewed-by: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5b084c7b34c6..583db1948145 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -955,10 +955,11 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) */ struct page *alloc_huge_page_node(struct hstate *h, int nid) { - struct page *page; + struct page *page = NULL; spin_lock(&hugetlb_lock); - page = dequeue_huge_page_node(h, nid); + if (h->free_huge_pages - h->resv_huge_pages > 0) + page = dequeue_huge_page_node(h, nid); spin_unlock(&hugetlb_lock); if (!page) -- cgit v1.2.3 From f522c3ac00a49128115f99a5fcb95a447601c1c3 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:53 -0700 Subject: mm, hugetlb: change variable name reservations to resv 'reservations' is so long name as a variable and we use 'resv_map' to represent 'struct resv_map' in other place. To reduce confusion and unreadability, change it. Signed-off-by: Joonsoo Kim Reviewed-by: Aneesh Kumar Cc: Naoya Horiguchi Reviewed-by: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 583db1948145..204550ae29c8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1115,9 +1115,9 @@ static long vma_needs_reservation(struct hstate *h, } else { long err; pgoff_t idx = vma_hugecache_offset(h, vma, addr); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); - err = region_chg(&reservations->regions, idx, idx + 1); + err = region_chg(&resv->regions, idx, idx + 1); if (err < 0) return err; return 0; @@ -1135,10 +1135,10 @@ static void vma_commit_reservation(struct hstate *h, } 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); + struct resv_map *resv = vma_resv_map(vma); /* Mark this page used in the map. */ - region_add(&reservations->regions, idx, idx + 1); + region_add(&resv->regions, idx, idx + 1); } } @@ -2188,7 +2188,7 @@ out: static void hugetlb_vm_op_open(struct vm_area_struct *vma) { - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); /* * This new VMA should share its siblings reservation map if present. @@ -2198,34 +2198,34 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (reservations) - kref_get(&reservations->refs); + if (resv) + kref_get(&resv->refs); } static void resv_map_put(struct vm_area_struct *vma) { - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); - if (!reservations) + if (!resv) return; - kref_put(&reservations->refs, resv_map_release); + kref_put(&resv->refs, resv_map_release); } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); - struct resv_map *reservations = vma_resv_map(vma); + struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve; unsigned long start; unsigned long end; - if (reservations) { + if (resv) { 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); + region_count(&resv->regions, start, end); resv_map_put(vma); -- cgit v1.2.3 From 8bb3f12e7d4f7b043a7c5aa3831e72041e80dc4a Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:54 -0700 Subject: mm, hugetlb: fix subpool accounting handling If we alloc hugepage with avoid_reserve, we don't dequeue reserved one. So, we should check subpool counter when avoid_reserve. This patch implement it. Signed-off-by: Joonsoo Kim Cc: Aneesh Kumar Cc: Naoya Horiguchi Cc: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 204550ae29c8..dec5772c8c5c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1164,13 +1164,14 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(-ENOMEM); - if (chg) - if (hugepage_subpool_get_pages(spool, chg)) + if (chg || avoid_reserve) + if (hugepage_subpool_get_pages(spool, 1)) return ERR_PTR(-ENOSPC); ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) { - hugepage_subpool_put_pages(spool, chg); + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); @@ -1182,7 +1183,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); - hugepage_subpool_put_pages(spool, chg); + if (chg || avoid_reserve) + hugepage_subpool_put_pages(spool, 1); return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); -- cgit v1.2.3 From 5944d0116c773319a48ea6812d1891aa6d0bbbbf Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:55 -0700 Subject: mm, hugetlb: remove useless check about mapping type is_vma_resv_set(vma, HPAGE_RESV_OWNER) implys that this mapping is for private. So we don't need to check whether this mapping is for shared or not. This patch is just for clean-up. Signed-off-by: Joonsoo Kim Cc: Aneesh Kumar Cc: Naoya Horiguchi Reviewed-by: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dec5772c8c5c..f6347ec4fd0a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2564,8 +2564,7 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_MAYSHARE) && - is_vma_resv_set(vma, HPAGE_RESV_OWNER) && + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; -- cgit v1.2.3 From 8312034f3604bc0339c40545c538116f4ddad152 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:57 -0700 Subject: mm, hugetlb: grab a page_table_lock after page_cache_release We don't need to grab a page_table_lock when we try to release a page. So, defer to grab a page_table_lock. Signed-off-by: Joonsoo Kim Reviewed-by: Naoya Horiguchi Cc: Aneesh Kumar Reviewed-by: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f6347ec4fd0a..5bf6468a8862 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2647,10 +2647,11 @@ retry_avoidcopy: } spin_unlock(&mm->page_table_lock); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - /* Caller expects lock to be held */ - spin_lock(&mm->page_table_lock); page_cache_release(new_page); page_cache_release(old_page); + + /* Caller expects lock to be held */ + spin_lock(&mm->page_table_lock); return 0; } -- cgit v1.2.3 From 07443a85ad90c7b62fbe11dcd3d6a1de1e10516f Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Sep 2013 14:21:58 -0700 Subject: mm, hugetlb: return a reserved page to a reserved pool if failed If we fail with a reserved page, just calling put_page() is not sufficient, because put_page() invoke free_huge_page() at last step and it doesn't know whether a page comes from a reserved pool or not. So it doesn't do anything related to reserved count. This makes reserve count lower than how we need, because reserve count already decrease in dequeue_huge_page_vma(). This patch fix this situation. Signed-off-by: Joonsoo Kim Cc: Aneesh Kumar Cc: Naoya Horiguchi Cc: Davidlohr Bueso Cc: David Gibson Cc: Wanpeng Li Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5bf6468a8862..06315560bd23 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -572,6 +572,7 @@ retry_cpuset: if (!vma_has_reserves(vma, chg)) break; + SetPagePrivate(page); h->resv_huge_pages--; break; } @@ -629,15 +630,20 @@ static void free_huge_page(struct page *page) int nid = page_to_nid(page); struct hugepage_subpool *spool = (struct hugepage_subpool *)page_private(page); + bool restore_reserve; set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); + restore_reserve = PagePrivate(page); spin_lock(&hugetlb_lock); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); + if (restore_reserve) + h->resv_huge_pages++; + if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { /* remove the page from active list */ list_del(&page->lru); @@ -2636,6 +2642,8 @@ retry_avoidcopy: 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))) { + ClearPagePrivate(new_page); + /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); set_huge_pte_at(mm, address, ptep, @@ -2747,6 +2755,7 @@ retry: goto retry; goto out; } + ClearPagePrivate(page); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); @@ -2793,8 +2802,10 @@ retry: if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; - if (anon_rmap) + if (anon_rmap) { + ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, address); + } else page_dup_rmap(page); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) -- cgit v1.2.3 From 31caf665e666b51fe36efd1e54031ed29e86c0b4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:21:59 -0700 Subject: mm: migrate: make core migration code aware of hugepage Currently hugepage migration is available only for soft offlining, but it's also useful for some other users of page migration (clearly because users of hugepage can enjoy the benefit of mempolicy and memory hotplug.) So this patchset tries to extend such users to support hugepage migration. The target of this patchset is to enable hugepage migration for NUMA related system calls (migrate_pages(2), move_pages(2), and mbind(2)), and memory hotplug. This patchset does not add hugepage migration for memory compaction, because users of memory compaction mainly expect to construct thp by arranging raw pages, and there's little or no need to compact hugepages. CMA, another user of page migration, can have benefit from hugepage migration, but is not enabled to support it for now (just because of lack of testing and expertise in CMA.) Hugepage migration of non pmd-based hugepage (for example 1GB hugepage in x86_64, or hugepages in architectures like ia64) is not enabled for now (again, because of lack of testing.) As for how these are achived, I extended the API (migrate_pages()) to handle hugepage (with patch 1 and 2) and adjusted code of each caller to check and collect movable hugepages (with patch 3-7). Remaining 2 patches are kind of miscellaneous ones to avoid unexpected behavior. Patch 8 is about making sure that we only migrate pmd-based hugepages. And patch 9 is about choosing appropriate zone for hugepage allocation. My test is mainly functional one, simply kicking hugepage migration via each entry point and confirm that migration is done correctly. Test code is available here: git://github.com/Naoya-Horiguchi/test_hugepage_migration_extension.git And I always run libhugetlbfs test when changing hugetlbfs's code. With this patchset, no regression was found in the test. This patch (of 9): Before enabling each user of page migration to support hugepage, this patch enables the list of pages for migration to link not only LRU pages, but also hugepages. As a result, putback_movable_pages() and migrate_pages() can handle both of LRU pages and hugepages. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 06315560bd23..e51723866fb1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -48,7 +48,8 @@ static unsigned long __initdata default_hstate_max_huge_pages; static unsigned long __initdata default_hstate_size; /* - * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages + * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, + * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); @@ -3422,3 +3423,23 @@ int dequeue_hwpoisoned_huge_page(struct page *hpage) return ret; } #endif + +bool isolate_huge_page(struct page *page, struct list_head *list) +{ + VM_BUG_ON(!PageHead(page)); + if (!get_page_unless_zero(page)) + return false; + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, list); + spin_unlock(&hugetlb_lock); + return true; +} + +void putback_active_hugepage(struct page *page) +{ + VM_BUG_ON(!PageHead(page)); + spin_lock(&hugetlb_lock); + list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); + spin_unlock(&hugetlb_lock); + put_page(page); +} -- cgit v1.2.3 From 74060e4d78795c7c43805133cb717d82533d4e0d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:06 -0700 Subject: mm: mbind: add hugepage migration code to mbind() Extend do_mbind() to handle vma with VM_HUGETLB set. We will be able to migrate hugepage with mbind(2) after applying the enablement patch which comes later in this series. Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Acked-by: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e51723866fb1..d37b3b95c439 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1207,6 +1207,20 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return page; } +/* + * alloc_huge_page()'s wrapper which simply returns the page if allocation + * succeeds, otherwise NULL. This function is called from new_vma_page(), + * where no ERR_VALUE is expected to be returned. + */ +struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve) +{ + struct page *page = alloc_huge_page(vma, addr, avoid_reserve); + if (IS_ERR(page)) + page = NULL; + return page; +} + int __weak alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; -- cgit v1.2.3 From c8721bbbdd36382de51cd6b7a56322e0acca2414 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:09 -0700 Subject: mm: memory-hotplug: enable memory hotplug to handle hugepage Until now we can't offline memory blocks which contain hugepages because a hugepage is considered as an unmovable page. But now with this patch series, a hugepage has become movable, so by using hugepage migration we can offline such memory blocks. What's different from other users of hugepage migration is that we need to decompose all the hugepages inside the target memory block into free buddy pages after hugepage migration, because otherwise free hugepages remaining in the memory block intervene the memory offlining. For this reason we introduce new functions dissolve_free_huge_page() and dissolve_free_huge_pages(). Other than that, what this patch does is straightforwardly to add hugepage migration code, that is, adding hugepage code to the functions which scan over pfn and collect hugepages to be migrated, and adding a hugepage allocation function to alloc_migrate_target(). As for larger hugepages (1GB for x86_64), it's not easy to do hotremove over them because it's larger than memory block. So we now simply leave it to fail as it is. [yongjun_wei@trendmicro.com.cn: remove duplicated include] Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Cc: Hillf Danton Cc: Wanpeng Li Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Wei Yongjun Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 69 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d37b3b95c439..fb4293b93fd0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -522,9 +523,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (list_empty(&h->hugepage_freelists[nid])) + list_for_each_entry(page, &h->hugepage_freelists[nid], lru) + if (!is_migrate_isolate_page(page)) + break; + /* + * if 'non-isolated free hugepage' not found on the list, + * the allocation fails. + */ + if (&h->hugepage_freelists[nid] == &page->lru) return NULL; - page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); h->free_huge_pages--; @@ -878,6 +885,44 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, return ret; } +/* + * Dissolve a given free hugepage into free buddy pages. This function does + * nothing for in-use (including surplus) hugepages. + */ +static void dissolve_free_huge_page(struct page *page) +{ + spin_lock(&hugetlb_lock); + if (PageHuge(page) && !page_count(page)) { + struct hstate *h = page_hstate(page); + int nid = page_to_nid(page); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + update_and_free_page(h, page); + } + spin_unlock(&hugetlb_lock); +} + +/* + * Dissolve free hugepages in a given pfn range. Used by memory hotplug to + * make specified memory blocks removable from the system. + * Note that start_pfn should aligned with (minimum) hugepage size. + */ +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; + + /* 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) + dissolve_free_huge_page(pfn_to_page(pfn)); +} + static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) { struct page *page; @@ -3457,3 +3502,25 @@ void putback_active_hugepage(struct page *page) spin_unlock(&hugetlb_lock); put_page(page); } + +bool is_hugepage_active(struct page *page) +{ + VM_BUG_ON(!PageHuge(page)); + /* + * This function can be called for a tail page because the caller, + * scan_movable_pages, scans through a given pfn-range which typically + * covers one memory block. In systems using gigantic hugepage (1GB + * for x86_64,) a hugepage is larger than a memory block, and we don't + * support migrating such large hugepages for now, so return false + * when called for tail pages. + */ + if (PageTail(page)) + return false; + /* + * Refcount of a hwpoisoned hugepages is 1, but they are not active, + * so we should return false for them. + */ + if (unlikely(PageHWPoison(page))) + return false; + return page_count(page) > 0; +} -- cgit v1.2.3 From 86cdb465cf3a9d81058b517af05074157fa9dcdd Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Sep 2013 14:22:13 -0700 Subject: mm: prepare to remove /proc/sys/vm/hugepages_treat_as_movable Now hugepage migration is enabled, although restricted on pmd-based hugepages for now (due to lack of testing.) So we should allocate migratable hugepages from ZONE_MOVABLE if possible. This patch makes GFP flags in hugepage allocation dependent on migration support, not only the value of hugepages_treat_as_movable. It provides no change on the behavior for architectures which do not support hugepage migration, Signed-off-by: Naoya Horiguchi Acked-by: Andi Kleen Reviewed-by: Wanpeng Li Cc: Hillf Danton Cc: Mel Gorman Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Michal Hocko Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fb4293b93fd0..b49579c7f2a5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -34,7 +34,6 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; @@ -539,6 +538,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) return page; } +/* Movability of hugepages depends on migration support. */ +static inline gfp_t htlb_alloc_mask(struct hstate *h) +{ + if (hugepages_treat_as_movable || hugepage_migration_support(h)) + return GFP_HIGHUSER_MOVABLE; + else + return GFP_HIGHUSER; +} + static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, @@ -568,11 +576,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, retry_cpuset: cpuset_mems_cookie = get_mems_allowed(); zonelist = huge_zonelist(vma, address, - htlb_alloc_mask, &mpol, &nodemask); + htlb_alloc_mask(h), &mpol, &nodemask); for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { - if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { + if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) { page = dequeue_huge_page_node(h, zone_to_nid(zone)); if (page) { if (avoid_reserve) @@ -738,7 +746,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) return NULL; page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { @@ -965,12 +973,12 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) spin_unlock(&hugetlb_lock); if (nid == NUMA_NO_NODE) - page = alloc_pages(htlb_alloc_mask|__GFP_COMP| + page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); else page = alloc_pages_exact_node(nid, - htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page && arch_prepare_hugepage(page)) { @@ -2117,18 +2125,6 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, } #endif /* CONFIG_NUMA */ -int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) -{ - proc_dointvec(table, write, buffer, length, ppos); - if (hugepages_treat_as_movable) - htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; - else - htlb_alloc_mask = GFP_HIGHUSER; - return 0; -} - int hugetlb_overcommit_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) -- cgit v1.2.3