From 9a76db099709388ae4126c4f441358b97c6ba20c Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:15 -0800 Subject: hugetlb: rework hstate_next_node_* functions Modify the hstate_next_node* functions to allow them to be called to obtain the "start_nid". Then, whereas prior to this patch we unconditionally called hstate_next_node_to_{alloc|free}(), whether or not we successfully allocated/freed a huge page on the node, now we only call these functions on failure to alloc/free to advance to next allowed node. Factor out the next_node_allowed() function to handle wrap at end of node_online_map. In this version, the allowed nodes include all of the online nodes. Signed-off-by: Lee Schermerhorn Reviewed-by: Mel Gorman Acked-by: David Rientjes Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: Andi Kleen Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 70 ++++++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 45 insertions(+), 25 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5d7601b0287..bffcf774f60 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -621,6 +621,20 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) return page; } +/* + * common helper function for hstate_next_node_to_{alloc|free}. + * return next node in node_online_map, wrapping at end. + */ +static int next_node_allowed(int nid) +{ + nid = next_node(nid, node_online_map); + if (nid == MAX_NUMNODES) + nid = first_node(node_online_map); + VM_BUG_ON(nid >= MAX_NUMNODES); + + return nid; +} + /* * Use a helper variable to find the next node and then * copy it back to next_nid_to_alloc afterwards: @@ -634,12 +648,12 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) */ static int hstate_next_node_to_alloc(struct hstate *h) { - int next_nid; - next_nid = next_node(h->next_nid_to_alloc, node_online_map); - if (next_nid == MAX_NUMNODES) - next_nid = first_node(node_online_map); + int nid, next_nid; + + nid = h->next_nid_to_alloc; + next_nid = next_node_allowed(nid); h->next_nid_to_alloc = next_nid; - return next_nid; + return nid; } static int alloc_fresh_huge_page(struct hstate *h) @@ -649,15 +663,17 @@ static int alloc_fresh_huge_page(struct hstate *h) int next_nid; int ret = 0; - start_nid = h->next_nid_to_alloc; + start_nid = hstate_next_node_to_alloc(h); next_nid = start_nid; do { page = alloc_fresh_huge_page_node(h, next_nid); - if (page) + if (page) { ret = 1; + break; + } next_nid = hstate_next_node_to_alloc(h); - } while (!page && next_nid != start_nid); + } while (next_nid != start_nid); if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -668,17 +684,19 @@ static int alloc_fresh_huge_page(struct hstate *h) } /* - * helper for free_pool_huge_page() - find next node - * from which to free a huge page + * helper for free_pool_huge_page() - return the next 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) { - int next_nid; - next_nid = next_node(h->next_nid_to_free, node_online_map); - if (next_nid == MAX_NUMNODES) - next_nid = first_node(node_online_map); + int nid, next_nid; + + nid = h->next_nid_to_free; + next_nid = next_node_allowed(nid); h->next_nid_to_free = next_nid; - return next_nid; + return nid; } /* @@ -693,7 +711,7 @@ static int free_pool_huge_page(struct hstate *h, bool acct_surplus) int next_nid; int ret = 0; - start_nid = h->next_nid_to_free; + start_nid = hstate_next_node_to_free(h); next_nid = start_nid; do { @@ -715,9 +733,10 @@ static int free_pool_huge_page(struct hstate *h, bool acct_surplus) } update_and_free_page(h, page); ret = 1; + break; } next_nid = hstate_next_node_to_free(h); - } while (!ret && next_nid != start_nid); + } while (next_nid != start_nid); return ret; } @@ -1028,10 +1047,9 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) void *addr; addr = __alloc_bootmem_node_nopanic( - NODE_DATA(h->next_nid_to_alloc), + NODE_DATA(hstate_next_node_to_alloc(h)), huge_page_size(h), huge_page_size(h), 0); - hstate_next_node_to_alloc(h); if (addr) { /* * Use the beginning of the huge page to store the @@ -1167,29 +1185,31 @@ static int adjust_pool_surplus(struct hstate *h, int delta) VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) - start_nid = h->next_nid_to_alloc; + start_nid = hstate_next_node_to_alloc(h); else - start_nid = h->next_nid_to_free; + start_nid = hstate_next_node_to_free(h); next_nid = start_nid; do { int nid = next_nid; if (delta < 0) { - next_nid = hstate_next_node_to_alloc(h); /* * To shrink on this node, there must be a surplus page */ - if (!h->surplus_huge_pages_node[nid]) + if (!h->surplus_huge_pages_node[nid]) { + next_nid = hstate_next_node_to_alloc(h); continue; + } } if (delta > 0) { - next_nid = hstate_next_node_to_free(h); /* * Surplus cannot exceed the total number of pages */ if (h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) + h->nr_huge_pages_node[nid]) { + next_nid = hstate_next_node_to_free(h); continue; + } } h->surplus_huge_pages += delta; -- cgit v1.2.3-70-g09d2 From 6ae11b278bca1cd41651bae49a8c69de2f6a6262 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:16 -0800 Subject: hugetlb: add nodemask arg to huge page alloc, free and surplus adjust functions In preparation for constraining huge page allocation and freeing by the controlling task's numa mempolicy, add a "nodes_allowed" nodemask pointer to the allocate, free and surplus adjustment functions. For now, pass NULL to indicate default behavior--i.e., use node_online_map. A subsqeuent patch will derive a non-default mask from the controlling task's numa mempolicy. Note that this method of updating the global hstate nr_hugepages under the constraint of a nodemask simplifies keeping the global state consistent--especially the number of persistent and surplus pages relative to reservations and overcommit limits. There are undoubtedly other ways to do this, but this works for both interfaces: mempolicy and per node attributes. [rientjes@google.com: fix HIGHMEM compile error] Signed-off-by: Lee Schermerhorn Reviewed-by: Mel Gorman Acked-by: David Rientjes Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: Andi Kleen Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 125 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 72 insertions(+), 53 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bffcf774f60..324d1abae87 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -622,48 +622,56 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) } /* - * common helper function for hstate_next_node_to_{alloc|free}. - * return next node in node_online_map, wrapping at end. + * 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 next_node_allowed(int nid) +static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { - nid = next_node(nid, node_online_map); + nid = next_node(nid, *nodes_allowed); if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); + 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; +} + /* - * Use a helper variable to find the next node and then - * copy it back to next_nid_to_alloc afterwards: - * otherwise there's a window in which a racer might - * pass invalid nid MAX_NUMNODES to alloc_pages_exact_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. + * 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) +static int hstate_next_node_to_alloc(struct hstate *h, + nodemask_t *nodes_allowed) { - int nid, next_nid; + 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); - nid = h->next_nid_to_alloc; - next_nid = next_node_allowed(nid); - h->next_nid_to_alloc = next_nid; return nid; } -static int alloc_fresh_huge_page(struct hstate *h) +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); + start_nid = hstate_next_node_to_alloc(h, nodes_allowed); next_nid = start_nid; do { @@ -672,7 +680,7 @@ static int alloc_fresh_huge_page(struct hstate *h) ret = 1; break; } - next_nid = hstate_next_node_to_alloc(h); + next_nid = hstate_next_node_to_alloc(h, nodes_allowed); } while (next_nid != start_nid); if (ret) @@ -684,18 +692,20 @@ static int alloc_fresh_huge_page(struct hstate *h) } /* - * helper for free_pool_huge_page() - return the next 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. + * 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) +static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { - int nid, next_nid; + 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); - nid = h->next_nid_to_free; - next_nid = next_node_allowed(nid); - h->next_nid_to_free = next_nid; return nid; } @@ -705,13 +715,14 @@ static int hstate_next_node_to_free(struct hstate *h) * balanced over allowed nodes. * Called with hugetlb_lock locked. */ -static int free_pool_huge_page(struct hstate *h, bool acct_surplus) +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); + start_nid = hstate_next_node_to_free(h, nodes_allowed); next_nid = start_nid; do { @@ -735,7 +746,7 @@ static int free_pool_huge_page(struct hstate *h, bool acct_surplus) ret = 1; break; } - next_nid = hstate_next_node_to_free(h); + next_nid = hstate_next_node_to_free(h, nodes_allowed); } while (next_nid != start_nid); return ret; @@ -937,7 +948,7 @@ static void return_unused_surplus_pages(struct hstate *h, * on-line nodes for us and will handle the hstate accounting. */ while (nr_pages--) { - if (!free_pool_huge_page(h, 1)) + if (!free_pool_huge_page(h, &node_online_map, 1)) break; } } @@ -1047,7 +1058,8 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) void *addr; addr = __alloc_bootmem_node_nopanic( - NODE_DATA(hstate_next_node_to_alloc(h)), + NODE_DATA(hstate_next_node_to_alloc(h, + &node_online_map)), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -1102,7 +1114,7 @@ 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_online_map)) break; } h->max_huge_pages = i; @@ -1144,14 +1156,15 @@ static void __init report_hugepages(void) } #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) { @@ -1167,7 +1180,8 @@ 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 @@ -1177,7 +1191,8 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count) * 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 adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, + int delta) { int start_nid, next_nid; int ret = 0; @@ -1185,9 +1200,9 @@ static int adjust_pool_surplus(struct hstate *h, int delta) VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) - start_nid = hstate_next_node_to_alloc(h); + start_nid = hstate_next_node_to_alloc(h, nodes_allowed); else - start_nid = hstate_next_node_to_free(h); + start_nid = hstate_next_node_to_free(h, nodes_allowed); next_nid = start_nid; do { @@ -1197,7 +1212,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta) * 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); + next_nid = hstate_next_node_to_alloc(h, + nodes_allowed); continue; } } @@ -1207,7 +1223,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta) */ if (h->surplus_huge_pages_node[nid] >= h->nr_huge_pages_node[nid]) { - next_nid = hstate_next_node_to_free(h); + next_nid = hstate_next_node_to_free(h, + nodes_allowed); continue; } } @@ -1222,7 +1239,8 @@ static int adjust_pool_surplus(struct hstate *h, int delta) } #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; @@ -1242,7 +1260,7 @@ 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; } @@ -1253,7 +1271,7 @@ 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; @@ -1277,13 +1295,13 @@ 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)) { - if (!free_pool_huge_page(h, 0)) + if (!free_pool_huge_page(h, nodes_allowed, 0)) break; } while (count < persistent_huge_pages(h)) { - if (!adjust_pool_surplus(h, 1)) + if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: @@ -1329,7 +1347,7 @@ static ssize_t nr_hugepages_store(struct kobject *kobj, if (err) return 0; - h->max_huge_pages = set_max_huge_pages(h, input); + h->max_huge_pages = set_max_huge_pages(h, input, &node_online_map); return count; } @@ -1571,7 +1589,8 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) - h->max_huge_pages = set_max_huge_pages(h, tmp); + h->max_huge_pages = set_max_huge_pages(h, tmp, + &node_online_map); return 0; } -- cgit v1.2.3-70-g09d2 From 06808b0827e1cd14eedc96bac2655d5b37ac246c Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:21 -0800 Subject: hugetlb: derive huge pages nodes allowed from task mempolicy This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes Signed-off-by: Lee Schermerhorn Acked-by: Mel Gorman Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 +++ include/linux/mempolicy.h | 3 ++ kernel/sysctl.c | 15 +++++++- mm/hugetlb.c | 97 ++++++++++++++++++++++++++++++++++++++++------- mm/mempolicy.c | 47 +++++++++++++++++++++++ 5 files changed, 153 insertions(+), 15 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 41a59afc70f..78b4bc64c00 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -23,6 +23,12 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); + +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); +#endif + int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 085c903fe0f..1cc966cd3e5 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -201,6 +201,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p); extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); +extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -328,6 +329,8 @@ static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, return node_zonelist(0, gfp_flags); } +static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } + static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 554ac4894f0..60fc9313109 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1051,7 +1051,7 @@ static struct ctl_table vm_table[] = { .extra2 = &one_hundred, }, #ifdef CONFIG_HUGETLB_PAGE - { + { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), @@ -1059,7 +1059,18 @@ static struct ctl_table vm_table[] = { .proc_handler = hugetlb_sysctl_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, - }, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, + }, +#endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 324d1abae87..1125d818ea0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1330,29 +1330,71 @@ static struct hstate *kobj_to_hstate(struct kobject *kobj) return NULL; } -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); } -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; + unsigned long count; struct hstate *h = kobj_to_hstate(kobj); + NODEMASK_ALLOC(nodemask_t, nodes_allowed); - 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, &node_online_map); + if (!(obey_mempolicy && init_nodemask_of_mempolicy(nodes_allowed))) { + NODEMASK_FREE(nodes_allowed); + nodes_allowed = &node_online_map; + } + h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed); - return count; + if (nodes_allowed != &node_online_map) + 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) { @@ -1408,6 +1450,9 @@ 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, }; @@ -1574,9 +1619,9 @@ static unsigned int cpuset_mems_nr(unsigned int *array) } #ifdef CONFIG_SYSCTL -int hugetlb_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) +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; @@ -1588,13 +1633,39 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, buffer, length, ppos); - if (write) - h->max_huge_pages = set_max_huge_pages(h, tmp, - &node_online_map); + if (write) { + NODEMASK_ALLOC(nodemask_t, nodes_allowed); + 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, void __user *buffer, size_t *length, loff_t *ppos) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0f89eabbaf3..f11fdad0620 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1568,6 +1568,53 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, } return zl; } + +/* + * init_nodemask_of_mempolicy + * + * If the current task's mempolicy is "default" [NULL], return 'false' + * to indicate default policy. Otherwise, extract the policy nodemask + * for 'bind' or 'interleave' policy into the argument nodemask, or + * initialize the argument nodemask to contain the single node for + * 'preferred' or 'local' policy and return 'true' to indicate presence + * of non-default mempolicy. + * + * We don't bother with reference counting the mempolicy [mpol_get/put] + * because the current task is examining it's own mempolicy and a task's + * mempolicy is only ever changed by the task itself. + * + * N.B., it is the caller's responsibility to free a returned nodemask. + */ +bool init_nodemask_of_mempolicy(nodemask_t *mask) +{ + struct mempolicy *mempolicy; + int nid; + + if (!(mask && current->mempolicy)) + return false; + + mempolicy = current->mempolicy; + switch (mempolicy->mode) { + case MPOL_PREFERRED: + if (mempolicy->flags & MPOL_F_LOCAL) + nid = numa_node_id(); + else + nid = mempolicy->v.preferred_node; + init_nodemask_of_node(mask, nid); + break; + + case MPOL_BIND: + /* Fall through */ + case MPOL_INTERLEAVE: + *mask = mempolicy->v.nodes; + break; + + default: + BUG(); + } + + return true; +} #endif /* Allocate a page in interleaved policy. -- cgit v1.2.3-70-g09d2 From 9a30523066cde73c1442b76224bb540de9f9b0b0 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:25 -0800 Subject: hugetlb: add per node hstate attributes Add the per huge page size control/query attributes to the per node sysdevs: /sys/devices/system/node/node/hugepages/hugepages-/ nr_hugepages - r/w free_huge_pages - r/o surplus_huge_pages - r/o The patch attempts to re-use/share as much of the existing global hstate attribute initialization and handling, and the "nodes_allowed" constraint processing as possible. Calling set_max_huge_pages() with no node indicates a change to global hstate parameters. In this case, any non-default task mempolicy will be used to generate the nodes_allowed mask. A valid node id indicates an update to that node's hstate parameters, and the count argument specifies the target count for the specified node. From this info, we compute the target global count for the hstate and construct a nodes_allowed node mask contain only the specified node. Setting the node specific nr_hugepages via the per node attribute effectively ignores any task mempolicy or cpuset constraints. With this patch: (me):ls /sys/devices/system/node/node0/hugepages/hugepages-2048kB ./ ../ free_hugepages nr_hugepages surplus_hugepages Starting from: Node 0 HugePages_Total: 0 Node 0 HugePages_Free: 0 Node 0 HugePages_Surp: 0 Node 1 HugePages_Total: 0 Node 1 HugePages_Free: 0 Node 1 HugePages_Surp: 0 Node 2 HugePages_Total: 0 Node 2 HugePages_Free: 0 Node 2 HugePages_Surp: 0 Node 3 HugePages_Total: 0 Node 3 HugePages_Free: 0 Node 3 HugePages_Surp: 0 vm.nr_hugepages = 0 Allocate 16 persistent huge pages on node 2: (me):echo 16 >/sys/devices/system/node/node2/hugepages/hugepages-2048kB/nr_hugepages [Note that this is equivalent to: numactl -m 2 hugeadmin --pool-pages-min 2M:+16 ] Yields: Node 0 HugePages_Total: 0 Node 0 HugePages_Free: 0 Node 0 HugePages_Surp: 0 Node 1 HugePages_Total: 0 Node 1 HugePages_Free: 0 Node 1 HugePages_Surp: 0 Node 2 HugePages_Total: 16 Node 2 HugePages_Free: 16 Node 2 HugePages_Surp: 0 Node 3 HugePages_Total: 0 Node 3 HugePages_Free: 0 Node 3 HugePages_Surp: 0 vm.nr_hugepages = 16 Global controls work as expected--reduce pool to 8 persistent huge pages: (me):echo 8 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages Node 0 HugePages_Total: 0 Node 0 HugePages_Free: 0 Node 0 HugePages_Surp: 0 Node 1 HugePages_Total: 0 Node 1 HugePages_Free: 0 Node 1 HugePages_Surp: 0 Node 2 HugePages_Total: 8 Node 2 HugePages_Free: 8 Node 2 HugePages_Surp: 0 Node 3 HugePages_Total: 0 Node 3 HugePages_Free: 0 Node 3 HugePages_Surp: 0 Signed-off-by: Lee Schermerhorn Acked-by: Mel Gorman Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: David Rientjes Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 39 ++++++++ include/linux/node.h | 11 +++ mm/hugetlb.c | 274 ++++++++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 298 insertions(+), 26 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 1fe5536d404..f502711d28d 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -173,6 +173,43 @@ static ssize_t node_read_distance(struct sys_device * dev, } static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL); +#ifdef CONFIG_HUGETLBFS +/* + * hugetlbfs per node attributes registration interface: + * When/if hugetlb[fs] subsystem initializes [sometime after this module], + * it will register its per node attributes for all nodes online at that + * time. It will also call register_hugetlbfs_with_node(), below, to + * register its attribute registration functions with this node driver. + * Once these hooks have been initialized, the node driver will call into + * the hugetlb module to [un]register attributes for hot-plugged nodes. + */ +static node_registration_func_t __hugetlb_register_node; +static node_registration_func_t __hugetlb_unregister_node; + +static inline void hugetlb_register_node(struct node *node) +{ + if (__hugetlb_register_node) + __hugetlb_register_node(node); +} + +static inline void hugetlb_unregister_node(struct node *node) +{ + if (__hugetlb_unregister_node) + __hugetlb_unregister_node(node); +} + +void register_hugetlbfs_with_node(node_registration_func_t doregister, + node_registration_func_t unregister) +{ + __hugetlb_register_node = doregister; + __hugetlb_unregister_node = unregister; +} +#else +static inline void hugetlb_register_node(struct node *node) {} + +static inline void hugetlb_unregister_node(struct node *node) {} +#endif + /* * register_node - Setup a sysfs device for a node. @@ -196,6 +233,7 @@ int register_node(struct node *node, int num, struct node *parent) sysdev_create_file(&node->sysdev, &attr_distance); scan_unevictable_register_node(node); + hugetlb_register_node(node); } return error; } @@ -216,6 +254,7 @@ void unregister_node(struct node *node) sysdev_remove_file(&node->sysdev, &attr_distance); scan_unevictable_unregister_node(node); + hugetlb_unregister_node(node); sysdev_unregister(&node->sysdev); } diff --git a/include/linux/node.h b/include/linux/node.h index 681a697b9a8..dae1521e1f0 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -28,6 +28,7 @@ struct node { struct memory_block; extern struct node node_devices[]; +typedef void (*node_registration_func_t)(struct node *); extern int register_node(struct node *, int, struct node *); extern void unregister_node(struct node *node); @@ -39,6 +40,11 @@ extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, int nid); extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk); + +#ifdef CONFIG_HUGETLBFS +extern void register_hugetlbfs_with_node(node_registration_func_t doregister, + node_registration_func_t unregister); +#endif #else static inline int register_one_node(int nid) { @@ -65,6 +71,11 @@ static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) { return 0; } + +static inline void register_hugetlbfs_with_node(node_registration_func_t reg, + node_registration_func_t unreg) +{ +} #endif #define to_node(sys_device) container_of(sys_device, struct node, sysdev) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1125d818ea0..544f7bcb615 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -24,6 +24,7 @@ #include #include +#include #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; @@ -1320,39 +1321,71 @@ 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_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_common(bool obey_mempolicy, struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int err; + int nid; unsigned long count; - struct hstate *h = kobj_to_hstate(kobj); + struct hstate *h; NODEMASK_ALLOC(nodemask_t, nodes_allowed); err = strict_strtoul(buf, 10, &count); if (err) return 0; - if (!(obey_mempolicy && init_nodemask_of_mempolicy(nodes_allowed))) { - NODEMASK_FREE(nodes_allowed); - nodes_allowed = &node_online_map; - } + 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); if (nodes_allowed != &node_online_map) @@ -1398,7 +1431,7 @@ HSTATE_ATTR(nr_hugepages_mempolicy); 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, @@ -1406,7 +1439,7 @@ 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) @@ -1423,15 +1456,24 @@ 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); @@ -1439,8 +1481,17 @@ 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); @@ -1460,19 +1511,21 @@ static struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; -static int __init hugetlb_sysfs_add_hstate(struct hstate *h) +static int __init 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; } @@ -1487,17 +1540,184 @@ 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; + + 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. All on-line nodes should have registered their + * associated sysdev by the time the hugetlb module initializes. + */ +static void hugetlb_register_all_nodes(void) +{ + int nid; + + for (nid = 0; nid < nr_node_ids; nid++) { + 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]); } @@ -1532,6 +1752,8 @@ static int __init hugetlb_init(void) hugetlb_sysfs_init(); + hugetlb_register_all_nodes(); + return 0; } module_init(hugetlb_init); -- cgit v1.2.3-70-g09d2 From 9b5e5d0fdc91b73bba8cf5e0fbe3521a953e4e4d Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:32 -0800 Subject: hugetlb: use only nodes with memory for huge pages Register per node hstate sysfs attributes only for nodes with memory. Global replacement of 'all online nodes" with "all nodes with memory" in mm/hugetlb.c. Suggested by David Rientjes. A subsequent patch will handle adding/removing of per node hstate sysfs attributes when nodes transition to/from memoryless state via memory hotplug. NOTE: this patch has not been tested with memoryless nodes. Signed-off-by: Lee Schermerhorn Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: Randy Dunlap Cc: Nishanth Aravamudan Acked-by: David Rientjes Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/hugetlbpage.txt | 12 ++++++------ mm/hugetlb.c | 35 ++++++++++++++++++----------------- 2 files changed, 24 insertions(+), 23 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index 01c3108d2e3..6a8e4667ab3 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -90,11 +90,11 @@ huge page pool to 20, allocating or freeing huge pages, as required. On a NUMA platform, the kernel will attempt to distribute the huge page pool over all the set of allowed nodes specified by the NUMA memory policy of the task that modifies nr_hugepages. The default for the allowed nodes--when the -task has default memory policy--is all on-line nodes. Allowed nodes with -insufficient available, contiguous memory for a huge page will be silently -skipped when allocating persistent huge pages. See the discussion below of -the interaction of task memory policy, cpusets and per node attributes with -the allocation and freeing of persistent huge pages. +task has default memory policy--is all on-line nodes with memory. Allowed +nodes with insufficient available, contiguous memory for a huge page will be +silently skipped when allocating persistent huge pages. See the discussion +below of the interaction of task memory policy, cpusets and per node attributes +with the allocation and freeing of persistent huge pages. The success or failure of huge page allocation depends on the amount of physically contiguous memory that is present in system at the time of the @@ -226,7 +226,7 @@ resulting effect on persistent huge page allocation is as follows: without first moving to a cpuset that contains all of the desired nodes. 5) Boot-time huge page allocation attempts to distribute the requested number - of huge pages over all on-lines nodes. + of huge pages over all on-lines nodes with memory. Per Node Hugepages Attributes diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 544f7bcb615..b4a263512cb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -942,14 +942,14 @@ static void return_unused_surplus_pages(struct hstate *h, /* * 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. - * free_pool_huge_page() will balance the the frees across the - * on-line nodes for us and will handle the hstate accounting. + * 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_online_map, 1)) + if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1)) break; } } @@ -1053,14 +1053,14 @@ 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_online_map); + int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]); while (nr_nodes) { void *addr; addr = __alloc_bootmem_node_nopanic( NODE_DATA(hstate_next_node_to_alloc(h, - &node_online_map)), + &node_states[N_HIGH_MEMORY])), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -1115,7 +1115,8 @@ 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, &node_online_map)) + } else if (!alloc_fresh_huge_page(h, + &node_states[N_HIGH_MEMORY])) break; } h->max_huge_pages = i; @@ -1388,7 +1389,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed); - if (nodes_allowed != &node_online_map) + if (nodes_allowed != &node_states[N_HIGH_MEMORY]) NODEMASK_FREE(nodes_allowed); return len; @@ -1610,7 +1611,7 @@ void hugetlb_unregister_node(struct node *node) struct node_hstate *nhs = &node_hstates[node->sysdev.id]; if (!nhs->hugepages_kobj) - return; + return; /* no hstate attributes */ for_each_hstate(h) if (nhs->hstate_kobjs[h - hstates]) { @@ -1675,15 +1676,15 @@ void hugetlb_register_node(struct node *node) } /* - * hugetlb init time: register hstate attributes for all registered - * node sysdevs. All on-line nodes should have registered their - * associated sysdev by the time the hugetlb module initializes. + * 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 (nid = 0; nid < nr_node_ids; nid++) { + for_each_node_state(nid, N_HIGH_MEMORY) { struct node *node = &node_devices[nid]; if (node->sysdev.id == nid) hugetlb_register_node(node); @@ -1777,8 +1778,8 @@ 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->next_nid_to_alloc = first_node(node_online_map); - h->next_nid_to_free = 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); -- cgit v1.2.3-70-g09d2 From bad44b5be84cf3bb1ff900bec02ee61e1993328c Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 14 Dec 2009 17:58:38 -0800 Subject: mm: add gfp flags for NODEMASK_ALLOC slab allocations Objects passed to NODEMASK_ALLOC() are relatively small in size and are backed by slab caches that are not of large order, traditionally never greater than PAGE_ALLOC_COSTLY_ORDER. Thus, using GFP_KERNEL for these allocations on large machines when CONFIG_NODES_SHIFT > 8 will cause the page allocator to loop endlessly in the allocation attempt, each time invoking both direct reclaim or the oom killer. This is of particular interest when using NODEMASK_ALLOC() from a mempolicy context (either directly in mm/mempolicy.c or the mempolicy constrained hugetlb allocations) since the oom killer always kills current when allocations are constrained by mempolicies. So for all present use cases in the kernel, current would end up being oom killed when direct reclaim fails. That would allow the NODEMASK_ALLOC() to succeed but current would have sacrificed itself upon returning. This patch adds gfp flags to NODEMASK_ALLOC() to pass to kmalloc() on CONFIG_NODES_SHIFT > 8; this parameter is a nop on other configurations. All current use cases either directly from hugetlb code or indirectly via NODEMASK_SCRATCH() union __GFP_NORETRY to avoid direct reclaim and the oom killer when the slab allocator needs to allocate additional pages. The side-effect of this change is that all current use cases of either NODEMASK_ALLOC() or NODEMASK_SCRATCH() need appropriate -ENOMEM handling when the allocation fails (never for CONFIG_NODES_SHIFT <= 8). All current use cases were audited and do have appropriate error handling at this time. Signed-off-by: David Rientjes Acked-by: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Mel Gorman Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: Andi Kleen Cc: David Rientjes Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 21 ++++++++++++--------- mm/hugetlb.c | 5 +++-- 2 files changed, 15 insertions(+), 11 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index cbd521a0312..454997cccbd 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -485,15 +485,17 @@ static inline int num_node_state(enum node_states state) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* - * For nodemask scrach area.(See CPUMASK_ALLOC() in cpumask.h) - * NODEMASK_ALLOC(x, m) allocates an object of type 'x' with the name 'm'. + * For nodemask scrach area. + * NODEMASK_ALLOC(type, name) allocates an object with a specified type and + * name. */ -#if NODES_SHIFT > 8 /* nodemask_t > 64 bytes */ -#define NODEMASK_ALLOC(x, m) x *m = kmalloc(sizeof(*m), GFP_KERNEL) -#define NODEMASK_FREE(m) kfree(m) +#if NODES_SHIFT > 8 /* nodemask_t > 256 bytes */ +#define NODEMASK_ALLOC(type, name, gfp_flags) \ + type *name = kmalloc(sizeof(*name), gfp_flags) +#define NODEMASK_FREE(m) kfree(m) #else -#define NODEMASK_ALLOC(x, m) x _m, *m = &_m -#define NODEMASK_FREE(m) do {} while (0) +#define NODEMASK_ALLOC(type, name, gfp_flags) type _name, *name = &_name +#define NODEMASK_FREE(m) do {} while (0) #endif /* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ @@ -502,8 +504,9 @@ struct nodemask_scratch { nodemask_t mask2; }; -#define NODEMASK_SCRATCH(x) \ - NODEMASK_ALLOC(struct nodemask_scratch, x) +#define NODEMASK_SCRATCH(x) \ + NODEMASK_ALLOC(struct nodemask_scratch, x, \ + GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b4a263512cb..450493d2557 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1361,7 +1361,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, int nid; unsigned long count; struct hstate *h; - NODEMASK_ALLOC(nodemask_t, nodes_allowed); + NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); err = strict_strtoul(buf, 10, &count); if (err) @@ -1857,7 +1857,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) { - NODEMASK_ALLOC(nodemask_t, nodes_allowed); + NODEMASK_ALLOC(nodemask_t, nodes_allowed, + GFP_KERNEL | __GFP_NORETRY); if (!(obey_mempolicy && init_nodemask_of_mempolicy(nodes_allowed))) { NODEMASK_FREE(nodes_allowed); -- cgit v1.2.3-70-g09d2 From b76c8cfbff94263fdf2f408e94b78b049c24a9dc Mon Sep 17 00:00:00 2001 From: Larry Woodman Date: Mon, 14 Dec 2009 17:59:37 -0800 Subject: hugetlb: prevent deadlock in __unmap_hugepage_range() when alloc_huge_page() fails hugetlb_fault() takes the mm->page_table_lock spinlock then calls hugetlb_cow(). If the alloc_huge_page() in hugetlb_cow() fails due to an insufficient huge page pool it calls unmap_ref_private() with the mm->page_table_lock held. unmap_ref_private() then calls unmap_hugepage_range() which tries to acquire the mm->page_table_lock. [] print_circular_bug_tail+0x80/0x9f [] ? check_noncircular+0xb0/0xe8 [] __lock_acquire+0x956/0xc0e [] lock_acquire+0xee/0x12e [] ? unmap_hugepage_range+0x3e/0x84 [] ? unmap_hugepage_range+0x3e/0x84 [] _spin_lock+0x40/0x89 [] ? unmap_hugepage_range+0x3e/0x84 [] ? alloc_huge_page+0x218/0x318 [] unmap_hugepage_range+0x3e/0x84 [] hugetlb_cow+0x1e2/0x3f4 [] ? hugetlb_fault+0x453/0x4f6 [] hugetlb_fault+0x480/0x4f6 [] follow_hugetlb_page+0x116/0x2d9 [] ? _spin_unlock_irq+0x3a/0x5c [] __get_user_pages+0x2a3/0x427 [] get_user_pages+0x3e/0x54 [] get_user_pages_fast+0x170/0x1b5 [] dio_get_page+0x64/0x14a [] __blockdev_direct_IO+0x4b7/0xb31 [] blkdev_direct_IO+0x58/0x6e [] ? blkdev_get_blocks+0x0/0xb8 [] generic_file_aio_read+0xdd/0x528 [] ? avc_has_perm+0x66/0x8c [] do_sync_read+0xf5/0x146 [] ? autoremove_wake_function+0x0/0x5a [] ? security_file_permission+0x24/0x3a [] vfs_read+0xb5/0x126 [] ? fget_light+0x5e/0xf8 [] sys_read+0x54/0x8c [] system_call_fastpath+0x16/0x1b This can be fixed by dropping the mm->page_table_lock around the call to unmap_ref_private() if alloc_huge_page() fails, its dropped right below in the normal path anyway. However, earlier in the that function, it's also possible to call into the page allocator with the same spinlock held. What this patch does is drop the spinlock before the page allocator is potentially entered. The check for page allocation failure can be made without the page_table_lock as well as the copy of the huge page. Even if the PTE changed while the spinlock was held, the consequence is that a huge page is copied unnecessarily. This resolves both the double taking of the lock and sleeping with the spinlock held. [mel@csn.ul.ie: Cover also the case where process can sleep with spinlock] Signed-off-by: Larry Woodman Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: Lee Schermerhorn Cc: Hugh Dickins Cc: David Gibson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 450493d2557..2ef66a2a148 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2293,6 +2293,9 @@ retry_avoidcopy: 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)) { @@ -2310,19 +2313,25 @@ 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 */ -- cgit v1.2.3-70-g09d2 From 4eb2b1dcd598f8489130405c81c60c289896d92a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 14 Dec 2009 17:59:53 -0800 Subject: hugetlb: acquire the i_mmap_lock before walking the prio_tree to unmap a page When the owner of a mapping fails COW because a child process is holding a reference, the children VMAs are walked and the page is unmapped. The i_mmap_lock is taken for the unmapping of the page but not the walking of the prio_tree. In theory, that tree could be changing if the lock is not held. This patch takes the i_mmap_lock properly for the duration of the prio_tree walk. [hugh.dickins@tiscali.co.uk: Spotted the problem in the first place] Signed-off-by: Mel Gorman Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2ef66a2a148..6df8065039e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2237,6 +2237,12 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, + (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) @@ -2250,10 +2256,11 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * 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, + __unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } + spin_unlock(&mapping->i_mmap_lock); return 1; } -- cgit v1.2.3-70-g09d2 From 536240f2bde98216feac87b4891d19a536b8884a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 14 Dec 2009 17:59:56 -0800 Subject: hugetlb: abort a hugepage pool resize if a signal is pending If a user asks for a hugepage pool resize but specified a large number, the machine can begin trashing. In response, they might hit ctrl-c but signals are ignored and the pool resize continues until it fails an allocation. This can take a considerable amount of time so this patch aborts a pool resize if a signal is pending. Suggested by Dave Hansen. Signed-off-by: Mel Gorman Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6df8065039e..65f38c21820 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1278,6 +1278,9 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, if (!ret) goto out; + /* Bail for signals. Probably ctrl-c from user */ + if (signal_pending(current)) + goto out; } /* -- cgit v1.2.3-70-g09d2 From 74dbdd239bb1348ad86d28b18574d9c1f28b62ca Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 8 Jan 2010 14:43:05 -0800 Subject: mm: hugetlb: fix clear_huge_page() sz is in bytes, MAX_ORDER_NR_PAGES is in pages. Signed-off-by: Andrea Arcangeli Acked-by: David Gibson Cc: Mel Gorman Cc: David Rientjes Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 65f38c21820..e91b81b6367 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -402,7 +402,7 @@ static void clear_huge_page(struct page *page, { int i; - if (unlikely(sz > MAX_ORDER_NR_PAGES)) { + if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, sz); return; } -- cgit v1.2.3-70-g09d2