From d3eb1570a9221b1b3ea8f6f460a9674c1bb761f1 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 22 Feb 2013 16:33:22 -0800 Subject: mempolicy: fix is_valid_nodemask() is_valid_nodemask() was introduced by commit 19770b32609b ("mm: filter based on a nodemask as well as a gfp_mask"). but it does not match its comments, because it does not check the zone which > policy_zone. Also in commit b377fd3982ad ("Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE"), this commits told us, if highest zone is ZONE_MOVABLE, we should also apply memory policies to it. so ZONE_MOVABLE should be valid zone for policies. is_valid_nodemask() need to be changed to match it. Fix: check all zones, even its zoneid > policy_zone. Use nodes_intersects() instead open code to check it. Reported-by: Wen Congyang Signed-off-by: Lai Jiangshan Signed-off-by: Tang Chen Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Jiang Liu Cc: Jianguo Wu Cc: Kamezawa Hiroyuki Cc: Lai Jiangshan Cc: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e2df1c1fb41f..6f7979c566d9 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -161,19 +161,7 @@ static const struct mempolicy_operations { /* Check that the nodemask contains at least one populated zone */ static int is_valid_nodemask(const nodemask_t *nodemask) { - int nd, k; - - for_each_node_mask(nd, *nodemask) { - struct zone *z; - - for (k = 0; k <= policy_zone; k++) { - z = &NODE_DATA(nd)->node_zones[k]; - if (z->present_pages > 0) - return 1; - } - } - - return 0; + return nodes_intersects(*nodemask, node_states[N_MEMORY]); } static inline int mpol_store_user_nodemask(const struct mempolicy *pol) @@ -1644,6 +1632,26 @@ struct mempolicy *get_vma_policy(struct task_struct *task, return pol; } +static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) +{ + enum zone_type dynamic_policy_zone = policy_zone; + + BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); + + /* + * if policy->v.nodes has movable memory only, + * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. + * + * policy->v.nodes is intersect with node_states[N_MEMORY]. + * so if the following test faile, it implies + * policy->v.nodes has movable memory only. + */ + if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + dynamic_policy_zone = ZONE_MOVABLE; + + return zone >= dynamic_policy_zone; +} + /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation @@ -1652,7 +1660,7 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && - gfp_zone(gfp) >= policy_zone && + apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; -- cgit v1.2.2 From 22b751c3d0376e86a377e3a0aa2ddbbe9d2eefc1 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 22 Feb 2013 16:34:59 -0800 Subject: mm: rename page struct field helpers The function names page_xchg_last_nid(), page_last_nid() and reset_page_last_nid() were judged to be inconsistent so rename them to a struct_field_op style pattern. As it looked jarring to have reset_page_mapcount() and page_nid_reset_last() beside each other in memmap_init_zone(), this patch also renames reset_page_mapcount() to page_mapcount_reset(). There are others like init_page_count() but as it is used throughout the arch code a rename would likely cause more conflicts than it is worth. [akpm@linux-foundation.org: fix zcache] Signed-off-by: Mel Gorman Suggested-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 6f7979c566d9..2ae78e255e08 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2316,7 +2316,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * it less likely we act on an unlikely task<->page * relation. */ - last_nid = page_xchg_last_nid(page, polnid); + last_nid = page_nid_xchg_last(page, polnid); if (last_nid != polnid) goto out; } -- cgit v1.2.2 From b79bc0a0c79e06cc87e17530e9c1c56c6f297e17 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 22 Feb 2013 16:35:13 -0800 Subject: ksm: enable KSM page migration Migration of KSM pages is now safe: remove the PageKsm restrictions from mempolicy.c and migrate.c. But keep PageKsm out of __unmap_and_move()'s anon_vma contortions, which are irrelevant to KSM: it looks as if that code was preventing hotremove migration of KSM pages, unless they happened to be in swapcache. There is some question as to whether enforcing a NUMA mempolicy migration ought to migrate KSM pages, mapped into entirely unrelated processes; but moving page_mapcount > 1 is only permitted with MPOL_MF_MOVE_ALL anyway, and it seems reasonable to assume that you wouldn't set MADV_MERGEABLE on any area where this is a worry. Signed-off-by: Hugh Dickins Cc: Rik van Riel Cc: Petr Holasek Cc: Andrea Arcangeli Cc: Izik Eidus Cc: Gerald Schaefer Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2ae78e255e08..d344c36db63f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -496,9 +496,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. - * And we cannot move PageKsm pages sensibly or safely yet. */ - if (PageReserved(page) || PageKsm(page)) + if (PageReserved(page)) continue; nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) -- cgit v1.2.2 From 9c620e2bc5aa4256c102ada34e6c76204ed5898b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 22 Feb 2013 16:35:14 -0800 Subject: mm: remove offlining arg to migrate_pages No functional change, but the only purpose of the offlining argument to migrate_pages() etc, was to ensure that __unmap_and_move() could migrate a KSM page for memory hotremove (which took ksm_thread_mutex) but not for other callers. Now all cases are safe, remove the arg. Signed-off-by: Hugh Dickins Cc: Rik van Riel Cc: Petr Holasek Cc: Andrea Arcangeli Cc: Izik Eidus Cc: Gerald Schaefer Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d344c36db63f..e2661d1c5c33 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1014,8 +1014,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, - false, MIGRATE_SYNC, - MR_SYSCALL); + MIGRATE_SYNC, MR_SYSCALL); if (err) putback_lru_pages(&pagelist); } @@ -1259,9 +1258,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, - false, MIGRATE_SYNC, - MR_MEMPOLICY_MBIND); + (unsigned long)vma, + MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_lru_pages(&pagelist); } -- cgit v1.2.2 From 00ef2d2f84babb9b209f0fc003bc490c6bf1e6ef Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 22 Feb 2013 16:35:36 -0800 Subject: mm: use NUMA_NO_NODE Make a sweep through mm/ and convert code that uses -1 directly to using the more appropriate NUMA_NO_NODE. Signed-off-by: David Rientjes Reviewed-by: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e2661d1c5c33..31d26637b658 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -26,7 +26,7 @@ * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. - * As a special case node -1 here means do the allocation + * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. @@ -127,7 +127,7 @@ static struct mempolicy *get_task_policy(struct task_struct *p) if (!pol) { node = numa_node_id(); - if (node != -1) + if (node != NUMA_NO_NODE) pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ @@ -258,7 +258,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", - mode, flags, nodes ? nodes_addr(*nodes)[0] : -1); + mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) @@ -1221,7 +1221,7 @@ static long do_mbind(unsigned long start, unsigned long len, pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, - nmask ? nodes_addr(*nmask)[0] : -1); + nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { @@ -2488,7 +2488,7 @@ int mpol_set_shared_policy(struct shared_policy *info, vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, - npol ? nodes_addr(npol->v.nodes)[0] : -1); + npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); -- cgit v1.2.2