diff options
Diffstat (limited to 'mm/mempolicy.c')
| -rw-r--r-- | mm/mempolicy.c | 2478 |
1 files changed, 1646 insertions, 832 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3c360112150..8f5330d74f4 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. @@ -63,9 +63,10 @@ grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. - could replace all the switch()es with a mempolicy_ops structure. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/highmem.h> @@ -74,10 +75,9 @@ #include <linux/sched.h> #include <linux/nodemask.h> #include <linux/cpuset.h> -#include <linux/gfp.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> @@ -86,17 +86,24 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> +#include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/ctype.h> +#include <linux/mm_inline.h> +#include <linux/mmu_notifier.h> +#include <linux/printk.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> +#include <linux/random.h> + +#include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ -#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2) /* Gather statistics */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; @@ -105,148 +112,378 @@ static struct kmem_cache *sn_cache; policied. */ enum zone_type policy_zone = 0; -struct mempolicy default_policy = { +/* + * run-time system-wide default policy => local allocation + */ +static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ - .policy = MPOL_DEFAULT, + .mode = MPOL_PREFERRED, + .flags = MPOL_F_LOCAL, }; -static void mpol_rebind_policy(struct mempolicy *pol, - const nodemask_t *newmask); +static struct mempolicy preferred_node_policy[MAX_NUMNODES]; -/* Do sanity checking on a policy */ -static int mpol_check_policy(int mode, nodemask_t *nodes) +static struct mempolicy *get_task_policy(struct task_struct *p) { - int was_empty, is_empty; + struct mempolicy *pol = p->mempolicy; - if (!nodes) - return 0; + if (!pol) { + int node = numa_node_id(); + if (node != NUMA_NO_NODE) { + pol = &preferred_node_policy[node]; + /* + * preferred_node_policy is not initialised early in + * boot + */ + if (!pol->mode) + pol = NULL; + } + } + + return pol; +} + +static const struct mempolicy_operations { + int (*create)(struct mempolicy *pol, const nodemask_t *nodes); /* - * "Contextualize" the in-coming nodemast for cpusets: - * Remember whether in-coming nodemask was empty, If not, - * restrict the nodes to the allowed nodes in the cpuset. - * This is guaranteed to be a subset of nodes with memory. + * If read-side task has no lock to protect task->mempolicy, write-side + * task will rebind the task->mempolicy by two step. The first step is + * setting all the newly nodes, and the second step is cleaning all the + * disallowed nodes. In this way, we can avoid finding no node to alloc + * page. + * If we have a lock to protect task->mempolicy in read-side, we do + * rebind directly. + * + * step: + * MPOL_REBIND_ONCE - do rebind work at once + * MPOL_REBIND_STEP1 - set all the newly nodes + * MPOL_REBIND_STEP2 - clean all the disallowed nodes */ - cpuset_update_task_memory_state(); - is_empty = was_empty = nodes_empty(*nodes); - if (!was_empty) { - nodes_and(*nodes, *nodes, cpuset_current_mems_allowed); - is_empty = nodes_empty(*nodes); /* after "contextualization" */ - } + void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes, + enum mpol_rebind_step step); +} mpol_ops[MPOL_MAX]; - switch (mode) { - case MPOL_DEFAULT: - /* - * require caller to specify an empty nodemask - * before "contextualization" - */ - if (!was_empty) - return -EINVAL; - break; - case MPOL_BIND: - case MPOL_INTERLEAVE: - /* - * require at least 1 valid node after "contextualization" - */ - if (is_empty) - return -EINVAL; - break; - case MPOL_PREFERRED: - /* - * Did caller specify invalid nodes? - * Don't silently accept this as "local allocation". - */ - if (!was_empty && is_empty) - return -EINVAL; - break; - } +/* Check that the nodemask contains at least one populated zone */ +static int is_valid_nodemask(const nodemask_t *nodemask) +{ + return nodes_intersects(*nodemask, node_states[N_MEMORY]); +} + +static inline int mpol_store_user_nodemask(const struct mempolicy *pol) +{ + return pol->flags & MPOL_MODE_FLAGS; +} + +static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, + const nodemask_t *rel) +{ + nodemask_t tmp; + nodes_fold(tmp, *orig, nodes_weight(*rel)); + nodes_onto(*ret, tmp, *rel); +} + +static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) +{ + if (nodes_empty(*nodes)) + return -EINVAL; + pol->v.nodes = *nodes; return 0; } -/* Generate a custom zonelist for the BIND policy. */ -static struct zonelist *bind_zonelist(nodemask_t *nodes) +static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - struct zonelist *zl; - int num, max, nd; - enum zone_type k; + if (!nodes) + pol->flags |= MPOL_F_LOCAL; /* local allocation */ + else if (nodes_empty(*nodes)) + return -EINVAL; /* no allowed nodes */ + else + pol->v.preferred_node = first_node(*nodes); + return 0; +} - max = 1 + MAX_NR_ZONES * nodes_weight(*nodes); - max++; /* space for zlcache_ptr (see mmzone.h) */ - zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL); - if (!zl) - return ERR_PTR(-ENOMEM); - zl->zlcache_ptr = NULL; - num = 0; - /* First put in the highest zones from all nodes, then all the next - lower zones etc. Avoid empty zones because the memory allocator - doesn't like them. If you implement node hot removal you - have to fix that. */ - k = MAX_NR_ZONES - 1; - while (1) { - for_each_node_mask(nd, *nodes) { - struct zone *z = &NODE_DATA(nd)->node_zones[k]; - if (z->present_pages > 0) - zl->zones[num++] = z; - } - if (k == 0) - break; - k--; - } - if (num == 0) { - kfree(zl); - return ERR_PTR(-EINVAL); +static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) +{ + if (!is_valid_nodemask(nodes)) + return -EINVAL; + pol->v.nodes = *nodes; + return 0; +} + +/* + * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if + * any, for the new policy. mpol_new() has already validated the nodes + * parameter with respect to the policy mode and flags. But, we need to + * handle an empty nodemask with MPOL_PREFERRED here. + * + * Must be called holding task's alloc_lock to protect task's mems_allowed + * and mempolicy. May also be called holding the mmap_semaphore for write. + */ +static int mpol_set_nodemask(struct mempolicy *pol, + const nodemask_t *nodes, struct nodemask_scratch *nsc) +{ + int ret; + + /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ + if (pol == NULL) + return 0; + /* Check N_MEMORY */ + nodes_and(nsc->mask1, + cpuset_current_mems_allowed, node_states[N_MEMORY]); + + VM_BUG_ON(!nodes); + if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) + nodes = NULL; /* explicit local allocation */ + else { + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1); + else + nodes_and(nsc->mask2, *nodes, nsc->mask1); + + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; + else + pol->w.cpuset_mems_allowed = + cpuset_current_mems_allowed; } - zl->zones[num] = NULL; - return zl; + + if (nodes) + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + else + ret = mpol_ops[pol->mode].create(pol, NULL); + return ret; } -/* Create a new policy */ -static struct mempolicy *mpol_new(int mode, nodemask_t *nodes) +/* + * This function just creates a new policy, does some check and simple + * initialization. You must invoke mpol_set_nodemask() to set nodes. + */ +static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, + nodemask_t *nodes) { struct mempolicy *policy; - pr_debug("setting mode %d nodes[0] %lx\n", - mode, nodes ? nodes_addr(*nodes)[0] : -1); + pr_debug("setting mode %d flags %d nodes[0] %lx\n", + mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); - if (mode == MPOL_DEFAULT) + if (mode == MPOL_DEFAULT) { + if (nodes && !nodes_empty(*nodes)) + return ERR_PTR(-EINVAL); return NULL; + } + VM_BUG_ON(!nodes); + + /* + * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or + * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). + * All other modes require a valid pointer to a non-empty nodemask. + */ + if (mode == MPOL_PREFERRED) { + if (nodes_empty(*nodes)) { + if (((flags & MPOL_F_STATIC_NODES) || + (flags & MPOL_F_RELATIVE_NODES))) + return ERR_PTR(-EINVAL); + } + } else if (mode == MPOL_LOCAL) { + if (!nodes_empty(*nodes)) + return ERR_PTR(-EINVAL); + mode = MPOL_PREFERRED; + } else if (nodes_empty(*nodes)) + return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); - switch (mode) { - case MPOL_INTERLEAVE: - policy->v.nodes = *nodes; - if (nodes_weight(policy->v.nodes) == 0) { - kmem_cache_free(policy_cache, policy); - return ERR_PTR(-EINVAL); - } - break; - case MPOL_PREFERRED: - policy->v.preferred_node = first_node(*nodes); - if (policy->v.preferred_node >= MAX_NUMNODES) - policy->v.preferred_node = -1; - break; - case MPOL_BIND: - policy->v.zonelist = bind_zonelist(nodes); - if (IS_ERR(policy->v.zonelist)) { - void *error_code = policy->v.zonelist; - kmem_cache_free(policy_cache, policy); - return error_code; - } - break; - } - policy->policy = mode; - policy->cpuset_mems_allowed = cpuset_mems_allowed(current); + policy->mode = mode; + policy->flags = flags; + return policy; } -static void gather_stats(struct page *, void *, int pte_dirty); +/* Slow path of a mpol destructor. */ +void __mpol_put(struct mempolicy *p) +{ + if (!atomic_dec_and_test(&p->refcnt)) + return; + kmem_cache_free(policy_cache, p); +} + +static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes, + enum mpol_rebind_step step) +{ +} + +/* + * step: + * MPOL_REBIND_ONCE - do rebind work at once + * MPOL_REBIND_STEP1 - set all the newly nodes + * MPOL_REBIND_STEP2 - clean all the disallowed nodes + */ +static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes, + enum mpol_rebind_step step) +{ + nodemask_t tmp; + + if (pol->flags & MPOL_F_STATIC_NODES) + nodes_and(tmp, pol->w.user_nodemask, *nodes); + else if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); + else { + /* + * if step == 1, we use ->w.cpuset_mems_allowed to cache the + * result + */ + if (step == MPOL_REBIND_ONCE || step == MPOL_REBIND_STEP1) { + nodes_remap(tmp, pol->v.nodes, + pol->w.cpuset_mems_allowed, *nodes); + pol->w.cpuset_mems_allowed = step ? tmp : *nodes; + } else if (step == MPOL_REBIND_STEP2) { + tmp = pol->w.cpuset_mems_allowed; + pol->w.cpuset_mems_allowed = *nodes; + } else + BUG(); + } + + if (nodes_empty(tmp)) + tmp = *nodes; + + if (step == MPOL_REBIND_STEP1) + nodes_or(pol->v.nodes, pol->v.nodes, tmp); + else if (step == MPOL_REBIND_ONCE || step == MPOL_REBIND_STEP2) + pol->v.nodes = tmp; + else + BUG(); + + if (!node_isset(current->il_next, tmp)) { + current->il_next = next_node(current->il_next, tmp); + if (current->il_next >= MAX_NUMNODES) + current->il_next = first_node(tmp); + if (current->il_next >= MAX_NUMNODES) + current->il_next = numa_node_id(); + } +} + +static void mpol_rebind_preferred(struct mempolicy *pol, + const nodemask_t *nodes, + enum mpol_rebind_step step) +{ + nodemask_t tmp; + + if (pol->flags & MPOL_F_STATIC_NODES) { + int node = first_node(pol->w.user_nodemask); + + if (node_isset(node, *nodes)) { + pol->v.preferred_node = node; + pol->flags &= ~MPOL_F_LOCAL; + } else + pol->flags |= MPOL_F_LOCAL; + } else if (pol->flags & MPOL_F_RELATIVE_NODES) { + mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); + pol->v.preferred_node = first_node(tmp); + } else if (!(pol->flags & MPOL_F_LOCAL)) { + pol->v.preferred_node = node_remap(pol->v.preferred_node, + pol->w.cpuset_mems_allowed, + *nodes); + pol->w.cpuset_mems_allowed = *nodes; + } +} + +/* + * mpol_rebind_policy - Migrate a policy to a different set of nodes + * + * If read-side task has no lock to protect task->mempolicy, write-side + * task will rebind the task->mempolicy by two step. The first step is + * setting all the newly nodes, and the second step is cleaning all the + * disallowed nodes. In this way, we can avoid finding no node to alloc + * page. + * If we have a lock to protect task->mempolicy in read-side, we do + * rebind directly. + * + * step: + * MPOL_REBIND_ONCE - do rebind work at once + * MPOL_REBIND_STEP1 - set all the newly nodes + * MPOL_REBIND_STEP2 - clean all the disallowed nodes + */ +static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask, + enum mpol_rebind_step step) +{ + if (!pol) + return; + if (!mpol_store_user_nodemask(pol) && step == MPOL_REBIND_ONCE && + nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) + return; + + if (step == MPOL_REBIND_STEP1 && (pol->flags & MPOL_F_REBINDING)) + return; + + if (step == MPOL_REBIND_STEP2 && !(pol->flags & MPOL_F_REBINDING)) + BUG(); + + if (step == MPOL_REBIND_STEP1) + pol->flags |= MPOL_F_REBINDING; + else if (step == MPOL_REBIND_STEP2) + pol->flags &= ~MPOL_F_REBINDING; + else if (step >= MPOL_REBIND_NSTEP) + BUG(); + + mpol_ops[pol->mode].rebind(pol, newmask, step); +} + +/* + * Wrapper for mpol_rebind_policy() that just requires task + * pointer, and updates task mempolicy. + * + * Called with task's alloc_lock held. + */ + +void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new, + enum mpol_rebind_step step) +{ + mpol_rebind_policy(tsk->mempolicy, new, step); +} + +/* + * Rebind each vma in mm to new nodemask. + * + * Call holding a reference to mm. Takes mm->mmap_sem during call. + */ + +void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) +{ + struct vm_area_struct *vma; + + down_write(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) + mpol_rebind_policy(vma->vm_policy, new, MPOL_REBIND_ONCE); + up_write(&mm->mmap_sem); +} + +static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { + [MPOL_DEFAULT] = { + .rebind = mpol_rebind_default, + }, + [MPOL_INTERLEAVE] = { + .create = mpol_new_interleave, + .rebind = mpol_rebind_nodemask, + }, + [MPOL_PREFERRED] = { + .create = mpol_new_preferred, + .rebind = mpol_rebind_preferred, + }, + [MPOL_BIND] = { + .create = mpol_new_bind, + .rebind = mpol_rebind_nodemask, + }, +}; + static void migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); -/* Scan through pages checking if pages follow certain conditions. */ -static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, +/* + * Scan through pages checking if pages follow certain conditions, + * and move them to the pagelist if they do. + */ +static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -266,15 +503,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (!page) continue; /* - * The check for PageReserved here is important to avoid - * handling zero pages and other pages that may have been - * marked special by the system. - * - * If the PageReserved would not be checked here then f.e. - * the location of the zero page could have an influence - * on MPOL_MF_STRICT, zero pages would be counted for - * the per node stats, and there would be useless attempts - * to put zero pages on the migration list. + * vm_normal_page() filters out zero pages, but there might + * still be PageReserved pages to skip, perhaps in a VDSO. */ if (PageReserved(page)) continue; @@ -282,9 +512,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) continue; - if (flags & MPOL_MF_STATS) - gather_stats(page, private, pte_dirty(*pte)); - else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) migrate_page_add(page, private, flags); else break; @@ -293,7 +521,36 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, return addr != end; } -static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, +static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, + pmd_t *pmd, const nodemask_t *nodes, unsigned long flags, + void *private) +{ +#ifdef CONFIG_HUGETLB_PAGE + int nid; + struct page *page; + spinlock_t *ptl; + pte_t entry; + + ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); + entry = huge_ptep_get((pte_t *)pmd); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); + nid = page_to_nid(page); + if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) + goto unlock; + /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ + if (flags & (MPOL_MF_MOVE_ALL) || + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) + isolate_huge_page(page, private); +unlock: + spin_unlock(ptl); +#else + BUG(); +#endif +} + +static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -304,16 +561,24 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) + if (!pmd_present(*pmd)) + continue; + if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) { + queue_pages_hugetlb_pmd_range(vma, pmd, nodes, + flags, private); + continue; + } + split_huge_page_pmd(vma, addr, pmd); + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - if (check_pte_range(vma, pmd, addr, next, nodes, + if (queue_pages_pte_range(vma, pmd, addr, next, nodes, flags, private)) return -EIO; } while (pmd++, addr = next, addr != end); return 0; } -static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -324,16 +589,18 @@ static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); + if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) + continue; if (pud_none_or_clear_bad(pud)) continue; - if (check_pmd_range(vma, pud, addr, next, nodes, + if (queue_pages_pmd_range(vma, pud, addr, next, nodes, flags, private)) return -EIO; } while (pud++, addr = next, addr != end); return 0; } -static inline int check_pgd_range(struct vm_area_struct *vma, +static inline int queue_pages_pgd_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) @@ -346,179 +613,263 @@ static inline int check_pgd_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (check_pud_range(vma, pgd, addr, next, nodes, + if (queue_pages_pud_range(vma, pgd, addr, next, nodes, flags, private)) return -EIO; } while (pgd++, addr = next, addr != end); return 0; } +#ifdef CONFIG_NUMA_BALANCING /* - * Check if all pages in a range are on a set of nodes. - * If pagelist != NULL then isolate pages from the LRU and - * put them on the pagelist. + * This is used to mark a range of virtual addresses to be inaccessible. + * These are later cleared by a NUMA hinting fault. Depending on these + * faults, pages may be migrated for better NUMA placement. + * + * This is assuming that NUMA faults are handled using PROT_NONE. If + * an architecture makes a different choice, it will need further + * changes to the core. */ -static struct vm_area_struct * -check_range(struct mm_struct *mm, unsigned long start, unsigned long end, - const nodemask_t *nodes, unsigned long flags, void *private) +unsigned long change_prot_numa(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { - int err; - struct vm_area_struct *first, *vma, *prev; + int nr_updated; - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); + if (nr_updated) + count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); - err = migrate_prep(); - if (err) - return ERR_PTR(err); - } + return nr_updated; +} +#else +static unsigned long change_prot_numa(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); +/* + * Walk through page tables and collect pages to be migrated. + * + * If pages found in a given range are on a set of nodes (determined by + * @nodes and @flags,) it's isolated and queued to the pagelist which is + * passed via @private.) + */ +static int +queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, + const nodemask_t *nodes, unsigned long flags, void *private) +{ + int err = 0; + struct vm_area_struct *vma, *prev; + + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { + unsigned long endvma = vma->vm_end; + + if (endvma > end) + endvma = end; + if (vma->vm_start > start) + start = vma->vm_start; + if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; + } + + if (flags & MPOL_MF_LAZY) { + change_prot_numa(vma, start, endvma); + goto next; } - if (!is_vm_hugetlb_page(vma) && - ((flags & MPOL_MF_STRICT) || + + if ((flags & MPOL_MF_STRICT) || ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && - vma_migratable(vma)))) { - unsigned long endvma = vma->vm_end; - - if (endvma > end) - endvma = end; - if (vma->vm_start > start) - start = vma->vm_start; - err = check_pgd_range(vma, start, endvma, nodes, + vma_migratable(vma))) { + + err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } +next: prev = vma; } - return first; + return err; } -/* Apply policy to a single VMA */ -static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new) +/* + * Apply policy to a single VMA + * This must be called with the mmap_sem held for writing. + */ +static int vma_replace_policy(struct vm_area_struct *vma, + struct mempolicy *pol) { - int err = 0; - struct mempolicy *old = vma->vm_policy; + int err; + struct mempolicy *old; + struct mempolicy *new; pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", vma->vm_start, vma->vm_end, vma->vm_pgoff, vma->vm_ops, vma->vm_file, vma->vm_ops ? vma->vm_ops->set_policy : NULL); - if (vma->vm_ops && vma->vm_ops->set_policy) + new = mpol_dup(pol); + if (IS_ERR(new)) + return PTR_ERR(new); + + if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); - if (!err) { - mpol_get(new); - vma->vm_policy = new; - mpol_free(old); + if (err) + goto err_out; } + + old = vma->vm_policy; + vma->vm_policy = new; /* protected by mmap_sem */ + mpol_put(old); + + return 0; + err_out: + mpol_put(new); return err; } /* Step 2: apply policy to a range and do splits. */ -static int mbind_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct mempolicy *new) +static int mbind_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct mempolicy *new_pol) { struct vm_area_struct *next; - int err; + struct vm_area_struct *prev; + struct vm_area_struct *vma; + int err = 0; + pgoff_t pgoff; + unsigned long vmstart; + unsigned long vmend; - err = 0; - for (; vma && vma->vm_start < end; vma = next) { + vma = find_vma(mm, start); + if (!vma || vma->vm_start > start) + return -EFAULT; + + prev = vma->vm_prev; + if (start > vma->vm_start) + prev = vma; + + for (; vma && vma->vm_start < end; prev = vma, vma = next) { next = vma->vm_next; - if (vma->vm_start < start) - err = split_vma(vma->vm_mm, vma, start, 1); - if (!err && vma->vm_end > end) - err = split_vma(vma->vm_mm, vma, end, 0); - if (!err) - err = policy_vma(vma, new); - if (err) - break; - } - return err; -} + vmstart = max(start, vma->vm_start); + vmend = min(end, vma->vm_end); -/* - * Update task->flags PF_MEMPOLICY bit: set iff non-default - * mempolicy. Allows more rapid checking of this (combined perhaps - * with other PF_* flag bits) on memory allocation hot code paths. - * - * If called from outside this file, the task 'p' should -only- be - * a newly forked child not yet visible on the task list, because - * manipulating the task flags of a visible task is not safe. - * - * The above limitation is why this routine has the funny name - * mpol_fix_fork_child_flag(). - * - * It is also safe to call this with a task pointer of current, - * which the static wrapper mpol_set_task_struct_flag() does, - * for use within this file. - */ + if (mpol_equal(vma_policy(vma), new_pol)) + continue; -void mpol_fix_fork_child_flag(struct task_struct *p) -{ - if (p->mempolicy) - p->flags |= PF_MEMPOLICY; - else - p->flags &= ~PF_MEMPOLICY; -} + pgoff = vma->vm_pgoff + + ((vmstart - vma->vm_start) >> PAGE_SHIFT); + prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, + new_pol); + if (prev) { + vma = prev; + next = vma->vm_next; + if (mpol_equal(vma_policy(vma), new_pol)) + continue; + /* vma_merge() joined vma && vma->next, case 8 */ + goto replace; + } + if (vma->vm_start != vmstart) { + err = split_vma(vma->vm_mm, vma, vmstart, 1); + if (err) + goto out; + } + if (vma->vm_end != vmend) { + err = split_vma(vma->vm_mm, vma, vmend, 0); + if (err) + goto out; + } + replace: + err = vma_replace_policy(vma, new_pol); + if (err) + goto out; + } -static void mpol_set_task_struct_flag(void) -{ - mpol_fix_fork_child_flag(current); + out: + return err; } /* Set the process memory policy */ -static long do_set_mempolicy(int mode, nodemask_t *nodes) +static long do_set_mempolicy(unsigned short mode, unsigned short flags, + nodemask_t *nodes) { - struct mempolicy *new; + struct mempolicy *new, *old; + struct mm_struct *mm = current->mm; + NODEMASK_SCRATCH(scratch); + int ret; - if (mpol_check_policy(mode, nodes)) - return -EINVAL; - new = mpol_new(mode, nodes); - if (IS_ERR(new)) - return PTR_ERR(new); - mpol_free(current->mempolicy); + if (!scratch) + return -ENOMEM; + + new = mpol_new(mode, flags, nodes); + if (IS_ERR(new)) { + ret = PTR_ERR(new); + goto out; + } + /* + * prevent changing our mempolicy while show_numa_maps() + * is using it. + * Note: do_set_mempolicy() can be called at init time + * with no 'mm'. + */ + if (mm) + down_write(&mm->mmap_sem); + task_lock(current); + ret = mpol_set_nodemask(new, nodes, scratch); + if (ret) { + task_unlock(current); + if (mm) + up_write(&mm->mmap_sem); + mpol_put(new); + goto out; + } + old = current->mempolicy; current->mempolicy = new; - mpol_set_task_struct_flag(); - if (new && new->policy == MPOL_INTERLEAVE) + if (new && new->mode == MPOL_INTERLEAVE && + nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); - return 0; + task_unlock(current); + if (mm) + up_write(&mm->mmap_sem); + + mpol_put(old); + ret = 0; +out: + NODEMASK_SCRATCH_FREE(scratch); + return ret; } -/* Fill a zone bitmap for a policy */ -static void get_zonemask(struct mempolicy *p, nodemask_t *nodes) +/* + * Return nodemask for policy for get_mempolicy() query + * + * Called with task's alloc_lock held + */ +static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) { - int i; - nodes_clear(*nodes); - switch (p->policy) { + if (p == &default_policy) + return; + + switch (p->mode) { case MPOL_BIND: - for (i = 0; p->v.zonelist->zones[i]; i++) - node_set(zone_to_nid(p->v.zonelist->zones[i]), - *nodes); - break; - case MPOL_DEFAULT: - break; + /* Fall through */ case MPOL_INTERLEAVE: *nodes = p->v.nodes; break; case MPOL_PREFERRED: - /* or use current node instead of memory_map? */ - if (p->v.preferred_node < 0) - *nodes = node_states[N_HIGH_MEMORY]; - else + if (!(p->flags & MPOL_F_LOCAL)) node_set(p->v.preferred_node, *nodes); + /* else return empty node mask for local allocation */ break; default: BUG(); @@ -547,7 +898,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy; - cpuset_update_task_memory_state(); if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; @@ -556,11 +906,18 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ + task_lock(current); *nmask = cpuset_current_mems_allowed; + task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { + /* + * Do NOT fall back to task policy if the + * vma/shared policy at addr is NULL. We + * want to return MPOL_DEFAULT in this case. + */ down_read(&mm->mmap_sem); vma = find_vma_intersection(mm, addr, addr+1); if (!vma) { @@ -575,7 +932,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, return -EINVAL; if (!pol) - pol = &default_policy; + pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { @@ -584,14 +941,21 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, goto out; *policy = err; } else if (pol == current->mempolicy && - pol->policy == MPOL_INTERLEAVE) { + pol->mode == MPOL_INTERLEAVE) { *policy = current->il_next; } else { err = -EINVAL; goto out; } - } else - *policy = pol->policy; + } else { + *policy = pol == &default_policy ? MPOL_DEFAULT : + pol->mode; + /* + * Internal mempolicy flags must be masked off before exposing + * the policy to userspace. + */ + *policy |= (pol->flags & MPOL_MODE_FLAGS); + } if (vma) { up_read(¤t->mm->mmap_sem); @@ -599,10 +963,18 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } err = 0; - if (nmask) - get_zonemask(pol, nmask); + if (nmask) { + if (mpol_store_user_nodemask(pol)) { + *nmask = pol->w.user_nodemask; + } else { + task_lock(current); + get_policy_nodemask(pol, nmask); + task_unlock(current); + } + } out: + mpol_cond_put(pol); if (vma) up_read(¤t->mm->mmap_sem); return err; @@ -618,13 +990,22 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, /* * Avoid migrating a page that is shared with others. */ - if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) - isolate_lru_page(page, pagelist); + if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) { + if (!isolate_lru_page(page)) { + list_add_tail(&page->lru, pagelist); + inc_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + } + } } static struct page *new_node_page(struct page *page, unsigned long node, int **x) { - return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0); + if (PageHuge(page)) + return alloc_huge_page_node(page_hstate(compound_head(page)), + node); + else + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); } /* @@ -641,11 +1022,21 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodes_clear(nmask); node_set(source, nmask); - check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask, + /* + * This does not "check" the range but isolates all pages that + * need migration. Between passing in the full user address + * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. + */ + VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); + queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); - if (!list_empty(&pagelist)) - err = migrate_pages(&pagelist, new_node_page, dest); + if (!list_empty(&pagelist)) { + err = migrate_pages(&pagelist, new_node_page, NULL, dest, + MIGRATE_SYNC, MR_SYSCALL); + if (err) + putback_movable_pages(&pagelist); + } return err; } @@ -656,59 +1047,82 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, * * Returns the number of page that could not be moved. */ -int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) { - LIST_HEAD(pagelist); int busy = 0; - int err = 0; + int err; nodemask_t tmp; - down_read(&mm->mmap_sem); + err = migrate_prep(); + if (err) + return err; + + down_read(&mm->mmap_sem); - err = migrate_vmas(mm, from_nodes, to_nodes, flags); + err = migrate_vmas(mm, from, to, flags); if (err) goto out; -/* - * Find a 'source' bit set in 'tmp' whose corresponding 'dest' - * bit in 'to' is not also set in 'tmp'. Clear the found 'source' - * bit in 'tmp', and return that <source, dest> pair for migration. - * The pair of nodemasks 'to' and 'from' define the map. - * - * If no pair of bits is found that way, fallback to picking some - * pair of 'source' and 'dest' bits that are not the same. If the - * 'source' and 'dest' bits are the same, this represents a node - * that will be migrating to itself, so no pages need move. - * - * If no bits are left in 'tmp', or if all remaining bits left - * in 'tmp' correspond to the same bit in 'to', return false - * (nothing left to migrate). - * - * This lets us pick a pair of nodes to migrate between, such that - * if possible the dest node is not already occupied by some other - * source node, minimizing the risk of overloading the memory on a - * node that would happen if we migrated incoming memory to a node - * before migrating outgoing memory source that same node. - * - * A single scan of tmp is sufficient. As we go, we remember the - * most recent <s, d> pair that moved (s != d). If we find a pair - * that not only moved, but what's better, moved to an empty slot - * (d is not set in tmp), then we break out then, with that pair. - * Otherwise when we finish scannng from_tmp, we at least have the - * most recent <s, d> pair that moved. If we get all the way through - * the scan of tmp without finding any node that moved, much less - * moved to an empty node, then there is nothing left worth migrating. - */ + /* + * Find a 'source' bit set in 'tmp' whose corresponding 'dest' + * bit in 'to' is not also set in 'tmp'. Clear the found 'source' + * bit in 'tmp', and return that <source, dest> pair for migration. + * The pair of nodemasks 'to' and 'from' define the map. + * + * If no pair of bits is found that way, fallback to picking some + * pair of 'source' and 'dest' bits that are not the same. If the + * 'source' and 'dest' bits are the same, this represents a node + * that will be migrating to itself, so no pages need move. + * + * If no bits are left in 'tmp', or if all remaining bits left + * in 'tmp' correspond to the same bit in 'to', return false + * (nothing left to migrate). + * + * This lets us pick a pair of nodes to migrate between, such that + * if possible the dest node is not already occupied by some other + * source node, minimizing the risk of overloading the memory on a + * node that would happen if we migrated incoming memory to a node + * before migrating outgoing memory source that same node. + * + * A single scan of tmp is sufficient. As we go, we remember the + * most recent <s, d> pair that moved (s != d). If we find a pair + * that not only moved, but what's better, moved to an empty slot + * (d is not set in tmp), then we break out then, with that pair. + * Otherwise when we finish scanning from_tmp, we at least have the + * most recent <s, d> pair that moved. If we get all the way through + * the scan of tmp without finding any node that moved, much less + * moved to an empty node, then there is nothing left worth migrating. + */ - tmp = *from_nodes; + tmp = *from; while (!nodes_empty(tmp)) { int s,d; - int source = -1; + int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { - d = node_remap(s, *from_nodes, *to_nodes); + + /* + * do_migrate_pages() tries to maintain the relative + * node relationship of the pages established between + * threads and memory areas. + * + * However if the number of source nodes is not equal to + * the number of destination nodes we can not preserve + * this node relative relationship. In that case, skip + * copying memory from a node that is in the destination + * mask. + * + * Example: [2,3,4] -> [3,4,5] moves everything. + * [0-7] - > [3,4,5] moves only 0,1,2,6,7. + */ + + if ((nodes_weight(*from) != nodes_weight(*to)) && + (node_isset(s, *to))) + continue; + + d = node_remap(s, *from, *to); if (s == d) continue; @@ -719,7 +1133,7 @@ int do_migrate_pages(struct mm_struct *mm, if (!node_isset(dest, tmp)) break; } - if (source == -1) + if (source == NUMA_NO_NODE) break; node_clear(source, tmp); @@ -739,16 +1153,17 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) @@ -756,6 +1171,10 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int * vma = vma->vm_next; } + if (PageHuge(page)) { + BUG_ON(!vma); + return alloc_huge_page_noerr(vma, address, 1); + } /* * if !vma, alloc_page_vma() will use task or system default policy */ @@ -768,32 +1187,29 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, { } -int do_migrate_pages(struct mm_struct *mm, - const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) +int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to, int flags) { return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, - unsigned long mode, nodemask_t *nmask, - unsigned long flags) + unsigned short mode, unsigned short mode_flags, + nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; int err; LIST_HEAD(pagelist); - if ((flags & ~(unsigned long)(MPOL_MF_STRICT | - MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) - || mode > MPOL_MAX) + if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; @@ -812,13 +1228,13 @@ static long do_mbind(unsigned long start, unsigned long len, if (end == start) return 0; - if (mpol_check_policy(mode, nmask)) - return -EINVAL; - - new = mpol_new(mode, nmask); + new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); + if (flags & MPOL_MF_LAZY) + new->flags |= MPOL_F_MOF; + /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all @@ -826,29 +1242,56 @@ static long do_mbind(unsigned long start, unsigned long len, if (!new) flags |= MPOL_MF_DISCONTIG_OK; - pr_debug("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len, - mode, nmask ? nodes_addr(*nmask)[0] : -1); + pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", + start, start + len, mode, mode_flags, + nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); - down_write(&mm->mmap_sem); - vma = check_range(mm, start, end, nmask, + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + + err = migrate_prep(); + if (err) + goto mpol_out; + } + { + NODEMASK_SCRATCH(scratch); + if (scratch) { + down_write(&mm->mmap_sem); + task_lock(current); + err = mpol_set_nodemask(new, nmask, scratch); + task_unlock(current); + if (err) + up_write(&mm->mmap_sem); + } else + err = -ENOMEM; + NODEMASK_SCRATCH_FREE(scratch); + } + if (err) + goto mpol_out; + + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); + if (!err) + err = mbind_range(mm, start, end, new); - err = PTR_ERR(vma); - if (!IS_ERR(vma)) { + if (!err) { int nr_failed = 0; - err = mbind_range(vma, start, end, new); - - if (!list_empty(&pagelist)) - nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma); + if (!list_empty(&pagelist)) { + WARN_ON_ONCE(flags & MPOL_MF_LAZY); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + if (nr_failed) + putback_movable_pages(&pagelist); + } - if (!err && nr_failed && (flags & MPOL_MF_STRICT)) + if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; - } + } else + putback_movable_pages(&pagelist); up_write(&mm->mmap_sem); - mpol_free(new); + mpol_out: + mpol_put(new); return err; } @@ -919,66 +1362,85 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } -asmlinkage long sys_mbind(unsigned long start, unsigned long len, - unsigned long mode, - unsigned long __user *nmask, unsigned long maxnode, - unsigned flags) +SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, + unsigned long, mode, const unsigned long __user *, nmask, + unsigned long, maxnode, unsigned, flags) { nodemask_t nodes; int err; + unsigned short mode_flags; + mode_flags = mode & MPOL_MODE_FLAGS; + mode &= ~MPOL_MODE_FLAGS; + if (mode >= MPOL_MAX) + return -EINVAL; + if ((mode_flags & MPOL_F_STATIC_NODES) && + (mode_flags & MPOL_F_RELATIVE_NODES)) + return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_mbind(start, len, mode, &nodes, flags); + return do_mbind(start, len, mode, mode_flags, &nodes, flags); } /* Set the process memory policy */ -asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask, - unsigned long maxnode) +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, + unsigned long, maxnode) { int err; nodemask_t nodes; + unsigned short flags; - if (mode < 0 || mode > MPOL_MAX) + flags = mode & MPOL_MODE_FLAGS; + mode &= ~MPOL_MODE_FLAGS; + if ((unsigned int)mode >= MPOL_MAX) + return -EINVAL; + if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_set_mempolicy(mode, &nodes); + return do_set_mempolicy(mode, flags, &nodes); } -asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, - const unsigned long __user *old_nodes, - const unsigned long __user *new_nodes) +SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, + const unsigned long __user *, old_nodes, + const unsigned long __user *, new_nodes) { - struct mm_struct *mm; + const struct cred *cred = current_cred(), *tcred; + struct mm_struct *mm = NULL; struct task_struct *task; - nodemask_t old; - nodemask_t new; nodemask_t task_nodes; int err; + nodemask_t *old; + nodemask_t *new; + NODEMASK_SCRATCH(scratch); + + if (!scratch) + return -ENOMEM; + + old = &scratch->mask1; + new = &scratch->mask2; - err = get_nodes(&old, old_nodes, maxnode); + err = get_nodes(old, old_nodes, maxnode); if (err) - return err; + goto out; - err = get_nodes(&new, new_nodes, maxnode); + err = get_nodes(new, new_nodes, maxnode); if (err) - return err; + goto out; /* Find the mm_struct */ - read_lock(&tasklist_lock); + rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { - read_unlock(&tasklist_lock); - return -ESRCH; + rcu_read_unlock(); + err = -ESRCH; + goto out; } - mm = get_task_mm(task); - read_unlock(&tasklist_lock); + get_task_struct(task); - if (!mm) - return -EINVAL; + err = -EINVAL; /* * Check if this process has the right to modify the specified @@ -986,42 +1448,60 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + tcred = __task_cred(task); + if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; - goto out; + goto out_put; } + rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ - if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) { + if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; - goto out; + goto out_put; } - if (!nodes_subset(new, node_states[N_HIGH_MEMORY])) { + if (!nodes_subset(*new, node_states[N_MEMORY])) { err = -EINVAL; - goto out; + goto out_put; } err = security_task_movememory(task); if (err) + goto out_put; + + mm = get_task_mm(task); + put_task_struct(task); + + if (!mm) { + err = -EINVAL; goto out; + } - err = do_migrate_pages(mm, &old, &new, + err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); -out: + mmput(mm); +out: + NODEMASK_SCRATCH_FREE(scratch); + return err; + +out_put: + put_task_struct(task); + goto out; + } /* Retrieve NUMA policy */ -asmlinkage long sys_get_mempolicy(int __user *policy, - unsigned long __user *nmask, - unsigned long maxnode, - unsigned long addr, unsigned long flags) +SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + unsigned long __user *, nmask, unsigned long, maxnode, + unsigned long, addr, unsigned long, flags) { int err; int uninitialized_var(pval); @@ -1046,10 +1526,10 @@ asmlinkage long sys_get_mempolicy(int __user *policy, #ifdef CONFIG_COMPAT -asmlinkage long compat_sys_get_mempolicy(int __user *policy, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, - compat_ulong_t addr, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, + compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, + compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; @@ -1065,7 +1545,9 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { - err = copy_from_user(bm, nm, alloc_size); + unsigned long copy_size; + copy_size = min_t(unsigned long, sizeof(bm), alloc_size); + err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); @@ -1074,8 +1556,8 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, return err; } -asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode) +COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode) { long err = 0; unsigned long __user *nm = NULL; @@ -1097,9 +1579,9 @@ asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, return sys_set_mempolicy(mode, nm, nr_bits+1); } -asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, - compat_ulong_t mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode, compat_ulong_t flags) +COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, + compat_ulong_t, mode, compat_ulong_t __user *, nmask, + compat_ulong_t, maxnode, compat_ulong_t, flags) { long err = 0; unsigned long __user *nm = NULL; @@ -1125,65 +1607,131 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, /* * get_vma_policy(@task, @vma, @addr) - * @task - task for fallback if vma policy == default - * @vma - virtual memory area whose policy is sought - * @addr - address in @vma for shared policy lookup + * @task: task for fallback if vma policy == default + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to @task or system default policy, as necessary. - * Returned policy has extra reference count if shared, vma, - * or some other task's policy [show_numa_maps() can pass - * @task != current]. It is the caller's responsibility to - * free the reference in these cases. + * Current or other task's task mempolicy and non-shared vma policies must be + * protected by task_lock(task) by the caller. + * Shared policies [those marked as MPOL_F_SHARED] require an extra reference + * count--added by the get_policy() vm_op, as appropriate--to protect against + * freeing by another task. It is the caller's responsibility to free the + * extra reference for shared policies. */ -static struct mempolicy * get_vma_policy(struct task_struct *task, +struct mempolicy *get_vma_policy(struct task_struct *task, struct vm_area_struct *vma, unsigned long addr) { - struct mempolicy *pol = task->mempolicy; - int shared_pol = 0; + struct mempolicy *pol = get_task_policy(task); if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) { - pol = vma->vm_ops->get_policy(vma, addr); - shared_pol = 1; /* if pol non-NULL, add ref below */ - } else if (vma->vm_policy && - vma->vm_policy->policy != MPOL_DEFAULT) + struct mempolicy *vpol = vma->vm_ops->get_policy(vma, + addr); + if (vpol) + pol = vpol; + } else if (vma->vm_policy) { pol = vma->vm_policy; + + /* + * shmem_alloc_page() passes MPOL_F_SHARED policy with + * a pseudo vma whose vma->vm_ops=NULL. Take a reference + * count on these policies which will be dropped by + * mpol_cond_put() later + */ + if (mpol_needs_cond_ref(pol)) + mpol_get(pol); + } } if (!pol) pol = &default_policy; - else if (!shared_pol && pol != current->mempolicy) - mpol_get(pol); /* vma or other task's policy */ return pol; } -/* Return a zonelist representing a mempolicy */ -static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy) +bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma) +{ + struct mempolicy *pol = get_task_policy(task); + if (vma) { + if (vma->vm_ops && vma->vm_ops->get_policy) { + bool ret = false; + + pol = vma->vm_ops->get_policy(vma, vma->vm_start); + if (pol && (pol->flags & MPOL_F_MOF)) + ret = true; + mpol_cond_put(pol); + + return ret; + } else if (vma->vm_policy) { + pol = vma->vm_policy; + } + } + + if (!pol) + return default_policy.flags & MPOL_F_MOF; + + return pol->flags & MPOL_F_MOF; +} + +static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { - int nd; + 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; - switch (policy->policy) { + return zone >= dynamic_policy_zone; +} + +/* + * Return a nodemask representing a mempolicy for filtering nodes for + * page allocation + */ +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) && + apply_policy_zone(policy, gfp_zone(gfp)) && + cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) + return &policy->v.nodes; + + return NULL; +} + +/* Return a zonelist indicated by gfp for node representing a mempolicy */ +static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, + int nd) +{ + switch (policy->mode) { case MPOL_PREFERRED: - nd = policy->v.preferred_node; - if (nd < 0) - nd = numa_node_id(); + if (!(policy->flags & MPOL_F_LOCAL)) + nd = policy->v.preferred_node; break; case MPOL_BIND: - /* Lower zones don't get a policy applied */ - /* Careful: current->mems_allowed might have moved */ - if (gfp_zone(gfp) >= policy_zone) - if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist)) - return policy->v.zonelist; - /*FALL THROUGH*/ - case MPOL_INTERLEAVE: /* should not happen */ - case MPOL_DEFAULT: - nd = numa_node_id(); + /* + * Normally, MPOL_BIND allocations are node-local within the + * allowed nodemask. However, if __GFP_THISNODE is set and the + * current node isn't part of the mask, we use the zonelist for + * the first node in the mask instead. + */ + if (unlikely(gfp & __GFP_THISNODE) && + unlikely(!node_isset(nd, policy->v.nodes))) + nd = first_node(policy->v.nodes); break; default: - nd = 0; BUG(); } - return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp); + return node_zonelist(nd, gfp); } /* Do dynamic interleaving for a process */ @@ -1196,7 +1744,8 @@ static unsigned interleave_nodes(struct mempolicy *policy) next = next_node(nid, policy->v.nodes); if (next >= MAX_NUMNODES) next = first_node(policy->v.nodes); - me->il_next = next; + if (next < MAX_NUMNODES) + me->il_next = next; return nid; } @@ -1204,28 +1753,45 @@ static unsigned interleave_nodes(struct mempolicy *policy) * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ -unsigned slab_node(struct mempolicy *policy) +unsigned int mempolicy_slab_node(void) { - int pol = policy ? policy->policy : MPOL_DEFAULT; + struct mempolicy *policy; + int node = numa_mem_id(); + + if (in_interrupt()) + return node; + + policy = current->mempolicy; + if (!policy || policy->flags & MPOL_F_LOCAL) + return node; + + switch (policy->mode) { + case MPOL_PREFERRED: + /* + * handled MPOL_F_LOCAL above + */ + return policy->v.preferred_node; - switch (pol) { case MPOL_INTERLEAVE: return interleave_nodes(policy); - case MPOL_BIND: + case MPOL_BIND: { /* * Follow bind policy behavior and start allocation at the * first node. */ - return zone_to_nid(policy->v.zonelist->zones[0]); - - case MPOL_PREFERRED: - if (policy->v.preferred_node >= 0) - return policy->v.preferred_node; - /* Fall through */ + struct zonelist *zonelist; + struct zone *zone; + enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); + zonelist = &NODE_DATA(node)->node_zonelists[0]; + (void)first_zones_zonelist(zonelist, highest_zoneidx, + &policy->v.nodes, + &zone); + return zone ? zone->node : node; + } default: - return numa_node_id(); + BUG(); } } @@ -1234,10 +1800,13 @@ static unsigned offset_il_node(struct mempolicy *pol, struct vm_area_struct *vma, unsigned long off) { unsigned nnodes = nodes_weight(pol->v.nodes); - unsigned target = (unsigned)off % nnodes; + unsigned target; int c; - int nid = -1; + int nid = NUMA_NO_NODE; + if (!nnodes) + return numa_node_id(); + target = (unsigned int)off % nnodes; c = 0; do { nid = next_node(nid, pol->v.nodes); @@ -1268,51 +1837,151 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } +/* + * Return the bit number of a random bit set in the nodemask. + * (returns NUMA_NO_NODE if nodemask is empty) + */ +int node_random(const nodemask_t *maskp) +{ + int w, bit = NUMA_NO_NODE; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +} + #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) - * @vma = virtual memory area whose policy is sought - * @addr = address in @vma for shared policy lookup and interleave policy - * @gfp_flags = for requested zone - * @mpol = pointer to mempolicy pointer for reference counted 'BIND policy + * @vma: virtual memory area whose policy is sought + * @addr: address in @vma for shared policy lookup and interleave policy + * @gfp_flags: for requested zone + * @mpol: pointer to mempolicy pointer for reference counted mempolicy + * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask + * + * Returns a zonelist suitable for a huge page allocation and a pointer + * to the struct mempolicy for conditional unref after allocation. + * If the effective policy is 'BIND, returns a pointer to the mempolicy's + * @nodemask for filtering the zonelist. * - * Returns a zonelist suitable for a huge page allocation. - * If the effective policy is 'BIND, returns pointer to policy's zonelist. - * If it is also a policy for which get_vma_policy() returns an extra - * reference, we must hold that reference until after allocation. - * In that case, return policy via @mpol so hugetlb allocation can drop - * the reference. For non-'BIND referenced policies, we can/do drop the - * reference here, so the caller doesn't need to know about the special case - * for default and current task policy. + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, - gfp_t gfp_flags, struct mempolicy **mpol) + gfp_t gfp_flags, struct mempolicy **mpol, + nodemask_t **nodemask) { - struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; - *mpol = NULL; /* probably no unref needed */ - if (pol->policy == MPOL_INTERLEAVE) { - unsigned nid; + *mpol = get_vma_policy(current, vma, addr); + *nodemask = NULL; /* assume !MPOL_BIND */ - nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT); - if (unlikely(pol != &default_policy && - pol != current->mempolicy)) - __mpol_free(pol); /* finished with pol */ - return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags); + if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { + zl = node_zonelist(interleave_nid(*mpol, vma, addr, + huge_page_shift(hstate_vma(vma))), gfp_flags); + } else { + zl = policy_zonelist(gfp_flags, *mpol, numa_node_id()); + if ((*mpol)->mode == MPOL_BIND) + *nodemask = &(*mpol)->v.nodes; } + 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; - zl = zonelist_policy(GFP_HIGHUSER, pol); - if (unlikely(pol != &default_policy && pol != current->mempolicy)) { - if (pol->policy != MPOL_BIND) - __mpol_free(pol); /* finished with pol */ + task_lock(current); + mempolicy = current->mempolicy; + switch (mempolicy->mode) { + case MPOL_PREFERRED: + if (mempolicy->flags & MPOL_F_LOCAL) + nid = numa_node_id(); else - *mpol = pol; /* unref needed after allocation */ + 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 zl; + task_unlock(current); + + return true; } #endif +/* + * mempolicy_nodemask_intersects + * + * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default + * policy. Otherwise, check for intersection between mask and the policy + * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' + * policy, always return true since it may allocate elsewhere on fallback. + * + * Takes task_lock(tsk) to prevent freeing of its mempolicy. + */ +bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask) +{ + struct mempolicy *mempolicy; + bool ret = true; + + if (!mask) + return ret; + task_lock(tsk); + mempolicy = tsk->mempolicy; + if (!mempolicy) + goto out; + + switch (mempolicy->mode) { + case MPOL_PREFERRED: + /* + * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to + * allocate from, they may fallback to other nodes when oom. + * Thus, it's possible for tsk to have allocated memory from + * nodes in mask. + */ + break; + case MPOL_BIND: + case MPOL_INTERLEAVE: + ret = nodes_intersects(mempolicy->v.nodes, *mask); + break; + default: + BUG(); + } +out: + task_unlock(tsk); + return ret; +} + /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, @@ -1321,15 +1990,15 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct zonelist *zl; struct page *page; - zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp); + zl = node_zonelist(nid, gfp); page = __alloc_pages(gfp, order, zl); - if (page && page_zone(page) == zl->zones[0]) + if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0])) inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); return page; } /** - * alloc_page_vma - Allocate a page for a VMA. + * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. @@ -1338,6 +2007,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * + * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @@ -1351,35 +2021,36 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * Should be called with the mm_sem of the vma hold. */ struct page * -alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) +alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, int node) { - struct mempolicy *pol = get_vma_policy(current, vma, addr); - struct zonelist *zl; + struct mempolicy *pol; + struct page *page; + unsigned int cpuset_mems_cookie; - cpuset_update_task_memory_state(); +retry_cpuset: + pol = get_vma_policy(current, vma, addr); + cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(pol->policy == MPOL_INTERLEAVE)) { + if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); - if (unlikely(pol != &default_policy && - pol != current->mempolicy)) - __mpol_free(pol); /* finished with pol */ - return alloc_page_interleave(gfp, 0, nid); - } - zl = zonelist_policy(gfp, pol); - if (pol != &default_policy && pol != current->mempolicy) { - /* - * slow path: ref counted policy -- shared or vma - */ - struct page *page = __alloc_pages(gfp, 0, zl); - __mpol_free(pol); + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); + mpol_cond_put(pol); + page = alloc_page_interleave(gfp, order, nid); + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; } - /* - * fast path: default or task policy - */ - return __alloc_pages(gfp, 0, zl); + page = __alloc_pages_nodemask(gfp, order, + policy_zonelist(gfp, pol, node), + policy_nodemask(gfp, pol)); + if (unlikely(mpol_needs_cond_ref(pol))) + __mpol_put(pol); + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; } /** @@ -1403,88 +2074,108 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) */ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { - struct mempolicy *pol = current->mempolicy; + struct mempolicy *pol = get_task_policy(current); + struct page *page; + unsigned int cpuset_mems_cookie; - if ((gfp & __GFP_WAIT) && !in_interrupt()) - cpuset_update_task_memory_state(); if (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; - if (pol->policy == MPOL_INTERLEAVE) - return alloc_page_interleave(gfp, order, interleave_nodes(pol)); - return __alloc_pages(gfp, order, zonelist_policy(gfp, pol)); + +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + + /* + * No reference counting needed for current->mempolicy + * nor system default_policy + */ + if (pol->mode == MPOL_INTERLEAVE) + page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); + else + page = __alloc_pages_nodemask(gfp, order, + policy_zonelist(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); + + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + + return page; } EXPORT_SYMBOL(alloc_pages_current); +int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) +{ + struct mempolicy *pol = mpol_dup(vma_policy(src)); + + if (IS_ERR(pol)) + return PTR_ERR(pol); + dst->vm_policy = pol; + return 0; +} + /* - * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it + * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). + * + * current's mempolicy may be rebinded by the other task(the task that changes + * cpuset's mems), so we needn't do rebind work for current task. */ -/* Slow path of a mempolicy copy */ -struct mempolicy *__mpol_copy(struct mempolicy *old) +/* Slow path of a mempolicy duplicate */ +struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); + + /* task's mempolicy is protected by alloc_lock */ + if (old == current->mempolicy) { + task_lock(current); + *new = *old; + task_unlock(current); + } else + *new = *old; + if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); - mpol_rebind_policy(old, &mems); + if (new->flags & MPOL_F_REBINDING) + mpol_rebind_policy(new, &mems, MPOL_REBIND_STEP2); + else + mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - *new = *old; atomic_set(&new->refcnt, 1); - if (new->policy == MPOL_BIND) { - int sz = ksize(old->v.zonelist); - new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL); - if (!new->v.zonelist) { - kmem_cache_free(policy_cache, new); - return ERR_PTR(-ENOMEM); - } - } return new; } /* Slow path of a mempolicy comparison */ -int __mpol_equal(struct mempolicy *a, struct mempolicy *b) +bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) - return 0; - if (a->policy != b->policy) - return 0; - switch (a->policy) { - case MPOL_DEFAULT: - return 1; + return false; + if (a->mode != b->mode) + return false; + if (a->flags != b->flags) + return false; + if (mpol_store_user_nodemask(a)) + if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) + return false; + + switch (a->mode) { + case MPOL_BIND: + /* Fall through */ case MPOL_INTERLEAVE: - return nodes_equal(a->v.nodes, b->v.nodes); + return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: return a->v.preferred_node == b->v.preferred_node; - case MPOL_BIND: { - int i; - for (i = 0; a->v.zonelist->zones[i]; i++) - if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i]) - return 0; - return b->v.zonelist->zones[i] == NULL; - } default: BUG(); - return 0; + return false; } } -/* Slow path of a mpol destructor. */ -void __mpol_free(struct mempolicy *p) -{ - if (!atomic_dec_and_test(&p->refcnt)) - return; - if (p->policy == MPOL_BIND) - kfree(p->v.zonelist); - p->policy = MPOL_DEFAULT; - kmem_cache_free(policy_cache, p); -} - /* * Shared memory backing store policy support. * @@ -1547,7 +2238,7 @@ static void sp_insert(struct shared_policy *sp, struct sp_node *new) rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, - new->policy ? new->policy->policy : 0); + new->policy ? new->policy->mode : 0); } /* Find shared policy intersecting idx */ @@ -1569,25 +2260,132 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) return pol; } +static void sp_free(struct sp_node *n) +{ + mpol_put(n->policy); + kmem_cache_free(sn_cache, n); +} + +/** + * mpol_misplaced - check whether current page node is valid in policy + * + * @page: page to be checked + * @vma: vm area where page mapped + * @addr: virtual address where page mapped + * + * Lookup current policy node id for vma,addr and "compare to" page's + * node id. + * + * Returns: + * -1 - not misplaced, page is in the right node + * node - node id where the page should be + * + * Policy determination "mimics" alloc_page_vma(). + * Called from fault path where we know the vma and faulting address. + */ +int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) +{ + struct mempolicy *pol; + struct zone *zone; + int curnid = page_to_nid(page); + unsigned long pgoff; + int thiscpu = raw_smp_processor_id(); + int thisnid = cpu_to_node(thiscpu); + int polnid = -1; + int ret = -1; + + BUG_ON(!vma); + + pol = get_vma_policy(current, vma, addr); + if (!(pol->flags & MPOL_F_MOF)) + goto out; + + switch (pol->mode) { + case MPOL_INTERLEAVE: + BUG_ON(addr >= vma->vm_end); + BUG_ON(addr < vma->vm_start); + + pgoff = vma->vm_pgoff; + pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; + polnid = offset_il_node(pol, vma, pgoff); + break; + + case MPOL_PREFERRED: + if (pol->flags & MPOL_F_LOCAL) + polnid = numa_node_id(); + else + polnid = pol->v.preferred_node; + break; + + case MPOL_BIND: + /* + * allows binding to multiple nodes. + * use current page if in policy nodemask, + * else select nearest allowed node, if any. + * If no allowed nodes, use current [!misplaced]. + */ + if (node_isset(curnid, pol->v.nodes)) + goto out; + (void)first_zones_zonelist( + node_zonelist(numa_node_id(), GFP_HIGHUSER), + gfp_zone(GFP_HIGHUSER), + &pol->v.nodes, &zone); + polnid = zone->node; + break; + + default: + BUG(); + } + + /* Migrate the page towards the node whose CPU is referencing it */ + if (pol->flags & MPOL_F_MORON) { + polnid = thisnid; + + if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) + goto out; + } + + if (curnid != polnid) + ret = polnid; +out: + mpol_cond_put(pol); + + return ret; +} + static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); rb_erase(&n->nd, &sp->root); - mpol_free(n->policy); - kmem_cache_free(sn_cache, n); + sp_free(n); +} + +static void sp_node_init(struct sp_node *node, unsigned long start, + unsigned long end, struct mempolicy *pol) +{ + node->start = start; + node->end = end; + node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { - struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL); + struct sp_node *n; + struct mempolicy *newpol; + n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; - n->start = start; - n->end = end; - mpol_get(pol); - n->policy = pol; + + newpol = mpol_dup(pol); + if (IS_ERR(newpol)) { + kmem_cache_free(sn_cache, n); + return NULL; + } + newpol->flags |= MPOL_F_SHARED; + sp_node_init(n, start, end, newpol); + return n; } @@ -1595,7 +2393,10 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end, static int shared_policy_replace(struct shared_policy *sp, unsigned long start, unsigned long end, struct sp_node *new) { - struct sp_node *n, *new2 = NULL; + struct sp_node *n; + struct sp_node *n_new = NULL; + struct mempolicy *mpol_new = NULL; + int ret = 0; restart: spin_lock(&sp->lock); @@ -1611,16 +2412,16 @@ restart: } else { /* Old policy spanning whole new range. */ if (n->end > end) { - if (!new2) { - spin_unlock(&sp->lock); - new2 = sp_alloc(end, n->end, n->policy); - if (!new2) - return -ENOMEM; - goto restart; - } + if (!n_new) + goto alloc_new; + + *mpol_new = *n->policy; + atomic_set(&mpol_new->refcnt, 1); + sp_node_init(n_new, end, n->end, mpol_new); n->end = start; - sp_insert(sp, new2); - new2 = NULL; + sp_insert(sp, n_new); + n_new = NULL; + mpol_new = NULL; break; } else n->end = start; @@ -1632,34 +2433,74 @@ restart: if (new) sp_insert(sp, new); spin_unlock(&sp->lock); - if (new2) { - mpol_free(new2->policy); - kmem_cache_free(sn_cache, new2); - } - return 0; -} + ret = 0; -void mpol_shared_policy_init(struct shared_policy *info, int policy, - nodemask_t *policy_nodes) -{ - info->root = RB_ROOT; - spin_lock_init(&info->lock); +err_out: + if (mpol_new) + mpol_put(mpol_new); + if (n_new) + kmem_cache_free(sn_cache, n_new); - if (policy != MPOL_DEFAULT) { - struct mempolicy *newpol; + return ret; - /* Falls back to MPOL_DEFAULT on any error */ - newpol = mpol_new(policy, policy_nodes); - if (!IS_ERR(newpol)) { - /* Create pseudo-vma that contains just the policy */ - struct vm_area_struct pvma; +alloc_new: + spin_unlock(&sp->lock); + ret = -ENOMEM; + n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); + if (!n_new) + goto err_out; + mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); + if (!mpol_new) + goto err_out; + goto restart; +} - memset(&pvma, 0, sizeof(struct vm_area_struct)); - /* Policy covers entire file */ - pvma.vm_end = TASK_SIZE; - mpol_set_shared_policy(info, &pvma, newpol); - mpol_free(newpol); - } +/** + * mpol_shared_policy_init - initialize shared policy for inode + * @sp: pointer to inode shared policy + * @mpol: struct mempolicy to install + * + * Install non-NULL @mpol in inode's shared policy rb-tree. + * On entry, the current task has a reference on a non-NULL @mpol. + * This must be released on exit. + * This is called at get_inode() calls and we can use GFP_KERNEL. + */ +void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) +{ + int ret; + + sp->root = RB_ROOT; /* empty tree == default mempolicy */ + spin_lock_init(&sp->lock); + + if (mpol) { + struct vm_area_struct pvma; + struct mempolicy *new; + NODEMASK_SCRATCH(scratch); + + if (!scratch) + goto put_mpol; + /* contextualize the tmpfs mount point mempolicy */ + new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); + if (IS_ERR(new)) + goto free_scratch; /* no valid nodemask intersection */ + + task_lock(current); + ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); + task_unlock(current); + if (ret) + goto put_new; + + /* Create pseudo-vma that contains just the policy */ + memset(&pvma, 0, sizeof(struct vm_area_struct)); + pvma.vm_end = TASK_SIZE; /* policy covers entire file */ + mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ + +put_new: + mpol_put(new); /* drop initial ref */ +free_scratch: + NODEMASK_SCRATCH_FREE(scratch); +put_mpol: + mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } @@ -1670,10 +2511,11 @@ int mpol_set_shared_policy(struct shared_policy *info, struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); - pr_debug("set_shared_policy %lx sz %lu %d %lx\n", + pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", vma->vm_pgoff, - sz, npol? npol->policy : -1, - npol ? nodes_addr(npol->v.nodes)[0] : -1); + sz, npol ? npol->mode : -1, + npol ? npol->flags : -1, + npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -1682,7 +2524,7 @@ int mpol_set_shared_policy(struct shared_policy *info, } err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); if (err && new) - kmem_cache_free(sn_cache, new); + sp_free(new); return err; } @@ -1699,13 +2541,60 @@ void mpol_free_shared_policy(struct shared_policy *p) while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); - rb_erase(&n->nd, &p->root); - mpol_free(n->policy); - kmem_cache_free(sn_cache, n); + sp_delete(p, n); } spin_unlock(&p->lock); } +#ifdef CONFIG_NUMA_BALANCING +static int __initdata numabalancing_override; + +static void __init check_numabalancing_enable(void) +{ + bool numabalancing_default = false; + + if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) + numabalancing_default = true; + + /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ + if (numabalancing_override) + set_numabalancing_state(numabalancing_override == 1); + + if (nr_node_ids > 1 && !numabalancing_override) { + pr_info("%s automatic NUMA balancing. " + "Configure with numa_balancing= or the " + "kernel.numa_balancing sysctl", + numabalancing_default ? "Enabling" : "Disabling"); + set_numabalancing_state(numabalancing_default); + } +} + +static int __init setup_numabalancing(char *str) +{ + int ret = 0; + if (!str) + goto out; + + if (!strcmp(str, "enable")) { + numabalancing_override = 1; + ret = 1; + } else if (!strcmp(str, "disable")) { + numabalancing_override = -1; + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse numa_balancing=\n"); + + return ret; +} +__setup("numa_balancing=", setup_numabalancing); +#else +static inline void __init check_numabalancing_enable(void) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + /* assumes fs == KERNEL_DS */ void __init numa_policy_init(void) { @@ -1721,13 +2610,22 @@ void __init numa_policy_init(void) sizeof(struct sp_node), 0, SLAB_PANIC, NULL); + for_each_node(nid) { + preferred_node_policy[nid] = (struct mempolicy) { + .refcnt = ATOMIC_INIT(1), + .mode = MPOL_PREFERRED, + .flags = MPOL_F_MOF | MPOL_F_MORON, + .v = { .preferred_node = nid, }, + }; + } + /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); - for_each_node_state(nid, N_HIGH_MEMORY) { + for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ @@ -1745,310 +2643,226 @@ void __init numa_policy_init(void) if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); - if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes)) - printk("numa_policy_init: interleaving failed\n"); + if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) + pr_err("%s: interleaving failed\n", __func__); + + check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { - do_set_mempolicy(MPOL_DEFAULT, NULL); + do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } -/* Migrate a policy to a different set of nodes */ -static void mpol_rebind_policy(struct mempolicy *pol, - const nodemask_t *newmask) -{ - nodemask_t *mpolmask; - nodemask_t tmp; +/* + * Parse and format mempolicy from/to strings + */ - if (!pol) - return; - mpolmask = &pol->cpuset_mems_allowed; - if (nodes_equal(*mpolmask, *newmask)) - return; +/* + * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. + */ +static const char * const policy_modes[] = +{ + [MPOL_DEFAULT] = "default", + [MPOL_PREFERRED] = "prefer", + [MPOL_BIND] = "bind", + [MPOL_INTERLEAVE] = "interleave", + [MPOL_LOCAL] = "local", +}; - switch (pol->policy) { - case MPOL_DEFAULT: - break; - case MPOL_INTERLEAVE: - nodes_remap(tmp, pol->v.nodes, *mpolmask, *newmask); - pol->v.nodes = tmp; - *mpolmask = *newmask; - current->il_next = node_remap(current->il_next, - *mpolmask, *newmask); - break; - case MPOL_PREFERRED: - pol->v.preferred_node = node_remap(pol->v.preferred_node, - *mpolmask, *newmask); - *mpolmask = *newmask; - break; - case MPOL_BIND: { - nodemask_t nodes; - struct zone **z; - struct zonelist *zonelist; +#ifdef CONFIG_TMPFS +/** + * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. + * @str: string containing mempolicy to parse + * @mpol: pointer to struct mempolicy pointer, returned on success. + * + * Format of input: + * <mode>[=<flags>][:<nodelist>] + * + * On success, returns 0, else 1 + */ +int mpol_parse_str(char *str, struct mempolicy **mpol) +{ + struct mempolicy *new = NULL; + unsigned short mode; + unsigned short mode_flags; + nodemask_t nodes; + char *nodelist = strchr(str, ':'); + char *flags = strchr(str, '='); + int err = 1; + + if (nodelist) { + /* NUL-terminate mode or flags string */ + *nodelist++ = '\0'; + if (nodelist_parse(nodelist, nodes)) + goto out; + if (!nodes_subset(nodes, node_states[N_MEMORY])) + goto out; + } else nodes_clear(nodes); - for (z = pol->v.zonelist->zones; *z; z++) - node_set(zone_to_nid(*z), nodes); - nodes_remap(tmp, nodes, *mpolmask, *newmask); - nodes = tmp; - zonelist = bind_zonelist(&nodes); + if (flags) + *flags++ = '\0'; /* terminate mode string */ - /* If no mem, then zonelist is NULL and we keep old zonelist. - * If that old zonelist has no remaining mems_allowed nodes, - * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT. - */ + for (mode = 0; mode < MPOL_MAX; mode++) { + if (!strcmp(str, policy_modes[mode])) { + break; + } + } + if (mode >= MPOL_MAX) + goto out; - if (!IS_ERR(zonelist)) { - /* Good - got mem - substitute new zonelist */ - kfree(pol->v.zonelist); - pol->v.zonelist = zonelist; + switch (mode) { + case MPOL_PREFERRED: + /* + * Insist on a nodelist of one node only + */ + if (nodelist) { + char *rest = nodelist; + while (isdigit(*rest)) + rest++; + if (*rest) + goto out; } - *mpolmask = *newmask; break; - } - default: - BUG(); + case MPOL_INTERLEAVE: + /* + * Default to online nodes with memory if no nodelist + */ + if (!nodelist) + nodes = node_states[N_MEMORY]; + break; + case MPOL_LOCAL: + /* + * Don't allow a nodelist; mpol_new() checks flags + */ + if (nodelist) + goto out; + mode = MPOL_PREFERRED; break; + case MPOL_DEFAULT: + /* + * Insist on a empty nodelist + */ + if (!nodelist) + err = 0; + goto out; + case MPOL_BIND: + /* + * Insist on a nodelist + */ + if (!nodelist) + goto out; } -} - -/* - * Wrapper for mpol_rebind_policy() that just requires task - * pointer, and updates task mempolicy. - */ -void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) -{ - mpol_rebind_policy(tsk->mempolicy, new); -} + mode_flags = 0; + if (flags) { + /* + * Currently, we only support two mutually exclusive + * mode flags. + */ + if (!strcmp(flags, "static")) + mode_flags |= MPOL_F_STATIC_NODES; + else if (!strcmp(flags, "relative")) + mode_flags |= MPOL_F_RELATIVE_NODES; + else + goto out; + } -/* - * Rebind each vma in mm to new nodemask. - * - * Call holding a reference to mm. Takes mm->mmap_sem during call. - */ + new = mpol_new(mode, mode_flags, &nodes); + if (IS_ERR(new)) + goto out; -void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) -{ - struct vm_area_struct *vma; + /* + * Save nodes for mpol_to_str() to show the tmpfs mount options + * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. + */ + if (mode != MPOL_PREFERRED) + new->v.nodes = nodes; + else if (nodelist) + new->v.preferred_node = first_node(nodes); + else + new->flags |= MPOL_F_LOCAL; - down_write(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) - mpol_rebind_policy(vma->vm_policy, new); - up_write(&mm->mmap_sem); -} + /* + * Save nodes for contextualization: this will be used to "clone" + * the mempolicy in a specific context [cpuset] at a later time. + */ + new->w.user_nodemask = nodes; -/* - * Display pages allocated per node and memory policy via /proc. - */ + err = 0; -static const char * const policy_types[] = - { "default", "prefer", "bind", "interleave" }; +out: + /* Restore string for error message */ + if (nodelist) + *--nodelist = ':'; + if (flags) + *--flags = '='; + if (!err) + *mpol = new; + return err; +} +#endif /* CONFIG_TMPFS */ -/* - * Convert a mempolicy into a string. - * Returns the number of characters in buffer (if positive) - * or an error (negative) +/** + * mpol_to_str - format a mempolicy structure for printing + * @buffer: to contain formatted mempolicy string + * @maxlen: length of @buffer + * @pol: pointer to mempolicy to be formatted + * + * Convert @pol into a string. If @buffer is too short, truncate the string. + * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the + * longest flag, "relative", and to display at least a few node ids. */ -static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) +void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; - int l; - nodemask_t nodes; - int mode = pol ? pol->policy : MPOL_DEFAULT; + nodemask_t nodes = NODE_MASK_NONE; + unsigned short mode = MPOL_DEFAULT; + unsigned short flags = 0; + + if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { + mode = pol->mode; + flags = pol->flags; + } switch (mode) { case MPOL_DEFAULT: - nodes_clear(nodes); break; - case MPOL_PREFERRED: - nodes_clear(nodes); - node_set(pol->v.preferred_node, nodes); + if (flags & MPOL_F_LOCAL) + mode = MPOL_LOCAL; + else + node_set(pol->v.preferred_node, nodes); break; - case MPOL_BIND: - get_zonemask(pol, &nodes); - break; - case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; - default: - BUG(); - return -EFAULT; - } - - l = strlen(policy_types[mode]); - if (buffer + maxlen < p + l + 1) - return -ENOSPC; - - strcpy(p, policy_types[mode]); - p += l; - - if (!nodes_empty(nodes)) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = '='; - p += nodelist_scnprintf(p, buffer + maxlen - p, nodes); - } - return p - buffer; -} - -struct numa_maps { - unsigned long pages; - unsigned long anon; - unsigned long active; - unsigned long writeback; - unsigned long mapcount_max; - unsigned long dirty; - unsigned long swapcache; - unsigned long node[MAX_NUMNODES]; -}; - -static void gather_stats(struct page *page, void *private, int pte_dirty) -{ - struct numa_maps *md = private; - int count = page_mapcount(page); - - md->pages++; - if (pte_dirty || PageDirty(page)) - md->dirty++; - - if (PageSwapCache(page)) - md->swapcache++; - - if (PageActive(page)) - md->active++; - - if (PageWriteback(page)) - md->writeback++; - - if (PageAnon(page)) - md->anon++; - - if (count > md->mapcount_max) - md->mapcount_max = count; - - md->node[page_to_nid(page)]++; -} - -#ifdef CONFIG_HUGETLB_PAGE -static void check_huge_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct numa_maps *md) -{ - unsigned long addr; - struct page *page; - - for (addr = start; addr < end; addr += HPAGE_SIZE) { - pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK); - pte_t pte; - - if (!ptep) - continue; - - pte = *ptep; - if (pte_none(pte)) - continue; - - page = pte_page(pte); - if (!page) - continue; - - gather_stats(page, md, pte_dirty(*ptep)); + WARN_ON_ONCE(1); + snprintf(p, maxlen, "unknown"); + return; } -} -#else -static inline void check_huge_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct numa_maps *md) -{ -} -#endif - -int show_numa_map(struct seq_file *m, void *v) -{ - struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - struct numa_maps *md; - struct file *file = vma->vm_file; - struct mm_struct *mm = vma->vm_mm; - struct mempolicy *pol; - int n; - char buffer[50]; - if (!mm) - return 0; - - md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL); - if (!md) - return 0; - - pol = get_vma_policy(priv->task, vma, vma->vm_start); - mpol_to_str(buffer, sizeof(buffer), pol); - /* - * unref shared or other task's mempolicy - */ - if (pol != &default_policy && pol != current->mempolicy) - __mpol_free(pol); + p += snprintf(p, maxlen, "%s", policy_modes[mode]); - seq_printf(m, "%08lx %s", vma->vm_start, buffer); + if (flags & MPOL_MODE_FLAGS) { + p += snprintf(p, buffer + maxlen - p, "="); - if (file) { - seq_printf(m, " file="); - seq_path(m, &file->f_path, "\n\t= "); - } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { - seq_printf(m, " heap"); - } else if (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack) { - seq_printf(m, " stack"); + /* + * Currently, the only defined flags are mutually exclusive + */ + if (flags & MPOL_F_STATIC_NODES) + p += snprintf(p, buffer + maxlen - p, "static"); + else if (flags & MPOL_F_RELATIVE_NODES) + p += snprintf(p, buffer + maxlen - p, "relative"); } - if (is_vm_hugetlb_page(vma)) { - check_huge_range(vma, vma->vm_start, vma->vm_end, md); - seq_printf(m, " huge"); - } else { - check_pgd_range(vma, vma->vm_start, vma->vm_end, - &node_states[N_HIGH_MEMORY], MPOL_MF_STATS, md); + if (!nodes_empty(nodes)) { + p += snprintf(p, buffer + maxlen - p, ":"); + p += nodelist_scnprintf(p, buffer + maxlen - p, nodes); } - - if (!md->pages) - goto out; - - if (md->anon) - seq_printf(m," anon=%lu",md->anon); - - if (md->dirty) - seq_printf(m," dirty=%lu",md->dirty); - - if (md->pages != md->anon && md->pages != md->dirty) - seq_printf(m, " mapped=%lu", md->pages); - - if (md->mapcount_max > 1) - seq_printf(m, " mapmax=%lu", md->mapcount_max); - - if (md->swapcache) - seq_printf(m," swapcache=%lu", md->swapcache); - - if (md->active < md->pages && !is_vm_hugetlb_page(vma)) - seq_printf(m," active=%lu", md->active); - - if (md->writeback) - seq_printf(m," writeback=%lu", md->writeback); - - for_each_node_state(n, N_HIGH_MEMORY) - if (md->node[n]) - seq_printf(m, " N%d=%lu", n, md->node[n]); -out: - seq_putc(m, '\n'); - kfree(md); - - if (m->count < m->size) - m->version = (vma != priv->tail_vma) ? vma->vm_start : 0; - return 0; } |