diff options
Diffstat (limited to 'mm/mempolicy.c')
| -rw-r--r-- | mm/mempolicy.c | 1238 |
1 files changed, 712 insertions, 526 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4a57f135b76..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. @@ -65,6 +65,8 @@ kernel is not always grateful with that. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/highmem.h> @@ -75,7 +77,7 @@ #include <linux/cpuset.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> @@ -90,16 +92,18 @@ #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; @@ -111,12 +115,35 @@ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ -struct mempolicy default_policy = { +static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, }; +static struct mempolicy preferred_node_policy[MAX_NUMNODES]; + +static struct mempolicy *get_task_policy(struct task_struct *p) +{ + struct mempolicy *pol = p->mempolicy; + + 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); /* @@ -140,19 +167,7 @@ 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) @@ -212,9 +227,9 @@ static int mpol_set_nodemask(struct mempolicy *pol, /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ if (pol == NULL) return 0; - /* Check N_HIGH_MEMORY */ + /* Check N_MEMORY */ nodes_and(nsc->mask1, - cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]); + cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) @@ -249,12 +264,12 @@ 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)) return ERR_PTR(-EINVAL); - return NULL; /* simply delete any existing policy */ + return NULL; } VM_BUG_ON(!nodes); @@ -269,6 +284,10 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, (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); @@ -390,7 +409,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask, { if (!pol) return; - if (!mpol_store_user_nodemask(pol) && step == 0 && + if (!mpol_store_user_nodemask(pol) && step == MPOL_REBIND_ONCE && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; @@ -457,12 +476,14 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static void gather_stats(struct page *, void *, int pte_dirty); 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) @@ -484,17 +505,14 @@ 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)) 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; @@ -503,7 +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) @@ -514,16 +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 (check_pte_range(vma, pmd, addr, next, nodes, + 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 (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) @@ -534,16 +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) @@ -556,77 +613,128 @@ 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; + + 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); + 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_put(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; } @@ -642,22 +750,34 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long vmstart; unsigned long vmend; - vma = find_vma_prev(mm, start, &prev); + 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; vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + if (mpol_equal(vma_policy(vma), new_pol)) + continue; + + 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); + vma->anon_vma, vma->vm_file, pgoff, + new_pol); if (prev) { vma = prev; next = vma->vm_next; - continue; + 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); @@ -669,7 +789,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (err) goto out; } - err = policy_vma(vma, new_pol); + replace: + err = vma_replace_policy(vma, new_pol); if (err) goto out; } @@ -678,36 +799,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, return err; } -/* - * 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. - */ - -void mpol_fix_fork_child_flag(struct task_struct *p) -{ - if (p->mempolicy) - p->flags |= PF_MEMPOLICY; - else - p->flags &= ~PF_MEMPOLICY; -} - -static void mpol_set_task_struct_flag(void) -{ - mpol_fix_fork_child_flag(current); -} - /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) @@ -744,7 +835,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, } old = current->mempolicy; current->mempolicy = new; - mpol_set_task_struct_flag(); if (new && new->mode == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); @@ -911,7 +1001,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, static struct page *new_node_page(struct page *page, unsigned long node, int **x) { - return alloc_pages_exact_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); } /* @@ -924,20 +1018,24 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; - struct vm_area_struct *vma; nodes_clear(nmask); node_set(source, nmask); - vma = check_range(mm, mm->mmap->vm_start, mm->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 (IS_ERR(vma)) - return PTR_ERR(vma); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, 0); + err = migrate_pages(&pagelist, new_node_page, NULL, dest, + MIGRATE_SYNC, MR_SYSCALL); if (err) - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } return err; @@ -949,8 +1047,8 @@ 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) { int busy = 0; int err; @@ -962,7 +1060,7 @@ int do_migrate_pages(struct mm_struct *mm, 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; @@ -991,20 +1089,40 @@ int do_migrate_pages(struct mm_struct *mm, * 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 + * 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; @@ -1015,7 +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); @@ -1035,16 +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) @@ -1052,6 +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 */ @@ -1064,13 +1187,13 @@ 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; } @@ -1080,15 +1203,13 @@ static long do_mbind(unsigned long start, unsigned long len, 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)) + if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; @@ -1111,6 +1232,9 @@ static long do_mbind(unsigned long start, unsigned long len, 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 @@ -1120,7 +1244,7 @@ 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)) { @@ -1144,26 +1268,26 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = check_range(mm, start, end, nmask, + 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(mm, start, end, new); - if (!list_empty(&pagelist)) { - nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, 0); + 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_lru_pages(&pagelist); + putback_movable_pages(&pagelist); } - if (!err && nr_failed && (flags & MPOL_MF_STRICT)) + if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; } else - putback_lru_pages(&pagelist); + putback_movable_pages(&pagelist); up_write(&mm->mmap_sem); mpol_out: @@ -1239,7 +1363,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, - unsigned long, mode, unsigned long __user *, nmask, + unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned, flags) { nodemask_t nodes; @@ -1260,7 +1384,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, } /* Set the process memory policy */ -SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask, +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { int err; @@ -1307,19 +1431,16 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, 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); + rcu_read_unlock(); err = -ESRCH; goto out; } - mm = get_task_mm(task); - read_unlock(&tasklist_lock); + get_task_struct(task); err = -EINVAL; - if (!mm) - goto out; /* * Check if this process has the right to modify the specified @@ -1327,14 +1448,13 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - rcu_read_lock(); tcred = __task_cred(task); - if (cred->euid != tcred->suid && cred->euid != tcred->uid && - cred->uid != tcred->suid && cred->uid != tcred->uid && + 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(); @@ -1342,26 +1462,39 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, /* Is the user allowed to access the target nodes? */ 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, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); + + mmput(mm); out: - if (mm) - mmput(mm); NODEMASK_SCRATCH_FREE(scratch); return err; + +out_put: + put_task_struct(task); + goto out; + } @@ -1393,10 +1526,10 @@ SYSCALL_DEFINE5(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; @@ -1412,7 +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); @@ -1421,8 +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; @@ -1444,9 +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; @@ -1472,24 +1607,23 @@ 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. - * Current or other task's task mempolicy and non-shared vma policies - * are protected by the task's mmap_sem, which must be held for read by - * the caller. + * 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; + struct mempolicy *pol = get_task_policy(task); if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) { @@ -1497,14 +1631,68 @@ static struct mempolicy *get_vma_policy(struct task_struct *task, addr); if (vpol) pol = vpol; - } else if (vma->vm_policy) + } 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; return pol; } +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) +{ + 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 @@ -1513,7 +1701,7 @@ 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; @@ -1521,10 +1709,9 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) } /* Return a zonelist indicated by gfp for node representing a mempolicy */ -static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy) +static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, + int nd) { - int nd = numa_node_id(); - switch (policy->mode) { case MPOL_PREFERRED: if (!(policy->flags & MPOL_F_LOCAL)) @@ -1565,15 +1752,18 @@ static unsigned interleave_nodes(struct mempolicy *policy) /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. - * @policy must be protected by freeing by the caller. If @policy is - * the current task's mempolicy, this protection is implicit, as only the - * task can change it's policy. The system default policy requires no - * such protection. */ -unsigned slab_node(struct mempolicy *policy) +unsigned int mempolicy_slab_node(void) { + struct mempolicy *policy; + int node = numa_mem_id(); + + if (in_interrupt()) + return node; + + policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) - return numa_node_id(); + return node; switch (policy->mode) { case MPOL_PREFERRED: @@ -1593,11 +1783,11 @@ unsigned slab_node(struct mempolicy *policy) struct zonelist *zonelist; struct zone *zone; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); - zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0]; + zonelist = &NODE_DATA(node)->node_zonelists[0]; (void)first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes, &zone); - return zone ? zone->node : numa_node_id(); + return zone ? zone->node : node; } default: @@ -1612,7 +1802,7 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int c; - int nid = -1; + int nid = NUMA_NO_NODE; if (!nnodes) return numa_node_id(); @@ -1647,21 +1837,36 @@ 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 mempolicy - * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask + * @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. * - * Must be protected by get_mems_allowed() + * 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, @@ -1676,7 +1881,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, zl = node_zonelist(interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))), gfp_flags); } else { - zl = policy_zonelist(gfp_flags, *mpol); + zl = policy_zonelist(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } @@ -1793,7 +1998,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, } /** - * alloc_page_vma - Allocate a page for a VMA. + * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. @@ -1802,6 +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. * @@ -1815,38 +2021,35 @@ 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; + +retry_cpuset: + pol = get_vma_policy(current, vma, addr); + cpuset_mems_cookie = read_mems_allowed_begin(); - get_mems_allowed(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); - page = alloc_page_interleave(gfp, 0, nid); - put_mems_allowed(); + page = alloc_page_interleave(gfp, order, nid); + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; } - zl = policy_zonelist(gfp, pol); - if (unlikely(mpol_needs_cond_ref(pol))) { - /* - * slow path: ref counted shared policy - */ - struct page *page = __alloc_pages_nodemask(gfp, 0, - zl, policy_nodemask(gfp, pol)); + 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); - put_mems_allowed(); - return page; - } - /* - * fast path: default or task policy - */ - page = __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol)); - put_mems_allowed(); + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; return page; } @@ -1871,13 +2074,16 @@ 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 (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = read_mems_allowed_begin(); + /* * No reference counting needed for current->mempolicy * nor system default_policy @@ -1886,12 +2092,26 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol), policy_nodemask(gfp, pol)); - put_mems_allowed(); + 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_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() @@ -1919,7 +2139,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -1927,57 +2146,33 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } -/* - * If *frompol needs [has] an extra ref, copy *frompol to *tompol , - * eliminate the * MPOL_F_* flags that require conditional ref and - * [NOTE!!!] drop the extra ref. Not safe to reference *frompol directly - * after return. Use the returned value. - * - * Allows use of a mempolicy for, e.g., multiple allocations with a single - * policy lookup, even if the policy needs/has extra ref on lookup. - * shmem_readahead needs this. - */ -struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol, - struct mempolicy *frompol) -{ - if (!mpol_needs_cond_ref(frompol)) - return frompol; - - *tompol = *frompol; - tompol->flags &= ~MPOL_F_SHARED; /* copy doesn't need unref */ - __mpol_put(frompol); - return tompol; -} - /* 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; + return false; if (a->mode != b->mode) - return 0; + return false; if (a->flags != b->flags) - return 0; + return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) - return 0; + 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 && - a->flags == b->flags; + return a->v.preferred_node == b->v.preferred_node; default: BUG(); - return 0; + return false; } } @@ -2065,26 +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_put(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); - pol->flags |= MPOL_F_SHARED; /* for unref */ - 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; } @@ -2092,7 +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); @@ -2108,16 +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; @@ -2129,11 +2433,26 @@ restart: if (new) sp_insert(sp, new); spin_unlock(&sp->lock); - if (new2) { - mpol_put(new2->policy); - kmem_cache_free(sn_cache, new2); - } - return 0; + ret = 0; + +err_out: + if (mpol_new) + mpol_put(mpol_new); + if (n_new) + kmem_cache_free(sn_cache, n_new); + + return ret; + +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; } /** @@ -2196,7 +2515,7 @@ 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); @@ -2205,7 +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; } @@ -2222,13 +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_put(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) { @@ -2244,13 +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 */ @@ -2269,7 +2644,9 @@ void __init numa_policy_init(void) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) - printk("numa_policy_init: interleaving failed\n"); + pr_err("%s: interleaving failed\n", __func__); + + check_numabalancing_enable(); } /* Reset policy of current process to default */ @@ -2283,44 +2660,34 @@ void numa_default_policy(void) */ /* - * "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag - * Used only for mpol_parse_str() and mpol_to_str() + * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. */ -#define MPOL_LOCAL MPOL_MAX static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", - [MPOL_LOCAL] = "local" + [MPOL_LOCAL] = "local", }; #ifdef CONFIG_TMPFS /** - * mpol_parse_str - parse string to mempolicy + * 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. - * @no_context: flag whether to "contextualize" the mempolicy * * Format of input: * <mode>[=<flags>][:<nodelist>] * - * if @no_context is true, save the input nodemask in w.user_nodemask in - * the returned mempolicy. This will be used to "clone" the mempolicy in - * a specific context [cpuset] at a later time. Used to parse tmpfs mpol - * mount option. Note that if 'static' or 'relative' mode flags were - * specified, the input nodemask will already have been saved. Saving - * it again is redundant, but safe. - * * On success, returns 0, else 1 */ -int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) +int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode; - unsigned short uninitialized_var(mode_flags); + unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); @@ -2331,7 +2698,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; - if (!nodes_subset(nodes, node_states[N_HIGH_MEMORY])) + if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); @@ -2339,12 +2706,12 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) if (flags) *flags++ = '\0'; /* terminate mode string */ - for (mode = 0; mode <= MPOL_LOCAL; mode++) { + for (mode = 0; mode < MPOL_MAX; mode++) { if (!strcmp(str, policy_modes[mode])) { break; } } - if (mode > MPOL_LOCAL) + if (mode >= MPOL_MAX) goto out; switch (mode) { @@ -2365,7 +2732,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) * Default to online nodes with memory if no nodelist */ if (!nodelist) - nodes = node_states[N_HIGH_MEMORY]; + nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* @@ -2408,24 +2775,23 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) if (IS_ERR(new)) goto out; - if (no_context) { - /* save for contextualization */ - new->w.user_nodemask = nodes; - } else { - int ret; - NODEMASK_SCRATCH(scratch); - if (scratch) { - task_lock(current); - ret = mpol_set_nodemask(new, &nodes, scratch); - task_unlock(current); - } else - ret = -ENOMEM; - NODEMASK_SCRATCH_FREE(scratch); - if (ret) { - mpol_put(new); - goto out; - } - } + /* + * 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; + + /* + * 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; + err = 0; out: @@ -2445,67 +2811,46 @@ out: * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted - * @no_context: "context free" mempolicy - use nodemask in w.user_nodemask * - * Convert a mempolicy into a string. - * Returns the number of characters in buffer (if positive) - * or an error (negative) + * 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. */ -int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context) +void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; - int l; - nodemask_t nodes; - unsigned short mode; - unsigned short flags = pol ? pol->flags : 0; - - /* - * Sanity check: room for longest mode, flag and some nodes - */ - VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16); + nodemask_t nodes = NODE_MASK_NONE; + unsigned short mode = MPOL_DEFAULT; + unsigned short flags = 0; - if (!pol || pol == &default_policy) - mode = MPOL_DEFAULT; - else + 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); if (flags & MPOL_F_LOCAL) - mode = MPOL_LOCAL; /* pseudo-policy */ + mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; - case MPOL_BIND: - /* Fall through */ case MPOL_INTERLEAVE: - if (no_context) - nodes = pol->w.user_nodemask; - else - nodes = pol->v.nodes; + nodes = pol->v.nodes; break; - default: - BUG(); + WARN_ON_ONCE(1); + snprintf(p, maxlen, "unknown"); + return; } - l = strlen(policy_modes[mode]); - if (buffer + maxlen < p + l + 1) - return -ENOSPC; - - strcpy(p, policy_modes[mode]); - p += l; + p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = '='; + p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive @@ -2517,166 +2862,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context) } if (!nodes_empty(nodes)) { - if (buffer + maxlen < p + 2) - return -ENOSPC; - *p++ = ':'; + p += snprintf(p, buffer + maxlen - 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) || PageUnevictable(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; - struct hstate *h = hstate_vma(vma); - unsigned long sz = huge_page_size(h); - - for (addr = start; addr < end; addr += sz) { - pte_t *ptep = huge_pte_offset(vma->vm_mm, - addr & huge_page_mask(h)); - 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)); - } -} -#else -static inline void check_huge_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct numa_maps *md) -{ -} -#endif - -/* - * Display pages allocated per node and memory policy via /proc. - */ -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, 0); - mpol_cond_put(pol); - - seq_printf(m, "%08lx %s", vma->vm_start, buffer); - - 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"); - } - - 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 (!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; } |