diff options
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r-- | mm/mempolicy.c | 303 |
1 files changed, 134 insertions, 169 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b5d95bf1025d..e32360e90274 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -121,8 +121,7 @@ enum zone_type policy_zone = 0; */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ - .mode = MPOL_PREFERRED, - .flags = MPOL_F_LOCAL, + .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; @@ -194,18 +193,17 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - 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); + if (nodes_empty(*nodes)) + return -EINVAL; + + nodes_clear(pol->nodes); + node_set(first_node(*nodes), pol->nodes); return 0; } @@ -213,15 +211,14 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->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. + * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. @@ -231,33 +228,31 @@ static int mpol_set_nodemask(struct mempolicy *pol, { int ret; - /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ - if (pol == NULL) + /* + * Default (pol==NULL) resp. local memory policies are not a + * subject of any remapping. They also do not need any special + * constructor. + */ + if (!pol || pol->mode == MPOL_LOCAL) 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; - } + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); + else + nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (nodes) - ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; else - ret = mpol_ops[pol->mode].create(pol, NULL); + pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; + + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } @@ -290,13 +285,14 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); + + mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_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); @@ -330,7 +326,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { - nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed, + nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } @@ -338,31 +334,13 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) if (nodes_empty(tmp)) tmp = *nodes; - pol->v.nodes = tmp; + pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - 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; - } + pol->w.cpuset_mems_allowed = *nodes; } /* @@ -376,7 +354,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol) return; - if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && + if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; @@ -427,6 +405,9 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, + [MPOL_LOCAL] = { + .rebind = mpol_rebind_default, + }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, @@ -458,7 +439,8 @@ static inline bool queue_pages_required(struct page *page, /* * queue_pages_pmd() has four possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. huge zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. @@ -482,8 +464,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); - __split_huge_pmd(walk->vma, pmd, addr, false, NULL); - ret = 2; + walk->action = ACTION_CONTINUE; goto out; } if (!queue_pages_required(page, qp)) @@ -510,7 +491,8 @@ out: * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already @@ -917,12 +899,11 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - *nodes = p->v.nodes; - break; case MPOL_PREFERRED: - if (!(p->flags & MPOL_F_LOCAL)) - node_set(p->v.preferred_node, *nodes); - /* else return empty node mask for local allocation */ + *nodes = p->nodes; + break; + case MPOL_LOCAL: + /* return empty node mask for local allocation */ break; default: BUG(); @@ -1007,7 +988,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { - *policy = next_node_in(current->il_prev, pol->v.nodes); + *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; @@ -1460,26 +1441,38 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } +/* Basic parameter sanity check used by both mbind() and set_mempolicy() */ +static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) +{ + *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; + + return 0; +} + static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { + unsigned short mode_flags; nodemask_t nodes; + int lmode = mode; int err; - unsigned short mode_flags; start = untagged_addr(start); - 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 = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; + err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_mbind(start, len, mode, mode_flags, &nodes, flags); + + return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, @@ -1493,20 +1486,20 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { - int err; + unsigned short mode_flags; nodemask_t nodes; - unsigned short flags; + int lmode = mode; + int err; + + err = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; - 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, flags, &nodes); + + return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, @@ -1863,14 +1856,14 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* - * if policy->v.nodes has movable memory only, + * if policy->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]. + * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies - * policy->v.nodes has movable memory only. + * policy->nodes has movable memory only. */ - if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; @@ -1885,8 +1878,8 @@ 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; + cpuset_nodemask_valid_mems_allowed(&policy->nodes)) + return &policy->nodes; return NULL; } @@ -1894,9 +1887,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { - if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) - nd = policy->v.preferred_node; - else { + if (policy->mode == MPOL_PREFERRED) { + nd = first_node(policy->nodes); + } else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the @@ -1914,7 +1907,7 @@ static unsigned interleave_nodes(struct mempolicy *policy) unsigned next; struct task_struct *me = current; - next = next_node_in(me->il_prev, policy->v.nodes); + next = next_node_in(me->il_prev, policy->nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; @@ -1933,15 +1926,12 @@ unsigned int mempolicy_slab_node(void) return node; policy = current->mempolicy; - if (!policy || policy->flags & MPOL_F_LOCAL) + if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: - /* - * handled MPOL_F_LOCAL above - */ - return policy->v.preferred_node; + return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); @@ -1957,9 +1947,11 @@ unsigned int mempolicy_slab_node(void) enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, - &policy->v.nodes); + &policy->nodes); return z->zone ? zone_to_nid(z->zone) : node; } + case MPOL_LOCAL: + return node; default: BUG(); @@ -1968,12 +1960,12 @@ unsigned int mempolicy_slab_node(void) /* * Do static interleaving for a VMA with known offset @n. Returns the n'th - * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the + * node in pol->nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { - unsigned nnodes = nodes_weight(pol->v.nodes); + unsigned nnodes = nodes_weight(pol->nodes); unsigned target; int i; int nid; @@ -1981,9 +1973,9 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; - nid = first_node(pol->v.nodes); + nid = first_node(pol->nodes); for (i = 0; i < target; i++) - nid = next_node(nid, pol->v.nodes); + nid = next_node(nid, pol->nodes); return nid; } @@ -2039,7 +2031,7 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) - *nodemask = &(*mpol)->v.nodes; + *nodemask = &(*mpol)->nodes; } return nid; } @@ -2063,7 +2055,6 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; - int nid; if (!(mask && current->mempolicy)) return false; @@ -2072,16 +2063,13 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: - if (mempolicy->flags & MPOL_F_LOCAL) - nid = numa_node_id(); - else - nid = mempolicy->v.preferred_node; - init_nodemask_of_node(mask, nid); - break; - case MPOL_BIND: case MPOL_INTERLEAVE: - *mask = mempolicy->v.nodes; + *mask = mempolicy->nodes; + break; + + case MPOL_LOCAL: + init_nodemask_of_node(mask, numa_node_id()); break; default: @@ -2094,16 +2082,16 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) #endif /* - * mempolicy_nodemask_intersects + * mempolicy_in_oom_domain * - * 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 'preferred' or 'local' - * policy, always return true since it may allocate elsewhere on fallback. + * If tsk's mempolicy is "bind", check for intersection between mask and + * the policy nodemask. Otherwise, return true for all other policies + * including "interleave", as a tsk with "interleave" policy may have + * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ -bool mempolicy_nodemask_intersects(struct task_struct *tsk, +bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; @@ -2111,29 +2099,13 @@ bool mempolicy_nodemask_intersects(struct task_struct *tsk, 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: + if (mempolicy && mempolicy->mode == MPOL_BIND) + ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); + return ret; } @@ -2204,8 +2176,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; + if (pol->mode == MPOL_PREFERRED) + hpage_node = first_node(pol->nodes); nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { @@ -2338,12 +2310,10 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: - /* a's ->flags is the same as b's */ - if (a->flags & MPOL_F_LOCAL) - return true; - return a->v.preferred_node == b->v.preferred_node; + return !!nodes_equal(a->nodes, b->nodes); + case MPOL_LOCAL: + return true; default: BUG(); return false; @@ -2481,16 +2451,17 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_PREFERRED: - if (pol->flags & MPOL_F_LOCAL) - polnid = numa_node_id(); - else - polnid = pol->v.preferred_node; + polnid = first_node(pol->nodes); + break; + + case MPOL_LOCAL: + polnid = numa_node_id(); break; case MPOL_BIND: /* Optimize placement among multiple nodes via NUMA balancing */ if (pol->flags & MPOL_F_MORON) { - if (node_isset(thisnid, pol->v.nodes)) + if (node_isset(thisnid, pol->nodes)) break; goto out; } @@ -2501,12 +2472,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ - if (node_isset(curnid, pol->v.nodes)) + if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), - &pol->v.nodes); + &pol->nodes); polnid = zone_to_nid(z->zone); break; @@ -2709,7 +2680,7 @@ 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] : NUMA_NO_NODE); + npol ? nodes_addr(npol->nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -2807,7 +2778,7 @@ void __init numa_policy_init(void) .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, - .v = { .preferred_node = nid, }, + .nodes = nodemask_of_node(nid), }; } @@ -2851,9 +2822,6 @@ void numa_default_policy(void) * Parse and format mempolicy from/to strings */ -/* - * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. - */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", @@ -2931,7 +2899,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) */ if (nodelist) goto out; - mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* @@ -2970,12 +2937,14 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) * 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; + if (mode != MPOL_PREFERRED) { + new->nodes = nodes; + } else if (nodelist) { + nodes_clear(new->nodes); + node_set(first_node(nodes), new->nodes); + } else { + new->mode = MPOL_LOCAL; + } /* * Save nodes for contextualization: this will be used to "clone" @@ -3021,16 +2990,12 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) switch (mode) { case MPOL_DEFAULT: + case MPOL_LOCAL: break; case MPOL_PREFERRED: - if (flags & MPOL_F_LOCAL) - mode = MPOL_LOCAL; - else - node_set(pol->v.preferred_node, nodes); - break; case MPOL_BIND: case MPOL_INTERLEAVE: - nodes = pol->v.nodes; + nodes = pol->nodes; break; default: WARN_ON_ONCE(1); |