diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig | 10 | ||||
| -rw-r--r-- | lib/Kconfig.kasan | 23 | ||||
| -rw-r--r-- | lib/maple_tree.c | 1088 | ||||
| -rw-r--r-- | lib/stackdepot.c | 461 | ||||
| -rw-r--r-- | lib/test_maple_tree.c | 331 | ||||
| -rw-r--r-- | lib/test_meminit.c | 2 | ||||
| -rw-r--r-- | lib/ubsan.c | 7 |
7 files changed, 1213 insertions, 709 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 3ea1c830efab..5ddda7c2ed9b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -713,10 +713,20 @@ config ARCH_STACKWALK config STACKDEPOT bool select STACKTRACE + help + Stack depot: stack trace storage that avoids duplication config STACKDEPOT_ALWAYS_INIT bool select STACKDEPOT + help + Always initialize stack depot during early boot + +config STACKDEPOT_MAX_FRAMES + int "Maximum number of frames in trace saved in stack depot" + range 1 256 + default 64 + depends on STACKDEPOT config REF_TRACKER bool diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 97e1fdbb5910..e6eda054ab27 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -129,7 +129,7 @@ endchoice choice prompt "Instrumentation type" depends on KASAN_GENERIC || KASAN_SW_TAGS - default KASAN_OUTLINE + default KASAN_INLINE if !ARCH_DISABLE_KASAN_INLINE config KASAN_OUTLINE bool "Outline instrumentation" @@ -202,4 +202,25 @@ config KASAN_MODULE_TEST A part of the KASAN test suite that is not integrated with KUnit. Incompatible with Hardware Tag-Based KASAN. +config KASAN_EXTRA_INFO + bool "Record and report more information" + depends on KASAN + help + Record and report more information to help us find the cause of the + bug and to help us correlate the error with other system events. + + Currently, the CPU number and timestamp are additionally + recorded for each heap block at allocation and free time, and + 8 bytes will be added to each metadata structure that records + allocation or free information. + + In Generic KASAN, each kmalloc-8 and kmalloc-16 object will add + 16 bytes of additional memory consumption, and each kmalloc-32 + object will add 8 bytes of additional memory consumption, not + affecting other larger objects. + + In SW_TAGS KASAN and HW_TAGS KASAN, depending on the stack_ring_size + boot parameter, it will add 8 * stack_ring_size bytes of additional + memory consumption. + endif # KASAN diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 684689457d77..6f241bb38799 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4,6 +4,8 @@ * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> + * Copyright (c) 2023 ByteDance + * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* @@ -14,8 +16,8 @@ * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to - * indicate that the tree is specifying ranges, Pivots may appear in the - * subtree with an entry attached to the value where as keys are unique to a + * indicate that the tree is specifying ranges. Pivots may appear in the + * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * @@ -165,6 +167,11 @@ static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } +static inline void mt_free_one(struct maple_node *node) +{ + kmem_cache_free(maple_node_cache, node); +} + static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); @@ -205,23 +212,29 @@ static unsigned int mas_mt_height(struct ma_state *mas) return mt_height(mas->tree); } -static inline enum maple_type mte_node_type(const struct maple_enode *entry) +static inline unsigned int mt_attr(struct maple_tree *mt) +{ + return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; +} + +static __always_inline enum maple_type mte_node_type( + const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } -static inline bool ma_is_dense(const enum maple_type type) +static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } -static inline bool ma_is_leaf(const enum maple_type type) +static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } -static inline bool mte_is_leaf(const struct maple_enode *entry) +static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } @@ -230,60 +243,50 @@ static inline bool mte_is_leaf(const struct maple_enode *entry) * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ -static inline bool mt_is_reserved(const void *entry) +static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } -static inline void mas_set_err(struct ma_state *mas, long err) +static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); + mas->status = ma_error; } -static inline bool mas_is_ptr(const struct ma_state *mas) +static __always_inline bool mas_is_ptr(const struct ma_state *mas) { - return mas->node == MAS_ROOT; + return mas->status == ma_root; } -static inline bool mas_is_start(const struct ma_state *mas) +static __always_inline bool mas_is_start(const struct ma_state *mas) { - return mas->node == MAS_START; + return mas->status == ma_start; } -bool mas_is_err(struct ma_state *mas) +static __always_inline bool mas_is_none(const struct ma_state *mas) { - return xa_is_err(mas->node); + return mas->status == ma_none; } -static __always_inline bool mas_is_overflow(struct ma_state *mas) +static __always_inline bool mas_is_paused(const struct ma_state *mas) { - if (unlikely(mas->node == MAS_OVERFLOW)) - return true; - - return false; + return mas->status == ma_pause; } -static __always_inline bool mas_is_underflow(struct ma_state *mas) +static __always_inline bool mas_is_overflow(struct ma_state *mas) { - if (unlikely(mas->node == MAS_UNDERFLOW)) - return true; - - return false; + return mas->status == ma_overflow; } -static inline bool mas_searchable(struct ma_state *mas) +static inline bool mas_is_underflow(struct ma_state *mas) { - if (mas_is_none(mas)) - return false; - - if (mas_is_ptr(mas)) - return false; - - return true; + return mas->status == ma_underflow; } -static inline struct maple_node *mte_to_node(const struct maple_enode *entry) +static __always_inline struct maple_node *mte_to_node( + const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } @@ -360,12 +363,12 @@ static inline bool mte_has_null(const struct maple_enode *node) return (unsigned long)node & MAPLE_ENODE_NULL; } -static inline bool ma_is_root(struct maple_node *node) +static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } -static inline bool mte_is_root(const struct maple_enode *node) +static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } @@ -375,7 +378,7 @@ static inline bool mas_is_root_limits(const struct ma_state *mas) return !mas->min && mas->max == ULONG_MAX; } -static inline bool mt_is_alloc(struct maple_tree *mt) +static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } @@ -514,11 +517,12 @@ void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, * * Return: The slot in the parent node where @enode resides. */ -static inline unsigned int mte_parent_slot(const struct maple_enode *enode) +static __always_inline +unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; - if (val & MA_ROOT_PARENT) + if (unlikely(val & MA_ROOT_PARENT)) return 0; /* @@ -534,7 +538,8 @@ static inline unsigned int mte_parent_slot(const struct maple_enode *enode) * * Return: The parent maple node. */ -static inline struct maple_node *mte_parent(const struct maple_enode *enode) +static __always_inline +struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); @@ -546,7 +551,7 @@ static inline struct maple_node *mte_parent(const struct maple_enode *enode) * * Return: true if dead, false otherwise. */ -static inline bool ma_dead_node(const struct maple_node *node) +static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; @@ -562,7 +567,7 @@ static inline bool ma_dead_node(const struct maple_node *node) * * Return: true if dead, false otherwise. */ -static inline bool mte_dead_node(const struct maple_enode *enode) +static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; @@ -680,35 +685,6 @@ static inline unsigned long *ma_gaps(struct maple_node *node, } /* - * mas_pivot() - Get the pivot at @piv of the maple encoded node. - * @mas: The maple state. - * @piv: The pivot. - * - * Return: the pivot at @piv of @mn. - */ -static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv) -{ - struct maple_node *node = mas_mn(mas); - enum maple_type type = mte_node_type(mas->node); - - if (MAS_WARN_ON(mas, piv >= mt_pivots[type])) { - mas_set_err(mas, -EIO); - return 0; - } - - switch (type) { - case maple_arange_64: - return node->ma64.pivot[piv]; - case maple_range_64: - case maple_leaf_64: - return node->mr64.pivot[piv]; - case maple_dense: - return 0; - } - return 0; -} - -/* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots @@ -718,7 +694,7 @@ static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv) * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ -static inline unsigned long +static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { @@ -759,7 +735,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, BUG_ON(piv >= mt_pivots[type]); switch (type) { - default: case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; @@ -783,7 +758,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { - default: case maple_arange_64: return mn->ma64.slot; case maple_range_64: @@ -792,6 +766,8 @@ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) case maple_dense: return mn->slot; } + + return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) @@ -800,20 +776,20 @@ static inline bool mt_write_locked(const struct maple_tree *mt) lockdep_is_held(&mt->ma_lock); } -static inline bool mt_locked(const struct maple_tree *mt) +static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } -static inline void *mt_slot(const struct maple_tree *mt, +static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } -static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, - unsigned char offset) +static __always_inline void *mt_slot_locked(struct maple_tree *mt, + void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } @@ -825,8 +801,8 @@ static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, * * Return: The entry stored in @slots at the @offset. */ -static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, - unsigned char offset) +static __always_inline void *mas_slot_locked(struct ma_state *mas, + void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } @@ -839,8 +815,8 @@ static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, * * Return: The entry stored in @slots at the @offset */ -static inline void *mas_slot(struct ma_state *mas, void __rcu **slots, - unsigned char offset) +static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, + unsigned char offset) { return mt_slot(mas->tree, slots, offset); } @@ -851,7 +827,7 @@ static inline void *mas_slot(struct ma_state *mas, void __rcu **slots, * * Return: The pointer to the root of the tree */ -static inline void *mas_root(struct ma_state *mas) +static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } @@ -954,10 +930,8 @@ static inline unsigned char ma_meta_end(struct maple_node *mn, /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node - * @mt: The maple node type */ -static inline unsigned char ma_meta_gap(struct maple_node *mn, - enum maple_type mt) +static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } @@ -1112,14 +1086,16 @@ static int mas_ascend(struct ma_state *mas) return 0; } - if (!mas->min) + min = 0; + max = ULONG_MAX; + if (!mas->offset) { + min = mas->min; set_min = true; + } if (mas->max == ULONG_MAX) set_max = true; - min = 0; - max = ULONG_MAX; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); @@ -1258,6 +1234,7 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; + BUG_ON(!allocated); WARN_ON(!allocated); } @@ -1363,14 +1340,14 @@ static void mas_node_count(struct ma_state *mas, int count) * mas_start() - Sets up maple state for operations. * @mas: The maple state. * - * If mas->node == MAS_START, then set the min, max and depth to + * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: - * - If mas->node is an error or not MAS_START, return NULL. - * - If it's an empty tree: NULL & mas->node == MAS_NONE - * - If it's a single entry: The entry & mas->node == MAS_ROOT - * - If it's a tree: NULL & mas->node == safe root node. + * - If mas->node is an error or not mas_start, return NULL. + * - If it's an empty tree: NULL & mas->status == ma_none + * - If it's a single entry: The entry & mas->status == mas_root + * - If it's a tree: NULL & mas->status == safe root node. */ static inline struct maple_enode *mas_start(struct ma_state *mas) { @@ -1386,6 +1363,7 @@ retry: /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; + mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) @@ -1396,13 +1374,14 @@ retry: /* empty tree */ if (unlikely(!root)) { - mas->node = MAS_NONE; + mas->node = NULL; + mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ - mas->node = MAS_ROOT; + mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ @@ -1425,10 +1404,8 @@ retry: * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ -static inline unsigned char ma_data_end(struct maple_node *node, - enum maple_type type, - unsigned long *pivots, - unsigned long max) +static __always_inline unsigned char ma_data_end(struct maple_node *node, + enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; @@ -1541,6 +1518,9 @@ static unsigned long mas_leaf_max_gap(struct ma_state *mas) gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; + + if (max_gap > pivots[max_piv] - mas->min) + return max_gap; } for (; i <= max_piv; i++) { @@ -1608,7 +1588,7 @@ static inline unsigned long mas_max_gap(struct ma_state *mas) node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); - offset = ma_meta_gap(node, mt); + offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } @@ -1639,7 +1619,7 @@ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); - meta_offset = ma_meta_gap(pnode, pmt); + meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; @@ -1987,27 +1967,13 @@ complete: /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. - * @mas: The maple state * @node: The maple node - * @pivots: pointer to the maple node pivots * @mt: The maple type - * @end: The assumed end - * - * Note, end may be incremented within this function but not modified at the - * source. This is fine since the metadata is the last thing to be stored in a - * node during a write. + * @end: The node end */ -static inline void mas_leaf_set_meta(struct ma_state *mas, - struct maple_node *node, unsigned long *pivots, +static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { - /* There is no room for metadata already */ - if (mt_pivots[mt] <= end) - return; - - if (pivots[end] && pivots[end] < mas->max) - end++; - if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } @@ -2064,7 +2030,7 @@ static inline void mab_mas_cp(struct maple_big_node *b_node, ma_set_meta(node, mt, offset, end); } else { - mas_leaf_set_meta(mas, node, pivots, mt, end); + mas_leaf_set_meta(node, mt, end); } } @@ -2152,11 +2118,11 @@ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, } slot = offset_end + 1; - if (slot > wr_mas->node_end) + if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ - mas_mab_cp(mas, slot, wr_mas->node_end + 1, b_node, ++b_end); + mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; @@ -2211,19 +2177,21 @@ static inline bool mas_next_sibling(struct ma_state *mas) } /* - * mte_node_or_node() - Return the encoded node or MAS_NONE. + * mte_node_or_none() - Set the enode and state. * @enode: The encoded maple node. * - * Shorthand to avoid setting %NULLs in the tree or maple_subtree_state. - * - * Return: @enode or MAS_NONE + * Set the node to the enode and the status. */ -static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode) +static inline void mas_node_or_none(struct ma_state *mas, + struct maple_enode *enode) { - if (enode) - return enode; - - return ma_enode_ptr(MAS_NONE); + if (enode) { + mas->node = enode; + mas->status = ma_active; + } else { + mas->node = NULL; + mas->status = ma_none; + } } /* @@ -2245,8 +2213,8 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); - count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type, - wr_mas->pivots, mas->max); + count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, + wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) @@ -2535,7 +2503,7 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast, } /* - * mas_topiary_node() - Dispose of a singe node + * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @enode: The encoded maple node * @in_rcu: If the tree is in rcu mode @@ -2543,13 +2511,15 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast, * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, - struct maple_enode *enode, bool in_rcu) + struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; + struct maple_enode *enode; - if (enode == MAS_NONE) + if (mas_is_none(tmp_mas)) return; + enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) @@ -2589,8 +2559,8 @@ static inline void mas_topiary_replace(struct ma_state *mas, /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; - tmp[1].node = MAS_NONE; - tmp[2].node = MAS_NONE; + tmp[1].status = ma_none; + tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { @@ -2610,7 +2580,7 @@ static inline void mas_topiary_replace(struct ma_state *mas, break; while (n < 3) - tmp_next[n++].node = MAS_NONE; + tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; @@ -2623,8 +2593,8 @@ static inline void mas_topiary_replace(struct ma_state *mas, tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; - tmp[1].node = MAS_NONE; - tmp[2].node = MAS_NONE; + tmp[1].status = ma_none; + tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; @@ -2639,7 +2609,7 @@ static inline void mas_topiary_replace(struct ma_state *mas, if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); - tmp_next[n].node = MAS_NONE; + tmp_next[n].status = ma_none; } else { n++; } @@ -2650,16 +2620,16 @@ static inline void mas_topiary_replace(struct ma_state *mas, break; while (n < 3) - tmp_next[n++].node = MAS_NONE; + tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { - mas_topiary_node(mas, tmp[i].node, in_rcu); + mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) - mas_topiary_node(mas, tmp[i].node, in_rcu); + mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } @@ -2698,9 +2668,9 @@ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, { bool new_lmax = true; - mast->l->node = mte_node_or_none(left); - mast->m->node = mte_node_or_none(middle); - mast->r->node = mte_node_or_none(right); + mas_node_or_none(mast->l, left); + mas_node_or_none(mast->m, middle); + mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { @@ -2796,32 +2766,29 @@ static inline void *mtree_range_walk(struct ma_state *mas) min = mas->min; max = mas->max; do { - offset = 0; last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); - if (unlikely(ma_dead_node(node))) - goto dead_node; - - if (pivots[offset] >= mas->index) { - prev_max = max; - prev_min = min; - max = pivots[offset]; + prev_min = min; + prev_max = max; + if (pivots[0] >= mas->index) { + offset = 0; + max = pivots[0]; goto next; } - do { + offset = 1; + while (offset < end) { + if (pivots[offset] >= mas->index) { + max = pivots[offset]; + break; + } offset++; - } while ((offset < end) && (pivots[offset] < mas->index)); + } - prev_min = min; min = pivots[offset - 1] + 1; - prev_max = max; - if (likely(offset < end && pivots[offset])) - max = pivots[offset]; - next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); @@ -2829,6 +2796,7 @@ next: goto dead_node; } while (!ma_is_leaf(type)); + mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; @@ -2879,7 +2847,7 @@ static int mas_spanning_rebalance(struct ma_state *mas, mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; - l_mas.node = r_mas.node = m_mas.node = MAS_NONE; + l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && @@ -3167,7 +3135,7 @@ done: * @mas: The maple state * @height: The height of the tree in case it's a new root. */ -static inline bool mas_split_final_node(struct maple_subtree_state *mast, +static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; @@ -3191,7 +3159,6 @@ static inline bool mas_split_final_node(struct maple_subtree_state *mast, mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; - return true; } /* @@ -3406,7 +3373,6 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; - /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; @@ -3495,6 +3461,7 @@ static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas, mas_replace_node(wr_mas->mas, old_enode); reuse_node: mas_update_gap(wr_mas->mas); + wr_mas->mas->end = b_end; return 1; } @@ -3521,6 +3488,7 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); + mas->status = ma_active; if (mas->index) { if (contents) { @@ -3553,7 +3521,7 @@ static inline void mas_store_root(struct ma_state *mas, void *entry) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); - mas->node = MAS_START; + mas->status = ma_start; } } @@ -3730,23 +3698,17 @@ static inline void *mtree_lookup_walk(struct ma_state *mas) enum maple_type type; void __rcu **slots; unsigned char end; - unsigned long max; next = mas->node; - max = ULONG_MAX; do { - offset = 0; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); - end = ma_data_end(node, type, pivots, max); - if (unlikely(ma_dead_node(node))) - goto dead_node; + end = mt_pivots[type]; + offset = 0; do { - if (pivots[offset] >= mas->index) { - max = pivots[offset]; + if (pivots[offset] >= mas->index) break; - } } while (++offset < end); slots = ma_slots(node, type); @@ -3785,7 +3747,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); - mas->node = MAS_START; + mas->status = ma_start; goto done; } @@ -3798,6 +3760,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); + mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; @@ -3891,10 +3854,10 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ - mas_store_b_node(&l_wr_mas, &b_node, l_wr_mas.node_end); + mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node. */ - if (r_mas.offset <= r_wr_mas.node_end) - mas_mab_cp(&r_mas, r_mas.offset, r_wr_mas.node_end, + if (r_mas.offset <= r_mas.end) + mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; @@ -3936,7 +3899,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) - mas_bulk_rebalance(mas, wr_mas->node_end, wr_mas->type); + mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { @@ -3972,12 +3935,12 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, * this range wrote to the end of the node or it overwrote the rest of * the data */ - if (offset_end > wr_mas->node_end) + if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ - copy_size = wr_mas->node_end - offset_end + 1; + copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, @@ -3987,7 +3950,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, dst_pivots[new_end] = mas->max; done: - mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end); + mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; @@ -3998,6 +3961,7 @@ done: } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); + mas->end = new_end; return true; } @@ -4063,10 +4027,10 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && - (wr_mas->node_end != wr_mas->offset_end) && + (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; - if (wr_mas->offset_end == wr_mas->node_end) + if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; @@ -4091,11 +4055,11 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { - while ((wr_mas->offset_end < wr_mas->node_end) && + while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; - if (wr_mas->offset_end < wr_mas->node_end) + if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; @@ -4107,7 +4071,7 @@ static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; - unsigned char new_end = wr_mas->node_end + 2; + unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) @@ -4141,10 +4105,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, if (mt_in_rcu(mas->tree)) return false; - if (mas->offset != wr_mas->node_end) - return false; - - end = wr_mas->node_end; + end = mas->end; if (mas->offset != end) return false; @@ -4178,6 +4139,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); + mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return true; } @@ -4195,7 +4157,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas) trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); - mas_commit_b_node(wr_mas, &b_node, wr_mas->node_end); + mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end); } static inline void mas_wr_modify(struct ma_wr_state *wr_mas) @@ -4223,7 +4185,7 @@ static inline void mas_wr_modify(struct ma_wr_state *wr_mas) if (mas_wr_append(wr_mas, new_end)) return; - if (new_end == wr_mas->node_end && mas_wr_slot_store(wr_mas)) + if (new_end == mas->end && mas_wr_slot_store(wr_mas)) return; if (mas_wr_node_store(wr_mas, new_end)) @@ -4328,7 +4290,7 @@ exists: } -static inline void mas_rewalk(struct ma_state *mas, unsigned long index) +static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); @@ -4337,7 +4299,7 @@ retry: goto retry; } -static inline bool mas_rewalk_if_dead(struct ma_state *mas, +static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { @@ -4349,14 +4311,16 @@ static inline bool mas_rewalk_if_dead(struct ma_state *mas, /* * mas_prev_node() - Find the prev non-null entry at the same level in the - * tree. The prev value will be mas->node[mas->offset] or MAS_NONE. + * tree. The prev value will be mas->node[mas->offset] or the status will be + * ma_none. * @mas: The maple state * @min: The lower limit to search * - * The prev node value will be mas->node[mas->offset] or MAS_NONE. + * The prev node value will be mas->node[mas->offset] or the status will be + * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ -static inline int mas_prev_node(struct ma_state *mas, unsigned long min) +static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; @@ -4416,13 +4380,14 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) if (unlikely(mte_dead_node(mas->node))) return 1; + mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; - mas->node = MAS_NONE; + mas->status = ma_underflow; return 0; } @@ -4436,8 +4401,7 @@ no_entry: * * Return: The entry in the previous slot which is possibly NULL */ -static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty, - bool set_underflow) +static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; @@ -4470,13 +4434,16 @@ again: mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { + if (mas->index <= min) + goto underflow; + if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } - if (mas_is_none(mas)) - goto underflow; + if (WARN_ON_ONCE(mas_is_underflow(mas))) + return NULL; mas->last = mas->max; node = mas_mn(mas); @@ -4490,12 +4457,15 @@ again: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; + if (likely(entry)) return entry; if (!empty) { - if (mas->index <= min) - goto underflow; + if (mas->index <= min) { + mas->status = ma_underflow; + return NULL; + } goto again; } @@ -4503,8 +4473,7 @@ again: return entry; underflow: - if (set_underflow) - mas->node = MAS_UNDERFLOW; + mas->status = ma_underflow; return NULL; } @@ -4513,28 +4482,30 @@ underflow: * @mas: The maple state * @max: The maximum pivot value to check. * - * The next value will be mas->node[mas->offset] or MAS_NONE. + * The next value will be mas->node[mas->offset] or the status will have + * overflowed. * Return: 1 on dead node, 0 otherwise. */ -static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, - unsigned long max) +static int mas_next_node(struct ma_state *mas, struct maple_node *node, + unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; + struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) - goto no_entry; + goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) - goto no_entry; + goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) @@ -4574,6 +4545,10 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); + tmp = mte_to_node(enode); + mt = mte_node_type(enode); + pivots = ma_pivots(tmp, mt); + mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; @@ -4581,11 +4556,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, mas->min = min; return 0; -no_entry: +overflow: if (unlikely(ma_dead_node(node))) return 1; - mas->node = MAS_NONE; + mas->status = ma_overflow; return 0; } @@ -4600,15 +4575,13 @@ no_entry: * * Return: The entry in the next slot which is possibly NULL */ -static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty, - bool set_overflow) +static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; - unsigned char data_end; unsigned long save_point = mas->last; void *entry; @@ -4616,42 +4589,45 @@ retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); - data_end = ma_data_end(node, type, pivots, mas->max); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { - if (likely(mas->offset < data_end)) + if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else - goto overflow; + pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; - if (pivot >= max) - goto overflow; + if (pivot >= max) { /* Was at the limit, next will extend beyond */ + mas->status = ma_overflow; + return NULL; + } } - if (likely(mas->offset < data_end)) { + if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; - if (likely(mas->offset < data_end)) + if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { + if (mas->last >= max) { + mas->status = ma_overflow; + return NULL; + } + if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } - if (WARN_ON_ONCE(mas_is_none(mas))) { - mas->node = MAS_OVERFLOW; + if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; - goto overflow; - } mas->offset = 0; mas->index = mas->min; @@ -4669,21 +4645,18 @@ again: if (entry) return entry; + if (!empty) { - if (mas->last >= max) - goto overflow; + if (mas->last >= max) { + mas->status = ma_overflow; + return NULL; + } mas->index = mas->last + 1; - /* Node cannot end on NULL, so it's safe to short-cut here */ goto again; } return entry; - -overflow: - if (set_overflow) - mas->node = MAS_OVERFLOW; - return NULL; } /* @@ -4702,11 +4675,11 @@ overflow: static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { - mas->node = MAS_OVERFLOW; + mas->status = ma_overflow; return NULL; } - return mas_next_slot(mas, limit, false, true); + return mas_next_slot(mas, limit, false); } /* @@ -4874,7 +4847,7 @@ done: * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If - * mas->node is MAS_NONE, reset to MAS_START. + * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ @@ -4883,7 +4856,7 @@ void *mas_walk(struct ma_state *mas) void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) - mas->node = MAS_START; + mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { @@ -4899,7 +4872,7 @@ retry: mas->index = 1; mas->last = ULONG_MAX; - mas->node = MAS_NONE; + mas->status = ma_none; return NULL; } @@ -5026,6 +4999,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned char offset; unsigned long *pivots; enum maple_type mt; + struct maple_node *node; if (min > max) return -EINVAL; @@ -5056,12 +5030,14 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; + node = mas_mn(mas); mt = mte_node_type(mas->node); - pivots = ma_pivots(mas_mn(mas), mt); + pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; + mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); @@ -5122,6 +5098,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, mas->last = max; mas->index = mas->last - size + 1; + mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); @@ -5503,7 +5480,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) node_size = mas_wr_new_end(&wr_mas); /* Slot store, does not require additional nodes */ - if (node_size == wr_mas.node_end) { + if (node_size == mas->end) { /* reuse node */ if (!mt_in_rcu(mas->tree)) return 0; @@ -5518,7 +5495,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) goto ask_now; } - /* New root needs a singe node */ + /* New root needs a single node */ if (unlikely(mte_is_root(mas->node))) goto ask_now; @@ -5566,7 +5543,7 @@ void mas_destroy(struct ma_state *mas) mas_start(mas); mtree_range_walk(mas); - end = mas_data_end(mas) + 1; + end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); @@ -5584,7 +5561,7 @@ void mas_destroy(struct ma_state *mas) mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } - kmem_cache_free(maple_node_cache, node); + mt_free_one(ma_mnode_ptr(node)); total--; } @@ -5654,33 +5631,46 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) } EXPORT_SYMBOL_GPL(mas_expected_entries); -static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, +static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { - mas->node = MAS_OVERFLOW; + mas->status = ma_overflow; return true; } - if (mas_is_active(mas)) + switch (mas->status) { + case ma_active: return false; - - if (mas_is_none(mas) || mas_is_paused(mas)) { - mas->node = MAS_START; - } else if (mas_is_overflow(mas)) { + case ma_none: + fallthrough; + case ma_pause: + mas->status = ma_start; + fallthrough; + case ma_start: + mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ + break; + case ma_overflow: /* Overflowed before, but the max changed */ - mas->node = MAS_START; - } else if (mas_is_underflow(mas)) { - mas->node = MAS_START; + mas->status = ma_active; + break; + case ma_underflow: + /* The user expects the mas to be one before where it is */ + mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; + break; + case ma_root: + break; + case ma_error: + return true; } - if (mas_is_start(mas)) - *entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ + if (likely(mas_is_active(mas))) /* Fast path */ + return false; if (mas_is_ptr(mas)) { *entry = NULL; @@ -5690,7 +5680,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, } mas->index = 1; mas->last = ULONG_MAX; - mas->node = MAS_NONE; + mas->status = ma_none; return true; } @@ -5719,7 +5709,7 @@ void *mas_next(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false, true); + return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); @@ -5742,7 +5732,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true, true); + return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); @@ -5770,37 +5760,48 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) } EXPORT_SYMBOL_GPL(mt_next); -static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, - void **entry) +static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { - mas->node = MAS_UNDERFLOW; + mas->status = ma_underflow; return true; } - if (mas_is_active(mas)) + switch (mas->status) { + case ma_active: return false; - - if (mas_is_overflow(mas)) { - mas->node = MAS_START; + case ma_start: + break; + case ma_none: + fallthrough; + case ma_pause: + mas->status = ma_start; + break; + case ma_underflow: + /* underflowed before but the min changed */ + mas->status = ma_active; + break; + case ma_overflow: + /* User expects mas to be one after where it is */ + mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; - } - - if (mas_is_none(mas) || mas_is_paused(mas)) { - mas->node = MAS_START; - } else if (mas_is_underflow(mas)) { - /* underflowed before but the min changed */ - mas->node = MAS_START; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { - if (!mas->index) - goto none; + if (!mas->index) { + mas->status = ma_none; + return true; + } mas->index = mas->last = 0; *entry = mas_root(mas); return true; @@ -5810,7 +5811,7 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; - mas->node = MAS_ROOT; + mas->status = ma_root; *entry = mas_root(mas); return true; } @@ -5818,10 +5819,6 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, } return false; - -none: - mas->node = MAS_NONE; - return true; } /** @@ -5830,7 +5827,7 @@ none: * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. - * Will reset mas to MAS_START if the node is MAS_NONE. Will stop on not + * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. @@ -5842,7 +5839,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, false, true); + return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); @@ -5853,7 +5850,7 @@ EXPORT_SYMBOL_GPL(mas_prev); * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. - * Will reset mas to MAS_START if the node is MAS_NONE. Will stop on not + * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. @@ -5865,7 +5862,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, true, true); + return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); @@ -5908,7 +5905,8 @@ EXPORT_SYMBOL_GPL(mt_prev); */ void mas_pause(struct ma_state *mas) { - mas->node = MAS_PAUSE; + mas->status = ma_pause; + mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); @@ -5920,35 +5918,54 @@ EXPORT_SYMBOL_GPL(mas_pause); * * Returns: True if entry is the answer, false otherwise. */ -static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, - void **entry) +static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { - if (mas_is_active(mas)) { + switch (mas->status) { + case ma_active: if (mas->last < max) return false; - return true; - } - - if (mas_is_paused(mas)) { + case ma_start: + break; + case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; - mas->node = MAS_START; - } else if (mas_is_none(mas)) { + mas->status = ma_start; + break; + case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; - mas->node = MAS_START; - } else if (mas_is_overflow(mas) || mas_is_underflow(mas)) { - if (mas->index > max) { - mas->node = MAS_OVERFLOW; + mas->status = ma_start; + break; + case ma_underflow: + /* mas is pointing at entry before unable to go lower */ + if (unlikely(mas->index >= max)) { + mas->status = ma_overflow; return true; } - mas->node = MAS_START; + mas->status = ma_active; + *entry = mas_walk(mas); + if (*entry) + return true; + break; + case ma_overflow: + if (unlikely(mas->last >= max)) + return true; + + mas->status = ma_active; + *entry = mas_walk(mas); + if (*entry) + return true; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) { @@ -5962,12 +5979,11 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, } - if (unlikely(!mas_searchable(mas))) { - if (unlikely(mas_is_ptr(mas))) - goto ptr_out_of_range; + if (unlikely(mas_is_ptr(mas))) + goto ptr_out_of_range; + if (unlikely(mas_is_none(mas))) return true; - } if (mas->index == max) return true; @@ -5975,7 +5991,7 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, return false; ptr_out_of_range: - mas->node = MAS_NONE; + mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; @@ -5989,7 +6005,7 @@ ptr_out_of_range: * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ @@ -6001,7 +6017,10 @@ void *mas_find(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false, false); + entry = mas_next_slot(mas, max, false); + /* Ignore overflow */ + mas->status = ma_active; + return entry; } EXPORT_SYMBOL_GPL(mas_find); @@ -6013,7 +6032,7 @@ EXPORT_SYMBOL_GPL(mas_find); * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ @@ -6025,7 +6044,7 @@ void *mas_find_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true, false); + return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); @@ -6037,36 +6056,48 @@ EXPORT_SYMBOL_GPL(mas_find_range); * * Returns: True if entry is the answer, false otherwise. */ -static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, +static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { - if (mas_is_active(mas)) { - if (mas->index > min) - return false; - - return true; - } - if (mas_is_paused(mas)) { + switch (mas->status) { + case ma_active: + goto active; + case ma_start: + break; + case ma_pause: if (unlikely(mas->index <= min)) { - mas->node = MAS_NONE; + mas->status = ma_underflow; return true; } - mas->node = MAS_START; mas->last = --mas->index; - } else if (mas_is_none(mas)) { + mas->status = ma_start; + break; + case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; - mas->node = MAS_START; - } else if (mas_is_underflow(mas) || mas_is_overflow(mas)) { - if (mas->last <= min) { - mas->node = MAS_UNDERFLOW; + mas->status = ma_start; + break; + case ma_overflow: /* user expects the mas to be one after where it is */ + if (unlikely(mas->index <= min)) { + mas->status = ma_underflow; return true; } - mas->node = MAS_START; + mas->status = ma_active; + break; + case ma_underflow: /* user expects the mas to be one before where it is */ + if (unlikely(mas->index <= min)) + return true; + + mas->status = ma_active; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) { @@ -6079,29 +6110,28 @@ static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, return true; } - if (unlikely(!mas_searchable(mas))) { - if (mas_is_ptr(mas)) - goto none; + if (unlikely(mas_is_ptr(mas))) + goto none; - if (mas_is_none(mas)) { - /* - * Walked to the location, and there was nothing so the - * previous location is 0. - */ - mas->last = mas->index = 0; - mas->node = MAS_ROOT; - *entry = mas_root(mas); - return true; - } + if (unlikely(mas_is_none(mas))) { + /* + * Walked to the location, and there was nothing so the previous + * location is 0. + */ + mas->last = mas->index = 0; + mas->status = ma_root; + *entry = mas_root(mas); + return true; } +active: if (mas->index < min) return true; return false; none: - mas->node = MAS_NONE; + mas->status = ma_none; return true; } @@ -6114,7 +6144,7 @@ none: * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ @@ -6126,7 +6156,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, false, false); + return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); @@ -6140,7 +6170,7 @@ EXPORT_SYMBOL_GPL(mas_find_rev); * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ @@ -6152,7 +6182,7 @@ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, true, false); + return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); @@ -6172,8 +6202,8 @@ void *mas_erase(struct ma_state *mas) void *entry; MA_WR_STATE(wr_mas, mas, NULL); - if (mas_is_none(mas) || mas_is_paused(mas)) - mas->node = MAS_START; + if (!mas_is_active(mas) || !mas_is_start(mas)) + mas->status = ma_start; /* Retry unnecessary when holding the write lock. */ entry = mas_state_walk(mas); @@ -6218,7 +6248,7 @@ bool mas_nomem(struct ma_state *mas, gfp_t gfp) if (!mas_allocated(mas)) return false; - mas->node = MAS_START; + mas->status = ma_start; return true; } @@ -6476,6 +6506,278 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index) } EXPORT_SYMBOL(mtree_erase); +/* + * mas_dup_free() - Free an incomplete duplication of a tree. + * @mas: The maple state of a incomplete tree. + * + * The parameter @mas->node passed in indicates that the allocation failed on + * this node. This function frees all nodes starting from @mas->node in the + * reverse order of mas_dup_build(). There is no need to hold the source tree + * lock at this time. + */ +static void mas_dup_free(struct ma_state *mas) +{ + struct maple_node *node; + enum maple_type type; + void __rcu **slots; + unsigned char count, i; + + /* Maybe the first node allocation failed. */ + if (mas_is_none(mas)) + return; + + while (!mte_is_root(mas->node)) { + mas_ascend(mas); + if (mas->offset) { + mas->offset--; + do { + mas_descend(mas); + mas->offset = mas_data_end(mas); + } while (!mte_is_leaf(mas->node)); + + mas_ascend(mas); + } + + node = mte_to_node(mas->node); + type = mte_node_type(mas->node); + slots = ma_slots(node, type); + count = mas_data_end(mas) + 1; + for (i = 0; i < count; i++) + ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; + mt_free_bulk(count, slots); + } + + node = mte_to_node(mas->node); + mt_free_one(node); +} + +/* + * mas_copy_node() - Copy a maple node and replace the parent. + * @mas: The maple state of source tree. + * @new_mas: The maple state of new tree. + * @parent: The parent of the new node. + * + * Copy @mas->node to @new_mas->node, set @parent to be the parent of + * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. + */ +static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, + struct maple_pnode *parent) +{ + struct maple_node *node = mte_to_node(mas->node); + struct maple_node *new_node = mte_to_node(new_mas->node); + unsigned long val; + + /* Copy the node completely. */ + memcpy(new_node, node, sizeof(struct maple_node)); + /* Update the parent node pointer. */ + val = (unsigned long)node->parent & MAPLE_NODE_MASK; + new_node->parent = ma_parent_ptr(val | (unsigned long)parent); +} + +/* + * mas_dup_alloc() - Allocate child nodes for a maple node. + * @mas: The maple state of source tree. + * @new_mas: The maple state of new tree. + * @gfp: The GFP_FLAGS to use for allocations. + * + * This function allocates child nodes for @new_mas->node during the duplication + * process. If memory allocation fails, @mas is set to -ENOMEM. + */ +static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, + gfp_t gfp) +{ + struct maple_node *node = mte_to_node(mas->node); + struct maple_node *new_node = mte_to_node(new_mas->node); + enum maple_type type; + unsigned char request, count, i; + void __rcu **slots; + void __rcu **new_slots; + unsigned long val; + + /* Allocate memory for child nodes. */ + type = mte_node_type(mas->node); + new_slots = ma_slots(new_node, type); + request = mas_data_end(mas) + 1; + count = mt_alloc_bulk(gfp, request, (void **)new_slots); + if (unlikely(count < request)) { + memset(new_slots, 0, request * sizeof(void *)); + mas_set_err(mas, -ENOMEM); + return; + } + + /* Restore node type information in slots. */ + slots = ma_slots(node, type); + for (i = 0; i < count; i++) { + val = (unsigned long)mt_slot_locked(mas->tree, slots, i); + val &= MAPLE_NODE_MASK; + ((unsigned long *)new_slots)[i] |= val; + } +} + +/* + * mas_dup_build() - Build a new maple tree from a source tree + * @mas: The maple state of source tree, need to be in MAS_START state. + * @new_mas: The maple state of new tree, need to be in MAS_START state. + * @gfp: The GFP_FLAGS to use for allocations. + * + * This function builds a new tree in DFS preorder. If the memory allocation + * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the + * last node. mas_dup_free() will free the incomplete duplication of a tree. + * + * Note that the attributes of the two trees need to be exactly the same, and the + * new tree needs to be empty, otherwise -EINVAL will be set in @mas. + */ +static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, + gfp_t gfp) +{ + struct maple_node *node; + struct maple_pnode *parent = NULL; + struct maple_enode *root; + enum maple_type type; + + if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || + unlikely(!mtree_empty(new_mas->tree))) { + mas_set_err(mas, -EINVAL); + return; + } + + root = mas_start(mas); + if (mas_is_ptr(mas) || mas_is_none(mas)) + goto set_new_tree; + + node = mt_alloc_one(gfp); + if (!node) { + new_mas->status = ma_none; + mas_set_err(mas, -ENOMEM); + return; + } + + type = mte_node_type(mas->node); + root = mt_mk_node(node, type); + new_mas->node = root; + new_mas->min = 0; + new_mas->max = ULONG_MAX; + root = mte_mk_root(root); + while (1) { + mas_copy_node(mas, new_mas, parent); + if (!mte_is_leaf(mas->node)) { + /* Only allocate child nodes for non-leaf nodes. */ + mas_dup_alloc(mas, new_mas, gfp); + if (unlikely(mas_is_err(mas))) + return; + } else { + /* + * This is the last leaf node and duplication is + * completed. + */ + if (mas->max == ULONG_MAX) + goto done; + + /* This is not the last leaf node and needs to go up. */ + do { + mas_ascend(mas); + mas_ascend(new_mas); + } while (mas->offset == mas_data_end(mas)); + + /* Move to the next subtree. */ + mas->offset++; + new_mas->offset++; + } + + mas_descend(mas); + parent = ma_parent_ptr(mte_to_node(new_mas->node)); + mas_descend(new_mas); + mas->offset = 0; + new_mas->offset = 0; + } +done: + /* Specially handle the parent of the root node. */ + mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); +set_new_tree: + /* Make them the same height */ + new_mas->tree->ma_flags = mas->tree->ma_flags; + rcu_assign_pointer(new_mas->tree->ma_root, root); +} + +/** + * __mt_dup(): Duplicate an entire maple tree + * @mt: The source maple tree + * @new: The new maple tree + * @gfp: The GFP_FLAGS to use for allocations + * + * This function duplicates a maple tree in Depth-First Search (DFS) pre-order + * traversal. It uses memcpy() to copy nodes in the source tree and allocate + * new child nodes in non-leaf nodes. The new node is exactly the same as the + * source node except for all the addresses stored in it. It will be faster than + * traversing all elements in the source tree and inserting them one by one into + * the new tree. + * The user needs to ensure that the attributes of the source tree and the new + * tree are the same, and the new tree needs to be an empty tree, otherwise + * -EINVAL will be returned. + * Note that the user needs to manually lock the source tree and the new tree. + * + * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If + * the attributes of the two trees are different or the new tree is not an empty + * tree. + */ +int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) +{ + int ret = 0; + MA_STATE(mas, mt, 0, 0); + MA_STATE(new_mas, new, 0, 0); + + mas_dup_build(&mas, &new_mas, gfp); + if (unlikely(mas_is_err(&mas))) { + ret = xa_err(mas.node); + if (ret == -ENOMEM) + mas_dup_free(&new_mas); + } + + return ret; +} +EXPORT_SYMBOL(__mt_dup); + +/** + * mtree_dup(): Duplicate an entire maple tree + * @mt: The source maple tree + * @new: The new maple tree + * @gfp: The GFP_FLAGS to use for allocations + * + * This function duplicates a maple tree in Depth-First Search (DFS) pre-order + * traversal. It uses memcpy() to copy nodes in the source tree and allocate + * new child nodes in non-leaf nodes. The new node is exactly the same as the + * source node except for all the addresses stored in it. It will be faster than + * traversing all elements in the source tree and inserting them one by one into + * the new tree. + * The user needs to ensure that the attributes of the source tree and the new + * tree are the same, and the new tree needs to be an empty tree, otherwise + * -EINVAL will be returned. + * + * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If + * the attributes of the two trees are different or the new tree is not an empty + * tree. + */ +int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) +{ + int ret = 0; + MA_STATE(mas, mt, 0, 0); + MA_STATE(new_mas, new, 0, 0); + + mas_lock(&new_mas); + mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); + mas_dup_build(&mas, &new_mas, gfp); + mas_unlock(&mas); + if (unlikely(mas_is_err(&mas))) { + ret = xa_err(mas.node); + if (ret == -ENOMEM) + mas_dup_free(&new_mas); + } + + mas_unlock(&new_mas); + return ret; +} +EXPORT_SYMBOL(mtree_dup); + /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree @@ -6490,7 +6792,7 @@ void __mt_destroy(struct maple_tree *mt) if (xa_is_node(root)) mte_destroy_walk(root, mt); - mt->ma_flags = 0; + mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); @@ -6549,7 +6851,7 @@ retry: if (entry) goto unlock; - while (mas_searchable(&mas) && (mas.last < max)) { + while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; @@ -6631,26 +6933,6 @@ unsigned int mt_nr_allocated(void) return kmem_cache_nr_allocated(maple_node_cache); } -/* - * mas_dead_node() - Check if the maple state is pointing to a dead node. - * @mas: The maple state - * @index: The index to restore in @mas. - * - * Used in test code. - * Return: 1 if @mas has been reset to MAS_START, 0 otherwise. - */ -static inline int mas_dead_node(struct ma_state *mas, unsigned long index) -{ - if (unlikely(!mas_searchable(mas) || mas_is_start(mas))) - return 0; - - if (likely(!mte_dead_node(mas->node))) - return 0; - - mas_rewalk(mas, index); - return 1; -} - void mt_cache_shrink(void) { } @@ -6689,11 +6971,11 @@ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { - struct maple_enode *p = MAS_NONE, *mn = mas->node; + struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); - if (!mas_is_none(mas)) + if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) @@ -6706,7 +6988,7 @@ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); - } while (!mas_is_none(mas)); + } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; @@ -6729,7 +7011,6 @@ static void mt_dump_range(unsigned long min, unsigned long max, else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; - default: case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); @@ -6769,7 +7050,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; - default: case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } @@ -6799,7 +7079,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; - default: case mt_dump_dec: pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); @@ -6824,7 +7103,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; - default: case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } @@ -6835,7 +7113,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; - default: case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } @@ -6976,7 +7253,8 @@ static void mas_validate_gaps(struct ma_state *mas) counted: if (mt == maple_arange_64) { - offset = ma_meta_gap(node, mt); + MT_BUG_ON(mas->tree, !gaps); + offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset %p[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); @@ -6988,7 +7266,6 @@ counted: MT_BUG_ON(mas->tree, 1); } - MT_BUG_ON(mas->tree, !gaps); for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap %p[%u] beyond node limit != 0\n", @@ -7166,7 +7443,7 @@ static void mt_validate_nulls(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); mas_start(&mas); - if (mas_is_none(&mas) || (mas.node == MAS_ROOT)) + if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) @@ -7183,7 +7460,7 @@ static void mt_validate_nulls(struct maple_tree *mt) last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); - if (mas_is_none(&mas)) + if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), @@ -7192,7 +7469,7 @@ static void mt_validate_nulls(struct maple_tree *mt) offset++; } - } while (!mas_is_none(&mas)); + } while (!mas_is_overflow(&mas)); } /* @@ -7207,13 +7484,13 @@ void mt_validate(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); rcu_read_lock(); mas_start(&mas); - if (!mas_searchable(&mas)) + if (!mas_is_active(&mas)) goto done; while (!mte_is_leaf(mas.node)) mas_descend(&mas); - while (!mas_is_none(&mas)) { + while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && @@ -7238,16 +7515,35 @@ EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node); - if (mas_is_none(mas)) - pr_err("(MAS_NONE) "); - else if (mas_is_ptr(mas)) - pr_err("(MAS_ROOT) "); - else if (mas_is_start(mas)) - pr_err("(MAS_START) "); - else if (mas_is_paused(mas)) - pr_err("(MAS_PAUSED) "); - - pr_err("[%u] index=%lx last=%lx\n", mas->offset, mas->index, mas->last); + switch (mas->status) { + case ma_active: + pr_err("(ma_active)"); + break; + case ma_none: + pr_err("(ma_none)"); + break; + case ma_root: + pr_err("(ma_root)"); + break; + case ma_start: + pr_err("(ma_start) "); + break; + case ma_pause: + pr_err("(ma_pause) "); + break; + case ma_overflow: + pr_err("(ma_overflow) "); + break; + case ma_underflow: + pr_err("(ma_underflow) "); + break; + case ma_error: + pr_err("(ma_error) "); + break; + } + + pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, + mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) @@ -7260,7 +7556,7 @@ void mas_wr_dump(const struct ma_wr_state *wr_mas) pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", - wr_mas->type, wr_mas->offset_end, wr_mas->node_end, + wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 2f5aa851834e..a0be5d05c7f0 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -18,11 +18,14 @@ #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/kmsan.h> +#include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/printk.h> +#include <linux/refcount.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #include <linux/string.h> @@ -32,14 +35,23 @@ #define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) -#define DEPOT_VALID_BITS 1 #define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */ #define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER)) #define DEPOT_STACK_ALIGN 4 #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) -#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_VALID_BITS - \ - DEPOT_OFFSET_BITS - STACK_DEPOT_EXTRA_BITS) +#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ + STACK_DEPOT_EXTRA_BITS) +#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32 +/* + * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack + * traces. As KMSAN does not support evicting stack traces from the stack + * depot, the stack depot capacity might be reached quickly with large stack + * records. Adjust the maximum number of stack depot pools for this case. + */ +#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16)) +#else #define DEPOT_POOLS_CAP 8192 +#endif #define DEPOT_MAX_POOLS \ (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) @@ -50,19 +62,22 @@ union handle_parts { struct { u32 pool_index : DEPOT_POOL_INDEX_BITS; u32 offset : DEPOT_OFFSET_BITS; - u32 valid : DEPOT_VALID_BITS; u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; struct stack_record { - struct stack_record *next; /* Link in the hash table */ - u32 hash; /* Hash in the hash table */ + struct list_head list; /* Links in hash table or freelist */ + u32 hash; /* Hash in hash table */ u32 size; /* Number of stored frames */ union handle_parts handle; - unsigned long entries[]; /* Variable-sized array of frames */ + refcount_t count; + unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ }; +#define DEPOT_STACK_RECORD_SIZE \ + ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN) + static bool stack_depot_disabled; static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); static bool __stack_depot_early_init_passed __initdata; @@ -75,40 +90,34 @@ static bool __stack_depot_early_init_passed __initdata; /* Initial seed for jhash2. */ #define STACK_HASH_SEED 0x9747b28c -/* Hash table of pointers to stored stack traces. */ -static struct stack_record **stack_table; +/* Hash table of stored stack records. */ +static struct list_head *stack_table; /* Fixed order of the number of table buckets. Used when KASAN is enabled. */ static unsigned int stack_bucket_number_order; /* Hash mask for indexing the table. */ static unsigned int stack_hash_mask; -/* Array of memory regions that store stack traces. */ +/* Array of memory regions that store stack records. */ static void *stack_pools[DEPOT_MAX_POOLS]; -/* Currently used pool in stack_pools. */ -static int pool_index; -/* Offset to the unused space in the currently used pool. */ -static size_t pool_offset; -/* Lock that protects the variables above. */ -static DEFINE_RAW_SPINLOCK(pool_lock); +/* Newly allocated pool that is not yet added to stack_pools. */ +static void *new_pool; +/* Number of pools in stack_pools. */ +static int pools_num; +/* Freelist of stack records within stack_pools. */ +static LIST_HEAD(free_stacks); /* * Stack depot tries to keep an extra pool allocated even before it runs out - * of space in the currently used pool. - * This flag marks that this next extra pool needs to be allocated and - * initialized. It has the value 0 when either the next pool is not yet - * initialized or the limit on the number of pools is reached. + * of space in the currently used pool. This flag marks whether this extra pool + * needs to be allocated. It has the value 0 when either an extra pool is not + * yet allocated or if the limit on the number of pools is reached. */ -static int next_pool_required = 1; +static bool new_pool_required = true; +/* Lock that protects the variables above. */ +static DEFINE_RWLOCK(pool_rwlock); static int __init disable_stack_depot(char *str) { - int ret; - - ret = kstrtobool(str, &stack_depot_disabled); - if (!ret && stack_depot_disabled) { - pr_info("disabled\n"); - stack_table = NULL; - } - return 0; + return kstrtobool(str, &stack_depot_disabled); } early_param("stack_depot_disable", disable_stack_depot); @@ -120,6 +129,15 @@ void __init stack_depot_request_early_init(void) __stack_depot_early_init_requested = true; } +/* Initialize list_head's within the hash table. */ +static void init_stack_table(unsigned long entries) +{ + unsigned long i; + + for (i = 0; i < entries; i++) + INIT_LIST_HEAD(&stack_table[i]); +} + /* Allocates a hash table via memblock. Can only be used during early boot. */ int __init stack_depot_early_init(void) { @@ -131,6 +149,15 @@ int __init stack_depot_early_init(void) __stack_depot_early_init_passed = true; /* + * Print disabled message even if early init has not been requested: + * stack_depot_init() will not print one. + */ + if (stack_depot_disabled) { + pr_info("disabled\n"); + return 0; + } + + /* * If KASAN is enabled, use the maximum order: KASAN is frequently used * in fuzzing scenarios, which leads to a large number of different * stack traces being stored in stack depot. @@ -138,21 +165,25 @@ int __init stack_depot_early_init(void) if (kasan_enabled() && !stack_bucket_number_order) stack_bucket_number_order = STACK_BUCKET_NUMBER_ORDER_MAX; - if (!__stack_depot_early_init_requested || stack_depot_disabled) + /* + * Check if early init has been requested after setting + * stack_bucket_number_order: stack_depot_init() uses its value. + */ + if (!__stack_depot_early_init_requested) return 0; /* * If stack_bucket_number_order is not set, leave entries as 0 to rely - * on the automatic calculations performed by alloc_large_system_hash. + * on the automatic calculations performed by alloc_large_system_hash(). */ if (stack_bucket_number_order) entries = 1UL << stack_bucket_number_order; pr_info("allocating hash table via alloc_large_system_hash\n"); stack_table = alloc_large_system_hash("stackdepot", - sizeof(struct stack_record *), + sizeof(struct list_head), entries, STACK_HASH_TABLE_SCALE, - HASH_EARLY | HASH_ZERO, + HASH_EARLY, NULL, &stack_hash_mask, 1UL << STACK_BUCKET_NUMBER_ORDER_MIN, @@ -162,6 +193,14 @@ int __init stack_depot_early_init(void) stack_depot_disabled = true; return -ENOMEM; } + if (!entries) { + /* + * Obtain the number of entries that was calculated by + * alloc_large_system_hash(). + */ + entries = stack_hash_mask + 1; + } + init_stack_table(entries); return 0; } @@ -202,7 +241,7 @@ int stack_depot_init(void) entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MAX; pr_info("allocating hash table of %lu entries via kvcalloc\n", entries); - stack_table = kvcalloc(entries, sizeof(struct stack_record *), GFP_KERNEL); + stack_table = kvcalloc(entries, sizeof(struct list_head), GFP_KERNEL); if (!stack_table) { pr_err("hash table allocation failed, disabling\n"); stack_depot_disabled = true; @@ -210,6 +249,7 @@ int stack_depot_init(void) goto out_unlock; } stack_hash_mask = entries - 1; + init_stack_table(entries); out_unlock: mutex_unlock(&stack_depot_init_mutex); @@ -218,41 +258,103 @@ out_unlock: } EXPORT_SYMBOL_GPL(stack_depot_init); -/* Uses preallocated memory to initialize a new stack depot pool. */ -static void depot_init_pool(void **prealloc) +/* Initializes a stack depol pool. */ +static void depot_init_pool(void *pool) { + int offset; + + lockdep_assert_held_write(&pool_rwlock); + + WARN_ON(!list_empty(&free_stacks)); + + /* Initialize handles and link stack records into the freelist. */ + for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE; + offset += DEPOT_STACK_RECORD_SIZE) { + struct stack_record *stack = pool + offset; + + stack->handle.pool_index = pools_num; + stack->handle.offset = offset >> DEPOT_STACK_ALIGN; + stack->handle.extra = 0; + + list_add(&stack->list, &free_stacks); + } + + /* Save reference to the pool to be used by depot_fetch_stack(). */ + stack_pools[pools_num] = pool; + pools_num++; +} + +/* Keeps the preallocated memory to be used for a new stack depot pool. */ +static void depot_keep_new_pool(void **prealloc) +{ + lockdep_assert_held_write(&pool_rwlock); + /* - * If the next pool is already initialized or the maximum number of + * If a new pool is already saved or the maximum number of * pools is reached, do not use the preallocated memory. - * smp_load_acquire() here pairs with smp_store_release() below and - * in depot_alloc_stack(). */ - if (!smp_load_acquire(&next_pool_required)) + if (!new_pool_required) return; - /* Check if the current pool is not yet allocated. */ - if (stack_pools[pool_index] == NULL) { - /* Use the preallocated memory for the current pool. */ - stack_pools[pool_index] = *prealloc; + /* + * Use the preallocated memory for the new pool + * as long as we do not exceed the maximum number of pools. + */ + if (pools_num < DEPOT_MAX_POOLS) { + new_pool = *prealloc; *prealloc = NULL; - } else { - /* - * Otherwise, use the preallocated memory for the next pool - * as long as we do not exceed the maximum number of pools. - */ - if (pool_index + 1 < DEPOT_MAX_POOLS) { - stack_pools[pool_index + 1] = *prealloc; - *prealloc = NULL; - } - /* - * At this point, either the next pool is initialized or the - * maximum number of pools is reached. In either case, take - * note that initializing another pool is not required. - * This smp_store_release pairs with smp_load_acquire() above - * and in stack_depot_save(). - */ - smp_store_release(&next_pool_required, 0); } + + /* + * At this point, either a new pool is kept or the maximum + * number of pools is reached. In either case, take note that + * keeping another pool is not required. + */ + new_pool_required = false; +} + +/* Updates references to the current and the next stack depot pools. */ +static bool depot_update_pools(void **prealloc) +{ + lockdep_assert_held_write(&pool_rwlock); + + /* Check if we still have objects in the freelist. */ + if (!list_empty(&free_stacks)) + goto out_keep_prealloc; + + /* Check if we have a new pool saved and use it. */ + if (new_pool) { + depot_init_pool(new_pool); + new_pool = NULL; + + /* Take note that we might need a new new_pool. */ + if (pools_num < DEPOT_MAX_POOLS) + new_pool_required = true; + + /* Try keeping the preallocated memory for new_pool. */ + goto out_keep_prealloc; + } + + /* Bail out if we reached the pool limit. */ + if (unlikely(pools_num >= DEPOT_MAX_POOLS)) { + WARN_ONCE(1, "Stack depot reached limit capacity"); + return false; + } + + /* Check if we have preallocated memory and use it. */ + if (*prealloc) { + depot_init_pool(*prealloc); + *prealloc = NULL; + return true; + } + + return false; + +out_keep_prealloc: + /* Keep the preallocated memory for a new pool if required. */ + if (*prealloc) + depot_keep_new_pool(prealloc); + return true; } /* Allocates a new stack in a stack depot pool. */ @@ -260,62 +362,72 @@ static struct stack_record * depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) { struct stack_record *stack; - size_t required_size = struct_size(stack, entries, size); - required_size = ALIGN(required_size, 1 << DEPOT_STACK_ALIGN); + lockdep_assert_held_write(&pool_rwlock); - /* Check if there is not enough space in the current pool. */ - if (unlikely(pool_offset + required_size > DEPOT_POOL_SIZE)) { - /* Bail out if we reached the pool limit. */ - if (unlikely(pool_index + 1 >= DEPOT_MAX_POOLS)) { - WARN_ONCE(1, "Stack depot reached limit capacity"); - return NULL; - } + /* Update current and new pools if required and possible. */ + if (!depot_update_pools(prealloc)) + return NULL; - /* - * Move on to the next pool. - * WRITE_ONCE pairs with potential concurrent read in - * stack_depot_fetch(). - */ - WRITE_ONCE(pool_index, pool_index + 1); - pool_offset = 0; - /* - * If the maximum number of pools is not reached, take note - * that the next pool needs to initialized. - * smp_store_release() here pairs with smp_load_acquire() in - * stack_depot_save() and depot_init_pool(). - */ - if (pool_index + 1 < DEPOT_MAX_POOLS) - smp_store_release(&next_pool_required, 1); - } + /* Check if we have a stack record to save the stack trace. */ + if (list_empty(&free_stacks)) + return NULL; - /* Assign the preallocated memory to a pool if required. */ - if (*prealloc) - depot_init_pool(prealloc); + /* Get and unlink the first entry from the freelist. */ + stack = list_first_entry(&free_stacks, struct stack_record, list); + list_del(&stack->list); - /* Check if we have a pool to save the stack trace. */ - if (stack_pools[pool_index] == NULL) - return NULL; + /* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */ + if (size > CONFIG_STACKDEPOT_MAX_FRAMES) + size = CONFIG_STACKDEPOT_MAX_FRAMES; /* Save the stack trace. */ - stack = stack_pools[pool_index] + pool_offset; stack->hash = hash; stack->size = size; - stack->handle.pool_index = pool_index; - stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; - stack->handle.valid = 1; - stack->handle.extra = 0; + /* stack->handle is already filled in by depot_init_pool(). */ + refcount_set(&stack->count, 1); memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); - pool_offset += required_size; + /* * Let KMSAN know the stored stack record is initialized. This shall * prevent false positive reports if instrumented code accesses it. */ - kmsan_unpoison_memory(stack, required_size); + kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE); return stack; } +static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) +{ + union handle_parts parts = { .handle = handle }; + void *pool; + size_t offset = parts.offset << DEPOT_STACK_ALIGN; + struct stack_record *stack; + + lockdep_assert_held(&pool_rwlock); + + if (parts.pool_index > pools_num) { + WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", + parts.pool_index, pools_num, handle); + return NULL; + } + + pool = stack_pools[parts.pool_index]; + if (!pool) + return NULL; + + stack = pool + offset; + return stack; +} + +/* Links stack into the freelist. */ +static void depot_free_stack(struct stack_record *stack) +{ + lockdep_assert_held_write(&pool_rwlock); + + list_add(&stack->list, &free_stacks); +} + /* Calculates the hash for a stack. */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) { @@ -340,13 +452,17 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2, } /* Finds a stack in a bucket of the hash table. */ -static inline struct stack_record *find_stack(struct stack_record *bucket, +static inline struct stack_record *find_stack(struct list_head *bucket, unsigned long *entries, int size, u32 hash) { + struct list_head *pos; struct stack_record *found; - for (found = bucket; found; found = found->next) { + lockdep_assert_held(&pool_rwlock); + + list_for_each(pos, bucket) { + found = list_entry(pos, struct stack_record, list); if (found->hash == hash && found->size == size && !stackdepot_memcmp(entries, found->entries, size)) @@ -355,17 +471,24 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } -depot_stack_handle_t __stack_depot_save(unsigned long *entries, - unsigned int nr_entries, - gfp_t alloc_flags, bool can_alloc) +depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags, + depot_flags_t depot_flags) { - struct stack_record *found = NULL, **bucket; - union handle_parts retval = { .handle = 0 }; + struct list_head *bucket; + struct stack_record *found = NULL; + depot_stack_handle_t handle = 0; struct page *page = NULL; void *prealloc = NULL; + bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC; + bool need_alloc = false; unsigned long flags; u32 hash; + if (WARN_ON(depot_flags & ~STACK_DEPOT_FLAGS_MASK)) + return 0; + /* * If this stack trace is from an interrupt, including anything before * interrupt entry usually leads to unbounded stack depot growth. @@ -377,28 +500,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, nr_entries = filter_irq_stacks(entries, nr_entries); if (unlikely(nr_entries == 0) || stack_depot_disabled) - goto fast_exit; + return 0; hash = hash_stack(entries, nr_entries); bucket = &stack_table[hash & stack_hash_mask]; - /* - * Fast path: look the stack trace up without locking. - * The smp_load_acquire() here pairs with smp_store_release() to - * |bucket| below. - */ - found = find_stack(smp_load_acquire(bucket), entries, nr_entries, hash); - if (found) + read_lock_irqsave(&pool_rwlock, flags); + printk_deferred_enter(); + + /* Fast path: look the stack trace up without full locking. */ + found = find_stack(bucket, entries, nr_entries, hash); + if (found) { + if (depot_flags & STACK_DEPOT_FLAG_GET) + refcount_inc(&found->count); + printk_deferred_exit(); + read_unlock_irqrestore(&pool_rwlock, flags); goto exit; + } + + /* Take note if another stack pool needs to be allocated. */ + if (new_pool_required) + need_alloc = true; + + printk_deferred_exit(); + read_unlock_irqrestore(&pool_rwlock, flags); /* - * Check if another stack pool needs to be initialized. If so, allocate - * the memory now - we won't be able to do that under the lock. - * - * The smp_load_acquire() here pairs with smp_store_release() to - * |next_pool_inited| in depot_alloc_stack() and depot_init_pool(). + * Allocate memory for a new pool if required now: + * we won't be able to do that under the lock. */ - if (unlikely(can_alloc && smp_load_acquire(&next_pool_required))) { + if (unlikely(can_alloc && need_alloc)) { /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic @@ -412,63 +543,56 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, prealloc = page_address(page); } - raw_spin_lock_irqsave(&pool_lock, flags); + write_lock_irqsave(&pool_rwlock, flags); + printk_deferred_enter(); - found = find_stack(*bucket, entries, nr_entries, hash); + found = find_stack(bucket, entries, nr_entries, hash); if (!found) { struct stack_record *new = depot_alloc_stack(entries, nr_entries, hash, &prealloc); if (new) { - new->next = *bucket; - /* - * This smp_store_release() pairs with - * smp_load_acquire() from |bucket| above. - */ - smp_store_release(bucket, new); + list_add(&new->list, bucket); found = new; } - } else if (prealloc) { + } else { + if (depot_flags & STACK_DEPOT_FLAG_GET) + refcount_inc(&found->count); /* * Stack depot already contains this stack trace, but let's - * keep the preallocated memory for the future. + * keep the preallocated memory for future. */ - depot_init_pool(&prealloc); + if (prealloc) + depot_keep_new_pool(&prealloc); } - raw_spin_unlock_irqrestore(&pool_lock, flags); + printk_deferred_exit(); + write_unlock_irqrestore(&pool_rwlock, flags); exit: if (prealloc) { /* Stack depot didn't use this memory, free it. */ free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER); } if (found) - retval.handle = found->handle.handle; -fast_exit: - return retval.handle; + handle = found->handle.handle; + return handle; } -EXPORT_SYMBOL_GPL(__stack_depot_save); +EXPORT_SYMBOL_GPL(stack_depot_save_flags); depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t alloc_flags) { - return __stack_depot_save(entries, nr_entries, alloc_flags, true); + return stack_depot_save_flags(entries, nr_entries, alloc_flags, + STACK_DEPOT_FLAG_CAN_ALLOC); } EXPORT_SYMBOL_GPL(stack_depot_save); unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) { - union handle_parts parts = { .handle = handle }; - /* - * READ_ONCE pairs with potential concurrent write in - * depot_alloc_stack. - */ - int pool_index_cached = READ_ONCE(pool_index); - void *pool; - size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; + unsigned long flags; *entries = NULL; /* @@ -477,24 +601,51 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, */ kmsan_unpoison_memory(entries, sizeof(*entries)); - if (!handle) + if (!handle || stack_depot_disabled) return 0; - if (parts.pool_index > pool_index_cached) { - WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", - parts.pool_index, pool_index_cached, handle); - return 0; - } - pool = stack_pools[parts.pool_index]; - if (!pool) - return 0; - stack = pool + offset; + read_lock_irqsave(&pool_rwlock, flags); + printk_deferred_enter(); + + stack = depot_fetch_stack(handle); + + printk_deferred_exit(); + read_unlock_irqrestore(&pool_rwlock, flags); *entries = stack->entries; return stack->size; } EXPORT_SYMBOL_GPL(stack_depot_fetch); +void stack_depot_put(depot_stack_handle_t handle) +{ + struct stack_record *stack; + unsigned long flags; + + if (!handle || stack_depot_disabled) + return; + + write_lock_irqsave(&pool_rwlock, flags); + printk_deferred_enter(); + + stack = depot_fetch_stack(handle); + if (WARN_ON(!stack)) + goto out; + + if (refcount_dec_and_test(&stack->count)) { + /* Unlink stack from the hash table. */ + list_del(&stack->list); + + /* Free stack. */ + depot_free_stack(stack); + } + +out: + printk_deferred_exit(); + write_unlock_irqrestore(&pool_rwlock, flags); +} +EXPORT_SYMBOL_GPL(stack_depot_put); + void stack_depot_print(depot_stack_handle_t stack) { unsigned long *entries; diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 464eeb90d5ad..29185ac5c727 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -43,6 +43,7 @@ atomic_t maple_tree_tests_passed; /* #define BENCH_NODE_STORE */ /* #define BENCH_AWALK */ /* #define BENCH_WALK */ +/* #define BENCH_LOAD */ /* #define BENCH_MT_FOR_EACH */ /* #define BENCH_FORK */ /* #define BENCH_MAS_FOR_EACH */ @@ -54,6 +55,11 @@ atomic_t maple_tree_tests_passed; #else #define cond_resched() do {} while (0) #endif + +#define mas_is_none(x) ((x)->status == ma_none) +#define mas_is_overflow(x) ((x)->status == ma_overflow) +#define mas_is_underflow(x) ((x)->status == ma_underflow) + static int __init mtree_insert_index(struct maple_tree *mt, unsigned long index, gfp_t gfp) { @@ -582,7 +588,7 @@ static noinline void __init check_find(struct maple_tree *mt) MT_BUG_ON(mt, last != mas.last); - mas.node = MAS_NONE; + mas.status = ma_none; mas.index = ULONG_MAX; mas.last = ULONG_MAX; entry2 = mas_prev(&mas, 0); @@ -1749,6 +1755,19 @@ static noinline void __init bench_walk(struct maple_tree *mt) } #endif +#if defined(BENCH_LOAD) +static noinline void __init bench_load(struct maple_tree *mt) +{ + int i, max = 2500, count = 550000000; + + for (i = 0; i < max; i += 10) + mtree_store_range(mt, i, i + 5, xa_mk_value(i), GFP_KERNEL); + + for (i = 0; i < count; i++) + mtree_load(mt, 1470); +} +#endif + #if defined(BENCH_MT_FOR_EACH) static noinline void __init bench_mt_for_each(struct maple_tree *mt) { @@ -1834,47 +1853,48 @@ static noinline void __init bench_mas_prev(struct maple_tree *mt) } #endif /* check_forking - simulate the kernel forking sequence with the tree. */ -static noinline void __init check_forking(struct maple_tree *mt) +static noinline void __init check_forking(void) { - - struct maple_tree newmt; - int i, nr_entries = 134; + struct maple_tree mt, newmt; + int i, nr_entries = 134, ret; void *val; - MA_STATE(mas, mt, 0, 0); - MA_STATE(newmas, mt, 0, 0); - struct rw_semaphore newmt_lock; + MA_STATE(mas, &mt, 0, 0); + MA_STATE(newmas, &newmt, 0, 0); + struct rw_semaphore mt_lock, newmt_lock; + init_rwsem(&mt_lock); init_rwsem(&newmt_lock); - for (i = 0; i <= nr_entries; i++) - mtree_store_range(mt, i*10, i*10 + 5, - xa_mk_value(i), GFP_KERNEL); + mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&mt, &mt_lock); - mt_set_non_kernel(99999); mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); mt_set_external_lock(&newmt, &newmt_lock); - newmas.tree = &newmt; - mas_reset(&newmas); - mas_reset(&mas); - down_write(&newmt_lock); - mas.index = 0; - mas.last = 0; - if (mas_expected_entries(&newmas, nr_entries)) { + + down_write(&mt_lock); + for (i = 0; i <= nr_entries; i++) { + mas_set_range(&mas, i*10, i*10 + 5); + mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL); + } + + down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING); + ret = __mt_dup(&mt, &newmt, GFP_KERNEL); + if (ret) { pr_err("OOM!"); BUG_ON(1); } - rcu_read_lock(); - mas_for_each(&mas, val, ULONG_MAX) { - newmas.index = mas.index; - newmas.last = mas.last; + + mas_set(&newmas, 0); + mas_for_each(&newmas, val, ULONG_MAX) mas_store(&newmas, val); - } - rcu_read_unlock(); + mas_destroy(&newmas); + mas_destroy(&mas); mt_validate(&newmt); - mt_set_non_kernel(0); __mt_destroy(&newmt); + __mt_destroy(&mt); up_write(&newmt_lock); + up_write(&mt_lock); } static noinline void __init check_iteration(struct maple_tree *mt) @@ -1977,49 +1997,51 @@ static noinline void __init check_mas_store_gfp(struct maple_tree *mt) } #if defined(BENCH_FORK) -static noinline void __init bench_forking(struct maple_tree *mt) +static noinline void __init bench_forking(void) { - - struct maple_tree newmt; - int i, nr_entries = 134, nr_fork = 80000; + struct maple_tree mt, newmt; + int i, nr_entries = 134, nr_fork = 80000, ret; void *val; - MA_STATE(mas, mt, 0, 0); - MA_STATE(newmas, mt, 0, 0); - struct rw_semaphore newmt_lock; + MA_STATE(mas, &mt, 0, 0); + MA_STATE(newmas, &newmt, 0, 0); + struct rw_semaphore mt_lock, newmt_lock; + init_rwsem(&mt_lock); init_rwsem(&newmt_lock); - mt_set_external_lock(&newmt, &newmt_lock); - for (i = 0; i <= nr_entries; i++) - mtree_store_range(mt, i*10, i*10 + 5, - xa_mk_value(i), GFP_KERNEL); + mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&mt, &mt_lock); + + down_write(&mt_lock); + for (i = 0; i <= nr_entries; i++) { + mas_set_range(&mas, i*10, i*10 + 5); + mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL); + } for (i = 0; i < nr_fork; i++) { - mt_set_non_kernel(99999); - mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE); - newmas.tree = &newmt; - mas_reset(&newmas); - mas_reset(&mas); - mas.index = 0; - mas.last = 0; - rcu_read_lock(); - down_write(&newmt_lock); - if (mas_expected_entries(&newmas, nr_entries)) { - printk("OOM!"); + mt_init_flags(&newmt, + MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&newmt, &newmt_lock); + + down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING); + ret = __mt_dup(&mt, &newmt, GFP_KERNEL); + if (ret) { + pr_err("OOM!"); BUG_ON(1); } - mas_for_each(&mas, val, ULONG_MAX) { - newmas.index = mas.index; - newmas.last = mas.last; + + mas_set(&newmas, 0); + mas_for_each(&newmas, val, ULONG_MAX) mas_store(&newmas, val); - } + mas_destroy(&newmas); - rcu_read_unlock(); mt_validate(&newmt); - mt_set_non_kernel(0); __mt_destroy(&newmt); up_write(&newmt_lock); } + mas_destroy(&mas); + __mt_destroy(&mt); + up_write(&mt_lock); } #endif @@ -2175,7 +2197,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt) MT_BUG_ON(mt, val != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 5); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); mas.index = 0; mas.last = 5; @@ -3039,10 +3061,6 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE active active range of NULL */ -#define mas_active(x) (((x).node != MAS_ROOT) && \ - ((x).node != MAS_START) && \ - ((x).node != MAS_PAUSE) && \ - ((x).node != MAS_NONE)) static noinline void __init check_state_handling(struct maple_tree *mt) { MA_STATE(mas, mt, 0, 0); @@ -3057,7 +3075,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) /* prev: Start -> underflow*/ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, mas.status != ma_underflow); /* prev: Start -> root */ mas_set(&mas, 10); @@ -3065,7 +3083,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* prev: pause -> root */ mas_set(&mas, 10); @@ -3074,7 +3092,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* next: start -> none */ mas_set(&mas, 0); @@ -3082,7 +3100,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* next: start -> none*/ mas_set(&mas, 10); @@ -3090,7 +3108,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: start -> root */ mas_set(&mas, 0); @@ -3098,21 +3116,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find: root -> none */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: none -> none */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: start -> none */ mas_set(&mas, 10); @@ -3120,14 +3138,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: none -> root */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find_rev: start -> root */ mas_set(&mas, 0); @@ -3135,21 +3153,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find_rev: root -> none */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: none -> none */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: start -> root */ mas_set(&mas, 10); @@ -3157,7 +3175,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: start -> none */ mas_set(&mas, 10); @@ -3165,7 +3183,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: pause -> none*/ mas_set(&mas, 10); @@ -3174,7 +3192,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> none */ mas.index = mas.last = 10; @@ -3182,14 +3200,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> none */ entry = mas_walk(&mas); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: start -> root */ mas_set(&mas, 0); @@ -3197,7 +3215,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: pause -> root */ mas_set(&mas, 0); @@ -3206,22 +3224,22 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: none -> root */ - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: root -> root */ entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: root -> none */ mas_set(&mas, 10); @@ -3229,7 +3247,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> root */ mas.index = mas.last = 0; @@ -3237,7 +3255,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); mas_unlock(&mas); @@ -3255,7 +3273,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: pause ->active */ mas_set(&mas, 0); @@ -3264,126 +3282,132 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: none ->active */ mas.index = mas.last = 0; mas.offset = 0; - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active ->active */ - entry = mas_next(&mas, ULONG_MAX); + /* next:active ->active (spanning limit) */ + entry = mas_next(&mas, 0x2100); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active -> active beyond data */ + /* next:active -> overflow (limit reached) beyond data */ entry = mas_next(&mas, 0x2999); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); - /* Continue after last range ends after max */ + /* next:overflow -> active (limit changed) */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); - - /* next:active -> active continued */ - entry = mas_next(&mas, ULONG_MAX); - MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.index != 0x3501); - MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active -> overflow */ + /* next:active -> overflow (limit reached) */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); /* next:overflow -> overflow */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); /* prev:overflow -> active */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: none -> active, skip value at location */ mas_set(&mas, 0); entry = mas_next(&mas, ULONG_MAX); - mas.node = MAS_NONE; + mas.status = ma_none; mas.offset = 0; entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev:active ->active */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* prev:active -> active spanning end range */ + /* prev:active -> underflow (span limit) */ + mas_next(&mas, ULONG_MAX); + entry = mas_prev(&mas, 0x1200); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* spanning limit */ + entry = mas_prev(&mas, 0x1200); /* underflow */ + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); + + /* prev:underflow -> underflow (lower limit) spanning end range */ entry = mas_prev(&mas, 0x0100); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); - /* prev:active -> underflow */ + /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* next:underflow -> active */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev:first value -> underflow */ entry = mas_prev(&mas, 0x1000); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* find:underflow -> first value */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev: pause ->active */ mas_set(&mas, 0x3600); @@ -3394,21 +3418,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* prev:active -> active spanning min */ + /* prev:active -> underflow spanning min */ entry = mas_prev(&mas, 0x1600); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* prev: active ->active, continue */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: start ->active */ mas_set(&mas, 0); @@ -3416,7 +3440,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: pause ->active */ mas_set(&mas, 0); @@ -3425,7 +3449,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: start ->active on value */; mas_set(&mas, 1200); @@ -3433,14 +3457,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active ->active */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active -> active (NULL)*/ @@ -3448,35 +3472,35 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MAS_BUG_ON(&mas, !mas_is_active(&mas)); /* find: overflow ->active */ entry = mas_find(&mas, 0x5000); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active -> active (NULL) end*/ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, !mas_active(mas)); + MAS_BUG_ON(&mas, !mas_is_active(&mas)); /* find_rev: active (END) ->active */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find_rev:active ->active */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find_rev: pause ->active */ mas_pause(&mas); @@ -3484,14 +3508,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* find_rev:active -> active */ + /* find_rev:active -> underflow */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* find_rev: start ->active */ mas_set(&mas, 0x1200); @@ -3499,7 +3523,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk start ->active */ mas_set(&mas, 0x1200); @@ -3507,7 +3531,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk start ->active */ mas_set(&mas, 0x1600); @@ -3515,7 +3539,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk pause ->active */ mas_set(&mas, 0x1200); @@ -3524,7 +3548,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk pause -> active */ mas_set(&mas, 0x1600); @@ -3533,25 +3557,25 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk none -> active */ mas_set(&mas, 0x1200); - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk none -> active */ mas_set(&mas, 0x1600); - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk active -> active */ mas.index = 0x1200; @@ -3561,7 +3585,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk active -> active */ mas.index = 0x1600; @@ -3570,7 +3594,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); mas_unlock(&mas); } @@ -3585,10 +3609,6 @@ static int __init maple_tree_seed(void) pr_info("\nTEST STARTING\n\n"); - mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_root_expand(&tree); - mtree_destroy(&tree); - #if defined(BENCH_SLOT_STORE) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); @@ -3617,13 +3637,18 @@ static int __init maple_tree_seed(void) mtree_destroy(&tree); goto skip; #endif -#if defined(BENCH_FORK) +#if defined(BENCH_LOAD) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - bench_forking(&tree); + bench_load(&tree); mtree_destroy(&tree); goto skip; #endif +#if defined(BENCH_FORK) +#define BENCH + bench_forking(); + goto skip; +#endif #if defined(BENCH_MT_FOR_EACH) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); @@ -3647,13 +3672,15 @@ static int __init maple_tree_seed(void) #endif mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_iteration(&tree); + check_root_expand(&tree); mtree_destroy(&tree); mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_forking(&tree); + check_iteration(&tree); mtree_destroy(&tree); + check_forking(); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_mas_store_gfp(&tree); mtree_destroy(&tree); diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 0ae35223d773..0dc173849a54 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures) int failures = 0, num_tests = 0; int i; - for (i = 0; i <= MAX_ORDER; i++) + for (i = 0; i < NR_PAGE_ORDERS; i++) num_tests += do_alloc_pages_order(i, &failures); REPORT_FAILURES_IN_FN(); diff --git a/lib/ubsan.c b/lib/ubsan.c index 3f90810f9f42..df4f8d1354bb 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -204,8 +204,8 @@ static void ubsan_prologue(struct source_location *loc, const char *reason) { current->in_ubsan++; - pr_err("========================================" - "========================================\n"); + pr_warn(CUT_HERE); + pr_err("UBSAN: %s in %s:%d:%d\n", reason, loc->file_name, loc->line & LINE_MASK, loc->column & COLUMN_MASK); @@ -215,8 +215,7 @@ static void ubsan_prologue(struct source_location *loc, const char *reason) static void ubsan_epilogue(void) { dump_stack(); - pr_err("========================================" - "========================================\n"); + pr_warn("---[ end trace ]---\n"); current->in_ubsan--; |