From efe1f3a1d5833c0ddd61ee50dbef8908f65a0a5e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:06 +0800 Subject: scsi: sbitmap: Maintain allocation round_robin in sbitmap Currently the allocation round_robin info is maintained by sbitmap_queue. However, bit allocation really belongs to sbitmap. Move it there. Link: https://lore.kernel.org/r/20210122023317.687987-3-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Cc: Hannes Reinecke Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- lib/sbitmap.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/lib/sbitmap.c b/lib/sbitmap.c index d693d9213ceb..7000636933b3 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -33,7 +33,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map) } int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, - gfp_t flags, int node) + gfp_t flags, int node, bool round_robin) { unsigned int bits_per_word; unsigned int i; @@ -58,6 +58,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, sb->shift = shift; sb->depth = depth; sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word); + sb->round_robin = round_robin; if (depth == 0) { sb->map = NULL; @@ -129,14 +130,14 @@ static int __sbitmap_get_word(unsigned long *word, unsigned long depth, } static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, - unsigned int alloc_hint, bool round_robin) + unsigned int alloc_hint) { struct sbitmap_word *map = &sb->map[index]; int nr; do { nr = __sbitmap_get_word(&map->word, map->depth, alloc_hint, - !round_robin); + !sb->round_robin); if (nr != -1) break; if (!sbitmap_deferred_clear(map)) @@ -146,7 +147,7 @@ static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, return nr; } -int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin) +int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) { unsigned int i, index; int nr = -1; @@ -158,14 +159,13 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin) * alloc_hint to find the right word index. No point in looping * twice in find_next_zero_bit() for that case. */ - if (round_robin) + if (sb->round_robin) alloc_hint = SB_NR_TO_BIT(sb, alloc_hint); else alloc_hint = 0; for (i = 0; i < sb->map_nr; i++) { - nr = sbitmap_find_bit_in_index(sb, index, alloc_hint, - round_robin); + nr = sbitmap_find_bit_in_index(sb, index, alloc_hint); if (nr != -1) { nr += index << sb->shift; break; @@ -350,7 +350,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int ret; int i; - ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node); + ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node, + round_robin); if (ret) return ret; @@ -382,7 +383,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, atomic_set(&sbq->ws[i].wait_cnt, sbq->wake_batch); } - sbq->round_robin = round_robin; return 0; } EXPORT_SYMBOL_GPL(sbitmap_queue_init_node); @@ -424,12 +424,12 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq) hint = depth ? prandom_u32() % depth : 0; this_cpu_write(*sbq->alloc_hint, hint); } - nr = sbitmap_get(&sbq->sb, hint, sbq->round_robin); + nr = sbitmap_get(&sbq->sb, hint); if (nr == -1) { /* If the map is full, a hint won't do us much good. */ this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->round_robin)) { + } else if (nr == hint || unlikely(sbq->sb.round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) @@ -460,7 +460,7 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, if (nr == -1) { /* If the map is full, a hint won't do us much good. */ this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->round_robin)) { + } else if (nr == hint || unlikely(sbq->sb.round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) @@ -576,7 +576,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, smp_mb__after_atomic(); sbitmap_queue_wake_up(sbq); - if (likely(!sbq->round_robin && nr < sbq->sb.depth)) + if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth)) *per_cpu_ptr(sbq->alloc_hint, cpu) = nr; } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); @@ -633,7 +633,7 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) } seq_puts(m, "}\n"); - seq_printf(m, "round_robin=%d\n", sbq->round_robin); + seq_printf(m, "round_robin=%d\n", sbq->sb.round_robin); seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_show); -- cgit v1.2.3 From bf2c4282a10a92810ba83e85677a5273d6ca0df5 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:07 +0800 Subject: scsi: sbitmap: Add helpers for updating allocation hint Add helpers for updating allocation hint so that we can avoid duplicate code. Prepare for moving allocation hint into sbitmap. Link: https://lore.kernel.org/r/20210122023317.687987-4-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Cc: Hannes Reinecke Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- lib/sbitmap.c | 93 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 54 insertions(+), 39 deletions(-) (limited to 'lib') diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 7000636933b3..2b43a6aefec3 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -9,6 +9,55 @@ #include #include +static int init_alloc_hint(struct sbitmap_queue *sbq, gfp_t flags) +{ + unsigned depth = sbq->sb.depth; + + sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); + if (!sbq->alloc_hint) + return -ENOMEM; + + if (depth && !sbq->sb.round_robin) { + int i; + + for_each_possible_cpu(i) + *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; + } + + return 0; +} + +static inline unsigned update_alloc_hint_before_get(struct sbitmap_queue *sbq, + unsigned int depth) +{ + unsigned hint; + + hint = this_cpu_read(*sbq->alloc_hint); + if (unlikely(hint >= depth)) { + hint = depth ? prandom_u32() % depth : 0; + this_cpu_write(*sbq->alloc_hint, hint); + } + + return hint; +} + +static inline void update_alloc_hint_after_get(struct sbitmap_queue *sbq, + unsigned int depth, + unsigned int hint, + unsigned int nr) +{ + if (nr == -1) { + /* If the map is full, a hint won't do us much good. */ + this_cpu_write(*sbq->alloc_hint, 0); + } else if (nr == hint || unlikely(sbq->sb.round_robin)) { + /* Only update the hint if we used it. */ + hint = nr + 1; + if (hint >= depth - 1) + hint = 0; + this_cpu_write(*sbq->alloc_hint, hint); + } +} + /* * See if we have deferred clears that we can batch move */ @@ -355,17 +404,11 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, if (ret) return ret; - sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); - if (!sbq->alloc_hint) { + if (init_alloc_hint(sbq, flags) != 0) { sbitmap_free(&sbq->sb); return -ENOMEM; } - if (depth && !round_robin) { - for_each_possible_cpu(i) - *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; - } - sbq->min_shallow_depth = UINT_MAX; sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); @@ -418,24 +461,10 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq) unsigned int hint, depth; int nr; - hint = this_cpu_read(*sbq->alloc_hint); depth = READ_ONCE(sbq->sb.depth); - if (unlikely(hint >= depth)) { - hint = depth ? prandom_u32() % depth : 0; - this_cpu_write(*sbq->alloc_hint, hint); - } + hint = update_alloc_hint_before_get(sbq, depth); nr = sbitmap_get(&sbq->sb, hint); - - if (nr == -1) { - /* If the map is full, a hint won't do us much good. */ - this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->sb.round_robin)) { - /* Only update the hint if we used it. */ - hint = nr + 1; - if (hint >= depth - 1) - hint = 0; - this_cpu_write(*sbq->alloc_hint, hint); - } + update_alloc_hint_after_get(sbq, depth, hint, nr); return nr; } @@ -449,24 +478,10 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth); - hint = this_cpu_read(*sbq->alloc_hint); depth = READ_ONCE(sbq->sb.depth); - if (unlikely(hint >= depth)) { - hint = depth ? prandom_u32() % depth : 0; - this_cpu_write(*sbq->alloc_hint, hint); - } + hint = update_alloc_hint_before_get(sbq, depth); nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth); - - if (nr == -1) { - /* If the map is full, a hint won't do us much good. */ - this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->sb.round_robin)) { - /* Only update the hint if we used it. */ - hint = nr + 1; - if (hint >= depth - 1) - hint = 0; - this_cpu_write(*sbq->alloc_hint, hint); - } + update_alloc_hint_after_get(sbq, depth, hint, nr); return nr; } -- cgit v1.2.3 From c548e62bcf6adc7066ff201e9ecc88e536dd8890 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:08 +0800 Subject: scsi: sbitmap: Move allocation hint into sbitmap Allocation hint should have belonged to sbitmap. Also, when sbitmap's depth is high and there is no need to use mulitple wakeup queues, user can benefit from percpu allocation hint too. Move allocation hint into sbitmap, then SCSI device queue can benefit from allocation hint when converting to plain sbitmap. Convert vhost/scsi.c to use sbitmap allocation with percpu alloc hint. This is more efficient than the previous approach. Link: https://lore.kernel.org/r/20210122023317.687987-5-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Cc: Mike Christie Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- block/blk-mq.c | 2 +- block/kyber-iosched.c | 2 +- drivers/vhost/scsi.c | 4 +- include/linux/sbitmap.h | 41 +++++++++++------- lib/sbitmap.c | 112 ++++++++++++++++++++++++++++-------------------- 5 files changed, 96 insertions(+), 65 deletions(-) (limited to 'lib') diff --git a/block/blk-mq.c b/block/blk-mq.c index f133bbfa6cd4..2e8c94e00f58 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2702,7 +2702,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), - gfp, node, false)) + gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx = 0; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index d39ac13f0105..8969e122f081 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -479,7 +479,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) for (i = 0; i < KYBER_NUM_DOMAINS; i++) { if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx, ilog2(8), GFP_KERNEL, hctx->numa_node, - false)) { + false, false)) { while (--i >= 0) sbitmap_free(&khd->kcq_map[i]); goto err_kcqs; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 3412a3ad28e6..936584250a0b 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -614,7 +614,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, return ERR_PTR(-EIO); } - tag = sbitmap_get(&svq->scsi_tags, 0); + tag = sbitmap_get(&svq->scsi_tags); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); @@ -1512,7 +1512,7 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) return 0; if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, - NUMA_NO_NODE, false)) + NUMA_NO_NODE, false, true)) return -ENOMEM; svq->max_cmds = max_cmds; diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 734ee6214cd6..247776fcc02c 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -65,6 +65,14 @@ struct sbitmap { * @map: Allocated bitmap. */ struct sbitmap_word *map; + + /* + * @alloc_hint: Cache of last successfully allocated or freed bit. + * + * This is per-cpu, which allows multiple users to stick to different + * cachelines until the map is exhausted. + */ + unsigned int __percpu *alloc_hint; }; #define SBQ_WAIT_QUEUES 8 @@ -100,14 +108,6 @@ struct sbitmap_queue { */ struct sbitmap sb; - /* - * @alloc_hint: Cache of last successfully allocated or freed bit. - * - * This is per-cpu, which allows multiple users to stick to different - * cachelines until the map is exhausted. - */ - unsigned int __percpu *alloc_hint; - /** * @wake_batch: Number of bits which must be freed before we wake up any * waiters. @@ -147,11 +147,13 @@ struct sbitmap_queue { * @round_robin: If true, be stricter about allocation order; always allocate * starting from the last allocated bit. This is less efficient * than the default behavior (false). + * @alloc_hint: If true, apply percpu hint for where to start searching for + * a free bit. * * Return: Zero on success or negative errno on failure. */ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, - gfp_t flags, int node, bool round_robin); + gfp_t flags, int node, bool round_robin, bool alloc_hint); /** * sbitmap_free() - Free memory used by a &struct sbitmap. @@ -159,6 +161,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, */ static inline void sbitmap_free(struct sbitmap *sb) { + free_percpu(sb->alloc_hint); kfree(sb->map); sb->map = NULL; } @@ -176,19 +179,17 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); /** * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap. * @sb: Bitmap to allocate from. - * @alloc_hint: Hint for where to start searching for a free bit. * * This operation provides acquire barrier semantics if it succeeds. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint); +int sbitmap_get(struct sbitmap *sb); /** * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, * limiting the depth used from each word. * @sb: Bitmap to allocate from. - * @alloc_hint: Hint for where to start searching for a free bit. * @shallow_depth: The maximum number of bits to allocate from a single word. * * This rather specific operation allows for having multiple users with @@ -200,8 +201,7 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint); * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, - unsigned long shallow_depth); +int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth); /** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. @@ -315,6 +315,18 @@ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int b set_bit(SB_NR_TO_BIT(sb, bitnr), addr); } +/* + * Pair of sbitmap_get, and this one applies both cleared bit and + * allocation hint. + */ +static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr) +{ + sbitmap_deferred_clear_bit(sb, bitnr); + + if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth)) + *this_cpu_ptr(sb->alloc_hint) = bitnr; +} + static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) { return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); @@ -363,7 +375,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) { kfree(sbq->ws); - free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); } diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2b43a6aefec3..e395435654aa 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -9,52 +9,51 @@ #include #include -static int init_alloc_hint(struct sbitmap_queue *sbq, gfp_t flags) +static int init_alloc_hint(struct sbitmap *sb, gfp_t flags) { - unsigned depth = sbq->sb.depth; + unsigned depth = sb->depth; - sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); - if (!sbq->alloc_hint) + sb->alloc_hint = alloc_percpu_gfp(unsigned int, flags); + if (!sb->alloc_hint) return -ENOMEM; - if (depth && !sbq->sb.round_robin) { + if (depth && !sb->round_robin) { int i; for_each_possible_cpu(i) - *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; + *per_cpu_ptr(sb->alloc_hint, i) = prandom_u32() % depth; } - return 0; } -static inline unsigned update_alloc_hint_before_get(struct sbitmap_queue *sbq, +static inline unsigned update_alloc_hint_before_get(struct sbitmap *sb, unsigned int depth) { unsigned hint; - hint = this_cpu_read(*sbq->alloc_hint); + hint = this_cpu_read(*sb->alloc_hint); if (unlikely(hint >= depth)) { hint = depth ? prandom_u32() % depth : 0; - this_cpu_write(*sbq->alloc_hint, hint); + this_cpu_write(*sb->alloc_hint, hint); } return hint; } -static inline void update_alloc_hint_after_get(struct sbitmap_queue *sbq, +static inline void update_alloc_hint_after_get(struct sbitmap *sb, unsigned int depth, unsigned int hint, unsigned int nr) { if (nr == -1) { /* If the map is full, a hint won't do us much good. */ - this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->sb.round_robin)) { + this_cpu_write(*sb->alloc_hint, 0); + } else if (nr == hint || unlikely(sb->round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) hint = 0; - this_cpu_write(*sbq->alloc_hint, hint); + this_cpu_write(*sb->alloc_hint, hint); } } @@ -82,7 +81,8 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map) } int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, - gfp_t flags, int node, bool round_robin) + gfp_t flags, int node, bool round_robin, + bool alloc_hint) { unsigned int bits_per_word; unsigned int i; @@ -114,9 +114,18 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, return 0; } + if (alloc_hint) { + if (init_alloc_hint(sb, flags)) + return -ENOMEM; + } else { + sb->alloc_hint = NULL; + } + sb->map = kcalloc_node(sb->map_nr, sizeof(*sb->map), flags, node); - if (!sb->map) + if (!sb->map) { + free_percpu(sb->alloc_hint); return -ENOMEM; + } for (i = 0; i < sb->map_nr; i++) { sb->map[i].depth = min(depth, bits_per_word); @@ -196,7 +205,7 @@ static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, return nr; } -int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) +static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) { unsigned int i, index; int nr = -1; @@ -228,10 +237,27 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) return nr; } + +int sbitmap_get(struct sbitmap *sb) +{ + int nr; + unsigned int hint, depth; + + if (WARN_ON_ONCE(unlikely(!sb->alloc_hint))) + return -1; + + depth = READ_ONCE(sb->depth); + hint = update_alloc_hint_before_get(sb, depth); + nr = __sbitmap_get(sb, hint); + update_alloc_hint_after_get(sb, depth, hint, nr); + + return nr; +} EXPORT_SYMBOL_GPL(sbitmap_get); -int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, - unsigned long shallow_depth) +static int __sbitmap_get_shallow(struct sbitmap *sb, + unsigned int alloc_hint, + unsigned long shallow_depth) { unsigned int i, index; int nr = -1; @@ -263,6 +289,22 @@ again: return nr; } + +int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) +{ + int nr; + unsigned int hint, depth; + + if (WARN_ON_ONCE(unlikely(!sb->alloc_hint))) + return -1; + + depth = READ_ONCE(sb->depth); + hint = update_alloc_hint_before_get(sb, depth); + nr = __sbitmap_get_shallow(sb, hint, shallow_depth); + update_alloc_hint_after_get(sb, depth, hint, nr); + + return nr; +} EXPORT_SYMBOL_GPL(sbitmap_get_shallow); bool sbitmap_any_bit_set(const struct sbitmap *sb) @@ -400,15 +442,10 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int i; ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node, - round_robin); + round_robin, true); if (ret) return ret; - if (init_alloc_hint(sbq, flags) != 0) { - sbitmap_free(&sbq->sb); - return -ENOMEM; - } - sbq->min_shallow_depth = UINT_MAX; sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); @@ -416,7 +453,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node); if (!sbq->ws) { - free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); return -ENOMEM; } @@ -458,32 +494,16 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_resize); int __sbitmap_queue_get(struct sbitmap_queue *sbq) { - unsigned int hint, depth; - int nr; - - depth = READ_ONCE(sbq->sb.depth); - hint = update_alloc_hint_before_get(sbq, depth); - nr = sbitmap_get(&sbq->sb, hint); - update_alloc_hint_after_get(sbq, depth, hint, nr); - - return nr; + return sbitmap_get(&sbq->sb); } EXPORT_SYMBOL_GPL(__sbitmap_queue_get); int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth) { - unsigned int hint, depth; - int nr; - WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth); - depth = READ_ONCE(sbq->sb.depth); - hint = update_alloc_hint_before_get(sbq, depth); - nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth); - update_alloc_hint_after_get(sbq, depth, hint, nr); - - return nr; + return sbitmap_get_shallow(&sbq->sb, shallow_depth); } EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow); @@ -592,7 +612,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, sbitmap_queue_wake_up(sbq); if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth)) - *per_cpu_ptr(sbq->alloc_hint, cpu) = nr; + *per_cpu_ptr(sbq->sb.alloc_hint, cpu) = nr; } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); @@ -630,7 +650,7 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) if (!first) seq_puts(m, ", "); first = false; - seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i)); + seq_printf(m, "%u", *per_cpu_ptr(sbq->sb.alloc_hint, i)); } seq_puts(m, "}\n"); -- cgit v1.2.3 From cbb9950b41dd9dfb7c2be3429ba09f83b8b1ff98 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:09 +0800 Subject: scsi: sbitmap: Export sbitmap_weight SCSI's .device_busy will be converted to sbitmap and sbitmap_weight is needed. Export the helper. The only existing user of sbitmap_weight() uses it to find out how many bits are set and not cleared. Align sbitmap_weight() meaning with this usage model. Link: https://lore.kernel.org/r/20210122023317.687987-6-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- include/linux/sbitmap.h | 10 ++++++++++ lib/sbitmap.c | 11 ++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 247776fcc02c..c65ba887dcc3 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -341,6 +341,16 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) */ void sbitmap_show(struct sbitmap *sb, struct seq_file *m); + +/** + * sbitmap_weight() - Return how many set and not cleared bits in a &struct + * sbitmap. + * @sb: Bitmap to check. + * + * Return: How many set and not cleared bits set + */ +unsigned int sbitmap_weight(const struct sbitmap *sb); + /** * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct * seq_file. diff --git a/lib/sbitmap.c b/lib/sbitmap.c index e395435654aa..73da26ad021e 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -334,20 +334,21 @@ static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set) return weight; } -static unsigned int sbitmap_weight(const struct sbitmap *sb) +static unsigned int sbitmap_cleared(const struct sbitmap *sb) { - return __sbitmap_weight(sb, true); + return __sbitmap_weight(sb, false); } -static unsigned int sbitmap_cleared(const struct sbitmap *sb) +unsigned int sbitmap_weight(const struct sbitmap *sb) { - return __sbitmap_weight(sb, false); + return __sbitmap_weight(sb, true) - sbitmap_cleared(sb); } +EXPORT_SYMBOL_GPL(sbitmap_weight); void sbitmap_show(struct sbitmap *sb, struct seq_file *m) { seq_printf(m, "depth=%u\n", sb->depth); - seq_printf(m, "busy=%u\n", sbitmap_weight(sb) - sbitmap_cleared(sb)); + seq_printf(m, "busy=%u\n", sbitmap_weight(sb)); seq_printf(m, "cleared=%u\n", sbitmap_cleared(sb)); seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift); seq_printf(m, "map_nr=%u\n", sb->map_nr); -- cgit v1.2.3 From 2d13b1ea9f4affdaa7af0e0e4a1358d28f80c54f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:10 +0800 Subject: scsi: sbitmap: Add sbitmap_calculate_shift() helper Move code for calculating default shift into a public helper which can be used by SCSI. Link: https://lore.kernel.org/r/20210122023317.687987-7-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- include/linux/sbitmap.h | 18 ++++++++++++++++++ lib/sbitmap.c | 16 +++------------- 2 files changed, 21 insertions(+), 13 deletions(-) (limited to 'lib') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index c65ba887dcc3..3087e1f15fdd 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -332,6 +332,24 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } +static inline int sbitmap_calculate_shift(unsigned int depth) +{ + int shift = ilog2(BITS_PER_LONG); + + /* + * If the bitmap is small, shrink the number of bits per word so + * we spread over a few cachelines, at least. If less than 4 + * bits, just forget about it, it's not going to work optimally + * anyway. + */ + if (depth >= 4) { + while ((4U << shift) > depth) + shift--; + } + + return shift; +} + /** * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. * @sb: Bitmap to show. diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 73da26ad021e..47b3691058eb 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -87,19 +87,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, unsigned int bits_per_word; unsigned int i; - if (shift < 0) { - shift = ilog2(BITS_PER_LONG); - /* - * If the bitmap is small, shrink the number of bits per word so - * we spread over a few cachelines, at least. If less than 4 - * bits, just forget about it, it's not going to work optimally - * anyway. - */ - if (depth >= 4) { - while ((4U << shift) > depth) - shift--; - } - } + if (shift < 0) + shift = sbitmap_calculate_shift(depth); + bits_per_word = 1U << shift; if (bits_per_word > BITS_PER_LONG) return -EINVAL; -- cgit v1.2.3 From 494215fbf298787e4ead16e4c68634d241336b02 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:20 -0500 Subject: lib: test_bitmap: clearly separate ERANGE from EINVAL tests. This block of tests was meant to find/flag incorrect use of the ":" and "/" separators (syntax errors) and invalid (zero) group len. However they were specified with an 8 bit width and 32 bit operations, so they really contained two errors (EINVAL and ERANGE). Promote them to 32 bit so it is clear what they are meant to target. Then we can add tests specific for ERANGE (no syntax errors, just doing 32bit op on 8 bit width, plus a typical 9-on-8 fencepost error). Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Acked-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/test_bitmap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 0ea0e8258f14..853a3a6ff59c 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -337,12 +337,12 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = { {-EINVAL, "-1", NULL, 8, 0}, {-EINVAL, "-0", NULL, 8, 0}, {-EINVAL, "10-1", NULL, 8, 0}, - {-EINVAL, "0-31:", NULL, 8, 0}, - {-EINVAL, "0-31:0", NULL, 8, 0}, - {-EINVAL, "0-31:0/", NULL, 8, 0}, - {-EINVAL, "0-31:0/0", NULL, 8, 0}, - {-EINVAL, "0-31:1/0", NULL, 8, 0}, - {-EINVAL, "0-31:10/1", NULL, 8, 0}, + {-EINVAL, "0-31:", NULL, 32, 0}, + {-EINVAL, "0-31:0", NULL, 32, 0}, + {-EINVAL, "0-31:0/", NULL, 32, 0}, + {-EINVAL, "0-31:0/0", NULL, 32, 0}, + {-EINVAL, "0-31:1/0", NULL, 32, 0}, + {-EINVAL, "0-31:10/1", NULL, 32, 0}, {-EOVERFLOW, "0-98765432123456789:10/1", NULL, 8, 0}, {-EINVAL, "a-31", NULL, 8, 0}, -- cgit v1.2.3 From 6fef5905fbd691aeb91093056b27d5ee7b106097 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:21 -0500 Subject: lib: test_bitmap: add tests to trigger ERANGE case. Add tests that specify a valid range, but one that is outside the width of the bitmap for which it is to be applied to. These should trigger an -ERANGE response from the code. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Acked-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/test_bitmap.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 853a3a6ff59c..0f2e91d0a84c 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -337,6 +337,8 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = { {-EINVAL, "-1", NULL, 8, 0}, {-EINVAL, "-0", NULL, 8, 0}, {-EINVAL, "10-1", NULL, 8, 0}, + {-ERANGE, "8-8", NULL, 8, 0}, + {-ERANGE, "0-31", NULL, 8, 0}, {-EINVAL, "0-31:", NULL, 32, 0}, {-EINVAL, "0-31:0", NULL, 32, 0}, {-EINVAL, "0-31:0/", NULL, 32, 0}, -- cgit v1.2.3 From 97330db3af9a41302d1ccb0f495fcb5b5da2cc44 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:22 -0500 Subject: lib: test_bitmap: add more start-end:offset/len tests There are inputs to bitmap_parselist() that would probably never be entered manually by a person, but might result from some kind of automated input generator. Things like ranges of length 1, or group lengths longer than nbits, overlaps, or offsets of zero. Adding these tests serve two purposes: 1) document what might seem odd but nonetheless valid input. 2) don't regress from what we currently accept as valid. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Acked-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/test_bitmap.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 0f2e91d0a84c..3c1c46deb8fe 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -34,6 +34,8 @@ static const unsigned long exp1[] __initconst = { BITMAP_FROM_U64(0x3333333311111111ULL), BITMAP_FROM_U64(0xffffffff77777777ULL), BITMAP_FROM_U64(0), + BITMAP_FROM_U64(0x00008000), + BITMAP_FROM_U64(0x80000000), }; static const unsigned long exp2[] __initconst = { @@ -334,6 +336,26 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = { {0, " , ,, , , ", &exp1[12 * step], 8, 0}, {0, " , ,, , , \n", &exp1[12 * step], 8, 0}, + {0, "0-0", &exp1[0], 32, 0}, + {0, "1-1", &exp1[1 * step], 32, 0}, + {0, "15-15", &exp1[13 * step], 32, 0}, + {0, "31-31", &exp1[14 * step], 32, 0}, + + {0, "0-0:0/1", &exp1[12 * step], 32, 0}, + {0, "0-0:1/1", &exp1[0], 32, 0}, + {0, "0-0:1/31", &exp1[0], 32, 0}, + {0, "0-0:31/31", &exp1[0], 32, 0}, + {0, "1-1:1/1", &exp1[1 * step], 32, 0}, + {0, "0-15:16/31", &exp1[2 * step], 32, 0}, + {0, "15-15:1/2", &exp1[13 * step], 32, 0}, + {0, "15-15:31/31", &exp1[13 * step], 32, 0}, + {0, "15-31:1/31", &exp1[13 * step], 32, 0}, + {0, "16-31:16/31", &exp1[3 * step], 32, 0}, + {0, "31-31:31/31", &exp1[14 * step], 32, 0}, + + {0, "0-31:1/3,1-31:1/3,2-31:1/3", &exp1[8 * step], 32, 0}, + {0, "1-10:8/12,8-31:24/29,0-31:0/3", &exp1[9 * step], 32, 0}, + {-EINVAL, "-1", NULL, 8, 0}, {-EINVAL, "-0", NULL, 8, 0}, {-EINVAL, "10-1", NULL, 8, 0}, -- cgit v1.2.3 From 9d7a3366b7028ae8dd16a0d7585cbf11b03b42a0 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:23 -0500 Subject: lib: bitmap: fold nbits into region struct This will reduce parameter passing and enable using nbits as part of future dynamic region parameter parsing. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Suggested-by: Yury Norov Acked-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/bitmap.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/bitmap.c b/lib/bitmap.c index 75006c4036e9..162e2850c622 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -487,24 +487,24 @@ EXPORT_SYMBOL(bitmap_print_to_pagebuf); /* * Region 9-38:4/10 describes the following bitmap structure: - * 0 9 12 18 38 - * .........****......****......****...... - * ^ ^ ^ ^ - * start off group_len end + * 0 9 12 18 38 N + * .........****......****......****.................. + * ^ ^ ^ ^ ^ + * start off group_len end nbits */ struct region { unsigned int start; unsigned int off; unsigned int group_len; unsigned int end; + unsigned int nbits; }; -static int bitmap_set_region(const struct region *r, - unsigned long *bitmap, int nbits) +static int bitmap_set_region(const struct region *r, unsigned long *bitmap) { unsigned int start; - if (r->end >= nbits) + if (r->end >= r->nbits) return -ERANGE; for (start = r->start; start <= r->end; start += r->group_len) @@ -640,7 +640,8 @@ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits) struct region r; long ret; - bitmap_zero(maskp, nmaskbits); + r.nbits = nmaskbits; + bitmap_zero(maskp, r.nbits); while (buf) { buf = bitmap_find_region(buf); @@ -655,7 +656,7 @@ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits) if (ret) return ret; - ret = bitmap_set_region(&r, maskp, nmaskbits); + ret = bitmap_set_region(&r, maskp); if (ret) return ret; } -- cgit v1.2.3 From f3c869caef648c541a7445f2a6ba2196d343f542 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:24 -0500 Subject: lib: bitmap: move ERANGE check from set_region to check_region It makes sense to do all the checks in check_region() and not 1/2 in check_region and 1/2 in set_region. Since set_region is called immediately after check_region, the net effect on runtime is zero, but it gets rid of an if (...) return... Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Acked-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/bitmap.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/bitmap.c b/lib/bitmap.c index 162e2850c622..833f152a2c43 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -500,17 +500,12 @@ struct region { unsigned int nbits; }; -static int bitmap_set_region(const struct region *r, unsigned long *bitmap) +static void bitmap_set_region(const struct region *r, unsigned long *bitmap) { unsigned int start; - if (r->end >= r->nbits) - return -ERANGE; - for (start = r->start; start <= r->end; start += r->group_len) bitmap_set(bitmap, start, min(r->end - start + 1, r->off)); - - return 0; } static int bitmap_check_region(const struct region *r) @@ -518,6 +513,9 @@ static int bitmap_check_region(const struct region *r) if (r->start > r->end || r->group_len == 0 || r->off > r->group_len) return -EINVAL; + if (r->end >= r->nbits) + return -ERANGE; + return 0; } @@ -656,9 +654,7 @@ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits) if (ret) return ret; - ret = bitmap_set_region(&r, maskp); - if (ret) - return ret; + bitmap_set_region(&r, maskp); } return 0; -- cgit v1.2.3 From 2c4885d24e64941702a8f81c8e83289823ba35d0 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:25 -0500 Subject: lib: bitmap: support "N" as an alias for size of bitmap While this is done for all bitmaps, the original use case in mind was for CPU masks and cpulist_parse() as described below. It seems that a common configuration is to use the 1st couple cores for housekeeping tasks. This tends to leave the remaining ones to form a pool of similarly configured cores to take on the real workload of interest to the user. So on machine A - with 32 cores, it could be 0-3 for "system" and then 4-31 being used in boot args like nohz_full=, or rcu_nocbs= as part of setting up the worker pool of CPUs. But then newer machine B is added, and it has 48 cores, and so while the 0-3 part remains unchanged, the pool setup cpu list becomes 4-47. Multiple deployment becomes easier when we can just simply replace 31 and 47 with "N" and let the system substitute in the actual number at boot; a number that it knows better than we do. Cc: Yury Norov Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Rasmus Villemoes Cc: Andy Shevchenko Suggested-by: Yury Norov # move it from CPU code Acked-by: Yury Norov Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- Documentation/admin-guide/kernel-parameters.rst | 7 +++++++ lib/bitmap.c | 22 +++++++++++++++++----- 2 files changed, 24 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst index 1132796a8d96..d6e3f67953a7 100644 --- a/Documentation/admin-guide/kernel-parameters.rst +++ b/Documentation/admin-guide/kernel-parameters.rst @@ -68,6 +68,13 @@ For example one can add to the command line following parameter: where the final item represents CPUs 100,101,125,126,150,151,... +The value "N" can be used to represent the numerically last CPU on the system, +i.e "foo_cpus=16-N" would be equivalent to "16-31" on a 32 core system. + +Keep in mind that "N" is dynamic, so if system changes cause the bitmap width +to change, such as less cores in the CPU list, then N and any ranges using N +will also change. Use the same on a small 4 core system, and "16-N" becomes +"16-3" and now the same boot input will be flagged as invalid (start > end). This document may not be entirely up to date and comprehensive. The command diff --git a/lib/bitmap.c b/lib/bitmap.c index 833f152a2c43..9f4626a4c95f 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -519,11 +519,17 @@ static int bitmap_check_region(const struct region *r) return 0; } -static const char *bitmap_getnum(const char *str, unsigned int *num) +static const char *bitmap_getnum(const char *str, unsigned int *num, + unsigned int lastbit) { unsigned long long n; unsigned int len; + if (str[0] == 'N') { + *num = lastbit; + return str + 1; + } + len = _parse_integer(str, 10, &n); if (!len) return ERR_PTR(-EINVAL); @@ -571,7 +577,9 @@ static const char *bitmap_find_region_reverse(const char *start, const char *end static const char *bitmap_parse_region(const char *str, struct region *r) { - str = bitmap_getnum(str, &r->start); + unsigned int lastbit = r->nbits - 1; + + str = bitmap_getnum(str, &r->start, lastbit); if (IS_ERR(str)) return str; @@ -581,7 +589,7 @@ static const char *bitmap_parse_region(const char *str, struct region *r) if (*str != '-') return ERR_PTR(-EINVAL); - str = bitmap_getnum(str + 1, &r->end); + str = bitmap_getnum(str + 1, &r->end, lastbit); if (IS_ERR(str)) return str; @@ -591,14 +599,14 @@ static const char *bitmap_parse_region(const char *str, struct region *r) if (*str != ':') return ERR_PTR(-EINVAL); - str = bitmap_getnum(str + 1, &r->off); + str = bitmap_getnum(str + 1, &r->off, lastbit); if (IS_ERR(str)) return str; if (*str != '/') return ERR_PTR(-EINVAL); - return bitmap_getnum(str + 1, &r->group_len); + return bitmap_getnum(str + 1, &r->group_len, lastbit); no_end: r->end = r->start; @@ -625,6 +633,10 @@ no_pattern: * From each group will be used only defined amount of bits. * Syntax: range:used_size/group_size * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769 + * The value 'N' can be used as a dynamically substituted token for the + * maximum allowed value; i.e (nmaskbits - 1). Keep in mind that it is + * dynamic, so if system changes cause the bitmap width to change, such + * as more cores in a CPU list, then any ranges using N will also change. * * Returns: 0 on success, -errno on invalid input strings. Error values: * -- cgit v1.2.3 From 99c58d1adbca25fb3ee2469bf0904e1e3e021f7e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 21 Feb 2021 03:08:26 -0500 Subject: lib: test_bitmap: add tests for "N" alias These are copies of existing tests, with just 31 --> N. This ensures the recently added "N" alias transparently works in any normally numeric fields of a region specification. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Andy Shevchenko Acked-by: Yury Norov Signed-off-by: Paul Gortmaker Signed-off-by: Paul E. McKenney --- lib/test_bitmap.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'lib') diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 3c1c46deb8fe..9cd575583180 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -353,6 +353,16 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = { {0, "16-31:16/31", &exp1[3 * step], 32, 0}, {0, "31-31:31/31", &exp1[14 * step], 32, 0}, + {0, "N-N", &exp1[14 * step], 32, 0}, + {0, "0-0:1/N", &exp1[0], 32, 0}, + {0, "0-0:N/N", &exp1[0], 32, 0}, + {0, "0-15:16/N", &exp1[2 * step], 32, 0}, + {0, "15-15:N/N", &exp1[13 * step], 32, 0}, + {0, "15-N:1/N", &exp1[13 * step], 32, 0}, + {0, "16-N:16/N", &exp1[3 * step], 32, 0}, + {0, "N-N:N/N", &exp1[14 * step], 32, 0}, + + {0, "0-N:1/3,1-N:1/3,2-N:1/3", &exp1[8 * step], 32, 0}, {0, "0-31:1/3,1-31:1/3,2-31:1/3", &exp1[8 * step], 32, 0}, {0, "1-10:8/12,8-31:24/29,0-31:0/3", &exp1[9 * step], 32, 0}, -- cgit v1.2.3 From a146fed56f8a06a6f17ac11ebdc7ca3f396bcb55 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 13 Jan 2021 17:05:56 +0100 Subject: kcsan: Make test follow KUnit style recommendations Per recently added KUnit style recommendations at Documentation/dev-tools/kunit/style.rst, make the following changes to the KCSAN test: 1. Rename 'kcsan-test.c' to 'kcsan_test.c'. 2. Rename suite name 'kcsan-test' to 'kcsan'. 3. Rename CONFIG_KCSAN_TEST to CONFIG_KCSAN_KUNIT_TEST and default to KUNIT_ALL_TESTS. Reviewed-by: David Gow Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- kernel/kcsan/Makefile | 4 +- kernel/kcsan/kcsan-test.c | 1207 --------------------------------------------- kernel/kcsan/kcsan_test.c | 1207 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.kcsan | 5 +- 4 files changed, 1212 insertions(+), 1211 deletions(-) delete mode 100644 kernel/kcsan/kcsan-test.c create mode 100644 kernel/kcsan/kcsan_test.c (limited to 'lib') diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index 65ca5539c470..c2bb07f5bcc7 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -13,5 +13,5 @@ CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \ obj-y := core.o debugfs.o report.o obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o -CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer -obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o +CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan-test.c deleted file mode 100644 index ebe7fd245104..000000000000 --- a/kernel/kcsan/kcsan-test.c +++ /dev/null @@ -1,1207 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * KCSAN test with various race scenarious to test runtime behaviour. Since the - * interface with which KCSAN's reports are obtained is via the console, this is - * the output we should verify. For each test case checks the presence (or - * absence) of generated reports. Relies on 'console' tracepoint to capture - * reports as they appear in the kernel log. - * - * Makes use of KUnit for test organization, and the Torture framework for test - * thread control. - * - * Copyright (C) 2020, Google LLC. - * Author: Marco Elver - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE -#define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) -#else -#define __KCSAN_ACCESS_RW(alt) (alt) -#endif - -/* Points to current test-case memory access "kernels". */ -static void (*access_kernels[2])(void); - -static struct task_struct **threads; /* Lists of threads. */ -static unsigned long end_time; /* End time of test. */ - -/* Report as observed from console. */ -static struct { - spinlock_t lock; - int nlines; - char lines[3][512]; -} observed = { - .lock = __SPIN_LOCK_UNLOCKED(observed.lock), -}; - -/* Setup test checking loop. */ -static __no_kcsan inline void -begin_test_checks(void (*func1)(void), void (*func2)(void)) -{ - kcsan_disable_current(); - - /* - * Require at least as long as KCSAN_REPORT_ONCE_IN_MS, to ensure at - * least one race is reported. - */ - end_time = jiffies + msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS + 500); - - /* Signal start; release potential initialization of shared data. */ - smp_store_release(&access_kernels[0], func1); - smp_store_release(&access_kernels[1], func2); -} - -/* End test checking loop. */ -static __no_kcsan inline bool -end_test_checks(bool stop) -{ - if (!stop && time_before(jiffies, end_time)) { - /* Continue checking */ - might_sleep(); - return false; - } - - kcsan_enable_current(); - return true; -} - -/* - * Probe for console output: checks if a race was reported, and obtains observed - * lines of interest. - */ -__no_kcsan -static void probe_console(void *ignore, const char *buf, size_t len) -{ - unsigned long flags; - int nlines; - - /* - * Note that KCSAN reports under a global lock, so we do not risk the - * possibility of having multiple reports interleaved. If that were the - * case, we'd expect tests to fail. - */ - - spin_lock_irqsave(&observed.lock, flags); - nlines = observed.nlines; - - if (strnstr(buf, "BUG: KCSAN: ", len) && strnstr(buf, "test_", len)) { - /* - * KCSAN report and related to the test. - * - * The provided @buf is not NUL-terminated; copy no more than - * @len bytes and let strscpy() add the missing NUL-terminator. - */ - strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); - nlines = 1; - } else if ((nlines == 1 || nlines == 2) && strnstr(buf, "bytes by", len)) { - strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); - - if (strnstr(buf, "race at unknown origin", len)) { - if (WARN_ON(nlines != 2)) - goto out; - - /* No second line of interest. */ - strcpy(observed.lines[nlines++], ""); - } - } - -out: - WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ - spin_unlock_irqrestore(&observed.lock, flags); -} - -/* Check if a report related to the test exists. */ -__no_kcsan -static bool report_available(void) -{ - return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); -} - -/* Report information we expect in a report. */ -struct expect_report { - /* Access information of both accesses. */ - struct { - void *fn; /* Function pointer to expected function of top frame. */ - void *addr; /* Address of access; unchecked if NULL. */ - size_t size; /* Size of access; unchecked if @addr is NULL. */ - int type; /* Access type, see KCSAN_ACCESS definitions. */ - } access[2]; -}; - -/* Check observed report matches information in @r. */ -__no_kcsan -static bool report_matches(const struct expect_report *r) -{ - const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; - bool ret = false; - unsigned long flags; - typeof(observed.lines) expect; - const char *end; - char *cur; - int i; - - /* Doubled-checked locking. */ - if (!report_available()) - return false; - - /* Generate expected report contents. */ - - /* Title */ - cur = expect[0]; - end = &expect[0][sizeof(expect[0]) - 1]; - cur += scnprintf(cur, end - cur, "BUG: KCSAN: %s in ", - is_assert ? "assert: race" : "data-race"); - if (r->access[1].fn) { - char tmp[2][64]; - int cmp; - - /* Expect lexographically sorted function names in title. */ - scnprintf(tmp[0], sizeof(tmp[0]), "%pS", r->access[0].fn); - scnprintf(tmp[1], sizeof(tmp[1]), "%pS", r->access[1].fn); - cmp = strcmp(tmp[0], tmp[1]); - cur += scnprintf(cur, end - cur, "%ps / %ps", - cmp < 0 ? r->access[0].fn : r->access[1].fn, - cmp < 0 ? r->access[1].fn : r->access[0].fn); - } else { - scnprintf(cur, end - cur, "%pS", r->access[0].fn); - /* The exact offset won't match, remove it. */ - cur = strchr(expect[0], '+'); - if (cur) - *cur = '\0'; - } - - /* Access 1 */ - cur = expect[1]; - end = &expect[1][sizeof(expect[1]) - 1]; - if (!r->access[1].fn) - cur += scnprintf(cur, end - cur, "race at unknown origin, with "); - - /* Access 1 & 2 */ - for (i = 0; i < 2; ++i) { - const int ty = r->access[i].type; - const char *const access_type = - (ty & KCSAN_ACCESS_ASSERT) ? - ((ty & KCSAN_ACCESS_WRITE) ? - "assert no accesses" : - "assert no writes") : - ((ty & KCSAN_ACCESS_WRITE) ? - ((ty & KCSAN_ACCESS_COMPOUND) ? - "read-write" : - "write") : - "read"); - const char *const access_type_aux = - (ty & KCSAN_ACCESS_ATOMIC) ? - " (marked)" : - ((ty & KCSAN_ACCESS_SCOPED) ? " (scoped)" : ""); - - if (i == 1) { - /* Access 2 */ - cur = expect[2]; - end = &expect[2][sizeof(expect[2]) - 1]; - - if (!r->access[1].fn) { - /* Dummy string if no second access is available. */ - strcpy(cur, ""); - break; - } - } - - cur += scnprintf(cur, end - cur, "%s%s to ", access_type, - access_type_aux); - - if (r->access[i].addr) /* Address is optional. */ - cur += scnprintf(cur, end - cur, "0x%px of %zu bytes", - r->access[i].addr, r->access[i].size); - } - - spin_lock_irqsave(&observed.lock, flags); - if (!report_available()) - goto out; /* A new report is being captured. */ - - /* Finally match expected output to what we actually observed. */ - ret = strstr(observed.lines[0], expect[0]) && - /* Access info may appear in any order. */ - ((strstr(observed.lines[1], expect[1]) && - strstr(observed.lines[2], expect[2])) || - (strstr(observed.lines[1], expect[2]) && - strstr(observed.lines[2], expect[1]))); -out: - spin_unlock_irqrestore(&observed.lock, flags); - return ret; -} - -/* ===== Test kernels ===== */ - -static long test_sink; -static long test_var; -/* @test_array should be large enough to fall into multiple watchpoint slots. */ -static long test_array[3 * PAGE_SIZE / sizeof(long)]; -static struct { - long val[8]; -} test_struct; -static DEFINE_SEQLOCK(test_seqlock); - -/* - * Helper to avoid compiler optimizing out reads, and to generate source values - * for writes. - */ -__no_kcsan -static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); } - -static noinline void test_kernel_read(void) { sink_value(test_var); } - -static noinline void test_kernel_write(void) -{ - test_var = READ_ONCE_NOCHECK(test_sink) + 1; -} - -static noinline void test_kernel_write_nochange(void) { test_var = 42; } - -/* Suffixed by value-change exception filter. */ -static noinline void test_kernel_write_nochange_rcu(void) { test_var = 42; } - -static noinline void test_kernel_read_atomic(void) -{ - sink_value(READ_ONCE(test_var)); -} - -static noinline void test_kernel_write_atomic(void) -{ - WRITE_ONCE(test_var, READ_ONCE_NOCHECK(test_sink) + 1); -} - -static noinline void test_kernel_atomic_rmw(void) -{ - /* Use builtin, so we can set up the "bad" atomic/non-atomic scenario. */ - __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED); -} - -__no_kcsan -static noinline void test_kernel_write_uninstrumented(void) { test_var++; } - -static noinline void test_kernel_data_race(void) { data_race(test_var++); } - -static noinline void test_kernel_assert_writer(void) -{ - ASSERT_EXCLUSIVE_WRITER(test_var); -} - -static noinline void test_kernel_assert_access(void) -{ - ASSERT_EXCLUSIVE_ACCESS(test_var); -} - -#define TEST_CHANGE_BITS 0xff00ff00 - -static noinline void test_kernel_change_bits(void) -{ - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { - /* - * Avoid race of unknown origin for this test, just pretend they - * are atomic. - */ - kcsan_nestable_atomic_begin(); - test_var ^= TEST_CHANGE_BITS; - kcsan_nestable_atomic_end(); - } else - WRITE_ONCE(test_var, READ_ONCE(test_var) ^ TEST_CHANGE_BITS); -} - -static noinline void test_kernel_assert_bits_change(void) -{ - ASSERT_EXCLUSIVE_BITS(test_var, TEST_CHANGE_BITS); -} - -static noinline void test_kernel_assert_bits_nochange(void) -{ - ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); -} - -/* To check that scoped assertions do trigger anywhere in scope. */ -static noinline void test_enter_scope(void) -{ - int x = 0; - - /* Unrelated accesses to scoped assert. */ - READ_ONCE(test_sink); - kcsan_check_read(&x, sizeof(x)); -} - -static noinline void test_kernel_assert_writer_scoped(void) -{ - ASSERT_EXCLUSIVE_WRITER_SCOPED(test_var); - test_enter_scope(); -} - -static noinline void test_kernel_assert_access_scoped(void) -{ - ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_var); - test_enter_scope(); -} - -static noinline void test_kernel_rmw_array(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(test_array); ++i) - test_array[i]++; -} - -static noinline void test_kernel_write_struct(void) -{ - kcsan_check_write(&test_struct, sizeof(test_struct)); - kcsan_disable_current(); - test_struct.val[3]++; /* induce value change */ - kcsan_enable_current(); -} - -static noinline void test_kernel_write_struct_part(void) -{ - test_struct.val[3] = 42; -} - -static noinline void test_kernel_read_struct_zero_size(void) -{ - kcsan_check_read(&test_struct.val[3], 0); -} - -static noinline void test_kernel_jiffies_reader(void) -{ - sink_value((long)jiffies); -} - -static noinline void test_kernel_seqlock_reader(void) -{ - unsigned int seq; - - do { - seq = read_seqbegin(&test_seqlock); - sink_value(test_var); - } while (read_seqretry(&test_seqlock, seq)); -} - -static noinline void test_kernel_seqlock_writer(void) -{ - unsigned long flags; - - write_seqlock_irqsave(&test_seqlock, flags); - test_var++; - write_sequnlock_irqrestore(&test_seqlock, flags); -} - -static noinline void test_kernel_atomic_builtins(void) -{ - /* - * Generate concurrent accesses, expecting no reports, ensuring KCSAN - * treats builtin atomics as actually atomic. - */ - __atomic_load_n(&test_var, __ATOMIC_RELAXED); -} - -/* ===== Test cases ===== */ - -/* Simple test with normal data race. */ -__no_kcsan -static void test_basic(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - static const struct expect_report never = { - .access = { - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - bool match_expect = false; - bool match_never = false; - - begin_test_checks(test_kernel_write, test_kernel_read); - do { - match_expect |= report_matches(&expect); - match_never = report_matches(&never); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_TRUE(test, match_expect); - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* - * Stress KCSAN with lots of concurrent races on different addresses until - * timeout. - */ -__no_kcsan -static void test_concurrent_races(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - /* NULL will match any address. */ - { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, - { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(0) }, - }, - }; - static const struct expect_report never = { - .access = { - { test_kernel_rmw_array, NULL, 0, 0 }, - { test_kernel_rmw_array, NULL, 0, 0 }, - }, - }; - bool match_expect = false; - bool match_never = false; - - begin_test_checks(test_kernel_rmw_array, test_kernel_rmw_array); - do { - match_expect |= report_matches(&expect); - match_never |= report_matches(&never); - } while (!end_test_checks(false)); - KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check matches exist. */ - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* Test the KCSAN_REPORT_VALUE_CHANGE_ONLY option. */ -__no_kcsan -static void test_novalue_change(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write_nochange, test_kernel_read); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) - KUNIT_EXPECT_FALSE(test, match_expect); - else - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* - * Test that the rules where the KCSAN_REPORT_VALUE_CHANGE_ONLY option should - * never apply work. - */ -__no_kcsan -static void test_novalue_change_exception(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* Test that data races of unknown origin are reported. */ -__no_kcsan -static void test_unknown_origin(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - { NULL }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write_uninstrumented, test_kernel_read); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN)) - KUNIT_EXPECT_TRUE(test, match_expect); - else - KUNIT_EXPECT_FALSE(test, match_expect); -} - -/* Test KCSAN_ASSUME_PLAIN_WRITES_ATOMIC if it is selected. */ -__no_kcsan -static void test_write_write_assume_atomic(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write, test_kernel_write); - do { - sink_value(READ_ONCE(test_var)); /* induce value-change */ - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) - KUNIT_EXPECT_FALSE(test, match_expect); - else - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* - * Test that data races with writes larger than word-size are always reported, - * even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. - */ -__no_kcsan -static void test_write_write_struct(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write_struct, test_kernel_write_struct); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* - * Test that data races where only one write is larger than word-size are always - * reported, even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. - */ -__no_kcsan -static void test_write_write_struct_part(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - { test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_write_struct, test_kernel_write_struct_part); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* Test that races with atomic accesses never result in reports. */ -__no_kcsan -static void test_read_atomic_write_atomic(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_read_atomic, test_kernel_write_atomic); - do { - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* Test that a race with an atomic and plain access result in reports. */ -__no_kcsan -static void test_read_plain_atomic_write(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - { test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, - }, - }; - bool match_expect = false; - - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; - - begin_test_checks(test_kernel_read, test_kernel_write_atomic); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* Test that atomic RMWs generate correct report. */ -__no_kcsan -static void test_read_plain_atomic_rmw(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - { test_kernel_atomic_rmw, &test_var, sizeof(test_var), - KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, - }, - }; - bool match_expect = false; - - if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) - return; - - begin_test_checks(test_kernel_read, test_kernel_atomic_rmw); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -/* Zero-sized accesses should never cause data race reports. */ -__no_kcsan -static void test_zero_size_access(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - }, - }; - const struct expect_report never = { - .access = { - { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, - { test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 }, - }, - }; - bool match_expect = false; - bool match_never = false; - - begin_test_checks(test_kernel_write_struct, test_kernel_read_struct_zero_size); - do { - match_expect |= report_matches(&expect); - match_never = report_matches(&never); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check. */ - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* Test the data_race() macro. */ -__no_kcsan -static void test_data_race(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_data_race, test_kernel_data_race); - do { - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -__no_kcsan -static void test_assert_exclusive_writer(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, - { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_assert_writer, test_kernel_write_nochange); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -__no_kcsan -static void test_assert_exclusive_access(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_assert_access, test_kernel_read); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -__no_kcsan -static void test_assert_exclusive_access_writer(struct kunit *test) -{ - const struct expect_report expect_access_writer = { - .access = { - { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, - { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, - }, - }; - const struct expect_report expect_access_access = { - .access = { - { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, - { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, - }, - }; - const struct expect_report never = { - .access = { - { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, - { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, - }, - }; - bool match_expect_access_writer = false; - bool match_expect_access_access = false; - bool match_never = false; - - begin_test_checks(test_kernel_assert_access, test_kernel_assert_writer); - do { - match_expect_access_writer |= report_matches(&expect_access_writer); - match_expect_access_access |= report_matches(&expect_access_access); - match_never |= report_matches(&never); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_TRUE(test, match_expect_access_writer); - KUNIT_EXPECT_TRUE(test, match_expect_access_access); - KUNIT_EXPECT_FALSE(test, match_never); -} - -__no_kcsan -static void test_assert_exclusive_bits_change(struct kunit *test) -{ - const struct expect_report expect = { - .access = { - { test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, - { test_kernel_change_bits, &test_var, sizeof(test_var), - KCSAN_ACCESS_WRITE | (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) ? 0 : KCSAN_ACCESS_ATOMIC) }, - }, - }; - bool match_expect = false; - - begin_test_checks(test_kernel_assert_bits_change, test_kernel_change_bits); - do { - match_expect = report_matches(&expect); - } while (!end_test_checks(match_expect)); - KUNIT_EXPECT_TRUE(test, match_expect); -} - -__no_kcsan -static void test_assert_exclusive_bits_nochange(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_assert_bits_nochange, test_kernel_change_bits); - do { - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -__no_kcsan -static void test_assert_exclusive_writer_scoped(struct kunit *test) -{ - const struct expect_report expect_start = { - .access = { - { test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, - { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - }, - }; - const struct expect_report expect_anywhere = { - .access = { - { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, - { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, - }, - }; - bool match_expect_start = false; - bool match_expect_anywhere = false; - - begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); - do { - match_expect_start |= report_matches(&expect_start); - match_expect_anywhere |= report_matches(&expect_anywhere); - } while (!end_test_checks(match_expect_start && match_expect_anywhere)); - KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_anywhere); -} - -__no_kcsan -static void test_assert_exclusive_access_scoped(struct kunit *test) -{ - const struct expect_report expect_start1 = { - .access = { - { test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - const struct expect_report expect_start2 = { - .access = { expect_start1.access[0], expect_start1.access[0] }, - }; - const struct expect_report expect_inscope = { - .access = { - { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, - { test_kernel_read, &test_var, sizeof(test_var), 0 }, - }, - }; - bool match_expect_start = false; - bool match_expect_inscope = false; - - begin_test_checks(test_kernel_assert_access_scoped, test_kernel_read); - end_time += msecs_to_jiffies(1000); /* This test requires a bit more time. */ - do { - match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); - match_expect_inscope |= report_matches(&expect_inscope); - } while (!end_test_checks(match_expect_start && match_expect_inscope)); - KUNIT_EXPECT_TRUE(test, match_expect_start); - KUNIT_EXPECT_TRUE(test, match_expect_inscope); -} - -/* - * jiffies is special (declared to be volatile) and its accesses are typically - * not marked; this test ensures that the compiler nor KCSAN gets confused about - * jiffies's declaration on different architectures. - */ -__no_kcsan -static void test_jiffies_noreport(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_jiffies_reader, test_kernel_jiffies_reader); - do { - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* Test that racing accesses in seqlock critical sections are not reported. */ -__no_kcsan -static void test_seqlock_noreport(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_seqlock_reader, test_kernel_seqlock_writer); - do { - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* - * Test atomic builtins work and required instrumentation functions exist. We - * also test that KCSAN understands they're atomic by racing with them via - * test_kernel_atomic_builtins(), and expect no reports. - * - * The atomic builtins _SHOULD NOT_ be used in normal kernel code! - */ -static void test_atomic_builtins(struct kunit *test) -{ - bool match_never = false; - - begin_test_checks(test_kernel_atomic_builtins, test_kernel_atomic_builtins); - do { - long tmp; - - kcsan_enable_current(); - - __atomic_store_n(&test_var, 42L, __ATOMIC_RELAXED); - KUNIT_EXPECT_EQ(test, 42L, __atomic_load_n(&test_var, __ATOMIC_RELAXED)); - - KUNIT_EXPECT_EQ(test, 42L, __atomic_exchange_n(&test_var, 20, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 20L, test_var); - - tmp = 20L; - KUNIT_EXPECT_TRUE(test, __atomic_compare_exchange_n(&test_var, &tmp, 30L, - 0, __ATOMIC_RELAXED, - __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, tmp, 20L); - KUNIT_EXPECT_EQ(test, test_var, 30L); - KUNIT_EXPECT_FALSE(test, __atomic_compare_exchange_n(&test_var, &tmp, 40L, - 1, __ATOMIC_RELAXED, - __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, tmp, 30L); - KUNIT_EXPECT_EQ(test, test_var, 30L); - - KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 31L, __atomic_fetch_sub(&test_var, 1, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_and(&test_var, 0xf, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 14L, __atomic_fetch_xor(&test_var, 0xf, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 1L, __atomic_fetch_or(&test_var, 0xf0, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, 241L, __atomic_fetch_nand(&test_var, 0xf, __ATOMIC_RELAXED)); - KUNIT_EXPECT_EQ(test, -2L, test_var); - - __atomic_thread_fence(__ATOMIC_SEQ_CST); - __atomic_signal_fence(__ATOMIC_SEQ_CST); - - kcsan_disable_current(); - - match_never = report_available(); - } while (!end_test_checks(match_never)); - KUNIT_EXPECT_FALSE(test, match_never); -} - -/* - * Each test case is run with different numbers of threads. Until KUnit supports - * passing arguments for each test case, we encode #threads in the test case - * name (read by get_num_threads()). [The '-' was chosen as a stylistic - * preference to separate test name and #threads.] - * - * The thread counts are chosen to cover potentially interesting boundaries and - * corner cases (range 2-5), and then stress the system with larger counts. - */ -#define KCSAN_KUNIT_CASE(test_name) \ - { .run_case = test_name, .name = #test_name "-02" }, \ - { .run_case = test_name, .name = #test_name "-03" }, \ - { .run_case = test_name, .name = #test_name "-04" }, \ - { .run_case = test_name, .name = #test_name "-05" }, \ - { .run_case = test_name, .name = #test_name "-08" }, \ - { .run_case = test_name, .name = #test_name "-16" } - -static struct kunit_case kcsan_test_cases[] = { - KCSAN_KUNIT_CASE(test_basic), - KCSAN_KUNIT_CASE(test_concurrent_races), - KCSAN_KUNIT_CASE(test_novalue_change), - KCSAN_KUNIT_CASE(test_novalue_change_exception), - KCSAN_KUNIT_CASE(test_unknown_origin), - KCSAN_KUNIT_CASE(test_write_write_assume_atomic), - KCSAN_KUNIT_CASE(test_write_write_struct), - KCSAN_KUNIT_CASE(test_write_write_struct_part), - KCSAN_KUNIT_CASE(test_read_atomic_write_atomic), - KCSAN_KUNIT_CASE(test_read_plain_atomic_write), - KCSAN_KUNIT_CASE(test_read_plain_atomic_rmw), - KCSAN_KUNIT_CASE(test_zero_size_access), - KCSAN_KUNIT_CASE(test_data_race), - KCSAN_KUNIT_CASE(test_assert_exclusive_writer), - KCSAN_KUNIT_CASE(test_assert_exclusive_access), - KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer), - KCSAN_KUNIT_CASE(test_assert_exclusive_bits_change), - KCSAN_KUNIT_CASE(test_assert_exclusive_bits_nochange), - KCSAN_KUNIT_CASE(test_assert_exclusive_writer_scoped), - KCSAN_KUNIT_CASE(test_assert_exclusive_access_scoped), - KCSAN_KUNIT_CASE(test_jiffies_noreport), - KCSAN_KUNIT_CASE(test_seqlock_noreport), - KCSAN_KUNIT_CASE(test_atomic_builtins), - {}, -}; - -/* ===== End test cases ===== */ - -/* Get number of threads encoded in test name. */ -static bool __no_kcsan -get_num_threads(const char *test, int *nthreads) -{ - int len = strlen(test); - - if (WARN_ON(len < 3)) - return false; - - *nthreads = test[len - 1] - '0'; - *nthreads += (test[len - 2] - '0') * 10; - - if (WARN_ON(*nthreads < 0)) - return false; - - return true; -} - -/* Concurrent accesses from interrupts. */ -__no_kcsan -static void access_thread_timer(struct timer_list *timer) -{ - static atomic_t cnt = ATOMIC_INIT(0); - unsigned int idx; - void (*func)(void); - - idx = (unsigned int)atomic_inc_return(&cnt) % ARRAY_SIZE(access_kernels); - /* Acquire potential initialization. */ - func = smp_load_acquire(&access_kernels[idx]); - if (func) - func(); -} - -/* The main loop for each thread. */ -__no_kcsan -static int access_thread(void *arg) -{ - struct timer_list timer; - unsigned int cnt = 0; - unsigned int idx; - void (*func)(void); - - timer_setup_on_stack(&timer, access_thread_timer, 0); - do { - might_sleep(); - - if (!timer_pending(&timer)) - mod_timer(&timer, jiffies + 1); - else { - /* Iterate through all kernels. */ - idx = cnt++ % ARRAY_SIZE(access_kernels); - /* Acquire potential initialization. */ - func = smp_load_acquire(&access_kernels[idx]); - if (func) - func(); - } - } while (!torture_must_stop()); - del_timer_sync(&timer); - destroy_timer_on_stack(&timer); - - torture_kthread_stopping("access_thread"); - return 0; -} - -__no_kcsan -static int test_init(struct kunit *test) -{ - unsigned long flags; - int nthreads; - int i; - - spin_lock_irqsave(&observed.lock, flags); - for (i = 0; i < ARRAY_SIZE(observed.lines); ++i) - observed.lines[i][0] = '\0'; - observed.nlines = 0; - spin_unlock_irqrestore(&observed.lock, flags); - - if (!torture_init_begin((char *)test->name, 1)) - return -EBUSY; - - if (!get_num_threads(test->name, &nthreads)) - goto err; - - if (WARN_ON(threads)) - goto err; - - for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) { - if (WARN_ON(access_kernels[i])) - goto err; - } - - if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { - /* - * Without any preemption, keep 2 CPUs free for other tasks, one - * of which is the main test case function checking for - * completion or failure. - */ - const int min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0; - const int min_required_cpus = 2 + min_unused_cpus; - - if (num_online_cpus() < min_required_cpus) { - pr_err("%s: too few online CPUs (%u < %d) for test", - test->name, num_online_cpus(), min_required_cpus); - goto err; - } else if (nthreads > num_online_cpus() - min_unused_cpus) { - nthreads = num_online_cpus() - min_unused_cpus; - pr_warn("%s: limiting number of threads to %d\n", - test->name, nthreads); - } - } - - if (nthreads) { - threads = kcalloc(nthreads + 1, sizeof(struct task_struct *), - GFP_KERNEL); - if (WARN_ON(!threads)) - goto err; - - threads[nthreads] = NULL; - for (i = 0; i < nthreads; ++i) { - if (torture_create_kthread(access_thread, NULL, - threads[i])) - goto err; - } - } - - torture_init_end(); - - return 0; - -err: - kfree(threads); - threads = NULL; - torture_init_end(); - return -EINVAL; -} - -__no_kcsan -static void test_exit(struct kunit *test) -{ - struct task_struct **stop_thread; - int i; - - if (torture_cleanup_begin()) - return; - - for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) - WRITE_ONCE(access_kernels[i], NULL); - - if (threads) { - for (stop_thread = threads; *stop_thread; stop_thread++) - torture_stop_kthread(reader_thread, *stop_thread); - - kfree(threads); - threads = NULL; - } - - torture_cleanup_end(); -} - -static struct kunit_suite kcsan_test_suite = { - .name = "kcsan-test", - .test_cases = kcsan_test_cases, - .init = test_init, - .exit = test_exit, -}; -static struct kunit_suite *kcsan_test_suites[] = { &kcsan_test_suite, NULL }; - -__no_kcsan -static void register_tracepoints(struct tracepoint *tp, void *ignore) -{ - check_trace_callback_type_console(probe_console); - if (!strcmp(tp->name, "console")) - WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); -} - -__no_kcsan -static void unregister_tracepoints(struct tracepoint *tp, void *ignore) -{ - if (!strcmp(tp->name, "console")) - tracepoint_probe_unregister(tp, probe_console, NULL); -} - -/* - * We only want to do tracepoints setup and teardown once, therefore we have to - * customize the init and exit functions and cannot rely on kunit_test_suite(). - */ -static int __init kcsan_test_init(void) -{ - /* - * Because we want to be able to build the test as a module, we need to - * iterate through all known tracepoints, since the static registration - * won't work here. - */ - for_each_kernel_tracepoint(register_tracepoints, NULL); - return __kunit_test_suites_init(kcsan_test_suites); -} - -static void kcsan_test_exit(void) -{ - __kunit_test_suites_exit(kcsan_test_suites); - for_each_kernel_tracepoint(unregister_tracepoints, NULL); - tracepoint_synchronize_unregister(); -} - -late_initcall(kcsan_test_init); -module_exit(kcsan_test_exit); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Marco Elver "); diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c new file mode 100644 index 000000000000..f16f632eb416 --- /dev/null +++ b/kernel/kcsan/kcsan_test.c @@ -0,0 +1,1207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KCSAN test with various race scenarious to test runtime behaviour. Since the + * interface with which KCSAN's reports are obtained is via the console, this is + * the output we should verify. For each test case checks the presence (or + * absence) of generated reports. Relies on 'console' tracepoint to capture + * reports as they appear in the kernel log. + * + * Makes use of KUnit for test organization, and the Torture framework for test + * thread control. + * + * Copyright (C) 2020, Google LLC. + * Author: Marco Elver + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE +#define __KCSAN_ACCESS_RW(alt) (KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE) +#else +#define __KCSAN_ACCESS_RW(alt) (alt) +#endif + +/* Points to current test-case memory access "kernels". */ +static void (*access_kernels[2])(void); + +static struct task_struct **threads; /* Lists of threads. */ +static unsigned long end_time; /* End time of test. */ + +/* Report as observed from console. */ +static struct { + spinlock_t lock; + int nlines; + char lines[3][512]; +} observed = { + .lock = __SPIN_LOCK_UNLOCKED(observed.lock), +}; + +/* Setup test checking loop. */ +static __no_kcsan inline void +begin_test_checks(void (*func1)(void), void (*func2)(void)) +{ + kcsan_disable_current(); + + /* + * Require at least as long as KCSAN_REPORT_ONCE_IN_MS, to ensure at + * least one race is reported. + */ + end_time = jiffies + msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS + 500); + + /* Signal start; release potential initialization of shared data. */ + smp_store_release(&access_kernels[0], func1); + smp_store_release(&access_kernels[1], func2); +} + +/* End test checking loop. */ +static __no_kcsan inline bool +end_test_checks(bool stop) +{ + if (!stop && time_before(jiffies, end_time)) { + /* Continue checking */ + might_sleep(); + return false; + } + + kcsan_enable_current(); + return true; +} + +/* + * Probe for console output: checks if a race was reported, and obtains observed + * lines of interest. + */ +__no_kcsan +static void probe_console(void *ignore, const char *buf, size_t len) +{ + unsigned long flags; + int nlines; + + /* + * Note that KCSAN reports under a global lock, so we do not risk the + * possibility of having multiple reports interleaved. If that were the + * case, we'd expect tests to fail. + */ + + spin_lock_irqsave(&observed.lock, flags); + nlines = observed.nlines; + + if (strnstr(buf, "BUG: KCSAN: ", len) && strnstr(buf, "test_", len)) { + /* + * KCSAN report and related to the test. + * + * The provided @buf is not NUL-terminated; copy no more than + * @len bytes and let strscpy() add the missing NUL-terminator. + */ + strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0]))); + nlines = 1; + } else if ((nlines == 1 || nlines == 2) && strnstr(buf, "bytes by", len)) { + strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0]))); + + if (strnstr(buf, "race at unknown origin", len)) { + if (WARN_ON(nlines != 2)) + goto out; + + /* No second line of interest. */ + strcpy(observed.lines[nlines++], ""); + } + } + +out: + WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */ + spin_unlock_irqrestore(&observed.lock, flags); +} + +/* Check if a report related to the test exists. */ +__no_kcsan +static bool report_available(void) +{ + return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines); +} + +/* Report information we expect in a report. */ +struct expect_report { + /* Access information of both accesses. */ + struct { + void *fn; /* Function pointer to expected function of top frame. */ + void *addr; /* Address of access; unchecked if NULL. */ + size_t size; /* Size of access; unchecked if @addr is NULL. */ + int type; /* Access type, see KCSAN_ACCESS definitions. */ + } access[2]; +}; + +/* Check observed report matches information in @r. */ +__no_kcsan +static bool report_matches(const struct expect_report *r) +{ + const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; + bool ret = false; + unsigned long flags; + typeof(observed.lines) expect; + const char *end; + char *cur; + int i; + + /* Doubled-checked locking. */ + if (!report_available()) + return false; + + /* Generate expected report contents. */ + + /* Title */ + cur = expect[0]; + end = &expect[0][sizeof(expect[0]) - 1]; + cur += scnprintf(cur, end - cur, "BUG: KCSAN: %s in ", + is_assert ? "assert: race" : "data-race"); + if (r->access[1].fn) { + char tmp[2][64]; + int cmp; + + /* Expect lexographically sorted function names in title. */ + scnprintf(tmp[0], sizeof(tmp[0]), "%pS", r->access[0].fn); + scnprintf(tmp[1], sizeof(tmp[1]), "%pS", r->access[1].fn); + cmp = strcmp(tmp[0], tmp[1]); + cur += scnprintf(cur, end - cur, "%ps / %ps", + cmp < 0 ? r->access[0].fn : r->access[1].fn, + cmp < 0 ? r->access[1].fn : r->access[0].fn); + } else { + scnprintf(cur, end - cur, "%pS", r->access[0].fn); + /* The exact offset won't match, remove it. */ + cur = strchr(expect[0], '+'); + if (cur) + *cur = '\0'; + } + + /* Access 1 */ + cur = expect[1]; + end = &expect[1][sizeof(expect[1]) - 1]; + if (!r->access[1].fn) + cur += scnprintf(cur, end - cur, "race at unknown origin, with "); + + /* Access 1 & 2 */ + for (i = 0; i < 2; ++i) { + const int ty = r->access[i].type; + const char *const access_type = + (ty & KCSAN_ACCESS_ASSERT) ? + ((ty & KCSAN_ACCESS_WRITE) ? + "assert no accesses" : + "assert no writes") : + ((ty & KCSAN_ACCESS_WRITE) ? + ((ty & KCSAN_ACCESS_COMPOUND) ? + "read-write" : + "write") : + "read"); + const char *const access_type_aux = + (ty & KCSAN_ACCESS_ATOMIC) ? + " (marked)" : + ((ty & KCSAN_ACCESS_SCOPED) ? " (scoped)" : ""); + + if (i == 1) { + /* Access 2 */ + cur = expect[2]; + end = &expect[2][sizeof(expect[2]) - 1]; + + if (!r->access[1].fn) { + /* Dummy string if no second access is available. */ + strcpy(cur, ""); + break; + } + } + + cur += scnprintf(cur, end - cur, "%s%s to ", access_type, + access_type_aux); + + if (r->access[i].addr) /* Address is optional. */ + cur += scnprintf(cur, end - cur, "0x%px of %zu bytes", + r->access[i].addr, r->access[i].size); + } + + spin_lock_irqsave(&observed.lock, flags); + if (!report_available()) + goto out; /* A new report is being captured. */ + + /* Finally match expected output to what we actually observed. */ + ret = strstr(observed.lines[0], expect[0]) && + /* Access info may appear in any order. */ + ((strstr(observed.lines[1], expect[1]) && + strstr(observed.lines[2], expect[2])) || + (strstr(observed.lines[1], expect[2]) && + strstr(observed.lines[2], expect[1]))); +out: + spin_unlock_irqrestore(&observed.lock, flags); + return ret; +} + +/* ===== Test kernels ===== */ + +static long test_sink; +static long test_var; +/* @test_array should be large enough to fall into multiple watchpoint slots. */ +static long test_array[3 * PAGE_SIZE / sizeof(long)]; +static struct { + long val[8]; +} test_struct; +static DEFINE_SEQLOCK(test_seqlock); + +/* + * Helper to avoid compiler optimizing out reads, and to generate source values + * for writes. + */ +__no_kcsan +static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); } + +static noinline void test_kernel_read(void) { sink_value(test_var); } + +static noinline void test_kernel_write(void) +{ + test_var = READ_ONCE_NOCHECK(test_sink) + 1; +} + +static noinline void test_kernel_write_nochange(void) { test_var = 42; } + +/* Suffixed by value-change exception filter. */ +static noinline void test_kernel_write_nochange_rcu(void) { test_var = 42; } + +static noinline void test_kernel_read_atomic(void) +{ + sink_value(READ_ONCE(test_var)); +} + +static noinline void test_kernel_write_atomic(void) +{ + WRITE_ONCE(test_var, READ_ONCE_NOCHECK(test_sink) + 1); +} + +static noinline void test_kernel_atomic_rmw(void) +{ + /* Use builtin, so we can set up the "bad" atomic/non-atomic scenario. */ + __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED); +} + +__no_kcsan +static noinline void test_kernel_write_uninstrumented(void) { test_var++; } + +static noinline void test_kernel_data_race(void) { data_race(test_var++); } + +static noinline void test_kernel_assert_writer(void) +{ + ASSERT_EXCLUSIVE_WRITER(test_var); +} + +static noinline void test_kernel_assert_access(void) +{ + ASSERT_EXCLUSIVE_ACCESS(test_var); +} + +#define TEST_CHANGE_BITS 0xff00ff00 + +static noinline void test_kernel_change_bits(void) +{ + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { + /* + * Avoid race of unknown origin for this test, just pretend they + * are atomic. + */ + kcsan_nestable_atomic_begin(); + test_var ^= TEST_CHANGE_BITS; + kcsan_nestable_atomic_end(); + } else + WRITE_ONCE(test_var, READ_ONCE(test_var) ^ TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_change(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, TEST_CHANGE_BITS); +} + +static noinline void test_kernel_assert_bits_nochange(void) +{ + ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS); +} + +/* To check that scoped assertions do trigger anywhere in scope. */ +static noinline void test_enter_scope(void) +{ + int x = 0; + + /* Unrelated accesses to scoped assert. */ + READ_ONCE(test_sink); + kcsan_check_read(&x, sizeof(x)); +} + +static noinline void test_kernel_assert_writer_scoped(void) +{ + ASSERT_EXCLUSIVE_WRITER_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_assert_access_scoped(void) +{ + ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_var); + test_enter_scope(); +} + +static noinline void test_kernel_rmw_array(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_array); ++i) + test_array[i]++; +} + +static noinline void test_kernel_write_struct(void) +{ + kcsan_check_write(&test_struct, sizeof(test_struct)); + kcsan_disable_current(); + test_struct.val[3]++; /* induce value change */ + kcsan_enable_current(); +} + +static noinline void test_kernel_write_struct_part(void) +{ + test_struct.val[3] = 42; +} + +static noinline void test_kernel_read_struct_zero_size(void) +{ + kcsan_check_read(&test_struct.val[3], 0); +} + +static noinline void test_kernel_jiffies_reader(void) +{ + sink_value((long)jiffies); +} + +static noinline void test_kernel_seqlock_reader(void) +{ + unsigned int seq; + + do { + seq = read_seqbegin(&test_seqlock); + sink_value(test_var); + } while (read_seqretry(&test_seqlock, seq)); +} + +static noinline void test_kernel_seqlock_writer(void) +{ + unsigned long flags; + + write_seqlock_irqsave(&test_seqlock, flags); + test_var++; + write_sequnlock_irqrestore(&test_seqlock, flags); +} + +static noinline void test_kernel_atomic_builtins(void) +{ + /* + * Generate concurrent accesses, expecting no reports, ensuring KCSAN + * treats builtin atomics as actually atomic. + */ + __atomic_load_n(&test_var, __ATOMIC_RELAXED); +} + +/* ===== Test cases ===== */ + +/* Simple test with normal data race. */ +__no_kcsan +static void test_basic(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + static const struct expect_report never = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write, test_kernel_read); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Stress KCSAN with lots of concurrent races on different addresses until + * timeout. + */ +__no_kcsan +static void test_concurrent_races(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + /* NULL will match any address. */ + { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) }, + { test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(0) }, + }, + }; + static const struct expect_report never = { + .access = { + { test_kernel_rmw_array, NULL, 0, 0 }, + { test_kernel_rmw_array, NULL, 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_rmw_array, test_kernel_rmw_array); + do { + match_expect |= report_matches(&expect); + match_never |= report_matches(&never); + } while (!end_test_checks(false)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check matches exist. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the KCSAN_REPORT_VALUE_CHANGE_ONLY option. */ +__no_kcsan +static void test_novalue_change(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_nochange, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that the rules where the KCSAN_REPORT_VALUE_CHANGE_ONLY option should + * never apply work. + */ +__no_kcsan +static void test_novalue_change_exception(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that data races of unknown origin are reported. */ +__no_kcsan +static void test_unknown_origin(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { NULL }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_uninstrumented, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN)) + KUNIT_EXPECT_TRUE(test, match_expect); + else + KUNIT_EXPECT_FALSE(test, match_expect); +} + +/* Test KCSAN_ASSUME_PLAIN_WRITES_ATOMIC if it is selected. */ +__no_kcsan +static void test_write_write_assume_atomic(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + { test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write, test_kernel_write); + do { + sink_value(READ_ONCE(test_var)); /* induce value-change */ + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) + KUNIT_EXPECT_FALSE(test, match_expect); + else + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races with writes larger than word-size are always reported, + * even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* + * Test that data races where only one write is larger than word-size are always + * reported, even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected. + */ +__no_kcsan +static void test_write_write_struct_part(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_write_struct_part); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that races with atomic accesses never result in reports. */ +__no_kcsan +static void test_read_atomic_write_atomic(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_read_atomic, test_kernel_write_atomic); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that a race with an atomic and plain access result in reports. */ +__no_kcsan +static void test_read_plain_atomic_write(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, + }, + }; + bool match_expect = false; + + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) + return; + + begin_test_checks(test_kernel_read, test_kernel_write_atomic); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Test that atomic RMWs generate correct report. */ +__no_kcsan +static void test_read_plain_atomic_rmw(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + { test_kernel_atomic_rmw, &test_var, sizeof(test_var), + KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC }, + }, + }; + bool match_expect = false; + + if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) + return; + + begin_test_checks(test_kernel_read, test_kernel_atomic_rmw); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +/* Zero-sized accesses should never cause data race reports. */ +__no_kcsan +static void test_zero_size_access(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report never = { + .access = { + { test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE }, + { test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 }, + }, + }; + bool match_expect = false; + bool match_never = false; + + begin_test_checks(test_kernel_write_struct, test_kernel_read_struct_zero_size); + do { + match_expect |= report_matches(&expect); + match_never = report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check. */ + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test the data_race() macro. */ +__no_kcsan +static void test_data_race(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_data_race, test_kernel_data_race); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_writer, test_kernel_write_nochange); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_read); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_access_writer(struct kunit *test) +{ + const struct expect_report expect_access_writer = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + const struct expect_report expect_access_access = { + .access = { + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + { test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report never = { + .access = { + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + }, + }; + bool match_expect_access_writer = false; + bool match_expect_access_access = false; + bool match_never = false; + + begin_test_checks(test_kernel_assert_access, test_kernel_assert_writer); + do { + match_expect_access_writer |= report_matches(&expect_access_writer); + match_expect_access_access |= report_matches(&expect_access_access); + match_never |= report_matches(&never); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_TRUE(test, match_expect_access_writer); + KUNIT_EXPECT_TRUE(test, match_expect_access_access); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_bits_change(struct kunit *test) +{ + const struct expect_report expect = { + .access = { + { test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT }, + { test_kernel_change_bits, &test_var, sizeof(test_var), + KCSAN_ACCESS_WRITE | (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) ? 0 : KCSAN_ACCESS_ATOMIC) }, + }, + }; + bool match_expect = false; + + begin_test_checks(test_kernel_assert_bits_change, test_kernel_change_bits); + do { + match_expect = report_matches(&expect); + } while (!end_test_checks(match_expect)); + KUNIT_EXPECT_TRUE(test, match_expect); +} + +__no_kcsan +static void test_assert_exclusive_bits_nochange(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_assert_bits_nochange, test_kernel_change_bits); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +__no_kcsan +static void test_assert_exclusive_writer_scoped(struct kunit *test) +{ + const struct expect_report expect_start = { + .access = { + { test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + const struct expect_report expect_anywhere = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED }, + { test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE }, + }, + }; + bool match_expect_start = false; + bool match_expect_anywhere = false; + + begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange); + do { + match_expect_start |= report_matches(&expect_start); + match_expect_anywhere |= report_matches(&expect_anywhere); + } while (!end_test_checks(match_expect_start && match_expect_anywhere)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_TRUE(test, match_expect_anywhere); +} + +__no_kcsan +static void test_assert_exclusive_access_scoped(struct kunit *test) +{ + const struct expect_report expect_start1 = { + .access = { + { test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + const struct expect_report expect_start2 = { + .access = { expect_start1.access[0], expect_start1.access[0] }, + }; + const struct expect_report expect_inscope = { + .access = { + { test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED }, + { test_kernel_read, &test_var, sizeof(test_var), 0 }, + }, + }; + bool match_expect_start = false; + bool match_expect_inscope = false; + + begin_test_checks(test_kernel_assert_access_scoped, test_kernel_read); + end_time += msecs_to_jiffies(1000); /* This test requires a bit more time. */ + do { + match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2); + match_expect_inscope |= report_matches(&expect_inscope); + } while (!end_test_checks(match_expect_start && match_expect_inscope)); + KUNIT_EXPECT_TRUE(test, match_expect_start); + KUNIT_EXPECT_TRUE(test, match_expect_inscope); +} + +/* + * jiffies is special (declared to be volatile) and its accesses are typically + * not marked; this test ensures that the compiler nor KCSAN gets confused about + * jiffies's declaration on different architectures. + */ +__no_kcsan +static void test_jiffies_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_jiffies_reader, test_kernel_jiffies_reader); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* Test that racing accesses in seqlock critical sections are not reported. */ +__no_kcsan +static void test_seqlock_noreport(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_seqlock_reader, test_kernel_seqlock_writer); + do { + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Test atomic builtins work and required instrumentation functions exist. We + * also test that KCSAN understands they're atomic by racing with them via + * test_kernel_atomic_builtins(), and expect no reports. + * + * The atomic builtins _SHOULD NOT_ be used in normal kernel code! + */ +static void test_atomic_builtins(struct kunit *test) +{ + bool match_never = false; + + begin_test_checks(test_kernel_atomic_builtins, test_kernel_atomic_builtins); + do { + long tmp; + + kcsan_enable_current(); + + __atomic_store_n(&test_var, 42L, __ATOMIC_RELAXED); + KUNIT_EXPECT_EQ(test, 42L, __atomic_load_n(&test_var, __ATOMIC_RELAXED)); + + KUNIT_EXPECT_EQ(test, 42L, __atomic_exchange_n(&test_var, 20, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 20L, test_var); + + tmp = 20L; + KUNIT_EXPECT_TRUE(test, __atomic_compare_exchange_n(&test_var, &tmp, 30L, + 0, __ATOMIC_RELAXED, + __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, tmp, 20L); + KUNIT_EXPECT_EQ(test, test_var, 30L); + KUNIT_EXPECT_FALSE(test, __atomic_compare_exchange_n(&test_var, &tmp, 40L, + 1, __ATOMIC_RELAXED, + __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, tmp, 30L); + KUNIT_EXPECT_EQ(test, test_var, 30L); + + KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_add(&test_var, 1, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 31L, __atomic_fetch_sub(&test_var, 1, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 30L, __atomic_fetch_and(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 14L, __atomic_fetch_xor(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 1L, __atomic_fetch_or(&test_var, 0xf0, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, 241L, __atomic_fetch_nand(&test_var, 0xf, __ATOMIC_RELAXED)); + KUNIT_EXPECT_EQ(test, -2L, test_var); + + __atomic_thread_fence(__ATOMIC_SEQ_CST); + __atomic_signal_fence(__ATOMIC_SEQ_CST); + + kcsan_disable_current(); + + match_never = report_available(); + } while (!end_test_checks(match_never)); + KUNIT_EXPECT_FALSE(test, match_never); +} + +/* + * Each test case is run with different numbers of threads. Until KUnit supports + * passing arguments for each test case, we encode #threads in the test case + * name (read by get_num_threads()). [The '-' was chosen as a stylistic + * preference to separate test name and #threads.] + * + * The thread counts are chosen to cover potentially interesting boundaries and + * corner cases (range 2-5), and then stress the system with larger counts. + */ +#define KCSAN_KUNIT_CASE(test_name) \ + { .run_case = test_name, .name = #test_name "-02" }, \ + { .run_case = test_name, .name = #test_name "-03" }, \ + { .run_case = test_name, .name = #test_name "-04" }, \ + { .run_case = test_name, .name = #test_name "-05" }, \ + { .run_case = test_name, .name = #test_name "-08" }, \ + { .run_case = test_name, .name = #test_name "-16" } + +static struct kunit_case kcsan_test_cases[] = { + KCSAN_KUNIT_CASE(test_basic), + KCSAN_KUNIT_CASE(test_concurrent_races), + KCSAN_KUNIT_CASE(test_novalue_change), + KCSAN_KUNIT_CASE(test_novalue_change_exception), + KCSAN_KUNIT_CASE(test_unknown_origin), + KCSAN_KUNIT_CASE(test_write_write_assume_atomic), + KCSAN_KUNIT_CASE(test_write_write_struct), + KCSAN_KUNIT_CASE(test_write_write_struct_part), + KCSAN_KUNIT_CASE(test_read_atomic_write_atomic), + KCSAN_KUNIT_CASE(test_read_plain_atomic_write), + KCSAN_KUNIT_CASE(test_read_plain_atomic_rmw), + KCSAN_KUNIT_CASE(test_zero_size_access), + KCSAN_KUNIT_CASE(test_data_race), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_access), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_change), + KCSAN_KUNIT_CASE(test_assert_exclusive_bits_nochange), + KCSAN_KUNIT_CASE(test_assert_exclusive_writer_scoped), + KCSAN_KUNIT_CASE(test_assert_exclusive_access_scoped), + KCSAN_KUNIT_CASE(test_jiffies_noreport), + KCSAN_KUNIT_CASE(test_seqlock_noreport), + KCSAN_KUNIT_CASE(test_atomic_builtins), + {}, +}; + +/* ===== End test cases ===== */ + +/* Get number of threads encoded in test name. */ +static bool __no_kcsan +get_num_threads(const char *test, int *nthreads) +{ + int len = strlen(test); + + if (WARN_ON(len < 3)) + return false; + + *nthreads = test[len - 1] - '0'; + *nthreads += (test[len - 2] - '0') * 10; + + if (WARN_ON(*nthreads < 0)) + return false; + + return true; +} + +/* Concurrent accesses from interrupts. */ +__no_kcsan +static void access_thread_timer(struct timer_list *timer) +{ + static atomic_t cnt = ATOMIC_INIT(0); + unsigned int idx; + void (*func)(void); + + idx = (unsigned int)atomic_inc_return(&cnt) % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); +} + +/* The main loop for each thread. */ +__no_kcsan +static int access_thread(void *arg) +{ + struct timer_list timer; + unsigned int cnt = 0; + unsigned int idx; + void (*func)(void); + + timer_setup_on_stack(&timer, access_thread_timer, 0); + do { + might_sleep(); + + if (!timer_pending(&timer)) + mod_timer(&timer, jiffies + 1); + else { + /* Iterate through all kernels. */ + idx = cnt++ % ARRAY_SIZE(access_kernels); + /* Acquire potential initialization. */ + func = smp_load_acquire(&access_kernels[idx]); + if (func) + func(); + } + } while (!torture_must_stop()); + del_timer_sync(&timer); + destroy_timer_on_stack(&timer); + + torture_kthread_stopping("access_thread"); + return 0; +} + +__no_kcsan +static int test_init(struct kunit *test) +{ + unsigned long flags; + int nthreads; + int i; + + spin_lock_irqsave(&observed.lock, flags); + for (i = 0; i < ARRAY_SIZE(observed.lines); ++i) + observed.lines[i][0] = '\0'; + observed.nlines = 0; + spin_unlock_irqrestore(&observed.lock, flags); + + if (!torture_init_begin((char *)test->name, 1)) + return -EBUSY; + + if (!get_num_threads(test->name, &nthreads)) + goto err; + + if (WARN_ON(threads)) + goto err; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) { + if (WARN_ON(access_kernels[i])) + goto err; + } + + if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) { + /* + * Without any preemption, keep 2 CPUs free for other tasks, one + * of which is the main test case function checking for + * completion or failure. + */ + const int min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0; + const int min_required_cpus = 2 + min_unused_cpus; + + if (num_online_cpus() < min_required_cpus) { + pr_err("%s: too few online CPUs (%u < %d) for test", + test->name, num_online_cpus(), min_required_cpus); + goto err; + } else if (nthreads > num_online_cpus() - min_unused_cpus) { + nthreads = num_online_cpus() - min_unused_cpus; + pr_warn("%s: limiting number of threads to %d\n", + test->name, nthreads); + } + } + + if (nthreads) { + threads = kcalloc(nthreads + 1, sizeof(struct task_struct *), + GFP_KERNEL); + if (WARN_ON(!threads)) + goto err; + + threads[nthreads] = NULL; + for (i = 0; i < nthreads; ++i) { + if (torture_create_kthread(access_thread, NULL, + threads[i])) + goto err; + } + } + + torture_init_end(); + + return 0; + +err: + kfree(threads); + threads = NULL; + torture_init_end(); + return -EINVAL; +} + +__no_kcsan +static void test_exit(struct kunit *test) +{ + struct task_struct **stop_thread; + int i; + + if (torture_cleanup_begin()) + return; + + for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) + WRITE_ONCE(access_kernels[i], NULL); + + if (threads) { + for (stop_thread = threads; *stop_thread; stop_thread++) + torture_stop_kthread(reader_thread, *stop_thread); + + kfree(threads); + threads = NULL; + } + + torture_cleanup_end(); +} + +static struct kunit_suite kcsan_test_suite = { + .name = "kcsan", + .test_cases = kcsan_test_cases, + .init = test_init, + .exit = test_exit, +}; +static struct kunit_suite *kcsan_test_suites[] = { &kcsan_test_suite, NULL }; + +__no_kcsan +static void register_tracepoints(struct tracepoint *tp, void *ignore) +{ + check_trace_callback_type_console(probe_console); + if (!strcmp(tp->name, "console")) + WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); +} + +__no_kcsan +static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +{ + if (!strcmp(tp->name, "console")) + tracepoint_probe_unregister(tp, probe_console, NULL); +} + +/* + * We only want to do tracepoints setup and teardown once, therefore we have to + * customize the init and exit functions and cannot rely on kunit_test_suite(). + */ +static int __init kcsan_test_init(void) +{ + /* + * Because we want to be able to build the test as a module, we need to + * iterate through all known tracepoints, since the static registration + * won't work here. + */ + for_each_kernel_tracepoint(register_tracepoints, NULL); + return __kunit_test_suites_init(kcsan_test_suites); +} + +static void kcsan_test_exit(void) +{ + __kunit_test_suites_exit(kcsan_test_suites); + for_each_kernel_tracepoint(unregister_tracepoints, NULL); + tracepoint_synchronize_unregister(); +} + +late_initcall(kcsan_test_init); +module_exit(kcsan_test_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Marco Elver "); diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index f271ff5fbb5a..0440f373248e 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -69,8 +69,9 @@ config KCSAN_SELFTEST panic. Recommended to be enabled, ensuring critical functionality works as intended. -config KCSAN_TEST - tristate "KCSAN test for integrated runtime behaviour" +config KCSAN_KUNIT_TEST + tristate "KCSAN test for integrated runtime behaviour" if !KUNIT_ALL_TESTS + default KUNIT_ALL_TESTS depends on TRACEPOINTS && KUNIT select TORTURE_TEST help -- cgit v1.2.3 From 9f961c2e08741579aa53095d0dbffbcb25a9ae66 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Mar 2021 20:42:05 +0100 Subject: lib/vsprintf: do not show no_hash_pointers message multiple times Do not show no_hash_pointers message multiple times if the option was passed more than once (e.g. via generated command line). Signed-off-by: Marco Elver Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210305194206.3165917-1-elver@google.com --- lib/vsprintf.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 41ddc353ebb8..4a14889ccb35 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2096,6 +2096,9 @@ EXPORT_SYMBOL_GPL(no_hash_pointers); static int __init no_hash_pointers_enable(char *str) { + if (no_hash_pointers) + return 0; + no_hash_pointers = true; pr_warn("**********************************************************\n"); -- cgit v1.2.3 From c244297acbe51f1db5764966c02cdbd69927f218 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Fri, 19 Mar 2021 18:12:46 +0800 Subject: vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao Cc: David Hildenbrand Cc: Joe Perches Cc: Miaohe Lin Cc: Vlastimil Babka Cc: Andy Shevchenko Cc: Matthew Wilcox Cc: Petr Mladek Cc: kernel test robot Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com --- Documentation/core-api/printk-formats.rst | 2 +- lib/test_printf.c | 90 +++++++++++++++++++++++++++---- lib/vsprintf.c | 66 +++++++++++++++++++++-- 3 files changed, 142 insertions(+), 16 deletions(-) (limited to 'lib') diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 160e710d992f..00d07c7eefd4 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -540,7 +540,7 @@ Flags bitfields such as page flags, gfp_flags :: - %pGp referenced|uptodate|lru|active|private + %pGp referenced|uptodate|lru|active|private|node=0|zone=2|lastcpupid=0x1fffff %pGg GFP_USER|GFP_DMA32|GFP_NOWARN %pGv read|exec|mayread|maywrite|mayexec|denywrite diff --git a/lib/test_printf.c b/lib/test_printf.c index 95a2f82427c7..27b964ec723d 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -577,24 +577,98 @@ netdev_features(void) { } +struct page_flags_test { + int width; + int shift; + int mask; + unsigned long value; + const char *fmt; + const char *name; +}; + +static struct page_flags_test pft[] = { + {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, + 0, "%d", "section"}, + {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, + 0, "%d", "node"}, + {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, + 0, "%d", "zone"}, + {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, + 0, "%#x", "lastcpupid"}, + {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, + 0, "%#x", "kasantag"}, +}; + +static void __init +page_flags_test(int section, int node, int zone, int last_cpupid, + int kasan_tag, int flags, const char *name, char *cmp_buf) +{ + unsigned long values[] = {section, node, zone, last_cpupid, kasan_tag}; + unsigned long page_flags = 0; + unsigned long size = 0; + bool append = false; + int i; + + flags &= BIT(NR_PAGEFLAGS) - 1; + if (flags) { + page_flags |= flags; + snprintf(cmp_buf + size, BUF_SIZE - size, "%s", name); + size = strlen(cmp_buf); +#if SECTIONS_WIDTH || NODES_WIDTH || ZONES_WIDTH || \ + LAST_CPUPID_WIDTH || KASAN_TAG_WIDTH + /* Other information also included in page flags */ + snprintf(cmp_buf + size, BUF_SIZE - size, "|"); + size = strlen(cmp_buf); +#endif + } + + /* Set the test value */ + for (i = 0; i < ARRAY_SIZE(pft); i++) + pft[i].value = values[i]; + + for (i = 0; i < ARRAY_SIZE(pft); i++) { + if (!pft[i].width) + continue; + + if (append) { + snprintf(cmp_buf + size, BUF_SIZE - size, "|"); + size = strlen(cmp_buf); + } + + page_flags |= (pft[i].value & pft[i].mask) << pft[i].shift; + snprintf(cmp_buf + size, BUF_SIZE - size, "%s=", pft[i].name); + size = strlen(cmp_buf); + snprintf(cmp_buf + size, BUF_SIZE - size, pft[i].fmt, + pft[i].value & pft[i].mask); + size = strlen(cmp_buf); + append = true; + } + + test(cmp_buf, "%pGp", &page_flags); +} + static void __init flags(void) { unsigned long flags; - gfp_t gfp; char *cmp_buffer; + gfp_t gfp; + + cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); + if (!cmp_buffer) + return; flags = 0; - test("", "%pGp", &flags); + page_flags_test(0, 0, 0, 0, 0, flags, "", cmp_buffer); - /* Page flags should filter the zone id */ flags = 1UL << NR_PAGEFLAGS; - test("", "%pGp", &flags); + page_flags_test(0, 0, 0, 0, 0, flags, "", cmp_buffer); flags |= 1UL << PG_uptodate | 1UL << PG_dirty | 1UL << PG_lru | 1UL << PG_active | 1UL << PG_swapbacked; - test("uptodate|dirty|lru|active|swapbacked", "%pGp", &flags); - + page_flags_test(1, 1, 1, 0x1fffff, 1, flags, + "uptodate|dirty|lru|active|swapbacked", + cmp_buffer); flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_DENYWRITE; @@ -609,10 +683,6 @@ flags(void) gfp = __GFP_ATOMIC; test("__GFP_ATOMIC", "%pGg", &gfp); - cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); - if (!cmp_buffer) - return; - /* Any flags not translated by the table should remain numeric */ gfp = ~__GFP_BITS_MASK; snprintf(cmp_buffer, BUF_SIZE, "%#lx", (unsigned long) gfp); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 41ddc353ebb8..92e6085eef15 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1916,6 +1916,66 @@ char *format_flags(char *buf, char *end, unsigned long flags, return buf; } +struct page_flags_fields { + int width; + int shift; + int mask; + const struct printf_spec *spec; + const char *name; +}; + +static const struct page_flags_fields pff[] = { + {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, + &default_dec_spec, "section"}, + {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, + &default_dec_spec, "node"}, + {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, + &default_dec_spec, "zone"}, + {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, + &default_flag_spec, "lastcpupid"}, + {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, + &default_flag_spec, "kasantag"}, +}; + +static +char *format_page_flags(char *buf, char *end, unsigned long flags) +{ + unsigned long main_flags = flags & (BIT(NR_PAGEFLAGS) - 1); + bool append = false; + int i; + + /* Page flags from the main area. */ + if (main_flags) { + buf = format_flags(buf, end, main_flags, pageflag_names); + append = true; + } + + /* Page flags from the fields area */ + for (i = 0; i < ARRAY_SIZE(pff); i++) { + /* Skip undefined fields. */ + if (!pff[i].width) + continue; + + /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ + if (append) { + if (buf < end) + *buf = '|'; + buf++; + } + + buf = string(buf, end, pff[i].name, default_str_spec); + if (buf < end) + *buf = '='; + buf++; + buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, + *pff[i].spec); + + append = true; + } + + return buf; +} + static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) @@ -1928,11 +1988,7 @@ char *flags_string(char *buf, char *end, void *flags_ptr, switch (fmt[1]) { case 'p': - flags = *(unsigned long *)flags_ptr; - /* Remove zone id */ - flags &= (1UL << NR_PAGEFLAGS) - 1; - names = pageflag_names; - break; + return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; -- cgit v1.2.3 From 2f9f21cdcd71d0c523676f551ea5c4f78d8e6f61 Mon Sep 17 00:00:00 2001 From: Lucas Stankus Date: Fri, 12 Mar 2021 16:11:26 -0300 Subject: kunit: Match parenthesis alignment to improve code readability Tidy up code by fixing the following checkpatch warnings: CHECK: Alignment should match open parenthesis CHECK: Lines should not end with a '(' Signed-off-by: Lucas Stankus Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- lib/kunit/assert.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index e0ec7d6fed6f..acfbf86bddd6 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -25,7 +25,7 @@ void kunit_base_assert_format(const struct kunit_assert *assert, } string_stream_add(stream, "%s FAILED at %s:%d\n", - expect_or_assert, assert->file, assert->line); + expect_or_assert, assert->file, assert->line); } EXPORT_SYMBOL_GPL(kunit_base_assert_format); @@ -48,8 +48,9 @@ EXPORT_SYMBOL_GPL(kunit_fail_assert_format); void kunit_unary_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_unary_assert *unary_assert = container_of( - assert, struct kunit_unary_assert, assert); + struct kunit_unary_assert *unary_assert; + + unary_assert = container_of(assert, struct kunit_unary_assert, assert); kunit_base_assert_format(assert, stream); if (unary_assert->expected_true) @@ -67,8 +68,10 @@ EXPORT_SYMBOL_GPL(kunit_unary_assert_format); void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_ptr_not_err_assert *ptr_assert = container_of( - assert, struct kunit_ptr_not_err_assert, assert); + struct kunit_ptr_not_err_assert *ptr_assert; + + ptr_assert = container_of(assert, struct kunit_ptr_not_err_assert, + assert); kunit_base_assert_format(assert, stream); if (!ptr_assert->value) { @@ -111,8 +114,10 @@ static bool is_literal(struct kunit *test, const char *text, long long value, void kunit_binary_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_assert *binary_assert = container_of( - assert, struct kunit_binary_assert, assert); + struct kunit_binary_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, @@ -137,8 +142,10 @@ EXPORT_SYMBOL_GPL(kunit_binary_assert_format); void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_ptr_assert *binary_assert = container_of( - assert, struct kunit_binary_ptr_assert, assert); + struct kunit_binary_ptr_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_ptr_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, @@ -159,8 +166,10 @@ EXPORT_SYMBOL_GPL(kunit_binary_ptr_assert_format); void kunit_binary_str_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { - struct kunit_binary_str_assert *binary_assert = container_of( - assert, struct kunit_binary_str_assert, assert); + struct kunit_binary_str_assert *binary_assert; + + binary_assert = container_of(assert, struct kunit_binary_str_assert, + assert); kunit_base_assert_format(assert, stream); string_stream_add(stream, -- cgit v1.2.3 From 4adec7f81df8e4fbf55f9d5ca98afa39f15b050f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 Mar 2021 14:03:32 +0100 Subject: rhashtable: avoid -Wrestrict warning on overlapping sprintf output sprintf() is declared with a restrict keyword to not allow input and output to point to the same buffer: lib/test_rhashtable.c: In function 'print_ht': lib/test_rhashtable.c:504:4: error: 'sprintf' argument 3 overlaps destination object 'buff' [-Werror=restrict] 504 | sprintf(buff, "%s\nbucket[%d] -> ", buff, i); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ lib/test_rhashtable.c:489:7: note: destination object referenced by 'restrict'-qualified argument 1 was declared here 489 | char buff[512] = ""; | ^~~~ Rework this function to remember the last offset instead to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- lib/test_rhashtable.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 76c607ee6db5..5a1dd4736b56 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -487,6 +487,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt) struct rhashtable *ht; const struct bucket_table *tbl; char buff[512] = ""; + int offset = 0; unsigned int i, cnt = 0; ht = &rhlt->ht; @@ -501,18 +502,18 @@ static unsigned int __init print_ht(struct rhltable *rhlt) next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; if (!rht_is_a_nulls(pos)) { - sprintf(buff, "%s\nbucket[%d] -> ", buff, i); + offset += sprintf(buff + offset, "\nbucket[%d] -> ", i); } while (!rht_is_a_nulls(pos)) { struct rhlist_head *list = container_of(pos, struct rhlist_head, rhead); - sprintf(buff, "%s[[", buff); + offset += sprintf(buff + offset, "[["); do { pos = &list->rhead; list = rht_dereference(list->next, ht); p = rht_obj(ht, pos); - sprintf(buff, "%s val %d (tid=%d)%s", buff, p->value.id, p->value.tid, + offset += sprintf(buff + offset, " val %d (tid=%d)%s", p->value.id, p->value.tid, list? ", " : " "); cnt++; } while (list); @@ -521,7 +522,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt) next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; - sprintf(buff, "%s]]%s", buff, !rht_is_a_nulls(pos) ? " -> " : ""); + offset += sprintf(buff + offset, "]]%s", !rht_is_a_nulls(pos) ? " -> " : ""); } } printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff); -- cgit v1.2.3 From d1a303e8616c5ba1260722bb9068bbc0d1704847 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 16 Mar 2021 17:07:36 -0400 Subject: x509: Detect sm2 keys by their parameters OID Detect whether a key is an sm2 type of key by its OID in the parameters array rather than assuming that everything under OID_id_ecPublicKey is sm2, which is not the case. Cc: David Howells Cc: keyrings@vger.kernel.org Signed-off-by: Stefan Berger Reviewed-by: Tianjia Zhang Tested-by: Tianjia Zhang Signed-off-by: Herbert Xu --- crypto/asymmetric_keys/x509_cert_parser.c | 12 +++++++++++- include/linux/oid_registry.h | 1 + lib/oid_registry.c | 24 ++++++++++++++++++++++++ 3 files changed, 36 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 52c9b455fc7d..1621ceaf5c95 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -459,6 +459,7 @@ int x509_extract_key_data(void *context, size_t hdrlen, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; + enum OID oid; ctx->key_algo = ctx->last_oid; switch (ctx->last_oid) { @@ -470,7 +471,16 @@ int x509_extract_key_data(void *context, size_t hdrlen, ctx->cert->pub->pkey_algo = "ecrdsa"; break; case OID_id_ecPublicKey: - ctx->cert->pub->pkey_algo = "sm2"; + if (parse_OID(ctx->params, ctx->params_size, &oid) != 0) + return -EBADMSG; + + switch (oid) { + case OID_sm2: + ctx->cert->pub->pkey_algo = "sm2"; + break; + default: + return -ENOPKG; + } break; default: return -ENOPKG; diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index b504e2f36b25..f32d91895e4d 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -121,6 +121,7 @@ enum OID { }; extern enum OID look_up_OID(const void *data, size_t datasize); +extern int parse_OID(const void *data, size_t datasize, enum OID *oid); extern int sprint_oid(const void *, size_t, char *, size_t); extern int sprint_OID(enum OID, char *, size_t); diff --git a/lib/oid_registry.c b/lib/oid_registry.c index f7ad43f28579..3dfaa836e7c5 100644 --- a/lib/oid_registry.c +++ b/lib/oid_registry.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "oid_registry_data.c" MODULE_DESCRIPTION("OID Registry"); @@ -92,6 +93,29 @@ enum OID look_up_OID(const void *data, size_t datasize) } EXPORT_SYMBOL_GPL(look_up_OID); +/** + * parse_OID - Parse an OID from a bytestream + * @data: Binary representation of the header + OID + * @datasize: Size of the binary representation + * @oid: Pointer to oid to return result + * + * Parse an OID from a bytestream that holds the OID in the format + * ASN1_OID | length | oid. The length indicator must equal to datasize - 2. + * -EBADMSG is returned if the bytestream is too short. + */ +int parse_OID(const void *data, size_t datasize, enum OID *oid) +{ + const unsigned char *v = data; + + /* we need 2 bytes of header and at least 1 byte for oid */ + if (datasize < 3 || v[0] != ASN1_OID || v[1] != datasize - 2) + return -EBADMSG; + + *oid = look_up_OID(data + 2, datasize - 2); + return 0; +} +EXPORT_SYMBOL_GPL(parse_OID); + /* * sprint_OID - Print an Object Identifier into a buffer * @data: The encoded OID to print -- cgit v1.2.3 From 3ad1a6cb0abc63d036fc866bd7c2c5983516dec5 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Thu, 18 Mar 2021 14:33:07 +0000 Subject: bug: Remove redundant condition check in report_bug report_bug() will return early if it cannot find a bug corresponding to the provided address. The subsequent test for the bug will always be true so remove it. Fixes: 1b4cfe3c0a30d ("lib/bug.c: exclude non-BUG/WARN exceptions from report_bug()") Signed-off-by: Andrew Scull Cc: Peter Zijlstra Cc: "Steven Rostedt (VMware)" Reviewed-by: Steven Rostedt (VMware) Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210318143311.839894-2-ascull@google.com --- lib/bug.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'lib') diff --git a/lib/bug.c b/lib/bug.c index 8f9d537bfb2a..b92da1f6e21b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -155,30 +155,27 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) file = NULL; line = 0; - warning = 0; - if (bug) { #ifdef CONFIG_DEBUG_BUGVERBOSE #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - file = bug->file; + file = bug->file; #else - file = (const char *)bug + bug->file_disp; + file = (const char *)bug + bug->file_disp; #endif - line = bug->line; + line = bug->line; #endif - warning = (bug->flags & BUGFLAG_WARNING) != 0; - once = (bug->flags & BUGFLAG_ONCE) != 0; - done = (bug->flags & BUGFLAG_DONE) != 0; - - if (warning && once) { - if (done) - return BUG_TRAP_TYPE_WARN; - - /* - * Since this is the only store, concurrency is not an issue. - */ - bug->flags |= BUGFLAG_DONE; - } + warning = (bug->flags & BUGFLAG_WARNING) != 0; + once = (bug->flags & BUGFLAG_ONCE) != 0; + done = (bug->flags & BUGFLAG_DONE) != 0; + + if (warning && once) { + if (done) + return BUG_TRAP_TYPE_WARN; + + /* + * Since this is the only store, concurrency is not an issue. + */ + bug->flags |= BUGFLAG_DONE; } /* -- cgit v1.2.3 From 26dbc7e299c7ebbb6a95e2c620b21b5280b37c57 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Thu, 18 Mar 2021 14:33:08 +0000 Subject: bug: Factor out a getter for a bug's file line There is some non-trivial config-based logic to get the file name and line number associated with a bug. Factor this out to a getter that can be resused. Signed-off-by: Andrew Scull Cc: Peter Zijlstra Cc: "Steven Rostedt (VMware)" Reviewed-by: Steven Rostedt (VMware) Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210318143311.839894-3-ascull@google.com --- include/linux/bug.h | 3 +++ lib/bug.c | 27 +++++++++++++++++---------- 2 files changed, 20 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/include/linux/bug.h b/include/linux/bug.h index f639bd0122f3..e3841bee4c8d 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -36,6 +36,9 @@ static inline int is_warning_bug(const struct bug_entry *bug) return bug->flags & BUGFLAG_WARNING; } +void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line); + struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); diff --git a/lib/bug.c b/lib/bug.c index b92da1f6e21b..e65398082cbc 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -127,6 +127,22 @@ static inline struct bug_entry *module_find_bug(unsigned long bugaddr) } #endif +void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line) +{ + *file = NULL; + *line = 0; + +#ifdef CONFIG_DEBUG_BUGVERBOSE +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + *file = bug->file; +#else + *file = (const char *)bug + bug->file_disp; +#endif + *line = bug->line; +#endif +} + struct bug_entry *find_bug(unsigned long bugaddr) { struct bug_entry *bug; @@ -153,17 +169,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) disable_trace_on_warning(); - file = NULL; - line = 0; + bug_get_file_line(bug, &file, &line); -#ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - file = bug->file; -#else - file = (const char *)bug + bug->file_disp; -#endif - line = bug->line; -#endif warning = (bug->flags & BUGFLAG_WARNING) != 0; once = (bug->flags & BUGFLAG_ONCE) != 0; done = (bug->flags & BUGFLAG_DONE) != 0; -- cgit v1.2.3 From 5b8be5d875a996776708ba174fcd08c8bcd721a5 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Thu, 18 Mar 2021 14:33:09 +0000 Subject: bug: Assign values once in bug_get_file_line() Set bug_get_file_line()'s output parameter values directly rather than first nullifying them and then conditionally setting new values. Signed-off-by: Andrew Scull Cc: Peter Zijlstra Cc: "Steven Rostedt (VMware)" Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210318143311.839894-4-ascull@google.com --- lib/bug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/bug.c b/lib/bug.c index e65398082cbc..45a0584f6541 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -130,9 +130,6 @@ static inline struct bug_entry *module_find_bug(unsigned long bugaddr) void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { - *file = NULL; - *line = 0; - #ifdef CONFIG_DEBUG_BUGVERBOSE #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS *file = bug->file; @@ -140,6 +137,9 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, *file = (const char *)bug + bug->file_disp; #endif *line = bug->line; +#else + *file = NULL; + *line = 0; #endif } -- cgit v1.2.3 From 8d195e7a8ada68928f2aedb2c18302a4518fe68e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Mar 2021 18:05:15 +0100 Subject: crypto: poly1305 - fix poly1305_core_setkey() declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc-11 points out a mismatch between the declaration and the definition of poly1305_core_setkey(): lib/crypto/poly1305-donna32.c:13:67: error: argument 2 of type ‘const u8[16]’ {aka ‘const unsigned char[16]’} with mismatched bound [-Werror=array-parameter=] 13 | void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) | ~~~~~~~~~^~~~~~~~~~~ In file included from lib/crypto/poly1305-donna32.c:11: include/crypto/internal/poly1305.h:21:68: note: previously declared as ‘const u8 *’ {aka ‘const unsigned char *’} 21 | void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key); This is harmless in principle, as the calling conventions are the same, but the more specific prototype allows better type checking in the caller. Change the declaration to match the actual function definition. The poly1305_simd_init() is a bit suspicious here, as it previously had a 32-byte argument type, but looks like it needs to take the 16-byte POLY1305_BLOCK_SIZE array instead. Fixes: 1c08a104360f ("crypto: poly1305 - add new 32 and 64-bit generic versions") Signed-off-by: Arnd Bergmann Reviewed-by: Ard Biesheuvel Reviewed-by: Eric Biggers Signed-off-by: Herbert Xu --- arch/arm/crypto/poly1305-glue.c | 2 +- arch/arm64/crypto/poly1305-glue.c | 2 +- arch/mips/crypto/poly1305-glue.c | 2 +- arch/x86/crypto/poly1305_glue.c | 6 +++--- include/crypto/internal/poly1305.h | 3 ++- include/crypto/poly1305.h | 6 ++++-- lib/crypto/poly1305-donna32.c | 3 ++- lib/crypto/poly1305-donna64.c | 3 ++- lib/crypto/poly1305.c | 3 ++- 9 files changed, 18 insertions(+), 12 deletions(-) (limited to 'lib') diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index 3023c1acfa19..c31bd8f7c092 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -29,7 +29,7 @@ void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit) static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_arm(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index 683de671741a..9c3d86e397bf 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -25,7 +25,7 @@ asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce); static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_arm64(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c index fc881b46d911..bc6110fb98e0 100644 --- a/arch/mips/crypto/poly1305-glue.c +++ b/arch/mips/crypto/poly1305-glue.c @@ -17,7 +17,7 @@ asmlinkage void poly1305_init_mips(void *state, const u8 *key); asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit); asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_mips(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 646da46e8d10..1dfb8af48a3c 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -16,7 +16,7 @@ #include asmlinkage void poly1305_init_x86_64(void *ctx, - const u8 key[POLY1305_KEY_SIZE]); + const u8 key[POLY1305_BLOCK_SIZE]); asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp, const size_t len, const u32 padbit); asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], @@ -81,7 +81,7 @@ static void convert_to_base2_64(void *ctx) state->is_base2_26 = 0; } -static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_KEY_SIZE]) +static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_BLOCK_SIZE]) { poly1305_init_x86_64(ctx, key); } @@ -129,7 +129,7 @@ static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], poly1305_emit_avx(ctx, mac, nonce); } -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_simd_init(&dctx->h, key); dctx->s[0] = get_unaligned_le32(&key[16]); diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h index 064e52ca5248..196aa769f296 100644 --- a/include/crypto/internal/poly1305.h +++ b/include/crypto/internal/poly1305.h @@ -18,7 +18,8 @@ * only the ε-almost-∆-universal hash function (not the full MAC) is computed. */ -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key); +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]); static inline void poly1305_core_init(struct poly1305_state *state) { *state = (struct poly1305_state){}; diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h index f1f67fc749cf..090692ec3bc7 100644 --- a/include/crypto/poly1305.h +++ b/include/crypto/poly1305.h @@ -58,8 +58,10 @@ struct poly1305_desc_ctx { }; }; -void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key); -void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key); +void poly1305_init_arch(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]); +void poly1305_init_generic(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]); static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key) { diff --git a/lib/crypto/poly1305-donna32.c b/lib/crypto/poly1305-donna32.c index 3cc77d94390b..7fb71845cc84 100644 --- a/lib/crypto/poly1305-donna32.c +++ b/lib/crypto/poly1305-donna32.c @@ -10,7 +10,8 @@ #include #include -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]) { /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ key->key.r[0] = (get_unaligned_le32(&raw_key[0])) & 0x3ffffff; diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c index 6ae181bb4345..d34cf4053668 100644 --- a/lib/crypto/poly1305-donna64.c +++ b/lib/crypto/poly1305-donna64.c @@ -12,7 +12,8 @@ typedef __uint128_t u128; -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]) { u64 t0, t1; diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index 9d2d14df0fee..26d87fc3823e 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -12,7 +12,8 @@ #include #include -void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key) +void poly1305_init_generic(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]) { poly1305_core_setkey(&desc->core_r, key); desc->s[0] = get_unaligned_le32(key + 16); -- cgit v1.2.3 From acd976253c0ce98e92c766bd720bb00e4c2facb6 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Fri, 2 Apr 2021 12:33:57 -0700 Subject: kunit: make KUNIT_EXPECT_STREQ() quote values, don't print literals Before: > Expected str == "world", but > str == hello > "world" == world After: > Expected str == "world", but > str == "hello" Note: like the literal ellision for integers, this doesn't handle the case of KUNIT_EXPECT_STREQ(test, "hello", "world") since we don't expect it to realistically happen in checked in tests. (If you really wanted a test to fail, KUNIT_FAIL("msg") exists) In that case, you'd get: > Expected "hello" == "world", but Signed-off-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- lib/kunit/assert.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index acfbf86bddd6..b972bda61c0c 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -163,6 +163,22 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, } EXPORT_SYMBOL_GPL(kunit_binary_ptr_assert_format); +/* Checks if KUNIT_EXPECT_STREQ() args were string literals. + * Note: `text` will have ""s where as `value` will not. + */ +static bool is_str_literal(const char *text, const char *value) +{ + int len; + + len = strlen(text); + if (len < 2) + return false; + if (text[0] != '\"' || text[len - 1] != '\"') + return false; + + return strncmp(text + 1, value, len - 2) == 0; +} + void kunit_binary_str_assert_format(const struct kunit_assert *assert, struct string_stream *stream) { @@ -177,12 +193,14 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, binary_assert->left_text, binary_assert->operation, binary_assert->right_text); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s == %s\n", - binary_assert->left_text, - binary_assert->left_value); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s == %s", - binary_assert->right_text, - binary_assert->right_value); + if (!is_str_literal(binary_assert->left_text, binary_assert->left_value)) + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s == \"%s\"\n", + binary_assert->left_text, + binary_assert->left_value); + if (!is_str_literal(binary_assert->right_text, binary_assert->right_value)) + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s == \"%s\"", + binary_assert->right_text, + binary_assert->right_value); kunit_assert_print_msg(assert, stream); } EXPORT_SYMBOL_GPL(kunit_binary_str_assert_format); -- cgit v1.2.3 From 9854781dba371dda22880fc6acac7688fb5e2bae Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Mon, 22 Feb 2021 14:52:41 -0800 Subject: kunit: tool: make --kunitconfig accept dirs, add lib/kunit fragment TL;DR $ ./tools/testing/kunit/kunit.py run --kunitconfig=lib/kunit Per suggestion from Ted [1], we can reduce the amount of typing by assuming a convention that these files are named '.kunitconfig'. In the case of [1], we now have $ ./tools/testing/kunit/kunit.py run --kunitconfig=fs/ext4 Also add in such a fragment for kunit itself so we can give that as an example more close to home (and thus less likely to be accidentally broken). [1] https://lore.kernel.org/linux-ext4/YCNF4yP1dB97zzwD@mit.edu/ Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- lib/kunit/.kunitconfig | 3 +++ tools/testing/kunit/kunit.py | 4 +++- tools/testing/kunit/kunit_kernel.py | 2 ++ tools/testing/kunit/kunit_tool_test.py | 6 ++++++ 4 files changed, 14 insertions(+), 1 deletion(-) create mode 100644 lib/kunit/.kunitconfig (limited to 'lib') diff --git a/lib/kunit/.kunitconfig b/lib/kunit/.kunitconfig new file mode 100644 index 000000000000..9235b7d42d38 --- /dev/null +++ b/lib/kunit/.kunitconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_KUNIT_TEST=y +CONFIG_KUNIT_EXAMPLE_TEST=y diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index d5144fcb03ac..5da8fb3762f9 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -184,7 +184,9 @@ def add_common_opts(parser) -> None: help='Run all KUnit tests through allyesconfig', action='store_true') parser.add_argument('--kunitconfig', - help='Path to Kconfig fragment that enables KUnit tests', + help='Path to Kconfig fragment that enables KUnit tests.' + ' If given a directory, (e.g. lib/kunit), "/.kunitconfig" ' + 'will get automatically appended.', metavar='kunitconfig') def add_build_opts(parser) -> None: diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index f309a33256cd..89a7d4024e87 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -132,6 +132,8 @@ class LinuxSourceTree(object): return if kunitconfig_path: + if os.path.isdir(kunitconfig_path): + kunitconfig_path = os.path.join(kunitconfig_path, KUNITCONFIG_PATH) if not os.path.exists(kunitconfig_path): raise ConfigError(f'Specified kunitconfig ({kunitconfig_path}) does not exist') else: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 1ad3049e9069..2e809dd956a7 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -251,6 +251,12 @@ class LinuxSourceTreeTest(unittest.TestCase): with tempfile.NamedTemporaryFile('wt') as kunitconfig: tree = kunit_kernel.LinuxSourceTree('', kunitconfig_path=kunitconfig.name) + def test_dir_kunitconfig(self): + with tempfile.TemporaryDirectory('') as dir: + with open(os.path.join(dir, '.kunitconfig'), 'w') as f: + pass + tree = kunit_kernel.LinuxSourceTree('', kunitconfig_path=dir) + # TODO: add more test cases. -- cgit v1.2.3 From 359a376081d4fadfb073e3ddeb6bd6dc94d98341 Mon Sep 17 00:00:00 2001 From: Uriel Guajardo Date: Thu, 11 Mar 2021 07:23:13 -0800 Subject: kunit: support failure from dynamic analysis tools Add a kunit_fail_current_test() function to fail the currently running test, if any, with an error message. This is largely intended for dynamic analysis tools like UBSAN and for fakes. E.g. say I had a fake ops struct for testing and I wanted my `free` function to complain if it was called with an invalid argument, or caught a double-free. Most return void and have no normal means of signalling failure (e.g. super_operations, iommu_ops, etc.). Key points: * Always update current->kunit_test so anyone can use it. * commit 83c4e7a0363b ("KUnit: KASAN Integration") only updated it for CONFIG_KASAN=y * Create a new header so non-test code doesn't have to include all of (e.g. lib/ubsan.c) * Forward the file and line number to make it easier to track down failures * Declare the helper function for nice __printf() warnings about mismatched format strings even when KUnit is not enabled. Example output from kunit_fail_current_test("message"): [15:19:34] [FAILED] example_simple_test [15:19:34] # example_simple_test: initializing [15:19:34] # example_simple_test: lib/kunit/kunit-example-test.c:24: message [15:19:34] not ok 1 - example_simple_test Fixed minor check patch with checkpatch --fix option: Shuah Khan Signed-off-by: Daniel Latypov Signed-off-by: Uriel Guajardo Reviewed-by: Alan Maguire Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test-bug.h | 29 +++++++++++++++++++++++++++++ lib/kunit/test.c | 39 +++++++++++++++++++++++++++++++++++---- 2 files changed, 64 insertions(+), 4 deletions(-) create mode 100644 include/kunit/test-bug.h (limited to 'lib') diff --git a/include/kunit/test-bug.h b/include/kunit/test-bug.h new file mode 100644 index 000000000000..ce6f6edc7801 --- /dev/null +++ b/include/kunit/test-bug.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KUnit API allowing dynamic analysis tools to interact with KUnit tests + * + * Copyright (C) 2020, Google LLC. + * Author: Uriel Guajardo + */ + +#ifndef _KUNIT_TEST_BUG_H +#define _KUNIT_TEST_BUG_H + +#define kunit_fail_current_test(fmt, ...) \ + __kunit_fail_current_test(__FILE__, __LINE__, fmt, ##__VA_ARGS__) + +#if IS_BUILTIN(CONFIG_KUNIT) + +extern __printf(3, 4) void __kunit_fail_current_test(const char *file, int line, + const char *fmt, ...); + +#else + +static __printf(3, 4) void __kunit_fail_current_test(const char *file, int line, + const char *fmt, ...) +{ +} + +#endif + +#endif /* _KUNIT_TEST_BUG_H */ diff --git a/lib/kunit/test.c b/lib/kunit/test.c index ec9494e914ef..2f6cc0123232 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -16,6 +17,40 @@ #include "string-stream.h" #include "try-catch-impl.h" +#if IS_BUILTIN(CONFIG_KUNIT) +/* + * Fail the current test and print an error message to the log. + */ +void __kunit_fail_current_test(const char *file, int line, const char *fmt, ...) +{ + va_list args; + int len; + char *buffer; + + if (!current->kunit_test) + return; + + kunit_set_failure(current->kunit_test); + + /* kunit_err() only accepts literals, so evaluate the args first. */ + va_start(args, fmt); + len = vsnprintf(NULL, 0, fmt, args) + 1; + va_end(args); + + buffer = kunit_kmalloc(current->kunit_test, len, GFP_KERNEL); + if (!buffer) + return; + + va_start(args, fmt); + vsnprintf(buffer, len, fmt, args); + va_end(args); + + kunit_err(current->kunit_test, "%s:%d: %s", file, line, buffer); + kunit_kfree(current->kunit_test, buffer); +} +EXPORT_SYMBOL_GPL(__kunit_fail_current_test); +#endif + /* * Append formatted message to log, size of which is limited to * KUNIT_LOG_SIZE bytes (including null terminating byte). @@ -273,9 +308,7 @@ static void kunit_try_run_case(void *data) struct kunit_suite *suite = ctx->suite; struct kunit_case *test_case = ctx->test_case; -#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT)) current->kunit_test = test; -#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT) */ /* * kunit_run_case_internal may encounter a fatal error; if it does, @@ -624,9 +657,7 @@ void kunit_cleanup(struct kunit *test) spin_unlock(&test->lock); kunit_remove_resource(test, res); } -#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT)) current->kunit_test = NULL; -#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT)*/ } EXPORT_SYMBOL_GPL(kunit_cleanup); -- cgit v1.2.3 From 5dc33592e95534dc8455ce3e9baaaf3dae0fff82 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 5 Apr 2021 20:33:57 +0900 Subject: lockdep: Allow tuning tracing capacity constants. Since syzkaller continues various test cases until the kernel crashes, syzkaller tends to examine more locking dependencies than normal systems. As a result, syzbot is reporting that the fuzz testing was terminated due to hitting upper limits lockdep can track [1] [2] [3]. Since analysis via /proc/lockdep* did not show any obvious culprit [4] [5], we have no choice but allow tuning tracing capacity constants. [1] https://syzkaller.appspot.com/bug?id=3d97ba93fb3566000c1c59691ea427370d33ea1b [2] https://syzkaller.appspot.com/bug?id=381cb436fe60dc03d7fd2a092b46d7f09542a72a [3] https://syzkaller.appspot.com/bug?id=a588183ac34c1437fc0785e8f220e88282e5a29f [4] https://lkml.kernel.org/r/4b8f7a57-fa20-47bd-48a0-ae35d860f233@i-love.sakura.ne.jp [5] https://lkml.kernel.org/r/1c351187-253b-2d49-acaf-4563c63ae7d2@i-love.sakura.ne.jp References: https://lkml.kernel.org/r/1595640639-9310-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Acked-by: Dmitry Vyukov --- kernel/locking/lockdep.c | 2 +- kernel/locking/lockdep_internals.h | 8 ++++---- lib/Kconfig.debug | 40 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c6d0c1dc6253..6b96a965bd44 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1392,7 +1392,7 @@ static int add_lock_to_list(struct lock_class *this, /* * For good efficiency of modular, we use power of 2 */ -#define MAX_CIRCULAR_QUEUE_SIZE 4096UL +#define MAX_CIRCULAR_QUEUE_SIZE (1UL << CONFIG_LOCKDEP_CIRCULAR_QUEUE_BITS) #define CQ_MASK (MAX_CIRCULAR_QUEUE_SIZE-1) /* diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index de49f9e1c11b..ecb8662e7a4e 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -99,16 +99,16 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_STACK_TRACE_ENTRIES 262144UL #define STACK_TRACE_HASH_SIZE 8192 #else -#define MAX_LOCKDEP_ENTRIES 32768UL +#define MAX_LOCKDEP_ENTRIES (1UL << CONFIG_LOCKDEP_BITS) -#define MAX_LOCKDEP_CHAINS_BITS 16 +#define MAX_LOCKDEP_CHAINS_BITS CONFIG_LOCKDEP_CHAINS_BITS /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ -#define MAX_STACK_TRACE_ENTRIES 524288UL -#define STACK_TRACE_HASH_SIZE 16384 +#define MAX_STACK_TRACE_ENTRIES (1UL << CONFIG_LOCKDEP_STACK_TRACE_BITS) +#define STACK_TRACE_HASH_SIZE (1 << CONFIG_LOCKDEP_STACK_TRACE_HASH_BITS) #endif /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..f107000e7c28 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1370,6 +1370,46 @@ config LOCKDEP config LOCKDEP_SMALL bool +config LOCKDEP_BITS + int "Bitsize for MAX_LOCKDEP_ENTRIES" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 15 + help + Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message. + +config LOCKDEP_CHAINS_BITS + int "Bitsize for MAX_LOCKDEP_CHAINS" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 16 + help + Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message. + +config LOCKDEP_STACK_TRACE_BITS + int "Bitsize for MAX_STACK_TRACE_ENTRIES" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 19 + help + Try increasing this value if you hit "BUG: MAX_STACK_TRACE_ENTRIES too low!" message. + +config LOCKDEP_STACK_TRACE_HASH_BITS + int "Bitsize for STACK_TRACE_HASH_SIZE" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 14 + help + Try increasing this value if you need large MAX_STACK_TRACE_ENTRIES. + +config LOCKDEP_CIRCULAR_QUEUE_BITS + int "Bitsize for elements in circular_queue struct" + depends on LOCKDEP + range 10 30 + default 12 + help + Try increasing this value if you hit "lockdep bfs error:-1" warning due to __cq_enqueue() failure. + config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP -- cgit v1.2.3 From a48849e2358ecf1a347a03b33dc27b9b2f25f8fd Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 25 Feb 2021 17:46:39 +0100 Subject: printk: clarify the documentation for plain pointer printing We have several modifiers for plain pointers (%p, %px and %pK) and now also the no_hash_pointers boot parameter. The documentation should help to choose which variant to use. Importantly, we should discourage %px in favor of %p (with the new boot parameter when debugging), and stress that %pK should be only used for procfs and similar files, not dmesg buffer. This patch clarifies the documentation in that regard. Signed-off-by: Vlastimil Babka Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210225164639.27212-1-vbabka@suse.cz --- Documentation/core-api/printk-formats.rst | 26 +++++++++++++++++++++++++- lib/vsprintf.c | 7 +++++-- 2 files changed, 30 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 160e710d992f..6724adf58082 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -79,7 +79,19 @@ Pointers printed without a specifier extension (i.e unadorned %p) are hashed to prevent leaking information about the kernel memory layout. This has the added benefit of providing a unique identifier. On 64-bit machines the first 32 bits are zeroed. The kernel will print ``(ptrval)`` until it -gathers enough entropy. If you *really* want the address see %px below. +gathers enough entropy. + +When possible, use specialised modifiers such as %pS or %pB (described below) +to avoid the need of providing an unhashed address that has to be interpreted +post-hoc. If not possible, and the aim of printing the address is to provide +more information for debugging, use %p and boot the kernel with the +``no_hash_pointers`` parameter during debugging, which will print all %p +addresses unmodified. If you *really* always want the unmodified address, see +%px below. + +If (and only if) you are printing addresses as a content of a virtual file in +e.g. procfs or sysfs (using e.g. seq_printf(), not printk()) read by a +userspace process, use the %pK modifier described below instead of %p or %px. Error Pointers -------------- @@ -139,6 +151,11 @@ For printing kernel pointers which should be hidden from unprivileged users. The behaviour of %pK depends on the kptr_restrict sysctl - see Documentation/admin-guide/sysctl/kernel.rst for more details. +This modifier is *only* intended when producing content of a file read by +userspace from e.g. procfs or sysfs, not for dmesg. Please refer to the +section about %p above for discussion about how to manage hashing pointers +in printk(). + Unmodified Addresses -------------------- @@ -153,6 +170,13 @@ equivalent to %lx (or %lu). %px is preferred because it is more uniquely grep'able. If in the future we need to modify the way the kernel handles printing pointers we will be better equipped to find the call sites. +Before using %px, consider if using %p is sufficient together with enabling the +``no_hash_pointers`` kernel parameter during debugging sessions (see the %p +description above). One valid scenario for %px might be printing information +immediately before a panic, which prevents any sensitive information to be +exploited anyway, and with %px there would be no need to reproduce the panic +with no_hash_pointers. + Pointer Differences ------------------- diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 4a14889ccb35..5ec8ad238d03 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2189,7 +2189,9 @@ early_param("no_hash_pointers", no_hash_pointers_enable); * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. - * - 'K' For a kernel pointer that should be hidden from unprivileged users + * - 'K' For a kernel pointer that should be hidden from unprivileged users. + * Use only for procfs, sysfs and similar files, not printk(); please + * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): @@ -2228,7 +2230,8 @@ early_param("no_hash_pointers", no_hash_pointers_enable); * Without an option prints the full name of the node * f full name * P node name, including a possible unit address - * - 'x' For printing the address. Equivalent to "%lx". + * - 'x' For printing the address unmodified. Equivalent to "%lx". + * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: -- cgit v1.2.3 From 7c566bb5e4d5fb0d89579a90d8a1f54eaff6f95d Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Thu, 11 Feb 2021 21:35:46 +0900 Subject: asm-generic/io.h: Add a non-posted variant of ioremap() ARM64 currently defaults to posted MMIO (nGnRE), but some devices require the use of non-posted MMIO (nGnRnE). Introduce a new ioremap() variant to handle this case. ioremap_np() returns NULL on arches that do not implement this variant. sparc64 is the only architecture that needs to be touched directly, because it includes neither of the generic io.h or iomap.h headers. This adds the IORESOURCE_MEM_NONPOSTED flag, which maps to this variant and marks a given resource as requiring non-posted mappings. This is implemented in the resource system because it is a SoC-level requirement, so existing drivers do not need special-case code to pick this ioremap variant. Then this is implemented in devres by introducing devm_ioremap_np(), and making devm_ioremap_resource() automatically select this variant when the resource has the IORESOURCE_MEM_NONPOSTED flag set. Acked-by: Marc Zyngier Signed-off-by: Hector Martin --- Documentation/driver-api/driver-model/devres.rst | 1 + arch/sparc/include/asm/io_64.h | 4 ++++ include/asm-generic/io.h | 22 +++++++++++++++++++++- include/asm-generic/iomap.h | 9 +++++++++ include/linux/io.h | 2 ++ include/linux/ioport.h | 1 + lib/devres.c | 22 ++++++++++++++++++++++ 7 files changed, 60 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index cd8b6e657b94..2f45877a539d 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -309,6 +309,7 @@ IOMAP devm_ioremap() devm_ioremap_uc() devm_ioremap_wc() + devm_ioremap_np() devm_ioremap_resource() : checks resource, requests memory region, ioremaps devm_ioremap_resource_wc() devm_platform_ioremap_resource() : calls devm_ioremap_resource() for platform device diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h index 9bb27e5c22f1..9fbfc9574432 100644 --- a/arch/sparc/include/asm/io_64.h +++ b/arch/sparc/include/asm/io_64.h @@ -409,6 +409,10 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size) #define ioremap_uc(X,Y) ioremap((X),(Y)) #define ioremap_wc(X,Y) ioremap((X),(Y)) #define ioremap_wt(X,Y) ioremap((X),(Y)) +static inline void __iomem *ioremap_np(unsigned long offset, unsigned long size) +{ + return NULL; +} static inline void iounmap(volatile void __iomem *addr) { diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index c6af40ce03be..082e0c96db6e 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -942,7 +942,9 @@ static inline void *phys_to_virt(unsigned long address) * * ioremap_wc() and ioremap_wt() can provide more relaxed caching attributes * for specific drivers if the architecture choses to implement them. If they - * are not implemented we fall back to plain ioremap. + * are not implemented we fall back to plain ioremap. Conversely, ioremap_np() + * can provide stricter non-posted write semantics if the architecture + * implements them. */ #ifndef CONFIG_MMU #ifndef ioremap @@ -993,6 +995,24 @@ static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size) { return NULL; } + +/* + * ioremap_np needs an explicit architecture implementation, as it + * requests stronger semantics than regular ioremap(). Portable drivers + * should instead use one of the higher-level abstractions, like + * devm_ioremap_resource(), to choose the correct variant for any given + * device and bus. Portable drivers with a good reason to want non-posted + * write semantics should always provide an ioremap() fallback in case + * ioremap_np() is not available. + */ +#ifndef ioremap_np +#define ioremap_np ioremap_np +static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) +{ + return NULL; +} +#endif + #endif #ifdef CONFIG_HAS_IOPORT_MAP diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 649224664969..9b3eb6d86200 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -101,6 +101,15 @@ extern void ioport_unmap(void __iomem *); #define ioremap_wt ioremap #endif +#ifndef ARCH_HAS_IOREMAP_NP +/* See the comment in asm-generic/io.h about ioremap_np(). */ +#define ioremap_np ioremap_np +static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) +{ + return NULL; +} +#endif + #ifdef CONFIG_PCI /* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ struct pci_dev; diff --git a/include/linux/io.h b/include/linux/io.h index 8394c56babc2..d718354ed3e1 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -68,6 +68,8 @@ void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, resource_size_t size); +void __iomem *devm_ioremap_np(struct device *dev, resource_size_t offset, + resource_size_t size); void devm_iounmap(struct device *dev, void __iomem *addr); int check_signature(const volatile void __iomem *io_addr, const unsigned char *signature, int length); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 55de385c839c..1de6c2e40c32 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -108,6 +108,7 @@ struct resource { #define IORESOURCE_MEM_32BIT (3<<3) #define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */ #define IORESOURCE_MEM_EXPANSIONROM (1<<6) +#define IORESOURCE_MEM_NONPOSTED (1<<7) /* PnP I/O specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IO_16BIT_ADDR (1<<0) diff --git a/lib/devres.c b/lib/devres.c index 2a4ff5d64288..4679dbb1bf5f 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -10,6 +10,7 @@ enum devm_ioremap_type { DEVM_IOREMAP = 0, DEVM_IOREMAP_UC, DEVM_IOREMAP_WC, + DEVM_IOREMAP_NP, }; void devm_ioremap_release(struct device *dev, void *res) @@ -42,6 +43,9 @@ static void __iomem *__devm_ioremap(struct device *dev, resource_size_t offset, case DEVM_IOREMAP_WC: addr = ioremap_wc(offset, size); break; + case DEVM_IOREMAP_NP: + addr = ioremap_np(offset, size); + break; } if (addr) { @@ -98,6 +102,21 @@ void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(devm_ioremap_wc); +/** + * devm_ioremap_np - Managed ioremap_np() + * @dev: Generic device to remap IO address for + * @offset: Resource address to map + * @size: Size of map + * + * Managed ioremap_np(). Map is automatically unmapped on driver detach. + */ +void __iomem *devm_ioremap_np(struct device *dev, resource_size_t offset, + resource_size_t size) +{ + return __devm_ioremap(dev, offset, size, DEVM_IOREMAP_NP); +} +EXPORT_SYMBOL(devm_ioremap_np); + /** * devm_iounmap - Managed iounmap() * @dev: Generic device to unmap for @@ -128,6 +147,9 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, return IOMEM_ERR_PTR(-EINVAL); } + if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED) + type = DEVM_IOREMAP_NP; + size = resource_size(res); if (res->name) -- cgit v1.2.3 From 4f0f586bf0c898233d8f316f471a21db2abd522d Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Thu, 8 Apr 2021 11:28:34 -0700 Subject: treewide: Change list_sort to use const pointers list_sort() internally casts the comparison function passed to it to a different type with constant struct list_head pointers, and uses this pointer to call the functions, which trips indirect call Control-Flow Integrity (CFI) checking. Instead of removing the consts, this change defines the list_cmp_func_t type and changes the comparison function types of all list_sort() callers to use const pointers, thus avoiding type mismatches. Suggested-by: Nick Desaulniers Signed-off-by: Sami Tolvanen Reviewed-by: Nick Desaulniers Reviewed-by: Christoph Hellwig Reviewed-by: Kees Cook Tested-by: Nick Desaulniers Tested-by: Nathan Chancellor Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210408182843.1754385-10-samitolvanen@google.com --- arch/arm64/kvm/vgic/vgic-its.c | 8 ++++---- arch/arm64/kvm/vgic/vgic.c | 3 ++- block/blk-mq-sched.c | 3 ++- block/blk-mq.c | 3 ++- drivers/acpi/nfit/core.c | 3 ++- drivers/acpi/numa/hmat.c | 3 ++- drivers/clk/keystone/sci-clk.c | 4 ++-- drivers/gpu/drm/drm_modes.c | 3 ++- drivers/gpu/drm/i915/gt/intel_engine_user.c | 3 ++- drivers/gpu/drm/i915/gvt/debugfs.c | 2 +- drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 3 ++- drivers/gpu/drm/radeon/radeon_cs.c | 4 ++-- drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c | 3 ++- drivers/interconnect/qcom/bcm-voter.c | 2 +- drivers/md/raid5.c | 3 ++- drivers/misc/sram.c | 4 ++-- drivers/nvme/host/core.c | 3 ++- drivers/pci/controller/cadence/pcie-cadence-host.c | 3 ++- drivers/spi/spi-loopback-test.c | 3 ++- fs/btrfs/raid56.c | 3 ++- fs/btrfs/tree-log.c | 3 ++- fs/btrfs/volumes.c | 3 ++- fs/ext4/fsmap.c | 4 ++-- fs/gfs2/glock.c | 3 ++- fs/gfs2/log.c | 2 +- fs/gfs2/lops.c | 3 ++- fs/iomap/buffered-io.c | 3 ++- fs/ubifs/gc.c | 7 ++++--- fs/ubifs/replay.c | 4 ++-- fs/xfs/scrub/bitmap.c | 4 ++-- fs/xfs/xfs_bmap_item.c | 4 ++-- fs/xfs/xfs_buf.c | 6 +++--- fs/xfs/xfs_extent_busy.c | 4 ++-- fs/xfs/xfs_extent_busy.h | 3 ++- fs/xfs/xfs_extfree_item.c | 4 ++-- fs/xfs/xfs_refcount_item.c | 4 ++-- fs/xfs/xfs_rmap_item.c | 4 ++-- include/linux/list_sort.h | 7 ++++--- lib/list_sort.c | 17 ++++++----------- lib/test_list_sort.c | 3 ++- net/tipc/name_table.c | 4 ++-- 41 files changed, 90 insertions(+), 72 deletions(-) (limited to 'lib') diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 40cbaca81333..b9518f94bd43 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2190,8 +2190,8 @@ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, return offset; } -static int vgic_its_ite_cmp(void *priv, struct list_head *a, - struct list_head *b) +static int vgic_its_ite_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct its_ite *itea = container_of(a, struct its_ite, ite_list); struct its_ite *iteb = container_of(b, struct its_ite, ite_list); @@ -2329,8 +2329,8 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, return offset; } -static int vgic_its_device_cmp(void *priv, struct list_head *a, - struct list_head *b) +static int vgic_its_device_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct its_device *deva = container_of(a, struct its_device, dev_list); struct its_device *devb = container_of(b, struct its_device, dev_list); diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 1c597c9885fa..15b666200f0b 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -255,7 +255,8 @@ static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq) * Return negative if "a" sorts before "b", 0 to preserve order, and positive * to sort "b" before "a". */ -static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) +static int vgic_irq_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list); struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index e1e997af89a0..3ebd6f10f728 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -75,7 +75,8 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) blk_mq_run_hw_queue(hctx, true); } -static int sched_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +static int sched_rq_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); diff --git a/block/blk-mq.c b/block/blk-mq.c index d4d7c1caa439..4e3a70ab5be1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1895,7 +1895,8 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, spin_unlock(&ctx->lock); } -static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +static int plug_rq_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 8c5dde628405..d15e3ee93b5b 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1195,7 +1195,8 @@ static int __nfit_mem_init(struct acpi_nfit_desc *acpi_desc, return 0; } -static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b) +static int nfit_mem_cmp(void *priv, const struct list_head *_a, + const struct list_head *_b) { struct nfit_mem *a = container_of(_a, typeof(*a), list); struct nfit_mem *b = container_of(_b, typeof(*b), list); diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index cb73a5d6ea76..137a5dd880c2 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -558,7 +558,8 @@ static bool hmat_update_best(u8 type, u32 value, u32 *best) return updated; } -static int initiator_cmp(void *priv, struct list_head *a, struct list_head *b) +static int initiator_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct memory_initiator *ia; struct memory_initiator *ib; diff --git a/drivers/clk/keystone/sci-clk.c b/drivers/clk/keystone/sci-clk.c index aaf31abe1c8f..7e1b136e71ae 100644 --- a/drivers/clk/keystone/sci-clk.c +++ b/drivers/clk/keystone/sci-clk.c @@ -503,8 +503,8 @@ static int ti_sci_scan_clocks_from_fw(struct sci_clk_provider *provider) #else -static int _cmp_sci_clk_list(void *priv, struct list_head *a, - struct list_head *b) +static int _cmp_sci_clk_list(void *priv, const struct list_head *a, + const struct list_head *b) { struct sci_clk *ca = container_of(a, struct sci_clk, node); struct sci_clk *cb = container_of(b, struct sci_clk, node); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 1ac67d4505e0..6662d0457ad6 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1290,7 +1290,8 @@ EXPORT_SYMBOL(drm_mode_prune_invalid); * Negative if @lh_a is better than @lh_b, zero if they're equivalent, or * positive if @lh_b is better than @lh_a. */ -static int drm_mode_compare(void *priv, struct list_head *lh_a, struct list_head *lh_b) +static int drm_mode_compare(void *priv, const struct list_head *lh_a, + const struct list_head *lh_b) { struct drm_display_mode *a = list_entry(lh_a, struct drm_display_mode, head); struct drm_display_mode *b = list_entry(lh_b, struct drm_display_mode, head); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 34e6096f196e..da21d2a10cc9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -49,7 +49,8 @@ static const u8 uabi_classes[] = { [VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE, }; -static int engine_cmp(void *priv, struct list_head *A, struct list_head *B) +static int engine_cmp(void *priv, const struct list_head *A, + const struct list_head *B) { const struct intel_engine_cs *a = container_of((struct rb_node *)A, typeof(*a), uabi_node); diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index 62e6a14ad58e..9f1c209d9251 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -41,7 +41,7 @@ struct diff_mmio { /* Compare two diff_mmio items. */ static int mmio_offset_compare(void *priv, - struct list_head *a, struct list_head *b) + const struct list_head *a, const struct list_head *b) { struct diff_mmio *ma; struct diff_mmio *mb; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index c1adea8765a9..52b9c39e0155 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1076,7 +1076,8 @@ static int igt_ppgtt_shrink_boom(void *arg) return exercise_ppgtt(arg, shrink_boom); } -static int sort_holes(void *priv, struct list_head *A, struct list_head *B) +static int sort_holes(void *priv, const struct list_head *A, + const struct list_head *B) { struct drm_mm_node *a = list_entry(A, typeof(*a), hole_stack); struct drm_mm_node *b = list_entry(B, typeof(*b), hole_stack); diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 35e937d39b51..1a5c3db1d53b 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -393,8 +393,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) return 0; } -static int cmp_size_smaller_first(void *priv, struct list_head *a, - struct list_head *b) +static int cmp_size_smaller_first(void *priv, const struct list_head *a, + const struct list_head *b) { struct radeon_bo_list *la = list_entry(a, struct radeon_bo_list, tv.head); struct radeon_bo_list *lb = list_entry(b, struct radeon_bo_list, tv.head); diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c index d399523206c7..29d71267af78 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c @@ -83,7 +83,8 @@ usnic_uiom_interval_node_alloc(long int start, long int last, int ref_cnt, return interval; } -static int interval_cmp(void *priv, struct list_head *a, struct list_head *b) +static int interval_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct usnic_uiom_interval_node *node_a, *node_b; diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c index 1cc565bce2f4..d1591a28b743 100644 --- a/drivers/interconnect/qcom/bcm-voter.c +++ b/drivers/interconnect/qcom/bcm-voter.c @@ -39,7 +39,7 @@ struct bcm_voter { u32 tcs_wait; }; -static int cmp_vcd(void *priv, struct list_head *a, struct list_head *b) +static int cmp_vcd(void *priv, const struct list_head *a, const struct list_head *b) { const struct qcom_icc_bcm *bcm_a = list_entry(a, struct qcom_icc_bcm, list); const struct qcom_icc_bcm *bcm_b = list_entry(b, struct qcom_icc_bcm, list); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5d57a5bd171f..841e1c1aa5e6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -953,7 +953,8 @@ static void dispatch_bio_list(struct bio_list *tmp) submit_bio_noacct(bio); } -static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b) +static int cmp_stripe(void *priv, const struct list_head *a, + const struct list_head *b) { const struct r5pending_data *da = list_entry(a, struct r5pending_data, sibling); diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c index 6c1a23cb3e8c..202bf951e909 100644 --- a/drivers/misc/sram.c +++ b/drivers/misc/sram.c @@ -144,8 +144,8 @@ static void sram_free_partitions(struct sram_dev *sram) } } -static int sram_reserve_cmp(void *priv, struct list_head *a, - struct list_head *b) +static int sram_reserve_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct sram_reserve *ra = list_entry(a, struct sram_reserve, list); struct sram_reserve *rb = list_entry(b, struct sram_reserve, list); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0896e21642be..5eaaa51a5e30 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3855,7 +3855,8 @@ out_unlock: return ret; } -static int ns_cmp(void *priv, struct list_head *a, struct list_head *b) +static int ns_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct nvme_ns *nsa = container_of(a, struct nvme_ns, list); struct nvme_ns *nsb = container_of(b, struct nvme_ns, list); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c index 73dcf8cf98fb..ae1c55503513 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-host.c +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -345,7 +345,8 @@ static int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, return 0; } -static int cdns_pcie_host_dma_ranges_cmp(void *priv, struct list_head *a, struct list_head *b) +static int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct resource_entry *entry1, *entry2; diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c index df981e55c24c..f1cf2232f0b5 100644 --- a/drivers/spi/spi-loopback-test.c +++ b/drivers/spi/spi-loopback-test.c @@ -454,7 +454,8 @@ struct rx_ranges { u8 *end; }; -static int rx_ranges_cmp(void *priv, struct list_head *a, struct list_head *b) +static int rx_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct rx_ranges *rx_a = list_entry(a, struct rx_ranges, list); struct rx_ranges *rx_b = list_entry(b, struct rx_ranges, list); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 8c31357f08ed..f4139de63b2e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1634,7 +1634,8 @@ struct btrfs_plug_cb { /* * rbios on the plug list are sorted for easier merging. */ -static int plug_cmp(void *priv, struct list_head *a, struct list_head *b) +static int plug_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct btrfs_raid_bio *ra = container_of(a, struct btrfs_raid_bio, plug_list); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 92a368627791..00a88bd8105e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4136,7 +4136,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, return ret; } -static int extent_cmp(void *priv, struct list_head *a, struct list_head *b) +static int extent_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct extent_map *em1, *em2; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1c6810bbaf8b..912dd8b9f156 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1224,7 +1224,8 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, return 0; } -static int devid_cmp(void *priv, struct list_head *a, struct list_head *b) +static int devid_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct btrfs_device *dev1, *dev2; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4c2a9fe30067..4493ef0c715e 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -354,8 +354,8 @@ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb, /* Compare two fsmap items. */ static int ext4_getfsmap_compare(void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct ext4_fsmap *fa; struct ext4_fsmap *fb; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9567520d79f7..c06a6cdf05de 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1732,7 +1732,8 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) spin_unlock(&gl->gl_lockref.lock); } -static int glock_cmp(void *priv, struct list_head *a, struct list_head *b) +static int glock_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct gfs2_glock *gla, *glb; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 6410281546f9..88649b43fcff 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -695,7 +695,7 @@ void log_flush_wait(struct gfs2_sbd *sdp) } } -static int ip_cmp(void *priv, struct list_head *a, struct list_head *b) +static int ip_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct gfs2_inode *ipa, *ipb; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index a82f4747aa8d..b4809967efc6 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -634,7 +634,8 @@ static void gfs2_check_magic(struct buffer_head *bh) kunmap_atomic(kaddr); } -static int blocknr_cmp(void *priv, struct list_head *a, struct list_head *b) +static int blocknr_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct gfs2_bufdata *bda, *bdb; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 414769a6ad11..0129e6bab985 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1155,7 +1155,8 @@ iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends, EXPORT_SYMBOL_GPL(iomap_ioend_try_merge); static int -iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b) +iomap_ioend_compare(void *priv, const struct list_head *a, + const struct list_head *b) { struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list); struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list); diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index a4aaeea63893..dc3e26e9ed7b 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -102,7 +102,8 @@ static int switch_gc_head(struct ubifs_info *c) * This function compares data nodes @a and @b. Returns %1 if @a has greater * inode or block number, and %-1 otherwise. */ -static int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) +static int data_nodes_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { ino_t inuma, inumb; struct ubifs_info *c = priv; @@ -145,8 +146,8 @@ static int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) * first and sorted by length in descending order. Directory entry nodes go * after inode nodes and are sorted in ascending hash valuer order. */ -static int nondata_nodes_cmp(void *priv, struct list_head *a, - struct list_head *b) +static int nondata_nodes_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { ino_t inuma, inumb; struct ubifs_info *c = priv; diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 0f8a6a16421b..4d17e5382b74 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -298,8 +298,8 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r) * entries @a and @b by comparing their sequence numer. Returns %1 if @a has * greater sequence number and %-1 otherwise. */ -static int replay_entries_cmp(void *priv, struct list_head *a, - struct list_head *b) +static int replay_entries_cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct ubifs_info *c = priv; struct replay_entry *ra, *rb; diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index f88694f22d05..813b5f219113 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -63,8 +63,8 @@ xbitmap_init( static int xbitmap_range_cmp( void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct xbitmap_range *ap; struct xbitmap_range *bp; diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 2344757ede63..e3a691937e92 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -265,8 +265,8 @@ xfs_trans_log_finish_bmap_update( static int xfs_bmap_update_diff_items( void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct xfs_bmap_intent *ba; struct xfs_bmap_intent *bb; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 37a1d12762d8..592800c8852f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2124,9 +2124,9 @@ xfs_buf_delwri_queue( */ static int xfs_buf_cmp( - void *priv, - struct list_head *a, - struct list_head *b) + void *priv, + const struct list_head *a, + const struct list_head *b) { struct xfs_buf *ap = container_of(a, struct xfs_buf, b_list); struct xfs_buf *bp = container_of(b, struct xfs_buf, b_list); diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index ef17c1f6db32..a4075685d9eb 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -629,8 +629,8 @@ xfs_extent_busy_wait_all( int xfs_extent_busy_ag_cmp( void *priv, - struct list_head *l1, - struct list_head *l2) + const struct list_head *l1, + const struct list_head *l2) { struct xfs_extent_busy *b1 = container_of(l1, struct xfs_extent_busy, list); diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index 990ab3891971..8aea07100092 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -58,7 +58,8 @@ void xfs_extent_busy_wait_all(struct xfs_mount *mp); int -xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b); +xfs_extent_busy_ag_cmp(void *priv, const struct list_head *a, + const struct list_head *b); static inline void xfs_extent_busy_sort(struct list_head *list) { diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 93223ebb3372..2424230ca2c3 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -397,8 +397,8 @@ xfs_trans_free_extent( static int xfs_extent_free_diff_items( void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct xfs_mount *mp = priv; struct xfs_extent_free_item *ra; diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 07ebccbbf4df..746f4eda724c 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -269,8 +269,8 @@ xfs_trans_log_finish_refcount_update( static int xfs_refcount_update_diff_items( void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct xfs_mount *mp = priv; struct xfs_refcount_intent *ra; diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 49cebd68b672..dc4f0c9f0897 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -337,8 +337,8 @@ xfs_trans_log_finish_rmap_update( static int xfs_rmap_update_diff_items( void *priv, - struct list_head *a, - struct list_head *b) + const struct list_head *a, + const struct list_head *b) { struct xfs_mount *mp = priv; struct xfs_rmap_intent *ra; diff --git a/include/linux/list_sort.h b/include/linux/list_sort.h index 20f178c24e9d..453105f74e05 100644 --- a/include/linux/list_sort.h +++ b/include/linux/list_sort.h @@ -6,8 +6,9 @@ struct list_head; +typedef int __attribute__((nonnull(2,3))) (*list_cmp_func_t)(void *, + const struct list_head *, const struct list_head *); + __attribute__((nonnull(2,3))) -void list_sort(void *priv, struct list_head *head, - int (*cmp)(void *priv, struct list_head *a, - struct list_head *b)); +void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp); #endif diff --git a/lib/list_sort.c b/lib/list_sort.c index 52f0c258c895..a926d96ffd44 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -7,16 +7,13 @@ #include #include -typedef int __attribute__((nonnull(2,3))) (*cmp_func)(void *, - struct list_head const *, struct list_head const *); - /* * Returns a list organized in an intermediate format suited * to chaining of merge() calls: null-terminated, no reserved or * sentinel head node, "prev" links not maintained. */ __attribute__((nonnull(2,3,4))) -static struct list_head *merge(void *priv, cmp_func cmp, +static struct list_head *merge(void *priv, list_cmp_func_t cmp, struct list_head *a, struct list_head *b) { struct list_head *head, **tail = &head; @@ -52,7 +49,7 @@ static struct list_head *merge(void *priv, cmp_func cmp, * throughout. */ __attribute__((nonnull(2,3,4,5))) -static void merge_final(void *priv, cmp_func cmp, struct list_head *head, +static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, struct list_head *a, struct list_head *b) { struct list_head *tail = head; @@ -185,9 +182,7 @@ static void merge_final(void *priv, cmp_func cmp, struct list_head *head, * 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1). */ __attribute__((nonnull(2,3))) -void list_sort(void *priv, struct list_head *head, - int (*cmp)(void *priv, struct list_head *a, - struct list_head *b)) +void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp) { struct list_head *list = head->next, *pending = NULL; size_t count = 0; /* Count of pending */ @@ -227,7 +222,7 @@ void list_sort(void *priv, struct list_head *head, if (likely(bits)) { struct list_head *a = *tail, *b = a->prev; - a = merge(priv, (cmp_func)cmp, b, a); + a = merge(priv, cmp, b, a); /* Install the merged result in place of the inputs */ a->prev = b->prev; *tail = a; @@ -249,10 +244,10 @@ void list_sort(void *priv, struct list_head *head, if (!next) break; - list = merge(priv, (cmp_func)cmp, pending, list); + list = merge(priv, cmp, pending, list); pending = next; } /* The final merge, rebuilding prev links */ - merge_final(priv, (cmp_func)cmp, head, pending, list); + merge_final(priv, cmp, head, pending, list); } EXPORT_SYMBOL(list_sort); diff --git a/lib/test_list_sort.c b/lib/test_list_sort.c index 1f017d3b610e..00daaf23316f 100644 --- a/lib/test_list_sort.c +++ b/lib/test_list_sort.c @@ -56,7 +56,8 @@ static int __init check(struct debug_el *ela, struct debug_el *elb) return 0; } -static int __init cmp(void *priv, struct list_head *a, struct list_head *b) +static int __init cmp(void *priv, const struct list_head *a, + const struct list_head *b) { struct debug_el *ela, *elb; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ee5ac40ea2b6..f8141443f2e2 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -397,8 +397,8 @@ static struct publication *tipc_service_remove_publ(struct service_range *sr, * Code reused: time_after32() for the same purpose */ #define publication_after(pa, pb) time_after32((pa)->id, (pb)->id) -static int tipc_publ_sort(void *priv, struct list_head *a, - struct list_head *b) +static int tipc_publ_sort(void *priv, const struct list_head *a, + const struct list_head *b) { struct publication *pa, *pb; -- cgit v1.2.3 From b4104180a2efb85f55e1ba1407885c9421970338 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Apr 2021 11:48:52 +0200 Subject: kobject_uevent: remove warning in init_uevent_argv() syzbot can trigger the WARN() in init_uevent_argv() which isn't the nicest as the code does properly recover and handle the error. So change the WARN() call to pr_warn() and provide some more information on what the buffer size that was needed. Link: https://lore.kernel.org/r/20201107082206.GA19079@kroah.com Cc: "Rafael J. Wysocki" Cc: linux-kernel@vger.kernel.org Reported-by: syzbot+92340f7b2b4789907fdb@syzkaller.appspotmail.com Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210405094852.1348499-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 7998affa45d4..c87d5b6a8a55 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -251,12 +251,13 @@ static int kobj_usermode_filter(struct kobject *kobj) static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { + int buffer_size = sizeof(env->buf) - env->buflen; int len; - len = strlcpy(&env->buf[env->buflen], subsystem, - sizeof(env->buf) - env->buflen); - if (len >= (sizeof(env->buf) - env->buflen)) { - WARN(1, KERN_ERR "init_uevent_argv: buffer size too small\n"); + len = strlcpy(&env->buf[env->buflen], subsystem, buffer_size); + if (len >= buffer_size) { + pr_warn("init_uevent_argv: buffer size of %d too small, needed %d\n", + buffer_size, len); return -ENOMEM; } -- cgit v1.2.3 From 2603f8a78dfb1d54f62dbacc490ea44aa6d80e04 Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Mon, 15 Mar 2021 13:20:12 +0000 Subject: kasan: Add KASAN mode kernel parameter Architectures supported by KASAN_HW_TAGS can provide a sync or async mode of execution. On an MTE enabled arm64 hw for example this can be identified with the synchronous or asynchronous tagging mode of execution. In synchronous mode, an exception is triggered if a tag check fault occurs. In asynchronous mode, if a tag check fault occurs, the TFSR_EL1 register is updated asynchronously. The kernel checks the corresponding bits periodically. KASAN requires a specific kernel command line parameter to make use of this hw features. Add KASAN HW execution mode kernel command line parameter. Note: This patch adds the kasan.mode kernel parameter and the sync/async kernel command line options to enable the described features. [ Add a new var instead of exposing kasan_arg_mode to be consistent with flags for other command line arguments. ] Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Reviewed-by: Andrey Konovalov Acked-by: Catalin Marinas Acked-by: Andrey Konovalov Tested-by: Andrey Konovalov Signed-off-by: Vincenzo Frascino Signed-off-by: Andrey Konovalov Link: https://lore.kernel.org/r/20210315132019.33202-3-vincenzo.frascino@arm.com Signed-off-by: Catalin Marinas --- Documentation/dev-tools/kasan.rst | 9 ++++++ lib/test_kasan.c | 2 +- mm/kasan/hw_tags.c | 60 ++++++++++++++++++++++++++++++++++++--- mm/kasan/kasan.h | 18 ++++++++---- 4 files changed, 78 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index ddf4239a5890..6f6ab3ed7b79 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -161,6 +161,15 @@ particular KASAN features. - ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``). +- ``kasan.mode=sync`` or ``=async`` controls whether KASAN is configured in + synchronous or asynchronous mode of execution (default: ``sync``). + Synchronous mode: a bad access is detected immediately when a tag + check fault occurs. + Asynchronous mode: a bad access detection is delayed. When a tag check + fault occurs, the information is stored in hardware (in the TFSR_EL1 + register for arm64). The kernel periodically checks the hardware and + only reports tag faults during these checks. + - ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack traces collection (default: ``on``). diff --git a/lib/test_kasan.c b/lib/test_kasan.c index e5647d147b35..479c31a5dc21 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -97,7 +97,7 @@ static void kasan_test_exit(struct kunit *test) READ_ONCE(fail_data.report_found)); \ if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) { \ if (READ_ONCE(fail_data.report_found)) \ - kasan_enable_tagging(); \ + kasan_enable_tagging_sync(); \ migrate_enable(); \ } \ } while (0) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 2aad21fda156..1df4ce803861 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -25,6 +25,12 @@ enum kasan_arg { KASAN_ARG_ON, }; +enum kasan_arg_mode { + KASAN_ARG_MODE_DEFAULT, + KASAN_ARG_MODE_SYNC, + KASAN_ARG_MODE_ASYNC, +}; + enum kasan_arg_stacktrace { KASAN_ARG_STACKTRACE_DEFAULT, KASAN_ARG_STACKTRACE_OFF, @@ -38,6 +44,7 @@ enum kasan_arg_fault { }; static enum kasan_arg kasan_arg __ro_after_init; +static enum kasan_arg_mode kasan_arg_mode __ro_after_init; static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init; static enum kasan_arg_fault kasan_arg_fault __ro_after_init; @@ -45,6 +52,10 @@ static enum kasan_arg_fault kasan_arg_fault __ro_after_init; DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled); EXPORT_SYMBOL(kasan_flag_enabled); +/* Whether the asynchronous mode is enabled. */ +bool kasan_flag_async __ro_after_init; +EXPORT_SYMBOL_GPL(kasan_flag_async); + /* Whether to collect alloc/free stack traces. */ DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace); @@ -68,6 +79,23 @@ static int __init early_kasan_flag(char *arg) } early_param("kasan", early_kasan_flag); +/* kasan.mode=sync/async */ +static int __init early_kasan_mode(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strcmp(arg, "sync")) + kasan_arg_mode = KASAN_ARG_MODE_SYNC; + else if (!strcmp(arg, "async")) + kasan_arg_mode = KASAN_ARG_MODE_ASYNC; + else + return -EINVAL; + + return 0; +} +early_param("kasan.mode", early_kasan_mode); + /* kasan.stacktrace=off/on */ static int __init early_kasan_flag_stacktrace(char *arg) { @@ -115,7 +143,15 @@ void kasan_init_hw_tags_cpu(void) return; hw_init_tags(KASAN_TAG_MAX); - hw_enable_tagging(); + + /* + * Enable async mode only when explicitly requested through + * the command line. + */ + if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC) + hw_enable_tagging_async(); + else + hw_enable_tagging_sync(); } /* kasan_init_hw_tags() is called once on boot CPU. */ @@ -132,6 +168,22 @@ void __init kasan_init_hw_tags(void) /* Enable KASAN. */ static_branch_enable(&kasan_flag_enabled); + switch (kasan_arg_mode) { + case KASAN_ARG_MODE_DEFAULT: + /* + * Default to sync mode. + * Do nothing, kasan_flag_async keeps its default value. + */ + break; + case KASAN_ARG_MODE_SYNC: + /* Do nothing, kasan_flag_async keeps its default value. */ + break; + case KASAN_ARG_MODE_ASYNC: + /* Async mode enabled. */ + kasan_flag_async = true; + break; + } + switch (kasan_arg_stacktrace) { case KASAN_ARG_STACKTRACE_DEFAULT: /* Default to enabling stack trace collection. */ @@ -194,10 +246,10 @@ void kasan_set_tagging_report_once(bool state) } EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once); -void kasan_enable_tagging(void) +void kasan_enable_tagging_sync(void) { - hw_enable_tagging(); + hw_enable_tagging_sync(); } -EXPORT_SYMBOL_GPL(kasan_enable_tagging); +EXPORT_SYMBOL_GPL(kasan_enable_tagging_sync); #endif diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8c55634d6edd..a3d0d165d97d 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -21,6 +21,7 @@ static inline bool kasan_stack_collection_enabled(void) #endif extern bool kasan_flag_panic __ro_after_init; +extern bool kasan_flag_async __ro_after_init; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #define KASAN_GRANULE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT) @@ -275,8 +276,11 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifdef CONFIG_KASAN_HW_TAGS -#ifndef arch_enable_tagging -#define arch_enable_tagging() +#ifndef arch_enable_tagging_sync +#define arch_enable_tagging_sync() +#endif +#ifndef arch_enable_tagging_async +#define arch_enable_tagging_async() #endif #ifndef arch_init_tags #define arch_init_tags(max_tag) @@ -294,7 +298,8 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define arch_set_mem_tag_range(addr, size, tag) ((void *)(addr)) #endif -#define hw_enable_tagging() arch_enable_tagging() +#define hw_enable_tagging_sync() arch_enable_tagging_sync() +#define hw_enable_tagging_async() arch_enable_tagging_async() #define hw_init_tags(max_tag) arch_init_tags(max_tag) #define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state) #define hw_get_random_tag() arch_get_random_tag() @@ -303,7 +308,8 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #else /* CONFIG_KASAN_HW_TAGS */ -#define hw_enable_tagging() +#define hw_enable_tagging_sync() +#define hw_enable_tagging_async() #define hw_set_tagging_report_once(state) #endif /* CONFIG_KASAN_HW_TAGS */ @@ -311,12 +317,12 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) void kasan_set_tagging_report_once(bool state); -void kasan_enable_tagging(void); +void kasan_enable_tagging_sync(void); #else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ static inline void kasan_set_tagging_report_once(bool state) { } -static inline void kasan_enable_tagging(void) { } +static inline void kasan_enable_tagging_sync(void) { } #endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ -- cgit v1.2.3 From e80a76aa1a91018d919d2210366943f9bf17009e Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 15 Mar 2021 13:20:19 +0000 Subject: kasan, arm64: tests supports for HW_TAGS async mode This change adds KASAN-KUnit tests support for the async HW_TAGS mode. In async mode, tag fault aren't being generated synchronously when a bad access happens, but are instead explicitly checked for by the kernel. As each KASAN-KUnit test expect a fault to happen before the test is over, check for faults as a part of the test handler. Acked-by: Catalin Marinas Acked-by: Andrey Konovalov Tested-by: Andrey Konovalov Signed-off-by: Andrey Konovalov Signed-off-by: Vincenzo Frascino Link: https://lore.kernel.org/r/20210315132019.33202-10-vincenzo.frascino@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/memory.h | 1 + lib/test_kasan.c | 17 +++++++++++------ mm/kasan/hw_tags.c | 6 ++++++ mm/kasan/kasan.h | 6 ++++++ mm/kasan/report.c | 5 +++++ 5 files changed, 29 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 8b0beaedbe1f..b943879c1c24 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -246,6 +246,7 @@ static inline const void *__tag_set(const void *addr, u8 tag) #define arch_enable_tagging_sync() mte_enable_kernel_sync() #define arch_enable_tagging_async() mte_enable_kernel_async() #define arch_set_tagging_report_once(state) mte_set_report_once(state) +#define arch_force_async_tag_fault() mte_check_tfsr_exit() #define arch_init_tags(max_tag) mte_init_tags(max_tag) #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 479c31a5dc21..785e724ce0d8 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -69,10 +69,10 @@ static void kasan_test_exit(struct kunit *test) * resource named "kasan_data". Do not use this name for KUnit resources * outside of KASAN tests. * - * For hardware tag-based KASAN, when a tag fault happens, tag checking is - * normally auto-disabled. When this happens, this test handler reenables - * tag checking. As tag checking can be only disabled or enabled per CPU, this - * handler disables migration (preemption). + * For hardware tag-based KASAN in sync mode, when a tag fault happens, tag + * checking is auto-disabled. When this happens, this test handler reenables + * tag checking. As tag checking can be only disabled or enabled per CPU, + * this handler disables migration (preemption). * * Since the compiler doesn't see that the expression can change the fail_data * fields, it can reorder or optimize away the accesses to those fields. @@ -80,7 +80,8 @@ static void kasan_test_exit(struct kunit *test) * expression to prevent that. */ #define KUNIT_EXPECT_KASAN_FAIL(test, expression) do { \ - if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) \ + if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \ + !kasan_async_mode_enabled()) \ migrate_disable(); \ WRITE_ONCE(fail_data.report_expected, true); \ WRITE_ONCE(fail_data.report_found, false); \ @@ -92,10 +93,14 @@ static void kasan_test_exit(struct kunit *test) barrier(); \ expression; \ barrier(); \ + if (kasan_async_mode_enabled()) \ + kasan_force_async_fault(); \ + barrier(); \ KUNIT_EXPECT_EQ(test, \ READ_ONCE(fail_data.report_expected), \ READ_ONCE(fail_data.report_found)); \ - if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) { \ + if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \ + !kasan_async_mode_enabled()) { \ if (READ_ONCE(fail_data.report_found)) \ kasan_enable_tagging_sync(); \ migrate_enable(); \ diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 1df4ce803861..4004388b4e4b 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -252,4 +252,10 @@ void kasan_enable_tagging_sync(void) } EXPORT_SYMBOL_GPL(kasan_enable_tagging_sync); +void kasan_force_async_fault(void) +{ + hw_force_async_tag_fault(); +} +EXPORT_SYMBOL_GPL(kasan_force_async_fault); + #endif diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 02e9656b857f..2d29069ae977 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -304,6 +304,9 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifndef arch_set_tagging_report_once #define arch_set_tagging_report_once(state) #endif +#ifndef arch_force_async_tag_fault +#define arch_force_async_tag_fault() +#endif #ifndef arch_get_random_tag #define arch_get_random_tag() (0xFF) #endif @@ -318,6 +321,7 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_enable_tagging_async() arch_enable_tagging_async() #define hw_init_tags(max_tag) arch_init_tags(max_tag) #define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state) +#define hw_force_async_tag_fault() arch_force_async_tag_fault() #define hw_get_random_tag() arch_get_random_tag() #define hw_get_mem_tag(addr) arch_get_mem_tag(addr) #define hw_set_mem_tag_range(addr, size, tag) arch_set_mem_tag_range((addr), (size), (tag)) @@ -334,11 +338,13 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) void kasan_set_tagging_report_once(bool state); void kasan_enable_tagging_sync(void); +void kasan_force_async_fault(void); #else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ static inline void kasan_set_tagging_report_once(bool state) { } static inline void kasan_enable_tagging_sync(void) { } +static inline void kasan_force_async_fault(void) { } #endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 8b0843a2cdd7..14bd51ea2348 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -366,6 +366,11 @@ void kasan_report_async(void) { unsigned long flags; +#if IS_ENABLED(CONFIG_KUNIT) + if (current->kunit_test) + kasan_update_kunit_status(current->kunit_test); +#endif /* IS_ENABLED(CONFIG_KUNIT) */ + start_report(&flags); pr_err("BUG: KASAN: invalid-access\n"); pr_err("Asynchronous mode enabled: no access details available\n"); -- cgit v1.2.3 From 58efe9f696cf908f40d6672aeca81cb2ad2bc762 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 31 Mar 2021 16:48:44 +0000 Subject: lib/vdso: Mark do_hres_timens() and do_coarse_timens() __always_inline() In the same spirit as commit c966533f8c6c ("lib/vdso: Mark do_hres() and do_coarse() as __always_inline"), mark do_hres_timens() and do_coarse_timens() __always_inline. The measurement below in on a non timens process, ie on the fastest path. On powerpc32, without the patch: clock-gettime-monotonic-raw: vdso: 1155 nsec/call clock-gettime-monotonic-coarse: vdso: 813 nsec/call clock-gettime-monotonic: vdso: 1076 nsec/call With the patch: clock-gettime-monotonic-raw: vdso: 1100 nsec/call clock-gettime-monotonic-coarse: vdso: 667 nsec/call clock-gettime-monotonic: vdso: 1025 nsec/call Signed-off-by: Christophe Leroy Reviewed-by: Thomas Gleixner Reviewed-by: Vincenzo Frascino Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/90dcf45ebadfd5a07f24241551c62f619d1cb930.1617209142.git.christophe.leroy@csgroup.eu --- lib/vdso/gettimeofday.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 2919f1698140..c6f6dee08746 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -46,8 +46,8 @@ static inline bool vdso_cycles_ok(u64 cycles) #endif #ifdef CONFIG_TIME_NS -static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, + struct __kernel_timespec *ts) { const struct vdso_data *vd = __arch_get_timens_vdso_data(); const struct timens_offset *offs = &vdns->offset[clk]; @@ -97,8 +97,8 @@ static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) return NULL; } -static int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, + struct __kernel_timespec *ts) { return -EINVAL; } @@ -159,8 +159,8 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, } #ifdef CONFIG_TIME_NS -static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, + struct __kernel_timespec *ts) { const struct vdso_data *vd = __arch_get_timens_vdso_data(); const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; @@ -188,8 +188,8 @@ static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, return 0; } #else -static int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, + struct __kernel_timespec *ts) { return -1; } -- cgit v1.2.3 From 808094fcbf4196be0feb17afbbdc182ec95c8cec Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 31 Mar 2021 16:48:45 +0000 Subject: lib/vdso: Add vdso_data pointer as input to __arch_get_timens_vdso_data() For the same reason as commit e876f0b69dc9 ("lib/vdso: Allow architectures to provide the vdso data pointer"), powerpc wants to avoid calculation of relative position to code. As the timens_vdso_data is next page to vdso_data, provide vdso_data pointer to __arch_get_timens_vdso_data() in order to ease the calculation on powerpc in following patches. Signed-off-by: Christophe Leroy Reviewed-by: Thomas Gleixner Reviewed-by: Vincenzo Frascino Acked-by: Andrei Vagin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/539c4204b1baa77c55f758904a1ea239abbc7a5c.1617209142.git.christophe.leroy@csgroup.eu --- arch/arm64/include/asm/vdso/compat_gettimeofday.h | 3 ++- arch/arm64/include/asm/vdso/gettimeofday.h | 2 +- arch/s390/include/asm/vdso/gettimeofday.h | 3 ++- arch/x86/include/asm/vdso/gettimeofday.h | 3 ++- lib/vdso/gettimeofday.c | 15 +++++++++------ 5 files changed, 16 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index 7508b0ac1d21..ecb6fd4c3c64 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -155,7 +155,8 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) } #ifdef CONFIG_TIME_NS -static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { const struct vdso_data *ret; diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 631ab1281633..de86230a9436 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -100,7 +100,7 @@ const struct vdso_data *__arch_get_vdso_data(void) #ifdef CONFIG_TIME_NS static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(void) +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { return _timens_data; } diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h index ed89ef742530..383c53c3dddd 100644 --- a/arch/s390/include/asm/vdso/gettimeofday.h +++ b/arch/s390/include/asm/vdso/gettimeofday.h @@ -68,7 +68,8 @@ long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts) } #ifdef CONFIG_TIME_NS -static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { return _timens_data; } diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index df01d7349d79..1936f21ed8cd 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -58,7 +58,8 @@ extern struct ms_hyperv_tsc_page hvclock_page #endif #ifdef CONFIG_TIME_NS -static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { return __timens_vdso_data; } diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index c6f6dee08746..ce2f69552003 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -49,13 +49,15 @@ static inline bool vdso_cycles_ok(u64 cycles) static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_data *vd = __arch_get_timens_vdso_data(); + const struct vdso_data *vd; const struct timens_offset *offs = &vdns->offset[clk]; const struct vdso_timestamp *vdso_ts; u64 cycles, last, ns; u32 seq; s64 sec; + vd = vdns - (clk == CLOCK_MONOTONIC_RAW ? CS_RAW : CS_HRES_COARSE); + vd = __arch_get_timens_vdso_data(vd); if (clk != CLOCK_MONOTONIC_RAW) vd = &vd[CS_HRES_COARSE]; else @@ -92,7 +94,8 @@ static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_ return 0; } #else -static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { return NULL; } @@ -162,7 +165,7 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_data *vd = __arch_get_timens_vdso_data(); + const struct vdso_data *vd = __arch_get_timens_vdso_data(vdns); const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; const struct timens_offset *offs = &vdns->offset[clk]; u64 nsec; @@ -310,7 +313,7 @@ __cvdso_gettimeofday_data(const struct vdso_data *vd, if (unlikely(tz != NULL)) { if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(); + vd = __arch_get_timens_vdso_data(vd); tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest; tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime; @@ -333,7 +336,7 @@ __cvdso_time_data(const struct vdso_data *vd, __kernel_old_time_t *time) if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(); + vd = __arch_get_timens_vdso_data(vd); t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec); @@ -363,7 +366,7 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock, if (IS_ENABLED(CONFIG_TIME_NS) && vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(); + vd = __arch_get_timens_vdso_data(vd); /* * Convert the clockid to a bitmask and use it to check which -- cgit v1.2.3 From b07067627cd5f1f6dc60c224b47c728f7f4b7b45 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 27 Jan 2021 11:06:13 -0800 Subject: lib: Add ASN.1 encoder We have a need in the TPM2 trusted keys to return the ASN.1 form of the TPM key blob so it can be operated on by tools outside of the kernel. The specific tools are the openssl_tpm2_engine, openconnect and the Intel tpm2-tss-engine. To do that, we have to be able to read and write the same binary key format the tools use. The current ASN.1 decoder does fine for reading, but we need pieces of an ASN.1 encoder to write the key blob in binary compatible form. For backwards compatibility, the trusted key reader code will still accept the two TPM2B quantities that it uses today, but the writer will only output the ASN.1 form. The current implementation only encodes the ASN.1 bits we actually need. Signed-off-by: James Bottomley Reviewed-by: David Howells Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/asn1_encoder.h | 32 +++ lib/Kconfig | 3 + lib/Makefile | 1 + lib/asn1_encoder.c | 454 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 490 insertions(+) create mode 100644 include/linux/asn1_encoder.h create mode 100644 lib/asn1_encoder.c (limited to 'lib') diff --git a/include/linux/asn1_encoder.h b/include/linux/asn1_encoder.h new file mode 100644 index 000000000000..08cd0c2ad34f --- /dev/null +++ b/include/linux/asn1_encoder.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _LINUX_ASN1_ENCODER_H +#define _LINUX_ASN1_ENCODER_H + +#include +#include +#include +#include + +#define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32)) +unsigned char * +asn1_encode_integer(unsigned char *data, const unsigned char *end_data, + s64 integer); +unsigned char * +asn1_encode_oid(unsigned char *data, const unsigned char *end_data, + u32 oid[], int oid_len); +unsigned char * +asn1_encode_tag(unsigned char *data, const unsigned char *end_data, + u32 tag, const unsigned char *string, int len); +unsigned char * +asn1_encode_octet_string(unsigned char *data, + const unsigned char *end_data, + const unsigned char *string, u32 len); +unsigned char * +asn1_encode_sequence(unsigned char *data, const unsigned char *end_data, + const unsigned char *seq, int len); +unsigned char * +asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, + bool val); + +#endif diff --git a/lib/Kconfig b/lib/Kconfig index a38cc61256f1..ac3b30697b2b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -701,3 +701,6 @@ config GENERIC_LIB_DEVMEM_IS_ALLOWED config PLDMFW bool default n + +config ASN1_ENCODER + tristate diff --git a/lib/Makefile b/lib/Makefile index b5307d3eec1a..e11cfc18b6c0 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -280,6 +280,7 @@ obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o obj-$(CONFIG_PERCPU_TEST) += percpu_test.o obj-$(CONFIG_ASN1) += asn1_decoder.o +obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o obj-$(CONFIG_FONT_SUPPORT) += fonts/ diff --git a/lib/asn1_encoder.c b/lib/asn1_encoder.c new file mode 100644 index 000000000000..41e71aae3ef6 --- /dev/null +++ b/lib/asn1_encoder.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Simple encoder primitives for ASN.1 BER/DER/CER + * + * Copyright (C) 2019 James.Bottomley@HansenPartnership.com + */ + +#include +#include +#include +#include + +/** + * asn1_encode_integer() - encode positive integer to ASN.1 + * @data: pointer to the pointer to the data + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @integer: integer to be encoded + * + * This is a simplified encoder: it only currently does + * positive integers, but it should be simple enough to add the + * negative case if a use comes along. + */ +unsigned char * +asn1_encode_integer(unsigned char *data, const unsigned char *end_data, + s64 integer) +{ + int data_len = end_data - data; + unsigned char *d = &data[2]; + bool found = false; + int i; + + if (WARN(integer < 0, + "BUG: integer encode only supports positive integers")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + /* need at least 3 bytes for tag, length and integer encoding */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + /* remaining length where at d (the start of the integer encoding) */ + data_len -= 2; + + data[0] = _tag(UNIV, PRIM, INT); + if (integer == 0) { + *d++ = 0; + goto out; + } + + for (i = sizeof(integer); i > 0 ; i--) { + int byte = integer >> (8 * (i - 1)); + + if (!found && byte == 0) + continue; + + /* + * for a positive number the first byte must have bit + * 7 clear in two's complement (otherwise it's a + * negative number) so prepend a leading zero if + * that's not the case + */ + if (!found && (byte & 0x80)) { + /* + * no check needed here, we already know we + * have len >= 1 + */ + *d++ = 0; + data_len--; + } + + found = true; + if (data_len == 0) + return ERR_PTR(-EINVAL); + + *d++ = byte; + data_len--; + } + + out: + data[1] = d - data - 2; + + return d; +} +EXPORT_SYMBOL_GPL(asn1_encode_integer); + +/* calculate the base 128 digit values setting the top bit of the first octet */ +static int asn1_encode_oid_digit(unsigned char **_data, int *data_len, u32 oid) +{ + unsigned char *data = *_data; + int start = 7 + 7 + 7 + 7; + int ret = 0; + + if (*data_len < 1) + return -EINVAL; + + /* quick case */ + if (oid == 0) { + *data++ = 0x80; + (*data_len)--; + goto out; + } + + while (oid >> start == 0) + start -= 7; + + while (start > 0 && *data_len > 0) { + u8 byte; + + byte = oid >> start; + oid = oid - (byte << start); + start -= 7; + byte |= 0x80; + *data++ = byte; + (*data_len)--; + } + + if (*data_len > 0) { + *data++ = oid; + (*data_len)--; + } else { + ret = -EINVAL; + } + + out: + *_data = data; + return ret; +} + +/** + * asn1_encode_oid() - encode an oid to ASN.1 + * @data: position to begin encoding at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @oid: array of oids + * @oid_len: length of oid array + * + * this encodes an OID up to ASN.1 when presented as an array of OID values + */ +unsigned char * +asn1_encode_oid(unsigned char *data, const unsigned char *end_data, + u32 oid[], int oid_len) +{ + int data_len = end_data - data; + unsigned char *d = data + 2; + int i, ret; + + if (WARN(oid_len < 2, "OID must have at least two elements")) + return ERR_PTR(-EINVAL); + + if (WARN(oid_len > 32, "OID is too large")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + + /* need at least 3 bytes for tag, length and OID encoding */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + data[0] = _tag(UNIV, PRIM, OID); + *d++ = oid[0] * 40 + oid[1]; + + data_len -= 3; + + ret = 0; + + for (i = 2; i < oid_len; i++) { + ret = asn1_encode_oid_digit(&d, &data_len, oid[i]); + if (ret < 0) + return ERR_PTR(ret); + } + + data[1] = d - data - 2; + + return d; +} +EXPORT_SYMBOL_GPL(asn1_encode_oid); + +/** + * asn1_encode_length() - encode a length to follow an ASN.1 tag + * @data: pointer to encode at + * @data_len: pointer to remaning length (adjusted by routine) + * @len: length to encode + * + * This routine can encode lengths up to 65535 using the ASN.1 rules. + * It will accept a negative length and place a zero length tag + * instead (to keep the ASN.1 valid). This convention allows other + * encoder primitives to accept negative lengths as singalling the + * sequence will be re-encoded when the length is known. + */ +static int asn1_encode_length(unsigned char **data, int *data_len, int len) +{ + if (*data_len < 1) + return -EINVAL; + + if (len < 0) { + *((*data)++) = 0; + (*data_len)--; + return 0; + } + + if (len <= 0x7f) { + *((*data)++) = len; + (*data_len)--; + return 0; + } + + if (*data_len < 2) + return -EINVAL; + + if (len <= 0xff) { + *((*data)++) = 0x81; + *((*data)++) = len & 0xff; + *data_len -= 2; + return 0; + } + + if (*data_len < 3) + return -EINVAL; + + if (len <= 0xffff) { + *((*data)++) = 0x82; + *((*data)++) = (len >> 8) & 0xff; + *((*data)++) = len & 0xff; + *data_len -= 3; + return 0; + } + + if (WARN(len > 0xffffff, "ASN.1 length can't be > 0xffffff")) + return -EINVAL; + + if (*data_len < 4) + return -EINVAL; + *((*data)++) = 0x83; + *((*data)++) = (len >> 16) & 0xff; + *((*data)++) = (len >> 8) & 0xff; + *((*data)++) = len & 0xff; + *data_len -= 4; + + return 0; +} + +/** + * asn1_encode_tag() - add a tag for optional or explicit value + * @data: pointer to place tag at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @tag: tag to be placed + * @string: the data to be tagged + * @len: the length of the data to be tagged + * + * Note this currently only handles short form tags < 31. + * + * Standard usage is to pass in a @tag, @string and @length and the + * @string will be ASN.1 encoded with @tag and placed into @data. If + * the encoding would put data past @end_data then an error is + * returned, otherwise a pointer to a position one beyond the encoding + * is returned. + * + * To encode in place pass a NULL @string and -1 for @len and the + * maximum allowable beginning and end of the data; all this will do + * is add the current maximum length and update the data pointer to + * the place where the tag contents should be placed is returned. The + * data should be copied in by the calling routine which should then + * repeat the prior statement but now with the known length. In order + * to avoid having to keep both before and after pointers, the repeat + * expects to be called with @data pointing to where the first encode + * returned it and still NULL for @string but the real length in @len. + */ +unsigned char * +asn1_encode_tag(unsigned char *data, const unsigned char *end_data, + u32 tag, const unsigned char *string, int len) +{ + int data_len = end_data - data; + int ret; + + if (WARN(tag > 30, "ASN.1 tag can't be > 30")) + return ERR_PTR(-EINVAL); + + if (!string && WARN(len > 127, + "BUG: recode tag is too big (>127)")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + if (!string && len > 0) { + /* + * we're recoding, so move back to the start of the + * tag and install a dummy length because the real + * data_len should be NULL + */ + data -= 2; + data_len = 2; + } + + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tagn(CONT, CONS, tag); + data_len--; + ret = asn1_encode_length(&data, &data_len, len); + if (ret < 0) + return ERR_PTR(ret); + + if (!string) + return data; + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, string, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_tag); + +/** + * asn1_encode_octet_string() - encode an ASN.1 OCTET STRING + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @string: string to be encoded + * @len: length of string + * + * Note ASN.1 octet strings may contain zeros, so the length is obligatory. + */ +unsigned char * +asn1_encode_octet_string(unsigned char *data, + const unsigned char *end_data, + const unsigned char *string, u32 len) +{ + int data_len = end_data - data; + int ret; + + if (IS_ERR(data)) + return data; + + /* need minimum of 2 bytes for tag and length of zero length string */ + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, PRIM, OTS); + data_len--; + + ret = asn1_encode_length(&data, &data_len, len); + if (ret) + return ERR_PTR(ret); + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, string, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_octet_string); + +/** + * asn1_encode_sequence() - wrap a byte stream in an ASN.1 SEQUENCE + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @seq: data to be encoded as a sequence + * @len: length of the data to be encoded as a sequence + * + * Fill in a sequence. To encode in place, pass NULL for @seq and -1 + * for @len; then call again once the length is known (still with NULL + * for @seq). In order to avoid having to keep both before and after + * pointers, the repeat expects to be called with @data pointing to + * where the first encode placed it. + */ +unsigned char * +asn1_encode_sequence(unsigned char *data, const unsigned char *end_data, + const unsigned char *seq, int len) +{ + int data_len = end_data - data; + int ret; + + if (!seq && WARN(len > 127, + "BUG: recode sequence is too big (>127)")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + if (!seq && len >= 0) { + /* + * we're recoding, so move back to the start of the + * sequence and install a dummy length because the + * real length should be NULL + */ + data -= 2; + data_len = 2; + } + + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, CONS, SEQ); + data_len--; + + ret = asn1_encode_length(&data, &data_len, len); + if (ret) + return ERR_PTR(ret); + + if (!seq) + return data; + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, seq, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_sequence); + +/** + * asn1_encode_boolean() - encode a boolean value to ASN.1 + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @val: the boolean true/false value + */ +unsigned char * +asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, + bool val) +{ + int data_len = end_data - data; + + if (IS_ERR(data)) + return data; + + /* booleans are 3 bytes: tag, length == 1 and value == 0 or 1 */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, PRIM, BOOL); + data_len--; + + asn1_encode_length(&data, &data_len, 1); + + if (val) + *(data++) = 1; + else + *(data++) = 0; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_boolean); + +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From d86ba831656611872e4939b895503ddac63d8196 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Mar 2021 19:48:34 +0100 Subject: sched: Don't make LATENCYTOP select SCHED_DEBUG SCHED_DEBUG is not in fact required for LATENCYTOP, don't select it. Suggested-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20210412102001.224578981@infradead.org --- lib/Kconfig.debug | 1 - 1 file changed, 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..5f983768d876 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1670,7 +1670,6 @@ config LATENCYTOP select KALLSYMS_ALL select STACKTRACE select SCHEDSTATS - select SCHED_DEBUG help Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. -- cgit v1.2.3 From 02c587733c8161355a43e6e110c2e29bd0acff72 Mon Sep 17 00:00:00 2001 From: Walter Wu Date: Fri, 16 Apr 2021 15:46:00 -0700 Subject: kasan: remove redundant config option CONFIG_KASAN_STACK and CONFIG_KASAN_STACK_ENABLE both enable KASAN stack instrumentation, but we should only need one config, so that we remove CONFIG_KASAN_STACK_ENABLE and make CONFIG_KASAN_STACK workable. see [1]. When enable KASAN stack instrumentation, then for gcc we could do no prompt and default value y, and for clang prompt and default value n. This patch fixes the following compilation warning: include/linux/kasan.h:333:30: warning: 'CONFIG_KASAN_STACK' is not defined, evaluates to 0 [-Wundef] [akpm@linux-foundation.org: fix merge snafu] Link: https://bugzilla.kernel.org/show_bug.cgi?id=210221 [1] Link: https://lkml.kernel.org/r/20210226012531.29231-1-walter-zh.wu@mediatek.com Fixes: d9b571c885a8 ("kasan: fix KASAN_STACK dependency for HW_TAGS") Signed-off-by: Walter Wu Suggested-by: Dmitry Vyukov Reviewed-by: Nathan Chancellor Acked-by: Arnd Bergmann Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Alexander Potapenko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/sleep.S | 2 +- arch/x86/kernel/acpi/wakeup_64.S | 2 +- include/linux/kasan.h | 2 +- lib/Kconfig.kasan | 9 ++------- mm/kasan/common.c | 2 +- mm/kasan/kasan.h | 2 +- mm/kasan/report_generic.c | 2 +- scripts/Makefile.kasan | 10 ++++++++-- security/Kconfig.hardening | 4 ++-- 9 files changed, 18 insertions(+), 17 deletions(-) (limited to 'lib') diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 5bfd9b87f85d..4ea9392f86e0 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -134,7 +134,7 @@ SYM_FUNC_START(_cpu_resume) */ bl cpu_do_resume -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) mov x0, sp bl kasan_unpoison_task_stack_below #endif diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 56b6865afb2a..d5d8a352eafa 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -115,7 +115,7 @@ SYM_FUNC_START(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) /* * The suspend path may have poisoned some areas deeper in the stack, * which we now need to unpoison. diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b91732bd05d7..14f72ec96492 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -330,7 +330,7 @@ static inline bool kasan_check_byte(const void *address) #endif /* CONFIG_KASAN */ -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index fba9909e31b7..cffc2ebbf185 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -138,9 +138,10 @@ config KASAN_INLINE endchoice -config KASAN_STACK_ENABLE +config KASAN_STACK bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST depends on KASAN_GENERIC || KASAN_SW_TAGS + default y if CC_IS_GCC help The LLVM stack address sanitizer has a know problem that causes excessive stack usage in a lot of functions, see @@ -154,12 +155,6 @@ config KASAN_STACK_ENABLE CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe to use and enabled by default. -config KASAN_STACK - int - depends on KASAN_GENERIC || KASAN_SW_TAGS - default 1 if KASAN_STACK_ENABLE || CC_IS_GCC - default 0 - config KASAN_SW_TAGS_IDENTIFY bool "Enable memory corruption identification" depends on KASAN_SW_TAGS diff --git a/mm/kasan/common.c b/mm/kasan/common.c index b5e08d4cefec..7b53291dafa1 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -63,7 +63,7 @@ void __kasan_unpoison_range(const void *address, size_t size) kasan_unpoison(address, size); } -#if CONFIG_KASAN_STACK +#ifdef CONFIG_KASAN_STACK /* Unpoison the entire stack for a task. */ void kasan_unpoison_task_stack(struct task_struct *task) { diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8c55634d6edd..3436c6bf7c0c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -231,7 +231,7 @@ void *kasan_find_first_bad_addr(void *addr, size_t size); const char *kasan_get_bug_type(struct kasan_access_info *info); void kasan_metadata_fetch_row(char *buffer, void *row); -#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN_GENERIC) && defined(CONFIG_KASAN_STACK) void kasan_print_address_stack_frame(const void *addr); #else static inline void kasan_print_address_stack_frame(const void *addr) { } diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c index 41f374585144..de732bc341c5 100644 --- a/mm/kasan/report_generic.c +++ b/mm/kasan/report_generic.c @@ -128,7 +128,7 @@ void kasan_metadata_fetch_row(char *buffer, void *row) memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW); } -#if CONFIG_KASAN_STACK +#ifdef CONFIG_KASAN_STACK static bool __must_check tokenize_frame_descr(const char **frame_descr, char *token, size_t max_tok_len, unsigned long *value) diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 127012f45166..3d791908ed36 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -4,6 +4,12 @@ KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET) cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1))) +ifdef CONFIG_KASAN_STACK + stack_enable := 1 +else + stack_enable := 0 +endif + ifdef CONFIG_KASAN_GENERIC ifdef CONFIG_KASAN_INLINE @@ -27,7 +33,7 @@ else CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \ $(call cc-param,asan-globals=1) \ $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ - $(call cc-param,asan-stack=$(CONFIG_KASAN_STACK)) \ + $(call cc-param,asan-stack=$(stack_enable)) \ $(call cc-param,asan-instrument-allocas=1) endif @@ -42,7 +48,7 @@ else endif CFLAGS_KASAN := -fsanitize=kernel-hwaddress \ - $(call cc-param,hwasan-instrument-stack=$(CONFIG_KASAN_STACK)) \ + $(call cc-param,hwasan-instrument-stack=$(stack_enable)) \ $(call cc-param,hwasan-use-short-granules=0) \ $(instrumentation_flags) diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 269967c4fc1b..a56c36470cb1 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -64,7 +64,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF bool "zero-init structs passed by reference (strong)" depends on GCC_PLUGINS - depends on !(KASAN && KASAN_STACK=1) + depends on !(KASAN && KASAN_STACK) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any structures on the stack that may @@ -82,7 +82,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL bool "zero-init anything passed by reference (very strong)" depends on GCC_PLUGINS - depends on !(KASAN && KASAN_STACK=1) + depends on !(KASAN && KASAN_STACK) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any stack variables that may be passed -- cgit v1.2.3 From c95c2d328cd051484bea161e66dfa715c02a7d7e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 16 Apr 2021 15:46:26 -0700 Subject: lib: remove "expecting prototype" kernel-doc warnings Fix various kernel-doc warnings in lib/ due to missing or erroneous function names. Add kernel-doc for some function parameters that was missing. Use kernel-doc "Return:" notation in earlycpio.c. Quietens the following warnings: lib/earlycpio.c:61: warning: expecting prototype for cpio_data find_cpio_data(). Prototype was for find_cpio_data() instead lib/lru_cache.c:640: warning: expecting prototype for lc_dump(). Prototype was for lc_seq_dump_details() instead lru_cache.c:90: warning: Function parameter or member 'cache' not described in 'lc_create' lib/parman.c:368: warning: expecting prototype for parman_item_del(). Prototype was for parman_item_remove() instead parman.c:309: warning: Excess function parameter 'prority' description in 'parman_prio_init' lib/radix-tree.c:703: warning: expecting prototype for __radix_tree_insert(). Prototype was for radix_tree_insert() instead radix-tree.c:180: warning: Excess function parameter 'addr' description in 'radix_tree_find_next_bit' radix-tree.c:180: warning: Excess function parameter 'size' description in 'radix_tree_find_next_bit' radix-tree.c:931: warning: Function parameter or member 'iter' not described in 'radix_tree_iter_replace' Link: https://lkml.kernel.org/r/20210411221756.15461-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Philipp Reisner Cc: Lars Ellenberg Cc: Jiri Pirko Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/earlycpio.c | 4 ++-- lib/lru_cache.c | 3 ++- lib/parman.c | 4 ++-- lib/radix-tree.c | 11 ++++++----- 4 files changed, 12 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/earlycpio.c b/lib/earlycpio.c index e83628882001..7921193f0424 100644 --- a/lib/earlycpio.c +++ b/lib/earlycpio.c @@ -40,7 +40,7 @@ enum cpio_fields { }; /** - * cpio_data find_cpio_data - Search for files in an uncompressed cpio + * find_cpio_data - Search for files in an uncompressed cpio * @path: The directory to search for, including a slash at the end * @data: Pointer to the cpio archive or a header inside * @len: Remaining length of the cpio based on data pointer @@ -49,7 +49,7 @@ enum cpio_fields { * matching file itself. It can be used to iterate through the cpio * to find all files inside of a directory path. * - * @return: struct cpio_data containing the address, length and + * Return: &struct cpio_data containing the address, length and * filename (with the directory path cut off) of the found file. * If you search for a filename and not for files in a directory, * pass the absolute path of the filename in the cpio and make sure diff --git a/lib/lru_cache.c b/lib/lru_cache.c index c69ee53d8dde..52313acbfa62 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -76,6 +76,7 @@ int lc_try_lock(struct lru_cache *lc) /** * lc_create - prepares to track objects in an active set * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details + * @cache: cache root pointer * @max_pending_changes: maximum changes to accumulate until a transaction is required * @e_count: number of elements allowed to be active simultaneously * @e_size: size of the tracked objects @@ -627,7 +628,7 @@ void lc_set(struct lru_cache *lc, unsigned int enr, int index) } /** - * lc_dump - Dump a complete LRU cache to seq in textual form. + * lc_seq_dump_details - Dump a complete LRU cache to seq in textual form. * @lc: the lru cache to operate on * @seq: the &struct seq_file pointer to seq_printf into * @utext: user supplied additional "heading" or other info diff --git a/lib/parman.c b/lib/parman.c index a11f2f667639..3f8f8d422e62 100644 --- a/lib/parman.c +++ b/lib/parman.c @@ -297,7 +297,7 @@ EXPORT_SYMBOL(parman_destroy); * parman_prio_init - initializes a parman priority chunk * @parman: parman instance * @prio: parman prio structure to be initialized - * @prority: desired priority of the chunk + * @priority: desired priority of the chunk * * Note: all locking must be provided by the caller. * @@ -356,7 +356,7 @@ int parman_item_add(struct parman *parman, struct parman_prio *prio, EXPORT_SYMBOL(parman_item_add); /** - * parman_item_del - deletes parman item + * parman_item_remove - deletes parman item * @parman: parman instance * @prio: parman prio instance to delete the item from * @item: parman item instance diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3a4da11b804d..b3afafe46fff 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -166,9 +166,9 @@ static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) /** * radix_tree_find_next_bit - find the next set bit in a memory region * - * @addr: The address to base the search on - * @size: The bitmap size in bits - * @offset: The bitnumber to start searching at + * @node: where to begin the search + * @tag: the tag index + * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. @@ -461,7 +461,7 @@ out: /** * radix_tree_shrink - shrink radix tree to minimum height - * @root radix tree root + * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { @@ -691,7 +691,7 @@ static inline int insert_entries(struct radix_tree_node *node, } /** - * __radix_tree_insert - insert into a radix tree + * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert @@ -919,6 +919,7 @@ EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root + * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * -- cgit v1.2.3 From 5086ea4b0f58ba72c19553c4a657d7b2c0d8efc2 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 20 Apr 2021 04:50:28 +0200 Subject: lib/math: Add a `do_div' test module Implement a module for correctness and performance evaluation for the `do_div' function, often handled in an optimised manner by platform code. Use a somewhat randomly generated set of inputs that is supposed to be representative, using the same set of divisors twice, expressed as a constant and as a variable each, so as to verify the implementation for both cases should they be handled by different code execution paths. Reference results were produced with GNU bc. At the conclusion output the total execution time elapsed. Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer --- lib/Kconfig.debug | 10 ++ lib/math/Makefile | 2 + lib/math/test_div64.c | 249 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 261 insertions(+) create mode 100644 lib/math/test_div64.c (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..b6e7f50d984f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2027,6 +2027,16 @@ config TEST_SORT If unsure, say N. +config TEST_DIV64 + tristate "64bit/32bit division and modulo test" + depends on DEBUG_KERNEL || m + help + Enable this to turn on 'do_div()' function test. This test is + executed only once during system boot (so affects only boot time), + or at module load time. + + If unsure, say N. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL diff --git a/lib/math/Makefile b/lib/math/Makefile index be6909e943bd..7456edb864fc 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -4,3 +4,5 @@ obj-y += div64.o gcd.o lcm.o int_pow.o int_sqrt.o reciprocal_div.o obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o + +obj-$(CONFIG_TEST_DIV64) += test_div64.o diff --git a/lib/math/test_div64.c b/lib/math/test_div64.c new file mode 100644 index 000000000000..eca8e8c6afe0 --- /dev/null +++ b/lib/math/test_div64.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Maciej W. Rozycki + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +#include + +#define TEST_DIV64_N_ITER 1024 + +static const u64 test_div64_dividents[] = { + 0x00000000ab275080, + 0x0000000fe73c1959, + 0x000000e54c0a74b1, + 0x00000d4398ff1ef9, + 0x0000a18c2ee1c097, + 0x00079fb80b072e4a, + 0x0072db27380dd689, + 0x0842f488162e2284, + 0xf66745411d8ab063, +}; +#define SIZE_DIV64_DIVIDENTS ARRAY_SIZE(test_div64_dividents) + +#define TEST_DIV64_DIVISOR_0 0x00000009 +#define TEST_DIV64_DIVISOR_1 0x0000007c +#define TEST_DIV64_DIVISOR_2 0x00000204 +#define TEST_DIV64_DIVISOR_3 0x0000cb5b +#define TEST_DIV64_DIVISOR_4 0x00010000 +#define TEST_DIV64_DIVISOR_5 0x0008a880 +#define TEST_DIV64_DIVISOR_6 0x003fd3ae +#define TEST_DIV64_DIVISOR_7 0x0b658fac +#define TEST_DIV64_DIVISOR_8 0xdc08b349 + +static const u32 test_div64_divisors[] = { + TEST_DIV64_DIVISOR_0, + TEST_DIV64_DIVISOR_1, + TEST_DIV64_DIVISOR_2, + TEST_DIV64_DIVISOR_3, + TEST_DIV64_DIVISOR_4, + TEST_DIV64_DIVISOR_5, + TEST_DIV64_DIVISOR_6, + TEST_DIV64_DIVISOR_7, + TEST_DIV64_DIVISOR_8, +}; +#define SIZE_DIV64_DIVISORS ARRAY_SIZE(test_div64_divisors) + +static const struct { + u64 quotient; + u32 remainder; +} test_div64_results[SIZE_DIV64_DIVISORS][SIZE_DIV64_DIVIDENTS] = { + { + { 0x0000000013045e47, 0x00000001 }, + { 0x000000000161596c, 0x00000030 }, + { 0x000000000054e9d4, 0x00000130 }, + { 0x000000000000d776, 0x0000278e }, + { 0x000000000000ab27, 0x00005080 }, + { 0x00000000000013c4, 0x0004ce80 }, + { 0x00000000000002ae, 0x001e143c }, + { 0x000000000000000f, 0x0033e56c }, + { 0x0000000000000000, 0xab275080 }, + }, { + { 0x00000001c45c02d1, 0x00000000 }, + { 0x0000000020d5213c, 0x00000049 }, + { 0x0000000007e3d65f, 0x000001dd }, + { 0x0000000000140531, 0x000065ee }, + { 0x00000000000fe73c, 0x00001959 }, + { 0x000000000001d637, 0x0004e5d9 }, + { 0x0000000000003fc9, 0x000713bb }, + { 0x0000000000000165, 0x029abe7d }, + { 0x0000000000000012, 0x6e9f7e37 }, + }, { + { 0x000000197a3a0cf7, 0x00000002 }, + { 0x00000001d9632e5c, 0x00000021 }, + { 0x0000000071c28039, 0x000001cd }, + { 0x000000000120a844, 0x0000b885 }, + { 0x0000000000e54c0a, 0x000074b1 }, + { 0x00000000001a7bb3, 0x00072331 }, + { 0x00000000000397ad, 0x0002c61b }, + { 0x000000000000141e, 0x06ea2e89 }, + { 0x000000000000010a, 0xab002ad7 }, + }, { + { 0x0000017949e37538, 0x00000001 }, + { 0x0000001b62441f37, 0x00000055 }, + { 0x0000000694a3391d, 0x00000085 }, + { 0x0000000010b2a5d2, 0x0000a753 }, + { 0x000000000d4398ff, 0x00001ef9 }, + { 0x0000000001882ec6, 0x0005cbf9 }, + { 0x000000000035333b, 0x0017abdf }, + { 0x00000000000129f1, 0x0ab4520d }, + { 0x0000000000000f6e, 0x8ac0ce9b }, + }, { + { 0x000011f321a74e49, 0x00000006 }, + { 0x0000014d8481d211, 0x0000005b }, + { 0x0000005025cbd92d, 0x000001e3 }, + { 0x00000000cb5e71e3, 0x000043e6 }, + { 0x00000000a18c2ee1, 0x0000c097 }, + { 0x0000000012a88828, 0x00036c97 }, + { 0x000000000287f16f, 0x002c2a25 }, + { 0x00000000000e2cc7, 0x02d581e3 }, + { 0x000000000000bbf4, 0x1ba08c03 }, + }, { + { 0x0000d8db8f72935d, 0x00000005 }, + { 0x00000fbd5aed7a2e, 0x00000002 }, + { 0x000003c84b6ea64a, 0x00000122 }, + { 0x0000000998fa8829, 0x000044b7 }, + { 0x000000079fb80b07, 0x00002e4a }, + { 0x00000000e16b20fa, 0x0002a14a }, + { 0x000000001e940d22, 0x00353b2e }, + { 0x0000000000ab40ac, 0x06fba6ba }, + { 0x000000000008debd, 0x72d98365 }, + }, { + { 0x000cc3045b8fc281, 0x00000000 }, + { 0x0000ed1f48b5c9fc, 0x00000079 }, + { 0x000038fb9c63406a, 0x000000e1 }, + { 0x000000909705b825, 0x00000a62 }, + { 0x00000072db27380d, 0x0000d689 }, + { 0x0000000d43fce827, 0x00082b09 }, + { 0x00000001ccaba11a, 0x0037e8dd }, + { 0x000000000a13f729, 0x0566dffd }, + { 0x000000000085a14b, 0x23d36726 }, + }, { + { 0x00eafeb9c993592b, 0x00000001 }, + { 0x00110e5befa9a991, 0x00000048 }, + { 0x00041947b4a1d36a, 0x000000dc }, + { 0x00000a6679327311, 0x0000c079 }, + { 0x00000842f488162e, 0x00002284 }, + { 0x000000f4459740fc, 0x00084484 }, + { 0x0000002122c47bf9, 0x002ca446 }, + { 0x00000000b9936290, 0x004979c4 }, + { 0x00000000099ca89d, 0x9db446bf }, + }, { + { 0x1b60cece589da1d2, 0x00000001 }, + { 0x01fcb42be1453f5b, 0x0000004f }, + { 0x007a3f2457df0749, 0x0000013f }, + { 0x0001363130e3ec7b, 0x000017aa }, + { 0x0000f66745411d8a, 0x0000b063 }, + { 0x00001c757dfab350, 0x00048863 }, + { 0x000003dc4979c652, 0x00224ea7 }, + { 0x000000159edc3144, 0x06409ab3 }, + { 0x000000011eadfee3, 0xa99c48a8 }, + }, +}; + +static inline bool test_div64_verify(u64 quotient, u32 remainder, int i, int j) +{ + return (quotient == test_div64_results[i][j].quotient && + remainder == test_div64_results[i][j].remainder); +} + +/* + * This needs to be a macro, because we don't want to rely on the compiler + * to do constant propagation, and `do_div' may take a different path for + * constants, so we do want to verify that as well. + */ +#define test_div64_one(divident, divisor, i, j) ({ \ + bool result = true; \ + u64 quotient; \ + u32 remainder; \ + \ + quotient = divident; \ + remainder = do_div(quotient, divisor); \ + if (!test_div64_verify(quotient, remainder, i, j)) { \ + pr_err("ERROR: %016llx / %08x => %016llx,%08x\n", \ + divident, divisor, quotient, remainder); \ + pr_err("ERROR: expected value=> %016llx,%08x\n", \ + test_div64_results[i][j].quotient, \ + test_div64_results[i][j].remainder); \ + result = false; \ + } \ + result; \ +}) + +/* + * Run calculation for the same divisor value expressed as a constant + * and as a variable, so as to verify the implementation for both cases + * should they be handled by different code execution paths. + */ +static bool __init test_div64(void) +{ + u64 divident; + int i, j; + + for (i = 0; i < SIZE_DIV64_DIVIDENTS; i++) { + divident = test_div64_dividents[i]; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_0, i, 0)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_1, i, 1)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_2, i, 2)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_3, i, 3)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_4, i, 4)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_5, i, 5)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_6, i, 6)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_7, i, 7)) + return false; + if (!test_div64_one(divident, TEST_DIV64_DIVISOR_8, i, 8)) + return false; + for (j = 0; j < SIZE_DIV64_DIVISORS; j++) { + if (!test_div64_one(divident, test_div64_divisors[j], + i, j)) + return false; + } + } + return true; +} + +static int __init test_div64_init(void) +{ + struct timespec64 ts, ts0, ts1; + int i; + + pr_info("Starting 64bit/32bit division and modulo test\n"); + ktime_get_ts64(&ts0); + + for (i = 0; i < TEST_DIV64_N_ITER; i++) + if (!test_div64()) + break; + + ktime_get_ts64(&ts1); + ts = timespec64_sub(ts1, ts0); + pr_info("Completed 64bit/32bit division and modulo test, " + "%llu.%09lus elapsed\n", ts.tv_sec, ts.tv_nsec); + + return 0; +} + +static void __exit test_div64_exit(void) +{ +} + +module_init(test_div64_init); +module_exit(test_div64_exit); + +MODULE_AUTHOR("Maciej W. Rozycki "); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("64bit/32bit division and modulo test module"); -- cgit v1.2.3 From 182dd5bad52c66a54c300fe320b772456572bf23 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 21 Apr 2021 15:25:22 +0200 Subject: lib/math/test_div64: Fix error message formatting Align the expected result with one actually produced for easier visual comparison; this has to take into account what the format specifiers will actually produce rather than the characters they consist of. E.g.: test_div64: ERROR: 10000000ab275080 / 00000009 => 01c71c71da20d00e,00000002 test_div64: ERROR: expected value => 0000000013045e47,00000001 (with a failure induced by setting bit #60 of the divident). Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer --- lib/math/test_div64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/math/test_div64.c b/lib/math/test_div64.c index eca8e8c6afe0..67bef184f2e3 100644 --- a/lib/math/test_div64.c +++ b/lib/math/test_div64.c @@ -170,7 +170,7 @@ static inline bool test_div64_verify(u64 quotient, u32 remainder, int i, int j) if (!test_div64_verify(quotient, remainder, i, j)) { \ pr_err("ERROR: %016llx / %08x => %016llx,%08x\n", \ divident, divisor, quotient, remainder); \ - pr_err("ERROR: expected value=> %016llx,%08x\n", \ + pr_err("ERROR: expected value => %016llx,%08x\n",\ test_div64_results[i][j].quotient, \ test_div64_results[i][j].remainder); \ result = false; \ -- cgit v1.2.3 From b2a4411aca29ab7feb17c927d1d91d979361983c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 11 Apr 2021 17:05:56 -0700 Subject: crypto: doc - fix kernel-doc notation in chacha.c and af_alg.c Fix function name in chacha.c kernel-doc comment to remove a warning. Convert af_alg.c to kernel-doc notation to eliminate many kernel-doc warnings. ../lib/crypto/chacha.c:77: warning: expecting prototype for chacha_block(). Prototype was for chacha_block_generic() instead chacha.c:104: warning: Excess function parameter 'out' description in 'hchacha_block_generic' af_alg.c:498: warning: Function parameter or member 'sk' not described in 'af_alg_alloc_tsgl' ../crypto/af_alg.c:539: warning: expecting prototype for aead_count_tsgl(). Prototype was for af_alg_count_tsgl() instead ../crypto/af_alg.c:596: warning: expecting prototype for aead_pull_tsgl(). Prototype was for af_alg_pull_tsgl() instead af_alg.c:663: warning: Function parameter or member 'areq' not described in 'af_alg_free_areq_sgls' af_alg.c:700: warning: Function parameter or member 'sk' not described in 'af_alg_wait_for_wmem' af_alg.c:700: warning: Function parameter or member 'flags' not described in 'af_alg_wait_for_wmem' af_alg.c:731: warning: Function parameter or member 'sk' not described in 'af_alg_wmem_wakeup' af_alg.c:757: warning: Function parameter or member 'sk' not described in 'af_alg_wait_for_data' af_alg.c:757: warning: Function parameter or member 'flags' not described in 'af_alg_wait_for_data' af_alg.c:757: warning: Function parameter or member 'min' not described in 'af_alg_wait_for_data' af_alg.c:796: warning: Function parameter or member 'sk' not described in 'af_alg_data_wakeup' af_alg.c:832: warning: Function parameter or member 'sock' not described in 'af_alg_sendmsg' af_alg.c:832: warning: Function parameter or member 'msg' not described in 'af_alg_sendmsg' af_alg.c:832: warning: Function parameter or member 'size' not described in 'af_alg_sendmsg' af_alg.c:832: warning: Function parameter or member 'ivsize' not described in 'af_alg_sendmsg' af_alg.c:985: warning: Function parameter or member 'sock' not described in 'af_alg_sendpage' af_alg.c:985: warning: Function parameter or member 'page' not described in 'af_alg_sendpage' af_alg.c:985: warning: Function parameter or member 'offset' not described in 'af_alg_sendpage' af_alg.c:985: warning: Function parameter or member 'size' not described in 'af_alg_sendpage' af_alg.c:985: warning: Function parameter or member 'flags' not described in 'af_alg_sendpage' af_alg.c:1040: warning: Function parameter or member 'areq' not described in 'af_alg_free_resources' af_alg.c:1059: warning: Function parameter or member '_req' not described in 'af_alg_async_cb' af_alg.c:1059: warning: Function parameter or member 'err' not described in 'af_alg_async_cb' af_alg.c:1083: warning: Function parameter or member 'file' not described in 'af_alg_poll' af_alg.c:1083: warning: Function parameter or member 'sock' not described in 'af_alg_poll' af_alg.c:1083: warning: Function parameter or member 'wait' not described in 'af_alg_poll' af_alg.c:1114: warning: Function parameter or member 'sk' not described in 'af_alg_alloc_areq' af_alg.c:1114: warning: Function parameter or member 'areqlen' not described in 'af_alg_alloc_areq' af_alg.c:1146: warning: Function parameter or member 'sk' not described in 'af_alg_get_rsgl' af_alg.c:1146: warning: Function parameter or member 'msg' not described in 'af_alg_get_rsgl' af_alg.c:1146: warning: Function parameter or member 'flags' not described in 'af_alg_get_rsgl' af_alg.c:1146: warning: Function parameter or member 'areq' not described in 'af_alg_get_rsgl' af_alg.c:1146: warning: Function parameter or member 'maxsize' not described in 'af_alg_get_rsgl' af_alg.c:1146: warning: Function parameter or member 'outlen' not described in 'af_alg_get_rsgl' Signed-off-by: Randy Dunlap Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Signed-off-by: Herbert Xu --- crypto/af_alg.c | 94 ++++++++++++++++++++++++++++++----------------------- lib/crypto/chacha.c | 4 +-- 2 files changed, 55 insertions(+), 43 deletions(-) (limited to 'lib') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 9acb9d2c4bcf..18cc82dc4a42 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -491,8 +491,8 @@ static int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) /** * af_alg_alloc_tsgl - allocate the TX SGL * - * @sk socket of connection to user space - * @return: 0 upon success, < 0 upon error + * @sk: socket of connection to user space + * Return: 0 upon success, < 0 upon error */ static int af_alg_alloc_tsgl(struct sock *sk) { @@ -525,15 +525,15 @@ static int af_alg_alloc_tsgl(struct sock *sk) } /** - * aead_count_tsgl - Count number of TX SG entries + * af_alg_count_tsgl - Count number of TX SG entries * * The counting starts from the beginning of the SGL to @bytes. If - * an offset is provided, the counting of the SG entries starts at the offset. + * an @offset is provided, the counting of the SG entries starts at the @offset. * - * @sk socket of connection to user space - * @bytes Count the number of SG entries holding given number of bytes. - * @offset Start the counting of SG entries from the given offset. - * @return Number of TX SG entries found given the constraints + * @sk: socket of connection to user space + * @bytes: Count the number of SG entries holding given number of bytes. + * @offset: Start the counting of SG entries from the given offset. + * Return: Number of TX SG entries found given the constraints */ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) { @@ -577,19 +577,19 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) EXPORT_SYMBOL_GPL(af_alg_count_tsgl); /** - * aead_pull_tsgl - Release the specified buffers from TX SGL + * af_alg_pull_tsgl - Release the specified buffers from TX SGL * - * If @dst is non-null, reassign the pages to dst. The caller must release + * If @dst is non-null, reassign the pages to @dst. The caller must release * the pages. If @dst_offset is given only reassign the pages to @dst starting * at the @dst_offset (byte). The caller must ensure that @dst is large * enough (e.g. by using af_alg_count_tsgl with the same offset). * - * @sk socket of connection to user space - * @used Number of bytes to pull from TX SGL - * @dst If non-NULL, buffer is reassigned to dst SGL instead of releasing. The - * caller must release the buffers in dst. - * @dst_offset Reassign the TX SGL from given offset. All buffers before - * reaching the offset is released. + * @sk: socket of connection to user space + * @used: Number of bytes to pull from TX SGL + * @dst: If non-NULL, buffer is reassigned to dst SGL instead of releasing. The + * caller must release the buffers in dst. + * @dst_offset: Reassign the TX SGL from given offset. All buffers before + * reaching the offset is released. */ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, size_t dst_offset) @@ -657,7 +657,7 @@ EXPORT_SYMBOL_GPL(af_alg_pull_tsgl); /** * af_alg_free_areq_sgls - Release TX and RX SGLs of the request * - * @areq Request holding the TX and RX SGL + * @areq: Request holding the TX and RX SGL */ static void af_alg_free_areq_sgls(struct af_alg_async_req *areq) { @@ -692,9 +692,9 @@ static void af_alg_free_areq_sgls(struct af_alg_async_req *areq) /** * af_alg_wait_for_wmem - wait for availability of writable memory * - * @sk socket of connection to user space - * @flags If MSG_DONTWAIT is set, then only report if function would sleep - * @return 0 when writable memory is available, < 0 upon error + * @sk: socket of connection to user space + * @flags: If MSG_DONTWAIT is set, then only report if function would sleep + * Return: 0 when writable memory is available, < 0 upon error */ static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) { @@ -725,7 +725,7 @@ static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) /** * af_alg_wmem_wakeup - wakeup caller when writable memory is available * - * @sk socket of connection to user space + * @sk: socket of connection to user space */ void af_alg_wmem_wakeup(struct sock *sk) { @@ -748,10 +748,10 @@ EXPORT_SYMBOL_GPL(af_alg_wmem_wakeup); /** * af_alg_wait_for_data - wait for availability of TX data * - * @sk socket of connection to user space - * @flags If MSG_DONTWAIT is set, then only report if function would sleep - * @min Set to minimum request size if partial requests are allowed. - * @return 0 when writable memory is available, < 0 upon error + * @sk: socket of connection to user space + * @flags: If MSG_DONTWAIT is set, then only report if function would sleep + * @min: Set to minimum request size if partial requests are allowed. + * Return: 0 when writable memory is available, < 0 upon error */ int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min) { @@ -790,7 +790,7 @@ EXPORT_SYMBOL_GPL(af_alg_wait_for_data); /** * af_alg_data_wakeup - wakeup caller when new data can be sent to kernel * - * @sk socket of connection to user space + * @sk: socket of connection to user space */ static void af_alg_data_wakeup(struct sock *sk) { @@ -820,12 +820,12 @@ static void af_alg_data_wakeup(struct sock *sk) * * In addition, the ctx is filled with the information sent via CMSG. * - * @sock socket of connection to user space - * @msg message from user space - * @size size of message from user space - * @ivsize the size of the IV for the cipher operation to verify that the + * @sock: socket of connection to user space + * @msg: message from user space + * @size: size of message from user space + * @ivsize: the size of the IV for the cipher operation to verify that the * user-space-provided IV has the right size - * @return the number of copied data upon success, < 0 upon error + * Return: the number of copied data upon success, < 0 upon error */ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unsigned int ivsize) @@ -977,6 +977,11 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg); /** * af_alg_sendpage - sendpage system call handler + * @sock: socket of connection to user space to write to + * @page: data to send + * @offset: offset into page to begin sending + * @size: length of data + * @flags: message send/receive flags * * This is a generic implementation of sendpage to fill ctx->tsgl_list. */ @@ -1035,6 +1040,7 @@ EXPORT_SYMBOL_GPL(af_alg_sendpage); /** * af_alg_free_resources - release resources required for crypto request + * @areq: Request holding the TX and RX SGL */ void af_alg_free_resources(struct af_alg_async_req *areq) { @@ -1047,6 +1053,9 @@ EXPORT_SYMBOL_GPL(af_alg_free_resources); /** * af_alg_async_cb - AIO callback handler + * @_req: async request info + * @err: if non-zero, error result to be returned via ki_complete(); + * otherwise return the AIO output length via ki_complete(). * * This handler cleans up the struct af_alg_async_req upon completion of the * AIO operation. @@ -1073,6 +1082,9 @@ EXPORT_SYMBOL_GPL(af_alg_async_cb); /** * af_alg_poll - poll system call handler + * @file: file pointer + * @sock: socket to poll + * @wait: poll_table */ __poll_t af_alg_poll(struct file *file, struct socket *sock, poll_table *wait) @@ -1098,9 +1110,9 @@ EXPORT_SYMBOL_GPL(af_alg_poll); /** * af_alg_alloc_areq - allocate struct af_alg_async_req * - * @sk socket of connection to user space - * @areqlen size of struct af_alg_async_req + crypto_*_reqsize - * @return allocated data structure or ERR_PTR upon error + * @sk: socket of connection to user space + * @areqlen: size of struct af_alg_async_req + crypto_*_reqsize + * Return: allocated data structure or ERR_PTR upon error */ struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk, unsigned int areqlen) @@ -1125,13 +1137,13 @@ EXPORT_SYMBOL_GPL(af_alg_alloc_areq); * af_alg_get_rsgl - create the RX SGL for the output data from the crypto * operation * - * @sk socket of connection to user space - * @msg user space message - * @flags flags used to invoke recvmsg with - * @areq instance of the cryptographic request that will hold the RX SGL - * @maxsize maximum number of bytes to be pulled from user space - * @outlen number of bytes in the RX SGL - * @return 0 on success, < 0 upon error + * @sk: socket of connection to user space + * @msg: user space message + * @flags: flags used to invoke recvmsg with + * @areq: instance of the cryptographic request that will hold the RX SGL + * @maxsize: maximum number of bytes to be pulled from user space + * @outlen: number of bytes in the RX SGL + * Return: 0 on success, < 0 upon error */ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, struct af_alg_async_req *areq, size_t maxsize, diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c index 4ccbec442469..b748fd3d256e 100644 --- a/lib/crypto/chacha.c +++ b/lib/crypto/chacha.c @@ -64,7 +64,7 @@ static void chacha_permute(u32 *x, int nrounds) } /** - * chacha_block - generate one keystream block and increment block counter + * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) @@ -92,7 +92,7 @@ EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) - * @out: output (8 32-bit words) + * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step -- cgit v1.2.3 From 7ff5062079ef5c2f92af0c770dfc0ab925fa2128 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 10 Feb 2020 10:00:21 +0000 Subject: iov_iter: Add ITER_XARRAY Add an iterator, ITER_XARRAY, that walks through a set of pages attached to an xarray, starting at a given page and offset and walking for the specified amount of bytes. The iterator supports transparent huge pages. The iterate_xarray() macro calls the helper function with rcu_access() helped. I think that this is only a problem for iov_iter_for_each_range() - and that returns an error for ITER_XARRAY (also, this function does not appear to be called). The caller must guarantee that the pages are all present and they must be locked using PG_locked, PG_writeback or PG_fscache to prevent them from going away or being migrated whilst they're being accessed. This is useful for copying data from socket buffers to inodes in network filesystems and for transferring data between those inodes and the cache using direct I/O. Whilst it is true that ITER_BVEC could be used instead, that would require a bio_vec array to be allocated to refer to all the pages - which should be redundant if inode->i_pages also points to all these pages. Note that older versions of this patch implemented an ITER_MAPPING instead, which was almost the same. Changes: v7: - Rename iter_xarray_copy_pages() to iter_xarray_populate_pages()[1]. Signed-off-by: David Howells Reviewed-and-tested-by: Jeff Layton Tested-by: Dave Wysochanski Tested-By: Marc Dionne cc: Alexander Viro cc: Matthew Wilcox (Oracle) cc: Christoph Hellwig cc: linux-mm@kvack.org cc: linux-cachefs@redhat.com cc: linux-afs@lists.infradead.org cc: linux-nfs@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: ceph-devel@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/3577430.1579705075@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/158861205740.340223.16592990225607814022.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/159465785214.1376674.6062549291411362531.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/160588477334.3465195.3608963255682568730.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/161118129703.1232039.17141248432017826976.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/161161026313.2537118.14676007075365418649.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/161340386671.1303470.10752208972482479840.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/161539527815.286939.14607323792547049341.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/161653786033.2770958.14154191921867463240.stgit@warthog.procyon.org.uk/ # v5 Link: https://lore.kernel.org/r/161789064740.6155.11932541175173658065.stgit@warthog.procyon.org.uk/ # v6 Link: https://lore.kernel.org/r/27c369a8f42bb8a617672b2dc0126a5c6df5a050.camel@kernel.org [1] --- include/linux/uio.h | 11 ++ lib/iov_iter.c | 313 ++++++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 301 insertions(+), 23 deletions(-) (limited to 'lib') diff --git a/include/linux/uio.h b/include/linux/uio.h index 27ff8eb786dc..5f5ffc45d4aa 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -10,6 +10,7 @@ #include struct page; +struct address_space; struct pipe_inode_info; struct kvec { @@ -24,6 +25,7 @@ enum iter_type { ITER_BVEC = 16, ITER_PIPE = 32, ITER_DISCARD = 64, + ITER_XARRAY = 128, }; struct iov_iter { @@ -39,6 +41,7 @@ struct iov_iter { const struct iovec *iov; const struct kvec *kvec; const struct bio_vec *bvec; + struct xarray *xarray; struct pipe_inode_info *pipe; }; union { @@ -47,6 +50,7 @@ struct iov_iter { unsigned int head; unsigned int start_head; }; + loff_t xarray_start; }; }; @@ -80,6 +84,11 @@ static inline bool iov_iter_is_discard(const struct iov_iter *i) return iov_iter_type(i) == ITER_DISCARD; } +static inline bool iov_iter_is_xarray(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_XARRAY; +} + static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); @@ -221,6 +230,8 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); +void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, + loff_t start, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f66c62aa7154..44fa726a8323 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -76,7 +76,44 @@ } \ } -#define iterate_all_kinds(i, n, v, I, B, K) { \ +#define iterate_xarray(i, n, __v, skip, STEP) { \ + struct page *head = NULL; \ + size_t wanted = n, seg, offset; \ + loff_t start = i->xarray_start + skip; \ + pgoff_t index = start >> PAGE_SHIFT; \ + int j; \ + \ + XA_STATE(xas, i->xarray, index); \ + \ + rcu_read_lock(); \ + xas_for_each(&xas, head, ULONG_MAX) { \ + if (xas_retry(&xas, head)) \ + continue; \ + if (WARN_ON(xa_is_value(head))) \ + break; \ + if (WARN_ON(PageHuge(head))) \ + break; \ + for (j = (head->index < index) ? index - head->index : 0; \ + j < thp_nr_pages(head); j++) { \ + __v.bv_page = head + j; \ + offset = (i->xarray_start + skip) & ~PAGE_MASK; \ + seg = PAGE_SIZE - offset; \ + __v.bv_offset = offset; \ + __v.bv_len = min(n, seg); \ + (void)(STEP); \ + n -= __v.bv_len; \ + skip += __v.bv_len; \ + if (n == 0) \ + break; \ + } \ + if (n == 0) \ + break; \ + } \ + rcu_read_unlock(); \ + n = wanted - n; \ +} + +#define iterate_all_kinds(i, n, v, I, B, K, X) { \ if (likely(n)) { \ size_t skip = i->iov_offset; \ if (unlikely(i->type & ITER_BVEC)) { \ @@ -88,6 +125,9 @@ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ } else if (unlikely(i->type & ITER_DISCARD)) { \ + } else if (unlikely(i->type & ITER_XARRAY)) { \ + struct bio_vec v; \ + iterate_xarray(i, n, v, skip, (X)); \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -96,7 +136,7 @@ } \ } -#define iterate_and_advance(i, n, v, I, B, K) { \ +#define iterate_and_advance(i, n, v, I, B, K, X) { \ if (unlikely(i->count < n)) \ n = i->count; \ if (i->count) { \ @@ -121,6 +161,9 @@ i->kvec = kvec; \ } else if (unlikely(i->type & ITER_DISCARD)) { \ skip += n; \ + } else if (unlikely(i->type & ITER_XARRAY)) { \ + struct bio_vec v; \ + iterate_xarray(i, n, v, skip, (X)) \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -622,7 +665,9 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), memcpy_to_page(v.bv_page, v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len), - memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) + memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), + memcpy_to_page(v.bv_page, v.bv_offset, + (from += v.bv_len) - v.bv_len, v.bv_len) ) return bytes; @@ -738,6 +783,16 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) bytes = curr_addr - s_addr - rem; return bytes; } + }), + ({ + rem = copy_mc_to_page(v.bv_page, v.bv_offset, + (from += v.bv_len) - v.bv_len, v.bv_len); + if (rem) { + curr_addr = (unsigned long) from; + bytes = curr_addr - s_addr - rem; + rcu_read_unlock(); + return bytes; + } }) ) @@ -759,7 +814,9 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) return bytes; @@ -785,7 +842,9 @@ bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) iov_iter_advance(i, bytes); @@ -805,7 +864,9 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) return bytes; @@ -840,7 +901,9 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, - v.iov_len) + v.iov_len), + memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) return bytes; @@ -864,7 +927,9 @@ bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), - memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) iov_iter_advance(i, bytes); @@ -901,7 +966,7 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; - if (i->type & (ITER_BVEC|ITER_KVEC)) { + if (i->type & (ITER_BVEC | ITER_KVEC | ITER_XARRAY)) { void *kaddr = kmap_atomic(page); size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); @@ -924,7 +989,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, WARN_ON(1); return 0; } - if (i->type & (ITER_BVEC|ITER_KVEC)) { + if (i->type & (ITER_BVEC | ITER_KVEC | ITER_XARRAY)) { void *kaddr = kmap_atomic(page); size_t wanted = _copy_from_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); @@ -968,7 +1033,8 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *i) iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), memzero_page(v.bv_page, v.bv_offset, v.bv_len), - memset(v.iov_base, 0, v.iov_len) + memset(v.iov_base, 0, v.iov_len), + memzero_page(v.bv_page, v.bv_offset, v.bv_len) ) return bytes; @@ -992,7 +1058,9 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, copyin((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), - memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), + memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len) ) kunmap_atomic(kaddr); return bytes; @@ -1078,11 +1146,16 @@ void iov_iter_advance(struct iov_iter *i, size_t size) i->count -= size; return; } + if (unlikely(iov_iter_is_xarray(i))) { + i->iov_offset += size; + i->count -= size; + return; + } if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); return; } - iterate_and_advance(i, size, v, 0, 0, 0) + iterate_and_advance(i, size, v, 0, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -1126,7 +1199,12 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) return; } unroll -= i->iov_offset; - if (iov_iter_is_bvec(i)) { + if (iov_iter_is_xarray(i)) { + BUG(); /* We should never go beyond the start of the specified + * range since we might then be straying into pages that + * aren't pinned. + */ + } else if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; @@ -1163,9 +1241,9 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; - if (unlikely(iov_iter_is_discard(i))) + if (unlikely(iov_iter_is_discard(i) || iov_iter_is_xarray(i))) return i->count; - else if (iov_iter_is_bvec(i)) + if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); @@ -1213,6 +1291,31 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_pipe); +/** + * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @xarray: The xarray to access. + * @start: The start file position. + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator to either draw data out of the pages attached to an + * inode or to inject data into those pages. The pages *must* be prevented + * from evaporation, either by taking a ref on them or locking them by the + * caller. + */ +void iov_iter_xarray(struct iov_iter *i, unsigned int direction, + struct xarray *xarray, loff_t start, size_t count) +{ + BUG_ON(direction & ~1); + i->type = ITER_XARRAY | (direction & (READ | WRITE)); + i->xarray = xarray; + i->xarray_start = start; + i->count = count; + i->iov_offset = 0; +} +EXPORT_SYMBOL(iov_iter_xarray); + /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. @@ -1246,7 +1349,8 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) iterate_all_kinds(i, size, v, (res |= (unsigned long)v.iov_base | v.iov_len, 0), res |= v.bv_offset | v.bv_len, - res |= (unsigned long)v.iov_base | v.iov_len + res |= (unsigned long)v.iov_base | v.iov_len, + res |= v.bv_offset | v.bv_len ) return res; } @@ -1268,7 +1372,9 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) (res |= (!res ? 0 : (unsigned long)v.bv_offset) | (size != v.bv_len ? size : 0)), (res |= (!res ? 0 : (unsigned long)v.iov_base) | - (size != v.iov_len ? size : 0)) + (size != v.iov_len ? size : 0)), + (res |= (!res ? 0 : (unsigned long)v.bv_offset) | + (size != v.bv_len ? size : 0)) ); return res; } @@ -1318,6 +1424,75 @@ static ssize_t pipe_get_pages(struct iov_iter *i, return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start); } +static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, + pgoff_t index, unsigned int nr_pages) +{ + XA_STATE(xas, xa, index); + struct page *page; + unsigned int ret = 0; + + rcu_read_lock(); + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + if (xas_retry(&xas, page)) + continue; + + /* Has the page moved or been split? */ + if (unlikely(page != xas_reload(&xas))) { + xas_reset(&xas); + continue; + } + + pages[ret] = find_subpage(page, xas.xa_index); + get_page(pages[ret]); + if (++ret == nr_pages) + break; + } + rcu_read_unlock(); + return ret; +} + +static ssize_t iter_xarray_get_pages(struct iov_iter *i, + struct page **pages, size_t maxsize, + unsigned maxpages, size_t *_start_offset) +{ + unsigned nr, offset; + pgoff_t index, count; + size_t size = maxsize, actual; + loff_t pos; + + if (!size || !maxpages) + return 0; + + pos = i->xarray_start + i->iov_offset; + index = pos >> PAGE_SHIFT; + offset = pos & ~PAGE_MASK; + *_start_offset = offset; + + count = 1; + if (size > PAGE_SIZE - offset) { + size -= PAGE_SIZE - offset; + count += size >> PAGE_SHIFT; + size &= ~PAGE_MASK; + if (size) + count++; + } + + if (count > maxpages) + count = maxpages; + + nr = iter_xarray_populate_pages(pages, i->xarray, index, count); + if (nr == 0) + return 0; + + actual = PAGE_SIZE * nr; + actual -= offset; + if (nr == count && size > 0) { + unsigned last_offset = (nr > 1) ? 0 : offset; + actual -= PAGE_SIZE - (last_offset + size); + } + return actual; +} + ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) @@ -1327,6 +1502,8 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); + if (unlikely(iov_iter_is_xarray(i))) + return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; @@ -1353,7 +1530,8 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, return v.bv_len; }),({ return -EFAULT; - }) + }), + 0 ) return 0; } @@ -1397,6 +1575,51 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i, return n; } +static ssize_t iter_xarray_get_pages_alloc(struct iov_iter *i, + struct page ***pages, size_t maxsize, + size_t *_start_offset) +{ + struct page **p; + unsigned nr, offset; + pgoff_t index, count; + size_t size = maxsize, actual; + loff_t pos; + + if (!size) + return 0; + + pos = i->xarray_start + i->iov_offset; + index = pos >> PAGE_SHIFT; + offset = pos & ~PAGE_MASK; + *_start_offset = offset; + + count = 1; + if (size > PAGE_SIZE - offset) { + size -= PAGE_SIZE - offset; + count += size >> PAGE_SHIFT; + size &= ~PAGE_MASK; + if (size) + count++; + } + + p = get_pages_array(count); + if (!p) + return -ENOMEM; + *pages = p; + + nr = iter_xarray_populate_pages(p, i->xarray, index, count); + if (nr == 0) + return 0; + + actual = PAGE_SIZE * nr; + actual -= offset; + if (nr == count && size > 0) { + unsigned last_offset = (nr > 1) ? 0 : offset; + actual -= PAGE_SIZE - (last_offset + size); + } + return actual; +} + ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) @@ -1408,6 +1631,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); + if (unlikely(iov_iter_is_xarray(i))) + return iter_xarray_get_pages_alloc(i, pages, maxsize, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; @@ -1440,7 +1665,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, return v.bv_len; }),({ return -EFAULT; - }) + }), 0 ) return 0; } @@ -1478,6 +1703,13 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, v.iov_base, v.iov_len, sum, off); off += v.iov_len; + }), ({ + char *p = kmap_atomic(v.bv_page); + sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, + p + v.bv_offset, v.bv_len, + sum, off); + kunmap_atomic(p); + off += v.bv_len; }) ) *csum = sum; @@ -1519,6 +1751,13 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, v.iov_base, v.iov_len, sum, off); off += v.iov_len; + }), ({ + char *p = kmap_atomic(v.bv_page); + sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, + p + v.bv_offset, v.bv_len, + sum, off); + kunmap_atomic(p); + off += v.bv_len; }) ) *csum = sum; @@ -1565,6 +1804,13 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, (from += v.iov_len) - v.iov_len, v.iov_len, sum, off); off += v.iov_len; + }), ({ + char *p = kmap_atomic(v.bv_page); + sum = csum_and_memcpy(p + v.bv_offset, + (from += v.bv_len) - v.bv_len, + v.bv_len, sum, off); + kunmap_atomic(p); + off += v.bv_len; }) ) csstate->csum = sum; @@ -1615,6 +1861,21 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) npages = pipe_space_for_user(iter_head, pipe->tail, pipe); if (npages >= maxpages) return maxpages; + } else if (unlikely(iov_iter_is_xarray(i))) { + unsigned offset; + + offset = (i->xarray_start + i->iov_offset) & ~PAGE_MASK; + + npages = 1; + if (size > PAGE_SIZE - offset) { + size -= PAGE_SIZE - offset; + npages += size >> PAGE_SHIFT; + size &= ~PAGE_MASK; + if (size) + npages++; + } + if (npages >= maxpages) + return maxpages; } else iterate_all_kinds(i, size, v, ({ unsigned long p = (unsigned long)v.iov_base; npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) @@ -1631,7 +1892,8 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) - p / PAGE_SIZE; if (npages >= maxpages) return maxpages; - }) + }), + 0 ) return npages; } @@ -1644,7 +1906,7 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) WARN_ON(1); return NULL; } - if (unlikely(iov_iter_is_discard(new))) + if (unlikely(iov_iter_is_discard(new) || iov_iter_is_xarray(new))) return NULL; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, @@ -1849,7 +2111,12 @@ int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, kunmap(v.bv_page); err;}), ({ w = v; - err = f(&w, context);}) + err = f(&w, context);}), ({ + w.iov_base = kmap(v.bv_page) + v.bv_offset; + w.iov_len = v.bv_len; + err = f(&w, context); + kunmap(v.bv_page); + err;}) ) return err; } -- cgit v1.2.3 From 517b322c07e17787fc8a22ca9cede709b6ae9ec0 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Thu, 22 Apr 2021 22:36:08 +0200 Subject: lib/math/test_div64: Correct the spelling of "dividend" The word is spelt with a final "d" of course. What a massive messup! Signed-off-by: Maciej W. Rozycki Signed-off-by: Thomas Bogendoerfer --- lib/math/test_div64.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'lib') diff --git a/lib/math/test_div64.c b/lib/math/test_div64.c index 67bef184f2e3..c15edd688dd2 100644 --- a/lib/math/test_div64.c +++ b/lib/math/test_div64.c @@ -16,7 +16,7 @@ #define TEST_DIV64_N_ITER 1024 -static const u64 test_div64_dividents[] = { +static const u64 test_div64_dividends[] = { 0x00000000ab275080, 0x0000000fe73c1959, 0x000000e54c0a74b1, @@ -27,7 +27,7 @@ static const u64 test_div64_dividents[] = { 0x0842f488162e2284, 0xf66745411d8ab063, }; -#define SIZE_DIV64_DIVIDENTS ARRAY_SIZE(test_div64_dividents) +#define SIZE_DIV64_DIVIDENDS ARRAY_SIZE(test_div64_dividends) #define TEST_DIV64_DIVISOR_0 0x00000009 #define TEST_DIV64_DIVISOR_1 0x0000007c @@ -55,7 +55,7 @@ static const u32 test_div64_divisors[] = { static const struct { u64 quotient; u32 remainder; -} test_div64_results[SIZE_DIV64_DIVISORS][SIZE_DIV64_DIVIDENTS] = { +} test_div64_results[SIZE_DIV64_DIVISORS][SIZE_DIV64_DIVIDENDS] = { { { 0x0000000013045e47, 0x00000001 }, { 0x000000000161596c, 0x00000030 }, @@ -160,16 +160,16 @@ static inline bool test_div64_verify(u64 quotient, u32 remainder, int i, int j) * to do constant propagation, and `do_div' may take a different path for * constants, so we do want to verify that as well. */ -#define test_div64_one(divident, divisor, i, j) ({ \ +#define test_div64_one(dividend, divisor, i, j) ({ \ bool result = true; \ u64 quotient; \ u32 remainder; \ \ - quotient = divident; \ + quotient = dividend; \ remainder = do_div(quotient, divisor); \ if (!test_div64_verify(quotient, remainder, i, j)) { \ pr_err("ERROR: %016llx / %08x => %016llx,%08x\n", \ - divident, divisor, quotient, remainder); \ + dividend, divisor, quotient, remainder); \ pr_err("ERROR: expected value => %016llx,%08x\n",\ test_div64_results[i][j].quotient, \ test_div64_results[i][j].remainder); \ @@ -185,31 +185,31 @@ static inline bool test_div64_verify(u64 quotient, u32 remainder, int i, int j) */ static bool __init test_div64(void) { - u64 divident; + u64 dividend; int i, j; - for (i = 0; i < SIZE_DIV64_DIVIDENTS; i++) { - divident = test_div64_dividents[i]; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_0, i, 0)) + for (i = 0; i < SIZE_DIV64_DIVIDENDS; i++) { + dividend = test_div64_dividends[i]; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_0, i, 0)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_1, i, 1)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_1, i, 1)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_2, i, 2)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_2, i, 2)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_3, i, 3)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_3, i, 3)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_4, i, 4)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_4, i, 4)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_5, i, 5)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_5, i, 5)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_6, i, 6)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_6, i, 6)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_7, i, 7)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_7, i, 7)) return false; - if (!test_div64_one(divident, TEST_DIV64_DIVISOR_8, i, 8)) + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_8, i, 8)) return false; for (j = 0; j < SIZE_DIV64_DIVISORS; j++) { - if (!test_div64_one(divident, test_div64_divisors[j], + if (!test_div64_one(dividend, test_div64_divisors[j], i, j)) return false; } -- cgit v1.2.3 From 84696cfaf4d90945eb2a8302edc6cf627db56b84 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 23 Apr 2021 11:45:29 +0200 Subject: lib/vsprintf.c: remove leftover 'f' and 'F' cases from bstr_printf() Commit 9af7706492f9 ("lib/vsprintf: Remove support for %pF and %pf in favour of %pS and %ps") removed support for %pF and %pf, and correctly removed the handling of those cases in vbin_printf(). However, the corresponding cases in bstr_printf() were left behind. In the same series, %pf was re-purposed for dealing with fwnodes (3bd32d6a2ee6, "lib/vsprintf: Add %pfw conversion specifier for printing fwnode names"). So should anyone use %pf with the binary printf routines, vbin_printf() would (correctly, as it involves dereferencing the pointer) do the string formatting to the u32 array, but bstr_printf() would not copy the string from the u32 array, but instead interpret the first sizeof(void*) bytes of the formatted string as a pointer - which generally won't end well (also, all subsequent get_args would be out of sync). Fixes: 9af7706492f9 ("lib/vsprintf: Remove support for %pF and %pf in favour of %pS and %ps") Cc: stable@vger.kernel.org Signed-off-by: Rasmus Villemoes Reviewed-by: Sakari Ailus Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210423094529.1862521-1-linux@rasmusvillemoes.dk --- lib/vsprintf.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 5ec8ad238d03..7caf619ee9c2 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -3141,8 +3141,6 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) switch (*fmt) { case 'S': case 's': - case 'F': - case 'f': case 'x': case 'K': case 'e': -- cgit v1.2.3 From 5cc1247204616528b427e276c97c5bc4c9612347 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 5 Mar 2021 10:27:07 +0100 Subject: kbuild: add CONFIG_VMLINUX_MAP expert option It can be quite useful to have ld emit a link map file, in order to debug or verify that special sections end up where they are supposed to, and to see what LD_DEAD_CODE_DATA_ELIMINATION manages to get rid of. The only reason I'm not just adding this unconditionally is that the .map file can be rather large (several MB), and that's a waste of space when one isn't interested in these things. Also make it depend on CONFIG_EXPERT. Signed-off-by: Rasmus Villemoes Signed-off-by: Masahiro Yamada --- .gitignore | 1 + Documentation/dontdiff | 1 + lib/Kconfig.debug | 10 ++++++++++ scripts/link-vmlinux.sh | 8 ++++++++ 4 files changed, 20 insertions(+) (limited to 'lib') diff --git a/.gitignore b/.gitignore index 3af66272d6f1..3adea59847ce 100644 --- a/.gitignore +++ b/.gitignore @@ -59,6 +59,7 @@ modules.order /linux /vmlinux /vmlinux.32 +/vmlinux.map /vmlinux.symvers /vmlinux-gdb.py /vmlinuz diff --git a/Documentation/dontdiff b/Documentation/dontdiff index e361fc95ca29..ac42ad8d430d 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -252,6 +252,7 @@ vmlinux-* vmlinux.aout vmlinux.bin.all vmlinux.lds +vmlinux.map vmlinux.symvers vmlinuz voffset.h diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..b479ae609a31 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -449,6 +449,16 @@ config VMLINUX_VALIDATION depends on STACK_VALIDATION && DEBUG_ENTRY && !PARAVIRT default y +config VMLINUX_MAP + bool "Generate vmlinux.map file when linking" + depends on EXPERT + help + Selecting this option will pass "-Map=vmlinux.map" to ld + when linking vmlinux. That file can be useful for verifying + and debugging magic section games, and for seeing which + pieces of code get eliminated with + CONFIG_LD_DEAD_CODE_DATA_ELIMINATION. + config DEBUG_FORCE_WEAK_PER_CPU bool "Force weak per-cpu definitions" depends on DEBUG_KERNEL diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 3b261b0f74f0..855fd4e6f03e 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -155,6 +155,7 @@ vmlinux_link() local output=${1} local objects local strip_debug + local map_option info LD ${output} @@ -166,6 +167,10 @@ vmlinux_link() strip_debug=-Wl,--strip-debug fi + if [ -n "${CONFIG_VMLINUX_MAP}" ]; then + map_option="-Map=${output}.map" + fi + if [ "${SRCARCH}" != "um" ]; then if [ -n "${CONFIG_LTO_CLANG}" ]; then # Use vmlinux.o instead of performing the slow LTO @@ -187,6 +192,7 @@ vmlinux_link() ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} \ ${strip_debug#-Wl,} \ -o ${output} \ + ${map_option} \ -T ${lds} ${objects} else objects="-Wl,--whole-archive \ @@ -200,6 +206,7 @@ vmlinux_link() ${CC} ${CFLAGS_vmlinux} \ ${strip_debug} \ -o ${output} \ + ${map_option:+-Wl,${map_option}} \ -Wl,-T,${lds} \ ${objects} \ -lutil -lrt -lpthread @@ -303,6 +310,7 @@ cleanup() rm -f .tmp_vmlinux* rm -f System.map rm -f vmlinux + rm -f vmlinux.map rm -f vmlinux.o } -- cgit v1.2.3 From 2e98815794fb51250da4528f67fc2f699d5e3c37 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Mar 2021 01:12:57 +0900 Subject: kbuild: dwarf: use AS_VERSION instead of test_dwarf5_support.sh The test code in scripts/test_dwarf5_support.sh is somewhat difficult to understand, but after all, we want to check binutils >= 2.35.2 From the former discussion, the requirement for generating DWARF v5 from C code is as follows: - gcc + gnu as -> requires gcc 5.0+ (but 7.0+ for full support) - clang + gnu as -> requires binutils 2.35.2+ - clang + integrated as -> OK Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor Reviewed-by: Nick Desaulniers --- lib/Kconfig.debug | 3 +-- scripts/test_dwarf5_support.sh | 8 -------- 2 files changed, 1 insertion(+), 10 deletions(-) delete mode 100755 scripts/test_dwarf5_support.sh (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b479ae609a31..c85d5f7a1aeb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -284,8 +284,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" - depends on GCC_VERSION >= 50000 || CC_IS_CLANG - depends on CC_IS_GCC || $(success,$(srctree)/scripts/test_dwarf5_support.sh $(CC) $(CLANG_FLAGS)) + depends on GCC_VERSION >= 50000 || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) depends on !DEBUG_INFO_BTF help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc diff --git a/scripts/test_dwarf5_support.sh b/scripts/test_dwarf5_support.sh deleted file mode 100755 index c46e2456b47a..000000000000 --- a/scripts/test_dwarf5_support.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -# Test that the assembler doesn't need -Wa,-gdwarf-5 when presented with DWARF -# v5 input, such as `.file 0` and `md5 0x00`. Should be fixed in GNU binutils -# 2.35.2. https://sourceware.org/bugzilla/show_bug.cgi?id=25611 -echo '.file 0 "filename" md5 0x7a0b65214090b6693bd1dc24dd248245' | \ - $* -gdwarf-5 -Wno-unused-command-line-argument -c -x assembler -o /dev/null - -- cgit v1.2.3 From 3d14ec1fe61aebe3da85a9b8f2c3d61e43d522e6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sun, 25 Apr 2021 22:02:38 +0100 Subject: iov_iter: Four fixes for ITER_XARRAY Fix four things[1] in the patch that adds ITER_XARRAY[2]: (1) Remove the address_space struct predeclaration. This is a holdover from when it was ITER_MAPPING. (2) Fix _copy_mc_to_iter() so that the xarray segment updates count and iov_offset in the iterator before returning. (3) Fix iov_iter_alignment() to not loop in the xarray case. Because the middle pages are all whole pages, only the end pages need be considered - and this can be reduced to just looking at the start position in the xarray and the iteration size. (4) Fix iov_iter_advance() to limit the size of the advance to no more than the remaining iteration size. Reported-by: Al Viro Signed-off-by: David Howells Reviewed-by: Al Viro Tested-by: Jeff Layton Tested-by: Dave Wysochanski Link: https://lore.kernel.org/r/YIVrJT8GwLI0Wlgx@zeniv-ca.linux.org.uk [1] Link: https://lore.kernel.org/r/161918448151.3145707.11541538916600921083.stgit@warthog.procyon.org.uk [2] --- include/linux/uio.h | 1 - lib/iov_iter.c | 5 +++++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5f5ffc45d4aa..d3ec87706d75 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -10,7 +10,6 @@ #include struct page; -struct address_space; struct pipe_inode_info; struct kvec { diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 44fa726a8323..61228a6c69f8 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -791,6 +791,8 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; rcu_read_unlock(); + i->iov_offset += bytes; + i->count -= bytes; return bytes; } }) @@ -1147,6 +1149,7 @@ void iov_iter_advance(struct iov_iter *i, size_t size) return; } if (unlikely(iov_iter_is_xarray(i))) { + size = min(size, i->count); i->iov_offset += size; i->count -= size; return; @@ -1346,6 +1349,8 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) return size | i->iov_offset; return size; } + if (unlikely(iov_iter_is_xarray(i))) + return (i->xarray_start + i->iov_offset) | i->count; iterate_all_kinds(i, size, v, (res |= (unsigned long)v.iov_base | v.iov_len, 0), res |= v.bv_offset | v.bv_len, -- cgit v1.2.3 From 7b1ae248279bea33af9e797a93c35f49601cb8a0 Mon Sep 17 00:00:00 2001 From: Shuo Chen Date: Wed, 14 Apr 2021 14:24:00 -0700 Subject: dyndbg: fix parsing file query without a line-range suffix Query like 'file tcp_input.c line 1234 +p' was broken by commit aaebe329bff0 ("dyndbg: accept 'file foo.c:func1' and 'file foo.c:10-100'") because a file name without a ':' now makes the loop in ddebug_parse_query() exits early before parsing the 'line 1234' part. As a result, all pr_debug() in tcp_input.c will be enabled, instead of only the one on line 1234. Changing 'break' to 'continue' fixes this. Fixes: aaebe329bff0 ("dyndbg: accept 'file foo.c:func1' and 'file foo.c:10-100'") Cc: stable Reviewed-by: Eric Dumazet Signed-off-by: Shuo Chen Acked-by: Jason Baron Link: https://lore.kernel.org/r/20210414212400.2927281-1-giantchen@gmail.com Signed-off-by: Greg Kroah-Hartman --- lib/dynamic_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index c70d6347afa2..921d0a654243 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -396,7 +396,7 @@ static int ddebug_parse_query(char *words[], int nwords, /* tail :$info is function or line-range */ fline = strchr(query->filename, ':'); if (!fline) - break; + continue; *fline++ = '\0'; if (isalpha(*fline) || *fline == '*' || *fline == '?') { /* take as function name */ -- cgit v1.2.3 From dce44566192ec0b38597fdfd435013c2d54653ff Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 29 Apr 2021 22:55:15 -0700 Subject: mm/memtest: add ARCH_USE_MEMTEST early_memtest() does not get called from all architectures. Hence enabling CONFIG_MEMTEST and providing a valid memtest=[1..N] kernel command line option might not trigger the memory pattern tests as would be expected in normal circumstances. This situation is misleading. The change here prevents the above mentioned problem after introducing a new config option ARCH_USE_MEMTEST that should be subscribed on platforms that call early_memtest(), in order to enable the config CONFIG_MEMTEST. Conversely CONFIG_MEMTEST cannot be enabled on platforms where it would not be tested anyway. Link: https://lkml.kernel.org/r/1617269193-22294-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Catalin Marinas (arm64) Reviewed-by: Max Filippov Cc: Russell King Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Chris Zankel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/Kconfig | 1 + arch/arm64/Kconfig | 1 + arch/mips/Kconfig | 1 + arch/powerpc/Kconfig | 1 + arch/x86/Kconfig | 1 + arch/xtensa/Kconfig | 1 + lib/Kconfig.debug | 9 ++++++++- 7 files changed, 14 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e6e08d8a45fc..085c830d344b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -33,6 +33,7 @@ config ARM select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_MEMTEST select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_LD_ORPHAN_WARN diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 570fa52eb6f0..7f2a80091337 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -67,6 +67,7 @@ config ARM64 select ARCH_KEEP_MEMBLOCK select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_GNU_PROPERTY + select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_SYM_ANNOTATIONS diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 702648f60e41..49a3c9cd1cb2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,6 +16,7 @@ config MIPS select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3b34c44832e0..2d060c002595 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -149,6 +149,7 @@ config PPC select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC32 || PPC_BOOK3S_64 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 + select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0fc82237414d..dac15f646f79 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -100,6 +100,7 @@ config X86 select ARCH_SUPPORTS_LTO_CLANG if X86_64 select ARCH_SUPPORTS_LTO_CLANG_THIN if X86_64 select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_SYM_ANNOTATIONS diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 9ad6b7b82707..524413aabbc4 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -7,6 +7,7 @@ config XTENSA select ARCH_HAS_SYNC_DMA_FOR_CPU if MMU select ARCH_HAS_SYNC_DMA_FOR_DEVICE if MMU select ARCH_HAS_DMA_SET_UNCACHED if MMU + select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_FRAME_POINTERS diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b38bbb5bb00e..678c13967580 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2573,11 +2573,18 @@ config TEST_FPU endif # RUNTIME_TESTING_MENU +config ARCH_USE_MEMTEST + bool + help + An architecture should select this when it uses early_memtest() + during boot process. + config MEMTEST bool "Memtest" + depends on ARCH_USE_MEMTEST help This option adds a kernel parameter 'memtest', which allows memtest - to be set. + to be set and executed. memtest=0, mean disabled; -- default memtest=1, mean do 1 test pattern; ... -- cgit v1.2.3 From a803315858bf8c6863f719f9fb251576fdf68a8c Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Thu, 29 Apr 2021 22:59:10 -0700 Subject: lib/test_vmalloc.c: remove two kvfree_rcu() tests Remove two test cases related to kvfree_rcu() and SLAB. Those are considered as redundant now, because similar test functionality has recently been introduced in the "rcuscale" RCU test-suite. Link: https://lkml.kernel.org/r/20210402202237.20334-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Cc: Hillf Danton Cc: Michal Hocko Cc: Matthew Wilcox Cc: Oleksiy Avramchenko Cc: Steven Rostedt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_vmalloc.c | 40 ---------------------------------------- 1 file changed, 40 deletions(-) (limited to 'lib') diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 5cf2fe9aab9e..4eb6abdaa74e 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -47,8 +47,6 @@ __param(int, run_test_mask, INT_MAX, "\t\tid: 128, name: pcpu_alloc_test\n" "\t\tid: 256, name: kvfree_rcu_1_arg_vmalloc_test\n" "\t\tid: 512, name: kvfree_rcu_2_arg_vmalloc_test\n" - "\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n" - "\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n" /* Add a new test case description here. */ ); @@ -363,42 +361,6 @@ kvfree_rcu_2_arg_vmalloc_test(void) return 0; } -static int -kvfree_rcu_1_arg_slab_test(void) -{ - struct test_kvfree_rcu *p; - int i; - - for (i = 0; i < test_loop_count; i++) { - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return -1; - - p->array[0] = 'a'; - kvfree_rcu(p); - } - - return 0; -} - -static int -kvfree_rcu_2_arg_slab_test(void) -{ - struct test_kvfree_rcu *p; - int i; - - for (i = 0; i < test_loop_count; i++) { - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return -1; - - p->array[0] = 'a'; - kvfree_rcu(p, rcu); - } - - return 0; -} - struct test_case_desc { const char *test_name; int (*test_func)(void); @@ -415,8 +377,6 @@ static struct test_case_desc test_case_array[] = { { "pcpu_alloc_test", pcpu_alloc_test }, { "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test }, { "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test }, - { "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test }, - { "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test }, /* Add a new test case here. */ }; -- cgit v1.2.3 From 80f4759964cc70ca8e3c793afbecbdc235ce7272 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Thu, 29 Apr 2021 22:59:13 -0700 Subject: lib/test_vmalloc.c: add a new 'nr_threads' parameter By using this parameter we can specify how many workers are created to perform vmalloc tests. By default it is one CPU. The maximum value is set to 1024. As a result of this change a 'single_cpu_test' one becomes obsolete, therefore it is no longer needed. [urezki@gmail.com: extend max value of nr_threads parameter] Link: https://lkml.kernel.org/r/20210406124536.19658-1-urezki@gmail.com Link: https://lkml.kernel.org/r/20210402202237.20334-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Cc: Hillf Danton Cc: Matthew Wilcox Cc: Michal Hocko Cc: Oleksiy Avramchenko Cc: Shuah Khan Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_vmalloc.c | 88 +++++++++++++++++++++++++----------------------------- 1 file changed, 40 insertions(+), 48 deletions(-) (limited to 'lib') diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 4eb6abdaa74e..01e9543de566 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -23,8 +23,8 @@ module_param(name, type, 0444); \ MODULE_PARM_DESC(name, msg) \ -__param(bool, single_cpu_test, false, - "Use single first online CPU to run tests"); +__param(int, nr_threads, 0, + "Number of workers to perform tests(min: 1 max: USHRT_MAX)"); __param(bool, sequential_test_order, false, "Use sequential stress tests order"); @@ -50,13 +50,6 @@ __param(int, run_test_mask, INT_MAX, /* Add a new test case description here. */ ); -/* - * Depends on single_cpu_test parameter. If it is true, then - * use first online CPU to trigger a test on, otherwise go with - * all online CPUs. - */ -static cpumask_t cpus_run_test_mask = CPU_MASK_NONE; - /* * Read write semaphore for synchronization of setup * phase that is done in main thread and workers. @@ -386,16 +379,13 @@ struct test_case_data { u64 time; }; -/* Split it to get rid of: WARNING: line over 80 characters */ -static struct test_case_data - per_cpu_test_data[NR_CPUS][ARRAY_SIZE(test_case_array)]; - static struct test_driver { struct task_struct *task; + struct test_case_data data[ARRAY_SIZE(test_case_array)]; + unsigned long start; unsigned long stop; - int cpu; -} per_cpu_test_driver[NR_CPUS]; +} *tdriver; static void shuffle_array(int *arr, int n) { @@ -423,9 +413,6 @@ static int test_func(void *private) ktime_t kt; u64 delta; - if (set_cpus_allowed_ptr(current, cpumask_of(t->cpu)) < 0) - pr_err("Failed to set affinity to %d CPU\n", t->cpu); - for (i = 0; i < ARRAY_SIZE(test_case_array); i++) random_array[i] = i; @@ -450,9 +437,9 @@ static int test_func(void *private) kt = ktime_get(); for (j = 0; j < test_repeat_count; j++) { if (!test_case_array[index].test_func()) - per_cpu_test_data[t->cpu][index].test_passed++; + t->data[index].test_passed++; else - per_cpu_test_data[t->cpu][index].test_failed++; + t->data[index].test_failed++; } /* @@ -461,7 +448,7 @@ static int test_func(void *private) delta = (u64) ktime_us_delta(ktime_get(), kt); do_div(delta, (u32) test_repeat_count); - per_cpu_test_data[t->cpu][index].time = delta; + t->data[index].time = delta; } t->stop = get_cycles(); @@ -477,53 +464,56 @@ static int test_func(void *private) return 0; } -static void +static int init_test_configurtion(void) { /* - * Reset all data of all CPUs. + * A maximum number of workers is defined as hard-coded + * value and set to USHRT_MAX. We add such gap just in + * case and for potential heavy stressing. */ - memset(per_cpu_test_data, 0, sizeof(per_cpu_test_data)); + nr_threads = clamp(nr_threads, 1, (int) USHRT_MAX); - if (single_cpu_test) - cpumask_set_cpu(cpumask_first(cpu_online_mask), - &cpus_run_test_mask); - else - cpumask_and(&cpus_run_test_mask, cpu_online_mask, - cpu_online_mask); + /* Allocate the space for test instances. */ + tdriver = kvcalloc(nr_threads, sizeof(*tdriver), GFP_KERNEL); + if (tdriver == NULL) + return -1; if (test_repeat_count <= 0) test_repeat_count = 1; if (test_loop_count <= 0) test_loop_count = 1; + + return 0; } static void do_concurrent_test(void) { - int cpu, ret; + int i, ret; /* * Set some basic configurations plus sanity check. */ - init_test_configurtion(); + ret = init_test_configurtion(); + if (ret < 0) + return; /* * Put on hold all workers. */ down_write(&prepare_for_test_rwsem); - for_each_cpu(cpu, &cpus_run_test_mask) { - struct test_driver *t = &per_cpu_test_driver[cpu]; + for (i = 0; i < nr_threads; i++) { + struct test_driver *t = &tdriver[i]; - t->cpu = cpu; - t->task = kthread_run(test_func, t, "vmalloc_test/%d", cpu); + t->task = kthread_run(test_func, t, "vmalloc_test/%d", i); if (!IS_ERR(t->task)) /* Success. */ atomic_inc(&test_n_undone); else - pr_err("Failed to start kthread for %d CPU\n", cpu); + pr_err("Failed to start %d kthread\n", i); } /* @@ -541,29 +531,31 @@ static void do_concurrent_test(void) ret = wait_for_completion_timeout(&test_all_done_comp, HZ); } while (!ret); - for_each_cpu(cpu, &cpus_run_test_mask) { - struct test_driver *t = &per_cpu_test_driver[cpu]; - int i; + for (i = 0; i < nr_threads; i++) { + struct test_driver *t = &tdriver[i]; + int j; if (!IS_ERR(t->task)) kthread_stop(t->task); - for (i = 0; i < ARRAY_SIZE(test_case_array); i++) { - if (!((run_test_mask & (1 << i)) >> i)) + for (j = 0; j < ARRAY_SIZE(test_case_array); j++) { + if (!((run_test_mask & (1 << j)) >> j)) continue; pr_info( "Summary: %s passed: %d failed: %d repeat: %d loops: %d avg: %llu usec\n", - test_case_array[i].test_name, - per_cpu_test_data[cpu][i].test_passed, - per_cpu_test_data[cpu][i].test_failed, + test_case_array[j].test_name, + t->data[j].test_passed, + t->data[j].test_failed, test_repeat_count, test_loop_count, - per_cpu_test_data[cpu][i].time); + t->data[j].time); } - pr_info("All test took CPU%d=%lu cycles\n", - cpu, t->stop - t->start); + pr_info("All test took worker%d=%lu cycles\n", + i, t->stop - t->start); } + + kvfree(tdriver); } static int vmalloc_test_init(void) -- cgit v1.2.3 From aa5c219c60ccb75b50c16329885b65c275172e4a Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 29 Apr 2021 22:59:59 -0700 Subject: kasan: init memory in kasan_(un)poison for HW_TAGS This change adds an argument to kasan_poison() and kasan_unpoison() that allows initializing memory along with setting the tags for HW_TAGS. Combining setting allocation tags with memory initialization will improve HW_TAGS KASAN performance when init_on_alloc/free is enabled. This change doesn't integrate memory initialization with KASAN, this is done is subsequent patches in this series. Link: https://lkml.kernel.org/r/3054314039fa64510947e674180d675cab1b4c41.1615296150.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Joonsoo Kim Cc: Kevin Brodsky Cc: Pekka Enberg Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 4 ++-- mm/kasan/common.c | 28 ++++++++++++++-------------- mm/kasan/generic.c | 12 ++++++------ mm/kasan/kasan.h | 14 ++++++++------ mm/kasan/shadow.c | 10 +++++----- mm/kasan/sw_tags.c | 2 +- 6 files changed, 36 insertions(+), 34 deletions(-) (limited to 'lib') diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 785e724ce0d8..0882d6c17e62 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -1049,14 +1049,14 @@ static void match_all_mem_tag(struct kunit *test) continue; /* Mark the first memory granule with the chosen memory tag. */ - kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag); + kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag, false); /* This access must cause a KASAN report. */ KUNIT_EXPECT_KASAN_FAIL(test, *ptr = 0); } /* Recover the memory tag and free. */ - kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr)); + kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr), false); kfree(ptr); } diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 7b53291dafa1..b3d8eb154f59 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -60,7 +60,7 @@ void kasan_disable_current(void) void __kasan_unpoison_range(const void *address, size_t size) { - kasan_unpoison(address, size); + kasan_unpoison(address, size, false); } #ifdef CONFIG_KASAN_STACK @@ -69,7 +69,7 @@ void kasan_unpoison_task_stack(struct task_struct *task) { void *base = task_stack_page(task); - kasan_unpoison(base, THREAD_SIZE); + kasan_unpoison(base, THREAD_SIZE, false); } /* Unpoison the stack for the current task beyond a watermark sp value. */ @@ -82,7 +82,7 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark) */ void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1)); - kasan_unpoison(base, watermark - base); + kasan_unpoison(base, watermark - base, false); } #endif /* CONFIG_KASAN_STACK */ @@ -108,14 +108,14 @@ void __kasan_alloc_pages(struct page *page, unsigned int order) tag = kasan_random_tag(); for (i = 0; i < (1 << order); i++) page_kasan_tag_set(page + i, tag); - kasan_unpoison(page_address(page), PAGE_SIZE << order); + kasan_unpoison(page_address(page), PAGE_SIZE << order, false); } void __kasan_free_pages(struct page *page, unsigned int order) { if (likely(!PageHighMem(page))) kasan_poison(page_address(page), PAGE_SIZE << order, - KASAN_FREE_PAGE); + KASAN_FREE_PAGE, false); } /* @@ -251,18 +251,18 @@ void __kasan_poison_slab(struct page *page) for (i = 0; i < compound_nr(page); i++) page_kasan_tag_reset(page + i); kasan_poison(page_address(page), page_size(page), - KASAN_KMALLOC_REDZONE); + KASAN_KMALLOC_REDZONE, false); } void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object) { - kasan_unpoison(object, cache->object_size); + kasan_unpoison(object, cache->object_size, false); } void __kasan_poison_object_data(struct kmem_cache *cache, void *object) { kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), - KASAN_KMALLOC_REDZONE); + KASAN_KMALLOC_REDZONE, false); } /* @@ -351,7 +351,7 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, } kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), - KASAN_KMALLOC_FREE); + KASAN_KMALLOC_FREE, false); if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine)) return false; @@ -407,7 +407,7 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) if (unlikely(!PageSlab(page))) { if (____kasan_kfree_large(ptr, ip)) return; - kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE); + kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE, false); } else { ____kasan_slab_free(page->slab_cache, ptr, ip, false); } @@ -453,7 +453,7 @@ void * __must_check __kasan_slab_alloc(struct kmem_cache *cache, * Unpoison the whole object. * For kmalloc() allocations, kasan_kmalloc() will do precise poisoning. */ - kasan_unpoison(tagged_object, cache->object_size); + kasan_unpoison(tagged_object, cache->object_size, false); /* Save alloc info (if possible) for non-kmalloc() allocations. */ if (kasan_stack_collection_enabled()) @@ -496,7 +496,7 @@ static inline void *____kasan_kmalloc(struct kmem_cache *cache, redzone_end = round_up((unsigned long)(object + cache->object_size), KASAN_GRANULE_SIZE); kasan_poison((void *)redzone_start, redzone_end - redzone_start, - KASAN_KMALLOC_REDZONE); + KASAN_KMALLOC_REDZONE, false); /* * Save alloc info (if possible) for kmalloc() allocations. @@ -546,7 +546,7 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, KASAN_GRANULE_SIZE); redzone_end = (unsigned long)ptr + page_size(virt_to_page(ptr)); kasan_poison((void *)redzone_start, redzone_end - redzone_start, - KASAN_PAGE_REDZONE); + KASAN_PAGE_REDZONE, false); return (void *)ptr; } @@ -563,7 +563,7 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag * Part of it might already have been unpoisoned, but it's unknown * how big that part is. */ - kasan_unpoison(object, size); + kasan_unpoison(object, size, false); page = virt_to_head_page(object); diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 2e55e0f82f39..53cbf28859b5 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -208,11 +208,11 @@ static void register_global(struct kasan_global *global) { size_t aligned_size = round_up(global->size, KASAN_GRANULE_SIZE); - kasan_unpoison(global->beg, global->size); + kasan_unpoison(global->beg, global->size, false); kasan_poison(global->beg + aligned_size, global->size_with_redzone - aligned_size, - KASAN_GLOBAL_REDZONE); + KASAN_GLOBAL_REDZONE, false); } void __asan_register_globals(struct kasan_global *globals, size_t size) @@ -292,11 +292,11 @@ void __asan_alloca_poison(unsigned long addr, size_t size) WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE)); kasan_unpoison((const void *)(addr + rounded_down_size), - size - rounded_down_size); + size - rounded_down_size, false); kasan_poison(left_redzone, KASAN_ALLOCA_REDZONE_SIZE, - KASAN_ALLOCA_LEFT); + KASAN_ALLOCA_LEFT, false); kasan_poison(right_redzone, padding_size + KASAN_ALLOCA_REDZONE_SIZE, - KASAN_ALLOCA_RIGHT); + KASAN_ALLOCA_RIGHT, false); } EXPORT_SYMBOL(__asan_alloca_poison); @@ -306,7 +306,7 @@ void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom) if (unlikely(!stack_top || stack_top > stack_bottom)) return; - kasan_unpoison(stack_top, stack_bottom - stack_top); + kasan_unpoison(stack_top, stack_bottom - stack_top, false); } EXPORT_SYMBOL(__asan_allocas_unpoison); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 0583033a7df6..071c456a3579 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -359,7 +359,7 @@ static inline u8 kasan_random_tag(void) { return 0; } #ifdef CONFIG_KASAN_HW_TAGS -static inline void kasan_poison(const void *addr, size_t size, u8 value) +static inline void kasan_poison(const void *addr, size_t size, u8 value, bool init) { addr = kasan_reset_tag(addr); @@ -372,10 +372,10 @@ static inline void kasan_poison(const void *addr, size_t size, u8 value) if (WARN_ON(size & KASAN_GRANULE_MASK)) return; - hw_set_mem_tag_range((void *)addr, size, value, false); + hw_set_mem_tag_range((void *)addr, size, value, init); } -static inline void kasan_unpoison(const void *addr, size_t size) +static inline void kasan_unpoison(const void *addr, size_t size, bool init) { u8 tag = get_tag(addr); @@ -389,7 +389,7 @@ static inline void kasan_unpoison(const void *addr, size_t size) return; size = round_up(size, KASAN_GRANULE_SIZE); - hw_set_mem_tag_range((void *)addr, size, tag, false); + hw_set_mem_tag_range((void *)addr, size, tag, init); } static inline bool kasan_byte_accessible(const void *addr) @@ -407,22 +407,24 @@ static inline bool kasan_byte_accessible(const void *addr) * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE * @size - range size, must be aligned to KASAN_GRANULE_SIZE * @value - value that's written to metadata for the range + * @init - whether to initialize the memory range (only for hardware tag-based) * * The size gets aligned to KASAN_GRANULE_SIZE before marking the range. */ -void kasan_poison(const void *addr, size_t size, u8 value); +void kasan_poison(const void *addr, size_t size, u8 value, bool init); /** * kasan_unpoison - mark the memory range as accessible * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE * @size - range size, can be unaligned + * @init - whether to initialize the memory range (only for hardware tag-based) * * For the tag-based modes, the @size gets aligned to KASAN_GRANULE_SIZE before * marking the range. * For the generic mode, the last granule of the memory range gets partially * unpoisoned based on the @size. */ -void kasan_unpoison(const void *addr, size_t size); +void kasan_unpoison(const void *addr, size_t size, bool init); bool kasan_byte_accessible(const void *addr); diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 63f43443f5d7..727ad4629173 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -69,7 +69,7 @@ void *memcpy(void *dest, const void *src, size_t len) return __memcpy(dest, src, len); } -void kasan_poison(const void *addr, size_t size, u8 value) +void kasan_poison(const void *addr, size_t size, u8 value, bool init) { void *shadow_start, *shadow_end; @@ -106,7 +106,7 @@ void kasan_poison_last_granule(const void *addr, size_t size) } #endif -void kasan_unpoison(const void *addr, size_t size) +void kasan_unpoison(const void *addr, size_t size, bool init) { u8 tag = get_tag(addr); @@ -129,7 +129,7 @@ void kasan_unpoison(const void *addr, size_t size) return; /* Unpoison all granules that cover the object. */ - kasan_poison(addr, round_up(size, KASAN_GRANULE_SIZE), tag); + kasan_poison(addr, round_up(size, KASAN_GRANULE_SIZE), tag, false); /* Partially poison the last granule for the generic mode. */ if (IS_ENABLED(CONFIG_KASAN_GENERIC)) @@ -344,7 +344,7 @@ void kasan_poison_vmalloc(const void *start, unsigned long size) return; size = round_up(size, KASAN_GRANULE_SIZE); - kasan_poison(start, size, KASAN_VMALLOC_INVALID); + kasan_poison(start, size, KASAN_VMALLOC_INVALID, false); } void kasan_unpoison_vmalloc(const void *start, unsigned long size) @@ -352,7 +352,7 @@ void kasan_unpoison_vmalloc(const void *start, unsigned long size) if (!is_vmalloc_or_module_addr(start)) return; - kasan_unpoison(start, size); + kasan_unpoison(start, size, false); } static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index 00ae8913fc74..9df8e7f69e87 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -163,7 +163,7 @@ EXPORT_SYMBOL(__hwasan_storeN_noabort); void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size) { - kasan_poison((void *)addr, size, tag); + kasan_poison((void *)addr, size, tag, false); } EXPORT_SYMBOL(__hwasan_tag_memory); -- cgit v1.2.3 From 99734b535d9bf8d5826be8f8f3719dfc586c3452 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 29 Apr 2021 23:00:49 -0700 Subject: kasan: detect false-positives in tests Currently, KASAN-KUnit tests can check that a particular annotated part of code causes a KASAN report. However, they do not check that no unwanted reports happen between the annotated parts. This patch implements these checks. It is done by setting report_data.report_found to false in kasan_test_init() and at the end of KUNIT_EXPECT_KASAN_FAIL() and then checking that it remains false at the beginning of KUNIT_EXPECT_KASAN_FAIL() and in kasan_test_exit(). kunit_add_named_resource() call is moved to kasan_test_init(), and the value of fail_data.report_expected is kept as false in between KUNIT_EXPECT_KASAN_FAIL() annotations for consistency. Link: https://lkml.kernel.org/r/48079c52cc329fbc52f4386996598d58022fb872.1617207873.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 55 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 26 deletions(-) (limited to 'lib') diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 0882d6c17e62..dc05cfc2d12f 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -54,6 +54,10 @@ static int kasan_test_init(struct kunit *test) multishot = kasan_save_enable_multi_shot(); kasan_set_tagging_report_once(false); + fail_data.report_found = false; + fail_data.report_expected = false; + kunit_add_named_resource(test, NULL, NULL, &resource, + "kasan_data", &fail_data); return 0; } @@ -61,6 +65,7 @@ static void kasan_test_exit(struct kunit *test) { kasan_set_tagging_report_once(true); kasan_restore_multi_shot(multishot); + KUNIT_EXPECT_FALSE(test, fail_data.report_found); } /** @@ -78,33 +83,31 @@ static void kasan_test_exit(struct kunit *test) * fields, it can reorder or optimize away the accesses to those fields. * Use READ/WRITE_ONCE() for the accesses and compiler barriers around the * expression to prevent that. + * + * In between KUNIT_EXPECT_KASAN_FAIL checks, fail_data.report_found is kept as + * false. This allows detecting KASAN reports that happen outside of the checks + * by asserting !fail_data.report_found at the start of KUNIT_EXPECT_KASAN_FAIL + * and in kasan_test_exit. */ -#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do { \ - if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \ - !kasan_async_mode_enabled()) \ - migrate_disable(); \ - WRITE_ONCE(fail_data.report_expected, true); \ - WRITE_ONCE(fail_data.report_found, false); \ - kunit_add_named_resource(test, \ - NULL, \ - NULL, \ - &resource, \ - "kasan_data", &fail_data); \ - barrier(); \ - expression; \ - barrier(); \ - if (kasan_async_mode_enabled()) \ - kasan_force_async_fault(); \ - barrier(); \ - KUNIT_EXPECT_EQ(test, \ - READ_ONCE(fail_data.report_expected), \ - READ_ONCE(fail_data.report_found)); \ - if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \ - !kasan_async_mode_enabled()) { \ - if (READ_ONCE(fail_data.report_found)) \ - kasan_enable_tagging_sync(); \ - migrate_enable(); \ - } \ +#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do { \ + if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \ + !kasan_async_mode_enabled()) \ + migrate_disable(); \ + KUNIT_EXPECT_FALSE(test, READ_ONCE(fail_data.report_found)); \ + WRITE_ONCE(fail_data.report_expected, true); \ + barrier(); \ + expression; \ + barrier(); \ + KUNIT_EXPECT_EQ(test, \ + READ_ONCE(fail_data.report_expected), \ + READ_ONCE(fail_data.report_found)); \ + if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) { \ + if (READ_ONCE(fail_data.report_found)) \ + kasan_enable_tagging_sync(); \ + migrate_enable(); \ + } \ + WRITE_ONCE(fail_data.report_found, false); \ + WRITE_ONCE(fail_data.report_expected, false); \ } while (0) #define KASAN_TEST_NEEDS_CONFIG_ON(test, config) do { \ -- cgit v1.2.3 From 9009b455811b0fa1f6b0adfa94db136984db5a38 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 30 Apr 2021 11:03:08 +0900 Subject: .gitignore: prefix local generated files with a slash The pattern prefixed with '/' matches files in the same directory, but not ones in sub-directories. Signed-off-by: Masahiro Yamada Acked-by: Miguel Ojeda Acked-by: Rob Herring Acked-by: Andra Paraschiv Acked-by: Greg Kroah-Hartman Acked-by: Gabriel Krisman Bertazi --- Documentation/devicetree/bindings/.gitignore | 4 ++-- arch/.gitignore | 4 ++-- certs/.gitignore | 4 ++-- drivers/memory/.gitignore | 2 +- drivers/tty/vt/.gitignore | 6 +++--- fs/unicode/.gitignore | 4 ++-- kernel/.gitignore | 2 +- lib/.gitignore | 10 +++++----- samples/auxdisplay/.gitignore | 2 +- samples/binderfs/.gitignore | 3 ++- samples/connector/.gitignore | 2 +- samples/hidraw/.gitignore | 2 +- samples/mei/.gitignore | 2 +- samples/nitro_enclaves/.gitignore | 2 +- samples/pidfd/.gitignore | 2 +- samples/seccomp/.gitignore | 8 ++++---- samples/timers/.gitignore | 2 +- samples/vfs/.gitignore | 4 ++-- samples/watch_queue/.gitignore | 3 ++- samples/watchdog/.gitignore | 2 +- scripts/.gitignore | 18 +++++++++--------- scripts/basic/.gitignore | 2 +- scripts/dtc/.gitignore | 4 ++-- scripts/gcc-plugins/.gitignore | 2 +- scripts/genksyms/.gitignore | 2 +- scripts/mod/.gitignore | 8 ++++---- usr/.gitignore | 4 ++-- 27 files changed, 56 insertions(+), 54 deletions(-) (limited to 'lib') diff --git a/Documentation/devicetree/bindings/.gitignore b/Documentation/devicetree/bindings/.gitignore index 3a05b99bfa26..a77719968a7e 100644 --- a/Documentation/devicetree/bindings/.gitignore +++ b/Documentation/devicetree/bindings/.gitignore @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only *.example.dts -processed-schema*.yaml -processed-schema*.json +/processed-schema*.yaml +/processed-schema*.json diff --git a/arch/.gitignore b/arch/.gitignore index 4191da401dbb..756c19c34f99 100644 --- a/arch/.gitignore +++ b/arch/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -i386 -x86_64 +/i386/ +/x86_64/ diff --git a/certs/.gitignore b/certs/.gitignore index 6cbd1f1a5837..8c3763f80be3 100644 --- a/certs/.gitignore +++ b/certs/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -x509_certificate_list -x509_revocation_list +/x509_certificate_list +/x509_revocation_list diff --git a/drivers/memory/.gitignore b/drivers/memory/.gitignore index caedc4c7d2db..5e84bee05ef8 100644 --- a/drivers/memory/.gitignore +++ b/drivers/memory/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -ti-emif-asm-offsets.h +/ti-emif-asm-offsets.h diff --git a/drivers/tty/vt/.gitignore b/drivers/tty/vt/.gitignore index 3ecf42234d89..0221709b177d 100644 --- a/drivers/tty/vt/.gitignore +++ b/drivers/tty/vt/.gitignore @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -conmakehash -consolemap_deftbl.c -defkeymap.c +/conmakehash +/consolemap_deftbl.c +/defkeymap.c diff --git a/fs/unicode/.gitignore b/fs/unicode/.gitignore index 9b2467e77b2d..361294571ab0 100644 --- a/fs/unicode/.gitignore +++ b/fs/unicode/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -mkutf8data -utf8data.h +/mkutf8data +/utf8data.h diff --git a/kernel/.gitignore b/kernel/.gitignore index dafdce3d18c5..c6b299a6b786 100644 --- a/kernel/.gitignore +++ b/kernel/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only /config_data -kheaders.md5 +/kheaders.md5 diff --git a/lib/.gitignore b/lib/.gitignore index 327cb2c7f2c9..5e7fa54c4536 100644 --- a/lib/.gitignore +++ b/lib/.gitignore @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -gen_crc32table -gen_crc64table -crc32table.h -crc64table.h -oid_registry_data.c +/crc32table.h +/crc64table.h +/gen_crc32table +/gen_crc64table +/oid_registry_data.c diff --git a/samples/auxdisplay/.gitignore b/samples/auxdisplay/.gitignore index 2ed744c0e741..d023816849bd 100644 --- a/samples/auxdisplay/.gitignore +++ b/samples/auxdisplay/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -cfag12864b-example +/cfag12864b-example diff --git a/samples/binderfs/.gitignore b/samples/binderfs/.gitignore index eb60241e8087..8fa415a3640b 100644 --- a/samples/binderfs/.gitignore +++ b/samples/binderfs/.gitignore @@ -1 +1,2 @@ -binderfs_example +# SPDX-License-Identifier: GPL-2.0 +/binderfs_example diff --git a/samples/connector/.gitignore b/samples/connector/.gitignore index d86f2ff9c947..0e26039f39b5 100644 --- a/samples/connector/.gitignore +++ b/samples/connector/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -ucon +/ucon diff --git a/samples/hidraw/.gitignore b/samples/hidraw/.gitignore index d7a6074ebcf9..5233ab63262e 100644 --- a/samples/hidraw/.gitignore +++ b/samples/hidraw/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -hid-example +/hid-example diff --git a/samples/mei/.gitignore b/samples/mei/.gitignore index db5e802f041e..fe894bcb6a62 100644 --- a/samples/mei/.gitignore +++ b/samples/mei/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -mei-amt-version +/mei-amt-version diff --git a/samples/nitro_enclaves/.gitignore b/samples/nitro_enclaves/.gitignore index 827934129c90..6a718eec71f4 100644 --- a/samples/nitro_enclaves/.gitignore +++ b/samples/nitro_enclaves/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -ne_ioctl_sample +/ne_ioctl_sample diff --git a/samples/pidfd/.gitignore b/samples/pidfd/.gitignore index eea857fca736..d4cfa3176b1b 100644 --- a/samples/pidfd/.gitignore +++ b/samples/pidfd/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -pidfd-metadata +/pidfd-metadata diff --git a/samples/seccomp/.gitignore b/samples/seccomp/.gitignore index 4a5a5b7db30b..a6df0da77c5d 100644 --- a/samples/seccomp/.gitignore +++ b/samples/seccomp/.gitignore @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -bpf-direct -bpf-fancy -dropper -user-trap +/bpf-direct +/bpf-fancy +/dropper +/user-trap diff --git a/samples/timers/.gitignore b/samples/timers/.gitignore index 40510c33cf08..cd9ff7b95383 100644 --- a/samples/timers/.gitignore +++ b/samples/timers/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -hpet_example +/hpet_example diff --git a/samples/vfs/.gitignore b/samples/vfs/.gitignore index 8fdabf7e5373..79212d91285b 100644 --- a/samples/vfs/.gitignore +++ b/samples/vfs/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -test-fsmount -test-statx +/test-fsmount +/test-statx diff --git a/samples/watch_queue/.gitignore b/samples/watch_queue/.gitignore index 2aa3c7e56a1a..823b351d3db9 100644 --- a/samples/watch_queue/.gitignore +++ b/samples/watch_queue/.gitignore @@ -1 +1,2 @@ -watch_test +# SPDX-License-Identifier: GPL-2.0-only +/watch_test diff --git a/samples/watchdog/.gitignore b/samples/watchdog/.gitignore index 74153b831244..a70a0150ed9f 100644 --- a/samples/watchdog/.gitignore +++ b/samples/watchdog/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -watchdog-simple +/watchdog-simple diff --git a/scripts/.gitignore b/scripts/.gitignore index a6c11316c969..e83c620ef52c 100644 --- a/scripts/.gitignore +++ b/scripts/.gitignore @@ -1,11 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only -bin2c -kallsyms -unifdef -recordmcount -sorttable -asn1_compiler -extract-cert -sign-file -insert-sys-cert +/asn1_compiler +/bin2c +/extract-cert +/insert-sys-cert +/kallsyms /module.lds +/recordmcount +/sign-file +/sorttable +/unifdef diff --git a/scripts/basic/.gitignore b/scripts/basic/.gitignore index 98ae1f509592..961c91c8a884 100644 --- a/scripts/basic/.gitignore +++ b/scripts/basic/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -fixdep +/fixdep diff --git a/scripts/dtc/.gitignore b/scripts/dtc/.gitignore index 8a8b62bf3d3c..e0b5c1d2464a 100644 --- a/scripts/dtc/.gitignore +++ b/scripts/dtc/.gitignore @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -dtc -fdtoverlay +/dtc +/fdtoverlay diff --git a/scripts/gcc-plugins/.gitignore b/scripts/gcc-plugins/.gitignore index b04e0f0f033e..5cc385b9eb97 100644 --- a/scripts/gcc-plugins/.gitignore +++ b/scripts/gcc-plugins/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -randomize_layout_seed.h +/randomize_layout_seed.h diff --git a/scripts/genksyms/.gitignore b/scripts/genksyms/.gitignore index 999af710f83d..0b275abf9405 100644 --- a/scripts/genksyms/.gitignore +++ b/scripts/genksyms/.gitignore @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -genksyms +/genksyms diff --git a/scripts/mod/.gitignore b/scripts/mod/.gitignore index 07e4a39f90a6..0465ec33c9bf 100644 --- a/scripts/mod/.gitignore +++ b/scripts/mod/.gitignore @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -elfconfig.h -mk_elfconfig -modpost -devicetable-offsets.h +/devicetable-offsets.h +/elfconfig.h +/mk_elfconfig +/modpost diff --git a/usr/.gitignore b/usr/.gitignore index 935442ed1eb2..8996e7a88902 100644 --- a/usr/.gitignore +++ b/usr/.gitignore @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -gen_init_cpio -initramfs_data.cpio +/gen_init_cpio +/initramfs_data.cpio /initramfs_inc_data -- cgit v1.2.3 From c13656b904b6173aad723d9680a81c60de2f5edc Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 15 Mar 2021 10:13:55 +0100 Subject: lib: bitmap: order includes alphabetically For better readability and maintenance: order the includes in bitmap source files alphabetically. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko --- include/linux/bitmap.h | 4 ++-- lib/bitmap.c | 9 +++++---- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 6939a8983026..3282db97e06c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -4,10 +4,10 @@ #ifndef __ASSEMBLY__ -#include #include -#include #include +#include +#include /* * bitmaps provide bit arrays that consume one or more unsigned diff --git a/lib/bitmap.c b/lib/bitmap.c index 75006c4036e9..78f70d9007ad 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -3,17 +3,18 @@ * lib/bitmap.c * Helper functions for bitmap.h. */ -#include -#include -#include -#include + #include #include #include +#include +#include +#include #include #include #include #include +#include #include #include -- cgit v1.2.3 From e829c2e4744850bab4d8f8ffebd00df10b4c6c2b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 15 Mar 2021 10:13:56 +0100 Subject: lib: bitmap: provide devm_bitmap_alloc() and devm_bitmap_zalloc() Provide managed variants of bitmap_alloc() and bitmap_zalloc(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko --- include/linux/bitmap.h | 8 ++++++++ lib/bitmap.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'lib') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3282db97e06c..73d039476fa4 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -9,6 +9,8 @@ #include #include +struct device; + /* * bitmaps provide bit arrays that consume one or more unsigned * longs. The bitmap interface and available operations are listed @@ -122,6 +124,12 @@ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); void bitmap_free(const unsigned long *bitmap); +/* Managed variants of the above. */ +unsigned long *devm_bitmap_alloc(struct device *dev, + unsigned int nbits, gfp_t flags); +unsigned long *devm_bitmap_zalloc(struct device *dev, + unsigned int nbits, gfp_t flags); + /* * lib/bitmap.c provides these functions: */ diff --git a/lib/bitmap.c b/lib/bitmap.c index 78f70d9007ad..27e08c0e547e 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -1263,6 +1264,38 @@ void bitmap_free(const unsigned long *bitmap) } EXPORT_SYMBOL(bitmap_free); +static void devm_bitmap_free(void *data) +{ + unsigned long *bitmap = data; + + bitmap_free(bitmap); +} + +unsigned long *devm_bitmap_alloc(struct device *dev, + unsigned int nbits, gfp_t flags) +{ + unsigned long *bitmap; + int ret; + + bitmap = bitmap_alloc(nbits, flags); + if (!bitmap) + return NULL; + + ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); + if (ret) + return NULL; + + return bitmap; +} +EXPORT_SYMBOL_GPL(devm_bitmap_alloc); + +unsigned long *devm_bitmap_zalloc(struct device *dev, + unsigned int nbits, gfp_t flags) +{ + return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); +} +EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); + #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap -- cgit v1.2.3 From 65dd36a39d3b350dc96d8324b348f0863d76404d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 1 Mar 2021 18:59:31 +0200 Subject: lib/cmdline: Export next_arg() for being used in modules At least one module will benefit from using next_arg() helper. Let's export it for that module and others if they consider it helpful. Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij Reviewed-by: Geert Uytterhoeven --- lib/cmdline.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/cmdline.c b/lib/cmdline.c index 5d474c626e24..5546bf588780 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -272,3 +272,4 @@ char *next_arg(char *args, char **param, char **val) /* Chew up trailing spaces. */ return skip_spaces(args); } +EXPORT_SYMBOL(next_arg); -- cgit v1.2.3 From 28961998f858114e51d2ae862065b858afcfa2b2 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 4 May 2021 18:40:03 -0700 Subject: iov_iter: lift memzero_page() to highmem.h Patch series "btrfs: Convert kmap/memset/kunmap to memzero_user()". Lifting memzero_user(), convert it to kmap_local_page() and then use it in btrfs. This patch (of 3): memzero_page() can replace the kmap/memset/kunmap pattern in other places in the code. While zero_user() has the same interface it is not the same call and its use should be limited and some of those calls may be better converted from zero_user() to memzero_page().[1] But that is not addressed in this series. Lift memzero_page() to highmem. [1] https://lore.kernel.org/lkml/CAHk-=wijdojzo56FzYqE5TOYw2Vws7ik3LEMGj9SPQaJJ+Z73Q@mail.gmail.com/ Link: https://lkml.kernel.org/r/20210309212137.2610186-1-ira.weiny@intel.com Link: https://lkml.kernel.org/r/20210309212137.2610186-2-ira.weiny@intel.com Signed-off-by: Ira Weiny Cc: Alexander Viro Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: Chaitanya Kulkarni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 7 +++++++ lib/iov_iter.c | 8 +------- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 44170f312ae7..832b49b50c7b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -332,4 +332,11 @@ static inline void memcpy_to_page(struct page *page, size_t offset, kunmap_local(to); } +static inline void memzero_page(struct page *page, size_t offset, size_t len) +{ + char *addr = kmap_atomic(page); + memset(addr + offset, 0, len); + kunmap_atomic(addr); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 61228a6c69f8..c701b7a187f2 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -507,13 +508,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_init); -static void memzero_page(struct page *page, size_t offset, size_t len) -{ - char *addr = kmap_atomic(page); - memset(addr + offset, 0, len); - kunmap_atomic(addr); -} - static inline bool allocated(struct pipe_buffer *buf) { return buf->ops == &default_pipe_buf_ops; -- cgit v1.2.3 From 407f1d8c1b5f3ec66a6a3eb835d3b81c76440f4e Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 4 May 2021 18:40:21 -0700 Subject: kfence: await for allocation using wait_event Patch series "kfence: optimize timer scheduling", v2. We have observed that mostly-idle systems with KFENCE enabled wake up otherwise idle CPUs, preventing such to enter a lower power state. Debugging revealed that KFENCE spends too much active time in toggle_allocation_gate(). While the first version of KFENCE was using all the right bits to be scheduling optimal, and thus power efficient, by simply using wait_event() + wake_up(), that code was unfortunately removed. As KFENCE was exposed to various different configs and tests, the scheduling optimal code slowly disappeared. First because of hung task warnings, and finally because of deadlocks when an allocation is made by timer code with debug objects enabled. Clearly, the "fixes" were not too friendly for devices that want to be power efficient. Therefore, let's try a little harder to fix the hung task and deadlock problems that we have with wait_event() + wake_up(), while remaining as scheduling friendly and power efficient as possible. Crucially, we need to defer the wake_up() to an irq_work, avoiding any potential for deadlock. The result with this series is that on the devices where we observed a power regression, power usage returns back to baseline levels. This patch (of 3): On mostly-idle systems, we have observed that toggle_allocation_gate() is a cause of frequent wake-ups, preventing an otherwise idle CPU to go into a lower power state. A late change in KFENCE's development, due to a potential deadlock [1], required changing the scheduling-friendly wait_event_timeout() and wake_up() to an open-coded wait-loop using schedule_timeout(). [1] https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com To avoid unnecessary wake-ups, switch to using wait_event_timeout(). Unfortunately, we still cannot use a version with direct wake_up() in __kfence_alloc() due to the same potential for deadlock as in [1]. Instead, add a level of indirection via an irq_work that is scheduled if we determine that the kfence_timer requires a wake_up(). Link: https://lkml.kernel.org/r/20210421105132.3965998-1-elver@google.com Link: https://lkml.kernel.org/r/20210421105132.3965998-2-elver@google.com Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Cc: Mark Rutland Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.kfence | 1 + mm/kfence/core.c | 45 +++++++++++++++++++++++++++++---------------- 2 files changed, 30 insertions(+), 16 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence index 78f50ccb3b45..e641add33947 100644 --- a/lib/Kconfig.kfence +++ b/lib/Kconfig.kfence @@ -7,6 +7,7 @@ menuconfig KFENCE bool "KFENCE: low-overhead sampling-based memory safety error detector" depends on HAVE_ARCH_KFENCE && (SLAB || SLUB) select STACKTRACE + select IRQ_WORK help KFENCE is a low-overhead sampling-based detector of heap out-of-bounds access, use-after-free, and invalid-free errors. KFENCE is designed diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 768dbd58170d..235d726f88bc 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -587,6 +588,17 @@ late_initcall(kfence_debugfs_init); /* === Allocation Gate Timer ================================================ */ +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* Wait queue to wake up allocation-gate timer task. */ +static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); + +static void wake_up_kfence_timer(struct irq_work *work) +{ + wake_up(&allocation_wait); +} +static DEFINE_IRQ_WORK(wake_up_kfence_timer_work, wake_up_kfence_timer); +#endif + /* * Set up delayed work, which will enable and disable the static key. We need to * use a work queue (rather than a simple timer), since enabling and disabling a @@ -604,25 +616,13 @@ static void toggle_allocation_gate(struct work_struct *work) if (!READ_ONCE(kfence_enabled)) return; - /* Enable static key, and await allocation to happen. */ atomic_set(&kfence_allocation_gate, 0); #ifdef CONFIG_KFENCE_STATIC_KEYS + /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); - /* - * Await an allocation. Timeout after 1 second, in case the kernel stops - * doing allocations, to avoid stalling this worker task for too long. - */ - { - unsigned long end_wait = jiffies + HZ; - - do { - set_current_state(TASK_UNINTERRUPTIBLE); - if (atomic_read(&kfence_allocation_gate) != 0) - break; - schedule_timeout(1); - } while (time_before(jiffies, end_wait)); - __set_current_state(TASK_RUNNING); - } + + wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), HZ); + /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); #endif @@ -729,6 +729,19 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) */ if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; +#ifdef CONFIG_KFENCE_STATIC_KEYS + /* + * waitqueue_active() is fully ordered after the update of + * kfence_allocation_gate per atomic_inc_return(). + */ + if (waitqueue_active(&allocation_wait)) { + /* + * Calling wake_up() here may deadlock when allocations happen + * from within timer code. Use an irq_work to defer it. + */ + irq_work_queue(&wake_up_kfence_timer_work); + } +#endif if (!READ_ONCE(kfence_enabled)) return NULL; -- cgit v1.2.3 From 2c16db6c92b0ee4aa61e88366df82169e83c3f7e Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Wed, 5 May 2021 09:58:31 -0700 Subject: net: fix nla_strcmp to handle more then one trailing null character Android userspace has been using TCA_KIND with a char[IFNAMESIZ] many-null-terminated buffer containing the string 'bpf'. This works on 4.19 and ceases to work on 5.10. I'm not entirely sure what fixes tag to use, but I think the issue was likely introduced in the below mentioned 5.4 commit. Reported-by: Nucca Chen Cc: Cong Wang Cc: David Ahern Cc: David S. Miller Cc: Jakub Kicinski Cc: Jamal Hadi Salim Cc: Jiri Pirko Cc: Jiri Pirko Fixes: 62794fc4fbf5 ("net_sched: add max len check for TCA_KIND") Change-Id: I66dc281f165a2858fc29a44869a270a2d698a82b Signed-off-by: David S. Miller --- lib/nlattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index 5b6116e81f9f..1d051ef66afe 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -828,7 +828,7 @@ int nla_strcmp(const struct nlattr *nla, const char *str) int attrlen = nla_len(nla); int d; - if (attrlen > 0 && buf[attrlen - 1] == '\0') + while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; -- cgit v1.2.3 From 5c88af59f9abc202648a431428ad9d32e5d2a201 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 6 May 2021 18:03:03 -0700 Subject: lib: inline _find_next_bit() wrappers lib/find_bit.c declares five single-line wrappers for _find_next_bit(). We may turn those wrappers to inline functions. It eliminates unneeded function calls and opens room for compile-time optimizations. Link: https://lkml.kernel.org/r/20210401003153.97325-8-yury.norov@gmail.com Signed-off-by: Yury Norov Acked-by: Rasmus Villemoes Acked-by: Andy Shevchenko Cc: Alexey Klimov Cc: Arnd Bergmann Cc: David Sterba Cc: Dennis Zhou Cc: Geert Uytterhoeven Cc: Jianpeng Ma Cc: Joe Perches Cc: John Paul Adrian Glaubitz Cc: Josh Poimboeuf Cc: Rich Felker Cc: Stefano Brivio Cc: Wei Yang Cc: Wolfram Sang Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bitops/find.h | 28 +++++++++++++++----- include/asm-generic/bitops/le.h | 17 +++++++++--- lib/find_bit.c | 56 ++------------------------------------- 3 files changed, 37 insertions(+), 64 deletions(-) (limited to 'lib') diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 9fdf21302fdf..7ad70dab8e93 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -2,6 +2,10 @@ #ifndef _ASM_GENERIC_BITOPS_FIND_H_ #define _ASM_GENERIC_BITOPS_FIND_H_ +extern unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert, unsigned long le); + #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region @@ -12,8 +16,12 @@ * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -extern unsigned long find_next_bit(const unsigned long *addr, unsigned long - size, unsigned long offset); +static inline +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); +} #endif #ifndef find_next_and_bit @@ -27,9 +35,13 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -extern unsigned long find_next_and_bit(const unsigned long *addr1, +static inline +unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, - unsigned long offset); + unsigned long offset) +{ + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); +} #endif #ifndef find_next_zero_bit @@ -42,8 +54,12 @@ extern unsigned long find_next_and_bit(const unsigned long *addr1, * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ -extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned - long size, unsigned long offset); +static inline +unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); +} #endif #ifdef CONFIG_GENERIC_FIND_FIRST_BIT diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h index 188d3eba3ace..21305f6cea0b 100644 --- a/include/asm-generic/bitops/le.h +++ b/include/asm-generic/bitops/le.h @@ -2,6 +2,7 @@ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ +#include #include #include @@ -32,13 +33,21 @@ static inline unsigned long find_first_zero_bit_le(const void *addr, #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) #ifndef find_next_zero_bit_le -extern unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset); +static inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); +} #endif #ifndef find_next_bit_le -extern unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset); +static inline +unsigned long find_next_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); +} #endif #ifndef find_first_zero_bit_le diff --git a/lib/find_bit.c b/lib/find_bit.c index f67f86fd2f62..b03a101367f8 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -29,7 +29,7 @@ * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ -static unsigned long _find_next_bit(const unsigned long *addr1, +unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { @@ -68,37 +68,7 @@ static unsigned long _find_next_bit(const unsigned long *addr1, return min(start + __ffs(tmp), nbits); } -#endif - -#ifndef find_next_bit -/* - * Find the next set bit in a memory region. - */ -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); -} -EXPORT_SYMBOL(find_next_bit); -#endif - -#ifndef find_next_zero_bit -unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); -} -EXPORT_SYMBOL(find_next_zero_bit); -#endif - -#if !defined(find_next_and_bit) -unsigned long find_next_and_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long size, - unsigned long offset) -{ - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); -} -EXPORT_SYMBOL(find_next_and_bit); +EXPORT_SYMBOL(_find_next_bit); #endif #ifndef find_first_bit @@ -157,28 +127,6 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) EXPORT_SYMBOL(find_last_bit); #endif -#ifdef __BIG_ENDIAN - -#ifndef find_next_zero_bit_le -unsigned long find_next_zero_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); -} -EXPORT_SYMBOL(find_next_zero_bit_le); -#endif - -#ifndef find_next_bit_le -unsigned long find_next_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); -} -EXPORT_SYMBOL(find_next_bit_le); -#endif - -#endif /* __BIG_ENDIAN */ - unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { -- cgit v1.2.3 From 2cc7b6a44ac21d31b398b03f4845c53152070416 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 6 May 2021 18:03:14 -0700 Subject: lib: add fast path for find_first_*_bit() and find_last_bit() Similarly to bitmap functions, users would benefit if we'll handle a case of small-size bitmaps that fit into a single word. While here, move the find_last_bit() declaration to bitops/find.h where other find_*_bit() functions sit. Link: https://lkml.kernel.org/r/20210401003153.97325-11-yury.norov@gmail.com Signed-off-by: Yury Norov Acked-by: Rasmus Villemoes Acked-by: Andy Shevchenko Cc: Alexey Klimov Cc: Arnd Bergmann Cc: David Sterba Cc: Dennis Zhou Cc: Geert Uytterhoeven Cc: Jianpeng Ma Cc: Joe Perches Cc: John Paul Adrian Glaubitz Cc: Josh Poimboeuf Cc: Rich Felker Cc: Stefano Brivio Cc: Wei Yang Cc: Wolfram Sang Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bitops/find.h | 50 +++++++++++++++++++++++++++++++++++---- include/linux/bitops.h | 12 ---------- lib/find_bit.c | 12 +++++----- 3 files changed, 52 insertions(+), 22 deletions(-) (limited to 'lib') diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 4148c74a1e4d..0d132ee2a291 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -5,6 +5,9 @@ extern unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le); +extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** @@ -102,8 +105,17 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ -extern unsigned long find_first_bit(const unsigned long *addr, - unsigned long size); +static inline +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_bit(addr, size); +} /** * find_first_zero_bit - find the first cleared bit in a memory region @@ -113,8 +125,17 @@ extern unsigned long find_first_bit(const unsigned long *addr, * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ -extern unsigned long find_first_zero_bit(const unsigned long *addr, - unsigned long size); +static inline +unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit(addr, size); +} #else /* CONFIG_GENERIC_FIND_FIRST_BIT */ #ifndef find_first_bit @@ -126,6 +147,27 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr, #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ +#ifndef find_last_bit +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The number of bits to search + * + * Returns the bit number of the last set bit, or size. + */ +static inline +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __fls(val) : size; + } + + return _find_last_bit(addr, size); +} +#endif + /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a5a48303b0f1..26bf15e6cd35 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -286,17 +286,5 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, }) #endif -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -extern unsigned long find_last_bit(const unsigned long *addr, - unsigned long size); -#endif - #endif /* __KERNEL__ */ #endif diff --git a/lib/find_bit.c b/lib/find_bit.c index b03a101367f8..0f8e2e369b1d 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -75,7 +75,7 @@ EXPORT_SYMBOL(_find_next_bit); /* * Find the first set bit in a memory region. */ -unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; @@ -86,14 +86,14 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) return size; } -EXPORT_SYMBOL(find_first_bit); +EXPORT_SYMBOL(_find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ -unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; @@ -104,11 +104,11 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) return size; } -EXPORT_SYMBOL(find_first_zero_bit); +EXPORT_SYMBOL(_find_first_zero_bit); #endif #ifndef find_last_bit -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +unsigned long _find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); @@ -124,7 +124,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) } return size; } -EXPORT_SYMBOL(find_last_bit); +EXPORT_SYMBOL(_find_last_bit); #endif unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, -- cgit v1.2.3 From 0523c6922e8bd8d31d3377a56d57730d448b85a8 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Thu, 6 May 2021 18:03:25 -0700 Subject: lib/bch.c: fix a typo in the file bch.c s/buid/build/ Link: https://lkml.kernel.org/r/20210301123129.18754-1-unixbhaskar@gmail.com Signed-off-by: Bhaskar Chowdhury Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/bch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/bch.c b/lib/bch.c index 7c031ee8b93b..c8095f30f254 100644 --- a/lib/bch.c +++ b/lib/bch.c @@ -584,7 +584,7 @@ static int find_affine4_roots(struct bch_control *bch, unsigned int a, k = a_log(bch, a); rows[0] = c; - /* buid linear system to solve X^4+aX^2+bX+c = 0 */ + /* build linear system to solve X^4+aX^2+bX+c = 0 */ for (i = 0; i < m; i++) { rows[i+1] = bch->a_pow_tab[4*i]^ (a ? bch->a_pow_tab[mod_s(bch, k)] : 0)^ -- cgit v1.2.3 From b8cf20277941f6954f12a8d5a54eb334c806a6a3 Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Thu, 6 May 2021 18:03:28 -0700 Subject: lib: fix inconsistent indenting in process_bit1() Smatch gives the warning: lib/decompress_unlzma.c:395 process_bit1() warn: inconsistent indenting Link: https://lkml.kernel.org/r/1614567775-4478-1-git-send-email-wangqing@vivo.com Signed-off-by: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/decompress_unlzma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 1cf409ef8d04..20a858031f12 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -391,7 +391,7 @@ static inline int INIT process_bit0(struct writer *wr, struct rc *rc, static inline int INIT process_bit1(struct writer *wr, struct rc *rc, struct cstate *cst, uint16_t *p, int pos_state, uint16_t *prob) { - int offset; + int offset; uint16_t *prob_len; int num_bits; int len; -- cgit v1.2.3 From e89b6358052de202e53e47623f50b6d28182ccdf Mon Sep 17 00:00:00 2001 From: ToastC Date: Thu, 6 May 2021 18:03:31 -0700 Subject: lib/list_sort.c: fix typo in function description Replace beautiully with beautifully Link: https://lkml.kernel.org/r/20210315090633.9759-1-mrtoastcheng@gmail.com Signed-off-by: ShihCheng Tu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/list_sort.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/list_sort.c b/lib/list_sort.c index a926d96ffd44..1e1e37762799 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -137,7 +137,7 @@ static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, * * * The merging is controlled by "count", the number of elements in the - * pending lists. This is beautiully simple code, but rather subtle. + * pending lists. This is beautifully simple code, but rather subtle. * * Each time we increment "count", we set one bit (bit k) and clear * bits k-1 .. 0. Each time this happens (except the very first time -- cgit v1.2.3 From ade29d4fdbe675d72ee6115baaf3b3382942fd12 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Thu, 6 May 2021 18:03:34 -0700 Subject: lib/genalloc.c: Fix a typo s/macthing/matching/ Link: https://lkml.kernel.org/r/20210326131530.30481-1-unixbhaskar@gmail.com Signed-off-by: Bhaskar Chowdhury Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/genalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/genalloc.c b/lib/genalloc.c index 5dcf9cdcbc46..8273760884a7 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -735,7 +735,7 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align); /** * gen_pool_best_fit - find the best fitting region of memory - * macthing the size requirement (no alignment constraint) + * matching the size requirement (no alignment constraint) * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at -- cgit v1.2.3 From e18baa7cc3598999317d6c2fe255756f6b3b7562 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 6 May 2021 18:03:37 -0700 Subject: lib: crc8: pointer to data block should be const crc8() does not change the data passed to it, so the pointer argument should be declared const. This avoids callers that receive const data having to cast it to a non-const pointer to call crc8(). Link: https://lkml.kernel.org/r/20210329122409.3291-1-rf@opensource.cirrus.com Signed-off-by: Richard Fitzgerald Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crc8.h | 2 +- lib/crc8.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/include/linux/crc8.h b/include/linux/crc8.h index 13c8dabb0441..674045c59a04 100644 --- a/include/linux/crc8.h +++ b/include/linux/crc8.h @@ -96,6 +96,6 @@ void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial); * Williams, Ross N., rossross.net * (see URL http://www.ross.net/crc/download/crc_v3.txt). */ -u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc); +u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc); #endif /* __CRC8_H_ */ diff --git a/lib/crc8.c b/lib/crc8.c index 595a5a75e3cd..1ad8e501d9b6 100644 --- a/lib/crc8.c +++ b/lib/crc8.c @@ -71,7 +71,7 @@ EXPORT_SYMBOL(crc8_populate_lsb); * @nbytes: number of bytes in data buffer. * @crc: previous returned crc8 value. */ -u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc) +u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc) { /* loop over the buffer data */ while (nbytes-- > 0) -- cgit v1.2.3 From 78564b9434878d686c5f88c4488b20cccbcc42bc Mon Sep 17 00:00:00 2001 From: Zqiang Date: Thu, 6 May 2021 18:03:40 -0700 Subject: lib: stackdepot: turn depot_lock spinlock to raw_spinlock In RT system, the spin_lock will be replaced by sleepable rt_mutex lock, in __call_rcu(), disable interrupts before calling kasan_record_aux_stack(), will trigger this calltrace: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:951 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 19, name: pgdatinit0 Call Trace: ___might_sleep.cold+0x1b2/0x1f1 rt_spin_lock+0x3b/0xb0 stack_depot_save+0x1b9/0x440 kasan_save_stack+0x32/0x40 kasan_record_aux_stack+0xa5/0xb0 __call_rcu+0x117/0x880 __exit_signal+0xafb/0x1180 release_task+0x1d6/0x480 exit_notify+0x303/0x750 do_exit+0x678/0xcf0 kthread+0x364/0x4f0 ret_from_fork+0x22/0x30 Replace spinlock with raw_spinlock. Link: https://lkml.kernel.org/r/20210329084009.27013-1-qiang.zhang@windriver.com Signed-off-by: Zqiang Reported-by: Andrew Halaney Cc: Alexander Potapenko Cc: Gustavo A. R. Silva Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Yogesh Lal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/stackdepot.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 49f67a0c6e5d..df9179f4f441 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -71,7 +71,7 @@ static void *stack_slabs[STACK_ALLOC_MAX_SLABS]; static int depot_index; static int next_slab_inited; static size_t depot_offset; -static DEFINE_SPINLOCK(depot_lock); +static DEFINE_RAW_SPINLOCK(depot_lock); static bool init_stack_slab(void **prealloc) { @@ -305,7 +305,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, prealloc = page_address(page); } - spin_lock_irqsave(&depot_lock, flags); + raw_spin_lock_irqsave(&depot_lock, flags); found = find_stack(*bucket, entries, nr_entries, hash); if (!found) { @@ -329,7 +329,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, WARN_ON(!init_stack_slab(&prealloc)); } - spin_unlock_irqrestore(&depot_lock, flags); + raw_spin_unlock_irqrestore(&depot_lock, flags); exit: if (prealloc) { /* Nobody used this memory, ok to free it. */ -- cgit v1.2.3 From db65a867fd40fb33d4a7d619e95f2b796e798999 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Thu, 6 May 2021 18:03:43 -0700 Subject: lib/percpu_counter: tame kernel-doc compile warning commit 3e8f399da490 ("writeback: rework wb_[dec|inc]_stat family of functions") add some function description of percpu_counter_add_batch. but the double '*' in comments means a kernel-doc format comment which isn't right. Since the whole file of lib/percpu_counter.c has no any other kernel-doc format comments, we'd better to remove this incomplete one to tame the kernel-doc warning: lib/percpu_counter.c:83: warning: Function parameter or member 'fbc' not described in 'percpu_counter_add_batch' lib/percpu_counter.c:83: warning: Function parameter or member 'amount' not described in 'percpu_counter_add_batch' lib/percpu_counter.c:83: warning: Function parameter or member 'batch' not described in 'percpu_counter_add_batch' Link: https://lkml.kernel.org/r/20210405135505.132446-1-alexs@kernel.org Signed-off-by: Alex Shi Cc: Nikolay Borisov Cc: Stephen Boyd Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/percpu_counter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 00f666d94486..ed610b75dc32 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,7 +72,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) } EXPORT_SYMBOL(percpu_counter_set); -/** +/* * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses -- cgit v1.2.3 From 9d6ecac093a2412822bdb5376b9bd434d45939af Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Thu, 6 May 2021 18:03:46 -0700 Subject: lib/genalloc: add parameter description to fix doc compile warning Commit 52fbf1134d47 ("lib/genalloc.c: fix allocation of aligned buffer from non-aligned chunk") added a new parameter 'start_addr' w/o description for it. That causes some doc compile warning: lib/genalloc.c:649: warning: Function parameter or member 'start_addr' not described in 'gen_pool_first_fit' lib/genalloc.c:667: warning: Function parameter or member 'start_addr' not described in 'gen_pool_first_fit_align' lib/genalloc.c:694: warning: Function parameter or member 'start_addr' not described in 'gen_pool_fixed_alloc' lib/genalloc.c:729: warning: Function parameter or member 'start_addr' not described in 'gen_pool_first_fit_order_align' lib/genalloc.c:752: warning: Function parameter or member 'start_addr' not described in 'gen_pool_best_fit' This fixes it by adding a parameter descriptions. Link: https://lkml.kernel.org/r/20210405132021.131231-1-alexs@kernel.org Signed-off-by: Alex Shi Cc: Alexey Skidanov Cc: Huang Shijie Cc: Alex Shi Cc: Bhaskar Chowdhury Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/genalloc.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'lib') diff --git a/lib/genalloc.c b/lib/genalloc.c index 8273760884a7..9a57257988c7 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -642,6 +642,7 @@ EXPORT_SYMBOL(gen_pool_set_algo); * @nr: The number of zeroed bits we're looking for * @data: additional data - unused * @pool: pool to find the fit region memory from + * @start_addr: not used in this function */ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data, @@ -660,6 +661,7 @@ EXPORT_SYMBOL(gen_pool_first_fit); * @nr: The number of zeroed bits we're looking for * @data: data for alignment * @pool: pool to get order from + * @start_addr: start addr of alloction chunk */ unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data, @@ -687,6 +689,7 @@ EXPORT_SYMBOL(gen_pool_first_fit_align); * @nr: The number of zeroed bits we're looking for * @data: data for alignment * @pool: pool to get order from + * @start_addr: not used in this function */ unsigned long gen_pool_fixed_alloc(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data, @@ -721,6 +724,7 @@ EXPORT_SYMBOL(gen_pool_fixed_alloc); * @nr: The number of zeroed bits we're looking for * @data: additional data - unused * @pool: pool to find the fit region memory from + * @start_addr: not used in this function */ unsigned long gen_pool_first_fit_order_align(unsigned long *map, unsigned long size, unsigned long start, @@ -742,6 +746,7 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align); * @nr: The number of zeroed bits we're looking for * @data: additional data - unused * @pool: pool to find the fit region memory from + * @start_addr: not used in this function * * Iterate over the bitmap to find the smallest free region * which we can allocate the memory. -- cgit v1.2.3 From edd9334c8dfed7341066a25f79dcaab6893465d9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 6 May 2021 18:03:49 -0700 Subject: lib: parser: clean up kernel-doc Mark match_uint() as kernel-doc notation since it is already fully annotated as such. Use % prefix on constants in kernel-doc comments. Convert function return descriptions to use the "Return:" kernel-doc notation. Link: https://lkml.kernel.org/r/20210407034514.5651-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Alexander Viro Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/parser.c | 61 +++++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 38 insertions(+), 23 deletions(-) (limited to 'lib') diff --git a/lib/parser.c b/lib/parser.c index 7a5769db389f..f1a6d90b8c34 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -98,7 +98,7 @@ static int match_one(char *s, const char *p, substring_t args[]) * locations. * * Description: Detects which if any of a set of token strings has been passed - * to it. Tokens can include up to MAX_OPT_ARGS instances of basic c-style + * to it. Tokens can include up to %MAX_OPT_ARGS instances of basic c-style * format identifiers which will be taken into account when matching the * tokens, and whose locations will be returned in the @args array. */ @@ -120,8 +120,10 @@ EXPORT_SYMBOL(match_token); * @base: base to use when converting string * * Description: Given a &substring_t and a base, attempts to parse the substring - * as a number in that base. On success, sets @result to the integer represented - * by the string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * as a number in that base. + * + * Return: On success, sets @result to the integer represented by the + * string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ static int match_number(substring_t *s, int *result, int base) { @@ -153,8 +155,10 @@ static int match_number(substring_t *s, int *result, int base) * @base: base to use when converting string * * Description: Given a &substring_t and a base, attempts to parse the substring - * as a number in that base. On success, sets @result to the integer represented - * by the string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * as a number in that base. + * + * Return: On success, sets @result to the integer represented by the + * string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ static int match_u64int(substring_t *s, u64 *result, int base) { @@ -178,9 +182,10 @@ static int match_u64int(substring_t *s, u64 *result, int base) * @s: substring_t to be scanned * @result: resulting integer on success * - * Description: Attempts to parse the &substring_t @s as a decimal integer. On - * success, sets @result to the integer represented by the string and returns 0. - * Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * Description: Attempts to parse the &substring_t @s as a decimal integer. + * + * Return: On success, sets @result to the integer represented by the string + * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_int(substring_t *s, int *result) { @@ -188,14 +193,15 @@ int match_int(substring_t *s, int *result) } EXPORT_SYMBOL(match_int); -/* +/** * match_uint - scan a decimal representation of an integer from a substring_t * @s: substring_t to be scanned * @result: resulting integer on success * - * Description: Attempts to parse the &substring_t @s as a decimal integer. On - * success, sets @result to the integer represented by the string and returns 0. - * Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * Description: Attempts to parse the &substring_t @s as a decimal integer. + * + * Return: On success, sets @result to the integer represented by the string + * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_uint(substring_t *s, unsigned int *result) { @@ -217,9 +223,10 @@ EXPORT_SYMBOL(match_uint); * @result: resulting unsigned long long on success * * Description: Attempts to parse the &substring_t @s as a long decimal - * integer. On success, sets @result to the integer represented by the - * string and returns 0. - * Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * integer. + * + * Return: On success, sets @result to the integer represented by the string + * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_u64(substring_t *s, u64 *result) { @@ -232,9 +239,10 @@ EXPORT_SYMBOL(match_u64); * @s: substring_t to be scanned * @result: resulting integer on success * - * Description: Attempts to parse the &substring_t @s as an octal integer. On - * success, sets @result to the integer represented by the string and returns - * 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * Description: Attempts to parse the &substring_t @s as an octal integer. + * + * Return: On success, sets @result to the integer represented by the string + * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_octal(substring_t *s, int *result) { @@ -248,8 +256,9 @@ EXPORT_SYMBOL(match_octal); * @result: resulting integer on success * * Description: Attempts to parse the &substring_t @s as a hexadecimal integer. - * On success, sets @result to the integer represented by the string and - * returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. + * + * Return: On success, sets @result to the integer represented by the string + * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_hex(substring_t *s, int *result) { @@ -263,10 +272,11 @@ EXPORT_SYMBOL(match_hex); * @str: the string to be parsed * * Description: Parse the string @str to check if matches wildcard - * pattern @pattern. The pattern may contain two type wildcardes: + * pattern @pattern. The pattern may contain two types of wildcards: * '*' - matches zero or more characters * '?' - matches one character - * If it's matched, return true, else return false. + * + * Return: If the @str matches the @pattern, return true, else return false. */ bool match_wildcard(const char *pattern, const char *str) { @@ -316,7 +326,9 @@ EXPORT_SYMBOL(match_wildcard); * * Description: Copy the characters in &substring_t @src to the * c-style string @dest. Copy no more than @size - 1 characters, plus - * the terminating NUL. Return length of @src. + * the terminating NUL. + * + * Return: length of @src. */ size_t match_strlcpy(char *dest, const substring_t *src, size_t size) { @@ -338,6 +350,9 @@ EXPORT_SYMBOL(match_strlcpy); * Description: Allocates and returns a string filled with the contents of * the &substring_t @s. The caller is responsible for freeing the returned * string with kfree(). + * + * Return: the address of the newly allocated NUL-terminated string or + * %NULL on error. */ char *match_strdup(const substring_t *s) { -- cgit v1.2.3