- Kernel - mailweb.openeuler.org

[PATCH kernel-4.19] arm64/config: Set CONFIG_TXGBE=m by default
by Yang Yingliang 19 Jul '21

19 Jul '21

From: zhenpengzheng <zhenpengzheng(a)net-swift.com> hulk inclusion category: feature bugzilla: 50777 CVE: NA ------------------------------------------------------------------------- Ensure the netswift 10G NIC driver ko can be distributed in ISO on X86. Signed-off-by: zhenpengzheng <zhenpengzheng(a)net-swift.com> Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 1e1f7f3201028..8cfe2c3cd7dde 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2489,6 +2489,8 @@ CONFIG_HNS3_CAE=m CONFIG_NET_VENDOR_HUAWEI=y CONFIG_HINIC=m CONFIG_BMA=m +CONFIG_NET_VENDOR_NETSWIFT=y +CONFIG_TXGBE=m # CONFIG_NET_VENDOR_I825XX is not set CONFIG_NET_VENDOR_INTEL=y # CONFIG_E100 is not set -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/4] Add traffic policy for low cache available.
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Xu Wei <xuwei56(a)huawei.com> euleros inclusion category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=327 CVE: NA When cache available is low, bcache turn to writethrough mode. Therefore, All write IO will be directly sent to backend device, which is usually HDD. At same time, cache device flush dirty data to the backend device in the bcache writeback process. So write IO from user will damage the sequentiality of writeback. And if there is lots of IO from writeback, user's write IO may be block. This patch add traffic policy in bcache to solve the problem and improve the performance for bcache when cache available is low. Signed-off-by: qinghaixiang <xuweiqhx(a)163.com> Signed-off-by: Xu Wei <xuwei56(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Li Ruilin <liruilin4(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/bcache/bcache.h | 49 ++++++++++++ drivers/md/bcache/btree.h | 6 +- drivers/md/bcache/request.c | 143 +++++++++++++++++++++++++++++++++- drivers/md/bcache/request.h | 2 + drivers/md/bcache/super.c | 35 +++++++++ drivers/md/bcache/sysfs.c | 56 +++++++++++++ drivers/md/bcache/writeback.c | 11 ++- drivers/md/bcache/writeback.h | 6 +- 8 files changed, 300 insertions(+), 8 deletions(-) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 99d12fce876b2..70fbde8ca70c9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -399,6 +399,28 @@ struct cached_dev { unsigned int offline_seconds; char backing_dev_name[BDEVNAME_SIZE]; + + /* Count the front and writeback io bandwidth per second */ + atomic_t writeback_sector_size; + atomic_t writeback_io_num; + atomic_t front_io_num; + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + struct timer_list io_stat_timer; + + unsigned int writeback_state; +#define WRITEBACK_DEFAULT 0 +#define WRITEBACK_QUICK 1 +#define WRITEBACK_SLOW 2 + + /* realize for token bucket */ + spinlock_t token_lock; + unsigned int max_sector_size; + unsigned int max_io_num; + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + struct timer_list token_assign_timer; }; enum alloc_reserve { @@ -717,6 +739,10 @@ struct cache_set { #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; + unsigned int cutoff_writeback_sync; + bool traffic_policy_start; + bool force_write_through; + unsigned int gc_sectors; }; struct bbio { @@ -732,6 +758,29 @@ struct bbio { struct bio bio; }; +struct get_bcache_status { + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + uint64_t dirty_rate; + unsigned int available; +}; + +struct set_bcache_status { + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + bool traffic_policy_start; + bool force_write_through; + bool copy_gc_enabled; + bool trigger_gc; + unsigned int writeback_state; + unsigned int gc_sectors; + unsigned int cutoff_writeback_sync; +}; +#define BCACHE_MAJOR 'B' +#define BCACHE_GET_WRITE_STATUS _IOR(BCACHE_MAJOR, 0x0, struct get_bcache_status) +#define BCACHE_SET_WRITE_STATUS _IOW(BCACHE_MAJOR, 0x1, struct set_bcache_status) + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 4d0cca145f699..7ddadcc485ea6 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -193,7 +193,11 @@ static inline unsigned int bset_block_offset(struct btree *b, struct bset *i) static inline void set_gc_sectors(struct cache_set *c) { - atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16); + if (c->gc_sectors == 0) + atomic_set(&c->sectors_to_gc, + c->sb.bucket_size * c->nbuckets / 16); + else + atomic_set(&c->sectors_to_gc, c->gc_sectors); } void bkey_put(struct cache_set *c, struct bkey *k); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 6d89e56a4a410..c05544e07722e 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -28,6 +28,7 @@ struct kmem_cache *bch_search_cache; static void bch_data_insert_start(struct closure *cl); +static void alloc_token(struct cached_dev *dc, unsigned int sectors); static unsigned int cache_mode(struct cached_dev *dc) { @@ -396,7 +397,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) goto skip; if (mode == CACHE_MODE_NONE || - (mode == CACHE_MODE_WRITEAROUND && + ((mode == CACHE_MODE_WRITEAROUND || + c->force_write_through == true) && op_is_write(bio_op(bio)))) goto skip; @@ -858,6 +860,10 @@ static void cached_dev_read_done(struct closure *cl) if (s->iop.bio && (!dc->read_bypass || s->prefetch) && !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) { BUG_ON(!s->iop.replace); + if ((dc->disk.c->traffic_policy_start == true) && + (dc->disk.c->force_write_through != true)) { + alloc_token(dc, bio_sectors(s->iop.bio)); + } closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } @@ -1000,6 +1006,35 @@ static void cached_dev_write_complete(struct closure *cl) continue_at(cl, cached_dev_bio_complete, NULL); } +static void alloc_token(struct cached_dev *dc, unsigned int sectors) +{ + int count = 0; + + spin_lock_bh(&dc->token_lock); + + while ((dc->write_token_sector_size < sectors) && + (dc->write_token_io_num == 0)) { + spin_unlock_bh(&dc->token_lock); + schedule_timeout_interruptible(msecs_to_jiffies(10)); + count++; + if ((dc->disk.c->traffic_policy_start != true) || + (cache_mode(dc) != CACHE_MODE_WRITEBACK) || + (count > 100)) + return; + spin_lock_bh(&dc->token_lock); + } + + if (dc->write_token_sector_size >= sectors) + dc->write_token_sector_size -= sectors; + else + dc->write_token_sector_size = 0; + + if (dc->write_token_io_num > 0) + dc->write_token_io_num--; + + spin_unlock_bh(&dc->token_lock); +} + static void cached_dev_write(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; @@ -1247,6 +1282,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, cached_dev_nodata, bcache_wq); } else { + atomic_inc(&dc->front_io_num); s->iop.bypass = check_should_bypass(dc, bio); if (!s->iop.bypass && bio->bi_iter.bi_size && !rw) { @@ -1258,10 +1294,17 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, save_circ_item(&s->smp); } - if (rw) + if (rw) { + if ((s->iop.bypass == false) && + (dc->disk.c->traffic_policy_start == true) && + (cache_mode(dc) == CACHE_MODE_WRITEBACK) && + (bio_op(bio) != REQ_OP_DISCARD)) { + alloc_token(dc, bio_sectors(bio)); + } cached_dev_write(dc, s); - else + } else { cached_dev_read(dc, s); + } } } else /* I/O request sent to backing device */ @@ -1270,6 +1313,65 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } +static int bcache_get_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct get_bcache_status a; + uint64_t cache_sectors; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + + a.writeback_sector_size_per_sec = dc->writeback_sector_size_per_sec; + a.writeback_io_num_per_sec = dc->writeback_io_num_per_sec; + a.front_io_num_per_sec = dc->front_io_num_per_sec; + cache_sectors = c->nbuckets * c->sb.bucket_size - + atomic_long_read(&c->flash_dev_dirty_sectors); + a.dirty_rate = div64_u64(bcache_dev_sectors_dirty(&dc->disk) * 100, + cache_sectors); + a.available = 100 - c->gc_stats.in_use; + if (copy_to_user((struct get_bcache_status *)arg, &a, + sizeof(struct get_bcache_status))) + return -EFAULT; + return 0; +} + +static int bcache_set_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct set_bcache_status a; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + if (copy_from_user(&a, (struct set_bcache_status *)arg, + sizeof(struct set_bcache_status))) + return -EFAULT; + + if (c->traffic_policy_start != a.traffic_policy_start) + pr_info("%s traffic policy %s", dc->disk.disk->disk_name, + (a.traffic_policy_start == true) ? "enable" : "disable"); + if (c->force_write_through != a.force_write_through) + pr_info("%s force write through %s", dc->disk.disk->disk_name, + (a.force_write_through == true) ? "enable" : "disable"); + if (a.trigger_gc) { + pr_info("trigger %s gc", dc->disk.disk->disk_name); + atomic_set(&c->sectors_to_gc, -1); + wake_up_gc(c); + } + if ((a.cutoff_writeback_sync >= MIN_CUTOFF_WRITEBACK_SYNC) && + (a.cutoff_writeback_sync <= MAX_CUTOFF_WRITEBACK_SYNC)) { + c->cutoff_writeback_sync = a.cutoff_writeback_sync; + } + + dc->max_sector_size = a.write_token_sector_size; + dc->max_io_num = a.write_token_io_num; + c->traffic_policy_start = a.traffic_policy_start; + c->force_write_through = a.force_write_through; + c->gc_sectors = a.gc_sectors; + dc->writeback_state = a.writeback_state; + return 0; +} + static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1278,7 +1380,14 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + switch (cmd) { + case BCACHE_GET_WRITE_STATUS: + return bcache_get_write_status(dc, arg); + case BCACHE_SET_WRITE_STATUS: + return bcache_set_write_status(dc, arg); + default: + return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + } } static int cached_dev_congested(void *data, int bits) @@ -1438,3 +1547,29 @@ int __init bch_request_init(void) return 0; } + +static void token_assign(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, token_assign_timer); + + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); + + spin_lock(&dc->token_lock); + dc->write_token_sector_size = dc->max_sector_size / 8; + dc->write_token_io_num = dc->max_io_num / 8; + dc->write_token_io_num = + (dc->write_token_io_num == 0) ? 1 : dc->write_token_io_num; + spin_unlock(&dc->token_lock); +} + +void bch_traffic_policy_init(struct cached_dev *dc) +{ + spin_lock_init(&dc->token_lock); + dc->write_token_sector_size = 0; + dc->write_token_io_num = 0; + + timer_setup(&dc->token_assign_timer, token_assign, 0); + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); +} diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 3667bc5390dfe..f677ba8704940 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -41,6 +41,8 @@ void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); +void bch_traffic_policy_init(struct cached_dev *dc); + extern struct kmem_cache *bch_search_cache, *bch_passthrough_cache; struct search { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e7f7a0f038682..3f858de9e9602 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1210,6 +1210,8 @@ static void cached_dev_free(struct closure *cl) { struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl); + del_timer_sync(&dc->io_stat_timer); + del_timer_sync(&dc->token_assign_timer); if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) cancel_writeback_rate_update_dwork(dc); @@ -1250,6 +1252,36 @@ static void cached_dev_flush(struct closure *cl) continue_at(cl, cached_dev_free, system_wq); } +static void cached_dev_io_stat(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, io_stat_timer); + + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); + + dc->writeback_sector_size_per_sec = + atomic_read(&dc->writeback_sector_size); + dc->writeback_io_num_per_sec = atomic_read(&dc->writeback_io_num); + dc->front_io_num_per_sec = atomic_read(&dc->front_io_num); + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); +} + +static void cached_dev_timer_init(struct cached_dev *dc) +{ + dc->writeback_sector_size_per_sec = 0; + dc->writeback_io_num_per_sec = 0; + dc->front_io_num_per_sec = 0; + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); + + timer_setup(&dc->io_stat_timer, cached_dev_io_stat, 0); + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); +} + static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) { int ret; @@ -1266,6 +1298,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) INIT_LIST_HEAD(&dc->io_lru); spin_lock_init(&dc->io_lock); bch_cache_accounting_init(&dc->accounting, &dc->disk.cl); + cached_dev_timer_init(dc); + bch_traffic_policy_init(dc); dc->sequential_cutoff = 4 << 20; dc->inflight_block_enable = 1; @@ -1774,6 +1808,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->cutoff_writeback_sync = MIN_CUTOFF_WRITEBACK_SYNC; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); return c; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 706d3a245dba6..4c693ac29b0e0 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -51,6 +51,13 @@ static const char * const error_actions[] = { NULL }; +static const char * const writeback_state[] = { + "default", + "quick", + "slow", + NULL +}; + write_attribute(attach); write_attribute(detach); write_attribute(unregister); @@ -96,6 +103,9 @@ read_attribute(io_errors); read_attribute(congested); rw_attribute(congested_read_threshold_us); rw_attribute(congested_write_threshold_us); +rw_attribute(gc_sectors); +rw_attribute(traffic_policy_start); +rw_attribute(force_write_through); rw_attribute(sequential_cutoff); rw_attribute(read_bypass); @@ -114,7 +124,13 @@ rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_i_term_inverse); rw_attribute(writeback_rate_p_term_inverse); rw_attribute(writeback_rate_minimum); +rw_attribute(writeback_state); +read_attribute(writeback_sector_size_per_sec); +read_attribute(writeback_io_num_per_sec); +read_attribute(front_io_num_per_sec); read_attribute(writeback_rate_debug); +read_attribute(write_token_sector_size); +read_attribute(write_token_io_num); read_attribute(stripe_size); read_attribute(partial_stripes_expensive); @@ -169,6 +185,11 @@ SHOW(__bch_cached_dev) bch_cache_modes, BDEV_CACHE_MODE(&dc->sb)); + if (attr == &sysfs_writeback_state) + return bch_snprint_string_list(buf, PAGE_SIZE, + writeback_state, + dc->writeback_state); + if (attr == &sysfs_readahead_cache_policy) return bch_snprint_string_list(buf, PAGE_SIZE, bch_reada_cache_policies, @@ -186,6 +207,9 @@ SHOW(__bch_cached_dev) var_printf(writeback_metadata, "%i"); var_printf(writeback_running, "%i"); var_print(writeback_delay); + var_print(writeback_sector_size_per_sec); + var_print(writeback_io_num_per_sec); + var_print(front_io_num_per_sec); var_print(writeback_percent); sysfs_hprint(writeback_rate, wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0); @@ -248,6 +272,8 @@ SHOW(__bch_cached_dev) sysfs_print(running, atomic_read(&dc->running)); sysfs_print(state, states[BDEV_STATE(&dc->sb)]); + var_print(write_token_sector_size); + var_print(write_token_io_num); if (attr == &sysfs_label) { memcpy(buf, dc->sb.label, SB_LABEL_SIZE); @@ -346,6 +372,15 @@ STORE(__cached_dev) } } + if (attr == &sysfs_writeback_state) { + v = __sysfs_match_string(writeback_state, -1, buf); + + if (v < 0) + return v; + + dc->writeback_state = v; + } + if (attr == &sysfs_readahead_cache_policy) { v = __sysfs_match_string(bch_reada_cache_policies, -1, buf); if (v < 0) @@ -448,11 +483,14 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_data_csum, #endif &sysfs_cache_mode, + &sysfs_writeback_state, &sysfs_readahead_cache_policy, &sysfs_stop_when_cache_set_failed, &sysfs_writeback_metadata, &sysfs_writeback_running, &sysfs_writeback_delay, + &sysfs_writeback_sector_size_per_sec, + &sysfs_writeback_io_num_per_sec, &sysfs_writeback_percent, &sysfs_writeback_rate, &sysfs_writeback_rate_update_seconds, @@ -460,6 +498,9 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_p_term_inverse, &sysfs_writeback_rate_minimum, &sysfs_writeback_rate_debug, + &sysfs_write_token_sector_size, + &sysfs_write_token_io_num, + &sysfs_front_io_num_per_sec, &sysfs_io_errors, &sysfs_io_error_limit, &sysfs_io_disable, @@ -714,6 +755,12 @@ SHOW(__bch_cache_set) c->congested_read_threshold_us); sysfs_print(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_print(gc_sectors, + c->gc_sectors); + sysfs_print(traffic_policy_start, + c->traffic_policy_start); + sysfs_print(force_write_through, + c->force_write_through); sysfs_print(active_journal_entries, fifo_used(&c->journal.pin)); sysfs_printf(verify, "%i", c->verify); @@ -800,6 +847,12 @@ STORE(__bch_cache_set) c->congested_read_threshold_us); sysfs_strtoul(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_strtoul(gc_sectors, + c->gc_sectors); + sysfs_strtoul(traffic_policy_start, + c->traffic_policy_start); + sysfs_strtoul(force_write_through, + c->force_write_through); if (attr == &sysfs_errors) { v = __sysfs_match_string(error_actions, -1, buf); @@ -926,6 +979,9 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_btree_shrinker_disabled, &sysfs_copy_gc_enabled, &sysfs_io_disable, + &sysfs_gc_sectors, + &sysfs_traffic_policy_start, + &sysfs_force_write_through, NULL }; KTYPE(bch_cache_set_internal); diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index b5fc3c6c7178e..901ad8bae7614 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -222,7 +222,13 @@ static unsigned int writeback_delay(struct cached_dev *dc, !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors); + if (dc->writeback_state == WRITEBACK_DEFAULT) { + return bch_next_delay(&dc->writeback_rate, sectors); + } else if (dc->writeback_state == WRITEBACK_QUICK) { + return 0; + } else { + return msecs_to_jiffies(1000); + } } struct dirty_io { @@ -287,6 +293,9 @@ static void write_dirty_finish(struct closure *cl) : &dc->disk.c->writeback_keys_done); } + atomic_add(KEY_SIZE(&w->key), &dc->writeback_sector_size); + atomic_inc(&dc->writeback_io_num); + bch_keybuf_del(&dc->writeback_keys, w); up(&dc->in_flight); diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index e75dc33339f6f..a3151c0e96609 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -3,7 +3,8 @@ #define _BCACHE_WRITEBACK_H #define CUTOFF_WRITEBACK 40 -#define CUTOFF_WRITEBACK_SYNC 70 +#define MIN_CUTOFF_WRITEBACK_SYNC 70 +#define MAX_CUTOFF_WRITEBACK_SYNC 90 #define MAX_WRITEBACKS_IN_PASS 5 #define MAX_WRITESIZE_IN_PASS 5000 /* *512b */ @@ -57,10 +58,11 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, unsigned int cache_mode, bool would_skip) { unsigned int in_use = dc->disk.c->gc_stats.in_use; + unsigned int cutoff = dc->disk.c->cutoff_writeback_sync; if (cache_mode != CACHE_MODE_WRITEBACK || test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || - in_use > CUTOFF_WRITEBACK_SYNC) + in_use > cutoff) return false; if (bio_op(bio) == REQ_OP_DISCARD) -- 2.25.1

1 3

[PATCH kernel-4.19 1/4] Add traffic policy for low cache available.
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Xu Wei <xuwei56(a)huawei.com> euleros inclusion category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=327 CVE: NA When cache available is low, bcache turn to writethrough mode. Therefore, All write IO will be directly sent to backend device, which is usually HDD. At same time, cache device flush dirty data to the backend device in the bcache writeback process. So write IO from user will damage the sequentiality of writeback. And if there is lots of IO from writeback, user's write IO may be block. This patch add traffic policy in bcache to solve the problem and improve the performance for bcache when cache available is low. Signed-off-by: qinghaixiang <xuweiqhx(a)163.com> Signed-off-by: Xu Wei <xuwei56(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Li Ruilin <liruilin4(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/bcache/bcache.h | 49 ++++++++++++ drivers/md/bcache/btree.h | 6 +- drivers/md/bcache/request.c | 145 ++++++++++++++++++++++++++++++++-- drivers/md/bcache/request.h | 2 + drivers/md/bcache/super.c | 36 +++++++++ drivers/md/bcache/sysfs.c | 56 +++++++++++++ drivers/md/bcache/writeback.c | 11 ++- drivers/md/bcache/writeback.h | 3 +- 8 files changed, 300 insertions(+), 8 deletions(-) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 3340f59117112..aa9e85dc04872 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -400,6 +400,28 @@ struct cached_dev { unsigned int offline_seconds; char backing_dev_name[BDEVNAME_SIZE]; + + /* Count the front and writeback io bandwidth per second */ + atomic_t writeback_sector_size; + atomic_t writeback_io_num; + atomic_t front_io_num; + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + struct timer_list io_stat_timer; + + unsigned int writeback_state; +#define WRITEBACK_DEFAULT 0 +#define WRITEBACK_QUICK 1 +#define WRITEBACK_SLOW 2 + + /* realize for token bucket */ + spinlock_t token_lock; + unsigned int max_sector_size; + unsigned int max_io_num; + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + struct timer_list token_assign_timer; }; enum alloc_reserve { @@ -739,6 +761,10 @@ struct cache_set { #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; + unsigned int cutoff_writeback_sync; + bool traffic_policy_start; + bool force_write_through; + unsigned int gc_sectors; }; struct bbio { @@ -754,6 +780,29 @@ struct bbio { struct bio bio; }; +struct get_bcache_status { + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + uint64_t dirty_rate; + unsigned int available; +}; + +struct set_bcache_status { + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + bool traffic_policy_start; + bool force_write_through; + bool copy_gc_enabled; + bool trigger_gc; + unsigned int writeback_state; + unsigned int gc_sectors; + unsigned int cutoff_writeback_sync; +}; +#define BCACHE_MAJOR 'B' +#define BCACHE_GET_WRITE_STATUS _IOR(BCACHE_MAJOR, 0x0, struct get_bcache_status) +#define BCACHE_SET_WRITE_STATUS _IOW(BCACHE_MAJOR, 0x1, struct set_bcache_status) + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 76cfd121a4861..7c5f7c235c533 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -193,7 +193,11 @@ static inline unsigned int bset_block_offset(struct btree *b, struct bset *i) static inline void set_gc_sectors(struct cache_set *c) { - atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16); + if (c->gc_sectors == 0) + atomic_set(&c->sectors_to_gc, + c->sb.bucket_size * c->nbuckets / 16); + else + atomic_set(&c->sectors_to_gc, c->gc_sectors); } void bkey_put(struct cache_set *c, struct bkey *k); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 2f3ecd8fc5801..50303841dd45b 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -28,6 +28,7 @@ struct kmem_cache *bch_search_cache; static void bch_data_insert_start(struct closure *cl); +static void alloc_token(struct cached_dev *dc, unsigned int sectors); static unsigned int cache_mode(struct cached_dev *dc) { @@ -384,8 +385,9 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) goto skip; if (mode == CACHE_MODE_NONE || - (mode == CACHE_MODE_WRITEAROUND && - op_is_write(bio_op(bio)))) + ((mode == CACHE_MODE_WRITEAROUND || + c->force_write_through == true) && + op_is_write(bio_op(bio)))) goto skip; /* @@ -863,6 +865,10 @@ static void cached_dev_read_done(struct closure *cl) if (s->iop.bio && (!dc->read_bypass || s->prefetch) && !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) { BUG_ON(!s->iop.replace); + if ((dc->disk.c->traffic_policy_start == true) && + (dc->disk.c->force_write_through != true)) { + alloc_token(dc, bio_sectors(s->iop.bio)); + } closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } @@ -1005,6 +1011,35 @@ static void cached_dev_write_complete(struct closure *cl) continue_at(cl, cached_dev_bio_complete, NULL); } +static void alloc_token(struct cached_dev *dc, unsigned int sectors) +{ + int count = 0; + + spin_lock_bh(&dc->token_lock); + + while ((dc->write_token_sector_size < sectors) && + (dc->write_token_io_num == 0)) { + spin_unlock_bh(&dc->token_lock); + schedule_timeout_interruptible(msecs_to_jiffies(10)); + count++; + if ((dc->disk.c->traffic_policy_start != true) || + (cache_mode(dc) != CACHE_MODE_WRITEBACK) || + (count > 100)) + return; + spin_lock_bh(&dc->token_lock); + } + + if (dc->write_token_sector_size >= sectors) + dc->write_token_sector_size -= sectors; + else + dc->write_token_sector_size = 0; + + if (dc->write_token_io_num > 0) + dc->write_token_io_num--; + + spin_unlock_bh(&dc->token_lock); +} + static void cached_dev_write(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; @@ -1252,6 +1287,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, cached_dev_nodata, bcache_wq); } else { + atomic_inc(&dc->front_io_num); s->iop.bypass = check_should_bypass(dc, bio); if (!s->iop.bypass && bio->bi_iter.bi_size && !rw) { @@ -1263,10 +1299,17 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, save_circ_item(&s->smp); } - if (rw) + if (rw) { + if ((s->iop.bypass == false) && + (dc->disk.c->traffic_policy_start == true) && + (cache_mode(dc) == CACHE_MODE_WRITEBACK) && + (bio_op(bio) != REQ_OP_DISCARD)) { + alloc_token(dc, bio_sectors(bio)); + } cached_dev_write(dc, s); - else + } else { cached_dev_read(dc, s); + } } } else /* I/O request sent to backing device */ @@ -1275,6 +1318,65 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } +static int bcache_get_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct get_bcache_status a; + uint64_t cache_sectors; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + + a.writeback_sector_size_per_sec = dc->writeback_sector_size_per_sec; + a.writeback_io_num_per_sec = dc->writeback_io_num_per_sec; + a.front_io_num_per_sec = dc->front_io_num_per_sec; + cache_sectors = c->nbuckets * c->sb.bucket_size - + atomic_long_read(&c->flash_dev_dirty_sectors); + a.dirty_rate = div64_u64(bcache_dev_sectors_dirty(&dc->disk) * 100, + cache_sectors); + a.available = 100 - c->gc_stats.in_use; + if (copy_to_user((struct get_bcache_status *)arg, &a, + sizeof(struct get_bcache_status))) + return -EFAULT; + return 0; +} + +static int bcache_set_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct set_bcache_status a; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + if (copy_from_user(&a, (struct set_bcache_status *)arg, + sizeof(struct set_bcache_status))) + return -EFAULT; + + if (c->traffic_policy_start != a.traffic_policy_start) + pr_info("%s traffic policy %s", dc->disk.disk->disk_name, + (a.traffic_policy_start == true) ? "enable" : "disable"); + if (c->force_write_through != a.force_write_through) + pr_info("%s force write through %s", dc->disk.disk->disk_name, + (a.force_write_through == true) ? "enable" : "disable"); + if (a.trigger_gc) { + pr_info("trigger %s gc", dc->disk.disk->disk_name); + atomic_set(&c->sectors_to_gc, -1); + wake_up_gc(c); + } + if ((a.cutoff_writeback_sync >= CUTOFF_WRITEBACK_SYNC) && + (a.cutoff_writeback_sync <= CUTOFF_WRITEBACK_SYNC_MAX)) { + c->cutoff_writeback_sync = a.cutoff_writeback_sync; + } + + dc->max_sector_size = a.write_token_sector_size; + dc->max_io_num = a.write_token_io_num; + c->traffic_policy_start = a.traffic_policy_start; + c->force_write_through = a.force_write_through; + c->gc_sectors = a.gc_sectors; + dc->writeback_state = a.writeback_state; + return 0; +} + static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1283,7 +1385,14 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + switch (cmd) { + case BCACHE_GET_WRITE_STATUS: + return bcache_get_write_status(dc, arg); + case BCACHE_SET_WRITE_STATUS: + return bcache_set_write_status(dc, arg); + default: + return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + } } static int cached_dev_congested(void *data, int bits) @@ -1443,3 +1552,29 @@ int __init bch_request_init(void) return 0; } + +static void token_assign(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, token_assign_timer); + + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); + + spin_lock(&dc->token_lock); + dc->write_token_sector_size = dc->max_sector_size / 8; + dc->write_token_io_num = dc->max_io_num / 8; + dc->write_token_io_num = + (dc->write_token_io_num == 0) ? 1 : dc->write_token_io_num; + spin_unlock(&dc->token_lock); +} + +void bch_traffic_policy_init(struct cached_dev *dc) +{ + spin_lock_init(&dc->token_lock); + dc->write_token_sector_size = 0; + dc->write_token_io_num = 0; + + timer_setup(&dc->token_assign_timer, token_assign, 0); + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); +} diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 7682630db73f6..8e2ab8071b5bf 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -41,6 +41,8 @@ void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); +void bch_traffic_policy_init(struct cached_dev *dc); + extern struct kmem_cache *bch_search_cache; struct search { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 754e88895738b..e2828c762edc5 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1260,6 +1260,9 @@ static void cached_dev_free(struct closure *cl) { struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl); + del_timer_sync(&dc->io_stat_timer); + del_timer_sync(&dc->token_assign_timer); + if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) cancel_writeback_rate_update_dwork(dc); @@ -1303,6 +1306,36 @@ static void cached_dev_flush(struct closure *cl) continue_at(cl, cached_dev_free, system_wq); } +static void cached_dev_io_stat(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, io_stat_timer); + + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); + + dc->writeback_sector_size_per_sec = + atomic_read(&dc->writeback_sector_size); + dc->writeback_io_num_per_sec = atomic_read(&dc->writeback_io_num); + dc->front_io_num_per_sec = atomic_read(&dc->front_io_num); + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); +} + +static void cached_dev_timer_init(struct cached_dev *dc) +{ + dc->writeback_sector_size_per_sec = 0; + dc->writeback_io_num_per_sec = 0; + dc->front_io_num_per_sec = 0; + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); + + timer_setup(&dc->io_stat_timer, cached_dev_io_stat, 0); + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); +} + static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) { int ret; @@ -1319,6 +1352,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) INIT_LIST_HEAD(&dc->io_lru); spin_lock_init(&dc->io_lock); bch_cache_accounting_init(&dc->accounting, &dc->disk.cl); + cached_dev_timer_init(dc); + bch_traffic_policy_init(dc); dc->sequential_cutoff = 4 << 20; dc->inflight_block_enable = 1; @@ -1837,6 +1872,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->cutoff_writeback_sync = bch_cutoff_writeback_sync; c->idle_max_writeback_rate_enabled = 1; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index e23c426229399..097560389760c 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -53,6 +53,13 @@ static const char * const error_actions[] = { NULL }; +static const char * const writeback_state[] = { + "default", + "quick", + "slow", + NULL +}; + write_attribute(attach); write_attribute(detach); write_attribute(unregister); @@ -102,6 +109,9 @@ read_attribute(cutoff_writeback); read_attribute(cutoff_writeback_sync); rw_attribute(congested_read_threshold_us); rw_attribute(congested_write_threshold_us); +rw_attribute(gc_sectors); +rw_attribute(traffic_policy_start); +rw_attribute(force_write_through); rw_attribute(sequential_cutoff); rw_attribute(read_bypass); @@ -120,7 +130,13 @@ rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_i_term_inverse); rw_attribute(writeback_rate_p_term_inverse); rw_attribute(writeback_rate_minimum); +rw_attribute(writeback_state); +read_attribute(writeback_sector_size_per_sec); +read_attribute(writeback_io_num_per_sec); +read_attribute(front_io_num_per_sec); read_attribute(writeback_rate_debug); +read_attribute(write_token_sector_size); +read_attribute(write_token_io_num); read_attribute(stripe_size); read_attribute(partial_stripes_expensive); @@ -177,6 +193,11 @@ SHOW(__bch_cached_dev) bch_cache_modes, BDEV_CACHE_MODE(&dc->sb)); + if (attr == &sysfs_writeback_state) + return bch_snprint_string_list(buf, PAGE_SIZE, + writeback_state, + dc->writeback_state); + if (attr == &sysfs_readahead_cache_policy) return bch_snprint_string_list(buf, PAGE_SIZE, bch_reada_cache_policies, @@ -194,6 +215,9 @@ SHOW(__bch_cached_dev) var_printf(writeback_metadata, "%i"); var_printf(writeback_running, "%i"); var_print(writeback_delay); + var_print(writeback_sector_size_per_sec); + var_print(writeback_io_num_per_sec); + var_print(front_io_num_per_sec); var_print(writeback_percent); sysfs_hprint(writeback_rate, wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0); @@ -256,6 +280,8 @@ SHOW(__bch_cached_dev) sysfs_print(running, atomic_read(&dc->running)); sysfs_print(state, states[BDEV_STATE(&dc->sb)]); + var_print(write_token_sector_size); + var_print(write_token_io_num); if (attr == &sysfs_label) { memcpy(buf, dc->sb.label, SB_LABEL_SIZE); @@ -375,6 +401,15 @@ STORE(__cached_dev) } } + if (attr == &sysfs_writeback_state) { + v = __sysfs_match_string(writeback_state, -1, buf); + + if (v < 0) + return v; + + dc->writeback_state = v; + } + if (attr == &sysfs_readahead_cache_policy) { v = __sysfs_match_string(bch_reada_cache_policies, -1, buf); if (v < 0) @@ -498,11 +533,14 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_data_csum, #endif &sysfs_cache_mode, + &sysfs_writeback_state, &sysfs_readahead_cache_policy, &sysfs_stop_when_cache_set_failed, &sysfs_writeback_metadata, &sysfs_writeback_running, &sysfs_writeback_delay, + &sysfs_writeback_sector_size_per_sec, + &sysfs_writeback_io_num_per_sec, &sysfs_writeback_percent, &sysfs_writeback_rate, &sysfs_writeback_rate_update_seconds, @@ -510,6 +548,9 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_p_term_inverse, &sysfs_writeback_rate_minimum, &sysfs_writeback_rate_debug, + &sysfs_write_token_sector_size, + &sysfs_write_token_io_num, + &sysfs_front_io_num_per_sec, &sysfs_io_errors, &sysfs_io_error_limit, &sysfs_io_disable, @@ -770,6 +811,12 @@ SHOW(__bch_cache_set) c->congested_read_threshold_us); sysfs_print(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_print(gc_sectors, + c->gc_sectors); + sysfs_print(traffic_policy_start, + c->traffic_policy_start); + sysfs_print(force_write_through, + c->force_write_through); sysfs_print(cutoff_writeback, bch_cutoff_writeback); sysfs_print(cutoff_writeback_sync, bch_cutoff_writeback_sync); @@ -855,6 +902,12 @@ STORE(__bch_cache_set) sysfs_strtoul_clamp(congested_write_threshold_us, c->congested_write_threshold_us, 0, UINT_MAX); + sysfs_strtoul(gc_sectors, + c->gc_sectors); + sysfs_strtoul(traffic_policy_start, + c->traffic_policy_start); + sysfs_strtoul(force_write_through, + c->force_write_through); if (attr == &sysfs_errors) { v = __sysfs_match_string(error_actions, -1, buf); @@ -997,6 +1050,9 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_idle_max_writeback_rate, &sysfs_gc_after_writeback, &sysfs_io_disable, + &sysfs_gc_sectors, + &sysfs_traffic_policy_start, + &sysfs_force_write_through, &sysfs_cutoff_writeback, &sysfs_cutoff_writeback_sync, NULL diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 25a66e54f7ba5..1e3041f6363c7 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -239,7 +239,13 @@ static unsigned int writeback_delay(struct cached_dev *dc, !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors); + if (dc->writeback_state == WRITEBACK_DEFAULT) { + return bch_next_delay(&dc->writeback_rate, sectors); + } else if (dc->writeback_state == WRITEBACK_QUICK) { + return 0; + } else { + return msecs_to_jiffies(1000); + } } struct dirty_io { @@ -304,6 +310,9 @@ static void write_dirty_finish(struct closure *cl) : &dc->disk.c->writeback_keys_done); } + atomic_add(KEY_SIZE(&w->key), &dc->writeback_sector_size); + atomic_inc(&dc->writeback_io_num); + bch_keybuf_del(&dc->writeback_keys, w); up(&dc->in_flight); diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index c4ff76037227b..912b1a146cea2 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -80,10 +80,11 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, unsigned int cache_mode, bool would_skip) { unsigned int in_use = dc->disk.c->gc_stats.in_use; + unsigned int cutoff = dc->disk.c->cutoff_writeback_sync; if (cache_mode != CACHE_MODE_WRITEBACK || test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || - in_use > bch_cutoff_writeback_sync) + in_use > cutoff) return false; if (bio_op(bio) == REQ_OP_DISCARD) -- 2.25.1

1 3

[PATCH openEuler-20.03-LTS-tag] kernel.spec: fix rpmbuild error with patch
by Gou Hao 19 Jul '21

19 Jul '21

From: gouhao <gouhao(a)uniontech.com> kernel.spec: fix rpmbuild error with patch uniontech inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I3ZNR0 CVE: NA -------------------------------------------------------------- When %{with_patch} is 1, the second compilation will fail when compiling with rpmbuild, and the failure message is: Reversed (or previously applied) patch detected! rpm package compilation usually deletes the source directory in ~/rpmbuild/BUILD in the %prep stage, but in our spec, in the %prep stage, if %{with patch} is 1 and vanilla-%{TarballVer} exists, there is no delete the source code directory and enter it directly， it will cause this bug. Signed-off-by: gouhao <gouhao(a)uniontech.com> --- kernel.spec | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/kernel.spec b/kernel.spec index e00a323..11c76aa 100644 --- a/kernel.spec +++ b/kernel.spec @@ -205,20 +205,14 @@ package or when debugging this package.\ %endif %prep -%if 0%{?with_patch} -if [ ! -d kernel-%{version}/vanilla-%{TarballVer} ];then -%setup -q -n kernel-%{version} -a 9998 -c - mv linux-%{TarballVer} vanilla-%{TarballVer} -else - cd kernel-%{version} -fi -cp -rl vanilla-%{TarballVer} linux-%{KernelVer} -%else + %setup -q -n kernel-%{version} -c -mv kernel linux-%{version} -cp -rl linux-%{version} linux-%{KernelVer} + +%if 0%{?with_patch} +tar -xjf %{SOURCE9998} %endif +mv linux-%{version} linux-%{KernelVer} cd linux-%{KernelVer} %if 0%{?with_patch} -- 2.20.1

1 0

[PATCH kernel-4.19] igmp: Add ip_mc_list lock in ip_check_mc_rcu
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Liu Jian <liujian56(a)huawei.com> mainline inclusion from mainline-net-next commit 23d2b94043ca8835bd1e67749020e839f396a1c2 category: bugfix bugzilla: NA CVE: NA -------------------------------- I got below panic when doing fuzz test: Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 4056 Comm: syz-executor.3 Tainted: G B 5.14.0-rc1-00195-gcff5c4254439-dirty #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x7a/0x9b panic+0x2cd/0x5af end_report.cold+0x5a/0x5a kasan_report+0xec/0x110 ip_check_mc_rcu+0x556/0x5d0 __mkroute_output+0x895/0x1740 ip_route_output_key_hash_rcu+0x2d0/0x1050 ip_route_output_key_hash+0x182/0x2e0 ip_route_output_flow+0x28/0x130 udp_sendmsg+0x165d/0x2280 udpv6_sendmsg+0x121e/0x24f0 inet6_sendmsg+0xf7/0x140 sock_sendmsg+0xe9/0x180 ____sys_sendmsg+0x2b8/0x7a0 ___sys_sendmsg+0xf0/0x160 __sys_sendmmsg+0x17e/0x3c0 __x64_sys_sendmmsg+0x9e/0x100 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x462eb9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f3df5af1c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462eb9 RDX: 0000000000000312 RSI: 0000000020001700 RDI: 0000000000000007 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f3df5af26bc R13: 00000000004c372d R14: 0000000000700b10 R15: 00000000ffffffff It is one use-after-free in ip_check_mc_rcu. In ip_mc_del_src, the ip_sf_list of pmc has been freed under pmc->lock protection. But access to ip_sf_list in ip_check_mc_rcu is not protected by the lock. Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/igmp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index ffa847fc96194..1a0953b2b1396 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2736,6 +2736,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2746,6 +2747,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] memcg: fix unsuitable null check after alloc memory
by Yang Yingliang 18 Jul '21

18 Jul '21

From: Lu Jialin <lujialin4(a)huawei.com> hulk inclusion category: bugfix bugzilla: 51815, https://gitee.com/openeuler/kernel/issues/I3IJ9I CVE: NA -------- Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/memcontrol.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 713a839013f72..e55b46d5d0fcb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4850,8 +4850,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; pn_ext = kzalloc_node(sizeof(*pn_ext), GFP_KERNEL, tmp); - pn = &pn_ext->pn; - if (!pn) + if (!pn_ext) return 1; pn_ext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); @@ -4860,6 +4859,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) return 1; } + pn = &pn_ext->pn; pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); if (!pn->lruvec_stat_cpu) { free_percpu(pn_ext->lruvec_stat_local); @@ -4927,10 +4927,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void) size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg_ext = kzalloc(size, GFP_KERNEL); - memcg = &memcg_ext->memcg; - if (!memcg) + if (!memcg_ext) return NULL; + memcg = &memcg_ext->memcg; memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] config: enable KASAN and UBSAN by default
by Yang Yingliang 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- Enable KASAN and UBSAN by default for test. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 10 ++++++++-- arch/x86/configs/hulk_defconfig | 10 ++++++++-- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index 741b33fab4e9c..6a3937a4017dd 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -5504,7 +5504,10 @@ CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PER_CPU_MAPS is not set CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -5668,7 +5671,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y CONFIG_IO_STRICT_DEVMEM=y diff --git a/arch/x86/configs/hulk_defconfig b/arch/x86/configs/hulk_defconfig index 6ea79ca8a8a1e..f43f5ead30fa4 100644 --- a/arch/x86/configs/hulk_defconfig +++ b/arch/x86/configs/hulk_defconfig @@ -7331,7 +7331,10 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_HAVE_DEBUG_STACKOVERFLOW=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_DEBUG_SHIRQ=y @@ -7504,7 +7507,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y # CONFIG_IO_STRICT_DEVMEM is not set -- 2.25.1

1 0

[PATCH kernel-4.19] config: enable KASAN and UBSAN by default
by Yang Yingliang 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- Enable KASAN and UBSAN by default for test. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 10 ++++++++-- arch/x86/configs/hulk_defconfig | 10 ++++++++-- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index 59069097da854..6e9b7ff0bf2dc 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -5542,7 +5542,10 @@ CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PER_CPU_MAPS is not set CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -5708,7 +5711,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y CONFIG_IO_STRICT_DEVMEM=y diff --git a/arch/x86/configs/hulk_defconfig b/arch/x86/configs/hulk_defconfig index b0e92300198c2..38ac853d4e31c 100644 --- a/arch/x86/configs/hulk_defconfig +++ b/arch/x86/configs/hulk_defconfig @@ -7320,7 +7320,10 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_HAVE_DEBUG_STACKOVERFLOW=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -7495,7 +7498,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y # CONFIG_IO_STRICT_DEVMEM is not set -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] cpuidle: fix a build error when compiling haltpoll into module
by GONG, Ruiqi 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZURN CVE: NA -------- Kernel build would fail in case of CONFIG_HALTPOLL_CPUIDLE=m, caused by haltpoll_switch_governor() not marked as an exported symbol. Fix this by complementing the EXPORT_SYMBOL statement. Fixes: 97c227885e0a ("cpuidle: fix container_of err in cpuidle_device and cpuidle_driver") Signed-off-by: GONG, Ruiqi <gongruiqi1(a)huawei.com> Cc: Jiajun Chen <chenjiajun8(a)huawei.com> --- drivers/cpuidle/driver.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 484d0e9655fc..c97d08c90655 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -260,6 +260,8 @@ void haltpoll_switch_governor(struct cpuidle_driver *drv) } } +EXPORT_SYMBOL_GPL(haltpoll_switch_governor); + /** * cpuidle_register_driver - registers a driver * @drv: a pointer to a valid struct cpuidle_driver -- 2.27.0

3 2

[PATCH openEuler-1.0-LTS 1/6] KVM: cpuid: do_cpuid_ent works on a whole CPUID function
by Yang Yingliang 16 Jul '21

16 Jul '21

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.3-rc1 commit ab8bcf64971180e1344ce2c7e70c49b0f24f6b0d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3YAEG CVE: NA ----------------------------- Rename it as well as __do_cpuid_ent and __do_cpuid_ent_emulated to have "func" in its name, and drop the index parameter which is always 0. Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Jingyi Wang <wangjingyi11(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/kvm/cpuid.c | 105 +++++++++++++++++++++---------------------- 1 file changed, 50 insertions(+), 55 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1a0b5843b0e34..fe925f146773a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -287,14 +287,19 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, { entry->function = function; entry->index = index; + entry->flags = 0; + cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; } -static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, u32 index, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, int *nent, int maxnent) { + entry->function = func; + entry->index = 0; + entry->flags = 0; + switch (func) { case 0: entry->eax = 7; @@ -306,21 +311,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - if (index == 0) - entry->ecx = F(RDPID); + entry->eax = 0; + entry->ecx = F(RDPID); ++*nent; default: break; } - entry->function = func; - entry->index = index; - return 0; } -static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, + int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -423,7 +425,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (WARN_ON(*nent >= maxnent)) goto out; - do_cpuid_1_ent(entry, function, index); + do_cpuid_1_ent(entry, function, 0); ++*nent; switch (function) { @@ -486,42 +488,36 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capability word 9 */ - if (index == 0) { - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - // TSC_ADJUST is emulated - entry->ebx |= F(TSC_ADJUST); - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && - boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - } else { - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - } entry->eax = 0; + /* Mask ebx against host capability word 9 */ + entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_7_0_EBX); + // TSC_ADJUST is emulated + entry->ebx |= F(TSC_ADJUST); + entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); + cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; + entry->ecx |= f_umip; + /* PKU is not yet implemented for shadow paging. */ + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) + entry->ecx &= ~F(PKU); + + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); break; } case 9: @@ -727,23 +723,22 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, return r; } -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, - u32 idx, int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, + int *nent, int maxnent, unsigned int type) { if (*nent >= maxnent) return -E2BIG; if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + return __do_cpuid_func_emulated(entry, func, nent, maxnent); - return __do_cpuid_ent(entry, func, idx, nent, maxnent); + return __do_cpuid_func(entry, func, nent, maxnent); } #undef F struct kvm_cpuid_param { u32 func; - u32 idx; bool has_leaf_count; bool (*qualifier)(const struct kvm_cpuid_param *param); }; @@ -816,8 +811,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (ent->qualifier && !ent->qualifier(ent)) continue; - r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], ent->func, + &nent, cpuid->nent, type); if (r) goto out_free; @@ -827,8 +822,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], func, + &nent, cpuid->nent, type); if (r) goto out_free; -- 2.25.1

1 5

[PATCH kernel-4.19 1/6] KVM: cpuid: do_cpuid_ent works on a whole CPUID function
by Yang Yingliang 15 Jul '21

15 Jul '21

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.3-rc1 commit ab8bcf64971180e1344ce2c7e70c49b0f24f6b0d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3YAEG CVE: NA ----------------------------- Rename it as well as __do_cpuid_ent and __do_cpuid_ent_emulated to have "func" in its name, and drop the index parameter which is always 0. Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Jingyi Wang <wangjingyi11(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/kvm/cpuid.c | 107 +++++++++++++++++++++---------------------- 1 file changed, 51 insertions(+), 56 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 85f439bd02f34..6775b9bd82911 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -287,14 +287,19 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, { entry->function = function; entry->index = index; + entry->flags = 0; + cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; } -static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, u32 index, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, int *nent, int maxnent) { + entry->function = func; + entry->index = 0; + entry->flags = 0; + switch (func) { case 0: entry->eax = 7; @@ -306,21 +311,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - if (index == 0) - entry->ecx = F(RDPID); + entry->eax = 0; + entry->ecx = F(RDPID); ++*nent; default: break; } - entry->function = func; - entry->index = index; - return 0; } -static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, + int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -423,7 +425,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (WARN_ON(*nent >= maxnent)) goto out; - do_cpuid_1_ent(entry, function, index); + do_cpuid_1_ent(entry, function, 0); ++*nent; switch (function) { @@ -486,43 +488,37 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capability word 9 */ - if (index == 0) { - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - // TSC_ADJUST is emulated - entry->ebx |= F(TSC_ADJUST); - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && - boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - } else { - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - } entry->eax = 0; + /* Mask ebx against host capability word 9 */ + entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_7_0_EBX); + // TSC_ADJUST is emulated + entry->ebx |= F(TSC_ADJUST); + entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); + cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; + entry->ecx |= f_umip; + /* PKU is not yet implemented for shadow paging. */ + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) + entry->ecx &= ~F(PKU); + + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); break; } case 9: @@ -728,23 +724,22 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, return r; } -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, - u32 idx, int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, + int *nent, int maxnent, unsigned int type) { if (*nent >= maxnent) return -E2BIG; if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + return __do_cpuid_func_emulated(entry, func, nent, maxnent); - return __do_cpuid_ent(entry, func, idx, nent, maxnent); + return __do_cpuid_func(entry, func, nent, maxnent); } #undef F struct kvm_cpuid_param { u32 func; - u32 idx; bool has_leaf_count; bool (*qualifier)(const struct kvm_cpuid_param *param); }; @@ -817,8 +812,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (ent->qualifier && !ent->qualifier(ent)) continue; - r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], ent->func, + &nent, cpuid->nent, type); if (r) goto out_free; @@ -828,8 +823,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], func, + &nent, cpuid->nent, type); if (r) goto out_free; -- 2.25.1

1 5

[PATCH openEuler-1.0-LTS 1/6] Revert "sched/membarrier: fix NULL poiner in membarrier_global_expedited"
by Yang Yingliang 15 Jul '21

15 Jul '21

From: Li Hua <hucool.lihua(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3UKOW CVE: NA ------------------------------------------------- This reverts commit 281caf306accfea76683f1dabc86749cc1de616a. Remove the work aroud to fix NULL poiner in membarrier_global_expedited, so as to prepare to introduce formal bug fix solution. Signed-off-by: Li Hua <hucool.lihua(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Reviewed-by: Zhang Qiao <zhangqiao22(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/membarrier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index ea888ddb914f6..c4ea07e857985 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -115,7 +115,7 @@ static int membarrier_global_expedited(void) * scheduling a kthread. */ p = task_rcu_dereference(&cpu_rq(cpu)->curr); - if (p && p->flags & PF_KTHREAD) + if (p->flags & PF_KTHREAD) continue; __cpumask_set_cpu(cpu, tmpmask); -- 2.25.1

1 5

[PATCH OLK-5.10] patchwork test
by Zheng Zengkai 14 Jul '21

14 Jul '21

From: Xiaofei Tan <tanxiaofei(a)huawei.com> mainline inclusion from mainline-5.13-rc2 commit ccb5ecdc2ddeaff744ee075b54cdff8a689e8fa7 category: bugfix bugzilla: 167378 DTS: #525 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Before commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work"), do_sea() would unconditionally signal the affected task from the arch code. Since that change, the GHES driver sends the signals. This exposes a problem as errors the GHES driver doesn't understand or doesn't handle effectively are silently ignored. It will cause the errors get taken again, and circulate endlessly. User-space task get stuck in this loop. Existing firmware on Kunpeng9xx systems reports cache errors with the 'ARM Processor Error' CPER records. Do memory failure handling for ARM Processor Error Section just like for Memory Error Section. Fixes: 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work") Signed-off-by: Xiaofei Tan <tanxiaofei(a)huawei.com> Reviewed-by: James Morse <james.morse(a)arm.com> [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Patchwork Links: http://patchwork.huawei.com/project/hulk5.10/list/?series=16359 --- drivers/acpi/apei/ghes.c | 81 +++++++++++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 17 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fce7ade2aba9..0c8330ed1ffd 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head) gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len); } -static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) +static bool ghes_do_memory_failure(u64 physical_addr, int flags) { unsigned long pfn; - int flags = -1; - int sec_sev = ghes_severity(gdata->error_severity); - struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE)) return false; - if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) - return false; - - pfn = mem_err->physical_addr >> PAGE_SHIFT; + pfn = PHYS_PFN(physical_addr); if (!pfn_valid(pfn)) { pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid address in generic error data: %#llx\n", - mem_err->physical_addr); + physical_addr); return false; } + memory_failure_queue(pfn, flags); + return true; +} + +static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, + int sev) +{ + int flags = -1; + int sec_sev = ghes_severity(gdata->error_severity); + struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); + + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) + return false; + /* iff following two events can be handled properly by now */ if (sec_sev == GHES_SEV_CORRECTED && (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) @@ -470,14 +477,56 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) flags = 0; - if (flags != -1) { - memory_failure_queue(pfn, flags); - return true; - } + if (flags != -1) + return ghes_do_memory_failure(mem_err->physical_addr, flags); return false; } +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +{ + struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + bool queued = false; + int sec_sev, i; + char *p; + + log_arm_hw_error(err); + + sec_sev = ghes_severity(gdata->error_severity); + if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE) + return false; + + p = (char *)(err + 1); + for (i = 0; i < err->err_info_num; i++) { + struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p; + bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR); + bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR); + const char *error_type = "unknown error"; + + /* + * The field (err_info->error_info & BIT(26)) is fixed to set to + * 1 in some old firmware of HiSilicon Kunpeng920. We assume that + * firmware won't mix corrected errors in an uncorrected section, + * and don't filter out 'corrected' error here. + */ + if (is_cache && has_pa) { + queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + p += err_info->length; + continue; + } + + if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs)) + error_type = cper_proc_error_type_strs[err_info->type]; + + pr_warn_ratelimited(FW_WARN GHES_PFX + "Unhandled processor error type: %s\n", + error_type); + p += err_info->length; + } + + return queued; +} + /* * PCIe AER errors need to be sent to the AER driver for reporting and * recovery. The GHES severities map to the following AER severities and @@ -605,9 +654,7 @@ static bool ghes_do_proc(struct ghes *ghes, ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); - - log_arm_hw_error(err); + queued = ghes_handle_arm_hw_error(gdata, sev); } else { void *err = acpi_hest_get_payload(gdata); -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] cifs: Fix leak when handling lease break for cached root fid
by Yang Yingliang 14 Jul '21

14 Jul '21

From: Paul Aurich <paul(a)darkrain42.org> mainline inclusion from mainline-5.9-rc1 commit baf57b56d3604880ccb3956ec6c62ea894f5de99 category: bugfix bugzilla: 40791 CVE: NA --------------------------- Handling a lease break for the cached root didn't free the smb2_lease_break_work allocation, resulting in a leak: unreferenced object 0xffff98383a5af480 (size 128): comm "cifsd", pid 684, jiffies 4294936606 (age 534.868s) hex dump (first 32 bytes): c0 ff ff ff 1f 00 00 00 88 f4 5a 3a 38 98 ff ff ..........Z:8... 88 f4 5a 3a 38 98 ff ff 80 88 d6 8a ff ff ff ff ..Z:8........... backtrace: [<0000000068957336>] smb2_is_valid_oplock_break+0x1fa/0x8c0 [<0000000073b70b9e>] cifs_demultiplex_thread+0x73d/0xcc0 [<00000000905fa372>] kthread+0x11c/0x150 [<0000000079378e4e>] ret_from_fork+0x22/0x30 Avoid this leak by only allocating when necessary. Fixes: a93864d93977 ("cifs: add lease tracking to the cached root fid") Signed-off-by: Paul Aurich <paul(a)darkrain42.org> CC: Stable <stable(a)vger.kernel.org> # v4.18+ Reviewed-by: Aurelien Aptel <aaptel(a)suse.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2misc.c [ Not apply 9bd4540836("CIFS: Properly process SMB3 lease breaks") ] Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/cifs/smb2misc.c | 73 +++++++++++++++++++++++++++++++++------------- 1 file changed, 52 insertions(+), 21 deletions(-) diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 3b2c1f2ac9563..5236636f71b54 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -509,15 +509,31 @@ cifs_ses_oplock_break(struct work_struct *work) kfree(lw); } +static void +smb2_queue_pending_open_break(struct tcon_link *tlink, __u8 *lease_key, + __le32 new_lease_state) +{ + struct smb2_lease_break_work *lw; + + lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); + if (!lw) { + cifs_put_tlink(tlink); + return; + } + + INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); + lw->tlink = tlink; + lw->lease_state = new_lease_state; + memcpy(lw->lease_key, lease_key, SMB2_LEASE_KEY_SIZE); + queue_work(cifsiod_wq, &lw->lease_break); +} + static bool -smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, - struct smb2_lease_break_work *lw) +smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) { - bool found; __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); @@ -556,22 +572,29 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, &cinode->flags); cifs_queue_oplock_break(cfile); - kfree(lw); return true; } - found = false; + return false; +} + +static struct cifs_pending_open * +smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, + struct smb2_lease_break *rsp) +{ + __u8 lease_state = le32_to_cpu(rsp->NewLeaseState); + int ack_req = le32_to_cpu(rsp->Flags & + SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); + struct cifs_pending_open *open; + struct cifs_pending_open *found = NULL; + list_for_each_entry(open, &tcon->pending_opens, olist) { if (memcmp(open->lease_key, rsp->LeaseKey, SMB2_LEASE_KEY_SIZE)) continue; if (!found && ack_req) { - found = true; - memcpy(lw->lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - lw->tlink = cifs_get_tlink(open->tlink); - queue_work(cifsiod_wq, &lw->lease_break); + found = open; } cifs_dbg(FYI, "found in the pending open list\n"); @@ -592,14 +615,7 @@ smb2_is_valid_lease_break(char *buffer) struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct smb2_lease_break_work *lw; - - lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); - if (!lw) - return false; - - INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); - lw->lease_state = rsp->NewLeaseState; + struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); @@ -617,11 +633,27 @@ smb2_is_valid_lease_break(char *buffer) spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp, lw)) { + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } spin_unlock(&tcon->open_file_lock); if (tcon->crfid.is_valid && @@ -639,7 +671,6 @@ smb2_is_valid_lease_break(char *buffer) } } spin_unlock(&cifs_tcp_ses_lock); - kfree(lw); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); return false; } -- 2.25.1

1 0

[PATCH kernel-4.19 1/6] nbd: handle device refs for DESTROY_ON_DISCONNECT properly
by Yang Yingliang 14 Jul '21

14 Jul '21

From: Josef Bacik <josef(a)toxicpanda.com> mainline inclusion from mainline-5.12-rc1 commit c9a2f90f4d6b category: bugfix bugzilla: 50455 CVE: NA ------------------------------------------------- There exists a race where we can be attempting to create a new nbd configuration while a previous configuration is going down, both configured with DESTROY_ON_DISCONNECT. Normally devices all have a reference of 1, as they won't be cleaned up until the module is torn down. However with DESTROY_ON_DISCONNECT we'll make sure that there is only 1 reference (generally) on the device for the config itself, and then once the config is dropped, the device is torn down. The race that exists looks like this TASK1 TASK2 nbd_genl_connect() idr_find() refcount_inc_not_zero(nbd) * count is 2 here ^^ nbd_config_put() nbd_put(nbd) (count is 1) setup new config check DESTROY_ON_DISCONNECT put_dev = true if (put_dev) nbd_put(nbd) * free'd here ^^ In nbd_genl_connect() we assume that the nbd ref count will be 2, however clearly that won't be true if the nbd device had been setup as DESTROY_ON_DISCONNECT with its prior configuration. Fix this by getting rid of the runtime flag to check if we need to mess with the nbd device refcount, and use the device NBD_DESTROY_ON_DISCONNECT flag to check if we need to adjust the ref counts. This was reported by syzkaller with the following kasan dump BUG: KASAN: use-after-free in instrument_atomic_read include/linux/instrumented.h:71 [inline] BUG: KASAN: use-after-free in atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] BUG: KASAN: use-after-free in refcount_dec_not_one+0x71/0x1e0 lib/refcount.c:76 Read of size 4 at addr ffff888143bf71a0 by task systemd-udevd/8451 CPU: 0 PID: 8451 Comm: systemd-udevd Not tainted 5.11.0-rc7-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:230 __kasan_report mm/kasan/report.c:396 [inline] kasan_report.cold+0x79/0xd5 mm/kasan/report.c:413 check_memory_region_inline mm/kasan/generic.c:179 [inline] check_memory_region+0x13d/0x180 mm/kasan/generic.c:185 instrument_atomic_read include/linux/instrumented.h:71 [inline] atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] refcount_dec_not_one+0x71/0x1e0 lib/refcount.c:76 refcount_dec_and_mutex_lock+0x19/0x140 lib/refcount.c:115 nbd_put drivers/block/nbd.c:248 [inline] nbd_release+0x116/0x190 drivers/block/nbd.c:1508 __blkdev_put+0x548/0x800 fs/block_dev.c:1579 blkdev_put+0x92/0x570 fs/block_dev.c:1632 blkdev_close+0x8c/0xb0 fs/block_dev.c:1640 __fput+0x283/0x920 fs/file_table.c:280 task_work_run+0xdd/0x190 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:174 [inline] exit_to_user_mode_prepare+0x249/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fc1e92b5270 Code: 73 01 c3 48 8b 0d 38 7d 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 59 c1 20 00 00 75 10 b8 03 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ee fb ff ff 48 89 04 24 RSP: 002b:00007ffe8beb2d18 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000007 RCX: 00007fc1e92b5270 RDX: 000000000aba9500 RSI: 0000000000000000 RDI: 0000000000000007 RBP: 00007fc1ea16f710 R08: 000000000000004a R09: 0000000000000008 R10: 0000562f8cb0b2a8 R11: 0000000000000246 R12: 0000000000000000 R13: 0000562f8cb0afd0 R14: 0000000000000003 R15: 000000000000000e Allocated by task 1: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:401 [inline] ____kasan_kmalloc.constprop.0+0x82/0xa0 mm/kasan/common.c:429 kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:682 [inline] nbd_dev_add+0x44/0x8e0 drivers/block/nbd.c:1673 nbd_init+0x250/0x271 drivers/block/nbd.c:2394 do_one_initcall+0x103/0x650 init/main.c:1223 do_initcall_level init/main.c:1296 [inline] do_initcalls init/main.c:1312 [inline] do_basic_setup init/main.c:1332 [inline] kernel_init_freeable+0x605/0x689 init/main.c:1533 kernel_init+0xd/0x1b8 init/main.c:1421 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Freed by task 8451: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track+0x1c/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:356 ____kasan_slab_free+0xe1/0x110 mm/kasan/common.c:362 kasan_slab_free include/linux/kasan.h:192 [inline] slab_free_hook mm/slub.c:1547 [inline] slab_free_freelist_hook+0x5d/0x150 mm/slub.c:1580 slab_free mm/slub.c:3143 [inline] kfree+0xdb/0x3b0 mm/slub.c:4139 nbd_dev_remove drivers/block/nbd.c:243 [inline] nbd_put.part.0+0x180/0x1d0 drivers/block/nbd.c:251 nbd_put drivers/block/nbd.c:295 [inline] nbd_config_put+0x6dd/0x8c0 drivers/block/nbd.c:1242 nbd_release+0x103/0x190 drivers/block/nbd.c:1507 __blkdev_put+0x548/0x800 fs/block_dev.c:1579 blkdev_put+0x92/0x570 fs/block_dev.c:1632 blkdev_close+0x8c/0xb0 fs/block_dev.c:1640 __fput+0x283/0x920 fs/file_table.c:280 task_work_run+0xdd/0x190 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:174 [inline] exit_to_user_mode_prepare+0x249/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888143bf7000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 416 bytes inside of 1024-byte region [ffff888143bf7000, ffff888143bf7400) The buggy address belongs to the page: page:000000005238f4ce refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x143bf0 head:000000005238f4ce order:3 compound_mapcount:0 compound_pincount:0 flags: 0x57ff00000010200(slab|head) raw: 057ff00000010200 ffffea00004b1400 0000000300000003 ffff888010c41140 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888143bf7080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888143bf7100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888143bf7180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888143bf7200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Reported-and-tested-by: syzbot+429d3f82d757c211bff3(a)syzkaller.appspotmail.com Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Luo Meng <luomeng12(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 55552f719b25b..01bede097ed25 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -76,8 +76,7 @@ struct link_dead_args { #define NBD_RT_HAS_PID_FILE 3 #define NBD_RT_HAS_CONFIG_REF 4 #define NBD_RT_BOUND 5 -#define NBD_RT_DESTROY_ON_DISCONNECT 6 -#define NBD_RT_DISCONNECT_ON_CLOSE 7 +#define NBD_RT_DISCONNECT_ON_CLOSE 6 #define NBD_DESTROY_ON_DISCONNECT 0 #define NBD_DISCONNECT_REQUESTED 1 @@ -1894,12 +1893,21 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { - set_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags); - set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); - put_dev = true; + /* + * We have 1 ref to keep the device around, and then 1 + * ref for our current operation here, which will be + * inherited by the config. If we already have + * DESTROY_ON_DISCONNECT set then we know we don't have + * that extra ref already held so we don't need the + * put_dev. + */ + if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) + put_dev = true; } else { - clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); + if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) + refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, @@ -2067,15 +2075,13 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { - if (!test_and_set_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags)) + if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) put_dev = true; - set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); } else { - if (test_and_clear_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags)) + if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) refcount_inc(&nbd->refs); - clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { -- 2.25.1

1 5

[PATCH kernel-4.19 00/33] backport linux-4.19.197
by Yang Yingliang 14 Jul '21

14 Jul '21

Alex Shi (1): mm: add VM_WARN_ON_ONCE_PAGE() macro Alper Gun (1): KVM: SVM: Call SEV Guest Decommission if ASID binding fails Anson Huang (1): ARM: dts: imx6qdl-sabresd: Remove incorrect power supply assignment Christian König (1): drm/nouveau: fix dma_address check for CPU/GPU sync Greg Kroah-Hartman (1): Linux 4.19.197 Hugh Dickins (16): mm/thp: fix __split_huge_pmd_locked() on shmem migration entry mm/thp: make is_huge_zero_pmd() safe and quicker mm/thp: try_to_unmap() use TTU_SYNC for safe splitting mm/thp: fix vma_address() if virtual address below file offset mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() mm: page_vma_mapped_walk(): use page for pvmw->page mm: page_vma_mapped_walk(): settle PageHuge on entry mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block mm: page_vma_mapped_walk(): crossing page table boundary mm: page_vma_mapped_walk(): add a level of indentation mm: page_vma_mapped_walk(): use goto instead of while (1) mm: page_vma_mapped_walk(): get vma_address_end() earlier mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk() mm, futex: fix shared futex pgoff on shmem huge page Jue Wang (1): mm/thp: fix page_address_in_vma() on file THP tails Juergen Gross (1): xen/events: reset active flag for lateeoi events later ManYi Li (1): scsi: sr: Return appropriate error code when disk is ejected Miaohe Lin (2): mm/rmap: remove unneeded semicolon in page_not_mapped() mm/rmap: use page_not_mapped in try_to_unmap() Petr Mladek (2): kthread_worker: split code for canceling the delayed work timer kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync() Tony Lindgren (3): clocksource/drivers/timer-ti-dm: Add clockevent and clocksource support clocksource/drivers/timer-ti-dm: Prepare to handle dra7 timer wrap issue clocksource/drivers/timer-ti-dm: Handle dra7 timer wrap errata i940 Yang Shi (1): mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split afzal mohammed (1): ARM: OMAP: replace setup_irq() by request_irq() Makefile | 2 +- arch/arm/boot/dts/dra7.dtsi | 11 ++ arch/arm/boot/dts/imx6qdl-sabresd.dtsi | 4 - arch/arm/mach-omap1/pm.c | 13 +- arch/arm/mach-omap1/time.c | 10 +- arch/arm/mach-omap1/timer32k.c | 10 +- arch/arm/mach-omap2/board-generic.c | 4 +- arch/arm/mach-omap2/timer.c | 181 +++++++++++++++++-------- arch/x86/kvm/svm.c | 32 +++-- drivers/clk/ti/clk-7xx.c | 1 + drivers/gpu/drm/nouveau/nouveau_bo.c | 4 +- drivers/scsi/sr.c | 2 + drivers/xen/events/events_base.c | 23 +++- include/linux/cpuhotplug.h | 1 + include/linux/huge_mm.h | 8 +- include/linux/hugetlb.h | 16 --- include/linux/mm.h | 3 + include/linux/mmdebug.h | 13 ++ include/linux/pagemap.h | 13 +- include/linux/rmap.h | 3 +- kernel/futex.c | 2 +- kernel/kthread.c | 77 +++++++---- mm/huge_memory.c | 56 ++++---- mm/hugetlb.c | 5 +- mm/internal.h | 53 ++++++-- mm/memory.c | 41 ++++++ mm/page_vma_mapped.c | 160 +++++++++++++--------- mm/pgtable-generic.c | 4 +- mm/rmap.c | 48 ++++--- mm/truncate.c | 43 +++--- 30 files changed, 541 insertions(+), 302 deletions(-) -- 2.25.1

1 33

[PATCH openEuler-1.0-LTS] mm/memcontrol.c: fix kasan slab-out-of-bounds in mem_cgroup_css_alloc
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Lu Jialin <lujialin4(a)huawei.com> hulk inclusion category: bugfix bugzilla: 51815, https://gitee.com/openeuler/kernel/issues/I3IJ9I CVE: NA -------- static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { ... pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; pnext = to_mgpn_ext(pn); pnext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); } the size of pnext is larger than pn, so pnext->lruvec_stat_local is out of bounds Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/memcontrol.h | 12 +++++----- mm/memcontrol.c | 48 +++++++++++++++++++------------------- 2 files changed, 30 insertions(+), 30 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c7c7c0a418771..b4a25979ee8c7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -609,11 +609,11 @@ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, { long x = 0; int cpu; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; - mgext = to_memcg_ext(memcg); + memcg_ext = to_memcg_ext(memcg); for_each_possible_cpu(cpu) - x += per_cpu(mgext->vmstats_local->count[idx], cpu); + x += per_cpu(memcg_ext->vmstats_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -687,7 +687,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; long x = 0; int cpu; @@ -695,9 +695,9 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - pnext = to_mgpn_ext(pn); + pn_ext = to_mgpn_ext(pn); for_each_possible_cpu(cpu) - x += per_cpu(pnext->lruvec_stat_local->count[idx], cpu); + x += per_cpu(pn_ext->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index da10300a6e7d7..713a839013f72 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -698,14 +698,14 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) x = val + __this_cpu_read(memcg->stat_cpu->count[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; /* * Batch local counters to keep them in sync with * the hierarchical ones. */ - mgext = to_memcg_ext(memcg); - __this_cpu_add(mgext->vmstats_local->count[idx], x); + memcg_ext = to_memcg_ext(memcg); + __this_cpu_add(memcg_ext->vmstats_local->count[idx], x); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->stat[idx]); x = 0; @@ -739,7 +739,7 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, { pg_data_t *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; struct mem_cgroup *memcg; long x; @@ -756,8 +756,8 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __mod_memcg_state(memcg, idx, val); /* Update lruvec */ - pnext = to_mgpn_ext(pn); - __this_cpu_add(pnext->lruvec_stat_local->count[idx], val); + pn_ext = to_mgpn_ext(pn); + __this_cpu_add(pn_ext->lruvec_stat_local->count[idx], val); x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { @@ -787,14 +787,14 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, x = count + __this_cpu_read(memcg->stat_cpu->events[idx]); if (unlikely(x > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; /* * Batch local counters to keep them in sync with * the hierarchical ones. */ - mgext = to_memcg_ext(memcg); - __this_cpu_add(mgext->vmstats_local->events[idx], x); + memcg_ext = to_memcg_ext(memcg); + __this_cpu_add(memcg_ext->vmstats_local->events[idx], x); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->events[idx]); x = 0; @@ -811,11 +811,11 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) { long x = 0; int cpu; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; - mgext = to_memcg_ext(memcg); + memcg_ext = to_memcg_ext(memcg); for_each_possible_cpu(cpu) - x += per_cpu(mgext->vmstats_local->events[event], cpu); + x += per_cpu(memcg_ext->vmstats_local->events[event], cpu); return x; } @@ -4837,7 +4837,7 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id) static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; int tmp = node; /* * This routine is called against possible nodes. @@ -4849,21 +4849,21 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) */ if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; - pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); + pn_ext = kzalloc_node(sizeof(*pn_ext), GFP_KERNEL, tmp); + pn = &pn_ext->pn; if (!pn) return 1; - pnext = to_mgpn_ext(pn); - pnext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); - if (!pnext->lruvec_stat_local) { - kfree(pnext); + pn_ext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); + if (!pn_ext->lruvec_stat_local) { + kfree(pn_ext); return 1; } pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); if (!pn->lruvec_stat_cpu) { - free_percpu(pnext->lruvec_stat_local); - kfree(pn); + free_percpu(pn_ext->lruvec_stat_local); + kfree(pn_ext); return 1; } @@ -4879,15 +4879,15 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; if (!pn) return; + pn_ext = to_mgpn_ext(pn); free_percpu(pn->lruvec_stat_cpu); - pnext = to_mgpn_ext(pn); - free_percpu(pnext->lruvec_stat_local); - kfree(pn); + free_percpu(pn_ext->lruvec_stat_local); + kfree(pn_ext); } static void __mem_cgroup_free(struct mem_cgroup *memcg) -- 2.25.1

1 0

[PATCH kernel-4.19] btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Qu Wenruo <wqu(a)suse.com> mainline inclusion from mainline-v5.13-rc5 commit 6d4572a9d71d5fc2affee0258d8582d39859188c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I39MZM CVE: NA ------------------------------------------------------ [BUG] When the data space is exhausted, even if the inode has NOCOW attribute, we will still refuse to truncate unaligned range due to ENOSPC. The following script can reproduce it pretty easily: #!/bin/bash dev=/dev/test/test mnt=/mnt/btrfs umount $dev &> /dev/null umount $mnt &> /dev/null mkfs.btrfs -f $dev -b 1G mount -o nospace_cache $dev $mnt touch $mnt/foobar chattr +C $mnt/foobar xfs_io -f -c "pwrite -b 4k 0 4k" $mnt/foobar > /dev/null xfs_io -f -c "pwrite -b 4k 0 1G" $mnt/padding &> /dev/null sync xfs_io -c "fpunch 0 2k" $mnt/foobar umount $mnt Currently this will fail at the fpunch part. [CAUSE] Because btrfs_truncate_block() always reserves space without checking the NOCOW attribute. Since the writeback path follows NOCOW bit, we only need to bother the space reservation code in btrfs_truncate_block(). [FIX] Make btrfs_truncate_block() follow btrfs_buffered_write() to try to reserve data space first, and fall back to NOCOW check only when we don't have enough space. Such always-try-reserve is an optimization introduced in btrfs_buffered_write(), to avoid expensive btrfs_check_can_nocow() call. This patch will export check_can_nocow() as btrfs_check_can_nocow(), and use it in btrfs_truncate_block() to fix the problem. Reference: https://patchwork.kernel.org/project/linux-btrfs/patch/20200130052822.11765… Reported-by: Martin Doucha <martin.doucha(a)suse.com> Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Anand Jain <anand.jain(a)oracle.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Conflicts: fs/btrfs/file.c fs/btrfs/inode.c Signed-off-by: Gou Hao <gouhao(a)uniontech.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Jiao Fenfang <jiaofenfang(a)uniontech.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/btrfs/ctree.h | 3 ++- fs/btrfs/file.c | 8 ++++---- fs/btrfs/inode.c | 39 +++++++++++++++++++++++++++++++++------ 3 files changed, 39 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4d1c12faada89..4f5c58d40a79f 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3271,7 +3271,8 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); - +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, struct btrfs_root *root); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 41ad37f8062a9..3cd05edca30ce 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1536,8 +1536,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1647,7 +1647,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, + btrfs_check_can_nocow(BTRFS_I(inode), pos, &write_bytes) > 0) { /* * For nodata cow case, no need to reserve @@ -1925,7 +1925,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + btrfs_check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { inode_unlock(inode); return -EAGAIN; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bf0e0e3e09c5d..9e3e003e4488e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4958,11 +4958,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; char *kaddr; + bool only_release_metadata = false; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); + size_t write_bytes = blocksize; int ret = 0; u64 block_start; u64 block_end; @@ -4974,10 +4976,26 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - block_start, blocksize); - if (ret) + ret = btrfs_check_data_free_space(inode, &data_reserved, + block_start, blocksize); + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + btrfs_check_can_nocow(BTRFS_I(inode), block_start, + &write_bytes) > 0) { + /* For nocow case, no need to reserve data space */ + only_release_metadata = true; + } else { + goto out; + } + } + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + if (ret < 0) { + if (!only_release_metadata) + btrfs_free_reserved_data_space(inode, data_reserved, + block_start, blocksize); goto out; + } again: page = find_or_create_page(mapping, index, mask); @@ -5048,10 +5066,19 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, set_page_dirty(page); unlock_extent_cached(io_tree, block_start, block_end, &cached_state); + if (only_release_metadata) + set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, + block_end, EXTENT_NORESERVE, NULL, NULL, + GFP_NOFS); out_unlock: - if (ret) - btrfs_delalloc_release_space(inode, data_reserved, block_start, - blocksize, true); + if (ret) { + if (only_release_metadata) + btrfs_delalloc_release_metadata(BTRFS_I(inode), + blocksize, true); + else + btrfs_delalloc_release_space(inode, data_reserved, + block_start, blocksize, true); + } btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] module: limit enabling module.sig_enforce
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Mimi Zohar <zohar(a)linux.ibm.com> stable inclusion from linux-4.19.196 commit ff660863628fb144badcb3395cde7821c82c13a6 CVE: CVE-2021-35039 -------------------------------- [ Upstream commit 0c18f29aae7ce3dadd26d8ee3505d07cc982df75 ] Irrespective as to whether CONFIG_MODULE_SIG is configured, specifying "module.sig_enforce=1" on the boot command line sets "sig_enforce". Only allow "sig_enforce" to be set when CONFIG_MODULE_SIG is configured. This patch makes the presence of /sys/module/module/parameters/sig_enforce dependent on CONFIG_MODULE_SIG=y. Fixes: fda784e50aac ("module: export module signature enforcement status") Reported-by: Nayna Jain <nayna(a)linux.ibm.com> Tested-by: Mimi Zohar <zohar(a)linux.ibm.com> Tested-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/module.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/module.c b/kernel/module.c index ad4c1d7b7a956..82c83cbf6ce6c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -268,9 +268,18 @@ static void module_assert_mutex_or_preempt(void) #endif } +#ifdef CONFIG_MODULE_SIG static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); module_param(sig_enforce, bool_enable_only, 0644); +void set_module_sig_enforced(void) +{ + sig_enforce = true; +} +#else +#define sig_enforce false +#endif + /* * Export sig_enforce kernel cmdline parameter to allow other subsystems rely * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] xfs: let writable tracepoint enable to clear flag of f_mode
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Yufen Yu <yuyufen(a)huawei.com> hulk inclusion category: feature bugzilla: 173267 CVE: NA --------------------------- Adding a new member clear_f_mode into struct xfs_writable_file, then we can clear some flag of file->f_mode. Signed-off-by: Yufen Yu <yuyufen(a)huawei.com> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/xfs/xfs_file.c | 10 +++++++--- include/linux/fs.h | 9 ++++++--- include/uapi/linux/xfs.h | 4 +++- tools/include/uapi/linux/xfs.h | 2 +- 4 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ffc388c8b4523..bd8ae4df20042 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -35,6 +35,8 @@ #include <linux/mman.h> #include <linux/fadvise.h> +#define FMODE_MASK (FMODE_RANDOM | FMODE_WILLNEED | FMODE_SPC_READAHEAD) + static const struct vm_operations_struct xfs_file_vm_ops; int @@ -238,15 +240,17 @@ xfs_file_buffered_aio_read( struct xfs_writable_file file; file.name = file_dentry(filp)->d_name.name; + file.clear_f_mode = 0; file.f_mode = 0; file.i_size = file_inode(filp)->i_size; - file.prev_pos = filp->f_ra.prev_pos; + file.prev_pos = filp->f_ra.prev_pos >> PAGE_SHIFT; + file.pos = iocb->ki_pos >> PAGE_SHIFT; trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); trace_xfs_file_read(&file, ip, iov_iter_count(to), iocb->ki_pos); - if (file.f_mode) - filp->f_mode |= file.f_mode; + filp->f_mode |= file.f_mode & FMODE_MASK; + filp->f_mode &= ~(file.clear_f_mode & FMODE_MASK); if (iocb->ki_flags & IOCB_NOWAIT) { if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) diff --git a/include/linux/fs.h b/include/linux/fs.h index f5bc43ac95035..394da46d143c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -160,6 +160,12 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File will try to read head of the file into pagecache */ +#define FMODE_WILLNEED ((__force fmode_t)0x400000) + +/* File will do specail readahead */ +#define FMODE_SPC_READAHEAD ((__force fmode_t)0x800000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -169,9 +175,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) -/* File will try to read head of the file into pagecache */ -#define FMODE_WILLNEED ((__force fmode_t)0x40000000) - /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are diff --git a/include/uapi/linux/xfs.h b/include/uapi/linux/xfs.h index 635a83914273b..0a11c2344e5a3 100644 --- a/include/uapi/linux/xfs.h +++ b/include/uapi/linux/xfs.h @@ -7,9 +7,11 @@ struct xfs_writable_file { const unsigned char *name; + unsigned int clear_f_mode; /* can be cleared from file->f_mode */ unsigned int f_mode; /* can be set into file->f_mode */ long long i_size; /* file size */ - long long prev_pos; /* ra->prev_pos */ + long long prev_pos; /* ra->prev_pos page index */ + long long pos; /* iocb->ki_pos page index */ }; #endif /* _UAPI_LINUX_XFS_H */ diff --git a/tools/include/uapi/linux/xfs.h b/tools/include/uapi/linux/xfs.h index f333a2eb74074..2c4c61d5ba539 100644 --- a/tools/include/uapi/linux/xfs.h +++ b/tools/include/uapi/linux/xfs.h @@ -5,7 +5,7 @@ #include <linux/types.h> #define FMODE_RANDOM (0x1000) -#define FMODE_WILLNEED (0x40000000) +#define FMODE_WILLNEED (0x400000) struct xfs_writable_file { const unsigned char *name; -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS] jbd2: fix kabi broken in struct journal_s
by Yang Yingliang 09 Jul '21

09 Jul '21

From: yangerkun <yangerkun(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172974 CVE: NA --------------------------- 72c9e4df6a99 ('jbd2: ensure abort the journal if detect IO error when writing original buffer back') will add 'j_atomic_flags' which can lead lots of kabi broken like jbd2_journal_destroy/jbd2_journal_abort and so on. Fix it by add a wrapper. Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/jbd2/checkpoint.c | 5 ++++- fs/jbd2/journal.c | 19 +++++++++++++------ include/linux/jbd2.h | 23 ++++++++++++++++++----- 3 files changed, 35 insertions(+), 12 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index b1af15ad36dcb..f2c36c9c58be3 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -562,6 +562,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; + journal_wrapper_t *journal_wrapper; struct buffer_head *bh = jh2bh(jh); JBUFFER_TRACE(jh, "entry"); @@ -572,6 +573,8 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) return 0; } journal = transaction->t_journal; + journal_wrapper = container_of(journal, journal_wrapper_t, + jw_journal); JBUFFER_TRACE(jh, "removing from transaction"); @@ -583,7 +586,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) * journal here and we abort the journal later from a better context. */ if (buffer_write_io_error(bh)) - set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags); + set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags); __buffer_unlink(jh); jh->b_cp_transaction = NULL; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 89fad4c3e13cb..ef9a942fc9a1a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1129,14 +1129,17 @@ static journal_t *journal_init_common(struct block_device *bdev, { static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; + journal_wrapper_t *journal_wrapper; int err; struct buffer_head *bh; int n; - journal = kzalloc(sizeof(*journal), GFP_KERNEL); - if (!journal) + journal_wrapper = kzalloc(sizeof(*journal_wrapper), GFP_KERNEL); + if (!journal_wrapper) return NULL; + journal = &(journal_wrapper->jw_journal); + init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); @@ -1195,7 +1198,7 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); - kfree(journal); + kfree(journal_wrapper); return NULL; } @@ -1425,11 +1428,13 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; + journal_wrapper_t *journal_wrapper = container_of(journal, + journal_wrapper_t, jw_journal); int ret; if (is_journal_aborted(journal)) return -EIO; - if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) { + if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags)) { jbd2_journal_abort(journal, -EIO); return -EIO; } @@ -1754,6 +1759,8 @@ int jbd2_journal_load(journal_t *journal) int jbd2_journal_destroy(journal_t *journal) { int err = 0; + journal_wrapper_t *journal_wrapper = container_of(journal, + journal_wrapper_t, jw_journal); /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); @@ -1795,7 +1802,7 @@ int jbd2_journal_destroy(journal_t *journal) * may become inconsistent. */ if (!is_journal_aborted(journal) && - test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) + test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags)) jbd2_journal_abort(journal, -EIO); if (journal->j_sb_buffer) { @@ -1823,7 +1830,7 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); - kfree(journal); + kfree(journal_wrapper); return err; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5c0446f22bee1..ef213666c3a3b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -105,6 +105,8 @@ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ + +typedef struct journal_wrapper_s journal_wrapper_t; #endif /* @@ -780,11 +782,6 @@ struct journal_s */ unsigned long j_flags; - /** - * @j_atomic_flags: Atomic journaling state flags. - */ - unsigned long j_atomic_flags; - /** * @j_errno: * @@ -1199,6 +1196,22 @@ struct journal_s #endif }; +/** + * struct journal_wrapper_s - The wrapper of journal_s to fix KABI. + */ +struct journal_wrapper_s +{ + /** + * @jw_journal: real journal. + */ + journal_t jw_journal; + + /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; +}; + #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ -- 2.25.1

1 0

[PATCH OLK-5.10] x86/perf: Add uncore performance monitor support for Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Zhaoxin CPUs have already provided a performance monitoring unit on hardware for uncore, but this feature has not been used. Therefore, add support for Zhaoxin CPUs to make it available to monitor the uncore performance. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/events/zhaoxin/Makefile | 1 + arch/x86/events/zhaoxin/uncore.c | 1123 ++++++++++++++++++++++++++++++ arch/x86/events/zhaoxin/uncore.h | 311 +++++++++ 3 files changed, 1435 insertions(+) create mode 100644 arch/x86/events/zhaoxin/uncore.c create mode 100644 arch/x86/events/zhaoxin/uncore.h diff --git a/arch/x86/events/zhaoxin/Makefile b/arch/x86/events/zhaoxin/Makefile index 642c1174d662..767d6212bac1 100644 --- a/arch/x86/events/zhaoxin/Makefile +++ b/arch/x86/events/zhaoxin/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += core.o +obj-y += uncore.o diff --git a/arch/x86/events/zhaoxin/uncore.c b/arch/x86/events/zhaoxin/uncore.c new file mode 100644 index 000000000000..96771063a61e --- /dev/null +++ b/arch/x86/events/zhaoxin/uncore.c @@ -0,0 +1,1123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <asm/cpu_device_id.h> +#include "uncore.h" + +static struct zhaoxin_uncore_type *empty_uncore[] = { NULL, }; +static struct zhaoxin_uncore_type **uncore_msr_uncores = empty_uncore; + +/* mask of cpus that collect uncore events */ +static cpumask_t uncore_cpu_mask; + +/* constraint for the fixed counter */ +static struct event_constraint uncore_constraint_fixed = + EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); + +static int max_packages; + +/* CHX event control */ +#define CHX_UNC_CTL_EV_SEL_MASK 0x000000ff +#define CHX_UNC_CTL_UMASK_MASK 0x0000ff00 +#define CHX_UNC_CTL_EDGE_DET (1 << 18) +#define CHX_UNC_CTL_EN (1 << 22) +#define CHX_UNC_CTL_INVERT (1 << 23) +#define CHX_UNC_CTL_CMASK_MASK 0xff000000 +#define CHX_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define CHX_UNC_RAW_EVENT_MASK (CHX_UNC_CTL_EV_SEL_MASK | \ + CHX_UNC_CTL_UMASK_MASK | \ + CHX_UNC_CTL_EDGE_DET | \ + CHX_UNC_CTL_INVERT | \ + CHX_UNC_CTL_CMASK_MASK) + +/* CHX global control register */ +#define CHX_UNC_PERF_GLOBAL_CTL 0x391 +#define CHX_UNC_FIXED_CTR 0x394 +#define CHX_UNC_FIXED_CTR_CTRL 0x395 + +/* CHX uncore global control */ +#define CHX_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 4) - 1) +#define CHX_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* CHX uncore register */ +#define CHX_UNC_PERFEVTSEL0 0x3c0 +#define CHX_UNC_UNCORE_PMC0 0x3b0 + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); + +ssize_t zx_uncore_event_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +/*chx uncore support */ +static void chx_uncore_msr_disable_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static u64 uncore_msr_read_counter(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + u64 count; + + rdmsrl(event->hw.event_base, count); + + return count; +} + +static void chx_uncore_msr_disable_box(struct zhaoxin_uncore_box *box) +{ + wrmsrl(CHX_UNC_PERF_GLOBAL_CTL, 0); +} + +static void chx_uncore_msr_enable_box(struct zhaoxin_uncore_box *box) +{ + wrmsrl(CHX_UNC_PERF_GLOBAL_CTL, CHX_UNC_GLOBAL_CTL_EN_PC_ALL | CHX_UNC_GLOBAL_CTL_EN_FC); +} + +static void chx_uncore_msr_enable_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | CHX_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, CHX_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *chx_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group chx_uncore_format_group = { + .name = "format", + .attrs = chx_uncore_formats_attr, +}; + +static struct uncore_event_desc chx_uncore_events[] = { + { /* end: all zeroes */ }, +}; + +static struct zhaoxin_uncore_ops chx_uncore_msr_ops = { + .disable_box = chx_uncore_msr_disable_box, + .enable_box = chx_uncore_msr_enable_box, + .disable_event = chx_uncore_msr_disable_event, + .enable_event = chx_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct zhaoxin_uncore_type chx_uncore_box = { + .name = "", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = CHX_UNC_PERFEVTSEL0, + .perf_ctr = CHX_UNC_UNCORE_PMC0, + .fixed_ctr = CHX_UNC_FIXED_CTR, + .fixed_ctl = CHX_UNC_FIXED_CTR_CTRL, + .event_mask = CHX_UNC_RAW_EVENT_MASK, + .event_descs = chx_uncore_events, + .ops = &chx_uncore_msr_ops, + .format_group = &chx_uncore_format_group, +}; + +static struct zhaoxin_uncore_type *chx_msr_uncores[] = { + &chx_uncore_box, + NULL, +}; + +static struct zhaoxin_uncore_box *uncore_pmu_to_box(struct zhaoxin_uncore_pmu *pmu, int cpu) +{ + unsigned int package_id = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return package_id < max_packages ? pmu->boxes[package_id] : NULL; +} + +static void uncore_assign_hw_event(struct zhaoxin_uncore_box *box, + struct perf_event *event, int idx) +{ + struct hw_perf_event *hwc = &event->hw; + + hwc->idx = idx; + hwc->last_tag = ++box->tags[idx]; + + if (uncore_pmc_fixed(hwc->idx)) { + hwc->event_base = uncore_fixed_ctr(box); + hwc->config_base = uncore_fixed_ctl(box); + return; + } + + hwc->config_base = uncore_event_ctl(box, hwc->idx); + hwc->event_base = uncore_perf_ctr(box, hwc->idx); +} + +void uncore_perf_event_update(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + u64 prev_count, new_count, delta; + int shift; + + if (uncore_pmc_fixed(event->hw.idx)) + shift = 64 - uncore_fixed_ctr_bits(box); + else + shift = 64 - uncore_perf_ctr_bits(box); + + /* the hrtimer might modify the previous event value */ +again: + prev_count = local64_read(&event->hw.prev_count); + new_count = uncore_read_counter(box, event); + if (local64_xchg(&event->hw.prev_count, new_count) != prev_count) + goto again; + + delta = (new_count << shift) - (prev_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); +} + +static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) +{ + struct zhaoxin_uncore_box *box; + struct perf_event *event; + unsigned long flags; + int bit; + + box = container_of(hrtimer, struct zhaoxin_uncore_box, hrtimer); + if (!box->n_active || box->cpu != smp_processor_id()) + return HRTIMER_NORESTART; + /* + * disable local interrupt to prevent uncore_pmu_event_start/stop + * to interrupt the update process + */ + local_irq_save(flags); + + /* + * handle boxes with an active event list as opposed to active + * counters + */ + list_for_each_entry(event, &box->active_list, active_entry) { + uncore_perf_event_update(box, event); + } + + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) + uncore_perf_event_update(box, box->events[bit]); + + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration)); + return HRTIMER_RESTART; +} + +static void uncore_pmu_start_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), + HRTIMER_MODE_REL_PINNED); +} + +static void uncore_pmu_cancel_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_cancel(&box->hrtimer); +} + +static void uncore_pmu_init_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + box->hrtimer.function = uncore_pmu_hrtimer; +} + +static struct zhaoxin_uncore_box *uncore_alloc_box(struct zhaoxin_uncore_type *type, + int node) +{ + int i, size, numshared = type->num_shared_regs; + struct zhaoxin_uncore_box *box; + + size = sizeof(*box) + numshared * sizeof(struct zhaoxin_uncore_extra_reg); + + box = kzalloc_node(size, GFP_KERNEL, node); + if (!box) + return NULL; + + for (i = 0; i < numshared; i++) + raw_spin_lock_init(&box->shared_regs[i].lock); + + uncore_pmu_init_hrtimer(box); + box->cpu = -1; + box->package_id = -1; + + /* set default hrtimer timeout */ + box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; + + INIT_LIST_HEAD(&box->active_list); + + return box; +} + +static bool is_box_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + return &box->pmu->pmu == event->pmu; +} + +static struct event_constraint * +uncore_get_event_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + struct zhaoxin_uncore_type *type = box->pmu->type; + struct event_constraint *c; + + if (type->ops->get_constraint) { + c = type->ops->get_constraint(box, event); + if (c) + return c; + } + + if (event->attr.config == UNCORE_FIXED_EVENT) + return &uncore_constraint_fixed; + + if (type->constraints) { + for_each_event_constraint(c, type->constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &type->unconstrainted; +} + +static void uncore_put_event_constraint(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + if (box->pmu->type->ops->put_constraint) + box->pmu->type->ops->put_constraint(box, event); +} + +static int uncore_assign_events(struct zhaoxin_uncore_box *box, int assign[], int n) +{ + unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + struct event_constraint *c; + int i, wmin, wmax, ret = 0; + struct hw_perf_event *hwc; + + bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); + + for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + c = uncore_get_event_constraint(box, box->event_list[i]); + box->event_constraint[i] = c; + wmin = min(wmin, c->weight); + wmax = max(wmax, c->weight); + } + + /* fastpath, try to reuse previous register */ + for (i = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; + c = box->event_constraint[i]; + + /* never assigned */ + if (hwc->idx == -1) + break; + + /* constraint still honored */ + if (!test_bit(hwc->idx, c->idxmsk)) + break; + + /* not already used */ + if (test_bit(hwc->idx, used_mask)) + break; + + __set_bit(hwc->idx, used_mask); + if (assign) + assign[i] = hwc->idx; + } + /* slow path */ + if (i != n) + ret = perf_assign_events(box->event_constraint, n, + wmin, wmax, n, assign); + + if (!assign || ret) { + for (i = 0; i < n; i++) + uncore_put_event_constraint(box, box->event_list[i]); + } + return ret ? -EINVAL : 0; +} + +static void uncore_pmu_event_start(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + int idx = event->hw.idx; + + + if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX)) + return; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->events[idx] = event; + box->n_active++; + __set_bit(idx, box->active_mask); + + local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); + uncore_enable_event(box, event); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void uncore_pmu_event_stop(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (__test_and_clear_bit(hwc->idx, box->active_mask)) { + uncore_disable_event(box, event); + box->n_active--; + box->events[hwc->idx] = NULL; + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int +uncore_collect_events(struct zhaoxin_uncore_box *box, struct perf_event *leader, + bool dogrp) +{ + struct perf_event *event; + int n, max_count; + + max_count = box->pmu->type->num_counters; + if (box->pmu->type->fixed_ctl) + max_count++; + + if (box->n_events >= max_count) + return -EINVAL; + + n = box->n_events; + + if (is_box_event(box, leader)) { + box->event_list[n] = leader; + n++; + } + + if (!dogrp) + return n; + + for_each_sibling_event(event, leader) { + if (!is_box_event(box, event) || + event->state <= PERF_EVENT_STATE_OFF) + continue; + + if (n >= max_count) + return -EINVAL; + + box->event_list[n] = event; + n++; + } + return n; +} + +static int uncore_pmu_event_add(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + int assign[UNCORE_PMC_IDX_MAX]; + int i, n, ret; + + if (!box) + return -ENODEV; + + ret = n = uncore_collect_events(box, event, false); + if (ret < 0) + return ret; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + ret = uncore_assign_events(box, assign, n); + if (ret) + return ret; + + /* save events moving to new counters */ + for (i = 0; i < box->n_events; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx == assign[i] && + hwc->last_tag == box->tags[assign[i]]) + continue; + /* + * Ensure we don't accidentally enable a stopped + * counter simply because we rescheduled. + */ + if (hwc->state & PERF_HES_STOPPED) + hwc->state |= PERF_HES_ARCH; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + } + + /* reprogram moved events into new counters */ + for (i = 0; i < n; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx != assign[i] || + hwc->last_tag != box->tags[assign[i]]) + uncore_assign_hw_event(box, event, assign[i]); + else if (i < box->n_events) + continue; + + if (hwc->state & PERF_HES_ARCH) + continue; + + uncore_pmu_event_start(event, 0); + } + box->n_events = n; + + return 0; +} + +static int uncore_validate_group(struct zhaoxin_uncore_pmu *pmu, + struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + struct zhaoxin_uncore_box *fake_box; + int ret = -EINVAL, n; + + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); + if (!fake_box) + return -ENOMEM; + + fake_box->pmu = pmu; + /* + * the event is not yet connected with its + * siblings therefore we must first collect + * existing siblings, then add the new event + * before we can simulate the scheduling + */ + n = uncore_collect_events(fake_box, leader, true); + if (n < 0) + goto out; + + fake_box->n_events = n; + n = uncore_collect_events(fake_box, event, false); + if (n < 0) + goto out; + + fake_box->n_events = n; + + ret = uncore_assign_events(fake_box, NULL, n); +out: + kfree(fake_box); + return ret; +} + +static void uncore_pmu_event_del(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + int i; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + uncore_put_event_constraint(box, event); + + for (++i; i < box->n_events; i++) + box->event_list[i - 1] = box->event_list[i]; + + --box->n_events; + break; + } + } + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; +} + +static void uncore_pmu_event_read(struct perf_event *event) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + + uncore_perf_event_update(box, event); +} + +static int uncore_pmu_event_init(struct perf_event *event) +{ + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + int ret; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + event->cpu = box->cpu; + event->pmu_private = box; + + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + + if (event->attr.config == UNCORE_FIXED_EVENT) { + /* no fixed counter */ + if (!pmu->type->fixed_ctl) + return -EINVAL; + /* + * if there is only one fixed counter, only the first pmu + * can access the fixed counter + */ + if (pmu->type->single_fixed && pmu->pmu_idx > 0) + return -EINVAL; + + /* fixed counters have event field hardcoded to zero */ + hwc->config = 0ULL; + } else { + hwc->config = event->attr.config & + (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32)); + if (pmu->type->ops->hw_config) { + ret = pmu->type->ops->hw_config(box, event); + if (ret) + return ret; + } + } + + if (event->group_leader != event) + ret = uncore_validate_group(pmu, event); + else + ret = 0; + + return ret; +} + +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct zhaoxin_uncore_pmu *uncore_pmu; + struct zhaoxin_uncore_box *box; + + uncore_pmu = container_of(pmu, struct zhaoxin_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct zhaoxin_uncore_pmu *uncore_pmu; + struct zhaoxin_uncore_box *box; + + uncore_pmu = container_of(pmu, struct zhaoxin_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + +static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask); +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + +static void uncore_pmu_unregister(struct zhaoxin_uncore_pmu *pmu) +{ + if (!pmu->registered) + return; + perf_pmu_unregister(&pmu->pmu); + pmu->registered = false; +} + +static void uncore_free_boxes(struct zhaoxin_uncore_pmu *pmu) +{ + int package; + + for (package = 0; package < max_packages; package++) + kfree(pmu->boxes[package]); + kfree(pmu->boxes); +} + +static void uncore_type_exit(struct zhaoxin_uncore_type *type) +{ + struct zhaoxin_uncore_pmu *pmu = type->pmus; + int i; + + if (pmu) { + for (i = 0; i < type->num_boxes; i++, pmu++) { + uncore_pmu_unregister(pmu); + uncore_free_boxes(pmu); + } + kfree(type->pmus); + type->pmus = NULL; + } + kfree(type->events_group); + type->events_group = NULL; +} + +static void uncore_types_exit(struct zhaoxin_uncore_type **types) +{ + for (; *types; types++) + uncore_type_exit(*types); +} + +static int __init uncore_type_init(struct zhaoxin_uncore_type *type, bool setid) +{ + struct zhaoxin_uncore_pmu *pmus; + size_t size; + int i, j; + + pmus = kcalloc(type->num_boxes, sizeof(*pmus), GFP_KERNEL); + if (!pmus) + return -ENOMEM; + + size = max_packages*sizeof(struct zhaoxin_uncore_box *); + + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = setid ? i : -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + pmus[i].boxes = kzalloc(size, GFP_KERNEL); + if (!pmus[i].boxes) + goto err; + } + + type->pmus = pmus; + type->unconstrainted = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, + 0, type->num_counters, 0, 0); + + if (type->event_descs) { + struct { + struct attribute_group group; + struct attribute *attrs[]; + } *attr_group; + for (i = 0; type->event_descs[i].attr.attr.name; i++) + ; + + attr_group = kzalloc(struct_size(attr_group, attrs, i + 1), GFP_KERNEL); + if (!attr_group) + goto err; + + attr_group->group.name = "events"; + attr_group->group.attrs = attr_group->attrs; + + for (j = 0; j < i; j++) + attr_group->attrs[j] = &type->event_descs[j].attr.attr; + + type->events_group = &attr_group->group; + } + + type->pmu_group = &uncore_pmu_attr_group; + + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; +} + +static int __init +uncore_types_init(struct zhaoxin_uncore_type **types, bool setid) +{ + int ret; + + for (; *types; types++) { + ret = uncore_type_init(*types, setid); + if (ret) + return ret; + } + return 0; +} + +static void uncore_change_type_ctx(struct zhaoxin_uncore_type *type, int old_cpu, + int new_cpu) +{ + struct zhaoxin_uncore_pmu *pmu = type->pmus; + struct zhaoxin_uncore_box *box; + int i, package; + + package = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[package]; + if (!box) + continue; + + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; + } + + WARN_ON_ONCE(box->cpu != old_cpu); + box->cpu = -1; + if (new_cpu < 0) + continue; + + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu); + box->cpu = new_cpu; + } +} + +static void uncore_change_context(struct zhaoxin_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + for (; *uncores; uncores++) + uncore_change_type_ctx(*uncores, old_cpu, new_cpu); +} + +static void uncore_box_unref(struct zhaoxin_uncore_type **types, int id) +{ + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + int i; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[id]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } +} + +static int uncore_event_cpu_offline(unsigned int cpu) +{ + int package, target; + + /* Check if exiting cpu is used for collecting uncore events */ + if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) + goto unref; + /* Find a new cpu to collect uncore events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); + + /* Migrate uncore events to the new target */ + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &uncore_cpu_mask); + else + target = -1; + + uncore_change_context(uncore_msr_uncores, cpu, target); + +unref: + /* Clear the references */ + package = topology_logical_package_id(cpu); + uncore_box_unref(uncore_msr_uncores, package); + return 0; +} + +static int allocate_boxes(struct zhaoxin_uncore_type **types, + unsigned int package, unsigned int cpu) +{ + struct zhaoxin_uncore_box *box, *tmp; + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[package]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->package_id = package; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[package] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + +static int uncore_box_ref(struct zhaoxin_uncore_type **types, + int id, unsigned int cpu) +{ + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + int i, ret; + + ret = allocate_boxes(types, id, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[id]; + if (box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } + return 0; +} + +static int uncore_event_cpu_online(unsigned int cpu) +{ + int package, target, msr_ret; + + package = topology_logical_package_id(cpu); + msr_ret = uncore_box_ref(uncore_msr_uncores, package, cpu); + + if (msr_ret) + return -ENOMEM; + + /* + * Check if there is an online cpu in the package + * which collects uncore events already. + */ + target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return 0; + + cpumask_set_cpu(cpu, &uncore_cpu_mask); + + if (!msr_ret) + uncore_change_context(uncore_msr_uncores, -1, cpu); + + return 0; +} + +static int uncore_pmu_register(struct zhaoxin_uncore_pmu *pmu) +{ + int ret; + + if (!pmu->type->pmu) { + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + .module = THIS_MODULE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + }; + } else { + pmu->pmu = *pmu->type->pmu; + pmu->pmu.attr_groups = pmu->type->attr_groups; + } + + if (pmu->type->num_boxes == 1) { + if (strlen(pmu->type->name) > 0) + sprintf(pmu->name, "uncore_%s", pmu->type->name); + else + sprintf(pmu->name, "uncore"); + } else { + sprintf(pmu->name, "uncore_%s_%d", pmu->type->name, + pmu->pmu_idx); + } + + ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + if (!ret) + pmu->registered = true; + return ret; +} + +static int __init type_pmu_register(struct zhaoxin_uncore_type *type) +{ + int i, ret; + + for (i = 0; i < type->num_boxes; i++) { + ret = uncore_pmu_register(&type->pmus[i]); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_msr_pmus_register(void) +{ + struct zhaoxin_uncore_type **types = uncore_msr_uncores; + int ret; + + for (; *types; types++) { + ret = type_pmu_register(*types); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_cpu_init(void) +{ + int ret; + + ret = uncore_types_init(uncore_msr_uncores, true); + if (ret) + goto err; + + ret = uncore_msr_pmus_register(); + if (ret) + goto err; + return 0; +err: + uncore_types_exit(uncore_msr_uncores); + uncore_msr_uncores = empty_uncore; + return ret; +} + +struct zhaoxin_uncore_init_fun { + void (*cpu_init)(void); +}; + +void chx_uncore_cpu_init(void) +{ + uncore_msr_uncores = chx_msr_uncores; +} + +static const struct zhaoxin_uncore_init_fun chx_uncore_init __initconst = { + .cpu_init = chx_uncore_cpu_init, +}; + +static const struct x86_cpu_id zhaoxin_uncore_match[] __initconst = { + X86_MATCH_VENDOR_FAM_MODEL(ZHAOXIN, 7, ZHAOXIN_FAM7_ZXD, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(ZHAOXIN, 7, ZHAOXIN_FAM7_ZXE, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, ZHAOXIN_FAM7_ZXD, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, ZHAOXIN_FAM7_ZXE, &chx_uncore_init), + {}, +}; + +MODULE_DEVICE_TABLE(x86cpu, zhaoxin_uncore_match); + +static int __init zhaoxin_uncore_init(void) +{ + const struct x86_cpu_id *id; + struct zhaoxin_uncore_init_fun *uncore_init; + int cret = 0, ret; + + id = x86_match_cpu(zhaoxin_uncore_match); + + if (!id) + return -ENODEV; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + + max_packages = topology_max_packages(); + + pr_info("welcome to uncore!\n"); + + uncore_init = (struct zhaoxin_uncore_init_fun *)id->driver_data; + + if (uncore_init->cpu_init) { + uncore_init->cpu_init(); + cret = uncore_cpu_init(); + } + + if (cret) + return -ENODEV; + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/zhaoxin/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + pr_info("zhaoxin uncore init success!\n"); + if (ret) + goto err; + return 0; + +err: + uncore_types_exit(uncore_msr_uncores); + return ret; +} +module_init(zhaoxin_uncore_init); + +static void __exit zhaoxin_uncore_exit(void) +{ + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); + uncore_types_exit(uncore_msr_uncores); +} +module_exit(zhaoxin_uncore_exit); diff --git a/arch/x86/events/zhaoxin/uncore.h b/arch/x86/events/zhaoxin/uncore.h new file mode 100644 index 000000000000..e0f4ec340725 --- /dev/null +++ b/arch/x86/events/zhaoxin/uncore.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Zhaoxin PMU; like Intel Architectural PerfMon-v2 + */ +#include <linux/slab.h> +#include <linux/pci.h> +#include <asm/apicdef.h> +#include <linux/io-64-nonatomic-lo-hi.h> + +#include <linux/perf_event.h> +#include "../perf_event.h" + +#define ZHAOXIN_FAM7_ZXD 0x1b +#define ZHAOXIN_FAM7_ZXE 0x3b + +#define UNCORE_PMU_NAME_LEN 32 +#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) +#define UNCORE_CHX_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC) + + +#define UNCORE_FIXED_EVENT 0xff +#define UNCORE_PMC_IDX_MAX_GENERIC 4 +#define UNCORE_PMC_IDX_MAX_FIXED 1 +#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC + +#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) + +struct zhaoxin_uncore_ops; +struct zhaoxin_uncore_pmu; +struct zhaoxin_uncore_box; +struct uncore_event_desc; + +struct zhaoxin_uncore_type { + const char *name; + int num_counters; + int num_boxes; + int perf_ctr_bits; + int fixed_ctr_bits; + unsigned int perf_ctr; + unsigned int event_ctl; + unsigned int event_mask; + unsigned int event_mask_ext; + unsigned int fixed_ctr; + unsigned int fixed_ctl; + unsigned int box_ctl; + unsigned int msr_offset; + unsigned int num_shared_regs:8; + unsigned int single_fixed:1; + unsigned int pair_ctr_ctl:1; + unsigned int *msr_offsets; + struct event_constraint unconstrainted; + struct event_constraint *constraints; + struct zhaoxin_uncore_pmu *pmus; + struct zhaoxin_uncore_ops *ops; + struct uncore_event_desc *event_descs; + const struct attribute_group *attr_groups[4]; + struct pmu *pmu; /* for custom pmu ops */ +}; + +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] + +struct zhaoxin_uncore_ops { + void (*init_box)(struct zhaoxin_uncore_box *); + void (*exit_box)(struct zhaoxin_uncore_box *); + void (*disable_box)(struct zhaoxin_uncore_box *); + void (*enable_box)(struct zhaoxin_uncore_box *); + void (*disable_event)(struct zhaoxin_uncore_box *, struct perf_event *); + void (*enable_event)(struct zhaoxin_uncore_box *, struct perf_event *); + u64 (*read_counter)(struct zhaoxin_uncore_box *, struct perf_event *); + int (*hw_config)(struct zhaoxin_uncore_box *, struct perf_event *); + struct event_constraint *(*get_constraint)(struct zhaoxin_uncore_box *, + struct perf_event *); + void (*put_constraint)(struct zhaoxin_uncore_box *, struct perf_event *); +}; + +struct zhaoxin_uncore_pmu { + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + bool registered; + atomic_t activeboxes; + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_box **boxes; +}; + +struct zhaoxin_uncore_extra_reg { + raw_spinlock_t lock; + u64 config, config1, config2; + atomic_t ref; +}; + +struct zhaoxin_uncore_box { + int pci_phys_id; + int package_id; /*Package ID */ + int n_active; /* number of active events */ + int n_events; + int cpu; /* cpu to collect events */ + unsigned long flags; + atomic_t refcnt; + struct perf_event *events[UNCORE_PMC_IDX_MAX]; + struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX]; + unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + u64 tags[UNCORE_PMC_IDX_MAX]; + struct pci_dev *pci_dev; + struct zhaoxin_uncore_pmu *pmu; + u64 hrtimer_duration; /* hrtimer timeout for this box */ + struct hrtimer hrtimer; + struct list_head list; + struct list_head active_list; + void __iomem *io_addr; + struct zhaoxin_uncore_extra_reg shared_regs[0]; +}; + +#define UNCORE_BOX_FLAG_INITIATED 0 + +struct uncore_event_desc { + struct device_attribute attr; + const char *config; +}; + +ssize_t zx_uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); + +#define ZHAOXIN_UNCORE_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, zx_uncore_event_show, NULL), \ + .config = _config, \ +} + +#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct device_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __uncore_##_var##_show, NULL) + +static inline bool uncore_pmc_fixed(int idx) +{ + return idx == UNCORE_PMC_IDX_FIXED; +} + +static inline unsigned int uncore_msr_box_offset(struct zhaoxin_uncore_box *box) +{ + struct zhaoxin_uncore_pmu *pmu = box->pmu; + + return pmu->type->msr_offsets ? + pmu->type->msr_offsets[pmu->pmu_idx] : + pmu->type->msr_offset * pmu->pmu_idx; +} + +static inline unsigned int uncore_msr_box_ctl(struct zhaoxin_uncore_box *box) +{ + if (!box->pmu->type->box_ctl) + return 0; + return box->pmu->type->box_ctl + uncore_msr_box_offset(box); +} + +static inline unsigned int uncore_msr_fixed_ctl(struct zhaoxin_uncore_box *box) +{ + if (!box->pmu->type->fixed_ctl) + return 0; + return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box); +} + +static inline unsigned int uncore_msr_fixed_ctr(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_msr_event_ctl(struct zhaoxin_uncore_box *box, int idx) +{ + return box->pmu->type->event_ctl + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_msr_perf_ctr(struct zhaoxin_uncore_box *box, int idx) +{ + return box->pmu->type->perf_ctr + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_fixed_ctl(struct zhaoxin_uncore_box *box) +{ + return uncore_msr_fixed_ctl(box); +} + +static inline +unsigned int uncore_fixed_ctr(struct zhaoxin_uncore_box *box) +{ + return uncore_msr_fixed_ctr(box); +} + +static inline +unsigned int uncore_event_ctl(struct zhaoxin_uncore_box *box, int idx) +{ + return uncore_msr_event_ctl(box, idx); +} + +static inline +unsigned int uncore_perf_ctr(struct zhaoxin_uncore_box *box, int idx) +{ + return uncore_msr_perf_ctr(box, idx); +} + +static inline int uncore_perf_ctr_bits(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->perf_ctr_bits; +} + +static inline int uncore_fixed_ctr_bits(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->fixed_ctr_bits; +} + +static inline int uncore_num_counters(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->num_counters; +} + +static inline void uncore_disable_box(struct zhaoxin_uncore_box *box) +{ + if (box->pmu->type->ops->disable_box) + box->pmu->type->ops->disable_box(box); +} + +static inline void uncore_enable_box(struct zhaoxin_uncore_box *box) +{ + if (box->pmu->type->ops->enable_box) + box->pmu->type->ops->enable_box(box); +} + +static inline void uncore_disable_event(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->disable_event(box, event); +} + +static inline void uncore_enable_event(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->enable_event(box, event); +} + +static inline u64 uncore_read_counter(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + return box->pmu->type->ops->read_counter(box, event); +} + +static inline void uncore_box_init(struct zhaoxin_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + +static inline void uncore_box_exit(struct zhaoxin_uncore_box *box) +{ + if (test_and_clear_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->exit_box) + box->pmu->type->ops->exit_box(box); + } +} + +static inline bool uncore_box_is_fake(struct zhaoxin_uncore_box *box) +{ + return (box->package_id < 0); +} + +static inline struct zhaoxin_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct zhaoxin_uncore_pmu, pmu); +} + +static inline struct zhaoxin_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + return event->pmu_private; +} + + +static struct zhaoxin_uncore_box *uncore_pmu_to_box(struct zhaoxin_uncore_pmu *pmu, int cpu); +static u64 uncore_msr_read_counter(struct zhaoxin_uncore_box *box, struct perf_event *event); + +static void uncore_pmu_start_hrtimer(struct zhaoxin_uncore_box *box); +static void uncore_pmu_cancel_hrtimer(struct zhaoxin_uncore_box *box); +static void uncore_pmu_event_start(struct perf_event *event, int flags); +static void uncore_pmu_event_stop(struct perf_event *event, int flags); +static int uncore_pmu_event_add(struct perf_event *event, int flags); +static void uncore_pmu_event_del(struct perf_event *event, int flags); +static void uncore_pmu_event_read(struct perf_event *event); +static void uncore_perf_event_update(struct zhaoxin_uncore_box *box, struct perf_event *event); +struct event_constraint * +uncore_get_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event); +void uncore_put_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event); +u64 uncore_shared_reg_config(struct zhaoxin_uncore_box *box, int idx); + +void chx_uncore_cpu_init(void); -- 2.20.1

1 0

[PATCH OLK-5.10] iommu/vt-d:Add support for detecting ACPI device in RMRR
by LeoLiuoc 09 Jul '21

09 Jul '21

Some ACPI devices need to issue dma requests to access the reserved memory area.BIOS uses the device scope type ACPI_NAMESPACE_DEVICE in RMRR to report these ACPI devices. This patch add support for detecting ACPI devices in RMRR and in order to distinguish it from PCI device, some interface functions are modified. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/iommu/intel/dmar.c | 77 +++++++++++++++++++-------------- drivers/iommu/intel/iommu.c | 86 ++++++++++++++++++++++++++++++++++--- drivers/iommu/iommu.c | 6 +++ include/linux/dmar.h | 11 ++++- include/linux/iommu.h | 3 ++ 5 files changed, 142 insertions(+), 41 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b8d0b56a7575..1d705589fe21 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -215,7 +215,7 @@ static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus, } /* Return: > 0 if match found, 0 if no match found, < 0 if error happens */ -int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, +int dmar_pci_insert_dev_scope(struct dmar_pci_notify_info *info, void *start, void*end, u16 segment, struct dmar_dev_scope *devices, int devices_cnt) @@ -304,7 +304,7 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info) drhd = container_of(dmaru->hdr, struct acpi_dmar_hardware_unit, header); - ret = dmar_insert_dev_scope(info, (void *)(drhd + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(drhd + 1), ((void *)drhd) + drhd->header.length, dmaru->segment, dmaru->devices, dmaru->devices_cnt); @@ -719,47 +719,58 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev) return dmaru; } -static void __init dmar_acpi_insert_dev_scope(u8 device_number, - struct acpi_device *adev) +/* Return: > 0 if match found, 0 if no match found */ +bool dmar_acpi_insert_dev_scope(u8 device_number, + struct acpi_device *adev, + void *start, void *end, + struct dmar_dev_scope *devices, + int devices_cnt) { - struct dmar_drhd_unit *dmaru; - struct acpi_dmar_hardware_unit *drhd; struct acpi_dmar_device_scope *scope; struct device *tmp; int i; struct acpi_dmar_pci_path *path; + for (; start < end; start += scope->length) { + scope = start; + if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE) + continue; + if (scope->enumeration_id != device_number) + continue; + path = (void *)(scope + 1); + for_each_dev_scope(devices, devices_cnt, i, tmp) + if (tmp == NULL) { + devices[i].bus = scope->bus; + devices[i].devfn = PCI_DEVFN(path->device, path->function); + rcu_assign_pointer(devices[i].dev, + get_device(&adev->dev)); + return true; + } + WARN_ON(i >= devices_cnt); + } + return false; +} + +static int dmar_acpi_bus_add_dev(u8 device_number, struct acpi_device *adev) +{ + struct dmar_drhd_unit *dmaru; + struct acpi_dmar_hardware_unit *drhd; + int ret; + for_each_drhd_unit(dmaru) { drhd = container_of(dmaru->hdr, struct acpi_dmar_hardware_unit, header); - - for (scope = (void *)(drhd + 1); - (unsigned long)scope < ((unsigned long)drhd) + drhd->header.length; - scope = ((void *)scope) + scope->length) { - if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE) - continue; - if (scope->enumeration_id != device_number) - continue; - - path = (void *)(scope + 1); - pr_info("ACPI device \"%s\" under DMAR at %llx as %02x:%02x.%d\n", - dev_name(&adev->dev), dmaru->reg_base_addr, - scope->bus, path->device, path->function); - for_each_dev_scope(dmaru->devices, dmaru->devices_cnt, i, tmp) - if (tmp == NULL) { - dmaru->devices[i].bus = scope->bus; - dmaru->devices[i].devfn = PCI_DEVFN(path->device, - path->function); - rcu_assign_pointer(dmaru->devices[i].dev, - get_device(&adev->dev)); - return; - } - BUG_ON(i >= dmaru->devices_cnt); - } + ret = dmar_acpi_insert_dev_scope(device_number, adev, (void *)(drhd+1), + ((void *)drhd)+drhd->header.length, + dmaru->devices, dmaru->devices_cnt); + if (ret) + break; } - pr_warn("No IOMMU scope found for ANDD enumeration ID %d (%s)\n", - device_number, dev_name(&adev->dev)); + if (ret > 0) + ret = dmar_rmrr_add_acpi_dev(device_number, adev); + + return ret; } static int __init dmar_acpi_dev_scope_init(void) @@ -788,7 +799,7 @@ static int __init dmar_acpi_dev_scope_init(void) andd->device_name); continue; } - dmar_acpi_insert_dev_scope(andd->device_number, adev); + dmar_acpi_bus_add_dev(andd->device_number, adev); } } return 0; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6cc6ef585aa4..5f2b7a64d2c7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4600,6 +4600,25 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev) return ret; } +int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev) +{ + int ret; + struct dmar_rmrr_unit *rmrru; + struct acpi_dmar_reserved_memory *rmrr; + + list_for_each_entry(rmrru, &dmar_rmrr_units, list) { + rmrr = container_of(rmrru->hdr, + struct acpi_dmar_reserved_memory, + header); + ret = dmar_acpi_insert_dev_scope(device_number, adev, (void *)(rmrr + 1), + ((void *)rmrr) + rmrr->header.length, + rmrru->devices, rmrru->devices_cnt); + if (ret) + break; + } + return 0; +} + int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { int ret; @@ -4615,7 +4634,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrr = container_of(rmrru->hdr, struct acpi_dmar_reserved_memory, header); if (info->event == BUS_NOTIFY_ADD_DEVICE) { - ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(rmrr + 1), ((void *)rmrr) + rmrr->header.length, rmrr->segment, rmrru->devices, rmrru->devices_cnt); @@ -4633,7 +4652,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header); if (info->event == BUS_NOTIFY_ADD_DEVICE) { - ret = dmar_insert_dev_scope(info, (void *)(atsr + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(atsr + 1), (void *)atsr + atsr->header.length, atsr->segment, atsru->devices, atsru->devices_cnt); @@ -4872,6 +4891,22 @@ static int __init platform_optin_force_iommu(void) return 1; } +static int acpi_device_create_direct_mappings(struct device *pn_dev, struct device *acpi_device) +{ + struct iommu_group *group; + + acpi_device->bus->iommu_ops = &intel_iommu_ops; + group = iommu_group_get(pn_dev); + if (!group) { + pr_warn("ACPI name space devices create direct mappings wrong!\n"); + return -EINVAL; + } + printk(KERN_INFO "pn_dev:%s enter to %s\n", dev_name(pn_dev), __func__); + __acpi_device_create_direct_mappings(group, acpi_device); + + return 0; +} + static int __init probe_acpi_namespace_devices(void) { struct dmar_drhd_unit *drhd; @@ -4879,6 +4914,7 @@ static int __init probe_acpi_namespace_devices(void) struct intel_iommu *iommu __maybe_unused; struct device *dev; int i, ret = 0; + u8 bus, devfn; for_each_active_iommu(iommu, drhd) { for_each_active_dev_scope(drhd->devices, @@ -4887,6 +4923,8 @@ static int __init probe_acpi_namespace_devices(void) struct iommu_group *group; struct acpi_device *adev; + struct device *pn_dev = NULL; + struct device_domain_info *info = NULL; if (dev->bus != &acpi_bus_type) continue; @@ -4896,19 +4934,53 @@ static int __init probe_acpi_namespace_devices(void) &adev->physical_node_list, node) { group = iommu_group_get(pn->dev); if (group) { + pn_dev = pn->dev; iommu_group_put(group); continue; } - pn->dev->bus->iommu_ops = &intel_iommu_ops; - ret = iommu_probe_device(pn->dev); - if (ret) - break; + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + if (!info) { + pn->dev->bus->iommu_ops = &intel_iommu_ops; + ret = iommu_probe_device(pn->dev); + if (ret) { + pr_err("pn->dev:%s probe fail! ret:%d\n", + dev_name(pn->dev), ret); + goto unlock; + } + } + pn_dev = pn->dev; + } + if (!pn_dev) { + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + if (!info) { + dev->bus->iommu_ops = &intel_iommu_ops; + ret = iommu_probe_device(dev); + if (ret) { + pr_err("dev:%s probe fail! ret:%d\n", + dev_name(dev), ret); + goto unlock; + } + goto unlock; + } } + if (!info) + ret = acpi_device_create_direct_mappings(pn_dev, dev); + else + ret = acpi_device_create_direct_mappings(info->dev, dev); +unlock: mutex_unlock(&adev->physical_node_lock); - if (ret) + if (ret) { + pr_err("%s fail! ret:%d\n", __func__, ret); return ret; + } } } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 86e3dbdfb7bd..6212eb1856f5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -814,6 +814,12 @@ static bool iommu_is_attach_deferred(struct iommu_domain *domain, return false; } +void __acpi_device_create_direct_mappings(struct iommu_group *group, struct device *acpi_device) +{ + iommu_create_device_direct_mappings(group, acpi_device); +} +EXPORT_SYMBOL_GPL(__acpi_device_create_direct_mappings); + /** * iommu_group_add_device - add a device to an iommu group * @group: the group into which to add the device (reference should be held) diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 65565820328a..248e3c2feeae 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -113,10 +113,13 @@ extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, struct dmar_dev_scope **devices, u16 segment); extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt); extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt); -extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, +extern int dmar_pci_insert_dev_scope(struct dmar_pci_notify_info *info, void *start, void*end, u16 segment, struct dmar_dev_scope *devices, int devices_cnt); +extern bool dmar_acpi_insert_dev_scope(u8 device_number, + struct acpi_device *adev, void *start, void *end, + struct dmar_dev_scope *devices, int devices_cnt); extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment, struct dmar_dev_scope *devices, int count); @@ -140,6 +143,7 @@ extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); +extern int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); #else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } @@ -150,6 +154,11 @@ static inline void intel_iommu_shutdown(void) { } #define dmar_check_one_atsr dmar_res_noop #define dmar_release_one_atsr dmar_res_noop +static inline int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev) +{ + return 0; +} + static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { return 0; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 3ff424d4f481..66ae2b7d65de 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -546,6 +546,9 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); +extern void __acpi_device_create_direct_mappings(struct iommu_group *group, + struct device *acpi_device); + static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { if (domain->ops->flush_iotlb_all) -- 2.20.1

1 0

[PATCH OLK-5.10] USB:Fix kernel NULL pointer when unbind UHCI form vfio-pci
by LeoLiuoc 09 Jul '21

09 Jul '21

This bug is found in Zhaoxin platform, but it's a commom code bug. Fail sequence: step1: Unbind UHCI controller from native driver; step2: Bind UHCI controller to vfio-pci, which will put UHCI controller in one vfio group's device list and set UHCI's dev->driver_data to struct vfio-pci(for UHCI) step3: Unbind EHCI controller from native driver, will try to tell UHCI native driver that "I'm removed by set companion_hcd->self.hs_companion to NULL. However, companion_hcd get from UHCI's dev->driver_data that has modified by vfio-pci already.So, the vfio-pci structure will be damaged! step4: Bind EHCI controller to vfio-pci driver, which will put EHCI controller in the same vfio group as UHCI controller; ... ... step5: Unbind UHCI controller from vfio-pci, which will delete UHCI from vfio group' device list that has been damaged in step 3. So,delete operation can random result into a NULL pointer dereference with the below stack dump. step6: Bind UHCI controller to native driver; step7: Unbind EHCI controller from vfio-pci, which will try to remove EHCI controller from the vfio group; step8: Bind EHCI controller to native driver; [ 929.114641] uhci_hcd 0000:00:10.0: remove, state 1 [ 929.114652] usb usb1: USB disconnect, device number 1 [ 929.114655] usb 1-1: USB disconnect, device number 2 [ 929.270313] usb 1-2: USB disconnect, device number 3 [ 929.318404] uhci_hcd 0000:00:10.0: USB bus 1 deregistered [ 929.343029] uhci_hcd 0000:00:10.1: remove, state 4 [ 929.343045] usb usb3: USB disconnect, device number 1 [ 929.343685] uhci_hcd 0000:00:10.1: USB bus 3 deregistered [ 929.369087] ehci-pci 0000:00:10.7: remove, state 4 [ 929.369102] usb usb4: USB disconnect, device number 1 [ 929.370325] ehci-pci 0000:00:10.7: USB bus 4 deregistered [ 932.398494] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 932.398496] PGD 42a67d067 P4D 42a67d067 PUD 42a65f067 PMD 0 [ 932.398502] Oops: 0002 [#2] SMP NOPTI [ 932.398505] CPU: 2 PID: 7824 Comm: vfio_unbind.sh Tainted: P D 4.19.65-2020051917-rainos #1 [ 932.398506] Hardware name: Shanghai Zhaoxin Semiconductor Co., Ltd. HX002EH/HX002EH, BIOS HX002EH0_01_R480_R_200408 04/08/2020 [ 932.398513] RIP: 0010:vfio_device_put+0x31/0xa0 [vfio] [ 932.398515] Code: 89 e5 41 54 53 4c 8b 67 18 48 89 fb 49 8d 74 24 30 e8 e3 0e f3 de 84 c0 74 67 48 8b 53 20 48 8b 43 28 48 8b 7b 18 48 89 42 08 <48> 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 43 20 48 b8 00 02 00 [ 932.398516] RSP: 0018:ffffbbfd04cffc18 EFLAGS: 00010202 [ 932.398518] RAX: 0000000000000000 RBX: ffff92c7ea717880 RCX: 0000000000000000 [ 932.398519] RDX: ffff92c7ea713620 RSI: ffff92c7ea713630 RDI: ffff92c7ea713600 [ 932.398521] RBP: ffffbbfd04cffc28 R08: ffff92c7f02a8080 R09: ffff92c7efc03980 [ 932.398522] R10: ffffbbfd04cff9a8 R11: 0000000000000000 R12: ffff92c7ea713600 [ 932.398523] R13: ffff92c7ed8bb0a8 R14: ffff92c7ea717880 R15: 0000000000000000 [ 932.398525] FS: 00007f3031500740(0000) GS:ffff92c7f0280000(0000) knlGS:0000000000000000 [ 932.398526] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 932.398527] CR2: 0000000000000000 CR3: 0000000428626004 CR4: 0000000000160ee0 [ 932.398528] Call Trace: [ 932.398534] vfio_del_group_dev+0xe8/0x2a0 [vfio] [ 932.398539] ? __blocking_notifier_call_chain+0x52/0x60 [ 932.398542] ? do_wait_intr_irq+0x90/0x90 [ 932.398546] ? iommu_bus_notifier+0x75/0x100 [ 932.398551] vfio_pci_remove+0x20/0xa0 [vfio_pci] [ 932.398554] pci_device_remove+0x3e/0xc0 [ 932.398557] device_release_driver_internal+0x17a/0x240 [ 932.398560] device_release_driver+0x12/0x20 [ 932.398561] unbind_store+0xee/0x180 [ 932.398564] drv_attr_store+0x27/0x40 [ 932.398567] sysfs_kf_write+0x3c/0x50 [ 932.398568] kernfs_fop_write+0x125/0x1a0 [ 932.398572] __vfs_write+0x3a/0x190 [ 932.398575] ? apparmor_file_permission+0x1a/0x20 [ 932.398577] ? security_file_permission+0x3b/0xc0 [ 932.398581] ? _cond_resched+0x1a/0x50 [ 932.398582] vfs_write+0xb8/0x1b0 [ 932.398584] ksys_write+0x5c/0xe0 [ 932.398586] __x64_sys_write+0x1a/0x20 [ 932.398589] do_syscall_64+0x5a/0x110 [ 932.398592] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Using virt-manager/qemu to boot guest os, we can see the same fail sequence! Fix this by determine whether the PCI Driver of the USB controller is a kernel native driver. If not, do not let it modify UHCI's dev->driver_data. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/core/hcd-pci.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index ec0d6c50610c..000ee7a6731f 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -49,6 +49,7 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, struct pci_dev *companion; struct usb_hcd *companion_hcd; unsigned int slot = PCI_SLOT(pdev->devfn); + struct pci_driver *drv; /* * Iterate through other PCI functions in the same slot. @@ -61,6 +62,15 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, PCI_SLOT(companion->devfn) != slot) continue; + drv = companion->driver; + if (!drv) + continue; + + if (strncmp(drv->name, "uhci_hcd", sizeof("uhci_hcd") - 1) && + strncmp(drv->name, "ooci_hcd", sizeof("uhci_hcd") - 1) && + strncmp(drv->name, "ehci_hcd", sizeof("uhci_hcd") - 1)) + continue; + /* * Companion device should be either UHCI,OHCI or EHCI host * controller, otherwise skip. -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: fix issue with resume from system Sx state
by LeoLiuoc 09 Jul '21

09 Jul '21

On Zhaoxin ZX-100 project, xHCI can't work normally after resume from system Sx state. To fix this issue, when resume from system sx state, reinitialize xHCI instead of restore. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 471cf3e96032..44dd77343cc1 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -307,6 +307,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_TI && pdev->device == 0x8241) xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_7; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN && pdev->device == 0x9202) + xhci->quirks |= XHCI_RESET_ON_RESUME; + if ((pdev->vendor == PCI_VENDOR_ID_BROADCOM || pdev->vendor == PCI_VENDOR_ID_CAVIUM) && pdev->device == 0x9026) -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Adjust the UHCI Controllers bit value
by LeoLiuoc 09 Jul '21

09 Jul '21

Over Current condition is not standardized in the UHCI spec. Zhaoxin UHCI controllers report Over Current active off. Intel controllers report it active on, so we'll adjust the bit value. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/uhci-pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 9b88745d247f..d90c391d4899 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -134,6 +134,9 @@ static int uhci_pci_init(struct usb_hcd *hcd) if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_INTEL) device_set_wakeup_capable(uhci_dev(uhci), true); + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) + uhci->oc_low = 1; + /* Set up pointers to PCI-specific functions */ uhci->reset_hc = uhci_pci_reset_hc; uhci->check_and_reset_hc = uhci_pci_check_and_reset_hc; -- 2.20.1

1 0

[PATCH OLK-5.10 3/3] ALSA: hda: Add support of Zhaoxin NB HDAC codec
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin NB HDAC codec support. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/patch_hdmi.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 6d2a4dfcfe43..f541aeb4ecca 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4249,6 +4249,20 @@ static int patch_via_hdmi(struct hda_codec *codec) return patch_simple_hdmi(codec, VIAHDMI_CVT_NID, VIAHDMI_PIN_NID); } +/* ZHAOXIN HDMI Implementation */ +static int patch_zx_hdmi(struct hda_codec *codec) +{ + int err; + + err = patch_generic_hdmi(codec); + codec->no_sticky_stream = 1; + + if (err) + return err; + + return 0; +} + /* * patch entries */ @@ -4342,6 +4356,12 @@ HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f84, "VX11 HDMI/DP", patch_generic_hdmi), HDA_CODEC_ENTRY(0x11069f85, "VX11 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f86, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f87, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f88, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f89, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f8a, "CHX002 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f8b, "CHX002 HDMI/DP", patch_zx_hdmi), HDA_CODEC_ENTRY(0x80860054, "IbexPeak HDMI", patch_i915_cpt_hdmi), HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862801, "Bearlake HDMI", patch_generic_hdmi), @@ -4369,6 +4389,12 @@ HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x808629fb, "Crestline HDMI", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f86, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f87, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f88, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f89, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f8a, "CHX002 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f8b, "CHX002 HDMI/DP", patch_zx_hdmi), /* special ID for generic HDMI */ HDA_CODEC_ENTRY(HDA_CODEC_ID_GENERIC_HDMI, "Generic HDMI", patch_generic_hdmi), {} /* terminator */ -- 2.20.1

1 0

[PATCH OLK-5.10 2/3] ALSA: hda: Add support of Zhaoxin NB HDAC
by LeoLiuoc 09 Jul '21

09 Jul '21

Add the new PCI ID 0x1d17 0x9141/0x9142/0x9144 Zhaoxin NB HDAC support. And add some special initialization for Zhaoxin NB HDAC. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/hda_controller.c | 17 ++++++++++- sound/pci/hda/hda_controller.h | 2 ++ sound/pci/hda/hda_intel.c | 53 +++++++++++++++++++++++++++++++++- 3 files changed, 70 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index b972d59eb1ec..d6de0b1fcb66 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1057,6 +1057,16 @@ void azx_stop_chip(struct azx *chip) } EXPORT_SYMBOL_GPL(azx_stop_chip); +static void azx_rirb_zxdelay(struct azx *chip, int enable) +{ + if (chip->remap_diu_addr) { + if (!enable) + writel(0x0, (char *)chip->remap_diu_addr + 0x490a8); + else + writel(0x1000000, (char *)chip->remap_diu_addr + 0x490a8); + } +} + /* * interrupt handler */ @@ -1116,9 +1126,14 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); active = true; if (status & RIRB_INT_RESPONSE) { - if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) + if ((chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) || + (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY)) { + azx_rirb_zxdelay(chip, 1); udelay(80); + } snd_hdac_bus_update_rirb(bus); + if (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY) + azx_rirb_zxdelay(chip, 0); } } } while (active && ++repeat < 10); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 68f9668788ea..543b9f75cf42 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -45,6 +45,7 @@ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ +#define AZX_DCAPS_RIRB_PRE_DELAY (1 << 31) enum { AZX_SNOOP_TYPE_NONE, @@ -147,6 +148,7 @@ struct azx { /* GTS present */ unsigned int gts_present:1; + void __iomem *remap_diu_addr; #ifdef CONFIG_SND_HDA_DSP_LOADER struct azx_dev saved_azx_dev; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 8ff7902ec6e6..5ac2e95fd5fa 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -241,7 +241,8 @@ MODULE_SUPPORTED_DEVICE("{{Intel, ICH6}," "{VIA, VT8251}," "{VIA, VT8237A}," "{ULI, M5461}," - "{ZX, ZhaoxinHDA}}"); + "{ZX, ZhaoxinHDA}," + "{ZX, ZhaoxinHDMI}}"); MODULE_DESCRIPTION("Intel HDA driver"); #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO) @@ -273,6 +274,7 @@ enum { AZX_DRIVER_CTHDA, AZX_DRIVER_CMEDIA, AZX_DRIVER_ZHAOXIN, + AZX_DRIVER_ZXHDMI, AZX_DRIVER_GENERIC, AZX_NUM_DRIVERS, /* keep this as last entry */ }; @@ -390,6 +392,7 @@ static const char * const driver_short_names[] = { [AZX_DRIVER_CTHDA] = "HDA Creative", [AZX_DRIVER_CMEDIA] = "HDA C-Media", [AZX_DRIVER_ZHAOXIN] = "HDA Zhaoxin", + [AZX_DRIVER_ZXHDMI] = "HDA Zhaoxin GFX", [AZX_DRIVER_GENERIC] = "HD-Audio Generic", }; @@ -411,6 +414,29 @@ static void update_pci_byte(struct pci_dev *pci, unsigned int reg, pci_write_config_byte(pci, reg, data); } +static int azx_init_chip_zx(struct azx *chip) +{ + struct snd_card *card = chip->card; + unsigned int diu_reg; + struct pci_dev *diu_pci = NULL; + + diu_pci = pci_get_device(0x1d17, 0x3a03, NULL); + if (!diu_pci) { + dev_err(card->dev, "hda no chx001 device.\n"); + return -ENXIO; + } + pci_read_config_dword(diu_pci, PCI_BASE_ADDRESS_0, &diu_reg); + chip->remap_diu_addr = ioremap(diu_reg, 0x50000); + dev_info(card->dev, "hda %x %p\n", diu_reg, chip->remap_diu_addr); + return 0; +} + +static void azx_free_chip_zx(struct azx *chip) +{ + if (chip->remap_diu_addr) + iounmap(chip->remap_diu_addr); +} + static void azx_init_pci(struct azx *chip) { int snoop_type = azx_get_snoop_type(chip); @@ -1386,6 +1412,9 @@ static void azx_free(struct azx *chip) hda->init_failed = 1; /* to be sure */ complete_all(&hda->probe_wait); + if (chip->driver_type == AZX_DRIVER_ZXHDMI) + azx_free_chip_zx(chip); + if (use_vga_switcheroo(hda)) { if (chip->disabled && hda->probe_continued) snd_hda_unlock_devices(&chip->bus); @@ -1786,6 +1815,8 @@ static int default_bdl_pos_adj(struct azx *chip) case AZX_DRIVER_ICH: case AZX_DRIVER_PCH: return 1; + case AZX_DRIVER_ZXHDMI: + return 128; default: return 32; } @@ -1903,6 +1934,11 @@ static int azx_first_init(struct azx *chip) } #endif + chip->remap_diu_addr = NULL; + + if (chip->driver_type == AZX_DRIVER_ZXHDMI) + azx_init_chip_zx(chip); + err = pci_request_regions(pci, "ICH HD audio"); if (err < 0) return err; @@ -2011,6 +2047,7 @@ static int azx_first_init(struct azx *chip) chip->playback_streams = ATIHDMI_NUM_PLAYBACK; chip->capture_streams = ATIHDMI_NUM_CAPTURE; break; + case AZX_DRIVER_ZXHDMI: case AZX_DRIVER_GENERIC: default: chip->playback_streams = ICH6_NUM_PLAYBACK; @@ -2732,6 +2769,13 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE(0x1106, 0x9170), .driver_data = AZX_DRIVER_GENERIC }, /* VIA GFX VT6122/VX11 */ { PCI_DEVICE(0x1106, 0x9140), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1106, 0x9141), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1106, 0x9142), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, + { PCI_DEVICE(0x1106, 0x9144), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, /* SIS966 */ { PCI_DEVICE(0x1039, 0x7502), .driver_data = AZX_DRIVER_SIS }, /* ULI M5461 */ @@ -2787,6 +2831,13 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI }, /* Zhaoxin */ { PCI_DEVICE(0x1d17, 0x3288), .driver_data = AZX_DRIVER_ZHAOXIN }, + { PCI_DEVICE(0x1d17, 0x9141), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1d17, 0x9142), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, + { PCI_DEVICE(0x1d17, 0x9144), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, { 0, } }; MODULE_DEVICE_TABLE(pci, azx_ids); -- 2.20.1

1 0

[PATCH OLK-5.10 1/3] ALSA: hda: Add Zhaoxin SB HDAC non snoop path support
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin SB HDAC non snoop path support. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/hda_intel.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4c8b281c3992..8ff7902ec6e6 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -240,8 +240,8 @@ MODULE_SUPPORTED_DEVICE("{{Intel, ICH6}," "{ATI, RV770}," "{VIA, VT8251}," "{VIA, VT8237A}," - "{SiS, SIS966}," - "{ULI, M5461}}"); + "{ULI, M5461}," + "{ZX, ZhaoxinHDA}}"); MODULE_DESCRIPTION("Intel HDA driver"); #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO) @@ -1744,6 +1744,15 @@ static void azx_check_snoop_available(struct azx *chip) snoop = false; } + if (azx_get_snoop_type(chip) == AZX_SNOOP_TYPE_NONE && + chip->driver_type == AZX_DRIVER_ZHAOXIN) { + u8 val1; + + pci_read_config_byte(chip->pci, 0x42, &val1); + if (!(val1 & 0x80) && chip->pci->revision == 0x20) + snoop = false; + } + if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF) snoop = false; -- 2.20.1

1 0

[PATCH OLK-5.10 0/3] Add support of Zhaoxin HDAC and codec
by LeoLiuoc 09 Jul '21

09 Jul '21

Zhaoxin have new SB & NB HDAC controller. And have new NB HDAC codec. This patch set add support for them. LeoLiu-oc (3): ALSA: hda: Add Zhaoxin SB HDAC non snoop path support ALSA: hda: Add support of Zhaoxin NB HDAC ALSA: hda: Add support of Zhaoxin NB HDAC codec sound/pci/hda/hda_controller.c | 17 ++++++++- sound/pci/hda/hda_controller.h | 2 ++ sound/pci/hda/hda_intel.c | 64 ++++++++++++++++++++++++++++++++-- sound/pci/hda/patch_hdmi.c | 26 ++++++++++++++ 4 files changed, 106 insertions(+), 3 deletions(-) -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Show Zhaoxin XHCI root hub speed correctly
by LeoLiuoc 09 Jul '21

09 Jul '21

Some Zhaoxin xHCI controllers follow usb3.1 spec, but only support gen1 speed 5G. While in Linux kernel, if xHCI suspport usb3.1,root hub speed will show on 10G. To fix this issue, read usb speed ID supported by xHCI to determine root hub speed. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a834f3927bee..e9d67ee299d9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5186,6 +5186,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) */ struct device *dev = hcd->self.sysdev; unsigned int minor_rev; + u8 i, j; int retval; /* Accept arbitrarily long scatter-gather lists */ @@ -5240,6 +5241,24 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; break; } + + /* usb3.1 has gen1 and gen2, Some zx's xHCI controller that follow usb3.1 spec + * but only support gen1 + */ + if (xhci->quirks & XHCI_ZHAOXIN_HOST) { + minor_rev = 0; + for (j = 0; j < xhci->num_port_caps; j++) { + for (i = 0; i < xhci->port_caps[j].psi_count; i++) { + if (XHCI_EXT_PORT_PSIV(xhci->port_caps[j].psi[i]) >= 5) + minor_rev = 1; + } + if (minor_rev != 1) { + hcd->speed = HCD_USB3; + hcd->self.root_hub->speed = USB_SPEED_SUPER; + } + } + } + xhci_info(xhci, "Host supports USB 3.%x %sSuperSpeed\n", minor_rev, minor_rev ? "Enhanced " : ""); -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: fix issue of cross page boundary in TRB prefetch
by LeoLiuoc 09 Jul '21

09 Jul '21

On some Zhaoxin platforms, xHCI will prefetch TRB for performance improvement. However this TRB prefetch mechanism may cross page boundary, which may access memory not belong to xHCI. In order to fix this issue, using two pages for TRB allocate and only the first page will be used. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-mem.c | 10 +++++++++- drivers/usb/host/xhci-pci.c | 5 +++++ drivers/usb/host/xhci.h | 1 + 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 8ce043e6ed87..67329b4188cf 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2458,8 +2458,16 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) * and our use of dma addresses in the trb_address_map radix tree needs * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need. */ - xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + /* With xHCI TRB prefetch patch:To fix cross page boundary access issue + * in IOV environment + */ + if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH) { + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + TRB_SEGMENT_SIZE*2, TRB_SEGMENT_SIZE*2, xhci->page_size*2); + } else { + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size); + } /* See Table 46 and Note on Figure 55 */ xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index e78316ed99d4..471cf3e96032 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -281,6 +281,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483) xhci->quirks |= XHCI_LPM_SUPPORT; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN && + (pdev->device == 0x9202 || + pdev->device == 0x9203)) + xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) xhci->quirks |= XHCI_BROKEN_STREAMS; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 576cafb5d873..e215431f927a 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1881,6 +1881,7 @@ struct xhci_hcd { #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) #define XHCI_ZHAOXIN_HOST BIT_ULL(41) +#define XHCI_ZHAOXIN_TRB_FETCH BIT_ULL(42) unsigned int num_active_eps; unsigned int limit_active_eps; -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Add Zhaoxin xHCI LPM U1/U2 feature support
by LeoLiuoc 09 Jul '21

09 Jul '21

Add LPM u1/u2 feature support for xHCI of zhaoxin Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-pci.c | 4 ++++ drivers/usb/host/xhci.c | 34 ++++++++++++++++++++++++++++++++-- drivers/usb/host/xhci.h | 1 + 3 files changed, 37 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 7bc18cf8042c..e78316ed99d4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -268,6 +268,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_VIA) xhci->quirks |= XHCI_RESET_ON_RESUME; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN) { + xhci->quirks |= XHCI_LPM_SUPPORT; + xhci->quirks |= XHCI_ZHAOXIN_HOST; + } /* See https://bugzilla.kernel.org/show_bug.cgi?id=79511 */ if (pdev->vendor == PCI_VENDOR_ID_VIA && diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a8d97e23f601..a834f3927bee 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4666,7 +4666,7 @@ static u16 xhci_calculate_u1_timeout(struct xhci_hcd *xhci, { unsigned long long timeout_ns; - if (xhci->quirks & XHCI_INTEL_HOST) + if (xhci->quirks & (XHCI_INTEL_HOST | XHCI_ZHAOXIN_HOST)) timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc); else timeout_ns = udev->u1_params.sel; @@ -4730,7 +4730,7 @@ static u16 xhci_calculate_u2_timeout(struct xhci_hcd *xhci, { unsigned long long timeout_ns; - if (xhci->quirks & XHCI_INTEL_HOST) + if (xhci->quirks & (XHCI_INTEL_HOST | XHCI_ZHAOXIN_HOST)) timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc); else timeout_ns = udev->u2_params.sel; @@ -4835,12 +4835,42 @@ static int xhci_check_intel_tier_policy(struct usb_device *udev, return -E2BIG; } +static int xhci_check_zhaoxin_tier_policy(struct usb_device *udev, + enum usb3_link_state state) +{ + struct usb_device *parent; + unsigned int num_hubs; + char *state_name; + + if (state == USB3_LPM_U1) + state_name = "U1"; + else if (state == USB3_LPM_U2) + state_name = "U2"; + else + state_name = "Unknown"; + /* Don't enable U1/U2 if the device is on an external hub*/ + for (parent = udev->parent, num_hubs = 0; parent->parent; + parent = parent->parent) + num_hubs++; + + if (num_hubs < 1) + return 0; + + dev_dbg(&udev->dev, "Disabling %s link state for device" + " below external hub.\n", state_name); + dev_dbg(&udev->dev, "Plug device into root port " + "to decrease power consumption.\n"); + return -E2BIG; +} + static int xhci_check_tier_policy(struct xhci_hcd *xhci, struct usb_device *udev, enum usb3_link_state state) { if (xhci->quirks & XHCI_INTEL_HOST) return xhci_check_intel_tier_policy(udev, state); + else if (xhci->quirks & XHCI_ZHAOXIN_HOST) + return xhci_check_zhaoxin_tier_policy(udev, state); else return 0; } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index d01241f1daf3..576cafb5d873 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1880,6 +1880,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) +#define XHCI_ZHAOXIN_HOST BIT_ULL(41) unsigned int num_active_eps; unsigned int limit_active_eps; -- 2.20.1

1 0

[PATCH OLK-5.10] ata: sata_zhaoxin: Add support for Zhaoxin Serial ATA
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin Serial ATA support for Zhaoxin CPUs. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/ata/Kconfig | 8 + drivers/ata/Makefile | 1 + drivers/ata/sata_zhaoxin.c | 384 +++++++++++++++++++++++++++++++++++++ 3 files changed, 393 insertions(+) create mode 100644 drivers/ata/sata_zhaoxin.c diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 030cb32da980..5f62dcdc546b 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -552,6 +552,14 @@ config SATA_VITESSE If unsure, say N. +config SATA_ZHAOXIN + tristate "ZhaoXin SATA support" + depends on PCI + help + This option enables support for ZhaoXin Serial ATA. + + If unsure, say N. + comment "PATA SFF controllers with BMDMA" config PATA_ALI diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index b8aebfb14e82..9a3ce171d9e8 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_SATA_SVW) += sata_svw.o obj-$(CONFIG_SATA_ULI) += sata_uli.o obj-$(CONFIG_SATA_VIA) += sata_via.o obj-$(CONFIG_SATA_VITESSE) += sata_vsc.o +obj-$(CONFIG_SATA_ZHAOXIN) += sata_zhaoxin.o # SFF PATA w/ BMDMA obj-$(CONFIG_PATA_ALI) += pata_ali.o diff --git a/drivers/ata/sata_zhaoxin.c b/drivers/ata/sata_zhaoxin.c new file mode 100644 index 000000000000..8e30a6525f54 --- /dev/null +++ b/drivers/ata/sata_zhaoxin.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sata_zhaoxin.c - ZhaoXin Serial ATA controllers + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/blkdev.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_host.h> +#include <linux/libata.h> + +#define DRV_NAME "sata_zx" +#define DRV_VERSION "2.6.1" + +enum board_ids_enum { + cnd001, +}; + +enum { + SATA_CHAN_ENAB = 0x40, /* SATA channel enable */ + SATA_INT_GATE = 0x41, /* SATA interrupt gating */ + SATA_NATIVE_MODE = 0x42, /* Native mode enable */ + PATA_UDMA_TIMING = 0xB3, /* PATA timing for DMA/ cable detect */ + PATA_PIO_TIMING = 0xAB, /* PATA timing register */ + + PORT0 = (1 << 1), + PORT1 = (1 << 0), + ALL_PORTS = PORT0 | PORT1, + + NATIVE_MODE_ALL = (1 << 7) | (1 << 6) | (1 << 5) | (1 << 4), + + SATA_EXT_PHY = (1 << 6), /* 0==use PATA, 1==ext phy */ +}; + +static int szx_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); +static int cnd001_scr_read(struct ata_link *link, unsigned int scr, u32 *val); +static int cnd001_scr_write(struct ata_link *link, unsigned int scr, u32 val); +static int szx_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline); + +static void szx_tf_load(struct ata_port *ap, const struct ata_taskfile *tf); + +static const struct pci_device_id szx_pci_tbl[] = { + { PCI_VDEVICE(ZHAOXIN, 0x9002), cnd001 }, + { PCI_VDEVICE(ZHAOXIN, 0x9003), cnd001 }, + + { } /* terminate list */ +}; + +static struct pci_driver szx_pci_driver = { + .name = DRV_NAME, + .id_table = szx_pci_tbl, + .probe = szx_init_one, +#ifdef CONFIG_PM_SLEEP + .suspend = ata_pci_device_suspend, + .resume = ata_pci_device_resume, +#endif + .remove = ata_pci_remove_one, +}; + +static struct scsi_host_template szx_sht = { + ATA_BMDMA_SHT(DRV_NAME), +}; + +static struct ata_port_operations szx_base_ops = { + .inherits = &ata_bmdma_port_ops, + .sff_tf_load = szx_tf_load, +}; + +static struct ata_port_operations cnd001_ops = { + .inherits = &szx_base_ops, + .hardreset = szx_hardreset, + .scr_read = cnd001_scr_read, + .scr_write = cnd001_scr_write, +}; + +static struct ata_port_info cnd001_port_info = { + .flags = ATA_FLAG_SATA | ATA_FLAG_SLAVE_POSS, + .pio_mask = ATA_PIO4, + .mwdma_mask = ATA_MWDMA2, + .udma_mask = ATA_UDMA6, + .port_ops = &cnd001_ops, +}; + + +static int szx_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + int rc; + + rc = sata_std_hardreset(link, class, deadline); + if (!rc || rc == -EAGAIN) { + struct ata_port *ap = link->ap; + int pmp = link->pmp; + int tmprc; + + if (pmp) { + ap->ops->sff_dev_select(ap, pmp); + tmprc = ata_sff_wait_ready(&ap->link, deadline); + } else { + tmprc = ata_sff_wait_ready(link, deadline); + } + if (tmprc) + ata_link_err(link, "COMRESET failed for wait (errno=%d)\n", + rc); + else + ata_link_err(link, "wait for bsy success\n"); + + ata_link_err(link, "COMRESET success (errno=%d) ap=%d link %d\n", + rc, link->ap->port_no, link->pmp); + } else { + ata_link_err(link, "COMRESET failed (errno=%d) ap=%d link %d\n", + rc, link->ap->port_no, link->pmp); + } + return rc; +} + +static int cnd001_scr_read(struct ata_link *link, unsigned int scr, u32 *val) +{ + static const u8 ipm_tbl[] = { 1, 2, 6, 0 }; + struct pci_dev *pdev = to_pci_dev(link->ap->host->dev); + int slot = 2 * link->ap->port_no + link->pmp; + u32 v = 0; + u8 raw; + + switch (scr) { + case SCR_STATUS: + pci_read_config_byte(pdev, 0xA0 + slot, &raw); + + /* read the DET field, bit0 and 1 of the config byte */ + v |= raw & 0x03; + + /* read the SPD field, bit4 of the configure byte */ + v |= raw & 0x30; + + /* read the IPM field, bit2 and 3 of the config byte */ + v |= ((ipm_tbl[(raw >> 2) & 0x3])<<8); + break; + + case SCR_ERROR: + /* devices other than 5287 uses 0xA8 as base */ + WARN_ON(pdev->device != 0x9002 && pdev->device != 0x9003); + pci_write_config_byte(pdev, 0x42, slot); + pci_read_config_dword(pdev, 0xA8, &v); + break; + + case SCR_CONTROL: + pci_read_config_byte(pdev, 0xA4 + slot, &raw); + + /* read the DET field, bit0 and bit1 */ + v |= ((raw & 0x02) << 1) | (raw & 0x01); + + /* read the IPM field, bit2 and bit3 */ + v |= ((raw >> 2) & 0x03) << 8; + + break; + + default: + return -EINVAL; + } + + *val = v; + return 0; +} + +static int cnd001_scr_write(struct ata_link *link, unsigned int scr, u32 val) +{ + struct pci_dev *pdev = to_pci_dev(link->ap->host->dev); + int slot = 2 * link->ap->port_no + link->pmp; + u32 v = 0; + + WARN_ON(pdev == NULL); + + switch (scr) { + case SCR_ERROR: + /* devices 0x9002 uses 0xA8 as base */ + WARN_ON(pdev->device != 0x9002 && pdev->device != 0x9003); + pci_write_config_byte(pdev, 0x42, slot); + pci_write_config_dword(pdev, 0xA8, val); + return 0; + + case SCR_CONTROL: + /* set the DET field */ + v |= ((val & 0x4) >> 1) | (val & 0x1); + + /* set the IPM field */ + v |= ((val >> 8) & 0x3) << 2; + + + pci_write_config_byte(pdev, 0xA4 + slot, v); + + + return 0; + + default: + return -EINVAL; + } +} + + +/** + * szx_tf_load - send taskfile registers to host controller + * @ap: Port to which output is sent + * @tf: ATA taskfile register set + * + * Outputs ATA taskfile to standard ATA host controller. + * + * This is to fix the internal bug of zx chipsets, which will + * reset the device register after changing the IEN bit on ctl + * register. + */ +static void szx_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) +{ + struct ata_taskfile ttf; + + if (tf->ctl != ap->last_ctl) { + ttf = *tf; + ttf.flags |= ATA_TFLAG_DEVICE; + tf = &ttf; + } + ata_sff_tf_load(ap, tf); +} + +static const unsigned int szx_bar_sizes[] = { + 8, 4, 8, 4, 16, 256 +}; + +static const unsigned int cnd001_bar_sizes0[] = { + 8, 4, 8, 4, 16, 0 +}; + +static const unsigned int cnd001_bar_sizes1[] = { + 8, 4, 0, 0, 16, 0 +}; + +static int cnd001_prepare_host(struct pci_dev *pdev, struct ata_host **r_host) +{ + const struct ata_port_info *ppi0[] = { + &cnd001_port_info, NULL + }; + const struct ata_port_info *ppi1[] = { + &cnd001_port_info, &ata_dummy_port_info + }; + struct ata_host *host; + int i, rc; + + if (pdev->device == 0x9002) + rc = ata_pci_bmdma_prepare_host(pdev, ppi0, &host); + else if (pdev->device == 0x9003) + rc = ata_pci_bmdma_prepare_host(pdev, ppi1, &host); + else + rc = -EINVAL; + + if (rc) + return rc; + + *r_host = host; + + /* cnd001 9002 hosts four sata ports as M/S of the two channels */ + /* cnd001 9003 hosts two sata ports as M/S of the one channel */ + for (i = 0; i < host->n_ports; i++) + ata_slave_link_init(host->ports[i]); + + return 0; +} + +static void szx_configure(struct pci_dev *pdev, int board_id) +{ + u8 tmp8; + + pci_read_config_byte(pdev, PCI_INTERRUPT_LINE, &tmp8); + dev_info(&pdev->dev, "routed to hard irq line %d\n", + (int) (tmp8 & 0xf0) == 0xf0 ? 0 : tmp8 & 0x0f); + + /* make sure SATA channels are enabled */ + pci_read_config_byte(pdev, SATA_CHAN_ENAB, &tmp8); + if ((tmp8 & ALL_PORTS) != ALL_PORTS) { + dev_dbg(&pdev->dev, "enabling SATA channels (0x%x)\n", + (int)tmp8); + tmp8 |= ALL_PORTS; + pci_write_config_byte(pdev, SATA_CHAN_ENAB, tmp8); + } + + /* make sure interrupts for each channel sent to us */ + pci_read_config_byte(pdev, SATA_INT_GATE, &tmp8); + if ((tmp8 & ALL_PORTS) != ALL_PORTS) { + dev_dbg(&pdev->dev, "enabling SATA channel interrupts (0x%x)\n", + (int) tmp8); + tmp8 |= ALL_PORTS; + pci_write_config_byte(pdev, SATA_INT_GATE, tmp8); + } + + /* make sure native mode is enabled */ + pci_read_config_byte(pdev, SATA_NATIVE_MODE, &tmp8); + if ((tmp8 & NATIVE_MODE_ALL) != NATIVE_MODE_ALL) { + dev_dbg(&pdev->dev, + "enabling SATA channel native mode (0x%x)\n", + (int) tmp8); + tmp8 |= NATIVE_MODE_ALL; + pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8); + } +} + +static int szx_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + unsigned int i; + int rc; + struct ata_host *host = NULL; + int board_id = (int) ent->driver_data; + const unsigned int *bar_sizes; + int legacy_mode = 0; + + ata_print_version_once(&pdev->dev, DRV_VERSION); + + if (pdev->device == 0x9002 || pdev->device == 0x9003) { + if ((pdev->class >> 8) == PCI_CLASS_STORAGE_IDE) { + u8 tmp8, mask; + + /* TODO: What if one channel is in native mode ... */ + pci_read_config_byte(pdev, PCI_CLASS_PROG, &tmp8); + mask = (1 << 2) | (1 << 0); + if ((tmp8 & mask) != mask) + legacy_mode = 1; + } + if (legacy_mode) + return -EINVAL; + } + + rc = pcim_enable_device(pdev); + if (rc) + return rc; + + if (board_id == cnd001 && pdev->device == 0x9002) + bar_sizes = &cnd001_bar_sizes0[0]; + else if (board_id == cnd001 && pdev->device == 0x9003) + bar_sizes = &cnd001_bar_sizes1[0]; + else + bar_sizes = &szx_bar_sizes[0]; + + for (i = 0; i < ARRAY_SIZE(szx_bar_sizes); i++) { + if ((pci_resource_start(pdev, i) == 0) || + (pci_resource_len(pdev, i) < bar_sizes[i])) { + if (bar_sizes[i] == 0) + continue; + + dev_err(&pdev->dev, + "invalid PCI BAR %u (sz 0x%llx, val 0x%llx)\n", + i, + (unsigned long long)pci_resource_start(pdev, i), + (unsigned long long)pci_resource_len(pdev, i)); + + return -ENODEV; + } + } + + switch (board_id) { + case cnd001: + rc = cnd001_prepare_host(pdev, &host); + break; + default: + rc = -EINVAL; + } + if (rc) + return rc; + + szx_configure(pdev, board_id); + + pci_set_master(pdev); + return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt, + IRQF_SHARED, &szx_sht); +} + +module_pci_driver(szx_pci_driver); + +MODULE_AUTHOR("Yanchen:YanchenSun@zhaoxin.com"); +MODULE_DESCRIPTION("SCSI low-level driver for ZX SATA controllers"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(pci, szx_pci_tbl); +MODULE_VERSION(DRV_VERSION); -- 2.20.1

1 0

[PATCH OLK-5.10] crypto: x86/crc32c-intel - Don't match some Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

The driver crc32c-intel match CPUs supporting X86_FEATURE_XMM4_2. On platforms with Zhaoxin CPUs supporting this X86 feature, when crc32c-intel and crc32c-generic are both registered, system will use crc32c-intel because its .cra_priority is greater than crc32c-generic. When doing lmbench3 Create and Delete file test on partitions with ext4 enabling metadata checksum, found using crc32c-generic driver could get about 20% performance gain than using the driver crc32c-intel on some Zhaoxin CPUs. This case expect to use crc32c-generic driver for these Zhaoxin CPUs to get performance gain, so remove these Zhaoxin CPUs support from crc32c-intel. This patch was submitted to mainline kernel but not accepted by upstream maintainer whose reason is "Then create a BUG flag for it,". We think this is not a CPU bug for Zhaoxin CPUs. So should patch the crc32c driver for Zhaoxin CPUs but not report a BUG. https://lkml.org/lkml/2020/12/11/308 Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/crypto/crc32c-intel_glue.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index feccb5254c7e..2d7fe5d24f5f 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -222,8 +222,16 @@ MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id); static int __init crc32c_intel_mod_init(void) { + struct cpuinfo_x86 *c = &boot_cpu_data; + if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; + + if ((c->x86_vendor == X86_VENDOR_ZHAOXIN || c->x86_vendor == X86_VENDOR_CENTAUR) && + (c->x86 <= 7 && c->x86_model <= 59)) { + return -ENODEV; + } + #ifdef CONFIG_X86_64 if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; -- 2.20.1

1 0

[PATCH OLK-5.10] Add MCA supprot for X86_VENDOR_CENTAUR CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Add MCA support for some Zhaoxin CPUs which use X86_VENDOR_CENTAUR as vendor ID. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/mce/core.c | 39 ++++++++++++--------------------- arch/x86/kernel/cpu/mce/intel.c | 3 ++- 2 files changed, 16 insertions(+), 26 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b7a27589dfa0..aca6ab19726f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -538,7 +538,8 @@ int mce_usable_address(struct mce *m) /* Checks after this one are Intel/Zhaoxin-specific: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && - boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 1; if (!(m->status & MCI_STATUS_MISCV)) @@ -562,6 +563,7 @@ bool mce_is_memory_error(struct mce *m) return amd_mce_is_memory_error(m); case X86_VENDOR_INTEL: + case X86_VENDOR_CENTAUR: case X86_VENDOR_ZHAOXIN: /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -1155,7 +1157,8 @@ static noinstr bool mce_check_crashing_cpu(void) mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS); - if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { + if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { if (mcgstatus & MCG_STATUS_LMCES) return false; } @@ -1358,7 +1361,8 @@ noinstr void do_machine_check(struct pt_regs *regs) * on Intel, Zhaoxin only. */ if (m.cpuvendor == X86_VENDOR_INTEL || - m.cpuvendor == X86_VENDOR_ZHAOXIN) + m.cpuvendor == X86_VENDOR_CENTAUR || + m.cpuvendor == X86_VENDOR_ZHAOXIN) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* @@ -1786,7 +1790,8 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) quirk_no_way_out = quirk_sandybridge_ifu; } - if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { + if (c->x86_vendor == X86_VENDOR_CENTAUR || + c->x86_vendor == X86_VENDOR_ZHAOXIN) { /* * All newer Zhaoxin CPUs support MCE broadcasting. Enable * synchronization with a one second timeout. @@ -1846,21 +1851,6 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) } } -static void mce_centaur_feature_init(struct cpuinfo_x86 *c) -{ - struct mca_config *cfg = &mca_cfg; - - /* - * All newer Centaur CPUs support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || - c->x86 > 6) { - if (cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; - } -} - static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); @@ -1908,9 +1898,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_CENTAUR: - mce_centaur_feature_init(c); - break; - case X86_VENDOR_ZHAOXIN: mce_zhaoxin_feature_init(c); break; @@ -1927,6 +1914,7 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) mce_intel_feature_clear(c); break; + case X86_VENDOR_CENTAUR: case X86_VENDOR_ZHAOXIN: mce_zhaoxin_feature_clear(c); break; @@ -2233,9 +2221,10 @@ static void vendor_disable_error_reporting(void) * controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || - boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index abe9fe0fb851..26d521ac5f7d 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -86,7 +86,8 @@ static int cmci_supported(int *banks) * makes sure none of the backdoors are entered otherwise. */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && - boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 0; if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) -- 2.20.1

1 0

[PATCH OLK-5.10 1/2] Get locgical processors numbers bits per package
by LeoLiuoc 09 Jul '21

09 Jul '21

Get locgical processors numbers bits per package by cpuid instruction for some Zhaoxin CPUs which vendor is Centaur Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/centaur.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 345f7d905db6..3d1e87b6a657 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -109,6 +109,19 @@ static void early_init_centaur(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); } + + if (c->cpuid_level >= 0x00000001) { + u32 eax, ebx, ecx, edx; + + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); + /* + * If HTT (EDX[28]) is set EBX[16:23] contain the number of + * apicids which are reserved per package. Store the resulting + * shift value for the package management code. + */ + if (edx & (1U << 28)) + c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); + } } static void init_centaur(struct cpuinfo_x86 *c) -- 2.20.1

1 0

[PATCH OLK-5.10 2/2] Add support for extended topology detection,of Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Newer Zhaoxin CPUs support get extended topology from CPUID leaf B/1F, So add support for it. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/centaur.c | 8 +++++++- arch/x86/kernel/cpu/zhaoxin.c | 7 ++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 3d1e87b6a657..dacac9135681 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -122,6 +122,9 @@ static void early_init_centaur(struct cpuinfo_x86 *c) if (edx & (1U << 28)) c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); } + + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } static void init_centaur(struct cpuinfo_x86 *c) @@ -140,11 +143,14 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, 0*32+31); #endif early_init_centaur(c); + detect_extended_topology(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); + if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif + } if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 05fa4ef63490..2126b10de796 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -79,16 +79,21 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c) c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); } + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); + detect_extended_topology(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); + if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif + } if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); -- 2.20.1

1 0

[PATCH OLK-5.10 0/2] New Zhaoxin CPU vendor ID/FMS patch
by LeoLiuoc 09 Jul '21

09 Jul '21

This set of patches is to add support for Zhaoxin Family 7 CPUs. With these patches, the kernel can identify Zhaoxin CPUs topology information. LeoLiu-oc (2): Get locgical processors numbers bits per package Add support for extended topology detection of Zhaoxin CPUs arch/x86/kernel/cpu/centaur.c | 21 ++++++++++++++++++++- arch/x86/kernel/cpu/zhaoxin.c | 7 ++++++- 2 files changed, 26 insertions(+), 2 deletions(-) -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] NFSv4.1: fix kabi for struct rpc_xprt
by Yang Yingliang 09 Jul '21

09 Jul '21

From: ChenXiaoSong <chenxiaosong2(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- commit a2ff6d97547e ("NFSv4.1: Don't rebind to the same source port when reconnecting to the server") add new member into struct rpc_xprt, which will break KABI. This patch try to fix it. Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/sunrpc/xprt.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 36a944dda1957..ccfacca1eba9d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -200,8 +200,12 @@ struct rpc_xprt { unsigned int min_reqs; /* min number of slots */ unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ +#ifdef __GENKSYMS__ + unsigned char resvport : 1; /* use a reserved port */ +#else unsigned char resvport : 1, /* use a reserved port */ reuseport : 1; /* reuse port on reconnect */ +#endif atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ -- 2.25.1

1 0

[PATCH kernel-4.19] usb: gadget: rndis: Fix info leak of rndis
by Yang Yingliang 08 Jul '21

08 Jul '21

From: Wang Hai <wanghai38(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172330 CVE: NA -------------------------------- We can construct some special USB packets that cause kernel info leak by the following steps of rndis. 1. construct the packet to make rndis call gen_ndis_set_resp(). In gen_ndis_set_resp(), BufOffset comes from the USB packet and it is not checked so that BufOffset can be any value. Therefore, if OID is RNDIS_OID_GEN_CURRENT_PACKET_FILTER, then *params->filter can get data at any address. 2. construct the packet to make rndis call rndis_query_response(). In rndis_query_response(), if OID is RNDIS_OID_GEN_CURRENT_PACKET_FILTER, then the data of *params->filter is fetched and returned, resulting in info leak. Therefore, we need to check the BufOffset to prevent info leak. Here, buf size is USB_COMP_EP0_BUFSIZ, as long as "8 + BufOffset + BufLength" is less than USB_COMP_EP0_BUFSIZ, it will be considered legal. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/gadget/composite.c | 2 +- drivers/usb/gadget/function/rndis.c | 37 +++++++++++++++++++++++++---- 2 files changed, 34 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d85bb3ba8263f..ef545934ce086 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2143,7 +2143,7 @@ int composite_dev_prepare(struct usb_composite_driver *composite, if (!cdev->req) return -ENOMEM; - cdev->req->buf = kmalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); + cdev->req->buf = kzalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); if (!cdev->req->buf) goto fail; diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 04c142c130759..7686b55ccf133 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -506,6 +506,10 @@ static int gen_ndis_set_resp(struct rndis_params *params, u32 OID, switch (OID) { case RNDIS_OID_GEN_CURRENT_PACKET_FILTER: + if (buf_len < 2) { + pr_err("%s:Not support for buf_len < 2\n", __func__); + break; + } /* these NDIS_PACKET_TYPE_* bitflags are shared with * cdc_filter; it's not RNDIS-specific @@ -592,6 +596,7 @@ static int rndis_query_response(struct rndis_params *params, rndis_query_msg_type *buf) { rndis_query_cmplt_type *resp; + u32 BufOffset, BufLength; rndis_resp_t *r; /* pr_debug("%s: OID = %08X\n", __func__, cpu_to_le32(buf->OID)); */ @@ -612,12 +617,25 @@ static int rndis_query_response(struct rndis_params *params, resp->MessageType = cpu_to_le32(RNDIS_MSG_QUERY_C); resp->RequestID = buf->RequestID; /* Still LE in msg buffer */ + BufOffset = le32_to_cpu(buf->InformationBufferOffset); + BufLength = le32_to_cpu(buf->InformationBufferLength); + + /* + * If the address of the buf to be accessed exceeds the valid + * range of the buf, then return RNDIS_STATUS_NOT_SUPPORTED. + */ + if (8 + BufOffset + BufLength >= USB_COMP_EP0_BUFSIZ) { + resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); + resp->MessageLength = cpu_to_le32(sizeof(*resp)); + resp->InformationBufferLength = cpu_to_le32(0); + resp->InformationBufferOffset = cpu_to_le32(0); + params->resp_avail(params->v); + return 0; + } if (gen_ndis_query_resp(params, le32_to_cpu(buf->OID), - le32_to_cpu(buf->InformationBufferOffset) - + 8 + (u8 *)buf, - le32_to_cpu(buf->InformationBufferLength), - r)) { + BufOffset + 8 + (u8 *)buf, BufLength, + r)) { /* OID not supported */ resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); resp->MessageLength = cpu_to_le32(sizeof *resp); @@ -660,6 +678,17 @@ static int rndis_set_response(struct rndis_params *params, resp->MessageType = cpu_to_le32(RNDIS_MSG_SET_C); resp->MessageLength = cpu_to_le32(16); resp->RequestID = buf->RequestID; /* Still LE in msg buffer */ + + /* + * If the address of the buf to be accessed exceeds the valid + * range of the buf, then return RNDIS_STATUS_NOT_SUPPORTED. + */ + if (8 + BufOffset + BufLength >= USB_COMP_EP0_BUFSIZ) { + resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); + params->resp_avail(params->v); + return 0; + } + if (gen_ndis_set_resp(params, le32_to_cpu(buf->OID), ((u8 *)buf) + 8 + BufOffset, BufLength, r)) resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); -- 2.25.1

1 0

【Meeting Notice】openEuler kernel 双周例会 Time: 2021-07-09 14:00-18:00
by Meeting Book 08 Jul '21

08 Jul '21

1 0

【kernel-sig例会议题申报】openEuler 21.09新特性简述
by Zheng Zengkai 08 Jul '21

08 Jul '21

*背景：* openEuler 21.09版本已启动开发，欢迎openEuler kernel开发者贡献补丁。申报一个议题： openEuler 21.09版本当前计划合入的特性简述。

1 0

[PATCH OLK-5.10 0/2] Add config switch and kernel parameter for CPU0
by Zheng Zengkai 05 Jul '21

05 Jul '21

Add config switch and kernel parameter for CPU0 hotplug. Besides, disable config ARM64_BOOTPARAM_HOTPLUG_CPU0 in openeuler_defconfig by default. Zheng Zengkai (2): arm64: Add config switch and kernel parameter for CPU0 hotplug config: disable config ARM64_BOOTPARAM_HOTPLUG_CPU0 by default .../admin-guide/kernel-parameters.txt | 8 ++++++ arch/arm64/Kconfig | 28 +++++++++++++++++++ arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/kernel/setup.c | 18 +++++++++++- 4 files changed, 54 insertions(+), 1 deletion(-) -- 2.20.1

1 2

[PATCH kernel-4.19] once: Fix panic when module unload
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Kefeng Wang <wangkefeng.wang(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172153 CVE: NA ------------------------------------------------- DO_ONCE DEFINE_STATIC_KEY_TRUE(___once_key); __do_once_done once_disable_jump(once_key); INIT_WORK(&w->work, once_deferred); struct once_work *w; w->key = key; schedule_work(&w->work); module unload //*the key is destroy* process_one_work once_deferred BUG_ON(!static_key_enabled(work->key)); static_key_count((struct static_key *)x) //*access key, crash* When module uses DO_ONCE mechanism, it could crash due to the above concurrency problem, we could reproduce it with link[1]. Fix it by add/put module refcount in the once work process. [1] https://lore.kernel.org/netdev/eaa6c371-465e-57eb-6be9-f4b16b9d7cbf@huawei.… Cc: Hannes Frederic Sowa <hannes(a)stressinduktion.org> Cc: Daniel Borkmann <daniel(a)iogearbox.net> Cc: David S. Miller <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Reported-by: Minmin chen <chenmingmin(a)huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- lib/once.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/lib/once.c b/lib/once.c index 8b7d6235217ee..959f8db41ccfa 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include <linux/spinlock.h> #include <linux/once.h> #include <linux/random.h> +#include <linux/module.h> struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,11 +18,24 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } +static struct module *find_module_by_key(struct static_key_true *key) +{ + struct module *mod; + + preempt_disable(); + mod = __module_address((unsigned long)key); + preempt_enable(); + + return mod; +} + static void once_disable_jump(struct static_key_true *key) { + struct module *mod = find_module_by_key(key); struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); @@ -29,6 +44,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/11] bpf: fix up selftests after backports were fixed
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Ovidiu Panait <ovidiu.panait(a)windriver.com> stable inclusion from linux-4.19.193 commit b190383c714a379002b00bc8de43371e78d291d8 -------------------------------- After the backport of the changes to fix CVE 2019-7308, the selftests also need to be fixed up, as was done originally in mainline 80c9b2fae87b ("bpf: add various test cases to selftests"). This is a backport of upstream commit 80c9b2fae87b ("bpf: add various test cases to selftests") adapted to 4.19 in order to fix the selftests that began to fail after CVE-2019-7308 fixes. Suggested-by: Frank van der Linden <fllinden(a)amazon.com> Signed-off-by: Ovidiu Panait <ovidiu.panait(a)windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/testing/selftests/bpf/test_verifier.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 9db5a7378f40f..fef1c9e3c4b81 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2448,6 +2448,7 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "invalid stack off=-79992 size=8", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", }, { "PTR_TO_STACK store/load - out of bounds high", @@ -2844,6 +2845,8 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -7457,6 +7460,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7481,6 +7485,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7507,6 +7512,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7532,6 +7538,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7580,6 +7587,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7651,6 +7659,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7702,6 +7711,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7729,6 +7739,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7755,6 +7766,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7784,6 +7796,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R7 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7814,6 +7827,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 4 }, .errstr = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7842,6 +7856,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, .result_unpriv = REJECT, }, @@ -7894,6 +7909,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8266,6 +8282,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "pointer offset 1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -8287,6 +8304,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "pointer offset -1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -8458,6 +8476,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN() }, .errstr = "fp pointer offset 1073741822", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", .result = REJECT }, { -- 2.25.1

1 10

[PATCH kernel-4.19 1/2] SUNRPC: Fix the batch tasks count wraparound.
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> mainline inclusion from mainline-v5.14 commit fcb170a9d825d7db4a3fb870b0300f5a40a8d096 category: bugfix bugzilla: 51898 CVE: NA --------------------------- The 'queue->nr' will wraparound from 0 to 255 when only current priority queue has tasks. This maybe lead a deadlock same as commit dfe1fe75e00e ("NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode()"): Privileged delegreturn task is queued to privileged list because all the slots are assigned. When non-privileged task complete and release the slot, a non-privileged maybe picked out. It maybe allocate slot failed when the session on draining. If the 'queue->nr' has wraparound to 255, and no enough slot to service it, then the privileged delegreturn will lost to wake up. So we should avoid the wraparound on 'queue->nr'. Reported-by: Hulk Robot <hulkci(a)huawei.com> Fixes: 5fcdfacc01f3 ("NFSv4: Return delegations synchronously in evict_inode") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/sunrpc/sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 8d204d5a76187..8cffcf58e6386 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -506,7 +506,8 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q * Service a batch of tasks from a single owner. */ q = &queue->tasks[queue->priority]; - if (!list_empty(q) && --queue->nr) { + if (!list_empty(q) && queue->nr) { + queue->nr--; task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto out; } -- 2.25.1

1 1

[PATCH kernel-4.19 1/3] bpf: Inherit expanded/patched seen count from old aux data
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v5.13-rc7 commit d203b0fd863a2261e5d00b97f3d060c4c2a6db71 category: bugfix bugzilla: NA CVE: CVE-2021-33624 -------------------------------- Instead of relying on current env->pass_cnt, use the seen count from the old aux data in adjust_insn_aux_data(), and expand it to the new range of patched instructions. This change is valid given we always expand 1:n with n>=1, so what applies to the old/original instruction needs to apply for the replacement as well. Not relying on env->pass_cnt is a prerequisite for a later change where we want to avoid marking an instruction seen when verified under speculative execution path. Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Reviewed-by: John Fastabend <john.fastabend(a)gmail.com> Reviewed-by: Benedict Schlueter <benedict.schlueter(a)rub.de> Reviewed-by: Piotr Krysiuk <piotras(a)gmail.com> Acked-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: kernel/bpf/verifier.c seen of bpf_insn_aux_data is bool in kernel-4.19. Signed-off-by: He Fengqing <hefengqing(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/verifier.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ac02469d0f154..6b919fba40c00 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5853,6 +5853,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, u32 off, u32 cnt) { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + bool old_seen = old_data[off].seen; int i; if (cnt == 1) @@ -5864,8 +5865,10 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); - for (i = off; i < off + cnt - 1; i++) - new_data[i].seen = true; + for (i = off; i < off + cnt - 1; i++) { + /* Expand insni[off]'s seen count to the patched range. */ + new_data[i].seen = old_seen; + } env->insn_aux_data = new_data; vfree(old_data); return 0; -- 2.25.1

1 2

[PATCH kernel-4.19] nvme-rdma: avoid request double completion for concurrent nvme_rdma_timeout
by Yang Yingliang 02 Jul '21

02 Jul '21

From: Chao Leng <lengchao(a)huawei.com> mainline inclusion from mainline-v5.11-rc5 commit 7674073b2ed35ac951a49c425dec6b39d5a57140 category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I1WGZE ------------------------------------------------- A crash happens when inject completing request long time(nearly 30s). Each name space has a request queue, when inject completing request long time, multi request queues may have time out requests at the same time, nvme_rdma_timeout will execute concurrently. Multi requests in different request queues may be queued in the same rdma queue, multi nvme_rdma_timeout may call nvme_rdma_stop_queue at the same time. The first nvme_rdma_timeout will clear NVME_RDMA_Q_LIVE and continue stopping the rdma queue(drain qp), but the others check NVME_RDMA_Q_LIVE is already cleared, and then directly complete the requests, complete request before the qp is fully drained may lead to a use-after-free condition. Add a multex lock to serialize nvme_rdma_stop_queue. Signed-off-by: Chao Leng <lengchao(a)huawei.com> Tested-by: Israel Rukshin <israelr(a)nvidia.com> Reviewed-by: Israel Rukshin <israelr(a)nvidia.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> conflicts: drivers/nvme/host/rdma.c [lrz: adjust context] Signed-off-by: Ruozhu Li <liruozhu(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/rdma.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 158d7417bcea6..91ff9262f6729 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -93,6 +93,7 @@ struct nvme_rdma_queue { struct rdma_cm_id *cm_id; int cm_error; struct completion cm_done; + struct mutex queue_lock; }; struct nvme_rdma_ctrl { @@ -503,6 +504,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, int ret; queue = &ctrl->queues[idx]; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; init_completion(&queue->cm_done); @@ -518,7 +520,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, if (IS_ERR(queue->cm_id)) { dev_info(ctrl->ctrl.device, "failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id)); - return PTR_ERR(queue->cm_id); + ret = PTR_ERR(queue->cm_id); + goto out_destroy_mutex; } if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) @@ -548,6 +551,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, out_destroy_cm_id: rdma_destroy_id(queue->cm_id); nvme_rdma_destroy_queue_ib(queue); +out_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -559,10 +564,10 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { - if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) - return; - - __nvme_rdma_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) + __nvme_rdma_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) @@ -572,6 +577,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + mutex_destroy(&queue->queue_lock); } static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) -- 2.25.1

1 0

[PATCH kernel-4.19] binfmt: Move install_exec_creds after setup_new_exec to match binfmt_elf
by Yang Yingliang 02 Jul '21

02 Jul '21

From: "Eric W. Biederman" <ebiederm(a)xmission.com> mainline inclusion from mainline-v5.8-rc1 commit e7f7785449a1f459a4a3ca92f82f56fb054dd2b9 category: bugfix bugzilla: 36868 CVE: NA ----------------------------------------------- In 2016 Linus moved install_exec_creds immediately after setup_new_exec, in binfmt_elf as a cleanup and as part of closing a potential information leak. Perform the same cleanup for the other binary formats. Different binary formats doing the same things the same way makes exec easier to reason about and easier to maintain. Greg Ungerer reports: > I tested the the whole series on non-MMU m68k and non-MMU arm > (exercising binfmt_flat) and it all tested out with no problems, > so for the binfmt_flat changes: Tested-by: Greg Ungerer <gerg(a)linux-m68k.org> Ref: 9f834ec18def ("binfmt_elf: switch to new creds when switching to new mm") Reviewed-by: Kees Cook <keescook(a)chromium.org> Reviewed-by: Greg Ungerer <gerg(a)linux-m68k.org> Signed-off-by: "Eric W. Biederman" <ebiederm(a)xmission.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/ia32/ia32_aout.c | 3 +-- fs/binfmt_aout.c | 2 +- fs/binfmt_elf_fdpic.c | 2 +- fs/binfmt_flat.c | 3 +-- 4 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 7dbbe9ffda173..8d78ea00d75fe 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm) set_personality_ia32(false); setup_new_exec(bprm); + install_exec_creds(bprm); regs->cs = __USER32_CS; regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = @@ -314,8 +315,6 @@ static int load_aout_binary(struct linux_binprm *bprm) if (retval < 0) return retval; - install_exec_creds(bprm); - if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ca9725f18e005..af09b55d5ac52 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -244,6 +244,7 @@ static int load_aout_binary(struct linux_binprm * bprm) set_personality(PER_LINUX); #endif setup_new_exec(bprm); + install_exec_creds(bprm); current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); @@ -256,7 +257,6 @@ static int load_aout_binary(struct linux_binprm * bprm) if (retval < 0) return retval; - install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b53bb3729ac1e..60896c16f103c 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -357,6 +357,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->personality |= READ_IMPLIES_EXEC; setup_new_exec(bprm); + install_exec_creds(bprm); set_binfmt(&elf_fdpic_format); @@ -438,7 +439,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - install_exec_creds(bprm); if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) goto error; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index e4b59e76afb0d..bbeff9385d609 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -517,6 +517,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* OK, This is the point of no return */ set_personality(PER_LINUX_32BIT); setup_new_exec(bprm); + install_exec_creds(bprm); } /* @@ -940,8 +941,6 @@ static int load_flat_binary(struct linux_binprm *bprm) } } - install_exec_creds(bprm); - set_binfmt(&flat_format); #ifdef CONFIG_MMU -- 2.25.1

1 0

2024

2023

2022

2021

2020

2019

Kernel