diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/afs/flock.c | 2 | ||||
-rw-r--r-- | fs/afs/fsclient.c | 2 | ||||
-rw-r--r-- | fs/afs/internal.h | 3 | ||||
-rw-r--r-- | fs/afs/misc.c | 1 | ||||
-rw-r--r-- | fs/afs/rxrpc.c | 7 | ||||
-rw-r--r-- | fs/afs/yfsclient.c | 3 | ||||
-rw-r--r-- | fs/btrfs/ctree.h | 2 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 43 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 7 | ||||
-rw-r--r-- | fs/btrfs/space-info.c | 2 | ||||
-rw-r--r-- | fs/btrfs/volumes.c | 3 | ||||
-rw-r--r-- | fs/btrfs/zoned.c | 139 | ||||
-rw-r--r-- | fs/cifs/cifsfs.h | 4 | ||||
-rw-r--r-- | fs/cifs/connect.c | 14 | ||||
-rw-r--r-- | fs/cifs/file.c | 3 | ||||
-rw-r--r-- | fs/cifs/transport.c | 6 | ||||
-rw-r--r-- | fs/dax.c | 3 | ||||
-rw-r--r-- | fs/debugfs/inode.c | 22 | ||||
-rw-r--r-- | fs/erofs/fscache.c | 8 | ||||
-rw-r--r-- | fs/erofs/internal.h | 29 | ||||
-rw-r--r-- | fs/erofs/zmap.c | 16 | ||||
-rw-r--r-- | fs/exec.c | 7 | ||||
-rw-r--r-- | fs/exfat/fatent.c | 3 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 10 | ||||
-rw-r--r-- | fs/ext4/extents.c | 4 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 2 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 318 | ||||
-rw-r--r-- | fs/ext4/mballoc.h | 1 | ||||
-rw-r--r-- | fs/nfs/internal.h | 25 | ||||
-rw-r--r-- | fs/nfs/nfs42proc.c | 9 | ||||
-rw-r--r-- | fs/nfs/super.c | 27 | ||||
-rw-r--r-- | fs/nfs/write.c | 25 | ||||
-rw-r--r-- | fs/nfsd/vfs.c | 31 | ||||
-rw-r--r-- | fs/open.c | 2 | ||||
-rw-r--r-- | fs/tracefs/inode.c | 31 |
35 files changed, 438 insertions, 376 deletions
diff --git a/fs/afs/flock.c b/fs/afs/flock.c index c4210a3964d8..bbcc5afd1576 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call) if (call->error == 0) { spin_lock(&vnode->lock); trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0); - vnode->locked_at = call->reply_time; + vnode->locked_at = call->issue_time; afs_schedule_lock_extension(vnode); spin_unlock(&vnode->lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 4943413d9c5f..7d37f63ef0f0 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -131,7 +131,7 @@ bad: static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; + return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry; } static void xdr_decode_AFSCallBack(const __be32 **_bp, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 64ad55494349..723d162078a3 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -137,7 +137,6 @@ struct afs_call { bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ bool upgrade; /* T to request service upgrade */ - bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ @@ -151,7 +150,7 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - ktime_t reply_time; /* Time of first reply packet */ + ktime_t issue_time; /* Time of issue of operation */ }; struct afs_call_type { diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 933e67fcdab1..805328ca5428 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code) /* Unified AFS error table */ case UAEPERM: return -EPERM; case UAENOENT: return -ENOENT; + case UAEAGAIN: return -EAGAIN; case UAEACCES: return -EACCES; case UAEBUSY: return -EBUSY; case UAEEXIST: return -EEXIST; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index d5c4785c862d..eccc3cd0cb70 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -351,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) if (call->max_lifespan) rxrpc_kernel_set_max_life(call->net->socket, rxcall, call->max_lifespan); + call->issue_time = ktime_get_real(); /* send the request */ iov[0].iov_base = call->request; @@ -501,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call) return; } - if (!call->have_reply_time && - rxrpc_kernel_get_reply_time(call->net->socket, - call->rxcall, - &call->reply_time)) - call->have_reply_time = true; - ret = call->type->deliver(call); state = READ_ONCE(call->state); if (ret == 0 && call->unmarshalling_error) diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index fdc7d675b4b0..11571cca86c1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp, struct afs_callback *cb = &scb->callback; ktime_t cb_expiry; - cb_expiry = call->reply_time; - cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100); cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); scb->have_cb = true; *_bp += xdr_size(x); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9ef162dbd4bc..df8c99c99df9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1088,8 +1088,6 @@ struct btrfs_fs_info { spinlock_t zone_active_bgs_lock; struct list_head zone_active_bgs; - /* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */ - wait_queue_head_t zone_finish_wait; /* Updates are not protected by any lock */ struct btrfs_commit_stats commit_stats; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 820b1f1e6b67..2633137c3e9f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3068,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); - init_waitqueue_head(&fs_info->zone_finish_wait); /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; @@ -4476,6 +4475,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); /* + * If we had UNFINISHED_DROPS we could still be processing them, so + * clear that bit and wake up relocation so it can stop. + * We must do this before stopping the block group reclaim task, because + * at btrfs_relocate_block_group() we wait for this bit, and after the + * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we + * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will + * return 1. + */ + btrfs_wake_unfinished_drop(fs_info); + + /* * We may have the reclaim task running and relocating a data block group, * in which case it may create delayed iputs. So stop it before we park * the cleaner kthread otherwise we can get new delayed iputs after @@ -4493,12 +4503,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ kthread_park(fs_info->cleaner_kthread); - /* - * If we had UNFINISHED_DROPS we could still be processing them, so - * clear that bit and wake up relocation so it can stop. - */ - btrfs_wake_unfinished_drop(fs_info); - /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -4521,6 +4525,31 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * After we parked the cleaner kthread, ordered extents may have + * completed and created new delayed iputs. If one of the async reclaim + * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we + * can hang forever trying to stop it, because if a delayed iput is + * added after it ran btrfs_run_delayed_iputs() and before it called + * btrfs_wait_on_delayed_iputs(), it will hang forever since there is + * no one else to run iputs. + * + * So wait for all ongoing ordered extents to complete and then run + * delayed iputs. This works because once we reach this point no one + * can either create new ordered extents nor create delayed iputs + * through some other means. + * + * Also note that btrfs_wait_ordered_roots() is not safe here, because + * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, + * but the delayed iput for the respective inode is made only when doing + * the final btrfs_put_ordered_extent() (which must happen at + * btrfs_finish_ordered_io() when we are unmounting). + */ + btrfs_flush_workqueue(fs_info->endio_write_workers); + /* Ordered extents for free space inodes. */ + btrfs_flush_workqueue(fs_info->endio_freespace_worker); + btrfs_run_delayed_iputs(fs_info); + cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); cancel_work_sync(&fs_info->preempt_reclaim_work); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ad250892028d..1372210869b1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode, done_offset = end; if (done_offset == start) { - struct btrfs_fs_info *info = inode->root->fs_info; - - wait_var_event(&info->zone_finish_wait, - !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags)); + wait_on_bit_io(&inode->root->fs_info->flags, + BTRFS_FS_NEED_ZONE_FINISH, + TASK_UNINTERRUPTIBLE); continue; } diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d0cbeb7ae81c..435559ba94fa 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags) ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK); if (flags & BTRFS_BLOCK_GROUP_DATA) - return SZ_1G; + return BTRFS_MAX_DATA_CHUNK_SIZE; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) return SZ_32M; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 064ab2a79c80..f63ff91e2883 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5267,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, ctl->stripe_size); } + /* Stripe size should not go beyond 1G. */ + ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G); + /* Align to BTRFS_STRIPE_LEN */ ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN); ctl->chunk_size = ctl->stripe_size * data_stripes; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b150b07ba1a7..73c6929f7be6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) * since btrfs adds the pages one by one to a bio, and btrfs cannot * increase the metadata reservation even if it increases the number of * extents, it is safe to stick with the limit. + * + * With the zoned emulation, we can have non-zoned device on the zoned + * mode. In this case, we don't have a valid max zone append size. So, + * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size. */ - zone_info->max_zone_append_size = - min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, - (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + if (bdev_is_zoned(bdev)) { + zone_info->max_zone_append_size = min_t(u64, + (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + } else { + zone_info->max_zone_append_size = + (u64)bdev_max_segments(bdev) << PAGE_SHIFT; + } if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; @@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) * offset. */ static int calculate_alloc_pointer(struct btrfs_block_group *cache, - u64 *offset_ret) + u64 *offset_ret, bool new) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_root *root; @@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, int ret; u64 length; + /* + * Avoid tree lookups for a new block group, there's no use for it. + * It must always be 0. + * + * Also, we have a lock chain of extent buffer lock -> chunk mutex. + * For new a block group, this function is called from + * btrfs_make_block_group() which is already taking the chunk mutex. + * Thus, we cannot call calculate_alloc_pointer() which takes extent + * buffer locks to avoid deadlock. + */ + if (new) { + *offset_ret = 0; + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) else num_conventional++; + /* + * Consider a zone as active if we can allow any number of + * active zones. + */ + if (!device->zone_info->max_active_zones) + __set_bit(i, active); + if (!is_sequential) { alloc_offsets[i] = WP_CONVENTIONAL; continue; @@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) __set_bit(i, active); break; } - - /* - * Consider a zone as active if we can allow any number of - * active zones. - */ - if (!device->zone_info->max_active_zones) - __set_bit(i, active); } if (num_sequential > 0) cache->seq_zone = true; if (num_conventional > 0) { - /* - * Avoid calling calculate_alloc_pointer() for new BG. It - * is no use for new BG. It must be always 0. - * - * Also, we have a lock chain of extent buffer lock -> - * chunk mutex. For new BG, this function is called from - * btrfs_make_block_group() which is already taking the - * chunk mutex. Thus, we cannot call - * calculate_alloc_pointer() which takes extent buffer - * locks to avoid deadlock. - */ - /* Zone capacity is always zone size in emulation */ cache->zone_capacity = cache->length; - if (new) { - cache->alloc_offset = 0; - goto out; - } - ret = calculate_alloc_pointer(cache, &last_alloc); - if (ret || map->num_stripes == num_conventional) { - if (!ret) - cache->alloc_offset = last_alloc; - else - btrfs_err(fs_info, + ret = calculate_alloc_pointer(cache, &last_alloc, new); + if (ret) { + btrfs_err(fs_info, "zoned: failed to determine allocation offset of bg %llu", - cache->start); + cache->start); + goto out; + } else if (map->num_stripes == num_conventional) { + cache->alloc_offset = last_alloc; + cache->zone_is_active = 1; goto out; } } @@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } - if (cache->zone_is_active) { - btrfs_get_block_group(cache); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } - out: if (cache->alloc_offset > fs_info->zone_size) { btrfs_err(fs_info, @@ -1526,10 +1528,16 @@ out: ret = -EIO; } - if (!ret) + if (!ret) { cache->meta_write_pointer = cache->alloc_offset + cache->start; - - if (ret) { + if (cache->zone_is_active) { + btrfs_get_block_group(cache); + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&cache->active_bg_list, + &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); + } + } else { kfree(cache->physical_map); cache->physical_map = NULL; } @@ -1910,10 +1918,44 @@ out_unlock: return ret; } +static void wait_eb_writebacks(struct btrfs_block_group *block_group) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + const u64 end = block_group->start + block_group->length; + struct radix_tree_iter iter; + struct extent_buffer *eb; + void __rcu **slot; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, + block_group->start >> fs_info->sectorsize_bits) { + eb = radix_tree_deref_slot(slot); + if (!eb) + continue; + if (radix_tree_deref_retry(eb)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (eb->start < block_group->start) + continue; + if (eb->start >= end) + break; + + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + wait_on_extent_buffer_writeback(eb); + rcu_read_lock(); + } + rcu_read_unlock(); +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; + const bool is_metadata = (block_group->flags & + (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)); int ret = 0; int i; @@ -1924,8 +1966,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } /* Check if we have unwritten allocated space */ - if ((block_group->flags & - (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) && + if (is_metadata && block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) { spin_unlock(&block_group->lock); return -EAGAIN; @@ -1950,6 +1991,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* No need to wait for NOCOW writers. Zoned mode does not allow that */ btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, block_group->length); + /* Wait for extent buffers to be written. */ + if (is_metadata) + wait_eb_writebacks(block_group); spin_lock(&block_group->lock); @@ -2007,8 +2051,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* For active_bg_list */ btrfs_put_block_group(block_group); - clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - wake_up_all(&fs_info->zone_finish_wait); + clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); return 0; } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 81f4c15936d0..5b4a7a32bdc5 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,6 +153,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 38 -#define CIFS_VERSION "2.38" +#define SMB3_PRODUCT_BUILD 39 +#define CIFS_VERSION "2.39" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a0a06b6f252b..7ae6f2c08153 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -702,9 +702,6 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) int length = 0; int total_read; - smb_msg->msg_control = NULL; - smb_msg->msg_controllen = 0; - for (total_read = 0; msg_data_left(smb_msg); total_read += length) { try_to_freeze(); @@ -760,7 +757,7 @@ int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, unsigned int to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; struct kvec iov = {.iov_base = buf, .iov_len = to_read}; iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read); @@ -770,15 +767,13 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, ssize_t cifs_discard_from_socket(struct TCP_Server_Info *server, size_t to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; /* * iov_iter_discard already sets smb_msg.type and count and iov_offset * and cifs_readv_from_socket sets msg_control and msg_controllen * so little to initialize in struct msghdr */ - smb_msg.msg_name = NULL; - smb_msg.msg_namelen = 0; iov_iter_discard(&smb_msg.msg_iter, READ, to_read); return cifs_readv_from_socket(server, &smb_msg); @@ -788,7 +783,7 @@ int cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, unsigned int page_offset, unsigned int to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; struct bio_vec bv = { .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read); @@ -2350,7 +2345,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) ses = tcon->ses; cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (--tcon->tc_count > 0) { + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return; } @@ -2359,6 +2356,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) WARN_ON(tcon->tc_count < 0); list_del_init(&tcon->tcon_list); + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); /* cancel polling of interfaces */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fa738adc031f..6f38b134a346 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3575,6 +3575,9 @@ static ssize_t __cifs_writev( ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; + + cifs_revalidate_mapping(file->f_inode); return __cifs_writev(iocb, from, true); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index c2fe035e573b..9a2753e21170 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -194,10 +194,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, *sent = 0; - smb_msg->msg_name = (struct sockaddr *) &server->dstaddr; - smb_msg->msg_namelen = sizeof(struct sockaddr); - smb_msg->msg_control = NULL; - smb_msg->msg_controllen = 0; if (server->noblocksnd) smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; else @@ -309,7 +305,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, sigset_t mask, oldmask; size_t total_len = 0, sent, size; struct socket *ssocket = server->ssocket; - struct msghdr smb_msg; + struct msghdr smb_msg = {}; __be32 rfc1002_marker; if (cifs_rdma_enabled(server)) { @@ -1445,6 +1445,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t done = 0; int ret; + if (!iomi.len) + return 0; + if (iov_iter_rw(iter) == WRITE) { lockdep_assert_held_write(&iomi.inode->i_rwsem); iomi.flags |= IOMAP_WRITE; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3dcf0b8b4e93..232cfdf095ae 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -745,6 +745,28 @@ void debugfs_remove(struct dentry *dentry) EXPORT_SYMBOL_GPL(debugfs_remove); /** + * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it + * @name: a pointer to a string containing the name of the item to look up. + * @parent: a pointer to the parent dentry of the item. + * + * This is the equlivant of doing something like + * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting + * handled for the directory being looked up. + */ +void debugfs_lookup_and_remove(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + dentry = debugfs_lookup(name, parent); + if (!dentry) + return; + + debugfs_remove(dentry); + dput(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); + +/** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8e01d89c3319..b5fd9d71e67f 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -222,8 +222,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out; + } return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, rreq, mdev.m_pa); @@ -301,8 +303,10 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out_unlock; + } pstart = mdev.m_pa + (pos - map.m_la); return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index cfee49d33b95..a01cc82795a2 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -195,7 +195,6 @@ struct erofs_workgroup { atomic_t refcount; }; -#if defined(CONFIG_SMP) static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, int val) { @@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) return atomic_cond_read_relaxed(&grp->refcount, VAL != EROFS_LOCKED_MAGIC); } -#else -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - /* no need to spin on UP platforms, let's just disable preemption. */ - if (val != atomic_read(&grp->refcount)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - int v = atomic_read(&grp->refcount); - - /* workgroup is never freezed on uniprocessor systems */ - DBG_BUGON(v == EROFS_LOCKED_MAGIC); - return v; -} -#endif /* !CONFIG_SMP */ #endif /* !CONFIG_EROFS_FS_ZIP */ /* we strictly follow PAGE_SIZE and no buffer head yet */ diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 572f0b8151ba..d58549ca1df9 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -141,7 +141,7 @@ struct z_erofs_maprecorder { u8 type, headtype; u16 clusterofs; u16 delta[2]; - erofs_blk_t pblk, compressedlcs; + erofs_blk_t pblk, compressedblks; erofs_off_t nextpackoff; }; @@ -192,7 +192,7 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = m->delta[0] & + m->compressedblks = m->delta[0] & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; } @@ -293,7 +293,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { @@ -497,7 +497,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return 0; } lcn = m->lcn + 1; - if (m->compressedlcs) + if (m->compressedblks) goto out; err = z_erofs_load_cluster_from_disk(m, lcn, false); @@ -506,7 +506,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, /* * If the 1st NONHEAD lcluster has already been handled initially w/o - * valid compressedlcs, which means at least it mustn't be CBLKCNT, or + * valid compressedblks, which means at least it mustn't be CBLKCNT, or * an internal implemenatation error is detected. * * The following code can also handle it properly anyway, but let's @@ -523,12 +523,12 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. */ - m->compressedlcs = 1; + m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE); break; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; - if (m->compressedlcs) + if (m->compressedblks) break; fallthrough; default: @@ -539,7 +539,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return -EFSCORRUPTED; } out: - map->m_plen = (u64)m->compressedlcs << lclusterbits; + map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE; return 0; err_bonus_cblkcnt: erofs_err(m->inode->i_sb, diff --git a/fs/exec.c b/fs/exec.c index 9a5ca7b82bfc..d046dbb9cbd0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -65,7 +65,6 @@ #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> -#include <linux/time_namespace.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -979,12 +978,10 @@ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; - bool vfork; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; - vfork = !!tsk->vfork_done; old_mm = current->mm; exec_mm_release(tsk, old_mm); if (old_mm) @@ -1029,10 +1026,6 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); - - if (vfork) - timens_on_fork(tsk->nsproxy, tsk); - if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index ee0b7cf51157..41ae4cce1f42 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -270,8 +270,7 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) struct super_block *sb = dir->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct buffer_head *bh; - sector_t blknr, last_blknr; - int i; + sector_t blknr, last_blknr, i; blknr = exfat_cluster_to_sector(sbi, clu); last_blknr = blknr + sbi->sect_per_clus; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9bca5565547b..3bf9a6926798 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -167,8 +167,6 @@ enum SHIFT_DIRECTION { #define EXT4_MB_CR0_OPTIMIZED 0x8000 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */ #define EXT4_MB_CR1_OPTIMIZED 0x00010000 -/* Perform linear traversal for one group */ -#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; @@ -1600,8 +1598,8 @@ struct ext4_sb_info { struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; - struct rb_root s_mb_avg_fragment_size_root; - rwlock_t s_mb_rb_lock; + struct list_head *s_mb_avg_fragment_size; + rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; @@ -3413,6 +3411,8 @@ struct ext4_group_info { ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ + int bb_avg_fragment_size_order; /* order of average + fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; @@ -3420,7 +3420,7 @@ struct ext4_group_info { void *bb_bitmap; #endif struct rw_semaphore alloc_sem; - struct rb_node bb_avg_fragment_size_rb; + struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c148bb97b527..5235974126bd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } + if (unlikely((eh->eh_entries == 0) && (depth > 0))) { + error_msg = "eh_entries is 0 but eh_depth is > 0"; + goto corrupted; + } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f73e5eb43eae..208b87ce8858 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, goto fallback; } - max_dirs = ndirs / ngroups + inodes_per_group / 16; + max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index bd8f8b5c3d30..71f5b67d7f28 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -140,13 +140,15 @@ * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * - * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root) + * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * - * Locking: sbi->s_mb_rb_lock (rwlock) + * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * - * This is a red black tree consisting of group infos and the tree is sorted - * by average fragment sizes (which is calculated as ext4_group_info->bb_free - * / ext4_group_info->bb_fragments). + * This is an array of lists where in the i-th list there are groups with + * average fragment size >= 2^i and < 2^(i+1). The average fragment size + * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. + * Note that we don't bother with a special list for completely empty groups + * so we only have MB_NUM_ORDERS(sb) lists. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for @@ -160,7 +162,8 @@ * * At CR = 1, we only consider groups where average fragment size > request * size. So, we lookup a group which has average fragment size just above or - * equal to request size using our rb tree (data structure 2) in O(log N) time. + * equal to request size using our average fragment size group lists (data + * structure 2) in O(1) time. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR 0 and CR 1 phase. @@ -802,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new, - int (*cmp)(struct rb_node *, struct rb_node *)) +static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { - struct rb_node **iter = &root->rb_node, *parent = NULL; + int order; - while (*iter) { - parent = *iter; - if (cmp(new, *iter) > 0) - iter = &((*iter)->rb_left); - else - iter = &((*iter)->rb_right); - } - - rb_link_node(new, parent, iter); - rb_insert_color(new, root); -} - -static int -ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2) -{ - struct ext4_group_info *grp1 = rb_entry(rb1, - struct ext4_group_info, - bb_avg_fragment_size_rb); - struct ext4_group_info *grp2 = rb_entry(rb2, - struct ext4_group_info, - bb_avg_fragment_size_rb); - int num_frags_1, num_frags_2; - - num_frags_1 = grp1->bb_fragments ? - grp1->bb_free / grp1->bb_fragments : 0; - num_frags_2 = grp2->bb_fragments ? - grp2->bb_free / grp2->bb_fragments : 0; - - return (num_frags_2 - num_frags_1); + /* + * We don't bother with a special lists groups with only 1 block free + * extents and for completely empty groups. + */ + order = fls(len) - 2; + if (order < 0) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; + return order; } -/* - * Reinsert grpinfo into the avg_fragment_size tree with new average - * fragment size. - */ +/* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); + int new_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) return; - write_lock(&sbi->s_mb_rb_lock); - if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) { - rb_erase(&grp->bb_avg_fragment_size_rb, - &sbi->s_mb_avg_fragment_size_root); - RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb); - } + new_order = mb_avg_fragment_size_order(sb, + grp->bb_free / grp->bb_fragments); + if (new_order == grp->bb_avg_fragment_size_order) + return; - ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root, - &grp->bb_avg_fragment_size_rb, - ext4_mb_avg_fragment_size_cmp); - write_unlock(&sbi->s_mb_rb_lock); + if (grp->bb_avg_fragment_size_order != -1) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_del(&grp->bb_avg_fragment_size_node); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + } + grp->bb_avg_fragment_size_order = new_order; + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); } /* @@ -909,86 +898,56 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, *new_cr = 1; } else { *group = grp->bb_group; - ac->ac_last_optimal_group = *group; ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED; } } /* - * Choose next group by traversing average fragment size tree. Updates *new_cr - * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that - * the linear search should continue for one iteration since there's lock - * contention on the rb tree lock. + * Choose next group by traversing average fragment size list of suitable + * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, int *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - int avg_fragment_size, best_so_far; - struct rb_node *node, *found; - struct ext4_group_info *grp; - - /* - * If there is contention on the lock, instead of waiting for the lock - * to become available, just continue searching lineraly. We'll resume - * our rb tree search later starting at ac->ac_last_optimal_group. - */ - if (!read_trylock(&sbi->s_mb_rb_lock)) { - ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR; - return; - } + struct ext4_group_info *grp, *iter; + int i; if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_cr1_bad_suggestions); - /* We have found something at CR 1 in the past */ - grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group); - for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL; - found = rb_next(found)) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + } + + for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); + i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) + continue; + read_lock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) { + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + continue; + } + grp = NULL; + list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], + bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[1]); - if (likely(ext4_mb_good_group(ac, grp->bb_group, 1))) + if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) { + grp = iter; break; - } - goto done; - } - - node = sbi->s_mb_avg_fragment_size_root.rb_node; - best_so_far = 0; - found = NULL; - - while (node) { - grp = rb_entry(node, struct ext4_group_info, - bb_avg_fragment_size_rb); - avg_fragment_size = 0; - if (ext4_mb_good_group(ac, grp->bb_group, 1)) { - avg_fragment_size = grp->bb_fragments ? - grp->bb_free / grp->bb_fragments : 0; - if (!best_so_far || avg_fragment_size < best_so_far) { - best_so_far = avg_fragment_size; - found = node; } } - if (avg_fragment_size > ac->ac_g_ex.fe_len) - node = node->rb_right; - else - node = node->rb_left; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (grp) + break; } -done: - if (found) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED; } else { *new_cr = 2; } - - read_unlock(&sbi->s_mb_rb_lock); - ac->ac_last_optimal_group = *group; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) @@ -1017,11 +976,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) goto inc_and_return; } - if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) { - ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR; - goto inc_and_return; - } - return group; inc_and_return: /* @@ -1049,8 +1003,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, { *new_cr = ac->ac_criteria; - if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) { + *group = next_linear_group(ac, *group, ngroups); return; + } if (*new_cr == 0) { ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); @@ -1075,23 +1031,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) + if (grp->bb_counters[i] > 0) + break; + /* No need to move between order lists? */ + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || + i == grp->bb_largest_free_order) { + grp->bb_largest_free_order = i; + return; + } + + if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } - grp->bb_largest_free_order = -1; /* uninit */ - - for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) { - if (grp->bb_counters[i] > 0) { - grp->bb_largest_free_order = i; - break; - } - } - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && - grp->bb_largest_free_order >= 0 && grp->bb_free) { + grp->bb_largest_free_order = i; + if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, @@ -1148,13 +1106,13 @@ void ext4_mb_generate_buddy(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); + mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); - mb_update_avg_fragment_size(sb, grp); } /* The buddy information is attached the buddy cache inode @@ -2636,7 +2594,7 @@ static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; - int cr = -1; + int cr = -1, new_cr; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; @@ -2707,17 +2665,14 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; - ac->ac_last_optimal_group = group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; - for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups), - i++) { - int ret = 0, new_cr; + for (i = 0, new_cr = cr; i < ngroups; i++, + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { + int ret = 0; cond_resched(); - - ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); if (new_cr != cr) { cr = new_cr; goto repeat; @@ -2991,9 +2946,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; - read_lock(&EXT4_SB(sb)->s_mb_rb_lock); - - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3005,7 +2958,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof unsigned long position; ++*pos; - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3017,29 +2970,22 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; - struct rb_node *n; - unsigned int count, min, max; + unsigned int count; position--; if (position >= MB_NUM_ORDERS(sb)) { - seq_puts(seq, "fragment_size_tree:\n"); - n = rb_first(&sbi->s_mb_avg_fragment_size_root); - if (!n) { - seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n"); - return 0; - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; - count = 1; - while (rb_next(n)) { - count++; - n = rb_next(n); - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + position -= MB_NUM_ORDERS(sb); + if (position == 0) + seq_puts(seq, "avg_fragment_size_lists:\n"); - seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", - min, max, count); + count = 0; + read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); + list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], + bb_avg_fragment_size_node) + count++; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); return 0; } @@ -3049,9 +2995,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) seq_puts(seq, "max_free_order_lists:\n"); } count = 0; + read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; + read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); @@ -3059,11 +3007,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) -__releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = pde_data(file_inode(seq->file)); - - read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } const struct seq_operations ext4_mb_seq_structs_summary_ops = { @@ -3176,8 +3120,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); - RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb); + INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); @@ -3426,7 +3371,24 @@ int ext4_mb_init(struct super_block *sb) i++; } while (i < MB_NUM_ORDERS(sb)); - sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_avg_fragment_size = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_avg_fragment_size_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); + rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); + } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); @@ -3445,7 +3407,6 @@ int ext4_mb_init(struct super_block *sb) INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } - rwlock_init(&sbi->s_mb_rb_lock); spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; @@ -3516,6 +3477,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3582,6 +3545,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -5193,6 +5158,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; + bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; @@ -5200,25 +5166,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; + group_pa_eligible = sbi->s_mb_group_prealloc > 0; + inode_pa_eligible = true; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; + /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && - !inode_is_open_for_write(ac->ac_inode)) { - ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; - return; - } + !inode_is_open_for_write(ac->ac_inode)) + inode_pa_eligible = false; - if (sbi->s_mb_group_prealloc <= 0) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; - return; - } - - /* don't use group allocation for large files */ size = max(size, isize); - if (size > sbi->s_mb_stream_request) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + /* Don't use group allocation for large files */ + if (size > sbi->s_mb_stream_request) + group_pa_eligible = false; + + if (!group_pa_eligible) { + if (inode_pa_eligible) + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + else + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } @@ -5565,6 +5533,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + int retries = 0; u64 seq; might_sleep(); @@ -5667,7 +5636,8 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) + if (++retries < 3 && + ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 39da92ceabf8..dcda2a943cee 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -178,7 +178,6 @@ struct ext4_allocation_context { /* copy of the best found extent taken before preallocation efforts */ struct ext4_free_extent ac_f_ex; - ext4_group_t ac_last_optimal_group; __u32 ac_groups_considered; __u32 ac_flags; /* allocation hints */ __u16 ac_groups_scanned; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 27c720d71b4e..898dd95bc7a7 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -606,6 +606,31 @@ static inline gfp_t nfs_io_gfp_mask(void) return GFP_KERNEL; } +/* + * Special version of should_remove_suid() that ignores capabilities. + */ +static inline int nfs_should_remove_suid(const struct inode *inode) +{ + umode_t mode = inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && S_ISREG(mode))) + return kill; + + return 0; +} + /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 068c45b3bc1a..6dab9e408372 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -78,10 +78,15 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); - if (status == 0) + if (status == 0) { + if (nfs_should_remove_suid(inode)) { + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + spin_unlock(&inode->i_lock); + } status = nfs_post_op_update_inode_force_wcc(inode, res.falloc_fattr); - + } if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE]) trace_nfs4_fallocate(inode, &args, status); else diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 82944e14fcea..ee66ffdb985e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1051,22 +1051,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) if (ctx->bsize) sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits); - if (server->nfs_client->rpc_ops->version != 2) { - /* The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. + switch (server->nfs_client->rpc_ops->version) { + case 2: + sb->s_time_gran = 1000; + sb->s_time_min = 0; + sb->s_time_max = U32_MAX; + break; + case 3: + /* + * The VFS shouldn't apply the umask to mode bits. + * We will do so ourselves when necessary. */ sb->s_flags |= SB_POSIXACL; sb->s_time_gran = 1; - sb->s_export_op = &nfs_export_ops; - } else - sb->s_time_gran = 1000; - - if (server->nfs_client->rpc_ops->version != 4) { sb->s_time_min = 0; sb->s_time_max = U32_MAX; - } else { + sb->s_export_op = &nfs_export_ops; + break; + case 4: + sb->s_flags |= SB_POSIXACL; + sb->s_time_gran = 1; sb->s_time_min = S64_MIN; sb->s_time_max = S64_MAX; + if (server->caps & NFS_CAP_ATOMIC_OPEN_V1) + sb->s_export_op = &nfs_export_ops; + break; } sb->s_magic = NFS_SUPER_MAGIC; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 1843fa235d9b..f41d24b54fd1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1496,31 +1496,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -/* - * Special version of should_remove_suid() that ignores capabilities. - */ -static int nfs_should_remove_suid(const struct inode *inode) -{ - umode_t mode = inode->i_mode; - int kill = 0; - - /* suid always must be killed */ - if (unlikely(mode & S_ISUID)) - kill = ATTR_KILL_SUID; - - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; - - if (unlikely(kill && S_ISREG(mode))) - return kill; - - return 0; -} - static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, struct nfs_fattr *fattr) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9f486b788ed0..fc17b0ac8729 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -300,6 +300,10 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { + /* Ignore mode updates on symlinks */ + if (S_ISLNK(inode->i_mode)) + iap->ia_valid &= ~ATTR_MODE; + /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -353,7 +357,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; - int host_err; + int host_err = 0; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); @@ -391,13 +395,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = fhp->fh_dentry; inode = d_inode(dentry); - /* Ignore any mode updates on symlinks */ - if (S_ISLNK(inode->i_mode)) - iap->ia_valid &= ~ATTR_MODE; - - if (!iap->ia_valid) - return 0; - nfsd_sanitize_attrs(inode, iap); if (check_guard && guardtime != inode->i_ctime.tv_sec) @@ -448,8 +445,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_unlock; } - iap->ia_valid |= ATTR_CTIME; - host_err = notify_change(&init_user_ns, dentry, iap, NULL); + if (iap->ia_valid) { + iap->ia_valid |= ATTR_CTIME; + host_err = notify_change(&init_user_ns, dentry, iap, NULL); + } out_unlock: if (attr->na_seclabel && attr->na_seclabel->len) @@ -846,10 +845,14 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct svc_rqst *rqstp = sd->u.data; - - svc_rqst_replace_page(rqstp, buf->page); - if (rqstp->rq_res.page_len == 0) - rqstp->rq_res.page_base = buf->offset; + struct page *page = buf->page; // may be a compound one + unsigned offset = buf->offset; + + page += offset / PAGE_SIZE; + for (int i = sd->len; i > 0; i -= PAGE_SIZE) + svc_rqst_replace_page(rqstp, page++); + if (rqstp->rq_res.page_len == 0) // first call + rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; return sd->len; } diff --git a/fs/open.c b/fs/open.c index 8a813fa5ca56..cf7e5c350a54 100644 --- a/fs/open.c +++ b/fs/open.c @@ -716,6 +716,8 @@ int chown_common(const struct path *path, uid_t user, gid_t group) fs_userns = i_user_ns(inode); retry_deleg: + newattrs.ia_vfsuid = INVALID_VFSUID; + newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 81d26abf486f..da85b3979195 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -141,6 +141,8 @@ struct tracefs_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; }; enum { @@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) kgid_t gid; char *p; + opts->opts = 0; opts->mode = TRACEFS_DEFAULT_MODE; while ((p = strsep(&data, ",")) != NULL) { @@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) * but traditionally tracefs has ignored all mount options */ } + + opts->opts |= BIT(token); } return 0; } -static int tracefs_apply_options(struct super_block *sb) +static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts; - inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= opts->mode; + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || opts->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + } - inode->i_uid = opts->uid; + if (!remount || opts->opts & BIT(Opt_uid)) + inode->i_uid = opts->uid; - /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); + if (!remount || opts->opts & BIT(Opt_gid)) { + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); + } return 0; } @@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data) if (err) goto fail; - tracefs_apply_options(sb); + tracefs_apply_options(sb, true); fail: return err; @@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &tracefs_super_operations; - tracefs_apply_options(sb); + tracefs_apply_options(sb, false); return 0; |