Received: from out-179.mta0.migadu.com (out-179.mta0.migadu.com [91.218.175.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3ECEA19A298 for ; Mon, 30 Dec 2024 21:43:05 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.179 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1735594987; cv=none; b=ZZk/qszpytpI/E5Ltug1pcYpd0WbaDmum4wJ7jlpo6tFEW0GFa+yuKGbvs5HCgn8m/vDnHXjLeueeuj0ERrDtzIsU7i4d/7D+Caga5A9JHKHuXx7/6XLhplIkRq7zuEa0m/twijBiWOkOu5p/ZesTc34H6SVEoYMri9/WQizpqY= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1735594987; c=relaxed/simple; bh=wyZbFTBNzoRg+8kBZ5EaOS5AgrGpWZiZUhdFfd7N6CY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Gs+PugRg+9MLkeEqv6Q6fkoiY505ufoZBXYdA5zzSLH/3O7B46q62++Me7JmTfmw+7IPwxMUlYn45e4opQOBhs+XhHa9eUrCTX+5UzixOutYlIgCrqSMskLJ39TqRhZAj8dvXUOOd+QmnAbfiEgr/G1oLX5Kjw6O0dqgKmNf+aQ= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=DF/YPOcY; arc=none smtp.client-ip=91.218.175.179 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="DF/YPOcY" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1735594983; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=8cxSKTM0RnjMCvbtdKoOraYJDy1xrvCpL7CaGkjD7Pw=; b=DF/YPOcYS++8wz4DsH9tMOmHRm8ns8PwMBhVA5EE/HJdUGSS+qjEvoyW5HYcAHMWLMeXiP GgpIY2v28qbORDz7Ohf95DF09zNrDUdLLB/gaGhU9RS6hkxPbnwmSOO9suWUJwUDsykDgG u20CXoeFp219KAxxTqrV3hkE8R4Ls8o= From: Kent Overstreet To: linux-bcachefs@vger.kernel.org Cc: Kent Overstreet Subject: [PATCH 09/11] bcachefs: bch2_btree_node_scrub() Date: Mon, 30 Dec 2024 16:42:47 -0500 Message-ID: <20241230214249.242966-9-kent.overstreet@linux.dev> In-Reply-To: <20241230214249.242966-1-kent.overstreet@linux.dev> References: <20241230214249.242966-1-kent.overstreet@linux.dev> Precedence: bulk X-Mailing-List: linux-bcachefs@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Migadu-Flow: FLOW_OUT Add a function for scrubbing btree nodes - reading them in, and kicking off a rewrite if there's an error. The btree_node_read_done() checks have to be duplicated because we're not using a pointer to a struct btree - the btree node might already be in cache, and we need to check a specific replica, which might not be the one we previously read from. This will be used in the next patch implementing high-level scrub. Signed-off-by: Kent Overstreet --- fs/bcachefs/bcachefs.h | 3 +- fs/bcachefs/btree_io.c | 185 +++++++++++++++++++++++++++++++++++++++++ fs/bcachefs/btree_io.h | 3 + fs/bcachefs/errcode.h | 1 + 4 files changed, 191 insertions(+), 1 deletion(-) diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 161cf2f05d2a..13acfbf3852a 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -687,7 +687,8 @@ struct btree_trans_buf { x(gc_gens) \ x(snapshot_delete_pagecache) \ x(sysfs) \ - x(btree_write_buffer) + x(btree_write_buffer) \ + x(btree_node_scrub) enum bch_write_ref { #define x(n) BCH_WRITE_REF_##n, diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 73f75e38da7f..13ab827ddab5 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "bkey_buf.h" #include "bkey_methods.h" #include "bkey_sort.h" #include "btree_cache.h" @@ -1811,6 +1812,190 @@ int bch2_btree_root_read(struct bch_fs *c, enum btree_id id, return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level)); } +struct btree_node_scrub { + struct bch_fs *c; + struct bch_dev *ca; + void *buf; + bool used_mempool; + unsigned written; + + enum btree_id btree; + unsigned level; + struct bkey_buf key; + __le64 seq; + + struct work_struct work; + struct bio bio; +}; + +static bool btree_node_scrub_check(struct bch_fs *c, struct btree_node *data, unsigned ptr_written, + struct printbuf *err) +{ + unsigned written = 0; + + if (le64_to_cpu(data->magic) != bset_magic(c)) { + prt_printf(err, "bad magic: want %llx, got %llx", + bset_magic(c), le64_to_cpu(data->magic)); + return false; + } + + while (written < (ptr_written ?: btree_sectors(c))) { + struct btree_node_entry *bne; + struct bset *i; + bool first = !written; + + if (first) { + bne = NULL; + i = &data->keys; + } else { + bne = (void *) data + (written << 9); + i = &bne->keys; + + if (!ptr_written && i->seq != data->keys.seq) + break; + } + + struct nonce nonce = btree_nonce(i, written << 9); + bool good_csum_type = bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)); + + if (first) { + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, data); + if (bch2_crc_cmp(data->csum, csum)) { + bch2_csum_err_msg(err, BSET_CSUM_TYPE(i), data->csum, csum); + return false; + } + } + + written += vstruct_sectors(data, c->block_bits); + } else { + if (good_csum_type) { + struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne); + if (bch2_crc_cmp(bne->csum, csum)) { + bch2_csum_err_msg(err, BSET_CSUM_TYPE(i), bne->csum, csum); + return false; + } + } + + written += vstruct_sectors(bne, c->block_bits); + } + } + + return true; +} + +static void btree_node_scrub_work(struct work_struct *work) +{ + struct btree_node_scrub *scrub = container_of(work, struct btree_node_scrub, work); + struct bch_fs *c = scrub->c; + struct printbuf err = PRINTBUF; + + __bch2_btree_pos_to_text(&err, c, scrub->btree, scrub->level, + bkey_i_to_s_c(scrub->key.k)); + prt_newline(&err); + + if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) { + struct btree_trans *trans = bch2_trans_get(c); + + struct btree_iter iter; + bch2_trans_node_iter_init(trans, &iter, scrub->btree, + scrub->key.k->k.p, 0, scrub->level - 1, 0); + + struct btree *b; + int ret = lockrestart_do(trans, PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(&iter))); + if (ret) + goto err; + + if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) { + bch_err(c, "error validating btree node during scrub on %s at btree %s", + scrub->ca->name, err.buf); + + ret = bch2_btree_node_rewrite(trans, &iter, b, 0); + } +err: + bch2_trans_iter_exit(trans, &iter); + bch2_trans_begin(trans); + bch2_trans_put(trans); + } + + printbuf_exit(&err); + bch2_bkey_buf_exit(&scrub->key, c);; + btree_bounce_free(c, c->opts.btree_node_size, scrub->used_mempool, scrub->buf); + percpu_ref_put(&scrub->ca->io_ref); + kfree(scrub); + bch2_write_ref_put(c, BCH_WRITE_REF_btree_node_scrub); +} + +static void btree_node_scrub_endio(struct bio *bio) +{ + struct btree_node_scrub *scrub = container_of(bio, struct btree_node_scrub, bio); + + queue_work(scrub->c->btree_read_complete_wq, &scrub->work); +} + +int bch2_btree_node_scrub(struct btree_trans *trans, + enum btree_id btree, unsigned level, + struct bkey_s_c k, unsigned dev) +{ + if (k.k->type != KEY_TYPE_btree_ptr_v2) + return 0; + + struct bch_fs *c = trans->c; + + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_btree_node_scrub)) + return -BCH_ERR_erofs_no_writes; + + struct extent_ptr_decoded pick; + int ret = bch2_bkey_pick_read_device(c, k, NULL, &pick, dev); + if (ret <= 0) + goto err; + + struct bch_dev *ca = bch2_dev_get_ioref(c, pick.ptr.dev, READ); + if (!ca) { + ret = -BCH_ERR_device_offline; + goto err; + } + + bool used_mempool = false; + void *buf = btree_bounce_alloc(c, c->opts.btree_node_size, &used_mempool); + + unsigned vecs = buf_pages(buf, c->opts.btree_node_size); + + struct btree_node_scrub *scrub = + kzalloc(sizeof(*scrub) + sizeof(struct bio_vec) * vecs, GFP_KERNEL); + if (!scrub) { + ret = -ENOMEM; + goto err_free; + } + + scrub->c = c; + scrub->ca = ca; + scrub->buf = buf; + scrub->used_mempool = used_mempool; + scrub->written = btree_ptr_sectors_written(k); + + scrub->btree = btree; + scrub->level = level; + bch2_bkey_buf_init(&scrub->key); + bch2_bkey_buf_reassemble(&scrub->key, c, k); + scrub->seq = bkey_s_c_to_btree_ptr_v2(k).v->seq; + + INIT_WORK(&scrub->work, btree_node_scrub_work); + + bio_init(&scrub->bio, ca->disk_sb.bdev, scrub->bio.bi_inline_vecs, vecs, REQ_OP_READ); + bch2_bio_map(&scrub->bio, scrub->buf, c->opts.btree_node_size); + scrub->bio.bi_iter.bi_sector = pick.ptr.offset; + scrub->bio.bi_end_io = btree_node_scrub_endio; + submit_bio(&scrub->bio); + return 0; +err_free: + btree_bounce_free(c, c->opts.btree_node_size, used_mempool, buf); + percpu_ref_put(&ca->io_ref); +err: + bch2_write_ref_put(c, BCH_WRITE_REF_btree_node_scrub); + return ret; +} + static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b, struct btree_write *w) { diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h index 6f9e4a6dacf7..75ead3815d67 100644 --- a/fs/bcachefs/btree_io.h +++ b/fs/bcachefs/btree_io.h @@ -132,6 +132,9 @@ void bch2_btree_node_read(struct btree_trans *, struct btree *, bool); int bch2_btree_root_read(struct bch_fs *, enum btree_id, const struct bkey_i *, unsigned); +int bch2_btree_node_scrub(struct btree_trans *, enum btree_id, unsigned, + struct bkey_s_c, unsigned); + bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *); enum btree_write_flags { diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 4590cd0c7c90..cae4fc3e8572 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -269,6 +269,7 @@ x(EIO, invalidate_stripe_to_dev) \ x(EIO, no_encryption_key) \ x(EIO, insufficient_journal_devices) \ + x(EIO, device_offline) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_fixable) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_want_retry) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_must_retry) \ -- 2.45.2