From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out-189.mta1.migadu.com (out-189.mta1.migadu.com [95.215.58.189]) (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 6811C176AB5 for ; Fri, 18 Oct 2024 04:40:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.189 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729226426; cv=none; b=qCaf8/i/rwV/eSGIuXCoVsZaS0NkHg62TzJVA1GZvIaTb9JFHCMNQX8qodMTXOfEwGAwp+kCqx6dxuKFUw3JRtpOibwrTnsKPrrvHmJfsfHEYWz1gz2KIQ+Q89uzV+mS4zFfLlUPvk2lHUo7lsnmbwkSb25boH4sUEogfhVPS4g= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1729226426; c=relaxed/simple; bh=DGWRzam+l45Hytc4+SmFYguxqlr36lRtPaRWeoG5oqo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=uEBTvCSp3MSw/HRB2gD5CETPEv3ahtfbjihnKfjHc99cSpo2hb1C+7yTlOFMCLdh8GxABYrWOV16iOd7QHPNIDxYMS+QxcMaBeYJvmrDQhsjcUcOGbh5fo9HPrAzd+UlbKK/zGEBHlQeyZfky+CEF0CPbKmmQCrFGU0y0wdK9VM= 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=C22r/tzO; arc=none smtp.client-ip=95.215.58.189 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="C22r/tzO" 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=1729226420; 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=4auIEaqQtjxB09SwMeQ6SEZ2NekbyifCjJveASvGTnA=; b=C22r/tzOTD/hrD5uSxx+Fn9U+hb+K0Cv/rzlWeHphVFsY6i3TMKO7QaPESrKdx6/jqKLvf QChx/ZcW9QiD0AyicSG/YIviOIdZq9GjsgI0Nchd98tIntGT3Pz0g4L7cqhcfrBSdmO9oF 7C+Kv21f8/M1tAsDDddAYOfnAbG6xRw= From: Kent Overstreet To: linux-bcachefs@vger.kernel.org Cc: Kent Overstreet Subject: [PATCH 2/3] bcachefs: bch2_folio_reservation_get_partial() is now better behaved Date: Fri, 18 Oct 2024 00:40:02 -0400 Message-ID: <20241018044006.4067521-3-kent.overstreet@linux.dev> In-Reply-To: <20241018044006.4067521-1-kent.overstreet@linux.dev> References: <20241018044006.4067521-1-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 bch2_folio_reservation_get_partial(), on partial success, will now return a reservation that's aligned to the filesystem blocksize. This is a partial fix for fstests generic/299 - fio verify is badly behaved in the presence of short writes that aren't aligned to its blocksize. Signed-off-by: Kent Overstreet --- fs/bcachefs/buckets.c | 7 +++- fs/bcachefs/buckets.h | 12 +++--- fs/bcachefs/fs-io-pagecache.c | 70 ++++++++++++++++++++++------------- 3 files changed, 57 insertions(+), 32 deletions(-) diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index 546cd01a72e3..ec7d9a59bea9 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -1160,11 +1160,11 @@ int bch2_trans_mark_dev_sbs(struct bch_fs *c) #define SECTORS_CACHE 1024 int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res, - u64 sectors, int flags) + u64 sectors, enum bch_reservation_flags flags) { struct bch_fs_pcpu *pcpu; u64 old, get; - s64 sectors_available; + u64 sectors_available; int ret; percpu_down_read(&c->mark_lock); @@ -1202,6 +1202,9 @@ int __bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res, percpu_u64_set(&c->pcpu->sectors_available, 0); sectors_available = avail_factor(__bch2_fs_usage_read_short(c).free); + if (sectors_available && (flags & BCH_DISK_RESERVATION_PARTIAL)) + sectors = min(sectors, sectors_available); + if (sectors <= sectors_available || (flags & BCH_DISK_RESERVATION_NOFAIL)) { atomic64_set(&c->sectors_available, diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index e2cb7b24b220..fd5e6ccad45e 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -344,14 +344,16 @@ static inline void bch2_disk_reservation_put(struct bch_fs *c, } } -#define BCH_DISK_RESERVATION_NOFAIL (1 << 0) +enum bch_reservation_flags { + BCH_DISK_RESERVATION_NOFAIL = 1 << 0, + BCH_DISK_RESERVATION_PARTIAL = 1 << 1, +}; -int __bch2_disk_reservation_add(struct bch_fs *, - struct disk_reservation *, - u64, int); +int __bch2_disk_reservation_add(struct bch_fs *, struct disk_reservation *, + u64, enum bch_reservation_flags); static inline int bch2_disk_reservation_add(struct bch_fs *c, struct disk_reservation *res, - u64 sectors, int flags) + u64 sectors, enum bch_reservation_flags flags) { #ifdef __KERNEL__ u64 old, new; diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c index cde3a0445ee9..1d4910ea0f1d 100644 --- a/fs/bcachefs/fs-io-pagecache.c +++ b/fs/bcachefs/fs-io-pagecache.c @@ -399,14 +399,17 @@ void bch2_folio_reservation_put(struct bch_fs *c, bch2_quota_reservation_put(c, inode, &res->quota); } -int bch2_folio_reservation_get(struct bch_fs *c, +static int __bch2_folio_reservation_get(struct bch_fs *c, struct bch_inode_info *inode, struct folio *folio, struct bch2_folio_reservation *res, - size_t offset, size_t len) + size_t offset, size_t len, + bool partial) { struct bch_folio *s = bch2_folio_create(folio, 0); unsigned i, disk_sectors = 0, quota_sectors = 0; + struct disk_reservation disk_res = {}; + size_t reserved = len; int ret; if (!s) @@ -422,48 +425,65 @@ int bch2_folio_reservation_get(struct bch_fs *c, } if (disk_sectors) { - ret = bch2_disk_reservation_add(c, &res->disk, disk_sectors, 0); + ret = bch2_disk_reservation_add(c, &disk_res, disk_sectors, + partial ? BCH_DISK_RESERVATION_PARTIAL : 0); if (unlikely(ret)) return ret; + + if (unlikely(disk_res.sectors != disk_sectors)) { + disk_sectors = quota_sectors = 0; + + for (i = round_down(offset, block_bytes(c)) >> 9; + i < round_up(offset + len, block_bytes(c)) >> 9; + i++) { + disk_sectors += sectors_to_reserve(&s->s[i], res->disk.nr_replicas); + if (disk_sectors > disk_res.sectors) { + /* + * Make sure to get a reservation that's + * aligned to the filesystem blocksize: + */ + unsigned reserved_offset = round_down(i << 9, block_bytes(c)); + reserved = clamp(reserved_offset, offset, offset + len) - offset; + + if (!reserved) { + bch2_disk_reservation_put(c, &disk_res); + return -BCH_ERR_ENOSPC_disk_reservation; + } + break; + } + quota_sectors += s->s[i].state == SECTOR_unallocated; + } + } } if (quota_sectors) { ret = bch2_quota_reservation_add(c, inode, &res->quota, quota_sectors, true); if (unlikely(ret)) { - struct disk_reservation tmp = { .sectors = disk_sectors }; - res->disk.sectors -= disk_sectors; - - bch2_disk_reservation_put(c, &tmp); + bch2_disk_reservation_put(c, &disk_res); return ret; } } - return 0; + res->disk.sectors += disk_res.sectors; + return partial ? reserved : 0; } -ssize_t bch2_folio_reservation_get_partial(struct bch_fs *c, +int bch2_folio_reservation_get(struct bch_fs *c, struct bch_inode_info *inode, struct folio *folio, struct bch2_folio_reservation *res, size_t offset, size_t len) { - size_t l, reserved = 0; - int ret; - - while ((l = len - reserved)) { - while ((ret = bch2_folio_reservation_get(c, inode, folio, res, offset, l))) { - if ((offset & (block_bytes(c) - 1)) + l <= block_bytes(c)) - return reserved ?: ret; - - len = reserved + l; - l /= 2; - } - - offset += l; - reserved += l; - } + return __bch2_folio_reservation_get(c, inode, folio, res, offset, len, false); +} - return reserved; +ssize_t bch2_folio_reservation_get_partial(struct bch_fs *c, + struct bch_inode_info *inode, + struct folio *folio, + struct bch2_folio_reservation *res, + size_t offset, size_t len) +{ + return __bch2_folio_reservation_get(c, inode, folio, res, offset, len, true); } static void bch2_clear_folio_bits(struct folio *folio) -- 2.45.2