From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-pj1-f73.google.com (mail-pj1-f73.google.com [209.85.216.73]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7614D23C8A0 for ; Fri, 10 Oct 2025 01:20:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.73 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1760059205; cv=none; b=e4//2mzd2E8wzlQ0kiCoI/O0/wG7+Aw8bZGCCX6vT15LD8WH9JgTzK8tKq6g0UccY7g5KPWO14cIPLAP5tTMASCRmVrKYJ9Y9ibEnmBz0jYL4Jz6sKiav9pCP2MtJAQk8hDGb3+v2DEEla7SB0inHkLuVWb26nVk6FCx5ze+nx8= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1760059205; c=relaxed/simple; bh=B/QFPXniGwEFGN4sNohbRDTRW/JKndUEcycvqtnTGMQ=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=sGPb2YsxIQaNLPnAMeRI3j6kMGpSEMtGFXnAJehN6gj4+oRqXo1bqpIq/qbFaWN2xosxQxdiEiaB9EoZWQ/RUFUsovjAU6kl1L0AL75npKPc8qs2n62C8lsTt8bF4vLdBwN8xRPt0piAtc0rVD0Nw11YpwU7k/MrXdXckMkfT0k= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=PIos4fRi; arc=none smtp.client-ip=209.85.216.73 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="PIos4fRi" Received: by mail-pj1-f73.google.com with SMTP id 98e67ed59e1d1-32ec69d22b2so3509218a91.1 for ; Thu, 09 Oct 2025 18:20:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1760059203; x=1760664003; darn=lists.linux.dev; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=qfFmaAKl937kSaDktiPuEwSl7VxkpxzCXx+g6sFaHjQ=; b=PIos4fRibwcIo12/Hcf0QeAH5lClU7eb16696f4eFqlO9dxZdPrm5KyiA78BuG/ZgT QKtHDTyL/Bh1pjhwwTPjU/o/seytwS8ooHXjM1vTDUtA6FI3BnZws7+NxNXE9V4Bf+V0 LQRN2eTJrRD8i8M7yobcPI+BT+jsUvZNEnK122GW8qLEHVnp/d+SjYFMWUDX77KEIlUC 2kzA8njTQKf19xDPiblGzNvw6BPXCECPGoPORWWmaV2vOLTzPvXb2YtJtcVt2oiRJmdT trGxEmXDXTGLJ1WZrHkHozDq6JDyc/ayZnYXshqwiJX7KfA3pApHu+qiJM/IjRO3S7Zu +VGA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1760059203; x=1760664003; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=qfFmaAKl937kSaDktiPuEwSl7VxkpxzCXx+g6sFaHjQ=; b=gXac1eqw5Gem9Lw9Me5fVVzchto5QnSFr5T8xreFffSodYg8iAzAok1/UCPVh+c56e OpwMXYnjuVygogUDbytSaS/FtWW6j0NZI4zlh3JFnvR3IFS38WVWmWFocIseTmlAHe05 7I2P9RShMCPa0mfzldH3DqVCfRR3hlmKxiURTgnJPs2n6UsXtahrmMcdY8TOgXV81wm0 6+JkKC4+rXeAFKpPs1C0ageojZIFiNGJBsk69Qm+EOcx6qnYXhEj82T79szGVH3pUXNY 7p1AAc2teVSFMxqfwR0KR22Av02CeVKVVhGxl0zfzIo9OOoOP089MvSWJQIPlo3MUlnz xC5A== X-Forwarded-Encrypted: i=1; AJvYcCVakG/PSxMOha70xSRJd2uuSGladafiZaq0OyoOzyR+vagLk/d4bI9XNWnta3xlAZVmaVLUmw==@lists.linux.dev X-Gm-Message-State: AOJu0YwCcIvKYeyVaHnC54EmC77iacSJn3d+by3Bu758Ba6tW72isguN Pdrx5XB9pYCKmPHJg2fQePUPoeRmUhox6LMBwDhxHH9rml2/vDp6tr9PASKnr6xdJJkFL30gEX6 wV45bdQ== X-Google-Smtp-Source: AGHT+IFjOaBKWzMfb/TvgcjiAKDwb9C3QEg3GiheZ0wej2yAwCBPTptgb70zWp2JQn59IyW7GzdntSOdWLc= X-Received: from pjbsr7.prod.google.com ([2002:a17:90b:4e87:b0:32e:e06a:4668]) (user=surenb job=prod-delivery.src-stubby-dispatcher) by 2002:a17:90b:1e07:b0:339:f09b:d372 with SMTP id 98e67ed59e1d1-33b513b4c91mr13745970a91.23.1760059202712; Thu, 09 Oct 2025 18:20:02 -0700 (PDT) Date: Thu, 9 Oct 2025 18:19:46 -0700 In-Reply-To: <20251010011951.2136980-1-surenb@google.com> Precedence: bulk X-Mailing-List: iommu@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20251010011951.2136980-1-surenb@google.com> X-Mailer: git-send-email 2.51.0.740.g6adb054d12-goog Message-ID: <20251010011951.2136980-4-surenb@google.com> Subject: [PATCH 3/8] mm/cleancache: readahead support From: Suren Baghdasaryan To: akpm@linux-foundation.org Cc: david@redhat.com, lorenzo.stoakes@oracle.com, Liam.Howlett@oracle.com, vbabka@suse.cz, alexandru.elisei@arm.com, peterx@redhat.com, sj@kernel.org, rppt@kernel.org, mhocko@suse.com, corbet@lwn.net, axboe@kernel.dk, viro@zeniv.linux.org.uk, brauner@kernel.org, hch@infradead.org, jack@suse.cz, willy@infradead.org, m.szyprowski@samsung.com, robin.murphy@arm.com, hannes@cmpxchg.org, zhengqi.arch@bytedance.com, shakeel.butt@linux.dev, axelrasmussen@google.com, yuanchu@google.com, weixugc@google.com, minchan@kernel.org, surenb@google.com, linux-mm@kvack.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org, iommu@lists.linux.dev Content-Type: text/plain; charset="UTF-8" Restore pages from the cleancache during readahead operation. Signed-off-by: Suren Baghdasaryan --- include/linux/cleancache.h | 17 +++++++++++ mm/cleancache.c | 59 ++++++++++++++++++++++++++++++++++++++ mm/readahead.c | 55 +++++++++++++++++++++++++++++++++++ 3 files changed, 131 insertions(+) diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index 458a7a25a8af..28b6d7b25964 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -11,6 +11,7 @@ #define CLEANCACHE_KEY_MAX 6 +struct cleancache_inode; #ifdef CONFIG_CLEANCACHE @@ -24,6 +25,14 @@ bool cleancache_invalidate_folio(struct address_space *mapping, bool cleancache_invalidate_inode(struct address_space *mapping, struct inode *inode); +struct cleancache_inode * +cleancache_start_inode_walk(struct address_space *mapping, + struct inode *inode, + unsigned long count); +void cleancache_end_inode_walk(struct cleancache_inode *ccinode); +bool cleancache_restore_from_inode(struct cleancache_inode *ccinode, + struct folio *folio); + /* * Backend API * @@ -53,6 +62,14 @@ static inline bool cleancache_invalidate_folio(struct address_space *mapping, static inline bool cleancache_invalidate_inode(struct address_space *mapping, struct inode *inode) { return false; } +static inline struct cleancache_inode * +cleancache_start_inode_walk(struct address_space *mapping, struct inode *inode, + unsigned long count) + { return NULL; } +static inline void cleancache_end_inode_walk(struct cleancache_inode *ccinode) {} +static inline bool cleancache_restore_from_inode(struct cleancache_inode *ccinode, + struct folio *folio) + { return false; } static inline int cleancache_backend_register_pool(const char *name) { return -EOPNOTSUPP; } static inline int cleancache_backend_get_folio(int pool_id, struct folio *folio) diff --git a/mm/cleancache.c b/mm/cleancache.c index 73a8b2655def..59b8fd309619 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -813,6 +813,65 @@ bool cleancache_invalidate_inode(struct address_space *mapping, return count > 0; } +struct cleancache_inode * +cleancache_start_inode_walk(struct address_space *mapping, struct inode *inode, + unsigned long count) +{ + struct cleancache_inode *ccinode; + struct cleancache_fs *fs; + int fs_id; + + if (!inode) + return ERR_PTR(-EINVAL); + + fs_id = mapping->host->i_sb->cleancache_id; + if (fs_id == CLEANCACHE_ID_INVALID) + return ERR_PTR(-EINVAL); + + fs = get_fs(fs_id); + if (!fs) + return NULL; + + ccinode = find_and_get_inode(fs, inode); + if (!ccinode) { + put_fs(fs); + return NULL; + } + + return ccinode; +} + +void cleancache_end_inode_walk(struct cleancache_inode *ccinode) +{ + struct cleancache_fs *fs = ccinode->fs; + + put_inode(ccinode); + put_fs(fs); +} + +bool cleancache_restore_from_inode(struct cleancache_inode *ccinode, + struct folio *folio) +{ + struct folio *stored_folio; + void *src, *dst; + bool ret = false; + + xa_lock(&ccinode->folios); + stored_folio = xa_load(&ccinode->folios, folio->index); + if (stored_folio) { + rotate_lru_folio(stored_folio); + src = kmap_local_folio(stored_folio, 0); + dst = kmap_local_folio(folio, 0); + memcpy(dst, src, PAGE_SIZE); + kunmap_local(dst); + kunmap_local(src); + ret = true; + } + xa_unlock(&ccinode->folios); + + return ret; +} + /* Backend API */ /* * Register a new backend and add its folios for cleancache to use. diff --git a/mm/readahead.c b/mm/readahead.c index 3a4b5d58eeb6..6f4986a5e14a 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -128,6 +128,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -146,12 +147,66 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) } EXPORT_SYMBOL_GPL(file_ra_state_init); +static inline bool restore_from_cleancache(struct readahead_control *rac) +{ + XA_STATE(xas, &rac->mapping->i_pages, rac->_index); + struct cleancache_inode *ccinode; + struct folio *folio; + unsigned long end; + bool ret = true; + + int count = readahead_count(rac); + + /* Readahead should not have started yet. */ + VM_BUG_ON(rac->_batch_count != 0); + + if (!count) + return true; + + ccinode = cleancache_start_inode_walk(rac->mapping, rac->mapping->host, + count); + if (!ccinode) + return false; + + end = rac->_index + rac->_nr_pages - 1; + xas_for_each(&xas, folio, end) { + unsigned long nr; + + if (xas_retry(&xas, folio)) { + ret = false; + break; + } + + if (!cleancache_restore_from_inode(ccinode, folio)) { + ret = false; + break; + } + + nr = folio_nr_pages(folio); + folio_mark_uptodate(folio); + folio_unlock(folio); + rac->_index += nr; + rac->_nr_pages -= nr; + rac->ra->size -= nr; + if (rac->ra->async_size >= nr) + rac->ra->async_size -= nr; + } + + cleancache_end_inode_walk(ccinode); + + return ret; +} + static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; + /* Try to read all pages from the cleancache */ + if (restore_from_cleancache(rac)) + return; + if (!readahead_count(rac)) return; -- 2.51.0.740.g6adb054d12-goog