From patchwork Fri Apr 15 12:35:54 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814858 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AF8B1C433FE for ; Fri, 15 Apr 2022 12:36:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353455AbiDOMi5 (ORCPT ); Fri, 15 Apr 2022 08:38:57 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39384 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353424AbiDOMix (ORCPT ); Fri, 15 Apr 2022 08:38:53 -0400 Received: from out30-43.freemail.mail.aliyun.com (out30-43.freemail.mail.aliyun.com [115.124.30.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D33B32316B; Fri, 15 Apr 2022 05:36:23 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R141e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e01424;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7GjEt_1650026176; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7GjEt_1650026176) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:17 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 01/21] cachefiles: extract write routine Date: Fri, 15 Apr 2022 20:35:54 +0800 Message-Id: <20220415123614.54024-2-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Extract the generic routine of writing data to cache files, and make it generally available. This will be used by the following patch implementing on-demand read mode. Since it's called inside cachefiles module in this case, make the interface generic and unrelated to netfs_cache_resources. It is worth noting that, ki->inval_counter is not initialized after this cleanup. It shall not make any visible difference, since inval_counter is no longer used in the write completion routine, i.e. cachefiles_write_complete(). Signed-off-by: Jeffle Xu Acked-by: David Howells --- fs/cachefiles/internal.h | 10 +++++++ fs/cachefiles/io.c | 61 +++++++++++++++++++++++----------------- 2 files changed, 45 insertions(+), 26 deletions(-) diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index c793d33b0224..e80673d0ab97 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -201,6 +201,16 @@ extern void cachefiles_put_object(struct cachefiles_object *object, */ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres, enum fscache_want_state want_state); +extern int __cachefiles_prepare_write(struct cachefiles_object *object, + struct file *file, + loff_t *_start, size_t *_len, + bool no_space_allocated_yet); +extern int __cachefiles_write(struct cachefiles_object *object, + struct file *file, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv); /* * key.c diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 9dc81e781f2b..50a14e8f0aac 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -277,36 +277,33 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret) /* * Initiate a write to the cache. */ -static int cachefiles_write(struct netfs_cache_resources *cres, - loff_t start_pos, - struct iov_iter *iter, - netfs_io_terminated_t term_func, - void *term_func_priv) +int __cachefiles_write(struct cachefiles_object *object, + struct file *file, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) { - struct cachefiles_object *object; struct cachefiles_cache *cache; struct cachefiles_kiocb *ki; struct inode *inode; - struct file *file; unsigned int old_nofs; - ssize_t ret = -ENOBUFS; + ssize_t ret; size_t len = iov_iter_count(iter); - if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) - goto presubmission_error; fscache_count_write(); - object = cachefiles_cres_object(cres); cache = object->volume->cache; - file = cachefiles_cres_file(cres); _enter("%pD,%li,%llx,%zx/%llx", file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); - ret = -ENOMEM; ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL); - if (!ki) - goto presubmission_error; + if (!ki) { + if (term_func) + term_func(term_func_priv, -ENOMEM, false); + return -ENOMEM; + } refcount_set(&ki->ki_refcnt, 2); ki->iocb.ki_filp = file; @@ -314,7 +311,6 @@ static int cachefiles_write(struct netfs_cache_resources *cres, ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE; ki->iocb.ki_ioprio = get_current_ioprio(); ki->object = object; - ki->inval_counter = cres->inval_counter; ki->start = start_pos; ki->len = len; ki->term_func = term_func; @@ -369,11 +365,24 @@ static int cachefiles_write(struct netfs_cache_resources *cres, cachefiles_put_kiocb(ki); _leave(" = %zd", ret); return ret; +} -presubmission_error: - if (term_func) - term_func(term_func_priv, ret, false); - return ret; +static int cachefiles_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) { + if (term_func) + term_func(term_func_priv, -ENOBUFS, false); + return -ENOBUFS; + } + + return __cachefiles_write(cachefiles_cres_object(cres), + cachefiles_cres_file(cres), + start_pos, iter, + term_func, term_func_priv); } /* @@ -484,13 +493,12 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * /* * Prepare for a write to occur. */ -static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet) +int __cachefiles_prepare_write(struct cachefiles_object *object, + struct file *file, + loff_t *_start, size_t *_len, + bool no_space_allocated_yet) { - struct cachefiles_object *object = cachefiles_cres_object(cres); struct cachefiles_cache *cache = object->volume->cache; - struct file *file = cachefiles_cres_file(cres); loff_t start = *_start, pos; size_t len = *_len, down; int ret; @@ -577,7 +585,8 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres, } cachefiles_begin_secure(cache, &saved_cred); - ret = __cachefiles_prepare_write(cres, _start, _len, i_size, + ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres), + _start, _len, no_space_allocated_yet); cachefiles_end_secure(cache, saved_cred); return ret; From patchwork Fri Apr 15 12:35:55 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814856 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9E063C433EF for ; Fri, 15 Apr 2022 12:36:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1347018AbiDOMiz (ORCPT ); Fri, 15 Apr 2022 08:38:55 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39350 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1349967AbiDOMix (ORCPT ); Fri, 15 Apr 2022 08:38:53 -0400 Received: from out30-42.freemail.mail.aliyun.com (out30-42.freemail.mail.aliyun.com [115.124.30.42]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CD6BF2625; Fri, 15 Apr 2022 05:36:22 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R101e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04423;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7DLSy_1650026178; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7DLSy_1650026178) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:19 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 02/21] cachefiles: notify user daemon when looking up cookie Date: Fri, 15 Apr 2022 20:35:55 +0800 Message-Id: <20220415123614.54024-3-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Fscache/cachefiles used to serve as a local cache for a remote networking fs. This patch, along with the following patches, introduces a new on-demand read mode for cachefiles, which can boost the scenario where on-demand read semantics is needed, e.g. container image distribution. The essential difference between these two modes is that, in original mode, when a cache miss occurs, the netfs will fetch the data from the remote server and then write it to the cache file. With on-demand read mode, however, fetching the data and writing it to the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon needs to give the hint on it. Signed-off-by: Jeffle Xu --- fs/cachefiles/Kconfig | 11 + fs/cachefiles/Makefile | 1 + fs/cachefiles/daemon.c | 79 +++++-- fs/cachefiles/internal.h | 47 ++++ fs/cachefiles/namei.c | 16 +- fs/cachefiles/ondemand.c | 371 ++++++++++++++++++++++++++++++ include/linux/fscache.h | 1 + include/trace/events/cachefiles.h | 2 + include/uapi/linux/cachefiles.h | 50 ++++ 9 files changed, 563 insertions(+), 15 deletions(-) create mode 100644 fs/cachefiles/ondemand.c create mode 100644 include/uapi/linux/cachefiles.h diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 719faeeda168..67371cb1eb08 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -26,3 +26,14 @@ config CACHEFILES_ERROR_INJECTION help This permits error injection to be enabled in cachefiles whilst a cache is in service. + +config CACHEFILES_ONDEMAND + bool "Support for on-demand read" + depends on CACHEFILES + default n + help + This permits on-demand read mode of cachefiles. In this mode, when + cache miss, the cachefiles backend instead of netfs, is responsible + for fetching data, e.g. through user daemon. + + If unsure, say N. diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 16d811f1a2fa..c37a7a9af10b 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -16,5 +16,6 @@ cachefiles-y := \ xattr.o cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o +cachefiles-$(CONFIG_CACHEFILES_ONDEMAND) += ondemand.o obj-$(CONFIG_CACHEFILES) := cachefiles.o diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 7ac04ee2c0a0..69ca22aa6abf 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -75,6 +75,9 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = { { "inuse", cachefiles_daemon_inuse }, { "secctx", cachefiles_daemon_secctx }, { "tag", cachefiles_daemon_tag }, +#ifdef CONFIG_CACHEFILES_ONDEMAND + { "copen", cachefiles_ondemand_copen }, +#endif { "", NULL } }; @@ -108,6 +111,10 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) INIT_LIST_HEAD(&cache->volumes); INIT_LIST_HEAD(&cache->object_list); spin_lock_init(&cache->object_list_lock); +#ifdef CONFIG_CACHEFILES_ONDEMAND + xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC); + xa_init_flags(&cache->ondemand_ids, XA_FLAGS_ALLOC1); +#endif /* set default caching limits * - limit at 1% free space and/or free files @@ -126,6 +133,30 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_CACHEFILES_ONDEMAND +static void cachefiles_flush_reqs(struct cachefiles_cache *cache) +{ + struct xarray *xa = &cache->reqs; + struct cachefiles_req *req; + unsigned long index; + + /* + * 1) Cache has been marked as dead state, and then 2) flush all + * pending requests in @reqs xarray. The barrier inside set_bit() + * will ensure that above two ops won't be reordered. + */ + xa_lock(xa); + xa_for_each(xa, index, req) { + req->error = -EIO; + complete(&req->done); + } + xa_unlock(xa); + + xa_destroy(&cache->reqs); + xa_destroy(&cache->ondemand_ids); +} +#endif + /* * Release a cache. */ @@ -139,6 +170,9 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) set_bit(CACHEFILES_DEAD, &cache->flags); +#ifdef CONFIG_CACHEFILES_ONDEMAND + cachefiles_flush_reqs(cache); +#endif cachefiles_daemon_unbind(cache); /* clean up the control file interface */ @@ -152,23 +186,14 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) return 0; } -/* - * Read the cache state. - */ -static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, - size_t buflen, loff_t *pos) +static ssize_t cachefiles_do_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) { - struct cachefiles_cache *cache = file->private_data; unsigned long long b_released; unsigned f_released; char buffer[256]; int n; - //_enter(",,%zu,", buflen); - - if (!test_bit(CACHEFILES_READY, &cache->flags)) - return 0; - /* check how much space the cache has */ cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); @@ -206,6 +231,26 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, return n; } +/* + * Read the cache state. + */ +static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, + size_t buflen, loff_t *pos) +{ + struct cachefiles_cache *cache = file->private_data; + + //_enter(",,%zu,", buflen); + + if (!test_bit(CACHEFILES_READY, &cache->flags)) + return 0; + + if (IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) && + test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return cachefiles_ondemand_daemon_read(cache, _buffer, buflen); + else + return cachefiles_do_daemon_read(cache, _buffer, buflen); +} + /* * Take a command from cachefilesd, parse it and act on it. */ @@ -297,8 +342,16 @@ static __poll_t cachefiles_daemon_poll(struct file *file, poll_wait(file, &cache->daemon_pollwq, poll); mask = 0; - if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) - mask |= EPOLLIN; + if (IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) && + test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) { +#ifdef CONFIG_CACHEFILES_ONDEMAND + if (!xa_empty(&cache->reqs)) + mask |= EPOLLIN; +#endif + } else { + if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) + mask |= EPOLLIN; + } if (test_bit(CACHEFILES_CULLING, &cache->flags)) mask |= EPOLLOUT; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index e80673d0ab97..8ebe238af20b 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -15,6 +15,8 @@ #include #include #include +#include +#include #define CACHEFILES_DIO_BLOCK_SIZE 4096 @@ -58,8 +60,13 @@ struct cachefiles_object { enum cachefiles_content content_info:8; /* Info about content presence */ unsigned long flags; #define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ +#ifdef CONFIG_CACHEFILES_ONDEMAND + int ondemand_id; +#endif }; +#define CACHEFILES_ONDEMAND_ID_CLOSED -1 + /* * Cache files cache definition */ @@ -98,11 +105,26 @@ struct cachefiles_cache { #define CACHEFILES_DEAD 1 /* T if cache dead */ #define CACHEFILES_CULLING 2 /* T if cull engaged */ #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ +#define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ +#ifdef CONFIG_CACHEFILES_ONDEMAND + struct xarray reqs; /* xarray of pending on-demand requests */ + struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ + u32 ondemand_id_next; +#endif +}; + +struct cachefiles_req { + struct cachefiles_object *object; + struct completion done; + int error; + struct cachefiles_msg msg; }; +#define CACHEFILES_REQ_NEW XA_MARK_1 + #include static inline @@ -250,6 +272,31 @@ extern struct file *cachefiles_create_tmpfile(struct cachefiles_object *object); extern bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, struct cachefiles_object *object); +/* + * ondemand.c + */ +#ifdef CONFIG_CACHEFILES_ONDEMAND +extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen); + +extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache, + char *args); + +extern int cachefiles_ondemand_init_object(struct cachefiles_object *object); + +#else +static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) +{ + return -EOPNOTSUPP; +} + +static inline int cachefiles_ondemand_init_object(struct cachefiles_object *object) +{ + return 0; +} +#endif + /* * security.c */ diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ca9f3e4ec4b3..facf2ebe464b 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -452,10 +452,9 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; struct file *file; struct path path; - uint64_t ni_size = object->cookie->object_size; + uint64_t ni_size; long ret; - ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); cachefiles_begin_secure(cache, &saved_cred); @@ -481,6 +480,15 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) goto out_dput; } + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) { + file = ERR_PTR(ret); + goto out_unuse; + } + + ni_size = object->cookie->object_size; + ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); + if (ni_size > 0) { trace_cachefiles_trunc(object, d_backing_inode(path.dentry), 0, ni_size, cachefiles_trunc_expand_tmpfile); @@ -586,6 +594,10 @@ static bool cachefiles_open_file(struct cachefiles_object *object, } _debug("file -> %pd positive", dentry); + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) + goto error_fput; + ret = cachefiles_check_auxdata(object, file); if (ret < 0) goto check_failed; diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c new file mode 100644 index 000000000000..890cd3ecc2f0 --- /dev/null +++ b/fs/cachefiles/ondemand.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include +#include +#include +#include "internal.h" + +static int cachefiles_ondemand_fd_release(struct inode *inode, + struct file *file) +{ + struct cachefiles_object *object = file->private_data; + struct cachefiles_cache *cache = object->volume->cache; + int object_id = object->ondemand_id; + + object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + xa_erase(&cache->ondemand_ids, object_id); + cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); + return 0; +} + +static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, + struct iov_iter *iter) +{ + struct cachefiles_object *object = kiocb->ki_filp->private_data; + struct cachefiles_cache *cache = object->volume->cache; + struct file *file = object->file; + size_t len = iter->count; + loff_t pos = kiocb->ki_pos; + const struct cred *saved_cred; + int ret; + + if (!file) + return -ENOBUFS; + + cachefiles_begin_secure(cache, &saved_cred); + ret = __cachefiles_prepare_write(object, file, &pos, &len, true); + cachefiles_end_secure(cache, saved_cred); + if (ret < 0) + return ret; + + ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); + if (!ret) + ret = len; + + return ret; +} + +static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos, + int whence) +{ + struct cachefiles_object *object = filp->private_data; + struct file *file = object->file; + + if (!file) + return -ENOBUFS; + + return vfs_llseek(file, pos, whence); +} + +static const struct file_operations cachefiles_ondemand_fd_fops = { + .owner = THIS_MODULE, + .release = cachefiles_ondemand_fd_release, + .write_iter = cachefiles_ondemand_fd_write_iter, + .llseek = cachefiles_ondemand_fd_llseek, +}; + +/* + * OPEN request Completion (copen) + * - command: "copen ," + * represents the object size if >=0, error code if negative + */ +int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) +{ + struct cachefiles_req *req; + struct fscache_cookie *cookie; + char *pid, *psize; + unsigned long id; + long size; + int ret; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return -EOPNOTSUPP; + + if (!*args) { + pr_err("Empty id specified\n"); + return -EINVAL; + } + + pid = args; + psize = strchr(args, ','); + if (!psize) { + pr_err("Cache size is not specified\n"); + return -EINVAL; + } + + *psize = 0; + psize++; + + ret = kstrtoul(pid, 0, &id); + if (ret) + return ret; + + req = xa_erase(&cache->reqs, id); + if (!req) + return -EINVAL; + + /* fail OPEN request if copen format is invalid */ + ret = kstrtol(psize, 0, &size); + if (ret) { + req->error = ret; + goto out; + } + + /* fail OPEN request if daemon reports an error */ + if (size < 0) { + if (!IS_ERR_VALUE(size)) + size = -EINVAL; + req->error = size; + goto out; + } + + cookie = req->object->cookie; + cookie->object_size = size; + if (size) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + else + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + +out: + complete(&req->done); + return ret; +} + +static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) +{ + struct cachefiles_object *object; + struct cachefiles_cache *cache; + struct cachefiles_open *load; + struct file *file; + u32 object_id; + int ret, fd; + + object = cachefiles_grab_object(req->object, + cachefiles_obj_get_ondemand_fd); + cache = object->volume->cache; + + ret = xa_alloc_cyclic(&cache->ondemand_ids, &object_id, NULL, + XA_LIMIT(1, INT_MAX), + &cache->ondemand_id_next, GFP_KERNEL); + if (ret < 0) + goto err; + + fd = get_unused_fd_flags(O_WRONLY); + if (fd < 0) { + ret = fd; + goto err_free_id; + } + + file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops, + object, O_WRONLY); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err_put_fd; + } + + file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; + fd_install(fd, file); + + load = (void *)req->msg.data; + load->fd = fd; + req->msg.object_id = object_id; + object->ondemand_id = object_id; + return 0; + +err_put_fd: + put_unused_fd(fd); +err_free_id: + xa_erase(&cache->ondemand_ids, object_id); +err: + cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); + return ret; +} + +ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, + char __user *_buffer, size_t buflen) +{ + struct cachefiles_req *req; + struct cachefiles_msg *msg; + unsigned long id = 0; + size_t n; + int ret = 0; + XA_STATE(xas, &cache->reqs, 0); + + /* + * Search for a request that has not ever been processed, to prevent + * requests from being processed repeatedly. + */ + xa_lock(&cache->reqs); + req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + if (!req) { + xa_unlock(&cache->reqs); + return 0; + } + + msg = &req->msg; + n = msg->len; + + if (n > buflen) { + xa_unlock(&cache->reqs); + return -EMSGSIZE; + } + + xas_clear_mark(&xas, CACHEFILES_REQ_NEW); + xa_unlock(&cache->reqs); + + id = xas.xa_index; + msg->msg_id = id; + + if (msg->opcode == CACHEFILES_OP_OPEN) { + ret = cachefiles_ondemand_get_fd(req); + if (ret) + goto error; + } + + if (copy_to_user(_buffer, msg, n) != 0) { + ret = -EFAULT; + goto err_put_fd; + } + + return n; + +err_put_fd: + if (msg->opcode == CACHEFILES_OP_OPEN) + close_fd(((struct cachefiles_open *)msg->data)->fd); +error: + xa_erase(&cache->reqs, id); + req->error = ret; + complete(&req->done); + return ret; +} + +typedef int (*init_req_fn)(struct cachefiles_req *req, void *private); + +static int cachefiles_ondemand_send_req(struct cachefiles_object *object, + enum cachefiles_opcode opcode, + size_t data_len, + init_req_fn init_req, + void *private) +{ + struct cachefiles_cache *cache = object->volume->cache; + struct cachefiles_req *req; + XA_STATE(xas, &cache->reqs, 0); + int ret; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return 0; + + if (test_bit(CACHEFILES_DEAD, &cache->flags)) + return -EIO; + + req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->object = object; + init_completion(&req->done); + req->msg.opcode = opcode; + req->msg.len = sizeof(struct cachefiles_msg) + data_len; + + ret = init_req(req, private); + if (ret) + goto out; + + do { + /* + * Stop enqueuing the request when daemon is dying. So we need + * to 1) check cache state, and 2) enqueue request if cache is + * alive. + * + * These two ops need to be atomic as a whole. Otherwise request + * may be enqueued after xarray has been flushed, in which case + * the orphan request will never be completed and thus netfs + * will hang there forever. + */ + xas_lock(&xas); + + /* recheck dead state with lock held */ + if (test_bit(CACHEFILES_DEAD, &cache->flags)) { + xas_unlock(&xas); + ret = -EIO; + goto out; + } + + xas.xa_index = 0; + xas_find_marked(&xas, UINT_MAX, XA_FREE_MARK); + if (xas.xa_node == XAS_RESTART) + xas_set_err(&xas, -EBUSY); + xas_store(&xas, req); + xas_clear_mark(&xas, XA_FREE_MARK); + xas_set_mark(&xas, CACHEFILES_REQ_NEW); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + ret = xas_error(&xas); + if (ret) + goto out; + + wake_up_all(&cache->daemon_pollwq); + wait_for_completion(&req->done); + ret = req->error; +out: + kfree(req); + return ret; +} + +static int cachefiles_ondemand_init_open_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + struct fscache_cookie *cookie = object->cookie; + struct fscache_volume *volume = object->volume->vcookie; + struct cachefiles_open *load = (void *)req->msg.data; + size_t volume_key_size, cookie_key_size; + void *volume_key, *cookie_key; + + /* + * Volume key is a NUL-terminated string. key[0] stores strlen() of the + * string, followed by the content of the string (excluding '\0'). + */ + volume_key_size = volume->key[0] + 1; + volume_key = volume->key + 1; + + /* Cookie key is binary data, which is netfs specific. */ + cookie_key_size = cookie->key_len; + cookie_key = fscache_get_key(cookie); + + if (!(object->cookie->advice & FSCACHE_ADV_WANT_CACHE_SIZE)) { + pr_err("WANT_CACHE_SIZE is needed for on-demand mode\n"); + return -EINVAL; + } + + load->volume_key_size = volume_key_size; + load->cookie_key_size = cookie_key_size; + memcpy(load->data, volume_key, volume_key_size); + memcpy(load->data + volume_key_size, cookie_key, cookie_key_size); + + return 0; +} + +int cachefiles_ondemand_init_object(struct cachefiles_object *object) +{ + struct fscache_cookie *cookie = object->cookie; + struct fscache_volume *volume = object->volume->vcookie; + size_t volume_key_size, cookie_key_size, data_len; + + /* + * Cachefiles will firstly check cache file under the root cache + * directory. If coherency check failed, it will fallback to creating a + * new tmpfile as the cache file. Reuse the previously allocated object + * ID if any. + */ + if (object->ondemand_id > 0) + return 0; + + volume_key_size = volume->key[0] + 1; + cookie_key_size = cookie->key_len; + data_len = sizeof(struct cachefiles_open) + + volume_key_size + cookie_key_size; + + return cachefiles_ondemand_send_req(object, CACHEFILES_OP_OPEN, + data_len, cachefiles_ondemand_init_open_req, NULL); +} diff --git a/include/linux/fscache.h b/include/linux/fscache.h index e25539072463..72585c9729a2 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,7 @@ struct fscache_cookie; #define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 311c14a20e70..93df9391bd7f 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_lookup_failed, cachefiles_obj_see_withdraw_cookie, cachefiles_obj_see_withdrawal, + cachefiles_obj_get_ondemand_fd, + cachefiles_obj_put_ondemand_fd, }; enum fscache_why_object_killed { diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h new file mode 100644 index 000000000000..521f2fe4fe9c --- /dev/null +++ b/include/uapi/linux/cachefiles.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_CACHEFILES_H +#define _LINUX_CACHEFILES_H + +#include + +/* + * Fscache ensures that the maximum length of cookie key is 255. The volume key + * is controlled by netfs, and generally no bigger than 255. + */ +#define CACHEFILES_MSG_MAX_SIZE 1024 + +enum cachefiles_opcode { + CACHEFILES_OP_OPEN, +}; + +/* + * Message Header + * + * @msg_id a unique ID identifying this message + * @opcode message type, CACHEFILE_OP_* + * @len message length, including message header and following data + * @object_id a unique ID identifying a cache file + * @data message type specific payload + */ +struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; +}; + +/* + * @data contains the volume_key followed directly by the cookie_key. volume_key + * is a NUL-terminated string; @volume_key_size indicates the size of the volume + * key in bytes. cookie_key is binary data, which is netfs specific; + * @cookie_key_size indicates the size of the cookie key in bytes. + * + * @fd identifies an anon_fd referring to the cache file. + */ +struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; +}; + +#endif From patchwork Fri Apr 15 12:35:56 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814859 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 60914C4332F for ; Fri, 15 Apr 2022 12:36:37 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353595AbiDOMjB (ORCPT ); Fri, 15 Apr 2022 08:39:01 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39548 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S245219AbiDOMiz (ORCPT ); Fri, 15 Apr 2022 08:38:55 -0400 Received: from out30-44.freemail.mail.aliyun.com (out30-44.freemail.mail.aliyun.com [115.124.30.44]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 0FF4031DE6; Fri, 15 Apr 2022 05:36:24 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R121e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04395;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7VPPx_1650026179; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7VPPx_1650026179) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:20 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 03/21] cachefiles: unbind cachefiles gracefully in on-demand mode Date: Fri, 15 Apr 2022 20:35:56 +0800 Message-Id: <20220415123614.54024-4-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Add a refcount to avoid the deadlock in on-demand read mode. The on-demand read mode will pin the corresponding cachefiles object for each anonymous fd. The cachefiles object is unpinned when the anonymous fd gets closed. When the user daemon exits and the fd of "/dev/cachefiles" device node gets closed, it will wait for all cahcefiles objects gets withdrawn. Then if there's any anonymous fd getting closed after the fd of the device node, the user daemon will hang forever, waiting for all objects getting withdrawn. To fix this, add a refcount indicating if there's any object pinned by anonymous fds. The cachefiles cache gets unbound and withdrawn when the refcount decreased to 0. It won't change the behaviour of the original mode, in which case the cachefiles cache gets unbound and withdrawn as long as the fd of the device node gets closed. Besides, kref_get() is adequate whilst kref_get_unless_zero() is not needed here, since no more anonymous fd will be created when the .release() callback of the device node fd has already been called. Signed-off-by: Jeffle Xu --- fs/cachefiles/daemon.c | 24 +++++++++++++++++++++--- fs/cachefiles/internal.h | 3 +++ fs/cachefiles/ondemand.c | 3 +++ 3 files changed, 27 insertions(+), 3 deletions(-) diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 69ca22aa6abf..2e946e4eb65a 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -111,6 +111,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) INIT_LIST_HEAD(&cache->volumes); INIT_LIST_HEAD(&cache->object_list); spin_lock_init(&cache->object_list_lock); + kref_init(&cache->unbind_pincount); #ifdef CONFIG_CACHEFILES_ONDEMAND xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC); xa_init_flags(&cache->ondemand_ids, XA_FLAGS_ALLOC1); @@ -157,6 +158,25 @@ static void cachefiles_flush_reqs(struct cachefiles_cache *cache) } #endif +static void cachefiles_release_cache(struct kref *kref) +{ + struct cachefiles_cache *cache; + + cache = container_of(kref, struct cachefiles_cache, unbind_pincount); + cachefiles_daemon_unbind(cache); + kfree(cache); +} + +void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache) +{ + kref_put(&cache->unbind_pincount, cachefiles_release_cache); +} + +void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache) +{ + kref_get(&cache->unbind_pincount); +} + /* * Release a cache. */ @@ -173,14 +193,12 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) #ifdef CONFIG_CACHEFILES_ONDEMAND cachefiles_flush_reqs(cache); #endif - cachefiles_daemon_unbind(cache); - /* clean up the control file interface */ cache->cachefilesd = NULL; file->private_data = NULL; cachefiles_open = 0; - kfree(cache); + cachefiles_put_unbind_pincount(cache); _leave(""); return 0; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 8ebe238af20b..9b83d8c82709 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -109,6 +109,7 @@ struct cachefiles_cache { char *rootdirname; /* name of cache root directory */ char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ + struct kref unbind_pincount;/* refcount to do daemon unbind */ #ifdef CONFIG_CACHEFILES_ONDEMAND struct xarray reqs; /* xarray of pending on-demand requests */ struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ @@ -167,6 +168,8 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache, * daemon.c */ extern const struct file_operations cachefiles_daemon_fops; +extern void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache); +extern void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache); /* * error_inject.c diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 890cd3ecc2f0..eec883640efa 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -14,6 +14,7 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; xa_erase(&cache->ondemand_ids, object_id); cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); + cachefiles_put_unbind_pincount(cache); return 0; } @@ -169,6 +170,8 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) load->fd = fd; req->msg.object_id = object_id; object->ondemand_id = object_id; + + cachefiles_get_unbind_pincount(cache); return 0; err_put_fd: From patchwork Fri Apr 15 12:35:57 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814860 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id DB0FBC433EF for ; Fri, 15 Apr 2022 12:37:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353700AbiDOMj2 (ORCPT ); Fri, 15 Apr 2022 08:39:28 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39610 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353569AbiDOMi7 (ORCPT ); Fri, 15 Apr 2022 08:38:59 -0400 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C7D4253B75; Fri, 15 Apr 2022 05:36:26 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R681e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04407;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7VPQE_1650026181; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7VPQE_1650026181) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:22 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 04/21] cachefiles: notify user daemon when withdrawing cookie Date: Fri, 15 Apr 2022 20:35:57 +0800 Message-Id: <20220415123614.54024-5-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Notify the user daemon that cookie is going to be withdrawn, providing a hint that the associated anonymous fd can be closed. Be noted that this is only a hint. The user daemon may close the associated anonymous fd when receiving the CLOSE request, then it will receive another anonymous fd when the cookie gets looked up. Or it may ignore the CLOSE request, and keep writing data through the anonymous fd. However the next time the cookie gets looked up, the user daemon will still receive another new anonymous fd. Signed-off-by: Jeffle Xu Acked-by: David Howells --- fs/cachefiles/interface.c | 2 ++ fs/cachefiles/internal.h | 5 +++++ fs/cachefiles/ondemand.c | 38 +++++++++++++++++++++++++++++++++ include/uapi/linux/cachefiles.h | 1 + 4 files changed, 46 insertions(+) diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index ae93cee9d25d..a69073a1d3f0 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -362,6 +362,8 @@ static void cachefiles_withdraw_cookie(struct fscache_cookie *cookie) spin_unlock(&cache->object_list_lock); } + cachefiles_ondemand_clean_object(object); + if (object->file) { cachefiles_begin_secure(cache, &saved_cred); cachefiles_clean_up_object(object, cache); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 9b83d8c82709..15332eae43c0 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -286,6 +286,7 @@ extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args); extern int cachefiles_ondemand_init_object(struct cachefiles_object *object); +extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object); #else static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, @@ -298,6 +299,10 @@ static inline int cachefiles_ondemand_init_object(struct cachefiles_object *obje { return 0; } + +static inline void cachefiles_ondemand_clean_object(struct cachefiles_object *object) +{ +} #endif /* diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index eec883640efa..7ce383536f27 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -229,6 +229,12 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, goto err_put_fd; } + /* CLOSE request has no reply */ + if (msg->opcode == CACHEFILES_OP_CLOSE) { + xa_erase(&cache->reqs, id); + complete(&req->done); + } + return n; err_put_fd: @@ -293,6 +299,13 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, goto out; } + if (opcode != CACHEFILES_OP_OPEN && object->ondemand_id <= 0) { + WARN_ON_ONCE(object->ondemand_id == 0); + xas_unlock(&xas); + ret = -EIO; + goto out; + } + xas.xa_index = 0; xas_find_marked(&xas, UINT_MAX, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) @@ -349,6 +362,25 @@ static int cachefiles_ondemand_init_open_req(struct cachefiles_req *req, return 0; } +static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + int object_id = object->ondemand_id; + + /* + * It's possiblie that object id is still 0 if the cookie looking up + * phase failed before OPEN request has ever been sent. Also avoid + * sending CLOSE request for CACHEFILES_ONDEMAND_ID_CLOSED, which means + * anon_fd has already been closed. + */ + if (object_id <= 0) + return -ENOENT; + + req->msg.object_id = object_id; + return 0; +} + int cachefiles_ondemand_init_object(struct cachefiles_object *object) { struct fscache_cookie *cookie = object->cookie; @@ -372,3 +404,9 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object) return cachefiles_ondemand_send_req(object, CACHEFILES_OP_OPEN, data_len, cachefiles_ondemand_init_open_req, NULL); } + +void cachefiles_ondemand_clean_object(struct cachefiles_object *object) +{ + cachefiles_ondemand_send_req(object, CACHEFILES_OP_CLOSE, 0, + cachefiles_ondemand_init_close_req, NULL); +} diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 521f2fe4fe9c..37a0071037c8 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -12,6 +12,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, + CACHEFILES_OP_CLOSE, }; /* From patchwork Fri Apr 15 12:35:58 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814861 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 52CE3C433F5 for ; Fri, 15 Apr 2022 12:37:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353721AbiDOMja (ORCPT ); Fri, 15 Apr 2022 08:39:30 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39608 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353568AbiDOMi7 (ORCPT ); Fri, 15 Apr 2022 08:38:59 -0400 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 932061A06F; Fri, 15 Apr 2022 05:36:27 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R191e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04400;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7GjGJ_1650026182; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7GjGJ_1650026182) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:23 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 05/21] cachefiles: implement on-demand read Date: Fri, 15 Apr 2022 20:35:58 +0800 Message-Id: <20220415123614.54024-6-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Implement the data plane of on-demand read mode. The early implementation [1] place the entry to cachefiles_ondemand_read() in fscache_read(). However, fscache_read() can only detect if the requested file range is fully cache miss, whilst we need to notify the user daemon as long as there's a hole inside the requested file range. Thus the entry is now placed in cachefiles_prepare_read(). When working in on-demand read mode, once a hole detected, the read routine will send a READ request to the user daemon. The user daemon needs to fetch the data and write it to the cache file. After sending the READ request, the read routine will hang there, until the READ request is handled by the user daemon. Then it will retry to read from the same file range. If no progress encountered, the read routine will fail then. A new NETFS_SREQ_ONDEMAND flag is introduced to indicate that on-demand read should be done when a cache miss encountered. Signed-off-by: Jeffle Xu [1] https://lore.kernel.org/all/20220406075612.60298-6-jefflexu@linux.alibaba.com/ #v8 Acked-by: David Howells --- fs/cachefiles/internal.h | 9 ++++ fs/cachefiles/io.c | 26 ++++++++++- fs/cachefiles/ondemand.c | 77 +++++++++++++++++++++++++++++++++ include/linux/netfs.h | 2 + include/uapi/linux/cachefiles.h | 17 ++++++++ 5 files changed, 129 insertions(+), 2 deletions(-) diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 15332eae43c0..3025556ff7d4 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -288,6 +288,9 @@ extern int cachefiles_ondemand_copen(struct cachefiles_cache *cache, extern int cachefiles_ondemand_init_object(struct cachefiles_object *object); extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object); +extern int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len); + #else static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) @@ -303,6 +306,12 @@ static inline int cachefiles_ondemand_init_object(struct cachefiles_object *obje static inline void cachefiles_ondemand_clean_object(struct cachefiles_object *object) { } + +static inline int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len) +{ + return -EOPNOTSUPP; +} #endif /* diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 50a14e8f0aac..ccf77a969653 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -95,6 +95,7 @@ static int cachefiles_read(struct netfs_cache_resources *cres, file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); +retry: /* If the caller asked us to seek for data before doing the read, then * we should do that now. If we find a gap, we fill it with zeros. */ @@ -119,6 +120,16 @@ static int cachefiles_read(struct netfs_cache_resources *cres, if (read_hole == NETFS_READ_HOLE_FAIL) goto presubmission_error; + if (read_hole == NETFS_READ_HOLE_ONDEMAND) { + ret = cachefiles_ondemand_read(object, off, len); + if (ret) + goto presubmission_error; + + /* fail the read if no progress achieved */ + read_hole = NETFS_READ_HOLE_FAIL; + goto retry; + } + iov_iter_zero(len, iter); skipped = len; ret = 0; @@ -403,6 +414,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER; loff_t off, to; ino_t ino = file ? file_inode(file)->i_ino : 0; + int rc; _enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size); @@ -415,7 +427,8 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) { __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); why = cachefiles_trace_read_no_data; - goto out_no_object; + if (!test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) + goto out_no_object; } /* The object and the file may be being created in the background. */ @@ -432,7 +445,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * object = cachefiles_cres_object(cres); cache = object->volume->cache; cachefiles_begin_secure(cache, &saved_cred); - +retry: off = cachefiles_inject_read_error(); if (off == 0) off = vfs_llseek(file, subreq->start, SEEK_DATA); @@ -483,6 +496,15 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * download_and_store: __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + if (test_bit(NETFS_SREQ_ONDEMAND, &subreq->flags)) { + rc = cachefiles_ondemand_read(object, subreq->start, + subreq->len); + if (!rc) { + __clear_bit(NETFS_SREQ_ONDEMAND, &subreq->flags); + goto retry; + } + ret = NETFS_INVALID_READ; + } out: cachefiles_end_secure(cache, saved_cred); out_no_object: diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 7ce383536f27..10bdac26ce23 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -10,8 +10,25 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, struct cachefiles_object *object = file->private_data; struct cachefiles_cache *cache = object->volume->cache; int object_id = object->ondemand_id; + struct cachefiles_req *req; + XA_STATE(xas, &cache->reqs, 0); + xa_lock(&cache->reqs); object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + + /* + * Flush all pending READ requests since their completion depends on + * anon_fd. + */ + xas_for_each(&xas, req, ULONG_MAX) { + if (req->msg.opcode == CACHEFILES_OP_READ) { + req->error = -EIO; + complete(&req->done); + xas_store(&xas, NULL); + } + } + xa_unlock(&cache->reqs); + xa_erase(&cache->ondemand_ids, object_id); cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); cachefiles_put_unbind_pincount(cache); @@ -57,11 +74,35 @@ static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos, return vfs_llseek(file, pos, whence); } +static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct cachefiles_object *object = filp->private_data; + struct cachefiles_cache *cache = object->volume->cache; + struct cachefiles_req *req; + unsigned long id; + + if (ioctl != CACHEFILES_IOC_CREAD) + return -EINVAL; + + if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) + return -EOPNOTSUPP; + + id = arg; + req = xa_erase(&cache->reqs, id); + if (!req) + return -EINVAL; + + complete(&req->done); + return 0; +} + static const struct file_operations cachefiles_ondemand_fd_fops = { .owner = THIS_MODULE, .release = cachefiles_ondemand_fd_release, .write_iter = cachefiles_ondemand_fd_write_iter, .llseek = cachefiles_ondemand_fd_llseek, + .unlocked_ioctl = cachefiles_ondemand_fd_ioctl, }; /* @@ -381,6 +422,32 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, return 0; } +struct cachefiles_read_ctx { + loff_t off; + size_t len; +}; + +static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, + void *private) +{ + struct cachefiles_object *object = req->object; + struct cachefiles_read *load = (void *)req->msg.data; + struct cachefiles_read_ctx *read_ctx = private; + int object_id = object->ondemand_id; + + /* Stop enqueuing requests when daemon has closed anon_fd. */ + if (object_id <= 0) { + WARN_ON_ONCE(object_id == 0); + pr_info_once("READ: anonymous fd closed prematurely.\n"); + return -EIO; + } + + req->msg.object_id = object_id; + load->off = read_ctx->off; + load->len = read_ctx->len; + return 0; +} + int cachefiles_ondemand_init_object(struct cachefiles_object *object) { struct fscache_cookie *cookie = object->cookie; @@ -410,3 +477,13 @@ void cachefiles_ondemand_clean_object(struct cachefiles_object *object) cachefiles_ondemand_send_req(object, CACHEFILES_OP_CLOSE, 0, cachefiles_ondemand_init_close_req, NULL); } + +int cachefiles_ondemand_read(struct cachefiles_object *object, + loff_t pos, size_t len) +{ + struct cachefiles_read_ctx read_ctx = {pos, len}; + + return cachefiles_ondemand_send_req(object, CACHEFILES_OP_READ, + sizeof(struct cachefiles_read), + cachefiles_ondemand_init_read_req, &read_ctx); +} diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..02dbde48bb68 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -159,6 +159,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ }; enum netfs_io_origin { @@ -222,6 +223,7 @@ enum netfs_read_from_hole { NETFS_READ_HOLE_IGNORE, NETFS_READ_HOLE_CLEAR, NETFS_READ_HOLE_FAIL, + NETFS_READ_HOLE_ONDEMAND, }; /* diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 37a0071037c8..028fbf15e02b 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -3,6 +3,7 @@ #define _LINUX_CACHEFILES_H #include +#include /* * Fscache ensures that the maximum length of cookie key is 255. The volume key @@ -13,6 +14,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, CACHEFILES_OP_CLOSE, + CACHEFILES_OP_READ, }; /* @@ -48,4 +50,19 @@ struct cachefiles_open { __u8 data[]; }; +/* + * @off indicates the starting offset of the requested file range + * @len indicates the length of the requested file range + */ +struct cachefiles_read { + __u64 off; + __u64 len; +}; + +/* + * Reply for READ request (Completion for READ) + * arg for CACHEFILES_IOC_CREAD ioctl is the @id field of READ request. + */ +#define CACHEFILES_IOC_CREAD _IOW(0x98, 1, int) + #endif From patchwork Fri Apr 15 12:35:59 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814862 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0FA05C433FE for ; Fri, 15 Apr 2022 12:37:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353732AbiDOMjb (ORCPT ); Fri, 15 Apr 2022 08:39:31 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40258 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1350256AbiDOMjZ (ORCPT ); Fri, 15 Apr 2022 08:39:25 -0400 Received: from out199-7.us.a.mail.aliyun.com (out199-7.us.a.mail.aliyun.com [47.90.199.7]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 29A383389C; Fri, 15 Apr 2022 05:36:31 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R761e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04426;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Ug.q_1650026184; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Ug.q_1650026184) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:25 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 06/21] cachefiles: enable on-demand read mode Date: Fri, 15 Apr 2022 20:35:59 +0800 Message-Id: <20220415123614.54024-7-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Enable on-demand read mode by adding an optional parameter to the "bind" command. On-demand mode will be turned on when this parameter is "ondemand", i.e. "bind ondemand". Otherwise cachefiles will work in the original mode. Signed-off-by: Jeffle Xu --- fs/cachefiles/daemon.c | 13 ++++++++----- fs/cachefiles/io.c | 11 ----------- 2 files changed, 8 insertions(+), 16 deletions(-) diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 2e946e4eb65a..c8bde21ace6a 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -758,11 +758,6 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) cache->brun_percent >= 100) return -ERANGE; - if (*args) { - pr_err("'bind' command doesn't take an argument\n"); - return -EINVAL; - } - if (!cache->rootdirname) { pr_err("No cache directory specified\n"); return -EINVAL; @@ -774,6 +769,14 @@ static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) return -EBUSY; } + if (IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) && + !strcmp(args, "ondemand")) { + set_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags); + } else if (*args) { + pr_err("'bind' command doesn't take an argument\n"); + return -EINVAL; + } + /* Make sure we have copies of the tag string */ if (!cache->tag) { /* diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index ccf77a969653..000a28f46e59 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -95,7 +95,6 @@ static int cachefiles_read(struct netfs_cache_resources *cres, file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); -retry: /* If the caller asked us to seek for data before doing the read, then * we should do that now. If we find a gap, we fill it with zeros. */ @@ -120,16 +119,6 @@ static int cachefiles_read(struct netfs_cache_resources *cres, if (read_hole == NETFS_READ_HOLE_FAIL) goto presubmission_error; - if (read_hole == NETFS_READ_HOLE_ONDEMAND) { - ret = cachefiles_ondemand_read(object, off, len); - if (ret) - goto presubmission_error; - - /* fail the read if no progress achieved */ - read_hole = NETFS_READ_HOLE_FAIL; - goto retry; - } - iov_iter_zero(len, iter); skipped = len; ret = 0; From patchwork Fri Apr 15 12:36:00 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814869 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 32528C4332F for ; Fri, 15 Apr 2022 12:37:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353561AbiDOMjp (ORCPT ); Fri, 15 Apr 2022 08:39:45 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40252 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1347325AbiDOMjZ (ORCPT ); Fri, 15 Apr 2022 08:39:25 -0400 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9448C31DE6; Fri, 15 Apr 2022 05:36:31 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R311e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04357;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Cc1m_1650026186; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Cc1m_1650026186) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:27 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 07/21] cachefiles: add tracepoints for on-demand read mode Date: Fri, 15 Apr 2022 20:36:00 +0800 Message-Id: <20220415123614.54024-8-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Add tracepoints for on-demand read mode. Currently following tracepoints are added: OPEN request / COPEN reply CLOSE request READ request / CREAD reply write through anonymous fd release of anonymous fd Signed-off-by: Jeffle Xu Acked-by: David Howells --- fs/cachefiles/ondemand.c | 7 ++ include/trace/events/cachefiles.h | 174 ++++++++++++++++++++++++++++++ 2 files changed, 181 insertions(+) diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 10bdac26ce23..3be65b825037 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -30,6 +30,7 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, xa_unlock(&cache->reqs); xa_erase(&cache->ondemand_ids, object_id); + trace_cachefiles_ondemand_fd_release(object, object_id); cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); cachefiles_put_unbind_pincount(cache); return 0; @@ -55,6 +56,7 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, if (ret < 0) return ret; + trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len); ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); if (!ret) ret = len; @@ -93,6 +95,7 @@ static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl, if (!req) return -EINVAL; + trace_cachefiles_ondemand_cread(object, id); complete(&req->done); return 0; } @@ -166,6 +169,7 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); else set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + trace_cachefiles_ondemand_copen(req->object, id, size); out: complete(&req->done); @@ -213,6 +217,7 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) object->ondemand_id = object_id; cachefiles_get_unbind_pincount(cache); + trace_cachefiles_ondemand_open(object, &req->msg, load); return 0; err_put_fd: @@ -419,6 +424,7 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, return -ENOENT; req->msg.object_id = object_id; + trace_cachefiles_ondemand_close(object, &req->msg); return 0; } @@ -445,6 +451,7 @@ static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, req->msg.object_id = object_id; load->off = read_ctx->off; load->len = read_ctx->len; + trace_cachefiles_ondemand_read(object, &req->msg, load); return 0; } diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 93df9391bd7f..d8d4d73fe7b6 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -673,6 +673,180 @@ TRACE_EVENT(cachefiles_io_error, __entry->error) ); +TRACE_EVENT(cachefiles_ondemand_open, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_open *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(unsigned int, fd ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->fd = load->fd; + __entry->flags = load->flags; + ), + + TP_printk("o=%08x mid=%x oid=%x fd=%d f=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->fd, + __entry->flags) + ); + +TRACE_EVENT(cachefiles_ondemand_copen, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id, + long len), + + TP_ARGS(obj, msg_id, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(long, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + __entry->len = len; + ), + + TP_printk("o=%08x mid=%x l=%lx", + __entry->obj, + __entry->msg_id, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_close, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg), + + TP_ARGS(obj, msg), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + ), + + TP_printk("o=%08x mid=%x oid=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id) + ); + +TRACE_EVENT(cachefiles_ondemand_read, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_read *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->start = load->off; + __entry->len = load->len; + ), + + TP_printk("o=%08x mid=%x oid=%x s=%llx l=%zx", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_cread, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id), + + TP_ARGS(obj, msg_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + ), + + TP_printk("o=%08x mid=%x", + __entry->obj, + __entry->msg_id) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_write, + TP_PROTO(struct cachefiles_object *obj, struct inode *backer, + loff_t start, size_t len), + + TP_ARGS(obj, backer, start, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, backer ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->backer = backer->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("o=%08x iB=%x s=%llx l=%zx", + __entry->obj, + __entry->backer, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_release, + TP_PROTO(struct cachefiles_object *obj, int object_id), + + TP_ARGS(obj, object_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->object_id = object_id; + ), + + TP_printk("o=%08x oid=%x", + __entry->obj, + __entry->object_id) + ); + #endif /* _TRACE_CACHEFILES_H */ /* This part must be outside protection */ From patchwork Fri Apr 15 12:36:01 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814872 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 90256C4332F for ; Fri, 15 Apr 2022 12:37:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237642AbiDOMju (ORCPT ); Fri, 15 Apr 2022 08:39:50 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39650 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353591AbiDOMjB (ORCPT ); Fri, 15 Apr 2022 08:39:01 -0400 Received: from out30-42.freemail.mail.aliyun.com (out30-42.freemail.mail.aliyun.com [115.124.30.42]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A0C5D6832D; Fri, 15 Apr 2022 05:36:32 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R181e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04400;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Y1b1_1650026187; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Y1b1_1650026187) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:28 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 08/21] cachefiles: document on-demand read mode Date: Fri, 15 Apr 2022 20:36:01 +0800 Message-Id: <20220415123614.54024-9-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Document new user interface introduced by on-demand read mode. Signed-off-by: Jeffle Xu --- .../filesystems/caching/cachefiles.rst | 170 ++++++++++++++++++ 1 file changed, 170 insertions(+) diff --git a/Documentation/filesystems/caching/cachefiles.rst b/Documentation/filesystems/caching/cachefiles.rst index 8bf396b76359..c10a16957141 100644 --- a/Documentation/filesystems/caching/cachefiles.rst +++ b/Documentation/filesystems/caching/cachefiles.rst @@ -28,6 +28,7 @@ Cache on Already Mounted Filesystem (*) Debugging. + (*) On-demand Read. Overview @@ -482,3 +483,172 @@ the control file. For example:: echo $((1|4|8)) >/sys/module/cachefiles/parameters/debug will turn on all function entry debugging. + + +On-demand Read +============== + +When working in its original mode, cachefiles mainly serves as a local cache +for a remote networking fs - while in on-demand read mode, cachefiles can boost +the scenario where on-demand read semantics is needed, e.g. container image +distribution. + +The essential difference between these two modes is that, in original mode, +when a cache miss occurs, the netfs will fetch the data from the remote server +and then write it to the cache file. With on-demand read mode, however, +fetching the data and writing it into the cache is delegated to a user daemon. + +``CONFIG_CACHEFILES_ONDEMAND`` should be enabled to support on-demand read mode. + + +Protocol Communication +---------------------- + +The on-demand read mode relies on a simple protocol used for communication +between kernel and user daemon. The protocol can be modeled as:: + + kernel --[request]--> user daemon --[reply]--> kernel + +The cachefiles kernel module will send requests to the user daemon when needed. +The user daemon needs to poll on the devnode ('/dev/cachefiles') to check if +there's a pending request to be processed. A POLLIN event will be returned +when there's a pending request. + +The user daemon then reads the devnode to fetch a request and process it +accordingly. It is worth noting that each read only gets one request. When +finished processing the request, the user daemon needs to write the reply to +the devnode. + +Each request starts with a message header of the form:: + + struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; + }; + + where: + + * ``msg_id`` is a unique ID identifying this request among all pending + requests. + + * ``opcode`` indicates the type of this request. + + * ``object_id`` is a unique ID identifying the cache file operated on. + + * ``data`` indicates the payload of this request. + + * ``len`` indicates the whole length of this request, including the + header and following type-specific payload. + + +Turn on On-demand Mode +---------------------- + +An optional parameter is added to the "bind" command:: + + bind [ondemand] + +When the "bind" command takes without argument, it defaults to the original +mode. When the "bind" command is given the "ondemand" argument, i.e. +"bind ondemand", on-demand read mode will be enabled. + + +The OPEN Request +---------------- + +When the netfs opens a cache file for the first time, a request with the +CACHEFILES_OP_OPEN opcode, a.k.a an OPEN request will be sent to the user +daemon. The payload format is of the form:: + + struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; + }; + + where: + + * ``data`` contains the volume_key followed directly by the cookie_key. + The volume key is a NUL-terminated string; the cookie key is binary + data. + + * ``volume_key_size`` indicates the size of the volume key in bytes. + + * ``cookie_key_size`` indicates the size of the cookie key in bytes. + + * ``fd`` indicates an anonymous fd referring to the cache file, through + which the user daemon can perform write/llseek file operations on the + cache file. + + +The user daemon is able to distinguish the requested cache file with the given +(volume_key, cookie_key) pair. Each cache file has a unique object_id, while it +may have multiple anonymous fds. The user daemon may duplicate anonymous fds +from the initial anonymous fd indicated by the @fd field through dup(). Thus +each object_id can be mapped to multiple anonymous fds, while the usr daemon +itself needs to maintain the mapping. + +With the given anonymous fd, the user daemon can fetch data and write it to the +cache file in the background, even when kernel has not triggered a cache miss +yet. + +The user daemon should complete the READ request by issuing a "copen" (complete +open) command on the devnode:: + + copen , + + * ``msg_id`` must match the msg_id field of the previous OPEN request. + + * When >= 0, ``cache_size`` indicates the size of the cache file; + when < 0, ``cache_size`` indicates the error code ecountered by the + user daemon. + + +The CLOSE Request +----------------- + +When a cookie withdrawn, a CLOSE request (opcode CACHEFILES_OP_CLOSE) will be +sent to the user daemon. It will notify the user daemon to close all anonymous +fds associated with the given object_id. The CLOSE request has no extea +payload. + + +The READ Request +---------------- + +When on-demand read mode is turned on, and a cache miss encountered, the kernel +will send a READ request (opcode CACHEFILES_OP_READ) to the user daemon. This +will tell the user daemon to fetch data of the requested file range. The payload +is of the form:: + + struct cachefiles_read { + __u64 off; + __u64 len; + }; + + where: + + * ``off`` indicates the starting offset of the requested file range. + + * ``len`` indicates the length of the requested file range. + + +When receiving a READ request, the user daemon needs to fetch the data of the +requested file range, and then write it to the cache file identified by +object_id. + +To finish processing the READ request, the user daemon should reply with the +CACHEFILES_IOC_CREAD ioctl on one of the anonymous fds associated with the given +object_id in the READ request. The ioctl is of the form:: + + ioctl(fd, CACHEFILES_IOC_CREAD, msg_id); + + * ``fd`` is one of the anonymous fds associated with the given object_id + in the READ request. + + * ``msg_id`` must match the msg_id field of the previous READ request. From patchwork Fri Apr 15 12:36:02 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814870 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9A188C43217 for ; Fri, 15 Apr 2022 12:37:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353781AbiDOMjr (ORCPT ); Fri, 15 Apr 2022 08:39:47 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40260 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353536AbiDOMjZ (ORCPT ); Fri, 15 Apr 2022 08:39:25 -0400 Received: from out30-56.freemail.mail.aliyun.com (out30-56.freemail.mail.aliyun.com [115.124.30.56]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CC0B622B0F; Fri, 15 Apr 2022 05:36:34 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R791e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04407;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Cc2H_1650026189; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Cc2H_1650026189) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:30 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 09/21] erofs: make erofs_map_blocks() generally available Date: Fri, 15 Apr 2022 20:36:02 +0800 Message-Id: <20220415123614.54024-10-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org ... so that it can be used in the following introduced fscache mode. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/data.c | 4 ++-- fs/erofs/internal.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 780db1e5f4b7..bc22642358ec 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -110,8 +110,8 @@ static int erofs_map_blocks_flatmode(struct inode *inode, return 0; } -static int erofs_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, int flags) +int erofs_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, int flags) { struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 5298c4ee277d..fe9564e5091e 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -486,6 +486,8 @@ void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); +int erofs_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, int flags); /* inode.c */ static inline unsigned long erofs_inode_hash(erofs_nid_t nid) From patchwork Fri Apr 15 12:36:03 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814871 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6ABBFC433F5 for ; Fri, 15 Apr 2022 12:37:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353788AbiDOMjs (ORCPT ); Fri, 15 Apr 2022 08:39:48 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39610 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353654AbiDOMj0 (ORCPT ); Fri, 15 Apr 2022 08:39:26 -0400 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E77E8C4E25; Fri, 15 Apr 2022 05:36:35 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R121e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04357;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Ug0v_1650026191; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Ug0v_1650026191) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:32 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 10/21] erofs: add fscache mode check helper Date: Fri, 15 Apr 2022 20:36:03 +0800 Message-Id: <20220415123614.54024-11-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Until then erofs is exactly blockdev based filesystem. A new fscache-based mode is going to be introduced for erofs to support scenarios where on-demand read semantics is needed, e.g. container image distribution. In this case, erofs could be mounted from data blobs through fscache. Add a helper checking which mode erofs works in, and twist the code in prep for the following fscache mode. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/internal.h | 5 +++++ fs/erofs/super.c | 44 +++++++++++++++++++++++++++++--------------- 2 files changed, 34 insertions(+), 15 deletions(-) diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index fe9564e5091e..05a97533b1e9 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -161,6 +161,11 @@ struct erofs_sb_info { #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) #define test_opt(opt, option) ((opt)->mount_opt & EROFS_MOUNT_##option) +static inline bool erofs_is_fscache_mode(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !sb->s_bdev; +} + enum { EROFS_ZIP_CACHE_DISABLED, EROFS_ZIP_CACHE_READAHEAD, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 0c4b41130c2f..724d5ff0d78c 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -259,15 +259,19 @@ static int erofs_init_devices(struct super_block *sb, } dis = ptr + erofs_blkoff(pos); - bdev = blkdev_get_by_path(dif->path, - FMODE_READ | FMODE_EXCL, - sb->s_type); - if (IS_ERR(bdev)) { - err = PTR_ERR(bdev); - break; + if (!erofs_is_fscache_mode(sb)) { + bdev = blkdev_get_by_path(dif->path, + FMODE_READ | FMODE_EXCL, + sb->s_type); + if (IS_ERR(bdev)) { + err = PTR_ERR(bdev); + break; + } + dif->bdev = bdev; + dif->dax_dev = fs_dax_get_by_bdev(bdev, + &dif->dax_part_off); } - dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); + dif->blocks = le32_to_cpu(dis->blocks); dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); sbi->total_blocks += dif->blocks; @@ -586,21 +590,28 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_magic = EROFS_SUPER_MAGIC; - if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { - erofs_err(sb, "failed to set erofs blksize"); - return -EINVAL; - } - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; sbi->opt = ctx->opt; - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off); sbi->devs = ctx->devs; ctx->devs = NULL; + if (erofs_is_fscache_mode(sb)) { + sb->s_blocksize = EROFS_BLKSIZ; + sb->s_blocksize_bits = LOG_BLOCK_SIZE; + } else { + if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { + erofs_err(sb, "failed to set erofs blksize"); + return -EINVAL; + } + + sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dax_part_off); + } + err = erofs_read_superblock(sb); if (err) return err; @@ -857,7 +868,10 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + u64 id = 0; + + if (!erofs_is_fscache_mode(sb)) + id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; buf->f_bsize = EROFS_BLKSIZ; From patchwork Fri Apr 15 12:36:04 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814863 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id DCE5EC433F5 for ; Fri, 15 Apr 2022 12:37:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353686AbiDOMjc (ORCPT ); Fri, 15 Apr 2022 08:39:32 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40268 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353665AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-130.freemail.mail.aliyun.com (out30-130.freemail.mail.aliyun.com [115.124.30.130]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BCE13C6834; Fri, 15 Apr 2022 05:36:39 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R121e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e01424;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Y1bu_1650026192; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Y1bu_1650026192) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:33 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 11/21] erofs: register fscache volume Date: Fri, 15 Apr 2022 20:36:04 +0800 Message-Id: <20220415123614.54024-12-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org A new fscache based mode is going to be introduced for erofs, in which case on-demand read semantics is implemented through fscache. As the first step, register fscache volume for each erofs filesystem. That means, data blobs can not be shared among erofs filesystems. In the following iteration, we are going to introduce the domain semantics, in which case several erofs filesystems can belong to one domain, and data blobs can be shared among these erofs filesystems of one domain. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/Kconfig | 10 ++++++++++ fs/erofs/Makefile | 1 + fs/erofs/fscache.c | 37 +++++++++++++++++++++++++++++++++++++ fs/erofs/internal.h | 16 ++++++++++++++++ fs/erofs/super.c | 5 +++++ 5 files changed, 69 insertions(+) create mode 100644 fs/erofs/fscache.c diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index f57255ab88ed..85490370e0ca 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -98,3 +98,13 @@ config EROFS_FS_ZIP_LZMA systems will be readable without selecting this option. If unsure, say N. + +config EROFS_FS_ONDEMAND + bool "EROFS fscache-based on-demand read support" + depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y) + default n + help + This permits EROFS to use fscache-backed data blobs with on-demand + read support. + + If unsure, say N. diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile index 8a3317e38e5a..99bbc597a3e9 100644 --- a/fs/erofs/Makefile +++ b/fs/erofs/Makefile @@ -5,3 +5,4 @@ erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o +erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c new file mode 100644 index 000000000000..7a6d0239ebb1 --- /dev/null +++ b/fs/erofs/fscache.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022, Alibaba Cloud + */ +#include +#include "internal.h" + +int erofs_fscache_register_fs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct fscache_volume *volume; + char *name; + int ret = 0; + + name = kasprintf(GFP_KERNEL, "erofs,%s", sbi->opt.fsid); + if (!name) + return -ENOMEM; + + volume = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR_OR_NULL(volume)) { + erofs_err(sb, "failed to register volume for %s", name); + ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP; + volume = NULL; + } + + sbi->volume = volume; + kfree(name); + return ret; +} + +void erofs_fscache_unregister_fs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + + fscache_relinquish_volume(sbi->volume, NULL, false); + sbi->volume = NULL; +} diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 05a97533b1e9..e4f6a13f161f 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -74,6 +74,7 @@ struct erofs_mount_opts { unsigned int max_sync_decompress_pages; #endif unsigned int mount_opt; + char *fsid; }; struct erofs_dev_context { @@ -146,6 +147,9 @@ struct erofs_sb_info { /* sysfs support */ struct kobject s_kobj; /* /sys/fs/erofs/ */ struct completion s_kobj_unregister; + + /* fscache support */ + struct fscache_volume *volume; }; #define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info) @@ -618,6 +622,18 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb, } #endif /* !CONFIG_EROFS_FS_ZIP */ +/* fscache.c */ +#ifdef CONFIG_EROFS_FS_ONDEMAND +int erofs_fscache_register_fs(struct super_block *sb); +void erofs_fscache_unregister_fs(struct super_block *sb); +#else +static inline int erofs_fscache_register_fs(struct super_block *sb) +{ + return 0; +} +static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} +#endif + #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* __EROFS_INTERNAL_H */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 724d5ff0d78c..fd8daa447237 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -602,6 +602,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (erofs_is_fscache_mode(sb)) { sb->s_blocksize = EROFS_BLKSIZ; sb->s_blocksize_bits = LOG_BLOCK_SIZE; + + err = erofs_fscache_register_fs(sb); + if (err) + return err; } else { if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { erofs_err(sb, "failed to set erofs blksize"); @@ -768,6 +772,7 @@ static void erofs_kill_sb(struct super_block *sb) erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev); + erofs_fscache_unregister_fs(sb); kfree(sbi); sb->s_fs_info = NULL; } From patchwork Fri Apr 15 12:36:05 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814867 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 16977C433EF for ; Fri, 15 Apr 2022 12:37:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353777AbiDOMjm (ORCPT ); Fri, 15 Apr 2022 08:39:42 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39592 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353662AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-133.freemail.mail.aliyun.com (out30-133.freemail.mail.aliyun.com [115.124.30.133]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 0285DC3351; Fri, 15 Apr 2022 05:36:38 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R111e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04407;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7GjI2_1650026194; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7GjI2_1650026194) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:35 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 12/21] erofs: add fscache context helper functions Date: Fri, 15 Apr 2022 20:36:05 +0800 Message-Id: <20220415123614.54024-13-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Introduce a context structure for managing data blobs, and helper functions for initializing and cleaning up this context structure. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/fscache.c | 46 +++++++++++++++++++++++++++++++++++++++++++++ fs/erofs/internal.h | 19 +++++++++++++++++++ 2 files changed, 65 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 7a6d0239ebb1..67a3c4935245 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -5,6 +5,52 @@ #include #include "internal.h" +/* + * Create an fscache context for data blob. + * Return: 0 on success and allocated fscache context is assigned to @fscache, + * negative error number on failure. + */ +int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, char *name) +{ + struct fscache_volume *volume = EROFS_SB(sb)->volume; + struct erofs_fscache *ctx; + struct fscache_cookie *cookie; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + cookie = fscache_acquire_cookie(volume, FSCACHE_ADV_WANT_CACHE_SIZE, + name, strlen(name), NULL, 0, 0); + if (!cookie) { + erofs_err(sb, "failed to get cookie for %s", name); + kfree(name); + return -EINVAL; + } + + fscache_use_cookie(cookie, false); + ctx->cookie = cookie; + + *fscache = ctx; + return 0; +} + +void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) +{ + struct erofs_fscache *ctx = *fscache; + + if (!ctx) + return; + + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); + ctx->cookie = NULL; + + kfree(ctx); + *fscache = NULL; +} + int erofs_fscache_register_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index e4f6a13f161f..b1f19f058503 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -97,6 +97,10 @@ struct erofs_sb_lz4_info { u16 max_pclusterblks; }; +struct erofs_fscache { + struct fscache_cookie *cookie; +}; + struct erofs_sb_info { struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP @@ -626,12 +630,27 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb, #ifdef CONFIG_EROFS_FS_ONDEMAND int erofs_fscache_register_fs(struct super_block *sb); void erofs_fscache_unregister_fs(struct super_block *sb); + +int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, char *name); +void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache); #else static inline int erofs_fscache_register_fs(struct super_block *sb) { return 0; } static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} + +static inline int erofs_fscache_register_cookie(struct super_block *sb, + struct erofs_fscache **fscache, + char *name) +{ + return -EOPNOTSUPP; +} + +static inline void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) +{ +} #endif #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ From patchwork Fri Apr 15 12:36:06 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814864 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 87968C433EF for ; Fri, 15 Apr 2022 12:37:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353680AbiDOMje (ORCPT ); Fri, 15 Apr 2022 08:39:34 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40322 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353677AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-43.freemail.mail.aliyun.com (out30-43.freemail.mail.aliyun.com [115.124.30.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9693DC6B61; Fri, 15 Apr 2022 05:36:41 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R221e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04394;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7DLVW_1650026195; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7DLVW_1650026195) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:36 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 13/21] erofs: add anonymous inode caching metadata for data blobs Date: Fri, 15 Apr 2022 20:36:06 +0800 Message-Id: <20220415123614.54024-14-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Introduce one anonymous inode for data blobs so that erofs can cache metadata directly within such anonymous inode. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/fscache.c | 39 ++++++++++++++++++++++++++++++++++++--- fs/erofs/internal.h | 6 ++++-- 2 files changed, 40 insertions(+), 5 deletions(-) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 67a3c4935245..1c88614203d2 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -5,17 +5,22 @@ #include #include "internal.h" +static const struct address_space_operations erofs_fscache_meta_aops = { +}; + /* * Create an fscache context for data blob. * Return: 0 on success and allocated fscache context is assigned to @fscache, * negative error number on failure. */ int erofs_fscache_register_cookie(struct super_block *sb, - struct erofs_fscache **fscache, char *name) + struct erofs_fscache **fscache, + char *name, bool need_inode) { struct fscache_volume *volume = EROFS_SB(sb)->volume; struct erofs_fscache *ctx; struct fscache_cookie *cookie; + int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -25,15 +30,40 @@ int erofs_fscache_register_cookie(struct super_block *sb, name, strlen(name), NULL, 0, 0); if (!cookie) { erofs_err(sb, "failed to get cookie for %s", name); - kfree(name); - return -EINVAL; + ret = -EINVAL; + goto err; } fscache_use_cookie(cookie, false); ctx->cookie = cookie; + if (need_inode) { + struct inode *const inode = new_inode(sb); + + if (!inode) { + erofs_err(sb, "failed to get anon inode for %s", name); + ret = -ENOMEM; + goto err_cookie; + } + + set_nlink(inode, 1); + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &erofs_fscache_meta_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + + ctx->inode = inode; + } + *fscache = ctx; return 0; + +err_cookie: + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); + ctx->cookie = NULL; +err: + kfree(ctx); + return ret; } void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) @@ -47,6 +77,9 @@ void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache) fscache_relinquish_cookie(ctx->cookie, false); ctx->cookie = NULL; + iput(ctx->inode); + ctx->inode = NULL; + kfree(ctx); *fscache = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index b1f19f058503..5867cb63fd74 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -99,6 +99,7 @@ struct erofs_sb_lz4_info { struct erofs_fscache { struct fscache_cookie *cookie; + struct inode *inode; }; struct erofs_sb_info { @@ -632,7 +633,8 @@ int erofs_fscache_register_fs(struct super_block *sb); void erofs_fscache_unregister_fs(struct super_block *sb); int erofs_fscache_register_cookie(struct super_block *sb, - struct erofs_fscache **fscache, char *name); + struct erofs_fscache **fscache, + char *name, bool need_inode); void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache); #else static inline int erofs_fscache_register_fs(struct super_block *sb) @@ -643,7 +645,7 @@ static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} static inline int erofs_fscache_register_cookie(struct super_block *sb, struct erofs_fscache **fscache, - char *name) + char *name, bool need_inode) { return -EOPNOTSUPP; } From patchwork Fri Apr 15 12:36:07 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814866 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 49D51C433F5 for ; Fri, 15 Apr 2022 12:37:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353587AbiDOMjk (ORCPT ); Fri, 15 Apr 2022 08:39:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39650 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353689AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-43.freemail.mail.aliyun.com (out30-43.freemail.mail.aliyun.com [115.124.30.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 965DDC6EE1; Fri, 15 Apr 2022 05:36:42 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R611e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04394;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Ug1q_1650026197; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Ug1q_1650026197) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:38 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 14/21] erofs: add erofs_fscache_read_folios() helper Date: Fri, 15 Apr 2022 20:36:07 +0800 Message-Id: <20220415123614.54024-15-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Add erofs_fscache_read_folios() helper reading from fscache. It supports on-demand read semantics. That is, it will make the backend prepare for the data when cache miss. Once data ready, it will read from the cache. This helper can then be used to implement .readpage()/.readahead() of on-demand read semantics. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/fscache.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 1c88614203d2..066f68c062e2 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -5,6 +5,59 @@ #include #include "internal.h" +/* + * Read data from fscache and fill the read data into page cache described by + * @start/len, which shall be both aligned with PAGE_SIZE. @pstart describes + * the start physical address in the cache file. + */ +static int erofs_fscache_read_folios(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, + loff_t pstart) +{ + enum netfs_io_source source; + struct netfs_io_subrequest subreq; + struct netfs_io_request rreq; + struct netfs_cache_resources *cres = &rreq.cache_resources; + struct iov_iter iter; + size_t done = 0; + int ret; + + memset(&rreq, 0, sizeof(rreq)); + memset(&subreq, 0, sizeof(subreq)); + subreq.rreq = &rreq; + + ret = fscache_begin_read_operation(cres, cookie); + if (ret) + return ret; + + while (done < len) { + subreq.start = pstart + done; + subreq.len = len - done; + subreq.flags = 1 << NETFS_SREQ_ONDEMAND; + + source = cres->ops->prepare_read(&subreq, LLONG_MAX); + if (WARN_ON(subreq.len == 0)) + source = NETFS_INVALID_READ; + if (source != NETFS_READ_FROM_CACHE) { + ret = -EIO; + goto out; + } + + iov_iter_xarray(&iter, READ, &mapping->i_pages, + start + done, subreq.len); + ret = fscache_read(cres, subreq.start, &iter, + NETFS_READ_HOLE_FAIL, NULL, NULL); + if (ret) + goto out; + + done += subreq.len; + } +out: + fscache_end_operation(cres); + return ret; +} + static const struct address_space_operations erofs_fscache_meta_aops = { }; From patchwork Fri Apr 15 12:36:08 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814865 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1C97BC433EF for ; Fri, 15 Apr 2022 12:37:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353710AbiDOMjh (ORCPT ); Fri, 15 Apr 2022 08:39:37 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40332 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353690AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-54.freemail.mail.aliyun.com (out30-54.freemail.mail.aliyun.com [115.124.30.54]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9DE74C6EE9; Fri, 15 Apr 2022 05:36:43 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R281e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04357;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Cc3m_1650026199; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Cc3m_1650026199) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:40 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 15/21] erofs: register fscache context for primary data blob Date: Fri, 15 Apr 2022 20:36:08 +0800 Message-Id: <20220415123614.54024-16-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Registers fscache context for primary data blob. Also move the initialization of s_op and related fields forward, since anonymous inode will be allocated under the super block when registering the fscache context. Something worth mentioning about the cleanup routine. 1. The fscache context will instantiate anonymous inodes under the super block. Release these anonymous inodes when .put_super() is called, or we'll get "VFS: Busy inodes after unmount." warning. 2. The fscache context is initialized prior to the root inode. If .kill_sb() is called when mount failed, .put_super() won't be called when root inode has not been initialized yet. Thus .kill_sb() shall also contain the cleanup routine. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/internal.h | 1 + fs/erofs/super.c | 15 +++++++++++---- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 5867cb63fd74..386658416159 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -155,6 +155,7 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; + struct erofs_fscache *s_fscache; }; #define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index fd8daa447237..61dc900295f9 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -589,6 +589,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) int err; sb->s_magic = EROFS_SUPER_MAGIC; + sb->s_flags |= SB_RDONLY | SB_NOATIME; + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_op = &erofs_sops; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) @@ -606,6 +609,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) err = erofs_fscache_register_fs(sb); if (err) return err; + + err = erofs_fscache_register_cookie(sb, &sbi->s_fscache, + sbi->opt.fsid, true); + if (err) + return err; } else { if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { erofs_err(sb, "failed to set erofs blksize"); @@ -628,11 +636,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) clear_opt(&sbi->opt, DAX_ALWAYS); } } - sb->s_flags |= SB_RDONLY | SB_NOATIME; - sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_time_gran = 1; - sb->s_op = &erofs_sops; + sb->s_time_gran = 1; sb->s_xattr = erofs_xattr_handlers; if (test_opt(&sbi->opt, POSIX_ACL)) @@ -772,6 +777,7 @@ static void erofs_kill_sb(struct super_block *sb) erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev); + erofs_fscache_unregister_cookie(&sbi->s_fscache); erofs_fscache_unregister_fs(sb); kfree(sbi); sb->s_fs_info = NULL; @@ -790,6 +796,7 @@ static void erofs_put_super(struct super_block *sb) iput(sbi->managed_cache); sbi->managed_cache = NULL; #endif + erofs_fscache_unregister_cookie(&sbi->s_fscache); } static struct file_system_type erofs_fs_type = { From patchwork Fri Apr 15 12:36:09 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814868 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7687BC433F5 for ; Fri, 15 Apr 2022 12:37:18 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1351805AbiDOMjo (ORCPT ); Fri, 15 Apr 2022 08:39:44 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40348 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353695AbiDOMj1 (ORCPT ); Fri, 15 Apr 2022 08:39:27 -0400 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A59BFC6EFB; Fri, 15 Apr 2022 05:36:45 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R191e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e01424;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Cc42_1650026200; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Cc42_1650026200) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:41 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 16/21] erofs: register fscache context for extra data blobs Date: Fri, 15 Apr 2022 20:36:09 +0800 Message-Id: <20220415123614.54024-17-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Similar to the multi device mode, erofs could be mounted from one primary data blob (mandatory) and multiple extra data blobs (optional). Register fscache context for each extra data blob. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/data.c | 3 +++ fs/erofs/internal.h | 2 ++ fs/erofs/super.c | 8 +++++++- 3 files changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index bc22642358ec..14b64d960541 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -199,6 +199,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = sb->s_bdev; map->m_daxdev = EROFS_SB(sb)->dax_dev; map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; + map->m_fscache = EROFS_SB(sb)->s_fscache; if (map->m_deviceid) { down_read(&devs->rwsem); @@ -210,6 +211,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; up_read(&devs->rwsem); } else if (devs->extra_devices) { down_read(&devs->rwsem); @@ -227,6 +229,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; break; } } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 386658416159..fa488af8dfcf 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -49,6 +49,7 @@ typedef u32 erofs_blk_t; struct erofs_device_info { char *path; + struct erofs_fscache *fscache; struct block_device *bdev; struct dax_device *dax_dev; u64 dax_part_off; @@ -482,6 +483,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode, #endif /* !CONFIG_EROFS_FS_ZIP */ struct erofs_map_dev { + struct erofs_fscache *m_fscache; struct block_device *m_bdev; struct dax_device *m_daxdev; u64 m_dax_part_off; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 61dc900295f9..c6755bcae4a6 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -259,7 +259,12 @@ static int erofs_init_devices(struct super_block *sb, } dis = ptr + erofs_blkoff(pos); - if (!erofs_is_fscache_mode(sb)) { + if (erofs_is_fscache_mode(sb)) { + err = erofs_fscache_register_cookie(sb, &dif->fscache, + dif->path, false); + if (err) + break; + } else { bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, sb->s_type); @@ -710,6 +715,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) fs_put_dax(dif->dax_dev); if (dif->bdev) blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); + erofs_fscache_unregister_cookie(&dif->fscache); kfree(dif->path); kfree(dif); return 0; From patchwork Fri Apr 15 12:36:10 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814873 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id D2B8FC433F5 for ; Fri, 15 Apr 2022 12:37:26 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353800AbiDOMjv (ORCPT ); Fri, 15 Apr 2022 08:39:51 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40384 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345514AbiDOMj2 (ORCPT ); Fri, 15 Apr 2022 08:39:28 -0400 Received: from out30-43.freemail.mail.aliyun.com (out30-43.freemail.mail.aliyun.com [115.124.30.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AE7F9C8BCE; Fri, 15 Apr 2022 05:36:48 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R601e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04426;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Ug2g_1650026202; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Ug2g_1650026202) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:43 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 17/21] erofs: implement fscache-based metadata read Date: Fri, 15 Apr 2022 20:36:10 +0800 Message-Id: <20220415123614.54024-18-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Implement the data plane of reading metadata from primary data blob over fscache. Signed-off-by: Jeffle Xu --- fs/erofs/data.c | 19 +++++++++++++++---- fs/erofs/fscache.c | 27 +++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 14b64d960541..bb9c1fd48c19 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -6,6 +6,7 @@ */ #include "internal.h" #include +#include #include #include @@ -35,14 +36,20 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, erofs_off_t offset = blknr_to_addr(blkaddr); pgoff_t index = offset >> PAGE_SHIFT; struct page *page = buf->page; + struct folio *folio; + unsigned int nofs_flag; if (!page || page->index != index) { erofs_put_metabuf(buf); - page = read_cache_page_gfp(mapping, index, - mapping_gfp_constraint(mapping, ~__GFP_FS)); - if (IS_ERR(page)) - return page; + + nofs_flag = memalloc_nofs_save(); + folio = read_cache_folio(mapping, index, NULL, NULL); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(folio)) + return folio; + /* should already be PageUptodate, no need to lock page */ + page = folio_file_page(folio, index); buf->page = page; } if (buf->kmap_type == EROFS_NO_KMAP) { @@ -63,6 +70,10 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, erofs_blk_t blkaddr, enum erofs_kmap_type type) { + if (erofs_is_fscache_mode(sb)) + return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode, + blkaddr, type); + return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type); } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 066f68c062e2..3f00eb34ac35 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -58,7 +58,34 @@ static int erofs_fscache_read_folios(struct fscache_cookie *cookie, return ret; } +static int erofs_fscache_meta_readpage(struct file *data, struct page *page) +{ + int ret; + struct folio *folio = page_folio(page); + struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct erofs_map_dev mdev = { + .m_deviceid = 0, + .m_pa = folio_pos(folio), + }; + + ret = erofs_map_dev(sb, &mdev); + if (ret) + goto out; + + ret = erofs_fscache_read_folios(mdev.m_fscache->cookie, + folio_mapping(folio), folio_pos(folio), + folio_size(folio), mdev.m_pa); + if (ret) + goto out; + + folio_mark_uptodate(folio); +out: + folio_unlock(folio); + return ret; +} + static const struct address_space_operations erofs_fscache_meta_aops = { + .readpage = erofs_fscache_meta_readpage, }; /* From patchwork Fri Apr 15 12:36:11 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814876 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6E287C433FE for ; Fri, 15 Apr 2022 12:37:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353857AbiDOMkB (ORCPT ); Fri, 15 Apr 2022 08:40:01 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40434 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353726AbiDOMja (ORCPT ); Fri, 15 Apr 2022 08:39:30 -0400 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D4518C6EEE; Fri, 15 Apr 2022 05:36:49 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R131e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04426;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7Cc4d_1650026203; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7Cc4d_1650026203) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:44 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 18/21] erofs: implement fscache-based data read for non-inline layout Date: Fri, 15 Apr 2022 20:36:11 +0800 Message-Id: <20220415123614.54024-19-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Implement the data plane of reading data from data blobs over fscache for non-inline layout. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/fscache.c | 51 +++++++++++++++++++++++++++++++++++++++++++++ fs/erofs/inode.c | 4 ++++ fs/erofs/internal.h | 2 ++ 3 files changed, 57 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 3f00eb34ac35..b799b0fe1b67 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -84,10 +84,61 @@ static int erofs_fscache_meta_readpage(struct file *data, struct page *page) return ret; } +static int erofs_fscache_readpage(struct file *file, struct page *page) +{ + struct folio *folio = page_folio(page); + struct inode *inode = folio_mapping(folio)->host; + struct super_block *sb = inode->i_sb; + struct erofs_map_blocks map; + struct erofs_map_dev mdev; + erofs_off_t pos; + loff_t pstart; + int ret = 0; + + DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ); + + pos = folio_pos(folio); + map.m_la = pos; + + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret) + goto out_unlock; + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + folio_zero_range(folio, 0, folio_size(folio)); + goto out_uptodate; + } + + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + + ret = erofs_map_dev(sb, &mdev); + if (ret) + goto out_unlock; + + pstart = mdev.m_pa + (pos - map.m_la); + ret = erofs_fscache_read_folios(mdev.m_fscache->cookie, + folio_mapping(folio), folio_pos(folio), + folio_size(folio), pstart); + +out_uptodate: + if (!ret) + folio_mark_uptodate(folio); +out_unlock: + folio_unlock(folio); + return ret; +} + static const struct address_space_operations erofs_fscache_meta_aops = { .readpage = erofs_fscache_meta_readpage, }; +const struct address_space_operations erofs_fscache_access_aops = { + .readpage = erofs_fscache_readpage, +}; + /* * Create an fscache context for data blob. * Return: 0 on success and allocated fscache context is assigned to @fscache, diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index e8b37ba5e9ad..8d3f56c6469b 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -297,6 +297,10 @@ static int erofs_fill_inode(struct inode *inode, int isdir) goto out_unlock; } inode->i_mapping->a_ops = &erofs_raw_access_aops; +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (erofs_is_fscache_mode(inode->i_sb)) + inode->i_mapping->a_ops = &erofs_fscache_access_aops; +#endif out_unlock: erofs_put_metabuf(&buf); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index fa488af8dfcf..c8f6ac910976 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -639,6 +639,8 @@ int erofs_fscache_register_cookie(struct super_block *sb, struct erofs_fscache **fscache, char *name, bool need_inode); void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache); + +extern const struct address_space_operations erofs_fscache_access_aops; #else static inline int erofs_fscache_register_fs(struct super_block *sb) { From patchwork Fri Apr 15 12:36:12 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814874 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5C4AFC433FE for ; Fri, 15 Apr 2022 12:37:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353694AbiDOMj4 (ORCPT ); Fri, 15 Apr 2022 08:39:56 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40252 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353724AbiDOMja (ORCPT ); Fri, 15 Apr 2022 08:39:30 -0400 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A0FDFC8BF1; Fri, 15 Apr 2022 05:36:50 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R131e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04400;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7DLWw_1650026205; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7DLWw_1650026205) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:46 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 19/21] erofs: implement fscache-based data read for inline layout Date: Fri, 15 Apr 2022 20:36:12 +0800 Message-Id: <20220415123614.54024-20-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Implement the data plane of reading data from data blobs over fscache for inline layout. For the heading non-inline part, the data plane for non-inline layout is reused, while only the tail packing part needs special handling. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/fscache.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index b799b0fe1b67..08849c15500f 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -84,6 +84,33 @@ static int erofs_fscache_meta_readpage(struct file *data, struct page *page) return ret; } +static int erofs_fscache_readpage_inline(struct folio *folio, + struct erofs_map_blocks *map) +{ + struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + erofs_blk_t blknr; + size_t offset, len; + void *src, *dst; + + /* For tail packing layout, the offset may be non-zero. */ + offset = erofs_blkoff(map->m_pa); + blknr = erofs_blknr(map->m_pa); + len = map->m_llen; + + src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP); + if (IS_ERR(src)) + return PTR_ERR(src); + + dst = kmap_local_folio(folio, 0); + memcpy(dst, src + offset, len); + memset(dst + len, 0, PAGE_SIZE - len); + kunmap_local(dst); + + erofs_put_metabuf(&buf); + return 0; +} + static int erofs_fscache_readpage(struct file *file, struct page *page) { struct folio *folio = page_folio(page); @@ -109,6 +136,11 @@ static int erofs_fscache_readpage(struct file *file, struct page *page) goto out_uptodate; } + if (map.m_flags & EROFS_MAP_META) { + ret = erofs_fscache_readpage_inline(folio, &map); + goto out_uptodate; + } + mdev = (struct erofs_map_dev) { .m_deviceid = map.m_deviceid, .m_pa = map.m_pa, From patchwork Fri Apr 15 12:36:13 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814875 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F3FB0C433F5 for ; Fri, 15 Apr 2022 12:37:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353733AbiDOMj7 (ORCPT ); Fri, 15 Apr 2022 08:39:59 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40476 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353674AbiDOMjb (ORCPT ); Fri, 15 Apr 2022 08:39:31 -0400 Received: from out30-133.freemail.mail.aliyun.com (out30-133.freemail.mail.aliyun.com [115.124.30.133]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AE7D3C90C1; Fri, 15 Apr 2022 05:36:51 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R721e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04423;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7VPV2_1650026207; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7VPV2_1650026207) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:48 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 20/21] erofs: implement fscache-based data readahead Date: Fri, 15 Apr 2022 20:36:13 +0800 Message-Id: <20220415123614.54024-21-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Implement fscache-based data readahead. Also registers an individual bdi for each erofs instance to enable readahead. Signed-off-by: Jeffle Xu --- fs/erofs/fscache.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++ fs/erofs/super.c | 4 +++ 2 files changed, 90 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 08849c15500f..eaa50692ddba 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -163,12 +163,98 @@ static int erofs_fscache_readpage(struct file *file, struct page *page) return ret; } +static void erofs_fscache_unlock_folios(struct readahead_control *rac, + size_t len) +{ + while (len) { + struct folio *folio = readahead_folio(rac); + + len -= folio_size(folio); + folio_mark_uptodate(folio); + folio_unlock(folio); + } +} + +static void erofs_fscache_readahead(struct readahead_control *rac) +{ + struct inode *inode = rac->mapping->host; + struct super_block *sb = inode->i_sb; + size_t len, count, done = 0; + erofs_off_t pos; + loff_t start, offset; + int ret; + + if (!readahead_count(rac)) + return; + + start = readahead_pos(rac); + len = readahead_length(rac); + + do { + struct erofs_map_blocks map; + struct erofs_map_dev mdev; + + pos = start + done; + map.m_la = pos; + + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret) + return; + + offset = start + done; + count = min_t(size_t, map.m_llen - (pos - map.m_la), + len - done); + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + struct iov_iter iter; + + iov_iter_xarray(&iter, READ, &rac->mapping->i_pages, + offset, count); + iov_iter_zero(count, &iter); + + erofs_fscache_unlock_folios(rac, count); + ret = count; + continue; + } + + if (map.m_flags & EROFS_MAP_META) { + struct folio *folio = readahead_folio(rac); + + ret = erofs_fscache_readpage_inline(folio, &map); + if (!ret) { + folio_mark_uptodate(folio); + ret = folio_size(folio); + } + + folio_unlock(folio); + continue; + } + + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + ret = erofs_map_dev(sb, &mdev); + if (ret) + return; + + ret = erofs_fscache_read_folios(mdev.m_fscache->cookie, + rac->mapping, offset, count, + mdev.m_pa + (pos - map.m_la)); + if (!ret) { + erofs_fscache_unlock_folios(rac, count); + ret = count; + } + } while (ret > 0 && ((done += ret) < len)); +} + static const struct address_space_operations erofs_fscache_meta_aops = { .readpage = erofs_fscache_meta_readpage, }; const struct address_space_operations erofs_fscache_access_aops = { .readpage = erofs_fscache_readpage, + .readahead = erofs_fscache_readahead, }; /* diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c6755bcae4a6..f68ba929100d 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -619,6 +619,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sbi->opt.fsid, true); if (err) return err; + + err = super_setup_bdi(sb); + if (err) + return err; } else { if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { erofs_err(sb, "failed to set erofs blksize"); From patchwork Fri Apr 15 12:36:14 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jingbo Xu X-Patchwork-Id: 12814877 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id E34B8C433EF for ; Fri, 15 Apr 2022 12:37:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1353755AbiDOMkG (ORCPT ); Fri, 15 Apr 2022 08:40:06 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40354 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1353752AbiDOMje (ORCPT ); Fri, 15 Apr 2022 08:39:34 -0400 Received: from out30-56.freemail.mail.aliyun.com (out30-56.freemail.mail.aliyun.com [115.124.30.56]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AB552C90E0; Fri, 15 Apr 2022 05:36:55 -0700 (PDT) X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R181e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e01424;MF=jefflexu@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0VA7VPVK_1650026208; Received: from localhost(mailfrom:jefflexu@linux.alibaba.com fp:SMTPD_---0VA7VPVK_1650026208) by smtp.aliyun-inc.com(127.0.0.1); Fri, 15 Apr 2022 20:36:49 +0800 From: Jeffle Xu To: dhowells@redhat.com, linux-cachefs@redhat.com, xiang@kernel.org, chao@kernel.org, linux-erofs@lists.ozlabs.org Cc: torvalds@linux-foundation.org, gregkh@linuxfoundation.org, willy@infradead.org, linux-fsdevel@vger.kernel.org, joseph.qi@linux.alibaba.com, bo.liu@linux.alibaba.com, tao.peng@linux.alibaba.com, gerry@linux.alibaba.com, eguan@linux.alibaba.com, linux-kernel@vger.kernel.org, luodaowen.backend@bytedance.com, tianzichen@kuaishou.com, fannaihao@baidu.com, zhangjiachen.jaycee@bytedance.com Subject: [PATCH v9 21/21] erofs: add 'fsid' mount option Date: Fri, 15 Apr 2022 20:36:14 +0800 Message-Id: <20220415123614.54024-22-jefflexu@linux.alibaba.com> X-Mailer: git-send-email 2.27.0 In-Reply-To: <20220415123614.54024-1-jefflexu@linux.alibaba.com> References: <20220415123614.54024-1-jefflexu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Introduce 'fsid' mount option to enable on-demand read sementics, in which case, erofs will be mounted from data blobs. Users could specify the name of primary data blob by this mount option. Signed-off-by: Jeffle Xu Reviewed-by: Gao Xiang --- fs/erofs/super.c | 31 ++++++++++++++++++++++++++++++- fs/erofs/sysfs.c | 4 ++-- 2 files changed, 32 insertions(+), 3 deletions(-) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index f68ba929100d..4a623630e1c4 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -371,6 +371,8 @@ static int erofs_read_superblock(struct super_block *sb) if (erofs_sb_has_ztailpacking(sbi)) erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!"); + if (erofs_is_fscache_mode(sb)) + erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!"); out: erofs_put_metabuf(&buf); return ret; @@ -399,6 +401,7 @@ enum { Opt_dax, Opt_dax_enum, Opt_device, + Opt_fsid, Opt_err }; @@ -423,6 +426,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_flag("dax", Opt_dax), fsparam_enum("dax", Opt_dax_enum, erofs_dax_param_enums), fsparam_string("device", Opt_device), + fsparam_string("fsid", Opt_fsid), {} }; @@ -518,6 +522,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, } ++ctx->devs->extra_devices; break; + case Opt_fsid: +#ifdef CONFIG_EROFS_FS_ONDEMAND + kfree(ctx->opt.fsid); + ctx->opt.fsid = kstrdup(param->string, GFP_KERNEL); + if (!ctx->opt.fsid) + return -ENOMEM; +#else + errorfc(fc, "fsid option not supported"); +#endif + break; default: return -ENOPARAM; } @@ -604,6 +618,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_fs_info = sbi; sbi->opt = ctx->opt; + ctx->opt.fsid = NULL; sbi->devs = ctx->devs; ctx->devs = NULL; @@ -690,6 +705,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) static int erofs_fc_get_tree(struct fs_context *fc) { + struct erofs_fs_context *ctx = fc->fs_private; + + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->opt.fsid) + return get_tree_nodev(fc, erofs_fc_fill_super); + return get_tree_bdev(fc, erofs_fc_fill_super); } @@ -739,6 +759,7 @@ static void erofs_fc_free(struct fs_context *fc) struct erofs_fs_context *ctx = fc->fs_private; erofs_free_dev_context(ctx->devs); + kfree(ctx->opt.fsid); kfree(ctx); } @@ -779,7 +800,10 @@ static void erofs_kill_sb(struct super_block *sb) WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC); - kill_block_super(sb); + if (erofs_is_fscache_mode(sb)) + generic_shutdown_super(sb); + else + kill_block_super(sb); sbi = EROFS_SB(sb); if (!sbi) @@ -789,6 +813,7 @@ static void erofs_kill_sb(struct super_block *sb) fs_put_dax(sbi->dax_dev); erofs_fscache_unregister_cookie(&sbi->s_fscache); erofs_fscache_unregister_fs(sb); + kfree(sbi->opt.fsid); kfree(sbi); sb->s_fs_info = NULL; } @@ -938,6 +963,10 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (opt->fsid) + seq_printf(seq, ",fsid=%s", opt->fsid); +#endif return 0; } diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index f3babf1e6608..c1383e508bbe 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -205,8 +205,8 @@ int erofs_register_sysfs(struct super_block *sb) sbi->s_kobj.kset = &erofs_root; init_completion(&sbi->s_kobj_unregister); - err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, - "%s", sb->s_id); + err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s", + erofs_is_fscache_mode(sb) ? sbi->opt.fsid : sb->s_id); if (err) goto put_sb_kobj; return 0;