From 8fb72b4a76933ae6f86725cc8e4a8190ba84d755 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:01 +0000 Subject: fscache: Convert fscache_set_page_dirty() to fscache_dirty_folio() Convert all users of fscache_set_page_dirty to use fscache_dirty_folio. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fscache.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux/fscache.h') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 296c5f1d9f35..d44ff747a657 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -616,9 +616,11 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } #if __fscache_available -extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie); +bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, + struct fscache_cookie *cookie); #else -#define fscache_set_page_dirty(PAGE, COOKIE) (__set_page_dirty_nobuffers((PAGE))) +#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ + filemap_dirty_folio(MAPPING, FOLIO) #endif /** @@ -626,7 +628,7 @@ extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cook * @wbc: The writeback control * @cookie: The cookie referring to the cache object * - * Unpin the writeback resources pinned by fscache_set_page_dirty(). This is + * Unpin the writeback resources pinned by fscache_dirty_folio(). This is * intended to be called by the netfs's ->write_inode() method. */ static inline void fscache_unpin_writeback(struct writeback_control *wbc, -- cgit v1.2.3 From e9b57aaae605eb869a628fdc21fe7d2c77a2205d Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Wed, 9 Feb 2022 14:00:47 +0800 Subject: fscache: export fscache_end_operation() Export fscache_end_operation() to avoid code duplication. Besides, considering the paired fscache_begin_read_operation() is already exported, it shall make sense to also export fscache_end_operation(). Signed-off-by: Jeffle Xu Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20220302125134.131039-2-jefflexu@linux.alibaba.com/ # Jeffle's v4 Link: https://lore.kernel.org/r/164622971432.3564931.12184135678781328146.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678190346.1200972.7453733431978569479.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692888334.2099075.5166283293894267365.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/20220316131723.111553-2-jefflexu@linux.alibaba.com/ # v5 --- fs/cifs/fscache.c | 8 -------- fs/fscache/internal.h | 11 ----------- fs/nfs/fscache.c | 8 -------- include/linux/fscache.h | 14 ++++++++++++++ 4 files changed, 14 insertions(+), 27 deletions(-) (limited to 'include/linux/fscache.h') diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 33af72e0ac0c..b47c2011ce5b 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -134,14 +134,6 @@ void cifs_fscache_release_inode_cookie(struct inode *inode) } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index f121c21590dc..ed1c9ed737f2 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -70,17 +70,6 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie, where); } -/* - * io.c - */ -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * main.c */ diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index cfe901650ab0..39654ca72d3d 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -249,14 +249,6 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 296c5f1d9f35..d2430da8aa67 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -456,6 +456,20 @@ int fscache_begin_read_operation(struct netfs_cache_resources *cres, return -ENOBUFS; } +/** + * fscache_end_operation - End the read operation for the netfs lib + * @cres: The cache resources for the read operation + * + * Clean up the resources at the end of the read request. + */ +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + /** * fscache_read - Start a read from the cache. * @cres: The cache resources to use -- cgit v1.2.3 From 2c547f299827c12244d613eb2ee3616d88f56088 Mon Sep 17 00:00:00 2001 From: Yue Hu Date: Wed, 6 Apr 2022 11:50:17 +0800 Subject: fscache: Remove the cookie parameter from fscache_clear_page_bits() The cookie is not used at all, remove it and update the usage in io.c and afs/write.c (which is the only user outside of fscache currently) at the same time. [DH: Amended the documentation also] Signed-off-by: Yue Hu Signed-off-by: David Howells cc: linux-cachefs@redhat.com Link: https://listman.redhat.com/archives/linux-cachefs/2022-April/006659.html --- Documentation/filesystems/caching/netfs-api.rst | 25 ++++++++++++------------- fs/afs/write.c | 3 +-- fs/fscache/io.c | 5 ++--- include/linux/fscache.h | 4 +--- 4 files changed, 16 insertions(+), 21 deletions(-) (limited to 'include/linux/fscache.h') diff --git a/Documentation/filesystems/caching/netfs-api.rst b/Documentation/filesystems/caching/netfs-api.rst index 5066113acad5..7308d76a29dc 100644 --- a/Documentation/filesystems/caching/netfs-api.rst +++ b/Documentation/filesystems/caching/netfs-api.rst @@ -404,22 +404,21 @@ schedule a write of that region:: And if an error occurs before that point is reached, the marks can be removed by calling:: - void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, + void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) -In both of these functions, the cookie representing the cache object to be -written to and a pointer to the mapping to which the source pages are attached -are passed in; start and len indicate the size of the region that's going to be -written (it doesn't have to align to page boundaries necessarily, but it does -have to align to DIO boundaries on the backing filesystem). The caching -parameter indicates if caching should be skipped, and if false, the functions -do nothing. - -The write function takes some additional parameters: i_size indicates the size -of the netfs file and term_func indicates an optional completion function, to -which term_func_priv will be passed, along with the error or amount written. +In these functions, a pointer to the mapping to which the source pages are +attached is passed in and start and len indicate the size of the region that's +going to be written (it doesn't have to align to page boundaries necessarily, +but it does have to align to DIO boundaries on the backing filesystem). The +caching parameter indicates if caching should be skipped, and if false, the +functions do nothing. + +The write function takes some additional parameters: the cookie representing +the cache object to be written to, i_size indicates the size of the netfs file +and term_func indicates an optional completion function, to which +term_func_priv will be passed, along with the error or amount written. Note that the write function will always run asynchronously and will unmark all the pages upon completion before calling term_func. diff --git a/fs/afs/write.c b/fs/afs/write.c index 6bcf1475511b..4763132ca57e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -616,8 +616,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(afs_vnode_cache(vnode), - mapping, start, len, caching); + fscache_clear_page_bits(mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } diff --git a/fs/fscache/io.c b/fs/fscache/io.c index c8c7fe9e9a6e..3af3b08a9bb3 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -235,8 +235,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, { struct fscache_write_request *wreq = priv; - fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), - wreq->mapping, wreq->start, wreq->len, + fscache_clear_page_bits(wreq->mapping, wreq->start, wreq->len, wreq->set_bits); if (wreq->term_func) @@ -296,7 +295,7 @@ abandon_end: abandon_free: kfree(wreq); abandon: - fscache_clear_page_bits(cookie, mapping, start, len, cond); + fscache_clear_page_bits(mapping, start, len, cond); if (term_func) term_func(term_func_priv, ret, false); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6727fb0db619..e25539072463 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -573,7 +573,6 @@ int fscache_write(struct netfs_cache_resources *cres, /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages - * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock @@ -582,8 +581,7 @@ int fscache_write(struct netfs_cache_resources *cres, * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ -static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, +static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { -- cgit v1.2.3 From c8383054506c77b814489c09877b5db83fd4abf2 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:24 +0800 Subject: cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into 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 the 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 should give the hint on it. Signed-off-by: Jeffle Xu Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells Signed-off-by: Gao Xiang --- fs/cachefiles/Kconfig | 12 ++ fs/cachefiles/Makefile | 1 + fs/cachefiles/daemon.c | 81 ++++++-- fs/cachefiles/internal.h | 51 +++++ fs/cachefiles/namei.c | 16 +- fs/cachefiles/ondemand.c | 378 ++++++++++++++++++++++++++++++++++++++ include/linux/fscache.h | 1 + include/trace/events/cachefiles.h | 2 + include/uapi/linux/cachefiles.h | 50 +++++ 9 files changed, 577 insertions(+), 15 deletions(-) create mode 100644 fs/cachefiles/ondemand.c create mode 100644 include/uapi/linux/cachefiles.h (limited to 'include/linux/fscache.h') diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 719faeeda168..8df715640a48 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -26,3 +26,15 @@ 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 userspace to enable the cachefiles on-demand read mode. + In this mode, when a cache miss occurs, responsibility for fetching + the data lies with the cachefiles backend instead of with the netfs + and is delegated to userspace. + + 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..d5417da7f792 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 +111,8 @@ 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); + xa_init_flags(&cache->reqs, XA_FLAGS_ALLOC); + xa_init_flags(&cache->ondemand_ids, XA_FLAGS_ALLOC1); /* set default caching limits * - limit at 1% free space and/or free files @@ -126,6 +131,39 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) return 0; } +static void cachefiles_flush_reqs(struct cachefiles_cache *cache) +{ + struct xarray *xa = &cache->reqs; + struct cachefiles_req *req; + unsigned long index; + + /* + * Make sure the following two operations won't be reordered. + * 1) set CACHEFILES_DEAD bit + * 2) flush requests in the xarray + * Otherwise the request may be enqueued after xarray has been + * flushed, leaving the orphan request never being completed. + * + * CPU 1 CPU 2 + * ===== ===== + * flush requests in the xarray + * test CACHEFILES_DEAD bit + * enqueue the request + * set CACHEFILES_DEAD bit + */ + smp_mb(); + + 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); +} + /* * Release a cache. */ @@ -139,6 +177,8 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) set_bit(CACHEFILES_DEAD, &cache->flags); + if (cachefiles_in_ondemand_mode(cache)) + cachefiles_flush_reqs(cache); cachefiles_daemon_unbind(cache); /* clean up the control file interface */ @@ -152,23 +192,14 @@ 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 +237,25 @@ 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 (cachefiles_in_ondemand_mode(cache)) + 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 +347,13 @@ 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 (cachefiles_in_ondemand_mode(cache)) { + if (!xa_empty(&cache->reqs)) + mask |= EPOLLIN; + } 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..4f5150a96849 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 +105,30 @@ 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 */ + struct xarray reqs; /* xarray of pending on-demand requests */ + struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ + u32 ondemand_id_next; }; +static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) +{ + return IS_ENABLED(CONFIG_CACHEFILES_ONDEMAND) && + test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags); +} + +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 +276,31 @@ 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..64fc312b16d3 --- /dev/null +++ b/fs/cachefiles/ondemand.c @@ -0,0 +1,378 @@ +// 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 ," + * indicates 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. The + * following two operations need to be atomic as a whole. + * 1) check cache state, and + * 2) enqueue request if cache is alive. + * Otherwise the request may be enqueued after xarray has been + * flushed, leaving the orphan request never being completed. + * + * CPU 1 CPU 2 + * ===== ===== + * test CACHEFILES_DEAD bit + * set CACHEFILES_DEAD bit + * flush requests in the xarray + * enqueue the request + */ + xas_lock(&xas); + + if (test_bit(CACHEFILES_DEAD, &cache->flags)) { + xas_unlock(&xas); + ret = -EIO; + goto out; + } + + /* coupled with the barrier in cachefiles_flush_reqs() */ + smp_mb(); + + 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 the cache file under the root cache + * directory. If the 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 -- cgit v1.2.3