From 6a19114b8e7f1e24d80b0812e26d78d7ae1ec6dd Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 10:01:23 +0000 Subject: netfs: Rename netfs_read_*request to netfs_io_*request Rename netfs_read_*request to netfs_io_*request so that the same structures can be used for the write helpers too. perl -p -i -e 's/netfs_read_(request|subrequest)/netfs_io_$1/g' \ `git grep -l 'netfs_read_\(sub\|\)request'` perl -p -i -e 's/nr_rd_ops/nr_outstanding/g' \ `git grep -l nr_rd_ops` perl -p -i -e 's/nr_wr_ops/nr_copy_ops/g' \ `git grep -l nr_wr_ops` perl -p -i -e 's/netfs_read_source/netfs_io_source/g' \ `git grep -l 'netfs_read_source'` perl -p -i -e 's/netfs_io_request_ops/netfs_request_ops/g' \ `git grep -l 'netfs_io_request_ops'` perl -p -i -e 's/init_rreq/init_request/g' \ `git grep -l 'init_rreq'` Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622988070.3564931.7089670190434315183.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678195157.1200972.366609966927368090.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692891535.2099075.18435198075367420588.stgit@warthog.procyon.org.uk/ # v3 --- Documentation/filesystems/netfs_library.rst | 40 ++++++++++++++--------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'Documentation/filesystems') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 4f373a8ec47b..a997e2d4321d 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -71,11 +71,11 @@ Read Helper Functions Three read helpers are provided:: void netfs_readahead(struct readahead_control *ractl, - const struct netfs_read_request_ops *ops, + const struct netfs_request_ops *ops, void *netfs_priv); int netfs_readpage(struct file *file, struct folio *folio, - const struct netfs_read_request_ops *ops, + const struct netfs_request_ops *ops, void *netfs_priv); int netfs_write_begin(struct file *file, struct address_space *mapping, @@ -84,7 +84,7 @@ Three read helpers are provided:: unsigned int flags, struct folio **_folio, void **_fsdata, - const struct netfs_read_request_ops *ops, + const struct netfs_request_ops *ops, void *netfs_priv); Each corresponds to a VM operation, with the addition of a couple of parameters @@ -116,7 +116,7 @@ occurs, the request will get partially completed if sufficient data is read. Additionally, there is:: - * void netfs_subreq_terminated(struct netfs_read_subrequest *subreq, + * void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, ssize_t transferred_or_error, bool was_async); @@ -132,7 +132,7 @@ Read Helper Structures The read helpers make use of a couple of structures to maintain the state of the read. The first is a structure that manages a read request as a whole:: - struct netfs_read_request { + struct netfs_io_request { struct inode *inode; struct address_space *mapping; struct netfs_cache_resources cache_resources; @@ -140,7 +140,7 @@ the read. The first is a structure that manages a read request as a whole:: loff_t start; size_t len; loff_t i_size; - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; unsigned int debug_id; ... }; @@ -187,8 +187,8 @@ The above fields are the ones the netfs can use. They are: The second structure is used to manage individual slices of the overall read request:: - struct netfs_read_subrequest { - struct netfs_read_request *rreq; + struct netfs_io_subrequest { + struct netfs_io_request *rreq; loff_t start; size_t len; size_t transferred; @@ -244,23 +244,23 @@ Read Helper Operations The network filesystem must provide the read helpers with a table of operations through which it can issue requests and negotiate:: - struct netfs_read_request_ops { - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); + struct netfs_request_ops { + void (*init_request)(struct netfs_io_request *rreq, struct file *file); bool (*is_cache_enabled)(struct inode *inode); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_op)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); + void (*done)(struct netfs_io_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; The operations are as follows: - * ``init_rreq()`` + * ``init_request()`` [Optional] This is called to initialise the request structure. It is given the file for reference and can modify the ->netfs_priv value. @@ -420,12 +420,12 @@ The network filesystem's ->begin_cache_operation() method is called to set up a cache and this must call into the cache to do the work. If using fscache, for example, the cache would call:: - int fscache_begin_read_operation(struct netfs_read_request *rreq, + int fscache_begin_read_operation(struct netfs_io_request *rreq, struct fscache_cookie *cookie); passing in the request pointer and the cookie corresponding to the file. -The netfs_read_request object contains a place for the cache to hang its +The netfs_io_request object contains a place for the cache to hang its state:: struct netfs_cache_resources { @@ -443,7 +443,7 @@ operation table looks like the following:: void (*expand_readahead)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, loff_t i_size); - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, loff_t i_size); int (*read)(struct netfs_cache_resources *cres, -- cgit v1.2.3 From f18a378580a761c8559b7d90afaa157269559c05 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 10:14:32 +0000 Subject: netfs: Finish off rename of netfs_read_request to netfs_io_request Adjust helper function names and comments after mass rename of struct netfs_read_*request to struct netfs_io_*request. Changes ======= ver #2) - Make the changes in the docs also. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622992433.3564931.6684311087845150271.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678196111.1200972.5001114956865989528.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692892567.2099075.13895804222087028813.stgit@warthog.procyon.org.uk/ # v3 --- Documentation/filesystems/netfs_library.rst | 4 +- fs/9p/vfs_addr.c | 6 +-- fs/afs/file.c | 4 +- fs/cachefiles/io.c | 4 +- fs/ceph/addr.c | 6 +-- fs/netfs/read_helper.c | 83 +++++++++++++++-------------- include/linux/netfs.h | 22 ++++---- 7 files changed, 65 insertions(+), 64 deletions(-) (limited to 'Documentation/filesystems') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index a997e2d4321d..4eb7e7b7b0fc 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -250,7 +250,7 @@ through which it can issue requests and negotiate:: int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); - void (*issue_op)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); @@ -305,7 +305,7 @@ The operations are as follows: This should return 0 on success and an error code on error. - * ``issue_op()`` + * ``issue_read()`` [Required] The helpers use this to dispatch a subrequest to the server for reading. In the subrequest, ->start, ->len and ->transferred indicate what diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 7b79fabe7593..fdc1033a1546 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -28,10 +28,10 @@ #include "fid.h" /** - * v9fs_req_issue_op - Issue a read from 9P + * v9fs_issue_read - Issue a read from 9P * @subreq: The read to make */ -static void v9fs_req_issue_op(struct netfs_io_subrequest *subreq) +static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; @@ -106,7 +106,7 @@ static const struct netfs_request_ops v9fs_req_ops = { .init_request = v9fs_init_request, .is_cache_enabled = v9fs_is_cache_enabled, .begin_cache_operation = v9fs_begin_cache_operation, - .issue_op = v9fs_req_issue_op, + .issue_read = v9fs_issue_read, .cleanup = v9fs_req_cleanup, }; diff --git a/fs/afs/file.c b/fs/afs/file.c index e55761f8858c..b19d635eed12 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -310,7 +310,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) return afs_do_sync_operation(op); } -static void afs_req_issue_op(struct netfs_io_subrequest *subreq) +static void afs_issue_read(struct netfs_io_subrequest *subreq) { struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); struct afs_read *fsreq; @@ -401,7 +401,7 @@ const struct netfs_request_ops afs_req_ops = { .is_cache_enabled = afs_is_cache_enabled, .begin_cache_operation = afs_begin_cache_operation, .check_write_begin = afs_check_write_begin, - .issue_op = afs_req_issue_op, + .issue_read = afs_issue_read, .cleanup = afs_priv_cleanup, }; diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 6ac6fdbc70d3..b19f496db9ad 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -406,7 +406,7 @@ 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_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); why = cachefiles_trace_read_no_data; goto out_no_object; } @@ -475,7 +475,7 @@ static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest * goto out; download_and_store: - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); out: cachefiles_end_secure(cache, saved_cred); out_no_object: diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9d995f351079..9189257476f8 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -259,7 +259,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) size_t len; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) goto out; @@ -298,7 +298,7 @@ out: return true; } -static void ceph_netfs_issue_op(struct netfs_io_subrequest *subreq) +static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; struct inode *inode = rreq->inode; @@ -367,7 +367,7 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) static const struct netfs_request_ops ceph_netfs_read_ops = { .is_cache_enabled = ceph_is_cache_enabled, .begin_cache_operation = ceph_begin_cache_operation, - .issue_op = ceph_netfs_issue_op, + .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, .clamp_length = ceph_netfs_clamp_length, .check_write_begin = ceph_netfs_check_write_begin, diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 50035d93f1dc..26d54055b17e 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -37,7 +37,7 @@ static void netfs_put_subrequest(struct netfs_io_subrequest *subreq, __netfs_put_subrequest(subreq, was_async); } -static struct netfs_io_request *netfs_alloc_read_request( +static struct netfs_io_request *netfs_alloc_request( const struct netfs_request_ops *ops, void *netfs_priv, struct file *file) { @@ -63,13 +63,12 @@ static struct netfs_io_request *netfs_alloc_read_request( return rreq; } -static void netfs_get_read_request(struct netfs_io_request *rreq) +static void netfs_get_request(struct netfs_io_request *rreq) { refcount_inc(&rreq->usage); } -static void netfs_rreq_clear_subreqs(struct netfs_io_request *rreq, - bool was_async) +static void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) { struct netfs_io_subrequest *subreq; @@ -81,11 +80,11 @@ static void netfs_rreq_clear_subreqs(struct netfs_io_request *rreq, } } -static void netfs_free_read_request(struct work_struct *work) +static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); - netfs_rreq_clear_subreqs(rreq, false); + netfs_clear_subrequests(rreq, false); if (rreq->netfs_priv) rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); trace_netfs_rreq(rreq, netfs_rreq_trace_free); @@ -95,15 +94,15 @@ static void netfs_free_read_request(struct work_struct *work) netfs_stat_d(&netfs_n_rh_rreq); } -static void netfs_put_read_request(struct netfs_io_request *rreq, bool was_async) +static void netfs_put_request(struct netfs_io_request *rreq, bool was_async) { if (refcount_dec_and_test(&rreq->usage)) { if (was_async) { - rreq->work.func = netfs_free_read_request; + rreq->work.func = netfs_free_request; if (!queue_work(system_unbound_wq, &rreq->work)) BUG(); } else { - netfs_free_read_request(&rreq->work); + netfs_free_request(&rreq->work); } } } @@ -121,14 +120,14 @@ static struct netfs_io_subrequest *netfs_alloc_subrequest( INIT_LIST_HEAD(&subreq->rreq_link); refcount_set(&subreq->usage, 2); subreq->rreq = rreq; - netfs_get_read_request(rreq); + netfs_get_request(rreq); netfs_stat(&netfs_n_rh_sreq); } return subreq; } -static void netfs_get_read_subrequest(struct netfs_io_subrequest *subreq) +static void netfs_get_subrequest(struct netfs_io_subrequest *subreq) { refcount_inc(&subreq->usage); } @@ -141,7 +140,7 @@ static void __netfs_put_subrequest(struct netfs_io_subrequest *subreq, trace_netfs_sreq(subreq, netfs_sreq_trace_free); kfree(subreq); netfs_stat_d(&netfs_n_rh_sreq); - netfs_put_read_request(rreq, was_async); + netfs_put_request(rreq, was_async); } /* @@ -216,7 +215,7 @@ static void netfs_read_from_server(struct netfs_io_request *rreq, struct netfs_io_subrequest *subreq) { netfs_stat(&netfs_n_rh_download); - rreq->netfs_ops->issue_op(subreq); + rreq->netfs_ops->issue_read(subreq); } /* @@ -225,8 +224,8 @@ static void netfs_read_from_server(struct netfs_io_request *rreq, static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) { trace_netfs_rreq(rreq, netfs_rreq_trace_done); - netfs_rreq_clear_subreqs(rreq, was_async); - netfs_put_read_request(rreq, was_async); + netfs_clear_subrequests(rreq, was_async); + netfs_put_request(rreq, was_async); } /* @@ -306,7 +305,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) atomic_inc(&rreq->nr_copy_ops); list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { list_del_init(&subreq->rreq_link); netfs_put_subrequest(subreq, false); } @@ -336,7 +335,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) atomic_inc(&rreq->nr_copy_ops); netfs_stat(&netfs_n_rh_write); - netfs_get_read_subrequest(subreq); + netfs_get_subrequest(subreq); trace_netfs_sreq(subreq, netfs_sreq_trace_write); cres->ops->write(cres, subreq->start, &iter, netfs_rreq_copy_terminated, subreq); @@ -378,9 +377,9 @@ static void netfs_rreq_unlock(struct netfs_io_request *rreq) XA_STATE(xas, &rreq->mapping->i_pages, start_page); if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); + __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); } } @@ -408,7 +407,7 @@ static void netfs_rreq_unlock(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) folio_start_fscache(folio); pg_failed |= subreq_failed; if (pgend < iopos + subreq->len) @@ -453,13 +452,13 @@ static void netfs_rreq_unlock(struct netfs_io_request *rreq) static void netfs_rreq_short_read(struct netfs_io_request *rreq, struct netfs_io_subrequest *subreq) { - __clear_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); + __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); netfs_stat(&netfs_n_rh_short_read); trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); - netfs_get_read_subrequest(subreq); + netfs_get_subrequest(subreq); atomic_inc(&rreq->nr_outstanding); if (subreq->source == NETFS_READ_FROM_CACHE) netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); @@ -493,10 +492,10 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) subreq->error = 0; netfs_stat(&netfs_n_rh_download_instead); trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); - netfs_get_read_subrequest(subreq); + netfs_get_subrequest(subreq); atomic_inc(&rreq->nr_outstanding); netfs_read_from_server(rreq, subreq); - } else if (test_bit(NETFS_SREQ_SHORT_READ, &subreq->flags)) { + } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { netfs_rreq_short_read(rreq, subreq); } } @@ -553,7 +552,7 @@ again: clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags)) + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) return netfs_rreq_write_to_cache(rreq); netfs_rreq_completed(rreq, was_async); @@ -642,8 +641,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, complete: __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); out: trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); @@ -674,7 +673,7 @@ incomplete: __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); } - __set_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); + __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); goto out; @@ -878,7 +877,7 @@ void netfs_readahead(struct readahead_control *ractl, if (readahead_count(ractl) == 0) goto cleanup; - rreq = netfs_alloc_read_request(ops, netfs_priv, ractl->file); + rreq = netfs_alloc_request(ops, netfs_priv, ractl->file); if (!rreq) goto cleanup; rreq->mapping = ractl->mapping; @@ -916,7 +915,7 @@ void netfs_readahead(struct readahead_control *ractl, return; cleanup_free: - netfs_put_read_request(rreq, false); + netfs_put_request(rreq, false); return; cleanup: if (netfs_priv) @@ -953,7 +952,7 @@ int netfs_readpage(struct file *file, _enter("%lx", folio_index(folio)); - rreq = netfs_alloc_read_request(ops, netfs_priv, file); + rreq = netfs_alloc_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) ops->cleanup(folio_file_mapping(folio), netfs_priv); @@ -975,7 +974,7 @@ int netfs_readpage(struct file *file, netfs_stat(&netfs_n_rh_readpage); trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); - netfs_get_read_request(rreq); + netfs_get_request(rreq); atomic_set(&rreq->nr_outstanding, 1); do { @@ -989,7 +988,8 @@ int netfs_readpage(struct file *file, * process. */ do { - wait_var_event(&rreq->nr_outstanding, atomic_read(&rreq->nr_outstanding) == 1); + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); netfs_rreq_assess(rreq, false); } while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)); @@ -999,7 +999,7 @@ int netfs_readpage(struct file *file, ret = -EIO; } out: - netfs_put_read_request(rreq, false); + netfs_put_request(rreq, false); return ret; } EXPORT_SYMBOL(netfs_readpage); @@ -1122,7 +1122,7 @@ retry: } ret = -ENOMEM; - rreq = netfs_alloc_read_request(ops, netfs_priv, file); + rreq = netfs_alloc_request(ops, netfs_priv, file); if (!rreq) goto error; rreq->mapping = folio_file_mapping(folio); @@ -1146,7 +1146,7 @@ retry: */ ractl._nr_pages = folio_nr_pages(folio); netfs_rreq_expand(rreq, &ractl); - netfs_get_read_request(rreq); + netfs_get_request(rreq); /* We hold the folio locks, so we can drop the references */ folio_get(folio); @@ -1160,12 +1160,13 @@ retry: } while (rreq->submitted < rreq->len); - /* Keep nr_outstanding incremented so that the ref always belongs to us, and - * the service code isn't punted off to a random thread pool to + /* Keep nr_outstanding incremented so that the ref always belongs to + * us, and the service code isn't punted off to a random thread pool to * process. */ for (;;) { - wait_var_event(&rreq->nr_outstanding, atomic_read(&rreq->nr_outstanding) == 1); + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); netfs_rreq_assess(rreq, false); if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) break; @@ -1177,7 +1178,7 @@ retry: trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_write_begin); ret = -EIO; } - netfs_put_read_request(rreq, false); + netfs_put_request(rreq, false); if (ret < 0) goto error; @@ -1193,7 +1194,7 @@ have_folio_no_wait: return 0; error_put: - netfs_put_read_request(rreq, false); + netfs_put_request(rreq, false); error: folio_unlock(folio); folio_put(folio); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index a2ca91cb7a68..f63de27d6f29 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -131,7 +131,7 @@ struct netfs_cache_resources { * Descriptor for a single component subrequest. */ struct netfs_io_subrequest { - struct netfs_io_request *rreq; /* Supervising read request */ + struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ @@ -139,29 +139,29 @@ struct netfs_io_subrequest { refcount_t usage; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_io_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; -#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#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 */ }; /* - * Descriptor for a read helper request. This is used to make multiple I/O - * requests on a variety of sources and then stitch the result together. + * Descriptor for an I/O helper request. This is used to make multiple I/O + * operations to a variety of data stores and then stitch the result together. */ struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; - struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_outstanding; /* Number of read ops in progress */ - atomic_t nr_copy_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of ops in progress */ + atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ @@ -171,7 +171,7 @@ struct netfs_io_request { refcount_t usage; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ @@ -188,7 +188,7 @@ struct netfs_request_ops { int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); - void (*issue_op)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); -- cgit v1.2.3 From bc899ee1c898e520574ff4d99356eb2e724a9265 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Jun 2021 22:37:05 +0100 Subject: netfs: Add a netfs inode context Add a netfs_i_context struct that should be included in the network filesystem's own inode struct wrapper, directly after the VFS's inode struct, e.g.: struct my_inode { struct { /* These must be contiguous */ struct inode vfs_inode; struct netfs_i_context netfs_ctx; }; }; The netfs_i_context struct so far contains a single field for the network filesystem to use - the cache cookie: struct netfs_i_context { ... struct fscache_cookie *cache; }; Three functions are provided to help with this: (1) void netfs_i_context_init(struct inode *inode, const struct netfs_request_ops *ops); Initialise the netfs context and set the operations. (2) struct netfs_i_context *netfs_i_context(struct inode *inode); Find the netfs context from the VFS inode. (3) struct inode *netfs_inode(struct netfs_i_context *ctx); Find the VFS inode from the netfs context. Changes ======= ver #4) - Fix netfs_is_cache_enabled() to check cookie->cache_priv to see if a cache is present[3]. - Fix netfs_skip_folio_read() to zero out all of the page, not just some of it[3]. ver #3) - Split out the bit to move ceph cap-getting on readahead into ceph_init_request()[1]. - Stick in a comment to the netfs inode structs indicating the contiguity requirements[2]. ver #2) - Adjust documentation to match. - Use "#if IS_ENABLED()" in netfs_i_cookie(), not "#ifdef". - Move the cap check from ceph_readahead() to ceph_init_request() to be called from netfslib. - Remove ceph_readahead() and use netfs_readahead() directly instead. Signed-off-by: David Howells Acked-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/8af0d47f17d89c06bbf602496dd845f2b0bf25b3.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/beaf4f6a6c2575ed489adb14b257253c868f9a5c.camel@kernel.org/ [2] Link: https://lore.kernel.org/r/3536452.1647421585@warthog.procyon.org.uk/ [3] Link: https://lore.kernel.org/r/164622984545.3564931.15691742939278418580.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678213320.1200972.16807551936267647470.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692909854.2099075.9535537286264248057.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/306388.1647595110@warthog.procyon.org.uk/ # v4 --- Documentation/filesystems/netfs_library.rst | 101 ++++++++++++++++++++-------- fs/9p/cache.c | 10 ++- fs/9p/v9fs.c | 4 +- fs/9p/v9fs.h | 13 ++-- fs/9p/vfs_addr.c | 43 ++---------- fs/9p/vfs_inode.c | 13 +++- fs/afs/dynroot.c | 1 + fs/afs/file.c | 26 +------ fs/afs/inode.c | 31 ++++++--- fs/afs/internal.h | 19 ++++-- fs/afs/super.c | 4 +- fs/afs/write.c | 3 +- fs/ceph/addr.c | 31 ++------- fs/ceph/cache.c | 28 ++++---- fs/ceph/cache.h | 11 +-- fs/ceph/inode.c | 6 +- fs/ceph/super.h | 17 +++-- fs/cifs/cifsglob.h | 10 +-- fs/cifs/fscache.c | 11 +-- fs/cifs/fscache.h | 2 +- fs/netfs/internal.h | 18 ++++- fs/netfs/objects.c | 12 ++-- fs/netfs/read_helper.c | 100 +++++++++++++-------------- fs/netfs/stats.c | 1 - include/linux/netfs.h | 81 +++++++++++++++++++--- 25 files changed, 318 insertions(+), 278 deletions(-) (limited to 'Documentation/filesystems') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 4eb7e7b7b0fc..9c8bc5666b46 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -7,6 +7,8 @@ Network Filesystem Helper Library .. Contents: - Overview. + - Per-inode context. + - Inode context helper functions. - Buffered read helpers. - Read helper functions. - Read helper structures. @@ -28,6 +30,69 @@ Note that the library module doesn't link against local caching directly, so access must be provided by the netfs. +Per-Inode Context +================= + +The network filesystem helper library needs a place to store a bit of state for +its use on each netfs inode it is helping to manage. To this end, a context +structure is defined:: + + struct netfs_i_context { + const struct netfs_request_ops *ops; + struct fscache_cookie *cache; + }; + +A network filesystem that wants to use netfs lib must place one of these +directly after the VFS ``struct inode`` it allocates, usually as part of its +own struct. This can be done in a way similar to the following:: + + struct my_inode { + struct { + /* These must be contiguous */ + struct inode vfs_inode; + struct netfs_i_context netfs_ctx; + }; + ... + }; + +This allows netfslib to find its state by simple offset from the inode pointer, +thereby allowing the netfslib helper functions to be pointed to directly by the +VFS/VM operation tables. + +The structure contains the following fields: + + * ``ops`` + + The set of operations provided by the network filesystem to netfslib. + + * ``cache`` + + Local caching cookie, or NULL if no caching is enabled. This field does not + exist if fscache is disabled. + + +Inode Context Helper Functions +------------------------------ + +To help deal with the per-inode context, a number helper functions are +provided. Firstly, a function to perform basic initialisation on a context and +set the operations table pointer:: + + void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops); + +then two functions to cast between the VFS inode structure and the netfs +context:: + + struct netfs_i_context *netfs_i_context(struct inode *inode); + struct inode *netfs_inode(struct netfs_i_context *ctx); + +and finally, a function to get the cache cookie pointer from the context +attached to an inode (or NULL if fscache is disabled):: + + struct fscache_cookie *netfs_i_cookie(struct inode *inode); + + Buffered Read Helpers ===================== @@ -70,38 +135,22 @@ Read Helper Functions Three read helpers are provided:: - void netfs_readahead(struct readahead_control *ractl, - const struct netfs_request_ops *ops, - void *netfs_priv); + void netfs_readahead(struct readahead_control *ractl); int netfs_readpage(struct file *file, - struct folio *folio, - const struct netfs_request_ops *ops, - void *netfs_priv); + struct page *page); int netfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int flags, struct folio **_folio, - void **_fsdata, - const struct netfs_request_ops *ops, - void *netfs_priv); - -Each corresponds to a VM operation, with the addition of a couple of parameters -for the use of the read helpers: + void **_fsdata); - * ``ops`` - - A table of operations through which the helpers can talk to the filesystem. - - * ``netfs_priv`` +Each corresponds to a VM address space operation. These operations use the +state in the per-inode context. - Filesystem private data (can be NULL). - -Both of these values will be stored into the read request structure. - -For ->readahead() and ->readpage(), the network filesystem should just jump -into the corresponding read helper; whereas for ->write_begin(), it may be a +For ->readahead() and ->readpage(), the network filesystem just point directly +at the corresponding read helper; whereas for ->write_begin(), it may be a little more complicated as the network filesystem might want to flush conflicting writes or track dirty data and needs to put the acquired folio if an error occurs after calling the helper. @@ -246,7 +295,6 @@ through which it can issue requests and negotiate:: struct netfs_request_ops { void (*init_request)(struct netfs_io_request *rreq, struct file *file); - bool (*is_cache_enabled)(struct inode *inode); int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); @@ -265,11 +313,6 @@ The operations are as follows: [Optional] This is called to initialise the request structure. It is given the file for reference and can modify the ->netfs_priv value. - * ``is_cache_enabled()`` - - [Required] This is called by netfs_write_begin() to ask if the file is being - cached. It should return true if it is being cached and false otherwise. - * ``begin_cache_operation()`` [Optional] This is called to ask the network filesystem to call into the diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 55e108e5e133..1c8dc696d516 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -49,22 +49,20 @@ int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, void v9fs_cache_inode_get_cookie(struct inode *inode) { - struct v9fs_inode *v9inode; + struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; __le32 version; __le64 path; if (!S_ISREG(inode->i_mode)) return; - - v9inode = V9FS_I(inode); - if (WARN_ON(v9inode->fscache)) + if (WARN_ON(v9fs_inode_cookie(v9inode))) return; version = cpu_to_le32(v9inode->qid.version); path = cpu_to_le64(v9inode->qid.path); v9ses = v9fs_inode2v9ses(inode); - v9inode->fscache = + v9inode->netfs_ctx.cache = fscache_acquire_cookie(v9fs_session_cache(v9ses), 0, &path, sizeof(path), @@ -72,5 +70,5 @@ void v9fs_cache_inode_get_cookie(struct inode *inode) i_size_read(&v9inode->vfs_inode)); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", - inode, v9inode->fscache); + inode, v9fs_inode_cookie(v9inode)); } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 08f65c40af4f..e28ddf763b3b 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -623,9 +623,7 @@ static void v9fs_sysfs_cleanup(void) static void v9fs_inode_init_once(void *foo) { struct v9fs_inode *v9inode = (struct v9fs_inode *)foo; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif + memset(&v9inode->qid, 0, sizeof(v9inode->qid)); inode_init_once(&v9inode->vfs_inode); } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index bc8b30205d36..ec0e8df3b2eb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -9,6 +9,7 @@ #define FS_9P_V9FS_H #include +#include /** * enum p9_session_flags - option flags for each 9P session @@ -108,14 +109,15 @@ struct v9fs_session_info { #define V9FS_INO_INVALID_ATTR 0x01 struct v9fs_inode { -#ifdef CONFIG_9P_FSCACHE - struct fscache_cookie *fscache; -#endif + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct p9_qid qid; unsigned int cache_validity; struct p9_fid *writeback_fid; struct mutex v_mutex; - struct inode vfs_inode; }; static inline struct v9fs_inode *V9FS_I(const struct inode *inode) @@ -126,7 +128,7 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode) { #ifdef CONFIG_9P_FSCACHE - return v9inode->fscache; + return netfs_i_cookie(&v9inode->vfs_inode); #else return NULL; #endif @@ -163,6 +165,7 @@ extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses, extern const struct inode_operations v9fs_dir_inode_operations_dotl; extern const struct inode_operations v9fs_file_inode_operations_dotl; extern const struct inode_operations v9fs_symlink_inode_operations_dotl; +extern const struct netfs_request_ops v9fs_req_ops; extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid, struct super_block *sb, int new); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 91d3926c9559..ed06f3c34e98 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -77,17 +77,6 @@ static void v9fs_req_cleanup(struct address_space *mapping, void *priv) p9_client_clunk(fid); } -/** - * v9fs_is_cache_enabled - Determine if caching is enabled for an inode - * @inode: The inode to check - */ -static bool v9fs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - /** * v9fs_begin_cache_operation - Begin a cache operation for a read * @rreq: The read request @@ -103,36 +92,13 @@ static int v9fs_begin_cache_operation(struct netfs_io_request *rreq) #endif } -static const struct netfs_request_ops v9fs_req_ops = { +const struct netfs_request_ops v9fs_req_ops = { .init_request = v9fs_init_request, - .is_cache_enabled = v9fs_is_cache_enabled, .begin_cache_operation = v9fs_begin_cache_operation, .issue_read = v9fs_issue_read, .cleanup = v9fs_req_cleanup, }; -/** - * v9fs_vfs_readpage - read an entire page in from 9P - * @file: file being read - * @page: structure to page - * - */ -static int v9fs_vfs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &v9fs_req_ops, NULL); -} - -/** - * v9fs_vfs_readahead - read a set of pages from 9P - * @ractl: The readahead parameters - */ -static void v9fs_vfs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &v9fs_req_ops, NULL); -} - /** * v9fs_release_page - release the private state associated with a page * @page: The page to be released @@ -326,8 +292,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, - &v9fs_req_ops, NULL); + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata); if (retval < 0) return retval; @@ -388,8 +353,8 @@ static int v9fs_set_page_dirty(struct page *page) #endif const struct address_space_operations v9fs_addr_operations = { - .readpage = v9fs_vfs_readpage, - .readahead = v9fs_vfs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .set_page_dirty = v9fs_set_page_dirty, .writepage = v9fs_vfs_writepage, .write_begin = v9fs_write_begin, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 2a10242c79c7..a7dc6781a622 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -231,9 +231,6 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) v9inode = kmem_cache_alloc(v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; mutex_init(&v9inode->v_mutex); @@ -250,6 +247,14 @@ void v9fs_free_inode(struct inode *inode) kmem_cache_free(v9fs_inode_cache, V9FS_I(inode)); } +/* + * Set parameters for the netfs library + */ +static void v9fs_set_netfs_context(struct inode *inode) +{ + netfs_i_context_init(inode, &v9fs_req_ops); +} + int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev) { @@ -338,6 +343,8 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } + + v9fs_set_netfs_context(inode); error: return err; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index db832cc931c8..f120bcb8bf73 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -76,6 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); + netfs_i_context_init(inode, NULL); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { diff --git a/fs/afs/file.c b/fs/afs/file.c index 6469d7f98ef5..2b68b2070248 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -19,13 +19,11 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_readpage(struct file *file, struct page *page); static int afs_symlink_readpage(struct file *file, struct page *page); static void afs_invalidatepage(struct page *page, unsigned int offset, unsigned int length); static int afs_releasepage(struct page *page, gfp_t gfp_flags); -static void afs_readahead(struct readahead_control *ractl); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static void afs_vm_open(struct vm_area_struct *area); static void afs_vm_close(struct vm_area_struct *area); @@ -52,8 +50,8 @@ const struct inode_operations afs_file_inode_operations = { }; const struct address_space_operations afs_file_aops = { - .readpage = afs_readpage, - .readahead = afs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .set_page_dirty = afs_set_page_dirty, .launder_page = afs_launder_page, .releasepage = afs_releasepage, @@ -365,13 +363,6 @@ static int afs_init_request(struct netfs_io_request *rreq, struct file *file) return 0; } -static bool afs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - static int afs_begin_cache_operation(struct netfs_io_request *rreq) { #ifdef CONFIG_AFS_FSCACHE @@ -399,25 +390,12 @@ static void afs_priv_cleanup(struct address_space *mapping, void *netfs_priv) const struct netfs_request_ops afs_req_ops = { .init_request = afs_init_request, - .is_cache_enabled = afs_is_cache_enabled, .begin_cache_operation = afs_begin_cache_operation, .check_write_begin = afs_check_write_begin, .issue_read = afs_issue_read, .cleanup = afs_priv_cleanup, }; -static int afs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &afs_req_ops, NULL); -} - -static void afs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &afs_req_ops, NULL); -} - int afs_write_inode(struct inode *inode, struct writeback_control *wbc) { fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode))); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 5964f8aee090..5b5e40197655 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -53,6 +53,14 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren dump_stack(); } +/* + * Set parameters for the netfs library + */ +static void afs_set_netfs_context(struct afs_vnode *vnode) +{ + netfs_i_context_init(&vnode->vfs_inode, &afs_req_ops); +} + /* * Initialise an inode from the vnode status. */ @@ -128,6 +136,7 @@ static int afs_inode_init_from_status(struct afs_operation *op, } afs_set_i_size(vnode, status->size); + afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); @@ -420,7 +429,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) struct afs_vnode_cache_aux aux; if (vnode->status.type != AFS_FTYPE_FILE) { - vnode->cache = NULL; + vnode->netfs_ctx.cache = NULL; return; } @@ -430,12 +439,14 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) key.vnode_id_ext[1] = htonl(vnode->fid.vnode_hi); afs_set_cache_aux(vnode, &aux); - vnode->cache = fscache_acquire_cookie( - vnode->volume->cache, - vnode->status.type == AFS_FTYPE_FILE ? 0 : FSCACHE_ADV_SINGLE_CHUNK, - &key, sizeof(key), - &aux, sizeof(aux), - vnode->status.size); + afs_vnode_set_cache(vnode, + fscache_acquire_cookie( + vnode->volume->cache, + vnode->status.type == AFS_FTYPE_FILE ? + 0 : FSCACHE_ADV_SINGLE_CHUNK, + &key, sizeof(key), + &aux, sizeof(aux), + vnode->status.size)); #endif } @@ -528,6 +539,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key) vnode = AFS_FS_I(inode); vnode->cb_v_break = as->volume->cb_v_break, + afs_set_netfs_context(vnode); op = afs_alloc_operation(key, as->volume); if (IS_ERR(op)) { @@ -786,11 +798,8 @@ void afs_evict_inode(struct inode *inode) afs_put_wb_key(wbk); } -#ifdef CONFIG_AFS_FSCACHE - fscache_relinquish_cookie(vnode->cache, + fscache_relinquish_cookie(afs_vnode_cache(vnode), test_bit(AFS_VNODE_DELETED, &vnode->flags)); - vnode->cache = NULL; -#endif afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index c56a0e1719ae..75ca3026457e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -619,15 +619,16 @@ enum afs_lock_state { * leak from one inode to another. */ struct afs_vnode { - struct inode vfs_inode; /* the VFS's inode record */ + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct afs_volume *volume; /* volume on which vnode resides */ struct afs_fid fid; /* the file identifier for this inode */ struct afs_file_status status; /* AFS status info for this file */ afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ struct mutex io_lock; /* Lock for serialising I/O on this mutex */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ @@ -674,12 +675,20 @@ struct afs_vnode { static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) { #ifdef CONFIG_AFS_FSCACHE - return vnode->cache; + return netfs_i_cookie(&vnode->vfs_inode); #else return NULL; #endif } +static inline void afs_vnode_set_cache(struct afs_vnode *vnode, + struct fscache_cookie *cookie) +{ +#ifdef CONFIG_AFS_FSCACHE + vnode->netfs_ctx.cache = cookie; +#endif +} + /* * cached security record for one user's attempt to access a vnode */ diff --git a/fs/afs/super.c b/fs/afs/super.c index 5ec9fd97eccc..e66c6f54ac8e 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -688,13 +688,11 @@ static struct inode *afs_alloc_inode(struct super_block *sb) /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); + afs_vnode_set_cache(vnode, NULL); vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; -#ifdef CONFIG_AFS_FSCACHE - vnode->cache = NULL; -#endif vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; diff --git a/fs/afs/write.c b/fs/afs/write.c index 5e9157d0da29..e4b47f67a408 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -59,8 +59,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, - &afs_req_ops, NULL); + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata); if (ret < 0) return ret; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 4aeccafa5dda..5512f448f609 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -403,7 +403,7 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) ceph_put_cap_refs(ci, got); } -static const struct netfs_request_ops ceph_netfs_read_ops = { +const struct netfs_request_ops ceph_netfs_ops = { .init_request = ceph_init_request, .begin_cache_operation = ceph_begin_cache_operation, .issue_read = ceph_netfs_issue_read, @@ -413,28 +413,6 @@ static const struct netfs_request_ops ceph_netfs_read_ops = { .cleanup = ceph_readahead_cleanup, }; -/* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *subpage) -{ - struct folio *folio = page_folio(subpage); - struct inode *inode = file_inode(file); - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_vino vino = ceph_vino(inode); - size_t len = folio_size(folio); - u64 off = folio_file_pos(folio); - - dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n inline %d", - vino.ino, vino.snap, file, off, len, folio, folio_index(folio), - ci->i_inline_version != CEPH_INLINE_NONE); - - return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); -} - -static void ceph_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &ceph_netfs_read_ops, NULL); -} - #ifdef CONFIG_CEPH_FSCACHE static void ceph_set_page_fscache(struct page *page) { @@ -1333,8 +1311,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, struct folio *folio = NULL; int r; - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, - &ceph_netfs_read_ops, NULL); + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL); if (r == 0) folio_wait_fscache(folio); if (r < 0) { @@ -1388,8 +1365,8 @@ out: } const struct address_space_operations ceph_aops = { - .readpage = ceph_readpage, - .readahead = ceph_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .writepage = ceph_writepage, .writepages = ceph_writepages_start, .write_begin = ceph_write_begin, diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 7d22850623ef..ddea99922073 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -29,26 +29,25 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) if (!(inode->i_state & I_NEW)) return; - WARN_ON_ONCE(ci->fscache); + WARN_ON_ONCE(ci->netfs_ctx.cache); - ci->fscache = fscache_acquire_cookie(fsc->fscache, 0, - &ci->i_vino, sizeof(ci->i_vino), - &ci->i_version, sizeof(ci->i_version), - i_size_read(inode)); + ci->netfs_ctx.cache = + fscache_acquire_cookie(fsc->fscache, 0, + &ci->i_vino, sizeof(ci->i_vino), + &ci->i_version, sizeof(ci->i_version), + i_size_read(inode)); } -void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci) { - struct fscache_cookie *cookie = ci->fscache; - - fscache_relinquish_cookie(cookie, false); + fscache_relinquish_cookie(ceph_fscache_cookie(ci), false); } void ceph_fscache_use_cookie(struct inode *inode, bool will_modify) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_use_cookie(ci->fscache, will_modify); + fscache_use_cookie(ceph_fscache_cookie(ci), will_modify); } void ceph_fscache_unuse_cookie(struct inode *inode, bool update) @@ -58,9 +57,10 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update) if (update) { loff_t i_size = i_size_read(inode); - fscache_unuse_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_unuse_cookie(ceph_fscache_cookie(ci), + &ci->i_version, &i_size); } else { - fscache_unuse_cookie(ci->fscache, NULL, NULL); + fscache_unuse_cookie(ceph_fscache_cookie(ci), NULL, NULL); } } @@ -69,14 +69,14 @@ void ceph_fscache_update(struct inode *inode) struct ceph_inode_info *ci = ceph_inode(inode); loff_t i_size = i_size_read(inode); - fscache_update_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_update_cookie(ceph_fscache_cookie(ci), &ci->i_version, &i_size); } void ceph_fscache_invalidate(struct inode *inode, bool dio_write) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_invalidate(ceph_inode(inode)->fscache, + fscache_invalidate(ceph_fscache_cookie(ci), &ci->i_version, i_size_read(inode), dio_write ? FSCACHE_INVAL_DIO_WRITE : 0); } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index b8b3b5cb6438..c20e43cade94 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -26,14 +26,9 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update); void ceph_fscache_update(struct inode *inode); void ceph_fscache_invalidate(struct inode *inode, bool dio_write); -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ - ci->fscache = NULL; -} - static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci) { - return ci->fscache; + return netfs_i_cookie(&ci->vfs_inode); } static inline void ceph_fscache_resize(struct inode *inode, loff_t to) @@ -91,10 +86,6 @@ static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) { } -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ -} - static inline void ceph_fscache_register_inode_cookie(struct inode *inode) { } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 7b1e93c8a0d2..6a176d9d394a 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -453,6 +453,9 @@ struct inode *ceph_alloc_inode(struct super_block *sb) dout("alloc_inode %p\n", &ci->vfs_inode); + /* Set parameters for the netfs library */ + netfs_i_context_init(&ci->vfs_inode, &ceph_netfs_ops); + spin_lock_init(&ci->i_ceph_lock); ci->i_version = 0; @@ -538,9 +541,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_WORK(&ci->i_work, ceph_inode_work); ci->i_work_mask = 0; memset(&ci->i_btime, '\0', sizeof(ci->i_btime)); - - ceph_fscache_inode_init(ci); - return &ci->vfs_inode; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 0b4b519682f1..e1c65aa8d3b6 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -17,13 +17,11 @@ #include #include #include +#include +#include #include -#ifdef CONFIG_CEPH_FSCACHE -#include -#endif - /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ @@ -317,6 +315,11 @@ struct ceph_inode_xattrs_info { * Ceph inode. */ struct ceph_inode_info { + struct { + /* These must be contiguous */ + struct inode vfs_inode; + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct ceph_vino i_vino; /* ceph ino + snap */ spinlock_t i_ceph_lock; @@ -427,11 +430,6 @@ struct ceph_inode_info { struct work_struct i_work; unsigned long i_work_mask; - -#ifdef CONFIG_CEPH_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; /* at end */ }; static inline struct ceph_inode_info * @@ -1215,6 +1213,7 @@ extern void __ceph_touch_fmode(struct ceph_inode_info *ci, /* addr.c */ extern const struct address_space_operations ceph_aops; +extern const struct netfs_request_ops ceph_netfs_ops; extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *file); extern int ceph_pool_perm_check(struct inode *inode, int need); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 48b343d03430..0a4085ced40f 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -16,6 +16,7 @@ #include #include #include +#include #include "cifs_fs_sb.h" #include "cifsacl.h" #include @@ -1402,6 +1403,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); */ struct cifsInodeInfo { + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ /* @@ -1432,10 +1438,6 @@ struct cifsInodeInfo { u64 uniqueid; /* server inode number */ u64 createtime; /* creation time on server */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for this inode */ -#ifdef CONFIG_CIFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index b47c2011ce5b..a638b29e9062 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -103,7 +103,7 @@ void cifs_fscache_get_inode_cookie(struct inode *inode) cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd); - cifsi->fscache = + cifsi->netfs_ctx.cache = fscache_acquire_cookie(tcon->fscache, 0, &cifsi->uniqueid, sizeof(cifsi->uniqueid), &cd, sizeof(cd), @@ -126,11 +126,12 @@ void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) void cifs_fscache_release_inode_cookie(struct inode *inode) { struct cifsInodeInfo *cifsi = CIFS_I(inode); + struct fscache_cookie *cookie = cifs_inode_cookie(inode); - if (cifsi->fscache) { - cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache); - fscache_relinquish_cookie(cifsi->fscache, false); - cifsi->fscache = NULL; + if (cookie) { + cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie); + fscache_relinquish_cookie(cookie, false); + cifsi->netfs_ctx.cache = NULL; } } diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 55129908e2c1..52355c0912ae 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -61,7 +61,7 @@ void cifs_fscache_fill_coherency(struct inode *inode, static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { - return CIFS_I(inode)->fscache; + return netfs_i_cookie(inode); } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 89837e904fa7..54c761bcc8e6 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -6,6 +6,7 @@ */ #include +#include #include #ifdef pr_fmt @@ -19,8 +20,6 @@ */ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct file *file, - const struct netfs_request_ops *ops, - void *netfs_priv, loff_t start, size_t len, enum netfs_io_origin origin); void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what); @@ -81,6 +80,21 @@ static inline void netfs_stat_d(atomic_t *stat) #define netfs_stat_d(x) do {} while(0) #endif +/* + * Miscellaneous functions. + */ +static inline bool netfs_is_cache_enabled(struct netfs_i_context *ctx) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cookie = ctx->cache; + + return fscache_cookie_valid(cookie) && cookie->cache_priv && + fscache_cookie_enabled(cookie); +#else + return false; +#endif +} + /*****************************************************************************/ /* * debug tracing diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index ae18827e156b..657b19e60118 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -13,12 +13,12 @@ */ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct file *file, - const struct netfs_request_ops *ops, - void *netfs_priv, loff_t start, size_t len, enum netfs_io_origin origin) { static atomic_t debug_ids; + struct inode *inode = file ? file_inode(file) : mapping->host; + struct netfs_i_context *ctx = netfs_i_context(inode); struct netfs_io_request *rreq; int ret; @@ -29,11 +29,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, rreq->start = start; rreq->len = len; rreq->origin = origin; - rreq->netfs_ops = ops; - rreq->netfs_priv = netfs_priv; + rreq->netfs_ops = ctx->ops; rreq->mapping = mapping; - rreq->inode = file_inode(file); - rreq->i_size = i_size_read(rreq->inode); + rreq->inode = inode; + rreq->i_size = i_size_read(inode); rreq->debug_id = atomic_inc_return(&debug_ids); INIT_LIST_HEAD(&rreq->subrequests); INIT_WORK(&rreq->work, netfs_rreq_work); @@ -76,6 +75,7 @@ static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + netfs_clear_subrequests(rreq, false); if (rreq->netfs_priv) rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index b5176f4320f4..c048cd328ce5 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -14,7 +14,6 @@ #include #include #include -#include #include "internal.h" #define CREATE_TRACE_POINTS #include @@ -735,8 +734,6 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, /** * netfs_readahead - Helper to manage a read request * @ractl: The description of the readahead request - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request * * Fulfil a readahead request by drawing data from the cache if possible, or * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O @@ -744,35 +741,32 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, * readahead window can be expanded in either direction to a more convenient * alighment for RPC efficiency or to make storage in the cache feasible. * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. * * This is usable whether or not caching is enabled. */ -void netfs_readahead(struct readahead_control *ractl, - const struct netfs_request_ops *ops, - void *netfs_priv) +void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host); unsigned int debug_index = 0; int ret; _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); if (readahead_count(ractl) == 0) - goto cleanup; + return; rreq = netfs_alloc_request(ractl->mapping, ractl->file, - ops, netfs_priv, readahead_pos(ractl), readahead_length(ractl), NETFS_READAHEAD); if (IS_ERR(rreq)) - goto cleanup; + return; - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; } @@ -804,42 +798,35 @@ void netfs_readahead(struct readahead_control *ractl, cleanup_free: netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); return; -cleanup: - if (netfs_priv) - ops->cleanup(ractl->mapping, netfs_priv); - return; } EXPORT_SYMBOL(netfs_readahead); /** * netfs_readpage - Helper to manage a readpage request * @file: The file to read from - * @folio: The folio to read - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request + * @subpage: A subpage of the folio to read * * Fulfil a readpage request by drawing data from the cache if possible, or the * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests * from different sources will get munged together. * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. * * This is usable whether or not caching is enabled. */ -int netfs_readpage(struct file *file, - struct folio *folio, - const struct netfs_request_ops *ops, - void *netfs_priv) +int netfs_readpage(struct file *file, struct page *subpage) { + struct folio *folio = page_folio(subpage); + struct address_space *mapping = folio->mapping; struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(mapping->host); unsigned int debug_index = 0; int ret; _enter("%lx", folio_index(folio)); - rreq = netfs_alloc_request(folio->mapping, file, ops, netfs_priv, + rreq = netfs_alloc_request(mapping, file, folio_file_pos(folio), folio_size(folio), NETFS_READPAGE); if (IS_ERR(rreq)) { @@ -847,8 +834,8 @@ int netfs_readpage(struct file *file, goto alloc_error; } - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { folio_unlock(folio); goto out; @@ -886,8 +873,6 @@ out: netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); return ret; alloc_error: - if (netfs_priv) - ops->cleanup(folio_file_mapping(folio), netfs_priv); folio_unlock(folio); return ret; } @@ -898,6 +883,7 @@ EXPORT_SYMBOL(netfs_readpage); * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write + * @always_fill: T if the folio should always be completely filled/cleared * * In some cases, write_begin doesn't need to read at all: * - full folio write @@ -907,17 +893,27 @@ EXPORT_SYMBOL(netfs_readpage); * If any of these criteria are met, then zero out the unwritten parts * of the folio and return true. Otherwise, return false. */ -static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, + bool always_fill) { struct inode *inode = folio_inode(folio); loff_t i_size = i_size_read(inode); size_t offset = offset_in_folio(folio, pos); + size_t plen = folio_size(folio); + + if (unlikely(always_fill)) { + if (pos - offset + len <= i_size) + return false; /* Page entirely before EOF */ + zero_user_segment(&folio->page, 0, plen); + folio_mark_uptodate(folio); + return true; + } /* Full folio write */ - if (offset == 0 && len >= folio_size(folio)) + if (offset == 0 && len >= plen) return true; - /* pos beyond last folio in the file */ + /* Page entirely beyond the end of the file */ if (pos - offset >= i_size) goto zero_out; @@ -927,7 +923,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) return false; zero_out: - zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); + zero_user_segments(&folio->page, 0, offset, offset + len, plen); return true; } @@ -940,8 +936,6 @@ zero_out: * @aop_flags: AOP_* flags * @_folio: Where to put the resultant folio * @_fsdata: Place for the netfs to store a cookie - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request * * Pre-read data for a write-begin request by drawing data from the cache if * possible, or the netfs if not. Space beyond the EOF is zero-filled. @@ -960,17 +954,18 @@ zero_out: * should go ahead; unlock the folio and return -EAGAIN to cause the folio to * be regot; or return an error. * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * * This is usable whether or not caching is enabled. */ int netfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int aop_flags, - struct folio **_folio, void **_fsdata, - const struct netfs_request_ops *ops, - void *netfs_priv) + struct folio **_folio, void **_fsdata) { struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); struct folio *folio; - struct inode *inode = file_inode(file); unsigned int debug_index = 0, fgp_flags; pgoff_t index = pos >> PAGE_SHIFT; int ret; @@ -986,9 +981,9 @@ retry: if (!folio) return -ENOMEM; - if (ops->check_write_begin) { + if (ctx->ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, folio, _fsdata); + ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); if (ret < 0) { trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); if (ret == -EAGAIN) @@ -1004,13 +999,13 @@ retry: * within the cache granule containing the EOF, in which case we need * to preload the granule. */ - if (!ops->is_cache_enabled(inode) && - netfs_skip_folio_read(folio, pos, len)) { + if (!netfs_is_cache_enabled(ctx) && + netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); goto have_folio_no_wait; } - rreq = netfs_alloc_request(mapping, file, ops, netfs_priv, + rreq = netfs_alloc_request(mapping, file, folio_file_pos(folio), folio_size(folio), NETFS_READ_FOR_WRITE); if (IS_ERR(rreq)) { @@ -1019,10 +1014,9 @@ retry: } rreq->no_unlock_folio = folio_index(folio); __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); - netfs_priv = NULL; - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto error_put; } @@ -1076,8 +1070,6 @@ have_folio: if (ret < 0) goto error; have_folio_no_wait: - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); *_folio = folio; _leave(" = 0"); return 0; @@ -1087,8 +1079,6 @@ error_put: error: folio_unlock(folio); folio_put(folio); - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); _leave(" = %d", ret); return ret; } diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 9ae538c85378..5510a7a14a40 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -7,7 +7,6 @@ #include #include -#include #include "internal.h" atomic_t netfs_n_rh_readahead; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 4b99e38f73d9..8458b30172a5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -118,6 +118,16 @@ enum netfs_io_source { typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); +/* + * Per-inode description. This must be directly after the inode struct. + */ +struct netfs_i_context { + const struct netfs_request_ops *ops; +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cache; +#endif +}; + /* * Resources required to do operations on a cache. */ @@ -192,7 +202,6 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - bool (*is_cache_enabled)(struct inode *inode); int (*init_request)(struct netfs_io_request *rreq, struct file *file); int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); @@ -263,18 +272,11 @@ struct netfs_cache_ops { }; struct readahead_control; -extern void netfs_readahead(struct readahead_control *, - const struct netfs_request_ops *, - void *); -extern int netfs_readpage(struct file *, - struct folio *, - const struct netfs_request_ops *, - void *); +extern void netfs_readahead(struct readahead_control *); +extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, unsigned int, struct folio **, - void **, - const struct netfs_request_ops *, - void *); + void **); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq, @@ -283,4 +285,61 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); extern void netfs_stats_show(struct seq_file *); +/** + * netfs_i_context - Get the netfs inode context from the inode + * @inode: The inode to query + * + * Get the netfs lib inode context from the network filesystem's inode. The + * context struct is expected to directly follow on from the VFS inode struct. + */ +static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +{ + return (struct netfs_i_context *)(inode + 1); +} + +/** + * netfs_inode - Get the netfs inode from the inode context + * @ctx: The context to query + * + * Get the netfs inode from the netfs library's inode context. The VFS inode + * is expected to directly precede the context struct. + */ +static inline struct inode *netfs_inode(struct netfs_i_context *ctx) +{ + return ((struct inode *)ctx) - 1; +} + +/** + * netfs_i_context_init - Initialise a netfs lib context + * @inode: The inode with which the context is associated + * @ops: The netfs's operations list + * + * Initialise the netfs library context struct. This is expected to follow on + * directly from the VFS inode struct. + */ +static inline void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + memset(ctx, 0, sizeof(*ctx)); + ctx->ops = ops; +} + +/** + * netfs_i_cookie - Get the cache cookie from the inode + * @inode: The inode to query + * + * Get the caching cookie (if enabled) from the network filesystem's inode. + */ +static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct netfs_i_context *ctx = netfs_i_context(inode); + return ctx->cache; +#else + return NULL; +#endif +} + #endif /* _LINUX_NETFS_H */ -- cgit v1.2.3 From 3be01750d7ac5803ad6fa76801d4d80b3814229f Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 7 Mar 2022 21:57:24 +0000 Subject: netfs: Rename read_helper.c to io.c Rename the read_helper.c file to io.c before splitting out the buffered read functions and some other bits. Changes ======= ver #2) - Rename read_helper.c before splitting. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164678216109.1200972.16567696909952495832.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692918076.2099075.8120961172717347610.stgit@warthog.procyon.org.uk/ # v3 --- Documentation/filesystems/netfs_library.rst | 3 +- fs/netfs/Makefile | 4 +- fs/netfs/internal.h | 14 +- fs/netfs/io.c | 1085 +++++++++++++++++++++++++++ fs/netfs/read_helper.c | 1085 --------------------------- 5 files changed, 1096 insertions(+), 1095 deletions(-) create mode 100644 fs/netfs/io.c delete mode 100644 fs/netfs/read_helper.c (limited to 'Documentation/filesystems') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 9c8bc5666b46..69f00179fdfe 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -605,4 +605,5 @@ API Function Reference ====================== .. kernel-doc:: include/linux/netfs.h -.. kernel-doc:: fs/netfs/read_helper.c +.. kernel-doc:: fs/netfs/buffered_read.c +.. kernel-doc:: fs/netfs/io.c diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index 939fd00a1fc9..51ece4f7bc77 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 netfs-y := \ - objects.o \ - read_helper.o + io.o \ + objects.o netfs-$(CONFIG_NETFS_STATS) += stats.o diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 7bf94a3beb98..05c4b2fe1965 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -20,6 +20,13 @@ */ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); +/* + * io.c + */ +extern unsigned int netfs_debug; + +int netfs_begin_read(struct netfs_io_request *rreq, bool sync); + /* * objects.c */ @@ -39,13 +46,6 @@ static inline void netfs_see_request(struct netfs_io_request *rreq, trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); } -/* - * read_helper.c - */ -extern unsigned int netfs_debug; - -int netfs_begin_read(struct netfs_io_request *rreq, bool sync); - /* * stats.c */ diff --git a/fs/netfs/io.c b/fs/netfs/io.c new file mode 100644 index 000000000000..80a106b46051 --- /dev/null +++ b/fs/netfs/io.c @@ -0,0 +1,1085 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" +#define CREATE_TRACE_POINTS +#include + +MODULE_DESCRIPTION("Network fs support"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned netfs_debug; +module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_io_subrequest *subreq) +{ + struct iov_iter iter; + + iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + iov_iter_zero(iov_iter_count(&iter), &iter); +} + +static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + + netfs_subreq_terminated(subreq, transferred_or_error, was_async); +} + +/* + * Issue a read against the cache. + * - Eats the caller's ref on subreq. + */ +static void netfs_read_from_cache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + enum netfs_read_from_hole read_hole) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct iov_iter iter; + + netfs_stat(&netfs_n_rh_read); + iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + + cres->ops->read(cres, subreq->start, &iter, read_hole, + netfs_cache_read_terminated, subreq); +} + +/* + * Fill a subrequest region with zeroes. + */ +static void netfs_fill_with_zeroes(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_zero); + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_subreq_terminated(subreq, 0, false); +} + +/* + * Ask the netfs to issue a read request to the server for us. + * + * The netfs is expected to read from subreq->pos + subreq->transferred to + * subreq->pos + subreq->len - 1. It may not backtrack and write data into the + * buffer prior to the transferred point as it might clobber dirty data + * obtained from the cache. + * + * Alternatively, the netfs is allowed to indicate one of two things: + * + * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and + * make progress. + * + * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be + * cleared. + */ +static void netfs_read_from_server(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_download); + rreq->netfs_ops->issue_read(subreq); +} + +/* + * Release those waiting. + */ +static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_done); + netfs_clear_subrequests(rreq, was_async); + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); +} + +/* + * Deal with the completion of writing the data to the cache. We have to clear + * the PG_fscache bits on the folios involved and release the caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio_index(folio) <= unlocked) + continue; + unlocked = folio_index(folio); + folio_end_fscache(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * Perform any outstanding writes to the cache. We inherit a ref from the + * caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + +/* + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + unsigned int iopos, account = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { + __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + } + } + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + iopos = 0; + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + folio_start_fscache(folio); + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + account += subreq->transferred; + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); + + task_io_account_read(account); + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +/* + * Handle a short read. + */ +static void netfs_rreq_short_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); + + netfs_stat(&netfs_n_rh_short_read); + trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_short_read); + atomic_inc(&rreq->nr_outstanding); + if (subreq->source == NETFS_READ_FROM_CACHE) + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); + else + netfs_read_from_server(rreq, subreq); +} + +/* + * Resubmit any short or failed operations. Returns true if we got the rreq + * ref back. + */ +static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + WARN_ON(in_interrupt()); + + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + + /* We don't want terminating submissions trying to wake us up whilst + * we're still going through the list. + */ + atomic_inc(&rreq->nr_outstanding); + + __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->error) { + if (subreq->source != NETFS_READ_FROM_CACHE) + break; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->error = 0; + netfs_stat(&netfs_n_rh_download_instead); + trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + atomic_inc(&rreq->nr_outstanding); + netfs_read_from_server(rreq, subreq); + } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { + netfs_rreq_short_read(rreq, subreq); + } + } + + /* If we decrement nr_outstanding to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + return true; + + wake_up_var(&rreq->nr_outstanding); + return false; +} + +/* + * Check to see if the data read is still valid. + */ +static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + if (!rreq->netfs_ops->is_still_valid || + rreq->netfs_ops->is_still_valid(rreq)) + return; + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->source == NETFS_READ_FROM_CACHE) { + subreq->error = -ESTALE; + __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } + } +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we could be in an ordinary kernel thread, on a workqueue or in + * softirq context at this point. We inherit a ref from the caller. + */ +static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + +again: + netfs_rreq_is_still_valid(rreq); + + if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && + test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { + if (netfs_rreq_perform_resubmissions(rreq)) + goto again; + return; + } + + netfs_rreq_unlock_folios(rreq); + + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + netfs_rreq_assess(rreq, false); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +static void netfs_rreq_terminated(struct netfs_io_request *rreq, + bool was_async) +{ + if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && + was_async) { + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_rreq_assess(rreq, was_async); + } +} + +/** + * netfs_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @transferred_or_error: The amount of data transferred or an error code. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates in @transferred_or_error the outcome of the operation, + * supplying a positive value to indicate the number of bytes transferred, 0 to + * indicate a failure to transfer anything that should be retried or a negative + * error code. The helper will look after reissuing I/O operations as + * appropriate and writing downloaded data to the cache. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, + ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + int u; + + _enter("[%u]{%llx,%lx},%zd", + subreq->debug_index, subreq->start, subreq->flags, + transferred_or_error); + + switch (subreq->source) { + case NETFS_READ_FROM_CACHE: + netfs_stat(&netfs_n_rh_read_done); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download_done); + break; + default: + break; + } + + if (IS_ERR_VALUE(transferred_or_error)) { + subreq->error = transferred_or_error; + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_read); + goto failed; + } + + if (WARN(transferred_or_error > subreq->len - subreq->transferred, + "Subreq overread: R%x[%x] %zd > %zu - %zu", + rreq->debug_id, subreq->debug_index, + transferred_or_error, subreq->len, subreq->transferred)) + transferred_or_error = subreq->len - subreq->transferred; + + subreq->error = 0; + subreq->transferred += transferred_or_error; + if (subreq->transferred < subreq->len) + goto incomplete; + +complete: + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + +out: + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + u = atomic_dec_return(&rreq->nr_outstanding); + if (u == 0) + netfs_rreq_terminated(rreq, was_async); + else if (u == 1) + wake_up_var(&rreq->nr_outstanding); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); + return; + +incomplete: + if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + goto complete; + } + + if (transferred_or_error == 0) { + if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + subreq->error = -ENODATA; + goto failed; + } + } else { + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + + __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + goto out; + +failed: + if (subreq->source == NETFS_READ_FROM_CACHE) { + netfs_stat(&netfs_n_rh_read_failed); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } else { + netfs_stat(&netfs_n_rh_download_failed); + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + goto out; +} +EXPORT_SYMBOL(netfs_subreq_terminated); + +static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest *subreq, + loff_t i_size) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops) + return cres->ops->prepare_read(subreq, i_size); + if (subreq->start >= rreq->i_size) + return NETFS_FILL_WITH_ZEROES; + return NETFS_DOWNLOAD_FROM_SERVER; +} + +/* + * Work out what sort of subrequest the next one will be. + */ +static enum netfs_io_source +netfs_rreq_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + enum netfs_io_source source; + + _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); + + source = netfs_cache_prepare_read(subreq, rreq->i_size); + if (source == NETFS_INVALID_READ) + goto out; + + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + /* Call out to the netfs to let it shrink the request to fit + * its own I/O sizes and boundaries. If it shinks it here, it + * will be called again to make simultaneous calls; if it wants + * to make serial calls, it can indicate a short read and then + * we will call it again. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; + + if (rreq->netfs_ops->clamp_length && + !rreq->netfs_ops->clamp_length(subreq)) { + source = NETFS_INVALID_READ; + goto out; + } + } + + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + +out: + subreq->source = source; + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + return source; +} + +/* + * Slice off a piece of a read request and submit an I/O request for it. + */ +static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, + unsigned int *_debug_index) +{ + struct netfs_io_subrequest *subreq; + enum netfs_io_source source; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return false; + + subreq->debug_index = (*_debug_index)++; + subreq->start = rreq->start + rreq->submitted; + subreq->len = rreq->len - rreq->submitted; + + _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + /* Call out to the cache to find out what it can do with the remaining + * subset. It tells us in subreq->flags what it decided should be done + * and adjusts subreq->len down if the subset crosses a cache boundary. + * + * Then when we hand the subset, it can choose to take a subset of that + * (the starts must coincide), in which case, we go around the loop + * again and ask it to download the next piece. + */ + source = netfs_rreq_prepare_read(rreq, subreq); + if (source == NETFS_INVALID_READ) + goto subreq_failed; + + atomic_inc(&rreq->nr_outstanding); + + rreq->submitted += subreq->len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + switch (source) { + case NETFS_FILL_WITH_ZEROES: + netfs_fill_with_zeroes(rreq, subreq); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_read_from_server(rreq, subreq); + break; + case NETFS_READ_FROM_CACHE: + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); + break; + default: + BUG(); + } + + return true; + +subreq_failed: + rreq->error = subreq->error; + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_failed); + return false; +} + +/* + * Begin the process of reading in a chunk of data, where that data may be + * stitched together from multiple sources, including multiple servers and the + * local cache. + */ +int netfs_begin_read(struct netfs_io_request *rreq, bool sync) +{ + unsigned int debug_index = 0; + int ret; + + _enter("R=%x %llx-%llx", + rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); + + if (rreq->len == 0) { + pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); + netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len); + return -EIO; + } + + INIT_WORK(&rreq->work, netfs_rreq_work); + + if (sync) + netfs_get_request(rreq, netfs_rreq_trace_get_hold); + + /* Chop the read into slices according to what the cache and the netfs + * want and submit each one. + */ + atomic_set(&rreq->nr_outstanding, 1); + do { + if (!netfs_rreq_submit_slice(rreq, &debug_index)) + break; + + } while (rreq->submitted < rreq->len); + + if (sync) { + /* Keep nr_outstanding incremented so that the ref always belongs to + * us, and the service code isn't punted off to a random thread pool to + * process. + */ + for (;;) { + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); + netfs_rreq_assess(rreq, false); + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + break; + cond_resched(); + } + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); + } else { + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_assess(rreq, false); + ret = 0; + } + return ret; +} + +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + loff_t *_start, size_t *_len, loff_t i_size) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} + +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. + */ + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); + + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} + +/** + * netfs_readahead - Helper to manage a read request + * @ractl: The description of the readahead request + * + * Fulfil a readahead request by drawing data from the cache if possible, or + * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O + * requests from different sources will get munged together. If necessary, the + * readahead window can be expanded in either direction to a more convenient + * alighment for RPC efficiency or to make storage in the cache feasible. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +void netfs_readahead(struct readahead_control *ractl) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host); + int ret; + + _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); + + if (readahead_count(ractl) == 0) + return; + + rreq = netfs_alloc_request(ractl->mapping, ractl->file, + readahead_pos(ractl), + readahead_length(ractl), + NETFS_READAHEAD); + if (IS_ERR(rreq)) + return; + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + } + + netfs_stat(&netfs_n_rh_readahead); + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_readahead); + + netfs_rreq_expand(rreq, ractl); + + /* Drop the refs on the folios here rather than in the cache or + * filesystem. The locks will be dropped in netfs_rreq_unlock(). + */ + while (readahead_folio(ractl)) + ; + + netfs_begin_read(rreq, false); + return; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return; +} +EXPORT_SYMBOL(netfs_readahead); + +/** + * netfs_readpage - Helper to manage a readpage request + * @file: The file to read from + * @subpage: A subpage of the folio to read + * + * Fulfil a readpage request by drawing data from the cache if possible, or the + * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests + * from different sources will get munged together. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_readpage(struct file *file, struct page *subpage) +{ + struct folio *folio = page_folio(subpage); + struct address_space *mapping = folio->mapping; + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(mapping->host); + int ret; + + _enter("%lx", folio_index(folio)); + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READPAGE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + } + + netfs_stat(&netfs_n_rh_readpage); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); + return netfs_begin_read(rreq, true); + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} +EXPORT_SYMBOL(netfs_readpage); + +/* + * Prepare a folio for writing without reading first + * @folio: The folio being prepared + * @pos: starting position for the write + * @len: length of write + * @always_fill: T if the folio should always be completely filled/cleared + * + * In some cases, write_begin doesn't need to read at all: + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the folio and return true. Otherwise, return false. + */ +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, + bool always_fill) +{ + struct inode *inode = folio_inode(folio); + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_folio(folio, pos); + size_t plen = folio_size(folio); + + if (unlikely(always_fill)) { + if (pos - offset + len <= i_size) + return false; /* Page entirely before EOF */ + zero_user_segment(&folio->page, 0, plen); + folio_mark_uptodate(folio); + return true; + } + + /* Full folio write */ + if (offset == 0 && len >= plen) + return true; + + /* Page entirely beyond the end of the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* Write that covers from the start of the folio to EOF or beyond */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(&folio->page, 0, offset, offset + len, plen); + return true; +} + +/** + * netfs_write_begin - Helper to prepare for writing + * @file: The file to read from + * @mapping: The mapping to read from + * @pos: File position at which the write will begin + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio + * @_fsdata: Place for the netfs to store a cookie + * + * Pre-read data for a write-begin request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. If + * necessary, the readahead window can be expanded in either direction to a + * more convenient alighment for RPC efficiency or to make storage in the cache + * feasible. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. + * + * The check_write_begin() operation can be provided to check for and flush + * conflicting writes once the folio is grabbed and locked. It is passed a + * pointer to the fsdata cookie that gets returned to the VM to be passed to + * write_end. It is permitted to sleep. It should return 0 if the request + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); + struct folio *folio; + unsigned int fgp_flags; + pgoff_t index = pos >> PAGE_SHIFT; + int ret; + + DEFINE_READAHEAD(ractl, file, NULL, mapping, index); + +retry: + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) + return -ENOMEM; + + if (ctx->ops->check_write_begin) { + /* Allow the netfs (eg. ceph) to flush conflicts. */ + ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); + if (ret < 0) { + trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); + if (ret == -EAGAIN) + goto retry; + goto error; + } + } + + if (folio_test_uptodate(folio)) + goto have_folio; + + /* If the page is beyond the EOF, we want to clear it - unless it's + * within the cache granule containing the EOF, in which case we need + * to preload the granule. + */ + if (!netfs_is_cache_enabled(ctx) && + netfs_skip_folio_read(folio, pos, len, false)) { + netfs_stat(&netfs_n_rh_write_zskip); + goto have_folio_no_wait; + } + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READ_FOR_WRITE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto error; + } + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; + } + + netfs_stat(&netfs_n_rh_write_begin); + trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); + + /* Expand the request to meet caching requirements and download + * preferences. + */ + ractl._nr_pages = folio_nr_pages(folio); + netfs_rreq_expand(rreq, &ractl); + + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; + + ret = netfs_begin_read(rreq, true); + if (ret < 0) + goto error; + +have_folio: + ret = folio_wait_fscache_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: + *_folio = folio; + _leave(" = 0"); + return 0; + +error_put: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); +error: + folio_unlock(folio); + folio_put(folio); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_write_begin); diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c deleted file mode 100644 index 80a106b46051..000000000000 --- a/fs/netfs/read_helper.c +++ /dev/null @@ -1,1085 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Network filesystem high-level read support. - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "internal.h" -#define CREATE_TRACE_POINTS -#include - -MODULE_DESCRIPTION("Network fs support"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - -unsigned netfs_debug; -module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); - -/* - * Clear the unread part of an I/O request. - */ -static void netfs_clear_unread(struct netfs_io_subrequest *subreq) -{ - struct iov_iter iter; - - iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - iov_iter_zero(iov_iter_count(&iter), &iter); -} - -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_subrequest *subreq = priv; - - netfs_subreq_terminated(subreq, transferred_or_error, was_async); -} - -/* - * Issue a read against the cache. - * - Eats the caller's ref on subreq. - */ -static void netfs_read_from_cache(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq, - enum netfs_read_from_hole read_hole) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct iov_iter iter; - - netfs_stat(&netfs_n_rh_read); - iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - - cres->ops->read(cres, subreq->start, &iter, read_hole, - netfs_cache_read_terminated, subreq); -} - -/* - * Fill a subrequest region with zeroes. - */ -static void netfs_fill_with_zeroes(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_zero); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, 0, false); -} - -/* - * Ask the netfs to issue a read request to the server for us. - * - * The netfs is expected to read from subreq->pos + subreq->transferred to - * subreq->pos + subreq->len - 1. It may not backtrack and write data into the - * buffer prior to the transferred point as it might clobber dirty data - * obtained from the cache. - * - * Alternatively, the netfs is allowed to indicate one of two things: - * - * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and - * make progress. - * - * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be - * cleared. - */ -static void netfs_read_from_server(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_download); - rreq->netfs_ops->issue_read(subreq); -} - -/* - * Release those waiting. - */ -static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_done); - netfs_clear_subrequests(rreq, was_async); - netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); -} - -/* - * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the folios involved and release the caller's ref. - * - * May be called in softirq mode and we inherit a ref from the caller. - */ -static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, - bool was_async) -{ - struct netfs_io_subrequest *subreq; - struct folio *folio; - pgoff_t unlocked = 0; - bool have_unlocked = false; - - rcu_read_lock(); - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - - xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { - /* We might have multiple writes from the same huge - * folio, but we mustn't unlock a folio more than once. - */ - if (have_unlocked && folio_index(folio) <= unlocked) - continue; - unlocked = folio_index(folio); - folio_end_fscache(folio); - have_unlocked = true; - } - } - - rcu_read_unlock(); - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_subrequest *subreq = priv; - struct netfs_io_request *rreq = subreq->rreq; - - if (IS_ERR_VALUE(transferred_or_error)) { - netfs_stat(&netfs_n_rh_write_failed); - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_copy_to_cache); - } else { - netfs_stat(&netfs_n_rh_write_done); - } - - trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); - - /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_copy_ops)) - netfs_rreq_unmark_after_write(rreq, was_async); - - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); -} - -/* - * Perform any outstanding writes to the cache. We inherit a ref from the - * caller. - */ -static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct netfs_io_subrequest *subreq, *next, *p; - struct iov_iter iter; - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_copy); - - /* We don't want terminating writes trying to wake us up whilst we're - * still going through the list. - */ - atomic_inc(&rreq->nr_copy_ops); - - list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { - list_del_init(&subreq->rreq_link); - netfs_put_subrequest(subreq, false, - netfs_sreq_trace_put_no_copy); - } - } - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - /* Amalgamate adjacent writes */ - while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - next = list_next_entry(subreq, rreq_link); - if (next->start != subreq->start + subreq->len) - break; - subreq->len += next->len; - list_del_init(&next->rreq_link); - netfs_put_subrequest(next, false, - netfs_sreq_trace_put_merged); - } - - ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size, true); - if (ret < 0) { - trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); - trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); - continue; - } - - iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, - subreq->start, subreq->len); - - atomic_inc(&rreq->nr_copy_ops); - netfs_stat(&netfs_n_rh_write); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); - trace_netfs_sreq(subreq, netfs_sreq_trace_write); - cres->ops->write(cres, subreq->start, &iter, - netfs_rreq_copy_terminated, subreq); - } - - /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_copy_ops)) - netfs_rreq_unmark_after_write(rreq, false); -} - -static void netfs_rreq_write_to_cache_work(struct work_struct *work) -{ - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); - - netfs_rreq_do_write_to_cache(rreq); -} - -static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) -{ - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); -} - -/* - * Unlock the folios in a read operation. We need to set PG_fscache on any - * folios we're going to write back before we unlock them. - */ -void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - struct folio *folio; - unsigned int iopos, account = 0; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - bool subreq_failed = false; - - XA_STATE(xas, &rreq->mapping->i_pages, start_page); - - if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } - } - - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. - */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_io_subrequest, rreq_link); - iopos = 0; - subreq_failed = (subreq->error < 0); - - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); - - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + folio_size(folio); - bool pg_failed = false; - - for (;;) { - if (!subreq) { - pg_failed = true; - break; - } - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) - folio_start_fscache(folio); - pg_failed |= subreq_failed; - if (pgend < iopos + subreq->len) - break; - - account += subreq->transferred; - iopos += subreq->len; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; - } - if (pgend == iopos) - break; - } - - if (!pg_failed) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } - - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio_index(folio) == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); - } - } - rcu_read_unlock(); - - task_io_account_read(account); - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); -} - -/* - * Handle a short read. - */ -static void netfs_rreq_short_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); - __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); - - netfs_stat(&netfs_n_rh_short_read); - trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); - - netfs_get_subrequest(subreq, netfs_sreq_trace_get_short_read); - atomic_inc(&rreq->nr_outstanding); - if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); - else - netfs_read_from_server(rreq, subreq); -} - -/* - * Resubmit any short or failed operations. Returns true if we got the rreq - * ref back. - */ -static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - - WARN_ON(in_interrupt()); - - trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); - - /* We don't want terminating submissions trying to wake us up whilst - * we're still going through the list. - */ - atomic_inc(&rreq->nr_outstanding); - - __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->error) { - if (subreq->source != NETFS_READ_FROM_CACHE) - break; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->error = 0; - netfs_stat(&netfs_n_rh_download_instead); - trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - atomic_inc(&rreq->nr_outstanding); - netfs_read_from_server(rreq, subreq); - } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { - netfs_rreq_short_read(rreq, subreq); - } - } - - /* If we decrement nr_outstanding to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_outstanding)) - return true; - - wake_up_var(&rreq->nr_outstanding); - return false; -} - -/* - * Check to see if the data read is still valid. - */ -static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) -{ - struct netfs_io_subrequest *subreq; - - if (!rreq->netfs_ops->is_still_valid || - rreq->netfs_ops->is_still_valid(rreq)) - return; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->source == NETFS_READ_FROM_CACHE) { - subreq->error = -ESTALE; - __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } - } -} - -/* - * Assess the state of a read request and decide what to do next. - * - * Note that we could be in an ordinary kernel thread, on a workqueue or in - * softirq context at this point. We inherit a ref from the caller. - */ -static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); - -again: - netfs_rreq_is_still_valid(rreq); - - if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && - test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { - if (netfs_rreq_perform_resubmissions(rreq)) - goto again; - return; - } - - netfs_rreq_unlock_folios(rreq); - - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); - - if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq); - - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_work(struct work_struct *work) -{ - struct netfs_io_request *rreq = - container_of(work, struct netfs_io_request, work); - netfs_rreq_assess(rreq, false); -} - -/* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. - */ -static void netfs_rreq_terminated(struct netfs_io_request *rreq, - bool was_async) -{ - if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && - was_async) { - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_assess(rreq, was_async); - } -} - -/** - * netfs_subreq_terminated - Note the termination of an I/O operation. - * @subreq: The I/O request that has terminated. - * @transferred_or_error: The amount of data transferred or an error code. - * @was_async: The termination was asynchronous - * - * This tells the read helper that a contributory I/O operation has terminated, - * one way or another, and that it should integrate the results. - * - * The caller indicates in @transferred_or_error the outcome of the operation, - * supplying a positive value to indicate the number of bytes transferred, 0 to - * indicate a failure to transfer anything that should be retried or a negative - * error code. The helper will look after reissuing I/O operations as - * appropriate and writing downloaded data to the cache. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. - */ -void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, - ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_io_request *rreq = subreq->rreq; - int u; - - _enter("[%u]{%llx,%lx},%zd", - subreq->debug_index, subreq->start, subreq->flags, - transferred_or_error); - - switch (subreq->source) { - case NETFS_READ_FROM_CACHE: - netfs_stat(&netfs_n_rh_read_done); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_stat(&netfs_n_rh_download_done); - break; - default: - break; - } - - if (IS_ERR_VALUE(transferred_or_error)) { - subreq->error = transferred_or_error; - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_read); - goto failed; - } - - if (WARN(transferred_or_error > subreq->len - subreq->transferred, - "Subreq overread: R%x[%x] %zd > %zu - %zu", - rreq->debug_id, subreq->debug_index, - transferred_or_error, subreq->len, subreq->transferred)) - transferred_or_error = subreq->len - subreq->transferred; - - subreq->error = 0; - subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) - goto incomplete; - -complete: - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) - set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); - -out: - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - /* If we decrement nr_outstanding to 0, the ref belongs to us. */ - u = atomic_dec_return(&rreq->nr_outstanding); - if (u == 0) - netfs_rreq_terminated(rreq, was_async); - else if (u == 1) - wake_up_var(&rreq->nr_outstanding); - - netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); - return; - -incomplete: - if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - goto complete; - } - - if (transferred_or_error == 0) { - if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; - goto failed; - } - } else { - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - - __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - goto out; - -failed: - if (subreq->source == NETFS_READ_FROM_CACHE) { - netfs_stat(&netfs_n_rh_read_failed); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } else { - netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; - } - goto out; -} -EXPORT_SYMBOL(netfs_subreq_terminated); - -static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest *subreq, - loff_t i_size) -{ - struct netfs_io_request *rreq = subreq->rreq; - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops) - return cres->ops->prepare_read(subreq, i_size); - if (subreq->start >= rreq->i_size) - return NETFS_FILL_WITH_ZEROES; - return NETFS_DOWNLOAD_FROM_SERVER; -} - -/* - * Work out what sort of subrequest the next one will be. - */ -static enum netfs_io_source -netfs_rreq_prepare_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) -{ - enum netfs_io_source source; - - _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); - - source = netfs_cache_prepare_read(subreq, rreq->i_size); - if (source == NETFS_INVALID_READ) - goto out; - - if (source == NETFS_DOWNLOAD_FROM_SERVER) { - /* Call out to the netfs to let it shrink the request to fit - * its own I/O sizes and boundaries. If it shinks it here, it - * will be called again to make simultaneous calls; if it wants - * to make serial calls, it can indicate a short read and then - * we will call it again. - */ - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; - - if (rreq->netfs_ops->clamp_length && - !rreq->netfs_ops->clamp_length(subreq)) { - source = NETFS_INVALID_READ; - goto out; - } - } - - if (WARN_ON(subreq->len == 0)) - source = NETFS_INVALID_READ; - -out: - subreq->source = source; - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - return source; -} - -/* - * Slice off a piece of a read request and submit an I/O request for it. - */ -static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, - unsigned int *_debug_index) -{ - struct netfs_io_subrequest *subreq; - enum netfs_io_source source; - - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - return false; - - subreq->debug_index = (*_debug_index)++; - subreq->start = rreq->start + rreq->submitted; - subreq->len = rreq->len - rreq->submitted; - - _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - - /* Call out to the cache to find out what it can do with the remaining - * subset. It tells us in subreq->flags what it decided should be done - * and adjusts subreq->len down if the subset crosses a cache boundary. - * - * Then when we hand the subset, it can choose to take a subset of that - * (the starts must coincide), in which case, we go around the loop - * again and ask it to download the next piece. - */ - source = netfs_rreq_prepare_read(rreq, subreq); - if (source == NETFS_INVALID_READ) - goto subreq_failed; - - atomic_inc(&rreq->nr_outstanding); - - rreq->submitted += subreq->len; - - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - switch (source) { - case NETFS_FILL_WITH_ZEROES: - netfs_fill_with_zeroes(rreq, subreq); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_read_from_server(rreq, subreq); - break; - case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); - break; - default: - BUG(); - } - - return true; - -subreq_failed: - rreq->error = subreq->error; - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_failed); - return false; -} - -/* - * Begin the process of reading in a chunk of data, where that data may be - * stitched together from multiple sources, including multiple servers and the - * local cache. - */ -int netfs_begin_read(struct netfs_io_request *rreq, bool sync) -{ - unsigned int debug_index = 0; - int ret; - - _enter("R=%x %llx-%llx", - rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); - - if (rreq->len == 0) { - pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); - netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len); - return -EIO; - } - - INIT_WORK(&rreq->work, netfs_rreq_work); - - if (sync) - netfs_get_request(rreq, netfs_rreq_trace_get_hold); - - /* Chop the read into slices according to what the cache and the netfs - * want and submit each one. - */ - atomic_set(&rreq->nr_outstanding, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - if (sync) { - /* Keep nr_outstanding incremented so that the ref always belongs to - * us, and the service code isn't punted off to a random thread pool to - * process. - */ - for (;;) { - wait_var_event(&rreq->nr_outstanding, - atomic_read(&rreq->nr_outstanding) == 1); - netfs_rreq_assess(rreq, false); - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) - break; - cond_resched(); - } - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; - } - netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); - } else { - /* If we decrement nr_outstanding to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_outstanding)) - netfs_rreq_assess(rreq, false); - ret = 0; - } - return ret; -} - -static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, - loff_t *_start, size_t *_len, loff_t i_size) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops && cres->ops->expand_readahead) - cres->ops->expand_readahead(cres, _start, _len, i_size); -} - -static void netfs_rreq_expand(struct netfs_io_request *rreq, - struct readahead_control *ractl) -{ - /* Give the cache a chance to change the request parameters. The - * resultant request must contain the original region. - */ - netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); - - /* Give the netfs a chance to change the request parameters. The - * resultant request must contain the original region. - */ - if (rreq->netfs_ops->expand_readahead) - rreq->netfs_ops->expand_readahead(rreq); - - /* Expand the request if the cache wants it to start earlier. Note - * that the expansion may get further extended if the VM wishes to - * insert THPs and the preferred start and/or end wind up in the middle - * of THPs. - * - * If this is the case, however, the THP size should be an integer - * multiple of the cache granule size, so we get a whole number of - * granules to deal with. - */ - if (rreq->start != readahead_pos(ractl) || - rreq->len != readahead_length(ractl)) { - readahead_expand(ractl, rreq->start, rreq->len); - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); - - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_expanded); - } -} - -/** - * netfs_readahead - Helper to manage a read request - * @ractl: The description of the readahead request - * - * Fulfil a readahead request by drawing data from the cache if possible, or - * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O - * requests from different sources will get munged together. If necessary, the - * readahead window can be expanded in either direction to a more convenient - * alighment for RPC efficiency or to make storage in the cache feasible. - * - * The calling netfs must initialise a netfs context contiguous to the vfs - * inode before calling this. - * - * This is usable whether or not caching is enabled. - */ -void netfs_readahead(struct readahead_control *ractl) -{ - struct netfs_io_request *rreq; - struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host); - int ret; - - _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); - - if (readahead_count(ractl) == 0) - return; - - rreq = netfs_alloc_request(ractl->mapping, ractl->file, - readahead_pos(ractl), - readahead_length(ractl), - NETFS_READAHEAD); - if (IS_ERR(rreq)) - return; - - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto cleanup_free; - } - - netfs_stat(&netfs_n_rh_readahead); - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_readahead); - - netfs_rreq_expand(rreq, ractl); - - /* Drop the refs on the folios here rather than in the cache or - * filesystem. The locks will be dropped in netfs_rreq_unlock(). - */ - while (readahead_folio(ractl)) - ; - - netfs_begin_read(rreq, false); - return; - -cleanup_free: - netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); - return; -} -EXPORT_SYMBOL(netfs_readahead); - -/** - * netfs_readpage - Helper to manage a readpage request - * @file: The file to read from - * @subpage: A subpage of the folio to read - * - * Fulfil a readpage request by drawing data from the cache if possible, or the - * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests - * from different sources will get munged together. - * - * The calling netfs must initialise a netfs context contiguous to the vfs - * inode before calling this. - * - * This is usable whether or not caching is enabled. - */ -int netfs_readpage(struct file *file, struct page *subpage) -{ - struct folio *folio = page_folio(subpage); - struct address_space *mapping = folio->mapping; - struct netfs_io_request *rreq; - struct netfs_i_context *ctx = netfs_i_context(mapping->host); - int ret; - - _enter("%lx", folio_index(folio)); - - rreq = netfs_alloc_request(mapping, file, - folio_file_pos(folio), folio_size(folio), - NETFS_READPAGE); - if (IS_ERR(rreq)) { - ret = PTR_ERR(rreq); - goto alloc_error; - } - - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto discard; - } - - netfs_stat(&netfs_n_rh_readpage); - trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); - return netfs_begin_read(rreq, true); - -discard: - netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); -alloc_error: - folio_unlock(folio); - return ret; -} -EXPORT_SYMBOL(netfs_readpage); - -/* - * Prepare a folio for writing without reading first - * @folio: The folio being prepared - * @pos: starting position for the write - * @len: length of write - * @always_fill: T if the folio should always be completely filled/cleared - * - * In some cases, write_begin doesn't need to read at all: - * - full folio write - * - write that lies in a folio that is completely beyond EOF - * - write that covers the folio from start to EOF or beyond it - * - * If any of these criteria are met, then zero out the unwritten parts - * of the folio and return true. Otherwise, return false. - */ -static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, - bool always_fill) -{ - struct inode *inode = folio_inode(folio); - loff_t i_size = i_size_read(inode); - size_t offset = offset_in_folio(folio, pos); - size_t plen = folio_size(folio); - - if (unlikely(always_fill)) { - if (pos - offset + len <= i_size) - return false; /* Page entirely before EOF */ - zero_user_segment(&folio->page, 0, plen); - folio_mark_uptodate(folio); - return true; - } - - /* Full folio write */ - if (offset == 0 && len >= plen) - return true; - - /* Page entirely beyond the end of the file */ - if (pos - offset >= i_size) - goto zero_out; - - /* Write that covers from the start of the folio to EOF or beyond */ - if (offset == 0 && (pos + len) >= i_size) - goto zero_out; - - return false; -zero_out: - zero_user_segments(&folio->page, 0, offset, offset + len, plen); - return true; -} - -/** - * netfs_write_begin - Helper to prepare for writing - * @file: The file to read from - * @mapping: The mapping to read from - * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the folio chosen) - * @aop_flags: AOP_* flags - * @_folio: Where to put the resultant folio - * @_fsdata: Place for the netfs to store a cookie - * - * Pre-read data for a write-begin request by drawing data from the cache if - * possible, or the netfs if not. Space beyond the EOF is zero-filled. - * Multiple I/O requests from different sources will get munged together. If - * necessary, the readahead window can be expanded in either direction to a - * more convenient alighment for RPC efficiency or to make storage in the cache - * feasible. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. - * - * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the folio is grabbed and locked. It is passed a - * pointer to the fsdata cookie that gets returned to the VM to be passed to - * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the folio and return -EAGAIN to cause the folio to - * be regot; or return an error. - * - * The calling netfs must initialise a netfs context contiguous to the vfs - * inode before calling this. - * - * This is usable whether or not caching is enabled. - */ -int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int aop_flags, - struct folio **_folio, void **_fsdata) -{ - struct netfs_io_request *rreq; - struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); - struct folio *folio; - unsigned int fgp_flags; - pgoff_t index = pos >> PAGE_SHIFT; - int ret; - - DEFINE_READAHEAD(ractl, file, NULL, mapping, index); - -retry: - fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; - if (aop_flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - folio = __filemap_get_folio(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (!folio) - return -ENOMEM; - - if (ctx->ops->check_write_begin) { - /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); - if (ret < 0) { - trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); - if (ret == -EAGAIN) - goto retry; - goto error; - } - } - - if (folio_test_uptodate(folio)) - goto have_folio; - - /* If the page is beyond the EOF, we want to clear it - unless it's - * within the cache granule containing the EOF, in which case we need - * to preload the granule. - */ - if (!netfs_is_cache_enabled(ctx) && - netfs_skip_folio_read(folio, pos, len, false)) { - netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio_no_wait; - } - - rreq = netfs_alloc_request(mapping, file, - folio_file_pos(folio), folio_size(folio), - NETFS_READ_FOR_WRITE); - if (IS_ERR(rreq)) { - ret = PTR_ERR(rreq); - goto error; - } - rreq->no_unlock_folio = folio_index(folio); - __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); - - if (ctx->ops->begin_cache_operation) { - ret = ctx->ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto error_put; - } - - netfs_stat(&netfs_n_rh_write_begin); - trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); - - /* Expand the request to meet caching requirements and download - * preferences. - */ - ractl._nr_pages = folio_nr_pages(folio); - netfs_rreq_expand(rreq, &ractl); - - /* We hold the folio locks, so we can drop the references */ - folio_get(folio); - while (readahead_folio(&ractl)) - ; - - ret = netfs_begin_read(rreq, true); - if (ret < 0) - goto error; - -have_folio: - ret = folio_wait_fscache_killable(folio); - if (ret < 0) - goto error; -have_folio_no_wait: - *_folio = folio; - _leave(" = 0"); - return 0; - -error_put: - netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); -error: - folio_unlock(folio); - folio_put(folio); - _leave(" = %d", ret); - return ret; -} -EXPORT_SYMBOL(netfs_write_begin); -- cgit v1.2.3