Initial NFS client support for RWF_DONTCACHE
Subsystems (5)
Trond Myklebust
maintainerv2 cover Initial NFS client support for RWF_DONTCACHE
From: Trond Myklebust <[email protected]>
The following patch set attempts to add support for the RWF_DONTCACHE flag in preadv2() and pwritev2() on NFS filesystems.
The main issue is allowing support on 2 stage writes (i.e. unstable WRITE followed by a COMMIT) since those don't follow the current assumption that the 'dropbehind' flag can be fulfilled as soon as the writeback lock is dropped.
v2:
- Make use of the new iocb parameter for nfs_write_begin()
Trond Myklebust (2):
filemap: Add a helper for filesystems implementing dropbehind
NFS: Enable the RWF_DONTCACHE flag for the NFS client
fs/nfs/file.c | 7 +++---- fs/nfs/nfs4file.c | 2 ++ fs/nfs/write.c | 12 +++++++++++- include/linux/nfs_page.h | 1 + include/linux/pagemap.h | 1 + mm/filemap.c | 16 ++++++++++++++++ 6 files changed, 34 insertions(+), 5 deletions(-)
Signature · 1 line
2.50.1
Trond Myklebust
maintainerPATCH v2 1/2 filemap: Add a helper for filesystems implementing dropbehind
From: Trond Myklebust <[email protected]>
Add a helper to allow filesystems to attempt to free the 'dropbehind' folio.
--- include/linux/pagemap.h | 1 + mm/filemap.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+)
include/linux/pagemap.h +1 -0
@@ -1221,6 +1221,7 @@ void folio_wait_writeback(struct folio *folio);int folio_wait_writeback_killable (struct folio *folio);void end_page_writeback (struct page *page);void folio_end_writeback (struct folio *folio); +void folio_end_dropbehind (struct folio *folio);void folio_wait_stable (struct folio *folio);void __folio_mark_dirty (struct folio *folio,struct address_space *,int warn);void folio_account_cleaned (struct folio *folio,struct bdi_writeback *wb);
mm/filemap.c +16 -0
@@ -1603,6 +1603,22 @@ static void filemap_end_dropbehind(struct folio *folio)folio_unmap_invalidate (mapping, folio,0 ); } +/* +* Helper for filesystems that want to implement dropbehind, and that +* need to keep the folio around after folio_end_writeback, e.g. due to +* the need to first commit NFS stable writes. +*/ +void folio_end_dropbehind (struct folio *folio) +{ +if (folio_trylock (folio)) { +if (folio->mapping && !folio_test_dirty (folio) && + !folio_test_writeback (folio)) +folio_unmap_invalidate (folio->mapping, folio,0 ); +folio_unlock (folio); + } +} +EXPORT_SYMBOL (folio_end_dropbehind); +/* * If folio was marked as dropbehind, then pages should be dropped when writeback * completes. Do that now. If we fail, it's likely because of a big folio -
Signature · 1 line
2.50.1
Trond Myklebust
maintainerPATCH v2 2/2 NFS: Enable the RWF_DONTCACHE flag for the NFS client
In reply to Trond MyklebustFrom: Trond Myklebust <[email protected]>
While the NFS readahead code has no problems using the generic code to manage the dropbehind behaviour enabled by RWF_DONTCACHE, the write code needs to deal with the fact that NFS writeback uses a 2 step process (UNSTABLE write followed by COMMIT).
This commit replaces the use of the folio dropbehind flag with a local NFS request flag that triggers the dropbehind behaviour once the data has been written to stable storage.
--- fs/nfs/file.c | 7 +++---- fs/nfs/nfs4file.c | 2 ++ fs/nfs/write.c | 12 +++++++++++- include/linux/nfs_page.h | 1 + 4 files changed, 17 insertions(+), 5 deletions(-)
fs/nfs/file.c +3 -4
@@ -348,7 +348,6 @@ static int nfs_write_begin(const struct kiocb *iocb, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { - fgf_t fgp = FGP_WRITEBEGIN; struct folio *folio;struct file *file = iocb->ki_filp;int once_thru =0 ;
@@ -357,10 +356,8 @@ static int nfs_write_begin(const struct kiocb *iocb,dfprintk (PAGECACHE ,"NFS: write_begin(%pD2(%lu), %u@%lld)\n" , file, mapping->host->i_ino, len, (long long ) pos); - fgp |=fgf_set_order (len); start: - folio =__filemap_get_folio (mapping, pos >>PAGE_SHIFT , fgp, -mapping_gfp_mask (mapping)); + folio =write_begin_get_folio (iocb, mapping, pos >>PAGE_SHIFT , len);if (IS_ERR (folio))return PTR_ERR (folio); *foliop = folio;
@@ -915,5 +912,7 @@ const struct file_operations nfs_file_operations = { .splice_write = iter_file_splice_write, .check_flags = nfs_check_flags, .setlease = simple_nosetlease, + + .fop_flags = FOP_DONTCACHE, };EXPORT_SYMBOL_GPL (nfs_file_operations);
fs/nfs/nfs4file.c +2 -0
@@ -454,4 +454,6 @@ const struct file_operations nfs4_file_operations = {#else .llseek = nfs_file_llseek, #endif + + .fop_flags = FOP_DONTCACHE, };
fs/nfs/write.c +11 -1
@@ -359,8 +359,12 @@ static void nfs_folio_end_writeback(struct folio *folio)static void nfs_page_end_writeback (struct nfs_page *req) {if (nfs_page_group_sync_on_bit (req,PG_WB_END )) { +struct folio *folio =nfs_page_to_folio (req); + +if (folio_test_clear_dropbehind (folio)) +set_bit (PG_DROPBEHIND , &req->wb_flags);nfs_unlock_request (req); -nfs_folio_end_writeback (nfs_page_to_folio (req)); +nfs_folio_end_writeback (folio); }else nfs_unlock_request (req); }
@@ -797,6 +801,9 @@ static void nfs_inode_remove_request(struct nfs_page *req)clear_bit (PG_MAPPED , &req->wb_head->wb_flags); }spin_unlock (&mapping->i_private_lock); + +if (test_bit (PG_DROPBEHIND , &req->wb_flags)) +folio_end_dropbehind (folio); }if (test_and_clear_bit (PG_INODE_REF , &req->wb_flags)) {
@@ -2077,6 +2084,7 @@ int nfs_wb_folio(struct inode *inode, struct folio *folio) .range_start = range_start, .range_end = range_start + len - 1, }; +bool dropbehind =folio_test_clear_dropbehind (folio);int ret;trace_nfs_writeback_folio (inode, range_start, len);
@@ -2097,6 +2105,8 @@ int nfs_wb_folio(struct inode *inode, struct folio *folio) goto out_error; } out_error: +if (dropbehind) +folio_set_dropbehind (folio);trace_nfs_writeback_folio_done (inode, range_start, len, ret);return ret; }
include/linux/nfs_page.h +1 -0
@@ -37,6 +37,7 @@ enum {PG_REMOVE ,/* page group sync bit in write path */ PG_CONTENDED1 ,/* Is someone waiting for a lock? */ PG_CONTENDED2 ,/* Is someone waiting for a lock? */ + PG_DROPBEHIND, /* Implement RWF_DONTCACHE */ };struct nfs_inode ;
Signature · 1 line
2.50.1