netfs: Optimise away reads above the point at which there can be no data

Track the file position above which the server is not expected to have any
data (the "zero point") and preemptively assume that we can satisfy
requests by filling them with zeroes locally rather than attempting to
download them if they're over that line - even if we've written data back
to the server.  Assume that any data that was written back above that
position is held in the local cache.  Note that we have to split requests
that straddle the line.

Make use of this to optimise away some reads from the server.  We need to
set the zero point in the following circumstances:

 (1) When we see an extant remote inode and have no cache for it, we set
     the zero_point to i_size.

 (2) On local inode creation, we set zero_point to 0.

 (3) On local truncation down, we reduce zero_point to the new i_size if
     the new i_size is lower.

 (4) On local truncation up, we don't change zero_point.

 (5) On local modification, we don't change zero_point.

 (6) On remote invalidation, we set zero_point to the new i_size.

 (7) If stored data is discarded from the pagecache or culled from fscache,
     we must set zero_point above that if the data also got written to the
     server.

 (8) If dirty data is written back to the server, but not fscache, we must
     set zero_point above that.

 (9) If a direct I/O write is made, set zero_point above that.

Assuming the above, any read from the server at or above the zero_point
position will return all zeroes.

The zero_point value can be stored in the cache, provided the above rules
are applied to it by any code that culls part of the local cache.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org

4 files changed, 20 insertions, 1 deletions

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6ca6c4bde5eb..08f28800232c 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -73,7 +73,7 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	if (folio_test_uptodate(folio))
 		return NETFS_FOLIO_IS_UPTODATE;
 
-	if (pos >= ctx->remote_i_size)
+	if (pos >= ctx->zero_point)
 		return NETFS_MODIFY_AND_CLEAR;
 
 	if (!maybe_trouble && offset == 0 && len >= flen)
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index bb0c2718f57b..aad05f2349a4 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -134,6 +134,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned long long end;
 	ssize_t ret;
 
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
@@ -155,6 +156,9 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
 	if (ret < 0)
 		goto out;
+	end = iocb->ki_pos + iov_iter_count(from);
+	if (end > ictx->zero_point)
+		ictx->zero_point = end;
 
 	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
 			   FSCACHE_INVAL_DIO_WRITE);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 14c18be5aca0..5b5af96cd4b9 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -569,6 +569,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
@@ -586,6 +587,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 * to make serial calls, it can indicate a short read and then
 		 * we will call it again.
 		 */
+		if (rreq->origin != NETFS_DIO_READ) {
+			if (subreq->start >= ictx->zero_point) {
+				source = NETFS_FILL_WITH_ZEROES;
+				goto set;
+			}
+			if (subreq->len > ictx->zero_point - subreq->start)
+				subreq->len = ictx->zero_point - subreq->start;
+		}
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
 		if (rreq->rsize && subreq->len > rreq->rsize)
@@ -607,6 +616,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		}
 	}
 
+set:
 	if (subreq->len > rreq->len)
 		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
 			rreq->debug_id, subreq->debug_index,
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index eeb44abe59c5..0e3af37fc924 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -240,6 +240,11 @@ EXPORT_SYMBOL(netfs_invalidate_folio);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+	unsigned long long end;
+
+	end = folio_pos(folio) + folio_size(folio);
+	if (end > ctx->zero_point)
+		ctx->zero_point = end;
 
 	if (folio_test_private(folio))
 		return false;