From 66f998f611897319b555364cefd5d6e88a205866 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Sun, 23 May 2010 11:00:54 -0400 Subject: fs: allow short direct-io reads to be completed via buffered IO This is similar to what already happens in the write case. If we have a short read while doing O_DIRECT, instead of just returning, fallthrough and try to read the rest via buffered IO. BTRFS needs this because if we encounter a compressed or inline extent during DIO, we need to fallback on buffered. If the extent is compressed we need to read the entire thing into memory and de-compress it into the users pages. I have tested this with fsx and everything works great. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- mm/filemap.c | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 140ebda9640..829ac9cdbd7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1263,7 +1263,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, { struct file *filp = iocb->ki_filp; ssize_t retval; - unsigned long seg; + unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; @@ -1290,21 +1290,47 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); } - if (retval > 0) + if (retval > 0) { *ppos = pos + retval; - if (retval) { + count -= retval; + } + + /* + * Btrfs can have a short DIO read if we encounter + * compressed extents, so if there was an error, or if + * we've already read everything we wanted to, or if + * there was a short read because we hit EOF, go ahead + * and return. Otherwise fallthrough to buffered io for + * the rest of the read. + */ + if (retval < 0 || !count || *ppos >= size) { file_accessed(filp); goto out; } } } + count = retval; for (seg = 0; seg < nr_segs; seg++) { read_descriptor_t desc; + loff_t offset = 0; + + /* + * If we did a short DIO read we need to skip the section of the + * iov that we've already read data into. + */ + if (count) { + if (count > iov[seg].iov_len) { + count -= iov[seg].iov_len; + continue; + } + offset = count; + count = 0; + } desc.written = 0; - desc.arg.buf = iov[seg].iov_base; - desc.count = iov[seg].iov_len; + desc.arg.buf = iov[seg].iov_base + offset; + desc.count = iov[seg].iov_len - offset; if (desc.count == 0) continue; desc.error = 0; -- cgit v1.2.3-70-g09d2