Because the NFS client will already happily handle misaligned O_DIRECT
IO (by sending it out to NFSD via RPC) this commit's new capabilities
are for the benefit of LOCALIO and require the nfs modparam:
localio_O_DIRECT_align_misaligned_IO=Y
When enabled, a misaligned DIO WRITE is split into a head, middle and
tail as needed. The large middle extent is DIO-aligned and the head
and/or tail are misaligned (due to each being a partial page).
The misaligned head and/or tail extents are issued using buffered IO
and the DIO-aligned middle is issued using O_DIRECT.
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
fs/nfs/direct.c | 40 +++++++++++++++++++++++++++++++++++-----
1 file changed, 35 insertions(+), 5 deletions(-)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index fc011571c5d29..3803289a94793 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -963,8 +963,15 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
if (result < 0)
break;
- bytes = result;
- npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
+ /* Limit the amount of bytes serviced each iteration to aligned batches */
+ if (pos < dreq->middle_offset && dreq->start_len)
+ bytes = min_t(size_t, dreq->start_len, result);
+ else if (pos < dreq->end_offset && dreq->middle_len)
+ bytes = min_t(size_t, dreq->middle_len, result);
+ else
+ bytes = result;
+ npages = (bytes + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
+
for (i = 0; i < npages; i++) {
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
@@ -983,6 +990,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
}
pgbase = 0;
+ result -= req_len;
bytes -= req_len;
requested_bytes += req_len;
pos += req_len;
@@ -992,9 +1000,28 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
continue;
}
+ /* Issue IO if this req was the end of the start or middle */
+ if (bytes == 0) {
+ if ((dreq->start_len &&
+ pos == dreq->middle_offset && result >= dreq->middle_len) ||
+ (dreq->end_len &&
+ pos == dreq->end_offset && result == dreq->end_len))
+ desc.pg_doio_now = 1;
+ }
+
nfs_lock_request(req);
- if (nfs_pageio_add_request(&desc, req))
+ if (nfs_pageio_add_request(&desc, req)) {
+ if (desc.pg_doio_now) {
+ /* Reset and handle iter to next aligned boundary */
+ iov_iter_revert(iter, result);
+ desc.pg_doio_now = 0;
+ break;
+ }
continue;
+ }
+
+ if (unlikely(desc.pg_doio_now))
+ desc.pg_doio_now = 0;
/* Exit on hard errors */
if (desc.pg_error < 0 && desc.pg_error != -EAGAIN) {
@@ -1092,8 +1119,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
goto out;
dreq->inode = inode;
- dreq->max_count = count;
- dreq->io_start = pos;
+ if (swap || !nfs_analyze_dio(pos, count, dreq)) {
+ dreq->max_count = count;
+ dreq->io_start = pos;
+ }
+
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
--
2.44.0
