Add 'io_cache_write' to NFSD's debugfs interface so that: Any data
written by NFSD will either be:
- cached using page cache (NFSD_IO_BUFFERED=0)
- cached but removed from the page cache upon completion
(NFSD_IO_DONTCACHE=1).
- not cached (NFSD_IO_DIRECT=2)
io_cache_write may be set by writing to:
/sys/kernel/debug/nfsd/io_cache_write
The default value for io_cache_write reflects NFSD's current default
IO mode (NFSD_IO_BUFFERED=0).
If NFSD_IO_DONTCACHE is specified using 1, FOP_DONTCACHE must be
advertised as supported by the underlying filesystem (e.g. XFS),
otherwise all IO flagged with RWF_DONTCACHE will fail with
-EOPNOTSUPP.
If NFSD_IO_DIRECT is specified using 2, the IO must be aligned
relative to the underlying block device's logical_block_size. Also the
memory buffer used to store the WRITE payload must be aligned relative
to the underlying block device's dma_alignment.
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
fs/nfsd/debugfs.c | 42 ++++++++++++++++++++++++++++++++++++++++++
fs/nfsd/nfsd.h | 1 +
fs/nfsd/vfs.c | 15 +++++++++++++++
3 files changed, 58 insertions(+)
diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c
index dd1dc28a53784..173032a04cdec 100644
--- a/fs/nfsd/debugfs.c
+++ b/fs/nfsd/debugfs.c
@@ -85,6 +85,45 @@ static int nfsd_io_cache_read_set(void *data, u64 val)
DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
nfsd_io_cache_read_set, "%llu\n");
+/*
+ * /sys/kernel/debug/nfsd/io_cache_write
+ *
+ * Contents:
+ * %0: NFS WRITE will use buffered IO
+ * %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind)
+ * %2: NFS WRITE will use direct IO
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_write_get(void *data, u64 *val)
+{
+ *val = nfsd_io_cache_write;
+ return 0;
+}
+
+static int nfsd_io_cache_write_set(void *data, u64 val)
+{
+ int ret = 0;
+
+ switch (val) {
+ case NFSD_IO_BUFFERED:
+ case NFSD_IO_DONTCACHE:
+ case NFSD_IO_DIRECT:
+ nfsd_io_cache_write = val;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get,
+ nfsd_io_cache_write_set, "%llu\n");
+
void nfsd_debugfs_exit(void)
{
debugfs_remove_recursive(nfsd_top_dir);
@@ -100,4 +139,7 @@ void nfsd_debugfs_init(void)
debugfs_create_file("io_cache_read", S_IWUSR | S_IRUGO,
nfsd_top_dir, NULL, &nfsd_io_cache_read_fops);
+
+ debugfs_create_file("io_cache_write", S_IWUSR | S_IRUGO,
+ nfsd_top_dir, NULL, &nfsd_io_cache_write_fops);
}
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 41cb7c7feff3e..c491eb258ecd3 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -161,6 +161,7 @@ enum {
};
extern u64 nfsd_io_cache_read __read_mostly;
+extern u64 nfsd_io_cache_write __read_mostly;
extern int nfsd_max_blksize;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 21441745df69a..358d10a0665f6 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -50,6 +50,7 @@
bool nfsd_disable_splice_read __read_mostly;
u64 nfsd_io_cache_read __read_mostly = NFSD_IO_BUFFERED;
+u64 nfsd_io_cache_write __read_mostly = NFSD_IO_BUFFERED;
/**
* nfserrno - Map Linux errnos to NFS errnos
@@ -1241,6 +1242,20 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
since = READ_ONCE(file->f_wb_err);
if (verf)
nfsd_copy_write_verifier(verf, nn);
+
+ switch (nfsd_io_cache_write) {
+ case NFSD_IO_DIRECT:
+ /* direct I/O must be aligned to device logical sector size */
+ if (nf->nf_dio_mem_align && nf->nf_dio_offset_align &&
+ (((offset | *cnt) & (nf->nf_dio_offset_align-1)) == 0))
+ kiocb.ki_flags |= IOCB_DIRECT;
+ break;
+ case NFSD_IO_DONTCACHE:
+ kiocb.ki_flags |= IOCB_DONTCACHE;
+ break;
+ case NFSD_IO_BUFFERED:
+ break;
+ }
host_err = vfs_iocb_iter_write(file, &kiocb, &iter);
if (host_err < 0) {
commit_reset_write_verifier(nn, rqstp, host_err);
--
2.44.0
