smb3: allow parallelizing decryption of reads
decrypting large reads on encrypted shares can be slow (e.g. adding
multiple milliseconds per-read on non-GCM capable servers or
when mounting with dialects prior to SMB3.1.1) - allow parallelizing
of read decryption by launching worker threads.
Testing to Samba on localhost showed 25% improvement.
Testing to remote server showed very large improvement when
doing more than one 'cp' command was called at one time.
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index de90e66..b0ea332 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -109,6 +109,7 @@ extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
+struct workqueue_struct *decrypt_wq;
struct workqueue_struct *cifsoplockd_wq;
__u32 cifs_lock_secret;
@@ -1499,11 +1500,22 @@ init_cifs(void)
goto out_clean_proc;
}
+ /*
+ * BB Consider setting limit!=0 maybe to min(num_of_cores - 1, 3) so we
+ * don't launch too many worker threads
+ */
+ decrypt_wq = alloc_workqueue("smb3decryptd",
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+ if (!decrypt_wq) {
+ rc = -ENOMEM;
+ goto out_destroy_cifsiod_wq;
+ }
+
cifsoplockd_wq = alloc_workqueue("cifsoplockd",
WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!cifsoplockd_wq) {
rc = -ENOMEM;
- goto out_destroy_cifsiod_wq;
+ goto out_destroy_decrypt_wq;
}
rc = cifs_fscache_register();
@@ -1569,6 +1581,8 @@ init_cifs(void)
cifs_fscache_unregister();
out_destroy_cifsoplockd_wq:
destroy_workqueue(cifsoplockd_wq);
+out_destroy_decrypt_wq:
+ destroy_workqueue(decrypt_wq);
out_destroy_cifsiod_wq:
destroy_workqueue(cifsiod_wq);
out_clean_proc:
@@ -1595,6 +1609,7 @@ exit_cifs(void)
cifs_destroy_inodecache();
cifs_fscache_unregister();
destroy_workqueue(cifsoplockd_wq);
+ destroy_workqueue(decrypt_wq);
destroy_workqueue(cifsiod_wq);
cifs_proc_clean();
}