[RFC,2/2] pmem: device flush over VIRTIO

Commit Message

Pankaj Gupta April 5, 2018, 10:48 a.m. UTC

This patch adds functionality to perform flush
 from guest to host over VIRTIO when 'ND_REGION_VIRTIO' 
 flag is set on nd_negion. This flag is set by 'virtio-pmem' 
 driver for virtio flush operation. 

Signed-off-by: Pankaj Gupta <[e-mail]>
---
 drivers/nvdimm/region_devs.c | 7 +++++++
 1 file changed, 7 insertions(+)

Patch

diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index abaf38c..1c6cd2a 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -20,6 +20,7 @@ 
 #include <linux/nd.h>
 #include "nd-core.h"
 #include "nd.h"
+#include <linux/virtio_pmem.h>
 
 /*
  * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
@@ -1043,6 +1044,12 @@  void nvdimm_flush(struct nd_region *nd_region)
 	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
 	int i, idx;
 
+       /* call PV device flush */
+	if (test_bit(ND_REGION_VIRTIO, &nd_region->flags)) {
+		virtio_pmem_flush(&nd_region->dev);
+		return;
+	}
+
 	/*
 	 * Try to encourage some diversity in flush hint addresses
 	 * across cpus assuming a limited number of flush hints.