[PATCH] virtio_pci_modern: skip unused trailing driver feature words

[Peng Hao <flyingpenghao@gmail.com>]

Since commit 69b9461512246 ("virtio_pci_modern: allow configuring
extended features"), vp_modern_set_extended_features() writes all 128
feature bits on every device.  Each 32-bit word requires one write to
guest_feature_select and another to guest_feature, even when the upper
64 feature bits are all zero.

Feature negotiation starts after a device reset, which clears the
device-side driver features.  There is therefore no need to write
trailing zero 64-bit words on the first feature finalization.

finalize_features() can, however, be called again without an intervening
reset when a driver's validate callback changes the negotiated features.
Remember how many words were written since the last reset and include
that range in the next write, so that a repeated finalization can clear
features which were previously enabled.

This avoids four MMIO writes for devices which negotiate no feature
above bit 63, while preserving the full-overwrite behavior when the
negotiated feature range shrinks.

Signed-off-by: Peng Hao <flyingpeng@tencent.com>
---
 drivers/virtio/virtio_pci_modern_dev.c | 22 +++++++++++++++++++++-
 include/linux/virtio_pci_modern.h      |  3 +++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 413a8c353463..8211e491a17b 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -230,6 +230,8 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 
 	check_offsets();
 
+	mdev->driver_features_u64s = 1;
+
 	if (mdev->device_id_check) {
 		devid = mdev->device_id_check(pci_dev);
 		if (devid < 0)
@@ -446,14 +448,29 @@ void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
 				     const u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	u8 u64s = VIRTIO_FEATURES_U64S;
+	u8 write_u64s;
 	int i;
 
-	for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) {
+	/*
+	 * A reset clears the device-side driver features, so trailing zero
+	 * words need not be written.  Include words written by the previous
+	 * call, though, so a repeated feature finalization can clear features
+	 * that were previously enabled.
+	 */
+	while (u64s > 1 && !features[u64s - 1])
+		u64s--;
+
+	write_u64s = max(u64s, mdev->driver_features_u64s);
+
+	for (i = 0; i < write_u64s * 2; i++) {
 		u32 cur = features[i >> 1] >> (32 * (i & 1));
 
 		vp_iowrite32(i, &cfg->guest_feature_select);
 		vp_iowrite32(cur, &cfg->guest_feature);
 	}
+
+	mdev->driver_features_u64s = u64s;
 }
 EXPORT_SYMBOL_GPL(vp_modern_set_extended_features);
 
@@ -495,6 +512,9 @@ void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
 
+	if (!status)
+		mdev->driver_features_u64s = 1;
+
 	/*
 	 * Per memory-barriers.txt, wmb() is not needed to guarantee
 	 * that the cache coherent memory writes have completed
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index 9a3f2fc53bd6..8df287d545c9 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -27,6 +27,8 @@
  *		    Returns the found device id or ERRNO
  * @dma_mask:	    Optional mask instead of the traditional DMA_BIT_MASK(64),
  *		    for vendor devices with DMA space address limitations
+ * @driver_features_u64s: Number of 64-bit driver feature words programmed
+ *		    since the last device reset
  */
 struct virtio_pci_modern_device {
 	struct pci_dev *pci_dev;
@@ -49,6 +51,7 @@ struct virtio_pci_modern_device {
 
 	int (*device_id_check)(struct pci_dev *pdev);
 	u64 dma_mask;
+	u8 driver_features_u64s;
 };
 
 /*
-- 
2.43.7