From: Catherine Sullivan <csully@google.com>
Date: Mon, 7 Dec 2020 14:45:23 -0800
Subject: gve: Add support for raw addressing device option
Patch-mainline: v5.11-rc1
Git-commit: 4944db80ac1133fe4acb0c9756758da088338b26
References: bsc#1176940

Add support to describe device for parsing device options. As
the first device option, add raw addressing.

"Raw Addressing" mode (as opposed to the current "qpl" mode) is an
operational mode which allows the driver avoid bounce buffer copies
which it currently performs using pre-allocated qpls (queue_page_lists)
when sending and receiving packets.
For egress packets, the provided skb data addresses will be dma_map'ed and
passed to the device, allowing the NIC can perform DMA directly - the
driver will not have to copy the buffer content into pre-allocated
buffers/qpls (as in qpl mode).
For ingress packets, copies are also eliminated as buffers are handed to
the networking stack and then recycled or re-allocated as
necessary, avoiding the use of skb_copy_to_linear_data().

This patch only introduces the option to the driver.
Subsequent patches will add the ingress and egress functionality.

Reviewed-by: Yangchun Fu <yangchun@google.com>
Signed-off-by: Catherine Sullivan <csully@google.com>
Signed-off-by: David Awogbemila <awogbemila@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/google/gve/gve.h        |    1 
 drivers/net/ethernet/google/gve/gve_adminq.c |   71 +++++++++++++++++++++++++++
 drivers/net/ethernet/google/gve/gve_adminq.h |   13 +++-
 drivers/net/ethernet/google/gve/gve_main.c   |    9 +++
 4 files changed, 91 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -199,6 +199,7 @@ struct gve_priv {
 	u64 num_registered_pages; /* num pages registered with NIC */
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
+	u8 raw_addressing; /* 1 if this dev supports raw addressing, 0 otherwise */
 
 	struct gve_queue_config tx_cfg;
 	struct gve_queue_config rx_cfg;
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -14,6 +14,57 @@
 #define GVE_ADMINQ_SLEEP_LEN		20
 #define GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK	100
 
+#define GVE_DEVICE_OPTION_ERROR_FMT "%s option error:\n" \
+"Expected: length=%d, feature_mask=%x.\n" \
+"Actual: length=%d, feature_mask=%x.\n"
+
+static
+struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *descriptor,
+					      struct gve_device_option *option)
+{
+	void *option_end, *descriptor_end;
+
+	option_end = (void *)(option + 1) + be16_to_cpu(option->option_length);
+	descriptor_end = (void *)descriptor + be16_to_cpu(descriptor->total_length);
+
+	return option_end > descriptor_end ? NULL : (struct gve_device_option *)option_end;
+}
+
+static
+void gve_parse_device_option(struct gve_priv *priv,
+			     struct gve_device_descriptor *device_descriptor,
+			     struct gve_device_option *option)
+{
+	u16 option_length = be16_to_cpu(option->option_length);
+	u16 option_id = be16_to_cpu(option->option_id);
+
+	switch (option_id) {
+	case GVE_DEV_OPT_ID_RAW_ADDRESSING:
+		/* If the length or feature mask doesn't match,
+		 * continue without enabling the feature.
+		 */
+		if (option_length != GVE_DEV_OPT_LEN_RAW_ADDRESSING ||
+		    option->feat_mask != cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING)) {
+			dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, "Raw Addressing",
+				 GVE_DEV_OPT_LEN_RAW_ADDRESSING,
+				 cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING),
+				 option_length, option->feat_mask);
+			priv->raw_addressing = 0;
+		} else {
+			dev_info(&priv->pdev->dev,
+				 "Raw addressing device option enabled.\n");
+			priv->raw_addressing = 1;
+		}
+		break;
+	default:
+		/* If we don't recognize the option just continue
+		 * without doing anything.
+		 */
+		dev_dbg(&priv->pdev->dev, "Unrecognized device option 0x%hx not enabled.\n",
+			option_id);
+	}
+}
+
 int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
 {
 	priv->adminq = dma_alloc_coherent(dev, PAGE_SIZE,
@@ -460,11 +511,14 @@ int gve_adminq_destroy_rx_queues(struct
 int gve_adminq_describe_device(struct gve_priv *priv)
 {
 	struct gve_device_descriptor *descriptor;
+	struct gve_device_option *dev_opt;
 	union gve_adminq_command cmd;
 	dma_addr_t descriptor_bus;
+	u16 num_options;
 	int err = 0;
 	u8 *mac;
 	u16 mtu;
+	int i;
 
 	memset(&cmd, 0, sizeof(cmd));
 	descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE,
@@ -518,6 +572,23 @@ int gve_adminq_describe_device(struct gv
 		priv->rx_desc_cnt = priv->rx_pages_per_qpl;
 	}
 	priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
+	dev_opt = (void *)(descriptor + 1);
+
+	num_options = be16_to_cpu(descriptor->num_device_options);
+	for (i = 0; i < num_options; i++) {
+		struct gve_device_option *next_opt;
+
+		next_opt = gve_get_next_option(descriptor, dev_opt);
+		if (!next_opt) {
+			dev_err(&priv->dev->dev,
+				"options exceed device_descriptor's total length.\n");
+			err = -EINVAL;
+			goto free_device_descriptor;
+		}
+
+		gve_parse_device_option(priv, descriptor, dev_opt);
+		dev_opt = next_opt;
+	}
 
 free_device_descriptor:
 	dma_free_coherent(&priv->pdev->dev, sizeof(*descriptor), descriptor,
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -77,12 +77,17 @@ struct gve_device_descriptor {
 };
 
 
-struct device_option {
-	__be32 option_id;
-	__be32 option_length;
+struct gve_device_option {
+	__be16 option_id;
+	__be16 option_length;
+	__be32 feat_mask;
 };
 
 
+#define GVE_DEV_OPT_ID_RAW_ADDRESSING 0x1
+#define GVE_DEV_OPT_LEN_RAW_ADDRESSING 0x0
+#define GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING 0x0
+
 struct gve_adminq_configure_device_resources {
 	__be64 counter_array;
 	__be64 irq_db_addr;
@@ -105,6 +110,8 @@ struct gve_adminq_unregister_page_list {
 };
 
 
+#define GVE_RAW_ADDRESSING_QPL_ID 0xFFFFFFFF
+
 struct gve_adminq_create_tx_queue {
 	__be32 queue_id;
 	__be32 reserved;
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -677,6 +677,10 @@ static int gve_alloc_qpls(struct gve_pri
 	int i, j;
 	int err;
 
+	/* Raw addressing means no QPLs */
+	if (priv->raw_addressing)
+		return 0;
+
 	priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL);
 	if (!priv->qpls)
 		return -ENOMEM;
@@ -717,6 +721,10 @@ static void gve_free_qpls(struct gve_pri
 	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
 	int i;
 
+	/* Raw addressing means no QPLs */
+	if (priv->raw_addressing)
+		return;
+
 	kvfree(priv->qpl_cfg.qpl_id_map);
 
 	for (i = 0; i < num_qpls; i++)
@@ -1077,6 +1085,7 @@ static int gve_init_priv(struct gve_priv
 	if (skip_describe_device)
 		goto setup_device;
 
+	priv->raw_addressing = false;
 	/* Get the initial information we need from the device */
 	err = gve_adminq_describe_device(priv);
 	if (err) {