Merge branch 'gve-adopt-page-pool'

Harshitha Ramamurthy says:

====================
gve: adopt page pool

This patchset implements page pool support for gve.
The first patch deals with movement of code to make
page pool adoption easier in the next patch. The
second patch adopts the page pool API. The third patch
adds basic per queue stats which includes page pool
allocation failures as well.
====================

Link: https://patch.msgid.link/20241014202108.1051963-1-pkaligineedi@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 446 insertions, 269 deletions

diff --git a/drivers/net/ethernet/google/Kconfig b/drivers/net/ethernet/google/Kconfig
index 8641a00f8e63..564862a57124 100644
--- a/drivers/net/ethernet/google/Kconfig
+++ b/drivers/net/ethernet/google/Kconfig
@@ -18,6 +18,7 @@ if NET_VENDOR_GOOGLE
 config GVE
 	tristate "Google Virtual NIC (gVNIC) support"
 	depends on (PCI_MSI && (X86 || CPU_LITTLE_ENDIAN))
+	select PAGE_POOL
 	help
 	  This driver supports Google Virtual NIC (gVNIC)"
 
diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile
index 9ed07080b38a..4520f1c07a63 100644
--- a/drivers/net/ethernet/google/gve/Makefile
+++ b/drivers/net/ethernet/google/gve/Makefile
@@ -1,4 +1,5 @@
 # Makefile for the Google virtual Ethernet (gve) driver
 
 obj-$(CONFIG_GVE) += gve.o
-gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o
+gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \
+	    gve_buffer_mgmt_dqo.o
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 301fa1ea4f51..dd92949bb214 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -13,6 +13,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/u64_stats_sync.h>
+#include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
 #include "gve_desc.h"
@@ -60,6 +61,8 @@
 
 #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048
 
+#define GVE_PAGE_POOL_SIZE_MULTIPLIER 4
+
 #define GVE_FLOW_RULES_CACHE_SIZE \
 	(GVE_ADMINQ_BUFFER_SIZE / sizeof(struct gve_adminq_queried_flow_rule))
 #define GVE_FLOW_RULE_IDS_CACHE_SIZE \
@@ -102,6 +105,7 @@ struct gve_rx_slot_page_info {
 	struct page *page;
 	void *page_address;
 	u32 page_offset; /* offset to write to in page */
+	unsigned int buf_size;
 	int pagecnt_bias; /* expected pagecnt if only the driver has a ref */
 	u16 pad; /* adjustment for rx padding */
 	u8 can_flip; /* tracks if the networking stack is using the page */
@@ -273,6 +277,8 @@ struct gve_rx_ring {
 
 			/* Address info of the buffers for header-split */
 			struct gve_header_buf hdr_bufs;
+
+			struct page_pool *page_pool;
 		} dqo;
 	};
 
@@ -1162,6 +1168,36 @@ void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx);
 u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hplit);
 bool gve_header_split_supported(const struct gve_priv *priv);
 int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split);
+/* rx buffer handling */
+int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs);
+void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs,
+		       bool free_page);
+struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx);
+bool gve_buf_state_is_allocated(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state);
+void gve_free_buf_state(struct gve_rx_ring *rx,
+			struct gve_rx_buf_state_dqo *buf_state);
+struct gve_rx_buf_state_dqo *gve_dequeue_buf_state(struct gve_rx_ring *rx,
+						   struct gve_index_list *list);
+void gve_enqueue_buf_state(struct gve_rx_ring *rx, struct gve_index_list *list,
+			   struct gve_rx_buf_state_dqo *buf_state);
+struct gve_rx_buf_state_dqo *gve_get_recycled_buf_state(struct gve_rx_ring *rx);
+void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
+			 struct gve_rx_buf_state_dqo *buf_state);
+void gve_free_to_page_pool(struct gve_rx_ring *rx,
+			   struct gve_rx_buf_state_dqo *buf_state,
+			   bool allow_direct);
+int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
+			   struct gve_rx_buf_state_dqo *buf_state);
+void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state);
+void gve_reuse_buffer(struct gve_rx_ring *rx,
+		      struct gve_rx_buf_state_dqo *buf_state);
+void gve_free_buffer(struct gve_rx_ring *rx,
+		     struct gve_rx_buf_state_dqo *buf_state);
+int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc);
+struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
+					  struct gve_rx_ring *rx);
+
 /* Reset */
 void gve_schedule_reset(struct gve_priv *priv);
 int gve_reset(struct gve_priv *priv, bool attempt_teardown);
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
new file mode 100644
index 000000000000..05bf1f80a79c
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2024 Google, Inc.
+ */
+
+#include "gve.h"
+#include "gve_utils.h"
+
+int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs)
+{
+	return page_count(bs->page_info.page) - bs->page_info.pagecnt_bias;
+}
+
+struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx)
+{
+	struct gve_rx_buf_state_dqo *buf_state;
+	s16 buffer_id;
+
+	buffer_id = rx->dqo.free_buf_states;
+	if (unlikely(buffer_id == -1))
+		return NULL;
+
+	buf_state = &rx->dqo.buf_states[buffer_id];
+
+	/* Remove buf_state from free list */
+	rx->dqo.free_buf_states = buf_state->next;
+
+	/* Point buf_state to itself to mark it as allocated */
+	buf_state->next = buffer_id;
+
+	return buf_state;
+}
+
+bool gve_buf_state_is_allocated(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state)
+{
+	s16 buffer_id = buf_state - rx->dqo.buf_states;
+
+	return buf_state->next == buffer_id;
+}
+
+void gve_free_buf_state(struct gve_rx_ring *rx,
+			struct gve_rx_buf_state_dqo *buf_state)
+{
+	s16 buffer_id = buf_state - rx->dqo.buf_states;
+
+	buf_state->next = rx->dqo.free_buf_states;
+	rx->dqo.free_buf_states = buffer_id;
+}
+
+struct gve_rx_buf_state_dqo *gve_dequeue_buf_state(struct gve_rx_ring *rx,
+						   struct gve_index_list *list)
+{
+	struct gve_rx_buf_state_dqo *buf_state;
+	s16 buffer_id;
+
+	buffer_id = list->head;
+	if (unlikely(buffer_id == -1))
+		return NULL;
+
+	buf_state = &rx->dqo.buf_states[buffer_id];
+
+	/* Remove buf_state from list */
+	list->head = buf_state->next;
+	if (buf_state->next == -1)
+		list->tail = -1;
+
+	/* Point buf_state to itself to mark it as allocated */
+	buf_state->next = buffer_id;
+
+	return buf_state;
+}
+
+void gve_enqueue_buf_state(struct gve_rx_ring *rx, struct gve_index_list *list,
+			   struct gve_rx_buf_state_dqo *buf_state)
+{
+	s16 buffer_id = buf_state - rx->dqo.buf_states;
+
+	buf_state->next = -1;
+
+	if (list->head == -1) {
+		list->head = buffer_id;
+		list->tail = buffer_id;
+	} else {
+		int tail = list->tail;
+
+		rx->dqo.buf_states[tail].next = buffer_id;
+		list->tail = buffer_id;
+	}
+}
+
+struct gve_rx_buf_state_dqo *gve_get_recycled_buf_state(struct gve_rx_ring *rx)
+{
+	struct gve_rx_buf_state_dqo *buf_state;
+	int i;
+
+	/* Recycled buf states are immediately usable. */
+	buf_state = gve_dequeue_buf_state(rx, &rx->dqo.recycled_buf_states);
+	if (likely(buf_state))
+		return buf_state;
+
+	if (unlikely(rx->dqo.used_buf_states.head == -1))
+		return NULL;
+
+	/* Used buf states are only usable when ref count reaches 0, which means
+	 * no SKBs refer to them.
+	 *
+	 * Search a limited number before giving up.
+	 */
+	for (i = 0; i < 5; i++) {
+		buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states);
+		if (gve_buf_ref_cnt(buf_state) == 0) {
+			rx->dqo.used_buf_states_cnt--;
+			return buf_state;
+		}
+
+		gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
+	}
+
+	return NULL;
+}
+
+int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
+			   struct gve_rx_buf_state_dqo *buf_state)
+{
+	struct gve_priv *priv = rx->gve;
+	u32 idx;
+
+	idx = rx->dqo.next_qpl_page_idx;
+	if (idx >= gve_get_rx_pages_per_qpl_dqo(priv->rx_desc_cnt)) {
+		net_err_ratelimited("%s: Out of QPL pages\n",
+				    priv->dev->name);
+		return -ENOMEM;
+	}
+	buf_state->page_info.page = rx->dqo.qpl->pages[idx];
+	buf_state->addr = rx->dqo.qpl->page_buses[idx];
+	rx->dqo.next_qpl_page_idx++;
+	buf_state->page_info.page_offset = 0;
+	buf_state->page_info.page_address =
+		page_address(buf_state->page_info.page);
+	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	buf_state->last_single_ref_offset = 0;
+
+	/* The page already has 1 ref. */
+	page_ref_add(buf_state->page_info.page, INT_MAX - 1);
+	buf_state->page_info.pagecnt_bias = INT_MAX;
+
+	return 0;
+}
+
+void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state)
+{
+	if (!buf_state->page_info.page)
+		return;
+
+	page_ref_sub(buf_state->page_info.page,
+		     buf_state->page_info.pagecnt_bias - 1);
+	buf_state->page_info.page = NULL;
+}
+
+void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
+			 struct gve_rx_buf_state_dqo *buf_state)
+{
+	const u16 data_buffer_size = priv->data_buffer_size_dqo;
+	int pagecount;
+
+	/* Can't reuse if we only fit one buffer per page */
+	if (data_buffer_size * 2 > PAGE_SIZE)
+		goto mark_used;
+
+	pagecount = gve_buf_ref_cnt(buf_state);
+
+	/* Record the offset when we have a single remaining reference.
+	 *
+	 * When this happens, we know all of the other offsets of the page are
+	 * usable.
+	 */
+	if (pagecount == 1) {
+		buf_state->last_single_ref_offset =
+			buf_state->page_info.page_offset;
+	}
+
+	/* Use the next buffer sized chunk in the page. */
+	buf_state->page_info.page_offset += data_buffer_size;
+	buf_state->page_info.page_offset &= (PAGE_SIZE - 1);
+
+	/* If we wrap around to the same offset without ever dropping to 1
+	 * reference, then we don't know if this offset was ever freed.
+	 */
+	if (buf_state->page_info.page_offset ==
+	    buf_state->last_single_ref_offset) {
+		goto mark_used;
+	}
+
+	gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state);
+	return;
+
+mark_used:
+	gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
+	rx->dqo.used_buf_states_cnt++;
+}
+
+void gve_free_to_page_pool(struct gve_rx_ring *rx,
+			   struct gve_rx_buf_state_dqo *buf_state,
+			   bool allow_direct)
+{
+	struct page *page = buf_state->page_info.page;
+
+	if (!page)
+		return;
+
+	page_pool_put_page(page->pp, page, buf_state->page_info.buf_size,
+			   allow_direct);
+	buf_state->page_info.page = NULL;
+}
+
+static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
+				    struct gve_rx_buf_state_dqo *buf_state)
+{
+	struct gve_priv *priv = rx->gve;
+	struct page *page;
+
+	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	page = page_pool_alloc(rx->dqo.page_pool,
+			       &buf_state->page_info.page_offset,
+			       &buf_state->page_info.buf_size, GFP_ATOMIC);
+
+	if (!page)
+		return -ENOMEM;
+
+	buf_state->page_info.page = page;
+	buf_state->page_info.page_address = page_address(page);
+	buf_state->addr = page_pool_get_dma_addr(page);
+
+	return 0;
+}
+
+struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
+					  struct gve_rx_ring *rx)
+{
+	u32 ntfy_id = gve_rx_idx_to_ntfy(priv, rx->q_num);
+	struct page_pool_params pp = {
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+		.order = 0,
+		.pool_size = GVE_PAGE_POOL_SIZE_MULTIPLIER * priv->rx_desc_cnt,
+		.dev = &priv->pdev->dev,
+		.netdev = priv->dev,
+		.napi = &priv->ntfy_blocks[ntfy_id].napi,
+		.max_len = PAGE_SIZE,
+		.dma_dir = DMA_FROM_DEVICE,
+	};
+
+	return page_pool_create(&pp);
+}
+
+void gve_free_buffer(struct gve_rx_ring *rx,
+		     struct gve_rx_buf_state_dqo *buf_state)
+{
+	if (rx->dqo.page_pool) {
+		gve_free_to_page_pool(rx, buf_state, true);
+		gve_free_buf_state(rx, buf_state);
+	} else {
+		gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states,
+				      buf_state);
+	}
+}
+
+void gve_reuse_buffer(struct gve_rx_ring *rx,
+		      struct gve_rx_buf_state_dqo *buf_state)
+{
+	if (rx->dqo.page_pool) {
+		buf_state->page_info.page = NULL;
+		gve_free_buf_state(rx, buf_state);
+	} else {
+		gve_dec_pagecnt_bias(&buf_state->page_info);
+		gve_try_recycle_buf(rx->gve, rx, buf_state);
+	}
+}
+
+int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc)
+{
+	struct gve_rx_buf_state_dqo *buf_state;
+
+	if (rx->dqo.page_pool) {
+		buf_state = gve_alloc_buf_state(rx);
+		if (WARN_ON_ONCE(!buf_state))
+			return -ENOMEM;
+
+		if (gve_alloc_from_page_pool(rx, buf_state))
+			goto free_buf_state;
+	} else {
+		buf_state = gve_get_recycled_buf_state(rx);
+		if (unlikely(!buf_state)) {
+			buf_state = gve_alloc_buf_state(rx);
+			if (unlikely(!buf_state))
+				return -ENOMEM;
+
+			if (unlikely(gve_alloc_qpl_page_dqo(rx, buf_state)))
+				goto free_buf_state;
+		}
+	}
+	desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
+	desc->buf_addr = cpu_to_le64(buf_state->addr +
+				     buf_state->page_info.page_offset);
+
+	return 0;
+
+free_buf_state:
+	gve_free_buf_state(rx, buf_state);
+	return -ENOMEM;
+}
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 294ddcd0bf6c..e171ca248f9a 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -2561,6 +2561,54 @@ static const struct netdev_queue_mgmt_ops gve_queue_mgmt_ops = {
 	.ndo_queue_stop		=	gve_rx_queue_stop,
 };
 
+static void gve_get_rx_queue_stats(struct net_device *dev, int idx,
+				   struct netdev_queue_stats_rx *rx_stats)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_rx_ring *rx = &priv->rx[idx];
+	unsigned int start;
+
+	do {
+		start = u64_stats_fetch_begin(&rx->statss);
+		rx_stats->packets = rx->rpackets;
+		rx_stats->bytes = rx->rbytes;
+		rx_stats->alloc_fail = rx->rx_skb_alloc_fail +
+				       rx->rx_buf_alloc_fail;
+	} while (u64_stats_fetch_retry(&rx->statss, start));
+}
+
+static void gve_get_tx_queue_stats(struct net_device *dev, int idx,
+				   struct netdev_queue_stats_tx *tx_stats)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_tx_ring *tx = &priv->tx[idx];
+	unsigned int start;
+
+	do {
+		start = u64_stats_fetch_begin(&tx->statss);
+		tx_stats->packets = tx->pkt_done;
+		tx_stats->bytes = tx->bytes_done;
+	} while (u64_stats_fetch_retry(&tx->statss, start));
+}
+
+static void gve_get_base_stats(struct net_device *dev,
+			       struct netdev_queue_stats_rx *rx,
+			       struct netdev_queue_stats_tx *tx)
+{
+	rx->packets = 0;
+	rx->bytes = 0;
+	rx->alloc_fail = 0;
+
+	tx->packets = 0;
+	tx->bytes = 0;
+}
+
+static const struct netdev_stat_ops gve_stat_ops = {
+	.get_queue_stats_rx	= gve_get_rx_queue_stats,
+	.get_queue_stats_tx	= gve_get_tx_queue_stats,
+	.get_base_stats		= gve_get_base_stats,
+};
+
 static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int max_tx_queues, max_rx_queues;
@@ -2616,6 +2664,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->ethtool_ops = &gve_ethtool_ops;
 	dev->netdev_ops = &gve_netdev_ops;
 	dev->queue_mgmt_ops = &gve_queue_mgmt_ops;
+	dev->stat_ops = &gve_stat_ops;
 
 	/* Set default and supported features.
 	 *
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 1154c1d8f66f..8ac0047f1ada 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -16,189 +16,6 @@
 #include <net/ipv6.h>
 #include <net/tcp.h>
 
-static int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs)
-{
-	return page_count(bs->page_info.page) - bs->page_info.pagecnt_bias;
-}
-
-static void gve_free_page_dqo(struct gve_priv *priv,
-			      struct gve_rx_buf_state_dqo *bs,
-			      bool free_page)
-{
-	page_ref_sub(bs->page_info.page, bs->page_info.pagecnt_bias - 1);
-	if (free_page)
-		gve_free_page(&priv->pdev->dev, bs->page_info.page, bs->addr,
-			      DMA_FROM_DEVICE);
-	bs->page_info.page = NULL;
-}
-
-static struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx)
-{
-	struct gve_rx_buf_state_dqo *buf_state;
-	s16 buffer_id;
-
-	buffer_id = rx->dqo.free_buf_states;
-	if (unlikely(buffer_id == -1))
-		return NULL;
-
-	buf_state = &rx->dqo.buf_states[buffer_id];
-
-	/* Remove buf_state from free list */
-	rx->dqo.free_buf_states = buf_state->next;
-
-	/* Point buf_state to itself to mark it as allocated */
-	buf_state->next = buffer_id;
-
-	return buf_state;
-}
-
-static bool gve_buf_state_is_allocated(struct gve_rx_ring *rx,
-				       struct gve_rx_buf_state_dqo *buf_state)
-{
-	s16 buffer_id = buf_state - rx->dqo.buf_states;
-
-	return buf_state->next == buffer_id;
-}
-
-static void gve_free_buf_state(struct gve_rx_ring *rx,
-			       struct gve_rx_buf_state_dqo *buf_state)
-{
-	s16 buffer_id = buf_state - rx->dqo.buf_states;
-
-	buf_state->next = rx->dqo.free_buf_states;
-	rx->dqo.free_buf_states = buffer_id;
-}
-
-static struct gve_rx_buf_state_dqo *
-gve_dequeue_buf_state(struct gve_rx_ring *rx, struct gve_index_list *list)
-{
-	struct gve_rx_buf_state_dqo *buf_state;
-	s16 buffer_id;
-
-	buffer_id = list->head;
-	if (unlikely(buffer_id == -1))
-		return NULL;
-
-	buf_state = &rx->dqo.buf_states[buffer_id];
-
-	/* Remove buf_state from list */
-	list->head = buf_state->next;
-	if (buf_state->next == -1)
-		list->tail = -1;
-
-	/* Point buf_state to itself to mark it as allocated */
-	buf_state->next = buffer_id;
-
-	return buf_state;
-}
-
-static void gve_enqueue_buf_state(struct gve_rx_ring *rx,
-				  struct gve_index_list *list,
-				  struct gve_rx_buf_state_dqo *buf_state)
-{
-	s16 buffer_id = buf_state - rx->dqo.buf_states;
-
-	buf_state->next = -1;
-
-	if (list->head == -1) {
-		list->head = buffer_id;
-		list->tail = buffer_id;
-	} else {
-		int tail = list->tail;
-
-		rx->dqo.buf_states[tail].next = buffer_id;
-		list->tail = buffer_id;
-	}
-}
-
-static struct gve_rx_buf_state_dqo *
-gve_get_recycled_buf_state(struct gve_rx_ring *rx)
-{
-	struct gve_rx_buf_state_dqo *buf_state;
-	int i;
-
-	/* Recycled buf states are immediately usable. */
-	buf_state = gve_dequeue_buf_state(rx, &rx->dqo.recycled_buf_states);
-	if (likely(buf_state))
-		return buf_state;
-
-	if (unlikely(rx->dqo.used_buf_states.head == -1))
-		return NULL;
-
-	/* Used buf states are only usable when ref count reaches 0, which means
-	 * no SKBs refer to them.
-	 *
-	 * Search a limited number before giving up.
-	 */
-	for (i = 0; i < 5; i++) {
-		buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states);
-		if (gve_buf_ref_cnt(buf_state) == 0) {
-			rx->dqo.used_buf_states_cnt--;
-			return buf_state;
-		}
-
-		gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
-	}
-
-	/* For QPL, we cannot allocate any new buffers and must
-	 * wait for the existing ones to be available.
-	 */
-	if (rx->dqo.qpl)
-		return NULL;
-
-	/* If there are no free buf states discard an entry from
-	 * `used_buf_states` so it can be used.
-	 */
-	if (unlikely(rx->dqo.free_buf_states == -1)) {
-		buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states);
-		if (gve_buf_ref_cnt(buf_state) == 0)
-			return buf_state;
-
-		gve_free_page_dqo(rx->gve, buf_state, true);
-		gve_free_buf_state(rx, buf_state);
-	}
-
-	return NULL;
-}
-
-static int gve_alloc_page_dqo(struct gve_rx_ring *rx,
-			      struct gve_rx_buf_state_dqo *buf_state)
-{
-	struct gve_priv *priv = rx->gve;
-	u32 idx;
-
-	if (!rx->dqo.qpl) {
-		int err;
-
-		err = gve_alloc_page(priv, &priv->pdev->dev,
-				     &buf_state->page_info.page,
-				     &buf_state->addr,
-				     DMA_FROM_DEVICE, GFP_ATOMIC);
-		if (err)
-			return err;
-	} else {
-		idx = rx->dqo.next_qpl_page_idx;
-		if (idx >= gve_get_rx_pages_per_qpl_dqo(priv->rx_desc_cnt)) {
-			net_err_ratelimited("%s: Out of QPL pages\n",
-					    priv->dev->name);
-			return -ENOMEM;
-		}
-		buf_state->page_info.page = rx->dqo.qpl->pages[idx];
-		buf_state->addr = rx->dqo.qpl->page_buses[idx];
-		rx->dqo.next_qpl_page_idx++;
-	}
-	buf_state->page_info.page_offset = 0;
-	buf_state->page_info.page_address =
-		page_address(buf_state->page_info.page);
-	buf_state->last_single_ref_offset = 0;
-
-	/* The page already has 1 ref. */
-	page_ref_add(buf_state->page_info.page, INT_MAX - 1);
-	buf_state->page_info.pagecnt_bias = INT_MAX;
-
-	return 0;
-}
-
 static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx)
 {
 	struct device *hdev = &priv->pdev->dev;
@@ -278,8 +95,10 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
 		for (i = 0; i < rx->dqo.num_buf_states; i++) {
 			struct gve_rx_buf_state_dqo *bs = &rx->dqo.buf_states[i];
 
-			if (bs->page_info.page)
-				gve_free_page_dqo(priv, bs, !rx->dqo.qpl);
+			if (rx->dqo.page_pool)
+				gve_free_to_page_pool(rx, bs, false);
+			else
+				gve_free_qpl_page_dqo(bs);
 		}
 	}
 
@@ -321,9 +140,11 @@ void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
 
 	for (i = 0; i < rx->dqo.num_buf_states; i++) {
 		struct gve_rx_buf_state_dqo *bs = &rx->dqo.buf_states[i];
-		/* Only free page for RDA. QPL pages are freed in gve_main. */
-		if (bs->page_info.page)
-			gve_free_page_dqo(priv, bs, !rx->dqo.qpl);
+
+		if (rx->dqo.page_pool)
+			gve_free_to_page_pool(rx, bs, false);
+		else
+			gve_free_qpl_page_dqo(bs);
 	}
 
 	if (rx->dqo.qpl) {
@@ -350,6 +171,11 @@ void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
 	kvfree(rx->dqo.buf_states);
 	rx->dqo.buf_states = NULL;
 
+	if (rx->dqo.page_pool) {
+		page_pool_destroy(rx->dqo.page_pool);
+		rx->dqo.page_pool = NULL;
+	}
+
 	gve_rx_free_hdr_bufs(priv, rx);
 
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
@@ -382,6 +208,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 			  int idx)
 {
 	struct device *hdev = &priv->pdev->dev;
+	struct page_pool *pool;
 	int qpl_page_cnt;
 	size_t size;
 	u32 qpl_id;
@@ -395,8 +222,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	rx->gve = priv;
 	rx->q_num = idx;
 
-	rx->dqo.num_buf_states = cfg->raw_addressing ?
-		min_t(s16, S16_MAX, buffer_queue_slots * 4) :
+	rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots :
 		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
 	rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states,
 				      sizeof(rx->dqo.buf_states[0]),
@@ -424,7 +250,13 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	if (!rx->dqo.bufq.desc_ring)
 		goto err;
 
-	if (!cfg->raw_addressing) {
+	if (cfg->raw_addressing) {
+		pool = gve_rx_create_page_pool(priv, rx);
+		if (IS_ERR(pool))
+			goto err;
+
+		rx->dqo.page_pool = pool;
+	} else {
 		qpl_id = gve_get_rx_qpl_id(cfg->qcfg_tx, rx->q_num);
 		qpl_page_cnt = gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
 
@@ -521,26 +353,14 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx)
 	num_avail_slots = min_t(u32, num_avail_slots, complq->num_free_slots);
 	while (num_posted < num_avail_slots) {
 		struct gve_rx_desc_dqo *desc = &bufq->desc_ring[bufq->tail];
-		struct gve_rx_buf_state_dqo *buf_state;
-
-		buf_state = gve_get_recycled_buf_state(rx);
-		if (unlikely(!buf_state)) {
-			buf_state = gve_alloc_buf_state(rx);
-			if (unlikely(!buf_state))
-				break;
-
-			if (unlikely(gve_alloc_page_dqo(rx, buf_state))) {
-				u64_stats_update_begin(&rx->statss);
-				rx->rx_buf_alloc_fail++;
-				u64_stats_update_end(&rx->statss);
-				gve_free_buf_state(rx, buf_state);
-				break;
-			}
+
+		if (unlikely(gve_alloc_buffer(rx, desc))) {
+			u64_stats_update_begin(&rx->statss);
+			rx->rx_buf_alloc_fail++;
+			u64_stats_update_end(&rx->statss);
+			break;
 		}
 
-		desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
-		desc->buf_addr = cpu_to_le64(buf_state->addr +
-					     buf_state->page_info.page_offset);
 		if (rx->dqo.hdr_bufs.data)
 			desc->header_buf_addr =
 				cpu_to_le64(rx->dqo.hdr_bufs.addr +
@@ -557,48 +377,6 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx)
 	rx->fill_cnt += num_posted;
 }
 
-static void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
-				struct gve_rx_buf_state_dqo *buf_state)
-{
-	const u16 data_buffer_size = priv->data_buffer_size_dqo;
-	int pagecount;
-
-	/* Can't reuse if we only fit one buffer per page */
-	if (data_buffer_size * 2 > PAGE_SIZE)
-		goto mark_used;
-
-	pagecount = gve_buf_ref_cnt(buf_state);
-
-	/* Record the offset when we have a single remaining reference.
-	 *
-	 * When this happens, we know all of the other offsets of the page are
-	 * usable.
-	 */
-	if (pagecount == 1) {
-		buf_state->last_single_ref_offset =
-			buf_state->page_info.page_offset;
-	}
-
-	/* Use the next buffer sized chunk in the page. */
-	buf_state->page_info.page_offset += data_buffer_size;
-	buf_state->page_info.page_offset &= (PAGE_SIZE - 1);
-
-	/* If we wrap around to the same offset without ever dropping to 1
-	 * reference, then we don't know if this offset was ever freed.
-	 */
-	if (buf_state->page_info.page_offset ==
-	    buf_state->last_single_ref_offset) {
-		goto mark_used;
-	}
-
-	gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state);
-	return;
-
-mark_used:
-	gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state);
-	rx->dqo.used_buf_states_cnt++;
-}
-
 static void gve_rx_skb_csum(struct sk_buff *skb,
 			    const struct gve_rx_compl_desc_dqo *desc,
 			    struct gve_ptype ptype)
@@ -713,6 +491,9 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 		if (!skb)
 			return -1;
 
+		if (rx->dqo.page_pool)
+			skb_mark_for_recycle(skb);
+
 		if (rx->ctx.skb_tail == rx->ctx.skb_head)
 			skb_shinfo(rx->ctx.skb_head)->frag_list = skb;
 		else
@@ -723,7 +504,7 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	if (rx->ctx.skb_tail != rx->ctx.skb_head) {
 		rx->ctx.skb_head->len += buf_len;
 		rx->ctx.skb_head->data_len += buf_len;
-		rx->ctx.skb_head->truesize += priv->data_buffer_size_dqo;
+		rx->ctx.skb_head->truesize += buf_state->page_info.buf_size;
 	}
 
 	/* Trigger ondemand page allocation if we are running low on buffers */
@@ -733,13 +514,8 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
 			buf_state->page_info.page,
 			buf_state->page_info.page_offset,
-			buf_len, priv->data_buffer_size_dqo);
-	gve_dec_pagecnt_bias(&buf_state->page_info);
-
-	/* Advances buffer page-offset if page is partially used.
-	 * Marks buffer as used if page is full.
-	 */
-	gve_try_recycle_buf(priv, rx, buf_state);
+			buf_len, buf_state->page_info.buf_size);
+	gve_reuse_buffer(rx, buf_state);
 	return 0;
 }
 
@@ -773,8 +549,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	}
 
 	if (unlikely(compl_desc->rx_error)) {
-		gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states,
-				      buf_state);
+		gve_free_buffer(rx, buf_state);
 		return -EINVAL;
 	}
 
@@ -798,6 +573,9 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 			if (unlikely(!rx->ctx.skb_head))
 				goto error;
 			rx->ctx.skb_tail = rx->ctx.skb_head;
+
+			if (rx->dqo.page_pool)
+				skb_mark_for_recycle(rx->ctx.skb_head);
 		} else {
 			unsplit = 1;
 		}
@@ -834,8 +612,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		rx->rx_copybreak_pkt++;
 		u64_stats_update_end(&rx->statss);
 
-		gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states,
-				      buf_state);
+		gve_free_buffer(rx, buf_state);
 		return 0;
 	}
 
@@ -850,16 +627,17 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		return 0;
 	}
 
+	if (rx->dqo.page_pool)
+		skb_mark_for_recycle(rx->ctx.skb_head);
+
 	skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page,
 			buf_state->page_info.page_offset, buf_len,
-			priv->data_buffer_size_dqo);
-	gve_dec_pagecnt_bias(&buf_state->page_info);
-
-	gve_try_recycle_buf(priv, rx, buf_state);
+			buf_state->page_info.buf_size);
+	gve_reuse_buffer(rx, buf_state);
 	return 0;
 
 error:
-	gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state);
+	gve_free_buffer(rx, buf_state);
 	return -ENOMEM;
 }