[RFC net-next 00/13] net: page_pool: add netlink-based introspection

@@ -56,18 +56,22 @@ struct pp_alloc_cache {
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
  */
 struct page_pool_params {
-	unsigned int	flags;
-	unsigned int	order;
-	unsigned int	pool_size;
-	int		nid;
-	struct device	*dev;
-	struct napi_struct *napi;
-	enum dma_data_direction dma_dir;
-	unsigned int	max_len;
-	unsigned int	offset;
+	struct_group_tagged(page_pool_params_fast, fast,
+		unsigned int	flags;
+		unsigned int	order;
+		unsigned int	pool_size;
+		int		nid;
+		struct device	*dev;
+		struct napi_struct *napi;
+		enum dma_data_direction dma_dir;
+		unsigned int	max_len;
+		unsigned int	offset;
+	);
+	struct_group_tagged(page_pool_params_slow, slow,
 /* private: used by test code only */
-	void (*init_callback)(struct page *page, void *arg);
-	void *init_arg;
+		void (*init_callback)(struct page *page, void *arg);
+		void *init_arg;
+	);
 };
 
 #ifdef CONFIG_PAGE_POOL_STATS

@@ -121,7 +125,7 @@ struct page_pool_stats {
 #endif
 
 struct page_pool {
-	struct page_pool_params p;
+	struct page_pool_params_fast p;
 
 	long frag_users;
 	struct page *frag_page;

@@ -180,6 +184,9 @@ struct page_pool {
 	refcount_t user_cnt;
 
 	u64 destroy_cnt;
+
+	/* Slow/Control-path information follows */
+	struct page_pool_params_slow slow;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);

@@ -173,7 +173,8 @@ static int page_pool_init(struct page_pool *pool,
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
-	memcpy(&pool->p, params, sizeof(pool->p));
+	memcpy(&pool->p, &params->fast, sizeof(pool->p));
+	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	/* Validate only known flags were used */
 	if (pool->p.flags & ~(PP_FLAG_ALL))

@@ -372,8 +373,8 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 {
 	page->pp = pool;
 	page->pp_magic |= PP_SIGNATURE;
-	if (pool->p.init_callback)
-		pool->p.init_callback(page, pool->p.init_arg);
+	if (pool->slow.init_callback)
+		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 
 static void page_pool_clear_pp_info(struct page *page)

@@ -127,6 +127,8 @@ struct page_pool_stats {
 struct page_pool {
 	struct page_pool_params_fast p;
 
+	bool has_init_callback;
+
 	long frag_users;
 	struct page *frag_page;
 	unsigned int frag_offset;

@@ -216,6 +216,8 @@ static int page_pool_init(struct page_pool *pool,
 	    pool->p.flags & PP_FLAG_PAGE_FRAG)
 		return -EINVAL;
 
+	pool->has_init_callback = !!pool->slow.init_callback;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
 	if (!pool->recycle_stats)

@@ -373,7 +375,7 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 {
 	page->pp = pool;
 	page->pp_magic |= PP_SIGNATURE;
-	if (pool->slow.init_callback)
+	if (pool->has_init_callback)
 		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 

@@ -238,6 +238,18 @@ static int page_pool_init(struct page_pool *pool,
 	return 0;
 }
 
+static void page_pool_uninit(struct page_pool *pool)
+{
+	ptr_ring_cleanup(&pool->ring, NULL);
+
+	if (pool->p.flags & PP_FLAG_DMA_MAP)
+		put_device(pool->p.dev);
+
+#ifdef CONFIG_PAGE_POOL_STATS
+	free_percpu(pool->recycle_stats);
+#endif
+}
+
 /**
  * page_pool_create() - create a page pool.
  * @params: parameters, see struct page_pool_params

@@ -806,14 +818,7 @@ static void page_pool_free(struct page_pool *pool)
 	if (pool->disconnect)
 		pool->disconnect(pool);
 
-	ptr_ring_cleanup(&pool->ring, NULL);
-
-	if (pool->p.flags & PP_FLAG_DMA_MAP)
-		put_device(pool->p.dev);
-
-#ifdef CONFIG_PAGE_POOL_STATS
-	free_percpu(pool->recycle_stats);
-#endif
+	page_pool_uninit(pool);
 	kfree(pool);
 }
 

@@ -189,6 +189,10 @@ struct page_pool {
 
 	/* Slow/Control-path information follows */
 	struct page_pool_params_slow slow;
+	/* User-facing fields, protected by page_pools_lock */
+	struct {
+		u32 id;
+	} user;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);

@@ -18,7 +18,7 @@ obj-y		     += dev.o dev_addr_lists.o dst.o netevent.o \
 obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
 obj-y += net-sysfs.o
-obj-$(CONFIG_PAGE_POOL) += page_pool.o
+obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
 obj-$(CONFIG_NETPOLL) += netpoll.o

@@ -23,6 +23,8 @@
 
 #include <trace/events/page_pool.h>
 
+#include "page_pool_priv.h"
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 

@@ -264,13 +266,21 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 		return ERR_PTR(-ENOMEM);
 
 	err = page_pool_init(pool, params);
-	if (err < 0) {
-		pr_warn("%s() gave up with errno %d\n", __func__, err);
-		kfree(pool);
-		return ERR_PTR(err);
-	}
+	if (err < 0)
+		goto err_free;
+
+	err = page_pool_list(pool);
+	if (err)
+		goto err_uninit;
 
 	return pool;
+
+err_uninit:
+	page_pool_uninit(pool);
+err_free:
+	pr_warn("%s() gave up with errno %d\n", __func__, err);
+	kfree(pool);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(page_pool_create);
 

@@ -818,6 +828,7 @@ static void page_pool_free(struct page_pool *pool)
 	if (pool->disconnect)
 		pool->disconnect(pool);
 
+	page_pool_unlist(pool);
 	page_pool_uninit(pool);
 	kfree(pool);
 }

@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __PAGE_POOL_PRIV_H
+#define __PAGE_POOL_PRIV_H
+
+int page_pool_list(struct page_pool *pool);
+void page_pool_unlist(struct page_pool *pool);
+
+#endif

@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/mutex.h>
+#include <linux/xarray.h>
+#include <net/page_pool/types.h>
+
+#include "page_pool_priv.h"
+
+static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
+static DEFINE_MUTEX(page_pools_lock);
+
+int page_pool_list(struct page_pool *pool)
+{
+	static u32 id_alloc_next;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b,
+			      &id_alloc_next, GFP_KERNEL);
+	if (err < 0)
+		goto err_unlock;
+
+	mutex_unlock(&page_pools_lock);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+void page_pool_unlist(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	xa_erase(&page_pools, pool->user.id);
+	mutex_unlock(&page_pools_lock);
+}

@@ -1030,6 +1030,26 @@ static inline void hlist_move_list(struct hlist_head *old,
 	old->first = NULL;
 }
 
+/**
+ * hlist_splice_init() - move all entries from one list to another
+ * @from: hlist_head from which entries will be moved
+ * @last: last entry on the @from list
+ * @to:   hlist_head to which entries will be moved
+ *
+ * @to can be empty, @from must contain at least @last.
+ */
+static inline void hlist_splice_init(struct hlist_head *from,
+				     struct hlist_node *last,
+				     struct hlist_head *to)
+{
+	if (to->first)
+		to->first->pprev = &last->next;
+	last->next = to->first;
+	to->first = from->first;
+	from->first->pprev = &to->first;
+	from->first = NULL;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \

@@ -2405,6 +2405,10 @@ struct net_device {
 	struct rtnl_hw_stats64	*offload_xstats_l3;
 
 	struct devlink_port	*devlink_port;
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	/** @page_pools: page pools created for this netdevice */
+	struct hlist_head	page_pools;
+#endif
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 

@@ -5,6 +5,7 @@
 
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
+#include <linux/types.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
 					* map/unmap

@@ -50,6 +51,7 @@ struct pp_alloc_cache {
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
  * @dev:	device, for DMA pre-mapping purposes
+ * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV

@@ -68,6 +70,7 @@ struct page_pool_params {
 		unsigned int	offset;
 	);
 	struct_group_tagged(page_pool_params_slow, slow,
+		struct net_device *netdev;
 /* private: used by test code only */
 		void (*init_callback)(struct page *page, void *arg);
 		void *init_arg;

@@ -191,6 +194,7 @@ struct page_pool {
 	struct page_pool_params_slow slow;
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
+		struct hlist_node list;
 		u32 id;
 	} user;
 };

@@ -1,14 +1,31 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 #include <linux/mutex.h>
+#include <linux/netdevice.h>
 #include <linux/xarray.h>
+#include <net/net_debug.h>
 #include <net/page_pool/types.h>
 
 #include "page_pool_priv.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
+/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
+ * Ordering: inside rtnl_lock
+ */
 static DEFINE_MUTEX(page_pools_lock);
 
+/* Page pools are only reachable from user space (via netlink) if they are
+ * linked to a netdev at creation time. Following page pool "visibility"
+ * states are possible:
+ *  - normal
+ *    - user.list: linked to real netdev, netdev: real netdev
+ *  - orphaned - real netdev has disappeared
+ *    - user.list: linked to lo, netdev: lo
+ *  - invisible - either (a) created without netdev linking, (b) unlisted due
+ *      to error, or (c) the entire namespace which owned this pool disappeared
+ *    - user.list: unhashed, netdev: unknown
+ */
+
 int page_pool_list(struct page_pool *pool)
 {
 	static u32 id_alloc_next;

@@ -20,6 +37,10 @@ int page_pool_list(struct page_pool *pool)
 	if (err < 0)
 		goto err_unlock;
 
+	if (pool->slow.netdev)
+		hlist_add_head(&pool->user.list,
+			       &pool->slow.netdev->page_pools);
+
 	mutex_unlock(&page_pools_lock);
 	return 0;
 

@@ -32,5 +53,70 @@ void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
 	xa_erase(&page_pools, pool->user.id);
+	hlist_del(&pool->user.list);
 	mutex_unlock(&page_pools_lock);
 }
+
+static void page_pool_unreg_netdev_wipe(struct net_device *netdev)
+{
+	struct hlist_node *c, *n;
+
+	mutex_lock(&page_pools_lock);
+	hlist_for_each_safe(c, n, &netdev->page_pools)
+		hlist_del_init(c);
+	mutex_unlock(&page_pools_lock);
+}
+
+static void page_pool_unreg_netdev(struct net_device *netdev)
+{
+	struct page_pool *pool, *last;
+	struct net_device *lo;
+
+	lo = __dev_get_by_index(dev_net(netdev), 1);
+	if (!lo) {
+		netdev_err_once(netdev,
+				"can't get lo to store orphan page pools\n");
+		page_pool_unreg_netdev_wipe(netdev);
+		return;
+	}
+
+	mutex_lock(&page_pools_lock);
+	hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+		pool->slow.netdev = lo;
+		last = pool;
+	}
+
+	hlist_splice_init(&netdev->page_pools, &last->user.list,
+			  &lo->page_pools);
+	mutex_unlock(&page_pools_lock);
+}
+
+static int
+page_pool_netdevice_event(struct notifier_block *nb,
+			  unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (event != NETDEV_UNREGISTER)
+		return NOTIFY_DONE;
+
+	if (hlist_empty(&netdev->page_pools))
+		return NOTIFY_OK;
+
+	if (netdev->ifindex != 1)
+		page_pool_unreg_netdev(netdev);
+	else
+		page_pool_unreg_netdev_wipe(netdev);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block page_pool_netdevice_nb = {
+	.notifier_call = page_pool_netdevice_event,
+};
+
+static int __init page_pool_user_init(void)
+{
+	return register_netdevice_notifier(&page_pool_netdevice_nb);
+}
+
+subsys_initcall(page_pool_user_init);

@@ -195,6 +195,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
+		u32 napi_id;
 		u32 id;
 	} user;
 };

@@ -37,9 +37,11 @@ int page_pool_list(struct page_pool *pool)
 	if (err < 0)
 		goto err_unlock;
 
-	if (pool->slow.netdev)
+	if (pool->slow.netdev) {
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
+		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
+	}
 
 	mutex_unlock(&page_pools_lock);
 	return 0;

@@ -3247,6 +3247,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	pp.pool_size = bp->rx_ring_size;
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
+	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = DMA_BIDIRECTIONAL;
 	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE)

@@ -839,6 +839,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 		pp_params.nid       = node;
 		pp_params.dev       = rq->pdev;
 		pp_params.napi      = rq->cq.napi;
+		pp_params.netdev    = rq->netdev;
 		pp_params.dma_dir   = rq->buff.map_dir;
 		pp_params.max_len   = PAGE_SIZE;
 

@@ -2056,6 +2056,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 	pprm.pool_size = RX_BUFFERS_PER_QUEUE;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
+	pprm.netdev = rxq->ndev;
 
 	rxq->page_pool = page_pool_create(&pprm);
 

@@ -68,6 +68,30 @@ name: netdev
         type: u32
         checks:
           min: 1
+  -
+    name: page-pool
+    attributes:
+      -
+        name: id
+        doc: Unique ID of a Page Pool instance.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: pad
+        type: pad
+      -
+        name: ifindex
+        doc: |
+          ifindex of the netdev to which the pool belongs.
+          May be reported as 0 if the page pool was allocated for a netdev
+          which got destroyed already (page pools may outlast their netdevs
+          because they wait for all memory to be returned).
+        type: u32
+      -
+        name: napi-id
+        doc: Id of NAPI using this Page Pool instance.
+        type: u32
 
 operations:
   list:

@@ -101,6 +125,23 @@ name: netdev
       doc: Notification about device configuration being changed.
       notify: dev-get
       mcgrp: mgmt
+    -
+      name: page-pool-get
+      doc: |
+        Get / dump information about Page Pools.
+        (Only Page Pools associated with a net_device can be listed.)
+      attribute-set: page-pool
+      do:
+        request:
+          attributes:
+            - id
+        reply: &pp-reply
+          attributes:
+            - id
+            - ifindex
+            - napi-id
+      dump:
+        reply: *pp-reply
 
 mcast-groups:
   list:

@@ -48,11 +48,22 @@ enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PAGE_POOL_ID = 1,
+	NETDEV_A_PAGE_POOL_PAD,
+	NETDEV_A_PAGE_POOL_IFINDEX,
+	NETDEV_A_PAGE_POOL_NAPI_ID,
+
+	__NETDEV_A_PAGE_POOL_MAX,
+	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)

@@ -15,6 +15,11 @@ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 };
 
+/* NETDEV_CMD_PAGE_POOL_GET - do */
+static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = {
+	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{

@@ -29,6 +34,18 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.dumpit	= netdev_nl_dev_get_dumpit,
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= NETDEV_CMD_PAGE_POOL_GET,
+		.doit		= netdev_nl_page_pool_get_doit,
+		.policy		= netdev_page_pool_get_nl_policy,
+		.maxattr	= NETDEV_A_PAGE_POOL_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_PAGE_POOL_GET,
+		.dumpit	= netdev_nl_page_pool_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {

@@ -13,6 +13,9 @@
 
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,

@@ -5,8 +5,10 @@
 #include <linux/xarray.h>
 #include <net/net_debug.h>
 #include <net/page_pool/types.h>
+#include <net/sock.h>
 
 #include "page_pool_priv.h"
+#include "netdev-genl-gen.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
 /* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.

@@ -26,6 +28,131 @@ static DEFINE_MUTEX(page_pools_lock);
  *    - user.list: unhashed, netdev: unknown
  */
 
+typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool,
+			     const struct genl_info *info);
+
+static int
+netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill)
+{
+	struct page_pool *pool;
+	struct sk_buff *rsp;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	pool = xa_load(&page_pools, id);
+	if (!pool || hlist_unhashed(&pool->user.list) ||
+	    !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) {
+		err = -ENOENT;
+		goto err_unlock;
+	}
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp) {
+		err = -ENOMEM;
+		goto err_unlock;
+	}
+
+	err = fill(rsp, pool, info);
+	if (err)
+		goto err_free_msg;
+
+	mutex_unlock(&page_pools_lock);
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+struct page_pool_dump_cb {
+	unsigned long ifindex;
+	u32 pp_id;
+};
+
+static int
+netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			     pp_nl_fill_cb fill)
+{
+	struct page_pool_dump_cb *state = (void *)cb->ctx;
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	struct page_pool *pool;
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&page_pools_lock);
+	for_each_netdev_dump(net, netdev, state->ifindex) {
+		hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+			if (state->pp_id && state->pp_id < pool->user.id)
+				continue;
+
+			state->pp_id = pool->user.id;
+			err = fill(skb, pool, info);
+			if (err)
+				break;
+		}
+
+		state->pp_id = 0;
+	}
+	mutex_unlock(&page_pools_lock);
+	rtnl_unlock();
+
+	if (skb->len && err == -EMSGSIZE)
+		return skb->len;
+	return err;
+}
+
+static int
+page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
+		  const struct genl_info *info)
+{
+	void *hdr;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id))
+		goto err_cancel;
+
+	if (pool->slow.netdev->ifindex != 1 &&
+	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
+			pool->slow.netdev->ifindex))
+		goto err_cancel;
+	if (pool->user.napi_id &&
+	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
+		goto err_cancel;
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+err_cancel:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 id;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID))
+		return -EINVAL;
+
+	id = nla_get_u32(info->attrs[NETDEV_A_PAGE_POOL_ID]);
+
+	return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill);
+}
+
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill);
+}
+
 int page_pool_list(struct page_pool *pool)
 {
 	static u32 id_alloc_next;

@@ -142,8 +142,25 @@ name: netdev
             - napi-id
       dump:
         reply: *pp-reply
+    -
+      name: page-pool-add-ntf
+      doc: Notification about page pool appearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+    -
+      name: page-pool-del-ntf
+      doc: Notification about page pool disappearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+    -
+      name: page-pool-change-ntf
+      doc: Notification about page pool configuration being changed.
+      notify: page-pool-get
+      mcgrp: page-pool
 
 mcast-groups:
   list:
     -
       name: mgmt
+    -
+      name: page-pool

@@ -64,11 +64,15 @@ enum {
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_GET,
+	NETDEV_CMD_PAGE_POOL_ADD_NTF,
+	NETDEV_CMD_PAGE_POOL_DEL_NTF,
+	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
+#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */

@@ -50,6 +50,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
 	[NETDEV_NLGRP_MGMT] = { "mgmt", },
+	[NETDEV_NLGRP_PAGE_POOL] = { "page-pool", },
 };
 
 struct genl_family netdev_nl_family __ro_after_init = {

@@ -19,6 +19,7 @@ int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
 
 enum {
 	NETDEV_NLGRP_MGMT,
+	NETDEV_NLGRP_PAGE_POOL,
 };
 
 extern struct genl_family netdev_nl_family;

@@ -135,6 +135,37 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	return -EMSGSIZE;
 }
 
+static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd)
+{
+	struct genl_info info;
+	struct sk_buff *ntf;
+	struct net *net;
+
+	lockdep_assert_held(&page_pools_lock);
+
+	/* 'invisible' page pools don't matter */
+	if (hlist_unhashed(&pool->user.list))
+		return;
+	net = dev_net(pool->slow.netdev);
+
+	if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL))
+		return;
+
+	genl_info_init_ntf(&info, &netdev_nl_family, cmd);
+
+	ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!ntf)
+		return;
+
+	if (page_pool_nl_fill(ntf, pool, &info)) {
+		nlmsg_free(ntf);
+		return;
+	}
+
+	genlmsg_multicast_netns(&netdev_nl_family, net, ntf,
+				0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL);
+}
+
 int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	u32 id;

@@ -168,6 +199,8 @@ int page_pool_list(struct page_pool *pool)
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
 		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
+
+		netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF);
 	}
 
 	mutex_unlock(&page_pools_lock);

@@ -181,6 +214,7 @@ int page_pool_list(struct page_pool *pool)
 void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF);
 	xa_erase(&page_pools, pool->user.id);
 	hlist_del(&pool->user.list);
 	mutex_unlock(&page_pools_lock);

@@ -212,6 +246,8 @@ static void page_pool_unreg_netdev(struct net_device *netdev)
 	mutex_lock(&page_pools_lock);
 	hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
 		pool->slow.netdev = lo;
+		netdev_nl_page_pool_event(pool,
+					  NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
 		last = pool;
 	}
 

@@ -92,6 +92,20 @@ name: netdev
         name: napi-id
         doc: Id of NAPI using this Page Pool instance.
         type: u32
+      -
+        name: destroyed
+        type: u64
+        doc: |
+          Seconds in CLOCK_BOOTTIME of when Page Pool was destroyed.
+          Page Pools wait for all the memory allocated from them to be freed
+          before truly disappearing.
+          Absent if Page Pool hasn't been destroyed.
+      -
+        name: inflight
+        type: u32
+        doc: |
+          Number of outstanding references to this page pool (allocated
+          but yet to be freed pages).
 
 operations:
   list:

@@ -140,6 +154,8 @@ name: netdev
             - id
             - ifindex
             - napi-id
+            - destroyed
+            - inflight
       dump:
         reply: *pp-reply
     -

@@ -195,6 +195,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
+		u64 destroyed;
 		u32 napi_id;
 		u32 id;
 	} user;

@@ -53,6 +53,8 @@ enum {
 	NETDEV_A_PAGE_POOL_PAD,
 	NETDEV_A_PAGE_POOL_IFINDEX,
 	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_DESTROYED,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)

@@ -513,7 +513,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages);
  */
 #define _distance(a, b)	(s32)((a) - (b))
 
-static s32 page_pool_inflight(struct page_pool *pool)
+s32 page_pool_inflight(const struct page_pool *pool)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);

@@ -933,6 +933,7 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_release(pool))
 		return;
 
+	page_pool_destroyed(pool);
 	pool->defer_start = jiffies;
 	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
 

@@ -3,7 +3,10 @@
 #ifndef __PAGE_POOL_PRIV_H
 #define __PAGE_POOL_PRIV_H
 
+s32 page_pool_inflight(const struct page_pool *pool);
+
 int page_pool_list(struct page_pool *pool);
+void page_pool_destroyed(struct page_pool *pool);
 void page_pool_unlist(struct page_pool *pool);
 
 #endif

@@ -126,6 +126,14 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	if (pool->user.napi_id &&
 	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
 		goto err_cancel;
+	if (pool->user.destroyed) {
+		if (nla_put_u64_64bit(rsp, NETDEV_A_PAGE_POOL_DESTROYED,
+				      pool->user.destroyed,
+				      NETDEV_A_PAGE_POOL_PAD) ||
+		    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_INFLIGHT,
+				page_pool_inflight(pool)))
+			goto err_cancel;
+	}
 
 	genlmsg_end(rsp, hdr);
 

@@ -211,6 +219,14 @@ int page_pool_list(struct page_pool *pool)
 	return err;
 }
 
+void page_pool_destroyed(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	pool->user.destroyed = ktime_get_boottime_seconds();
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
+	mutex_unlock(&page_pools_lock);
+}
+
 void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);

@@ -106,6 +106,66 @@ name: netdev
         doc: |
           Number of outstanding references to this page pool (allocated
           but yet to be freed pages).
+  -
+    name: page-pool-info
+    subset-of: page-pool
+    attributes:
+      -
+        name: id
+        type: u32
+        checks:
+          min: 1
+      -
+        name: ifindex
+        type: u32
+  -
+    name: page-pool-stats
+    doc: |
+      Page pool statistics, see docs for struct page_pool_stats
+      for information about individual statistics.
+    attributes:
+      -
+        name: info
+        doc: Page pool identifying information.
+        type: nest
+        nested-attributes: page-pool-info
+      -
+        name: pad
+        type: pad
+      -
+        name: alloc-fast
+        type: u64
+        value: 8 # reserve some attr ids in case we need more metadata later
+      -
+        name: alloc-slow
+        type: u64
+      -
+        name: alloc-slow-high-order
+        type: u64
+      -
+        name: alloc-empty
+        type: u64
+      -
+        name: alloc-refill
+        type: u64
+      -
+        name: alloc-waive
+        type: u64
+      -
+        name: recycle-cached
+        type: u64
+      -
+        name: recycle-cache-full
+        type: u64
+      -
+        name: recycle-ring
+        type: u64
+      -
+        name: recycle-ring-full
+        type: u64
+      -
+        name: recycle-released-refcnt
+        type: u64
 
 operations:
   list:

@@ -173,6 +233,30 @@ name: netdev
       doc: Notification about page pool configuration being changed.
       notify: page-pool-get
       mcgrp: page-pool
+    -
+      name: page-pool-stats-get
+      doc: Get page pool statistics.
+      attribute-set: page-pool-stats
+      do:
+        request:
+          attributes:
+            - info
+        reply: &pp-stats-reply
+          attributes:
+            - info
+            - alloc-fast
+            - alloc-slow
+            - alloc-slow-high-order
+            - alloc-empty
+            - alloc-refill
+            - alloc-waive
+            - recycle-cached
+            - recycle-cache-full
+            - recycle-ring
+            - recycle-ring-full
+            - recycle-released-refcnt
+      dump:
+        reply: *pp-stats-reply
 
 mcast-groups:
   list:

@@ -105,8 +105,9 @@ page_pool_get_stats() and structures described below are available.
 It takes a  pointer to a ``struct page_pool`` and a pointer to a struct
 page_pool_stats allocated by the caller.
 
-The API will fill in the provided struct page_pool_stats with
-statistics about the page_pool.
+Older drivers expose page pool statistics via ethtool or debugfs.
+The same statistics are accessible via the netlink netdev family
+in a driver-independent fashion.
 
 .. kernel-doc:: include/net/page_pool/types.h
    :identifiers: struct page_pool_recycle_stats

@@ -32,16 +32,12 @@
 #include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
+/* Deprecated driver-facing API, use netlink instead */
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
 u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
 
-/*
- * Drivers that wish to harvest page pool stats and report them to users
- * (perhaps via ethtool, debugfs, or another mechanism) can allocate a
- * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool.
- */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats);
 #else
 static inline int page_pool_ethtool_stats_get_count(void)

@@ -60,6 +60,25 @@ enum {
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+	NETDEV_A_PAGE_POOL_STATS_PAD,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+	__NETDEV_A_PAGE_POOL_STATS_MAX,
+	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,