Resguardo inicial

linux-7.2.3/net/xdp/Kconfig

@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config XDP_SOCKETS
+	bool "XDP sockets"
+	depends on BPF_SYSCALL
+	default n
+	help
+	  XDP sockets allows a channel between XDP programs and
+	  userspace applications.
+
+config XDP_SOCKETS_DIAG
+	tristate "XDP sockets: monitoring interface"
+	depends on XDP_SOCKETS
+	default n
+	help
+	  Support for PF_XDP sockets monitoring interface used by the ss tool.
+	  If unsure, say Y.

linux-7.2.3/net/xdp/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o xskmap.o
+obj-$(CONFIG_XDP_SOCKETS) += xsk_buff_pool.o
+obj-$(CONFIG_XDP_SOCKETS_DIAG) += xsk_diag.o

linux-7.2.3/net/xdp/xdp_umem.c

@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/mm.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/idr.h>
+#include <linux/vmalloc.h>
+
+#include "xdp_umem.h"
+#include "xsk_queue.h"
+
+static DEFINE_IDA(umem_ida);
+
+static void xdp_umem_unpin_pages(struct xdp_umem *umem)
+{
+	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
+
+	kvfree(umem->pgs);
+	umem->pgs = NULL;
+}
+
+static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
+{
+	if (umem->user) {
+		atomic_long_sub(umem->npgs, &umem->user->locked_vm);
+		free_uid(umem->user);
+	}
+}
+
+static void xdp_umem_addr_unmap(struct xdp_umem *umem)
+{
+	vunmap(umem->addrs);
+	umem->addrs = NULL;
+}
+
+static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages,
+			     u32 nr_pages)
+{
+	umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!umem->addrs)
+		return -ENOMEM;
+	return 0;
+}
+
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+	umem->zc = false;
+	ida_free(&umem_ida, umem->id);
+
+	xdp_umem_addr_unmap(umem);
+	xdp_umem_unpin_pages(umem);
+
+	xdp_umem_unaccount_pages(umem);
+	kfree(umem);
+}
+
+static void xdp_umem_release_deferred(struct work_struct *work)
+{
+	struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
+
+	xdp_umem_release(umem);
+}
+
+void xdp_get_umem(struct xdp_umem *umem)
+{
+	refcount_inc(&umem->users);
+}
+
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup)
+{
+	if (!umem)
+		return;
+
+	if (refcount_dec_and_test(&umem->users)) {
+		if (defer_cleanup) {
+			INIT_WORK(&umem->work, xdp_umem_release_deferred);
+			schedule_work(&umem->work);
+		} else {
+			xdp_umem_release(umem);
+		}
+	}
+}
+
+static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
+{
+	unsigned int gup_flags = FOLL_WRITE;
+	long npgs;
+	int err;
+
+	umem->pgs = kvzalloc_objs(*umem->pgs, umem->npgs,
+				  GFP_KERNEL | __GFP_NOWARN);
+	if (!umem->pgs)
+		return -ENOMEM;
+
+	mmap_read_lock(current->mm);
+	npgs = pin_user_pages(address, umem->npgs,
+			      gup_flags | FOLL_LONGTERM, &umem->pgs[0]);
+	mmap_read_unlock(current->mm);
+
+	if (npgs != umem->npgs) {
+		if (npgs >= 0) {
+			umem->npgs = npgs;
+			err = -ENOMEM;
+			goto out_pin;
+		}
+		err = npgs;
+		goto out_pgs;
+	}
+	return 0;
+
+out_pin:
+	xdp_umem_unpin_pages(umem);
+out_pgs:
+	kvfree(umem->pgs);
+	umem->pgs = NULL;
+	return err;
+}
+
+static int xdp_umem_account_pages(struct xdp_umem *umem)
+{
+	unsigned long lock_limit, new_npgs, old_npgs;
+
+	if (capable(CAP_IPC_LOCK))
+		return 0;
+
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	umem->user = get_uid(current_user());
+
+	do {
+		old_npgs = atomic_long_read(&umem->user->locked_vm);
+		new_npgs = old_npgs + umem->npgs;
+		if (new_npgs > lock_limit) {
+			free_uid(umem->user);
+			umem->user = NULL;
+			return -ENOBUFS;
+		}
+	} while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
+				     new_npgs) != old_npgs);
+	return 0;
+}
+
+#define XDP_UMEM_FLAGS_VALID ( \
+		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+		XDP_UMEM_TX_SW_CSUM | \
+		XDP_UMEM_TX_METADATA_LEN | \
+	0)
+
+static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+{
+	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+	u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
+	u64 addr = mr->addr, size = mr->len;
+	u32 chunks_rem, npgs_rem;
+	u64 chunks, npgs;
+	int err;
+
+	if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
+		/* Strictly speaking we could support this, if:
+		 * - huge pages, or*
+		 * - using an IOMMU, or
+		 * - making sure the memory area is consecutive
+		 * but for now, we simply say "computer says no".
+		 */
+		return -EINVAL;
+	}
+
+	if (mr->flags & ~XDP_UMEM_FLAGS_VALID)
+		return -EINVAL;
+
+	if (!unaligned_chunks && !is_power_of_2(chunk_size))
+		return -EINVAL;
+
+	if (!PAGE_ALIGNED(addr)) {
+		/* Memory area has to be page size aligned. For
+		 * simplicity, this might change.
+		 */
+		return -EINVAL;
+	}
+
+	if ((addr + size) < addr)
+		return -EINVAL;
+
+	npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem);
+	if (npgs_rem)
+		npgs++;
+	if (npgs > U32_MAX)
+		return -EINVAL;
+
+	chunks = div_u64_rem(size, chunk_size, &chunks_rem);
+	if (!chunks || chunks > U32_MAX)
+		return -EINVAL;
+
+	if (!unaligned_chunks && chunks_rem)
+		return -EINVAL;
+
+	if (headroom > chunk_size - XDP_PACKET_HEADROOM -
+		       SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - 128)
+		return -EINVAL;
+
+	if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
+		if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+			return -EINVAL;
+		if (mr->tx_metadata_len < 16)
+			return -EINVAL;
+		umem->tx_metadata_len = mr->tx_metadata_len;
+	}
+
+	umem->size = size;
+	umem->headroom = headroom;
+	umem->chunk_size = chunk_size;
+	umem->chunks = chunks;
+	umem->npgs = npgs;
+	umem->pgs = NULL;
+	umem->user = NULL;
+	umem->flags = mr->flags;
+
+	INIT_LIST_HEAD(&umem->xsk_dma_list);
+	refcount_set(&umem->users, 1);
+
+	err = xdp_umem_account_pages(umem);
+	if (err)
+		return err;
+
+	err = xdp_umem_pin_pages(umem, (unsigned long)addr);
+	if (err)
+		goto out_account;
+
+	err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs);
+	if (err)
+		goto out_unpin;
+
+	return 0;
+
+out_unpin:
+	xdp_umem_unpin_pages(umem);
+out_account:
+	xdp_umem_unaccount_pages(umem);
+	return err;
+}
+
+struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
+{
+	struct xdp_umem *umem;
+	int err;
+
+	umem = kzalloc_obj(*umem);
+	if (!umem)
+		return ERR_PTR(-ENOMEM);
+
+	err = ida_alloc(&umem_ida, GFP_KERNEL);
+	if (err < 0) {
+		kfree(umem);
+		return ERR_PTR(err);
+	}
+	umem->id = err;
+
+	err = xdp_umem_reg(umem, mr);
+	if (err) {
+		ida_free(&umem_ida, umem->id);
+		kfree(umem);
+		return ERR_PTR(err);
+	}
+
+	return umem;
+}

linux-7.2.3/net/xdp/xdp_umem.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* XDP user-space packet buffer
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#ifndef XDP_UMEM_H_
+#define XDP_UMEM_H_
+
+#include <net/xdp_sock_drv.h>
+
+void xdp_get_umem(struct xdp_umem *umem);
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup);
+struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
+
+#endif /* XDP_UMEM_H_ */

linux-7.2.3/net/xdp/xsk.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2019 Intel Corporation. */
+
+#ifndef XSK_H_
+#define XSK_H_
+
+struct xdp_ring_offset_v1 {
+	__u64 producer;
+	__u64 consumer;
+	__u64 desc;
+};
+
+struct xdp_mmap_offsets_v1 {
+	struct xdp_ring_offset_v1 rx;
+	struct xdp_ring_offset_v1 tx;
+	struct xdp_ring_offset_v1 fr;
+	struct xdp_ring_offset_v1 cr;
+};
+
+/* Nodes are linked in the struct xdp_sock map_list field, and used to
+ * track which maps a certain socket reside in.
+ */
+
+struct xsk_map_node {
+	struct list_head node;
+	struct xsk_map *map;
+	struct xdp_sock __rcu **map_entry;
+};
+
+static inline struct xdp_sock *xdp_sk(struct sock *sk)
+{
+	return (struct xdp_sock *)sk;
+}
+
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock __rcu **map_entry);
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+			u16 queue_id);
+
+#endif /* XSK_H_ */

linux-7.2.3/net/xdp/xsk_buff_pool.c

@@ -0,0 +1,785 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <net/netdev_lock.h>
+#include <net/xsk_buff_pool.h>
+#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
+
+#include "xsk_queue.h"
+#include "xdp_umem.h"
+#include "xsk.h"
+
+#define ETH_PAD_LEN (ETH_HLEN + 2 * VLAN_HLEN  + ETH_FCS_LEN)
+
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	if (!xs->tx)
+		return;
+
+	spin_lock(&pool->xsk_tx_list_lock);
+	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
+	spin_unlock(&pool->xsk_tx_list_lock);
+}
+
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	if (!xs->tx)
+		return;
+
+	spin_lock(&pool->xsk_tx_list_lock);
+	list_del_rcu(&xs->tx_list);
+	spin_unlock(&pool->xsk_tx_list_lock);
+}
+
+void xp_destroy(struct xsk_buff_pool *pool)
+{
+	if (!pool)
+		return;
+
+	kvfree(pool->tx_descs);
+	kvfree(pool->heads);
+	kvfree(pool);
+}
+
+int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs,
+		      u32 max_segs)
+{
+	u32 nentries = max(xs->tx->nentries, max_segs);
+
+	pool->tx_descs = kvzalloc_objs(*pool->tx_descs, nentries);
+	if (!pool->tx_descs)
+		return -ENOMEM;
+
+	pool->tx_descs_nentries = nentries;
+	return 0;
+}
+
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+						struct xdp_umem *umem,
+						u32 max_segs)
+{
+	bool unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+	struct xsk_buff_pool *pool;
+	struct xdp_buff_xsk *xskb;
+	u32 i, entries;
+
+	entries = unaligned ? umem->chunks : 0;
+	pool = kvzalloc_flex(*pool, free_heads, entries);
+	if (!pool)
+		goto out;
+
+	pool->heads = kvzalloc_objs(*pool->heads, umem->chunks);
+	if (!pool->heads)
+		goto out;
+
+	if (xs->tx)
+		if (xp_alloc_tx_descs(pool, xs, max_segs))
+			goto out;
+
+	pool->chunk_mask = ~((u64)umem->chunk_size - 1);
+	pool->addrs_cnt = umem->size;
+	pool->heads_cnt = umem->chunks;
+	pool->free_heads_cnt = umem->chunks;
+	pool->headroom = umem->headroom;
+	pool->chunk_size = umem->chunk_size;
+	pool->chunk_shift = ffs(umem->chunk_size) - 1;
+	pool->unaligned = unaligned;
+	pool->frame_len = umem->chunk_size - umem->headroom -
+		XDP_PACKET_HEADROOM;
+	pool->umem = umem;
+	pool->addrs = umem->addrs;
+	pool->tx_metadata_len = umem->tx_metadata_len;
+	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
+	spin_lock_init(&pool->rx_lock);
+	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xskb_list);
+	INIT_LIST_HEAD(&pool->xsk_tx_list);
+	spin_lock_init(&pool->xsk_tx_list_lock);
+	spin_lock_init(&pool->cq_prod_lock);
+	spin_lock_init(&xs->cq_tmp->cq_cached_prod_lock);
+	refcount_set(&pool->users, 1);
+
+	pool->fq = xs->fq_tmp;
+	pool->cq = xs->cq_tmp;
+
+	for (i = 0; i < pool->free_heads_cnt; i++) {
+		xskb = &pool->heads[i];
+		xskb->pool = pool;
+		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
+		INIT_LIST_HEAD(&xskb->list_node);
+		if (pool->unaligned)
+			pool->free_heads[i] = xskb;
+		else
+			xp_init_xskb_addr(xskb, pool, (u64)i * pool->chunk_size);
+	}
+
+	return pool;
+
+out:
+	xp_destroy(pool);
+	return NULL;
+}
+
+void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++)
+		pool->heads[i].xdp.rxq = rxq;
+}
+EXPORT_SYMBOL(xp_set_rxq_info);
+
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
+static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
+{
+	struct netdev_bpf bpf;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (pool->umem->zc) {
+		bpf.command = XDP_SETUP_XSK_POOL;
+		bpf.xsk.pool = NULL;
+		bpf.xsk.queue_id = pool->queue_id;
+
+		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
+
+		if (err)
+			WARN(1, "Failed to disable zero-copy!\n");
+	}
+}
+
+int xp_assign_dev(struct xsk_buff_pool *pool,
+		  struct net_device *netdev, u16 queue_id, u16 flags)
+{
+	u32 needed = netdev->mtu + ETH_PAD_LEN;
+	u32 segs = netdev->xdp_zc_max_segs;
+	bool mbuf = flags & XDP_USE_SG;
+	bool force_zc, force_copy;
+	struct netdev_bpf bpf;
+	u32 frame_size;
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	force_zc = flags & XDP_ZEROCOPY;
+	force_copy = flags & XDP_COPY;
+
+	if (force_zc && force_copy)
+		return -EINVAL;
+
+	if (pool->tx_sw_csum && (netdev->priv_flags & IFF_TX_SKB_NO_LINEAR))
+		return -EOPNOTSUPP;
+
+	if (xsk_get_pool_from_qid(netdev, queue_id))
+		return -EBUSY;
+
+	pool->netdev = netdev;
+	pool->queue_id = queue_id;
+	err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
+	if (err)
+		return err;
+
+	if (mbuf)
+		pool->umem->flags |= XDP_UMEM_SG_FLAG;
+
+	if (flags & XDP_USE_NEED_WAKEUP)
+		pool->uses_need_wakeup = true;
+	/* Tx needs to be explicitly woken up the first time.  Also
+	 * for supporting drivers that do not implement this
+	 * feature. They will always have to call sendto() or poll().
+	 */
+	pool->cached_need_wakeup = XDP_WAKEUP_TX;
+
+	dev_hold(netdev);
+
+	if (force_copy)
+		/* For copy-mode, we are done. */
+		return 0;
+
+	if ((netdev->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_pool;
+	}
+
+	if (mbuf) {
+		if (segs == 1) {
+			err = -EOPNOTSUPP;
+			goto err_unreg_pool;
+		}
+	} else {
+		segs = 1;
+	}
+
+	/* open-code xsk_pool_get_rx_frame_size() as pool->dev is not
+	 * set yet at this point; we are before getting down to driver
+	 */
+	frame_size = __xsk_pool_get_rx_frame_size(pool) -
+		     xsk_pool_get_tailroom(mbuf);
+	frame_size = ALIGN_DOWN(frame_size, 128);
+
+	if (needed > frame_size * segs) {
+		err = -EINVAL;
+		goto err_unreg_pool;
+	}
+
+	if (dev_get_min_mp_channel_count(netdev)) {
+		err = -EBUSY;
+		goto err_unreg_pool;
+	}
+
+	bpf.command = XDP_SETUP_XSK_POOL;
+	bpf.xsk.pool = pool;
+	bpf.xsk.queue_id = queue_id;
+
+	netdev_assert_locked_ops_compat(netdev);
+	err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
+	if (err)
+		goto err_unreg_pool;
+
+	if (!pool->dma_pages) {
+		WARN(1, "Driver did not DMA map zero-copy buffers");
+		err = -EINVAL;
+		goto err_unreg_xsk;
+	}
+	pool->umem->zc = true;
+	pool->xdp_zc_max_segs = netdev->xdp_zc_max_segs;
+	return 0;
+
+err_unreg_xsk:
+	xp_disable_drv_zc(pool);
+err_unreg_pool:
+	if (!force_zc)
+		err = 0; /* fallback to copy mode */
+	if (err) {
+		xsk_clear_pool_at_qid(netdev, queue_id);
+		dev_put(netdev);
+	}
+	return err;
+}
+
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
+			 struct net_device *dev, u16 queue_id)
+{
+	u16 flags;
+	struct xdp_umem *umem = umem_xs->umem;
+
+	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
+
+	if (umem->flags & XDP_UMEM_SG_FLAG)
+		flags |= XDP_USE_SG;
+
+	if (umem_xs->pool->uses_need_wakeup)
+		flags |= XDP_USE_NEED_WAKEUP;
+
+	return xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+void xp_clear_dev(struct xsk_buff_pool *pool)
+{
+	struct net_device *netdev = pool->netdev;
+
+	if (!pool->netdev)
+		return;
+
+	netdev_lock_ops(netdev);
+	xp_disable_drv_zc(pool);
+	xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
+	pool->netdev = NULL;
+	netdev_unlock_ops(netdev);
+	dev_put(netdev);
+}
+
+static void xp_release_deferred(struct work_struct *work)
+{
+	struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool,
+						  work);
+
+	rtnl_lock();
+	xp_clear_dev(pool);
+	rtnl_unlock();
+
+	if (pool->fq) {
+		xskq_destroy(pool->fq);
+		pool->fq = NULL;
+	}
+
+	if (pool->cq) {
+		xskq_destroy(pool->cq);
+		pool->cq = NULL;
+	}
+
+	xdp_put_umem(pool->umem, false);
+	xp_destroy(pool);
+}
+
+void xp_get_pool(struct xsk_buff_pool *pool)
+{
+	refcount_inc(&pool->users);
+}
+
+bool xp_put_pool(struct xsk_buff_pool *pool)
+{
+	if (!pool)
+		return false;
+
+	if (refcount_dec_and_test(&pool->users)) {
+		INIT_WORK(&pool->work, xp_release_deferred);
+		schedule_work(&pool->work);
+		return true;
+	}
+
+	return false;
+}
+
+static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
+{
+	struct xsk_dma_map *dma_map;
+
+	list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) {
+		if (dma_map->netdev == pool->netdev)
+			return dma_map;
+	}
+
+	return NULL;
+}
+
+static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev,
+					     u32 nr_pages, struct xdp_umem *umem)
+{
+	struct xsk_dma_map *dma_map;
+
+	dma_map = kzalloc_obj(*dma_map);
+	if (!dma_map)
+		return NULL;
+
+	dma_map->dma_pages = kvzalloc_objs(*dma_map->dma_pages, nr_pages);
+	if (!dma_map->dma_pages) {
+		kfree(dma_map);
+		return NULL;
+	}
+
+	dma_map->netdev = netdev;
+	dma_map->dev = dev;
+	dma_map->dma_pages_cnt = nr_pages;
+	refcount_set(&dma_map->users, 1);
+	list_add(&dma_map->list, &umem->xsk_dma_list);
+	return dma_map;
+}
+
+static void xp_destroy_dma_map(struct xsk_dma_map *dma_map)
+{
+	list_del(&dma_map->list);
+	kvfree(dma_map->dma_pages);
+	kfree(dma_map);
+}
+
+static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
+{
+	dma_addr_t *dma;
+	u32 i;
+
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
+		dma = &dma_map->dma_pages[i];
+		if (*dma) {
+			*dma &= ~XSK_NEXT_PG_CONTIG_MASK;
+			dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
+					     DMA_BIDIRECTIONAL, attrs);
+			*dma = 0;
+		}
+	}
+
+	xp_destroy_dma_map(dma_map);
+}
+
+void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+{
+	struct xsk_dma_map *dma_map;
+
+	if (!pool->dma_pages)
+		return;
+
+	dma_map = xp_find_dma_map(pool);
+	if (!dma_map) {
+		WARN(1, "Could not find dma_map for device");
+		return;
+	}
+
+	if (refcount_dec_and_test(&dma_map->users))
+		__xp_dma_unmap(dma_map, attrs);
+
+	kvfree(pool->dma_pages);
+	pool->dma_pages = NULL;
+	pool->dma_pages_cnt = 0;
+	pool->dev = NULL;
+}
+EXPORT_SYMBOL(xp_dma_unmap);
+
+static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
+{
+	u32 i;
+
+	for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) {
+		if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1])
+			dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
+		else
+			dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
+	}
+}
+
+static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
+{
+	if (!pool->unaligned) {
+		u32 i;
+
+		for (i = 0; i < pool->heads_cnt; i++) {
+			struct xdp_buff_xsk *xskb = &pool->heads[i];
+			u64 orig_addr;
+
+			orig_addr = xskb->xdp.data_hard_start - pool->addrs - pool->headroom;
+			xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, orig_addr);
+		}
+	}
+
+	pool->dma_pages = kvzalloc_objs(*pool->dma_pages,
+					dma_map->dma_pages_cnt);
+	if (!pool->dma_pages)
+		return -ENOMEM;
+
+	pool->dev = dma_map->dev;
+	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
+	memcpy(pool->dma_pages, dma_map->dma_pages,
+	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
+
+	return 0;
+}
+
+int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
+	       unsigned long attrs, struct page **pages, u32 nr_pages)
+{
+	struct xsk_dma_map *dma_map;
+	dma_addr_t dma;
+	int err;
+	u32 i;
+
+	dma_map = xp_find_dma_map(pool);
+	if (dma_map) {
+		err = xp_init_dma_info(pool, dma_map);
+		if (err)
+			return err;
+
+		refcount_inc(&dma_map->users);
+		return 0;
+	}
+
+	dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem);
+	if (!dma_map)
+		return -ENOMEM;
+
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
+		dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
+					 DMA_BIDIRECTIONAL, attrs);
+		if (dma_mapping_error(dev, dma)) {
+			__xp_dma_unmap(dma_map, attrs);
+			return -ENOMEM;
+		}
+		dma_map->dma_pages[i] = dma;
+	}
+
+	if (pool->unaligned)
+		xp_check_dma_contiguity(dma_map);
+
+	err = xp_init_dma_info(pool, dma_map);
+	if (err) {
+		__xp_dma_unmap(dma_map, attrs);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(xp_dma_map);
+
+static bool xp_addr_crosses_non_contig_pg(struct xsk_buff_pool *pool,
+					  u64 addr)
+{
+	return xp_desc_crosses_non_contig_pg(pool, addr, pool->chunk_size);
+}
+
+static bool xp_check_unaligned(struct xsk_buff_pool *pool, u64 *addr)
+{
+	*addr = xp_unaligned_extract_addr(*addr);
+	if (*addr >= pool->addrs_cnt ||
+	    *addr + pool->chunk_size > pool->addrs_cnt ||
+	    xp_addr_crosses_non_contig_pg(pool, *addr))
+		return false;
+	return true;
+}
+
+static bool xp_check_aligned(struct xsk_buff_pool *pool, u64 *addr)
+{
+	*addr = xp_aligned_extract_addr(pool, *addr);
+	return *addr < pool->addrs_cnt;
+}
+
+static struct xdp_buff_xsk *xp_get_xskb(struct xsk_buff_pool *pool, u64 addr)
+{
+	struct xdp_buff_xsk *xskb;
+
+	if (pool->unaligned) {
+		xskb = pool->free_heads[--pool->free_heads_cnt];
+		xp_init_xskb_addr(xskb, pool, addr);
+		if (pool->dma_pages)
+			xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr);
+	} else {
+		xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)];
+	}
+
+	return xskb;
+}
+
+static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
+{
+	struct xdp_buff_xsk *xskb;
+	u64 addr;
+	bool ok;
+
+	if (pool->free_heads_cnt == 0)
+		return NULL;
+
+	for (;;) {
+		if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) {
+			pool->fq->queue_empty_descs++;
+			return NULL;
+		}
+
+		ok = pool->unaligned ? xp_check_unaligned(pool, &addr) :
+		     xp_check_aligned(pool, &addr);
+		if (!ok) {
+			pool->fq->invalid_descs++;
+			xskq_cons_release(pool->fq);
+			continue;
+		}
+		break;
+	}
+
+	xskb = xp_get_xskb(pool, addr);
+
+	xskq_cons_release(pool->fq);
+	return xskb;
+}
+
+struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
+{
+	struct xdp_buff_xsk *xskb;
+
+	if (!pool->free_list_cnt) {
+		xskb = __xp_alloc(pool);
+		if (!xskb)
+			return NULL;
+	} else {
+		pool->free_list_cnt--;
+		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk,
+					list_node);
+		list_del_init(&xskb->list_node);
+	}
+
+	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
+	xskb->xdp.data_meta = xskb->xdp.data;
+	xskb->xdp.flags = 0;
+
+	if (pool->dev)
+		xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len);
+
+	return &xskb->xdp;
+}
+EXPORT_SYMBOL(xp_alloc);
+
+static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	u32 i, cached_cons, nb_entries;
+
+	if (max > pool->free_heads_cnt)
+		max = pool->free_heads_cnt;
+	max = xskq_cons_nb_entries(pool->fq, max);
+
+	cached_cons = pool->fq->cached_cons;
+	nb_entries = max;
+	i = max;
+	while (i--) {
+		struct xdp_buff_xsk *xskb;
+		u64 addr;
+		bool ok;
+
+		__xskq_cons_read_addr_unchecked(pool->fq, cached_cons++, &addr);
+
+		ok = pool->unaligned ? xp_check_unaligned(pool, &addr) :
+			xp_check_aligned(pool, &addr);
+		if (unlikely(!ok)) {
+			pool->fq->invalid_descs++;
+			nb_entries--;
+			continue;
+		}
+
+		xskb = xp_get_xskb(pool, addr);
+
+		*xdp = &xskb->xdp;
+		xdp++;
+	}
+
+	xskq_cons_release_n(pool->fq, max);
+	return nb_entries;
+}
+
+static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 nb_entries)
+{
+	struct xdp_buff_xsk *xskb;
+	u32 i;
+
+	nb_entries = min_t(u32, nb_entries, pool->free_list_cnt);
+
+	i = nb_entries;
+	while (i--) {
+		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, list_node);
+		list_del_init(&xskb->list_node);
+
+		*xdp = &xskb->xdp;
+		xdp++;
+	}
+	pool->free_list_cnt -= nb_entries;
+
+	return nb_entries;
+}
+
+static u32 xp_alloc_slow(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+			 u32 max)
+{
+	int i;
+
+	for (i = 0; i < max; i++) {
+		struct xdp_buff *buff;
+
+		buff = xp_alloc(pool);
+		if (unlikely(!buff))
+			return i;
+		*xdp = buff;
+		xdp++;
+	}
+
+	return max;
+}
+
+u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	u32 nb_entries1 = 0, nb_entries2;
+
+	if (unlikely(pool->dev && dma_dev_need_sync(pool->dev)))
+		return xp_alloc_slow(pool, xdp, max);
+
+	if (unlikely(pool->free_list_cnt)) {
+		nb_entries1 = xp_alloc_reused(pool, xdp, max);
+		if (nb_entries1 == max)
+			return nb_entries1;
+
+		max -= nb_entries1;
+		xdp += nb_entries1;
+	}
+
+	nb_entries2 = xp_alloc_new_from_fq(pool, xdp, max);
+	if (!nb_entries2)
+		pool->fq->queue_empty_descs++;
+
+	return nb_entries1 + nb_entries2;
+}
+EXPORT_SYMBOL(xp_alloc_batch);
+
+bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count)
+{
+	u32 req_count, avail_count;
+
+	if (pool->free_list_cnt >= count)
+		return true;
+
+	req_count = count - pool->free_list_cnt;
+	avail_count = xskq_cons_nb_entries(pool->fq, req_count);
+	if (!avail_count)
+		pool->fq->queue_empty_descs++;
+
+	return avail_count >= req_count;
+}
+EXPORT_SYMBOL(xp_can_alloc);
+
+void xp_free(struct xdp_buff_xsk *xskb)
+{
+	if (!list_empty(&xskb->list_node))
+		return;
+
+	xskb->pool->free_list_cnt++;
+	list_add(&xskb->list_node, &xskb->pool->free_list);
+}
+EXPORT_SYMBOL(xp_free);
+
+static u64 __xp_raw_get_addr(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
+}
+
+static void *__xp_raw_get_data(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return pool->addrs + addr;
+}
+
+void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
+{
+	return __xp_raw_get_data(pool, __xp_raw_get_addr(pool, addr));
+}
+EXPORT_SYMBOL(xp_raw_get_data);
+
+static dma_addr_t __xp_raw_get_dma(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return (pool->dma_pages[addr >> PAGE_SHIFT] &
+		~XSK_NEXT_PG_CONTIG_MASK) +
+		(addr & ~PAGE_MASK);
+}
+
+dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
+{
+	return __xp_raw_get_dma(pool, __xp_raw_get_addr(pool, addr));
+}
+EXPORT_SYMBOL(xp_raw_get_dma);
+
+/**
+ * xp_raw_get_ctx - get &xdp_desc context
+ * @pool: XSk buff pool desc address belongs to
+ * @addr: desc address (from userspace)
+ *
+ * Helper for getting desc's DMA address and metadata pointer, if present.
+ * Saves one call on hotpath and double calculation of the actual address.
+ * Metadata is validated later by xsk_tx_metadata_request().
+ *
+ * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
+ * pointer, if it is present (initialized to %NULL otherwise).
+ */
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	struct xdp_desc_ctx ret;
+
+	addr = __xp_raw_get_addr(pool, addr);
+
+	ret.dma = __xp_raw_get_dma(pool, addr);
+	ret.meta = __xsk_buff_get_metadata(pool, __xp_raw_get_data(pool, addr));
+
+	return ret;
+}
+EXPORT_SYMBOL(xp_raw_get_ctx);

linux-7.2.3/net/xdp/xsk_diag.c

@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP sockets monitoring support
+ *
+ * Copyright(c) 2019 Intel Corporation.
+ *
+ * Author: Björn Töpel <bjorn.topel@intel.com>
+ */
+
+#include <linux/module.h>
+#include <net/xdp_sock.h>
+#include <linux/xdp_diag.h>
+#include <linux/sock_diag.h>
+
+#include "xsk_queue.h"
+#include "xsk.h"
+
+static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xdp_diag_info di = {};
+
+	di.ifindex = xs->dev ? xs->dev->ifindex : 0;
+	di.queue_id = xs->queue_id;
+	return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di);
+}
+
+static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type,
+			     struct sk_buff *nlskb)
+{
+	struct xdp_diag_ring dr = {};
+
+	dr.entries = queue->nentries;
+	return nla_put(nlskb, nl_type, sizeof(dr), &dr);
+}
+
+static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs,
+				  struct sk_buff *nlskb)
+{
+	int err = 0;
+
+	if (xs->rx)
+		err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb);
+	if (!err && xs->tx)
+		err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb);
+	return err;
+}
+
+static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xsk_buff_pool *pool = xs->pool;
+	struct xdp_umem *umem = xs->umem;
+	struct xdp_diag_umem du = {};
+	int err;
+
+	if (!umem)
+		return 0;
+
+	du.id = umem->id;
+	du.size = umem->size;
+	du.num_pages = umem->npgs;
+	du.chunk_size = umem->chunk_size;
+	du.headroom = umem->headroom;
+	du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0;
+	du.queue_id = pool ? pool->queue_id : 0;
+	du.flags = 0;
+	if (umem->zc)
+		du.flags |= XDP_DU_F_ZEROCOPY;
+	du.refs = refcount_read(&umem->users);
+
+	err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
+	if (!err && pool && pool->fq)
+		err = xsk_diag_put_ring(pool->fq,
+					XDP_DIAG_UMEM_FILL_RING, nlskb);
+	if (!err && pool && pool->cq)
+		err = xsk_diag_put_ring(pool->cq,
+					XDP_DIAG_UMEM_COMPLETION_RING, nlskb);
+	return err;
+}
+
+static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xdp_diag_stats du = {};
+
+	du.n_rx_dropped = xs->rx_dropped;
+	du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx);
+	du.n_rx_full = xs->rx_queue_full;
+	du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
+	du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx);
+	du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx);
+	return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du);
+}
+
+static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
+			 struct xdp_diag_req *req,
+			 struct user_namespace *user_ns,
+			 u32 portid, u32 seq, u32 flags, u64 sk_ino)
+{
+	struct xdp_sock *xs = xdp_sk(sk);
+	struct xdp_diag_msg *msg;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	msg = nlmsg_data(nlh);
+	memset(msg, 0, sizeof(*msg));
+	msg->xdiag_family = AF_XDP;
+	msg->xdiag_type = sk->sk_type;
+	msg->xdiag_ino = sk_ino;
+	sock_diag_save_cookie(sk, msg->xdiag_cookie);
+
+	mutex_lock(&xs->mutex);
+	if (READ_ONCE(xs->state) == XSK_UNBOUND)
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_INFO) &&
+	    nla_put_u32(nlskb, XDP_DIAG_UID,
+			from_kuid_munged(user_ns, sk_uid(sk))))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_RING_CFG) &&
+	    xsk_diag_put_rings_cfg(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_UMEM) &&
+	    xsk_diag_put_umem(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_STATS) &&
+	    xsk_diag_put_stats(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	mutex_unlock(&xs->mutex);
+	nlmsg_end(nlskb, nlh);
+	return 0;
+
+out_nlmsg_trim:
+	mutex_unlock(&xs->mutex);
+	nlmsg_cancel(nlskb, nlh);
+	return -EMSGSIZE;
+}
+
+static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb)
+{
+	struct xdp_diag_req *req = nlmsg_data(cb->nlh);
+	struct net *net = sock_net(nlskb->sk);
+	int num = 0, s_num = cb->args[0];
+	struct sock *sk;
+
+	mutex_lock(&net->xdp.lock);
+
+	sk_for_each(sk, &net->xdp.list) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (num++ < s_num)
+			continue;
+
+		if (xsk_diag_fill(sk, nlskb, req,
+				  sk_user_ns(NETLINK_CB(cb->skb).sk),
+				  NETLINK_CB(cb->skb).portid,
+				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				  sock_i_ino(sk)) < 0) {
+			num--;
+			break;
+		}
+	}
+
+	mutex_unlock(&net->xdp.lock);
+	cb->args[0] = num;
+	return nlskb->len;
+}
+
+static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr)
+{
+	struct netlink_dump_control c = { .dump = xsk_diag_dump };
+	int hdrlen = sizeof(struct xdp_diag_req);
+	struct net *net = sock_net(nlskb->sk);
+
+	if (nlmsg_len(hdr) < hdrlen)
+		return -EINVAL;
+
+	if (!(hdr->nlmsg_flags & NLM_F_DUMP))
+		return -EOPNOTSUPP;
+
+	return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c);
+}
+
+static const struct sock_diag_handler xsk_diag_handler = {
+	.owner = THIS_MODULE,
+	.family = AF_XDP,
+	.dump = xsk_diag_handler_dump,
+};
+
+static int __init xsk_diag_init(void)
+{
+	return sock_diag_register(&xsk_diag_handler);
+}
+
+static void __exit xsk_diag_exit(void)
+{
+	sock_diag_unregister(&xsk_diag_handler);
+}
+
+module_init(xsk_diag_init);
+module_exit(xsk_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP);

linux-7.2.3/net/xdp/xsk_queue.c

@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <linux/log2.h>
+#include <linux/slab.h>
+#include <linux/overflow.h>
+#include <linux/vmalloc.h>
+#include <net/xdp_sock_drv.h>
+
+#include "xsk_queue.h"
+
+static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue)
+{
+	struct xdp_umem_ring *umem_ring;
+	struct xdp_rxtx_ring *rxtx_ring;
+
+	if (umem_queue)
+		return struct_size(umem_ring, desc, q->nentries);
+	return struct_size(rxtx_ring, desc, q->nentries);
+}
+
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
+{
+	struct xsk_queue *q;
+	size_t size;
+
+	q = kzalloc_obj(*q);
+	if (!q)
+		return NULL;
+
+	q->nentries = nentries;
+	q->ring_mask = nentries - 1;
+
+	size = xskq_get_ring_size(q, umem_queue);
+
+	/* size which is overflowing or close to SIZE_MAX will become 0 in
+	 * PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous
+	 * is_power_of_2(), the rest will be handled by vmalloc_user()
+	 */
+	if (unlikely(size == SIZE_MAX)) {
+		kfree(q);
+		return NULL;
+	}
+
+	size = PAGE_ALIGN(size);
+
+	q->ring = vmalloc_user(size);
+	if (!q->ring) {
+		kfree(q);
+		return NULL;
+	}
+
+	q->ring_vmalloc_size = size;
+	return q;
+}
+
+void xskq_destroy(struct xsk_queue *q)
+{
+	if (!q)
+		return;
+
+	vfree(q->ring);
+	kfree(q);
+}

linux-7.2.3/net/xdp/xsk_queue.h

@@ -0,0 +1,537 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* XDP user-space ring structure
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#ifndef _LINUX_XSK_QUEUE_H
+#define _LINUX_XSK_QUEUE_H
+
+#include <linux/types.h>
+#include <linux/if_xdp.h>
+#include <net/xdp_sock.h>
+#include <net/xsk_buff_pool.h>
+
+#include "xsk.h"
+
+struct xdp_ring {
+	u32 producer ____cacheline_aligned_in_smp;
+	/* Hinder the adjacent cache prefetcher to prefetch the consumer
+	 * pointer if the producer pointer is touched and vice versa.
+	 */
+	u32 pad1 ____cacheline_aligned_in_smp;
+	u32 consumer ____cacheline_aligned_in_smp;
+	u32 pad2 ____cacheline_aligned_in_smp;
+	u32 flags;
+	u32 pad3 ____cacheline_aligned_in_smp;
+};
+
+/* Used for the RX and TX queues for packets */
+struct xdp_rxtx_ring {
+	struct xdp_ring ptrs;
+	struct xdp_desc desc[] ____cacheline_aligned_in_smp;
+};
+
+/* Used for the fill and completion queues for buffers */
+struct xdp_umem_ring {
+	struct xdp_ring ptrs;
+	u64 desc[] ____cacheline_aligned_in_smp;
+};
+
+struct xsk_queue {
+	u32 ring_mask;
+	u32 nentries;
+	u32 cached_prod;
+	u32 cached_cons;
+	struct xdp_ring *ring;
+	u64 invalid_descs;
+	u64 queue_empty_descs;
+	size_t ring_vmalloc_size;
+	/* Mutual exclusion of the completion ring in the SKB mode.
+	 * Protect: when sockets share a single cq when the same netdev
+	 * and queue id is shared.
+	 */
+	spinlock_t cq_cached_prod_lock;
+};
+
+struct parsed_desc {
+	u32 mb;
+	u32 valid;
+};
+
+struct xsk_tx_batch {
+	u32 tx_descs;
+	u32 reclaim_descs;
+	bool budget_limited;
+};
+
+static inline u32 xsk_tx_batch_cq_descs(const struct xsk_tx_batch *batch)
+{
+	return batch->tx_descs + batch->reclaim_descs;
+}
+
+/* The structure of the shared state of the rings are a simple
+ * circular buffer, as outlined in
+ * Documentation/core-api/circular-buffers.rst. For the Rx and
+ * completion ring, the kernel is the producer and user space is the
+ * consumer. For the Tx and fill rings, the kernel is the consumer and
+ * user space is the producer.
+ *
+ * producer                         consumer
+ *
+ * if (LOAD ->consumer) {  (A)      LOAD.acq ->producer  (C)
+ *    STORE $data                   LOAD $data
+ *    STORE.rel ->producer (B)      STORE.rel ->consumer (D)
+ * }
+ *
+ * (A) pairs with (D), and (B) pairs with (C).
+ *
+ * Starting with (B), it protects the data from being written after
+ * the producer pointer. If this barrier was missing, the consumer
+ * could observe the producer pointer being set and thus load the data
+ * before the producer has written the new data. The consumer would in
+ * this case load the old data.
+ *
+ * (C) protects the consumer from speculatively loading the data before
+ * the producer pointer actually has been read. If we do not have this
+ * barrier, some architectures could load old data as speculative loads
+ * are not discarded as the CPU does not know there is a dependency
+ * between ->producer and data.
+ *
+ * (A) is a control dependency that separates the load of ->consumer
+ * from the stores of $data. In case ->consumer indicates there is no
+ * room in the buffer to store $data we do not. The dependency will
+ * order both of the stores after the loads. So no barrier is needed.
+ *
+ * (D) protects the load of the data to be observed to happen after the
+ * store of the consumer pointer. If we did not have this memory
+ * barrier, the producer could observe the consumer pointer being set
+ * and overwrite the data with a new value before the consumer got the
+ * chance to read the old value. The consumer would thus miss reading
+ * the old entry and very likely read the new entry twice, once right
+ * now and again after circling through the ring.
+ */
+
+/* The operations on the rings are the following:
+ *
+ * producer                           consumer
+ *
+ * RESERVE entries                    PEEK in the ring for entries
+ * WRITE data into the ring           READ data from the ring
+ * SUBMIT entries                     RELEASE entries
+ *
+ * The producer reserves one or more entries in the ring. It can then
+ * fill in these entries and finally submit them so that they can be
+ * seen and read by the consumer.
+ *
+ * The consumer peeks into the ring to see if the producer has written
+ * any new entries. If so, the consumer can then read these entries
+ * and when it is done reading them release them back to the producer
+ * so that the producer can use these slots to fill in new entries.
+ *
+ * The function names below reflect these operations.
+ */
+
+/* Functions that read and validate content from consumer rings. */
+
+static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+	u32 idx = cached_cons & q->ring_mask;
+
+	*addr = ring->desc[idx];
+}
+
+static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
+{
+	if (q->cached_cons != q->cached_prod) {
+		__xskq_cons_read_addr_unchecked(q, q->cached_cons, addr);
+		return true;
+	}
+
+	return false;
+}
+
+static inline bool xp_unused_options_set(u32 options)
+{
+	return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA);
+}
+
+static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
+					    struct xdp_desc *desc)
+{
+	u64 len = desc->len;
+	u64 addr, offset;
+
+	if (!len)
+		return false;
+
+	/* Can overflow if desc->addr < pool->tx_metadata_len */
+	if (check_sub_overflow(desc->addr, pool->tx_metadata_len, &addr))
+		return false;
+
+	offset = addr & (pool->chunk_size - 1);
+
+	/*
+	 * Can't overflow: @offset is guaranteed to be < ``U32_MAX``
+	 * (pool->chunk_size is ``u32``), @len is guaranteed
+	 * to be <= ``U32_MAX``.
+	 */
+	if (offset + len + pool->tx_metadata_len > pool->chunk_size)
+		return false;
+
+	if (addr >= pool->addrs_cnt)
+		return false;
+
+	if (xp_unused_options_set(desc->options))
+		return false;
+
+	return true;
+}
+
+static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
+					      struct xdp_desc *desc)
+{
+	u64 len = desc->len;
+	u64 addr, end;
+
+	if (!len)
+		return false;
+
+	/* Can't overflow: @len is guaranteed to be <= ``U32_MAX`` */
+	len += pool->tx_metadata_len;
+	if (len > pool->chunk_size)
+		return false;
+
+	/* Can overflow if desc->addr is close to 0 */
+	if (check_sub_overflow(xp_unaligned_add_offset_to_addr(desc->addr),
+			       pool->tx_metadata_len, &addr))
+		return false;
+
+	if (addr >= pool->addrs_cnt)
+		return false;
+
+	/* Can overflow if pool->addrs_cnt is high enough */
+	if (check_add_overflow(addr, len, &end) || end > pool->addrs_cnt)
+		return false;
+
+	if (xp_desc_crosses_non_contig_pg(pool, addr, len))
+		return false;
+
+	if (xp_unused_options_set(desc->options))
+		return false;
+
+	return true;
+}
+
+static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
+				    struct xdp_desc *desc)
+{
+	return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) :
+		xp_aligned_validate_desc(pool, desc);
+}
+
+static inline bool xskq_has_descs(struct xsk_queue *q)
+{
+	return q->cached_cons != q->cached_prod;
+}
+
+static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
+					   struct xdp_desc *d,
+					   struct xsk_buff_pool *pool)
+{
+	if (!xp_validate_desc(pool, d)) {
+		q->invalid_descs++;
+		return false;
+	}
+	return true;
+}
+
+static inline bool xskq_cons_read_desc(struct xsk_queue *q,
+				       struct xdp_desc *desc,
+				       struct xsk_buff_pool *pool)
+{
+	if (q->cached_cons != q->cached_prod) {
+		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+		u32 idx = q->cached_cons & q->ring_mask;
+
+		*desc = ring->desc[idx];
+		return xskq_cons_is_valid_desc(q, desc, pool);
+	}
+
+	q->queue_empty_descs++;
+	return false;
+}
+
+static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons += cnt;
+}
+
+static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool,
+			      struct xdp_desc *desc, struct parsed_desc *parsed)
+{
+	parsed->valid = xskq_cons_is_valid_desc(q, desc, pool);
+	parsed->mb = xp_mb_desc(desc);
+}
+
+static inline struct xsk_tx_batch
+xskq_cons_read_desc_batch(struct xdp_sock *xs, struct xsk_buff_pool *pool,
+			  struct xdp_desc *descs, u32 max)
+{
+	bool drain = READ_ONCE(xs->drain_cont);
+	u32 cached_cons, nb_entries = 0;
+	struct xsk_tx_batch batch = {};
+	struct xsk_queue *q = xs->tx;
+	u32 nr_frags = 0;
+
+	cached_cons = q->cached_cons;
+
+	while (cached_cons != q->cached_prod && nb_entries < max) {
+		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+		u32 idx = cached_cons & q->ring_mask;
+		struct parsed_desc parsed;
+
+		descs[nb_entries] = ring->desc[idx];
+		cached_cons++;
+		parse_desc(q, pool, &descs[nb_entries], &parsed);
+		if (unlikely(!parsed.valid))
+			drain = true;
+
+		nr_frags++;
+		nb_entries++;
+
+		if (likely(!parsed.mb)) {
+			if (unlikely(drain)) {
+				batch.reclaim_descs = nr_frags;
+				WRITE_ONCE(xs->drain_cont, false);
+				nr_frags = 0;
+				break;
+			}
+
+			batch.tx_descs += nr_frags;
+			nr_frags = 0;
+			continue;
+		}
+
+		if (nr_frags == pool->xdp_zc_max_segs)
+			drain = true;
+	}
+
+	if (nr_frags) {
+		if (drain) {
+			batch.reclaim_descs = nr_frags;
+			WRITE_ONCE(xs->drain_cont, true);
+		} else {
+			if (nb_entries == max)
+				batch.budget_limited = true;
+			cached_cons -= nr_frags;
+		}
+	}
+
+	/* Release valid plus any invalid entries */
+	xskq_cons_release_n(q, cached_cons - q->cached_cons);
+	return batch;
+}
+
+/* Functions for consumers */
+
+static inline void __xskq_cons_release(struct xsk_queue *q)
+{
+	smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */
+}
+
+static inline void __xskq_cons_peek(struct xsk_queue *q)
+{
+	/* Refresh the local pointer */
+	q->cached_prod = smp_load_acquire(&q->ring->producer);  /* C, matches B */
+}
+
+static inline void xskq_cons_get_entries(struct xsk_queue *q)
+{
+	__xskq_cons_release(q);
+	__xskq_cons_peek(q);
+}
+
+static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max)
+{
+	u32 entries = q->cached_prod - q->cached_cons;
+
+	if (entries >= max)
+		return max;
+
+	__xskq_cons_peek(q);
+	entries = q->cached_prod - q->cached_cons;
+
+	return entries >= max ? max : entries;
+}
+
+static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
+{
+	if (q->cached_prod == q->cached_cons)
+		xskq_cons_get_entries(q);
+	return xskq_cons_read_addr_unchecked(q, addr);
+}
+
+static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
+				       struct xdp_desc *desc,
+				       struct xsk_buff_pool *pool)
+{
+	if (q->cached_prod == q->cached_cons)
+		xskq_cons_get_entries(q);
+	return xskq_cons_read_desc(q, desc, pool);
+}
+
+/* To improve performance in the xskq_cons_release functions, only update local state here.
+ * Reflect this to global state when we get new entries from the ring in
+ * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop.
+ */
+static inline void xskq_cons_release(struct xsk_queue *q)
+{
+	q->cached_cons++;
+}
+
+static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons -= cnt;
+}
+
+static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
+{
+	/* No barriers needed since data is not accessed */
+	return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer);
+}
+
+/* Functions for producers */
+
+static inline u32 xskq_get_prod(struct xsk_queue *q)
+{
+	return READ_ONCE(q->ring->producer);
+}
+
+static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
+{
+	u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
+
+	if (free_entries >= max)
+		return max;
+
+	/* Refresh the local tail pointer */
+	q->cached_cons = READ_ONCE(q->ring->consumer);
+	free_entries = q->nentries - (q->cached_prod - q->cached_cons);
+
+	return free_entries >= max ? max : free_entries;
+}
+
+static inline bool xskq_prod_is_full(struct xsk_queue *q)
+{
+	return xskq_prod_nb_free(q, 1) ? false : true;
+}
+
+static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_prod -= cnt;
+}
+
+static inline int xskq_prod_reserve(struct xsk_queue *q)
+{
+	if (xskq_prod_is_full(q))
+		return -ENOSPC;
+
+	/* A, matches D */
+	q->cached_prod++;
+	return 0;
+}
+
+static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+	if (xskq_prod_is_full(q))
+		return -ENOSPC;
+
+	/* A, matches D */
+	ring->desc[q->cached_prod++ & q->ring_mask] = addr;
+	return 0;
+}
+
+static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+	ring->desc[idx & q->ring_mask] = addr;
+}
+
+static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
+					      u32 nb_entries)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+	u32 i, cached_prod;
+
+	/* A, matches D */
+	cached_prod = q->cached_prod;
+	for (i = 0; i < nb_entries; i++)
+		ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr;
+	q->cached_prod = cached_prod;
+}
+
+static inline void __xskq_prod_reserve_desc(struct xsk_queue *q,
+					    u64 addr, u32 len, u32 flags)
+{
+	struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+	u32 idx;
+
+	/* A, matches D */
+	idx = q->cached_prod++ & q->ring_mask;
+	ring->desc[idx].addr = addr;
+	ring->desc[idx].len = len;
+	ring->desc[idx].options = flags;
+}
+
+static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
+					 u64 addr, u32 len, u32 flags)
+{
+	if (xskq_prod_is_full(q))
+		return -ENOBUFS;
+
+	__xskq_prod_reserve_desc(q, addr, len, flags);
+
+	return 0;
+}
+
+static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx)
+{
+	smp_store_release(&q->ring->producer, idx); /* B, matches C */
+}
+
+static inline void xskq_prod_submit(struct xsk_queue *q)
+{
+	__xskq_prod_submit(q, q->cached_prod);
+}
+
+static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries)
+{
+	__xskq_prod_submit(q, q->ring->producer + nb_entries);
+}
+
+static inline bool xskq_prod_is_empty(struct xsk_queue *q)
+{
+	/* No barriers needed since data is not accessed */
+	return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer);
+}
+
+/* For both producers and consumers */
+
+static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
+{
+	return q ? q->invalid_descs : 0;
+}
+
+static inline u64 xskq_nb_queue_empty_descs(struct xsk_queue *q)
+{
+	return q ? q->queue_empty_descs : 0;
+}
+
+struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
+void xskq_destroy(struct xsk_queue *q_ops);
+
+#endif /* _LINUX_XSK_QUEUE_H */

linux-7.2.3/net/xdp/xskmap.c

@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XSKMAP used for AF_XDP sockets
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <net/xdp_sock.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/btf_ids.h>
+
+#include "xsk.h"
+
+static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
+					       struct xdp_sock __rcu **map_entry)
+{
+	struct xsk_map_node *node;
+
+	node = bpf_map_kzalloc(&map->map, sizeof(*node),
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (!node)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_inc(&map->map);
+	atomic_inc(&map->count);
+
+	node->map = map;
+	node->map_entry = map_entry;
+	return node;
+}
+
+static void xsk_map_node_free(struct xsk_map_node *node)
+{
+	struct xsk_map *map = node->map;
+
+	bpf_map_put(&node->map->map);
+	kfree(node);
+	atomic_dec(&map->count);
+}
+
+static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
+{
+	spin_lock_bh(&xs->map_list_lock);
+	list_add_tail(&node->node, &xs->map_list);
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
+static void xsk_map_sock_delete(struct xdp_sock *xs,
+				struct xdp_sock __rcu **map_entry)
+{
+	struct xsk_map_node *n, *tmp;
+
+	spin_lock_bh(&xs->map_list_lock);
+	list_for_each_entry_safe(n, tmp, &xs->map_list, node) {
+		if (map_entry == n->map_entry) {
+			list_del(&n->node);
+			xsk_map_node_free(n);
+		}
+	}
+	spin_unlock_bh(&xs->map_list_lock);
+}
+
+static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
+{
+	struct xsk_map *m;
+	int numa_node;
+	u64 size;
+
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 ||
+	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
+		return ERR_PTR(-EINVAL);
+
+	numa_node = bpf_map_attr_numa_node(attr);
+	size = struct_size(m, xsk_map, attr->max_entries);
+
+	m = bpf_map_area_alloc(size, numa_node);
+	if (!m)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&m->map, attr);
+	spin_lock_init(&m->lock);
+
+	return &m->map;
+}
+
+static u64 xsk_map_mem_usage(const struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	return struct_size(m, xsk_map, map->max_entries) +
+		   (u64)atomic_read(&m->count) * sizeof(struct xsk_map_node);
+}
+
+static void xsk_map_free(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	synchronize_net();
+	bpf_map_area_free(m);
+}
+
+static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= m->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == m->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
+	struct bpf_insn *insn = insn_buf;
+
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
+	*insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
+}
+
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
+static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held());
+}
+
+static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return __xsk_map_lookup_elem(map, *(u32 *)key);
+}
+
+static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static long xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *xs, *old_xs;
+	u32 i = *(u32 *)key, fd = *(u32 *)value;
+	struct xsk_map_node *node;
+	struct socket *sock;
+	int err;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(i >= m->map.max_entries))
+		return -E2BIG;
+
+	sock = sockfd_lookup(fd, &err);
+	if (!sock)
+		return err;
+
+	if (sock->sk->sk_family != PF_XDP) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	xs = (struct xdp_sock *)sock->sk;
+	if (!READ_ONCE(xs->rx)) {
+		sockfd_put(sock);
+		return -ENOBUFS;
+	}
+
+	map_entry = &m->xsk_map[i];
+	node = xsk_map_node_alloc(m, map_entry);
+	if (IS_ERR(node)) {
+		sockfd_put(sock);
+		return PTR_ERR(node);
+	}
+
+	spin_lock_bh(&m->lock);
+	old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock));
+	if (old_xs == xs) {
+		err = 0;
+		goto out;
+	} else if (old_xs && map_flags == BPF_NOEXIST) {
+		err = -EEXIST;
+		goto out;
+	} else if (!old_xs && map_flags == BPF_EXIST) {
+		err = -ENOENT;
+		goto out;
+	}
+	xsk_map_sock_add(xs, node);
+	rcu_assign_pointer(*map_entry, xs);
+	if (old_xs)
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
+	sockfd_put(sock);
+	return 0;
+
+out:
+	spin_unlock_bh(&m->lock);
+	sockfd_put(sock);
+	xsk_map_node_free(node);
+	return err;
+}
+
+static long xsk_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *old_xs;
+	u32 k = *(u32 *)key;
+
+	if (k >= map->max_entries)
+		return -EINVAL;
+
+	spin_lock_bh(&m->lock);
+	map_entry = &m->xsk_map[k];
+	old_xs = unrcu_pointer(xchg(map_entry, NULL));
+	if (old_xs)
+		xsk_map_sock_delete(old_xs, map_entry);
+	spin_unlock_bh(&m->lock);
+
+	return 0;
+}
+
+static long xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, index, flags, 0,
+				      __xsk_map_lookup_elem);
+}
+
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock __rcu **map_entry)
+{
+	spin_lock_bh(&map->lock);
+	if (rcu_access_pointer(*map_entry) == xs) {
+		rcu_assign_pointer(*map_entry, NULL);
+		xsk_map_sock_delete(xs, map_entry);
+	}
+	spin_unlock_bh(&map->lock);
+}
+
+static bool xsk_map_meta_equal(const struct bpf_map *meta0,
+			       const struct bpf_map *meta1)
+{
+	return meta0->max_entries == meta1->max_entries &&
+		bpf_map_meta_equal(meta0, meta1);
+}
+
+BTF_ID_LIST_SINGLE(xsk_map_btf_ids, struct, xsk_map)
+const struct bpf_map_ops xsk_map_ops = {
+	.map_meta_equal = xsk_map_meta_equal,
+	.map_alloc = xsk_map_alloc,
+	.map_free = xsk_map_free,
+	.map_get_next_key = xsk_map_get_next_key,
+	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_gen_lookup = xsk_map_gen_lookup,
+	.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
+	.map_update_elem = xsk_map_update_elem,
+	.map_delete_elem = xsk_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = xsk_map_mem_usage,
+	.map_btf_id = &xsk_map_btf_ids[0],
+	.map_redirect = xsk_map_redirect,
+};