Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 280 insertions, 0 deletions

diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
new file mode 100644
index 000000000..025ea7987
--- /dev/null
+++ b/drivers/net/netdevsim/ethtool.c
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/debugfs.h>
+#include <linux/random.h>
+#include <net/netdev_queues.h>
+
+#include "netdevsim.h"
+
+static void
+nsim_get_pause_stats(struct net_device *dev,
+		     struct ethtool_pause_stats *pause_stats)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (ns->ethtool.pauseparam.report_stats_rx)
+		pause_stats->rx_pause_frames = 1;
+	if (ns->ethtool.pauseparam.report_stats_tx)
+		pause_stats->tx_pause_frames = 2;
+}
+
+static void
+nsim_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	pause->autoneg = 0; /* We don't support ksettings, so can't pretend */
+	pause->rx_pause = ns->ethtool.pauseparam.rx;
+	pause->tx_pause = ns->ethtool.pauseparam.tx;
+}
+
+static int
+nsim_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (pause->autoneg)
+		return -EINVAL;
+
+	ns->ethtool.pauseparam.rx = pause->rx_pause;
+	ns->ethtool.pauseparam.tx = pause->tx_pause;
+	return 0;
+}
+
+static int nsim_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(coal, &ns->ethtool.coalesce, sizeof(ns->ethtool.coalesce));
+	return 0;
+}
+
+static int nsim_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *coal,
+			     struct kernel_ethtool_coalesce *kernel_coal,
+			     struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(&ns->ethtool.coalesce, coal, sizeof(ns->ethtool.coalesce));
+	return 0;
+}
+
+static void nsim_get_ringparam(struct net_device *dev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring));
+	kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX;
+
+	if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
+		kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED;
+}
+
+static int nsim_set_ringparam(struct net_device *dev,
+			      struct ethtool_ringparam *ring,
+			      struct kernel_ethtool_ringparam *kernel_ring,
+			      struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	ns->ethtool.ring.rx_pending = ring->rx_pending;
+	ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending;
+	ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending;
+	ns->ethtool.ring.tx_pending = ring->tx_pending;
+	return 0;
+}
+
+static void
+nsim_get_channels(struct net_device *dev, struct ethtool_channels *ch)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	ch->max_combined = ns->nsim_bus_dev->num_queues;
+	ch->combined_count = ns->ethtool.channels;
+}
+
+static void
+nsim_wake_queues(struct net_device *dev)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct netdevsim *peer;
+
+	synchronize_net();
+	netif_tx_wake_all_queues(dev);
+
+	rcu_read_lock();
+	peer = rcu_dereference(ns->peer);
+	if (peer)
+		netif_tx_wake_all_queues(peer->netdev);
+	rcu_read_unlock();
+}
+
+static int
+nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	int err;
+
+	err = netif_set_real_num_queues(dev, ch->combined_count,
+					ch->combined_count);
+	if (err)
+		return err;
+
+	ns->ethtool.channels = ch->combined_count;
+
+	/* Only wake up queues if devices are linked */
+	if (rcu_access_pointer(ns->peer))
+		nsim_wake_queues(dev);
+
+	return 0;
+}
+
+static int
+nsim_get_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (ns->ethtool.get_err)
+		return -ns->ethtool.get_err;
+	memcpy(fecparam, &ns->ethtool.fec, sizeof(ns->ethtool.fec));
+	return 0;
+}
+
+static int
+nsim_set_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	u32 fec;
+
+	if (ns->ethtool.set_err)
+		return -ns->ethtool.set_err;
+	memcpy(&ns->ethtool.fec, fecparam, sizeof(ns->ethtool.fec));
+	fec = fecparam->fec;
+	if (fec == ETHTOOL_FEC_AUTO)
+		fec |= ETHTOOL_FEC_OFF;
+	fec |= ETHTOOL_FEC_NONE;
+	ns->ethtool.fec.active_fec = 1 << (fls(fec) - 1);
+	return 0;
+}
+
+static const struct ethtool_fec_hist_range netdevsim_fec_ranges[] = {
+	{ 0, 0},
+	{ 1, 3},
+	{ 4, 7},
+	{ 0, 0}
+};
+
+static void
+nsim_get_fec_stats(struct net_device *dev, struct ethtool_fec_stats *fec_stats,
+		   struct ethtool_fec_hist *hist)
+{
+	struct ethtool_fec_hist_value *values = hist->values;
+
+	hist->ranges = netdevsim_fec_ranges;
+
+	fec_stats->corrected_blocks.total = 123;
+	fec_stats->uncorrectable_blocks.total = 4;
+
+	values[0].per_lane[0] = 125;
+	values[0].per_lane[1] = 120;
+	values[0].per_lane[2] = 100;
+	values[0].per_lane[3] = 100;
+	values[1].sum = 12;
+	values[2].sum = 2;
+	values[2].per_lane[0] = 2;
+	values[2].per_lane[1] = 0;
+	values[2].per_lane[2] = 0;
+	values[2].per_lane[3] = 0;
+}
+
+static int nsim_get_ts_info(struct net_device *dev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	info->phc_index = mock_phc_index(ns->phc);
+
+	return 0;
+}
+
+static const struct ethtool_ops nsim_ethtool_ops = {
+	.supported_coalesce_params	= ETHTOOL_COALESCE_ALL_PARAMS,
+	.supported_ring_params		= ETHTOOL_RING_USE_TCP_DATA_SPLIT |
+					  ETHTOOL_RING_USE_HDS_THRS,
+	.op_needs_rtnl			= ETHTOOL_OP_NEEDS_RTNL_SCHANNELS,
+	.get_pause_stats	        = nsim_get_pause_stats,
+	.get_pauseparam		        = nsim_get_pauseparam,
+	.set_pauseparam		        = nsim_set_pauseparam,
+	.set_coalesce			= nsim_set_coalesce,
+	.get_coalesce			= nsim_get_coalesce,
+	.get_ringparam			= nsim_get_ringparam,
+	.set_ringparam			= nsim_set_ringparam,
+	.get_channels			= nsim_get_channels,
+	.set_channels			= nsim_set_channels,
+	.get_fecparam			= nsim_get_fecparam,
+	.set_fecparam			= nsim_set_fecparam,
+	.get_fec_stats			= nsim_get_fec_stats,
+	.get_ts_info			= nsim_get_ts_info,
+};
+
+static void nsim_ethtool_ring_init(struct netdevsim *ns)
+{
+	ns->ethtool.ring.rx_pending = 512;
+	ns->ethtool.ring.rx_max_pending = 4096;
+	ns->ethtool.ring.rx_jumbo_max_pending = 4096;
+	ns->ethtool.ring.rx_mini_max_pending = 4096;
+	ns->ethtool.ring.tx_pending = 512;
+	ns->ethtool.ring.tx_max_pending = 4096;
+}
+
+void nsim_ethtool_init(struct netdevsim *ns)
+{
+	struct dentry *ethtool, *dir;
+
+	ns->netdev->ethtool_ops = &nsim_ethtool_ops;
+
+	nsim_ethtool_ring_init(ns);
+
+	ns->ethtool.pauseparam.report_stats_rx = true;
+	ns->ethtool.pauseparam.report_stats_tx = true;
+
+	ns->ethtool.fec.fec = ETHTOOL_FEC_NONE;
+	ns->ethtool.fec.active_fec = ETHTOOL_FEC_NONE;
+
+	ns->ethtool.channels = ns->nsim_bus_dev->num_queues;
+
+	ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir);
+	ns->ethtool_ddir = ethtool;
+
+	debugfs_create_u32("get_err", 0600, ethtool, &ns->ethtool.get_err);
+	debugfs_create_u32("set_err", 0600, ethtool, &ns->ethtool.set_err);
+
+	dir = debugfs_create_dir("pause", ethtool);
+	debugfs_create_bool("report_stats_rx", 0600, dir,
+			    &ns->ethtool.pauseparam.report_stats_rx);
+	debugfs_create_bool("report_stats_tx", 0600, dir,
+			    &ns->ethtool.pauseparam.report_stats_tx);
+
+	dir = debugfs_create_dir("ring", ethtool);
+	debugfs_create_u32("rx_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_max_pending);
+	debugfs_create_u32("rx_jumbo_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_jumbo_max_pending);
+	debugfs_create_u32("rx_mini_max_pending", 0600, dir,
+			   &ns->ethtool.ring.rx_mini_max_pending);
+	debugfs_create_u32("tx_max_pending", 0600, dir,
+			   &ns->ethtool.ring.tx_max_pending);
+}
+
+void nsim_ethtool_fini(struct netdevsim *ns)
+{
+	debugfs_remove(ns->ethtool_ddir);
+}