This is the 5.4.177 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmH+YWMACgkQONu9yGCS
 aT5l4A/9H/kD2Z+YQMVRF9YHaL3ZSvd8FE6q1qiX8zldr/z9ZB5LM/4qTvsDAsyQ
 RweeFu0GEnPP9R5NrMCikI/rU4mslOFfSt7CiffqZaZK+hLlmj/OKcm9TFhuFXWh
 zX7pdVukw2mCnI6nQ0jD5nfdZMi3l9GAkMxShsU0QOKA29DmdWeoVmxHSAaaVWoD
 FhBmXlO+l3Y42NP3fqmpaSpVhr/f31c3zaP9O62rXc2BRQCBIunmywezt23QsYEL
 fvELgefQTX05ne/Ek+wQQkGBkQNYBK1zaq7nCYASypHsVOi6oa/6pgVVCJWw/LA4
 AHj8iGUnZ7NHi0+4i44HrQn2P1UH/gb65lxHNh4SbhNY3gDb+jjvCLMO6zdUdaz+
 0iRY1Th2aqGi/OzHHatt6TyOxhJ1jHbgGttPY2dzy5/nH3fw6pnmIaY5HZdVpqm5
 gqE4dOUNBdnXHpnDFQBgd9xyqr6aHKjnTQcLuBji3G/EcnCmetHeGUXri/CdtyPj
 vcbj+VXCQmCx3TinsUrNmevN8JA0tPDHha5u62IPrpjSb5EE0+sxbTSnZ8QazMI6
 MSllNHWTaDFPFjWYNFNDyYLINMPY9l2FZtgZttjbCnbyxZ8ytP9OnC2V7ZAt2y0G
 aBBn97AT2h7CM/tRm3bvK5o2aAcOs25fo9mcvJeley3mlIjgFcI=
 =3OwF
 -----END PGP SIGNATURE-----

Merge 5.4.177 into android11-5.4-lts

Changes in 5.4.177
	PCI: pciehp: Fix infinite loop in IRQ handler upon power fault
	psi: Fix uaf issue when psi trigger is destroyed while being polled
	cgroup-v1: Require capabilities to set release_agent
	ipheth: fix EOVERFLOW in ipheth_rcvbulk_callback
	net: amd-xgbe: ensure to reset the tx_timer_active flag
	net: amd-xgbe: Fix skb data length underflow
	net: sched: fix use-after-free in tc_new_tfilter()
	rtnetlink: make sure to refresh master_dev/m_ops in __rtnl_newlink()
	cpuset: Fix the bug that subpart_cpus updated wrongly in update_cpumask()
	af_packet: fix data-race in packet_setsockopt / packet_setsockopt
	Linux 5.4.177

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I41791ffa382aae8c424ca4950ca2b367302ef59a

Documentation/accounting/psi.rst

@@ -90,7 +90,8 @@ Triggers can be set on more than one psi metric and more than one trigger
 for the same psi metric can be specified. However for each trigger a separate
 file descriptor is required to be able to poll it separately from others,
 therefore for each trigger a separate open() syscall should be made even
-when opening the same psi interface file.
+when opening the same psi interface file. Write operations to a file descriptor
+with an already existing psi trigger will fail with EBUSY.
 
 Monitors activate only when system enters stall state for the monitored
 psi metric and deactivates upon exit from the stall state. While system is

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 176
+SUBLEVEL = 177
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

@@ -721,7 +721,9 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 		if (!channel->tx_ring)
 			break;
 
+		/* Deactivate the Tx timer */
 		del_timer_sync(&channel->tx_timer);
+		channel->tx_timer_active = 0;
 	}
 }
 
@@ -2765,6 +2767,14 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
 			len += buf2_len;
 
+			if (buf2_len > rdata->rx.buf.dma_len) {
+				/* Hardware inconsistency within the descriptors
+				 * that has resulted in a length underflow.
+				 */
+				error = 1;
+				goto skip_data;
+			}
+
 			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
 						      buf1_len);
@@ -2794,8 +2804,10 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		if (!last || context_next)
 			goto read_again;
 
-		if (!skb)
+		if (!skb || error) {
+			dev_kfree_skb(skb);
 			goto next_packet;
+		}
 
 		/* Be sure we don't exceed the configured MTU */
 		max_len = netdev->mtu + ETH_HLEN;

drivers/net/usb/ipheth.c

@@ -121,7 +121,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone)
 	if (tx_buf == NULL)
 		goto free_rx_urb;
 
-	rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE,
+	rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
 				    GFP_KERNEL, &rx_urb->transfer_dma);
 	if (rx_buf == NULL)
 		goto free_tx_buf;
@@ -146,7 +146,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone)
 
 static void ipheth_free_urbs(struct ipheth_device *iphone)
 {
-	usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->rx_buf,
+	usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf,
 			  iphone->rx_urb->transfer_dma);
 	usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf,
 			  iphone->tx_urb->transfer_dma);
@@ -317,7 +317,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags)
 
 	usb_fill_bulk_urb(dev->rx_urb, udev,
 			  usb_rcvbulkpipe(udev, dev->bulk_in),
-			  dev->rx_buf, IPHETH_BUF_SIZE,
+			  dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
 			  ipheth_rcvbulk_callback,
 			  dev);
 	dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;

drivers/pci/hotplug/pciehp_hpc.c

@@ -577,6 +577,8 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	 */
 	if (ctrl->power_fault_detected)
 		status &= ~PCI_EXP_SLTSTA_PFD;
+	else if (status & PCI_EXP_SLTSTA_PFD)
+		ctrl->power_fault_detected = true;
 
 	events |= status;
 	if (!events) {
@@ -586,7 +588,7 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	}
 
 	if (status) {
-		pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events);
+		pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, status);
 
 		/*
 		 * In MSI mode, all event bits must be zero before the port
@@ -660,8 +662,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	}
 
 	/* Check Power Fault Detected */
-	if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
-		ctrl->power_fault_detected = 1;
+	if (events & PCI_EXP_SLTSTA_PFD) {
 		ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(ctrl));
 		pciehp_set_indicators(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF,
 				      PCI_EXP_SLTCTL_ATTN_IND_ON);

include/linux/psi.h

@@ -31,7 +31,7 @@ void cgroup_move_task(struct task_struct *p, struct css_set *to);
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
 			char *buf, size_t nbytes, enum psi_res res);
-void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);
+void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
 			poll_table *wait);

include/linux/psi_types.h

@@ -120,9 +120,6 @@ struct psi_trigger {
 	 * events to one per window
 	 */
 	u64 last_event_time;
-
-	/* Refcounting to prevent premature destruction */
-	struct kref refcount;
 };
 
 struct psi_group {

kernel/cgroup/cgroup-v1.c

@@ -552,6 +552,14 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
 
+	/*
+	 * Release agent gets called with all capabilities,
+	 * require capabilities to set release agent.
+	 */
+	if ((of->file->f_cred->user_ns != &init_user_ns) ||
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
@@ -964,6 +972,12 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		/* Specifying two release agents is forbidden */
 		if (ctx->release_agent)
 			return cg_invalf(fc, "cgroup1: release_agent respecified");
+		/*
+		 * Release agent gets called with all capabilities,
+		 * require capabilities to set release agent.
+		 */
+		if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN))
+			return cg_invalf(fc, "cgroup1: Setting release_agent not allowed");
 		ctx->release_agent = param->string;
 		param->string = NULL;
 		break;

kernel/cgroup/cgroup.c

@@ -3659,6 +3659,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 	cgroup_get(cgrp);
 	cgroup_kn_unlock(of->kn);
 
+	/* Allow only one trigger per file descriptor */
+	if (of->priv) {
+		cgroup_put(cgrp);
+		return -EBUSY;
+	}
+
 	psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;
 	new = psi_trigger_create(psi, buf, nbytes, res);
 	if (IS_ERR(new)) {
@@ -3666,8 +3672,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 		return PTR_ERR(new);
 	}
 
-	psi_trigger_replace(&of->priv, new);
-
+	smp_store_release(&of->priv, new);
 	cgroup_put(cgrp);
 
 	return nbytes;
@@ -3702,7 +3707,7 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
-	psi_trigger_replace(&of->priv, NULL);
+	psi_trigger_destroy(of->priv);
 }
 #endif /* CONFIG_PSI */
 

kernel/cgroup/cpuset.c

@@ -1547,8 +1547,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	 * Make sure that subparts_cpus is a subset of cpus_allowed.
 	 */
 	if (cs->nr_subparts_cpus) {
-		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
-			       cs->cpus_allowed);
+		cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed);
 		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
 	}
 	spin_unlock_irq(&callback_lock);

kernel/sched/psi.c

@@ -1046,7 +1046,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->event = 0;
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
-	kref_init(&t->refcount);
 
 	mutex_lock(&group->trigger_lock);
 
@@ -1079,15 +1078,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	return t;
 }
 
-static void psi_trigger_destroy(struct kref *ref)
+void psi_trigger_destroy(struct psi_trigger *t)
 {
-	struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
-	struct psi_group *group = t->group;
+	struct psi_group *group;
 	struct kthread_worker *kworker_to_destroy = NULL;
 
-	if (static_branch_likely(&psi_disabled))
+	/*
+	 * We do not check psi_disabled since it might have been disabled after
+	 * the trigger got created.
+	 */
+	if (!t)
 		return;
 
+	group = t->group;
 	/*
 	 * Wakeup waiters to stop polling. Can happen if cgroup is deleted
 	 * from under a polling process.
@@ -1122,9 +1125,9 @@ static void psi_trigger_destroy(struct kref *ref)
 	mutex_unlock(&group->trigger_lock);
 
 	/*
-	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_kworker RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_kworker
+	 * Wait for psi_schedule_poll_work RCU to complete its read-side
+	 * critical section before destroying the trigger and optionally the
+	 * poll_task.
 	 */
 	synchronize_rcu();
 	/*
@@ -1146,18 +1149,6 @@ static void psi_trigger_destroy(struct kref *ref)
 	kfree(t);
 }
 
-void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new)
-{
-	struct psi_trigger *old = *trigger_ptr;
-
-	if (static_branch_likely(&psi_disabled))
-		return;
-
-	rcu_assign_pointer(*trigger_ptr, new);
-	if (old)
-		kref_put(&old->refcount, psi_trigger_destroy);
-}
-
 __poll_t psi_trigger_poll(void **trigger_ptr,
 				struct file *file, poll_table *wait)
 {
@@ -1167,24 +1158,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr,
 	if (static_branch_likely(&psi_disabled))
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
 
-	rcu_read_lock();
-
-	t = rcu_dereference(*(void __rcu __force **)trigger_ptr);
-	if (!t) {
-		rcu_read_unlock();
+	t = smp_load_acquire(trigger_ptr);
+	if (!t)
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
-	}
-	kref_get(&t->refcount);
-
-	rcu_read_unlock();
 
 	poll_wait(file, &t->event_wait, wait);
 
 	if (cmpxchg(&t->event, 1, 0) == 1)
 		ret |= EPOLLPRI;
 
-	kref_put(&t->refcount, psi_trigger_destroy);
-
 	return ret;
 }
 
@@ -1208,14 +1190,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 
 	buf[buf_size - 1] = '\0';
 
-	new = psi_trigger_create(&psi_system, buf, nbytes, res);
-	if (IS_ERR(new))
-		return PTR_ERR(new);
-
 	seq = file->private_data;
+
 	/* Take seq->lock to protect seq->private from concurrent writes */
 	mutex_lock(&seq->lock);
-	psi_trigger_replace(&seq->private, new);
+
+	/* Allow only one trigger per file descriptor */
+	if (seq->private) {
+		mutex_unlock(&seq->lock);
+		return -EBUSY;
+	}
+
+	new = psi_trigger_create(&psi_system, buf, nbytes, res);
+	if (IS_ERR(new)) {
+		mutex_unlock(&seq->lock);
+		return PTR_ERR(new);
+	}
+
+	smp_store_release(&seq->private, new);
 	mutex_unlock(&seq->lock);
 
 	return nbytes;
@@ -1250,7 +1242,7 @@ static int psi_fop_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *seq = file->private_data;
 
-	psi_trigger_replace(&seq->private, NULL);
+	psi_trigger_destroy(seq->private);
 	return single_release(inode, file);
 }
 

net/core/rtnetlink.c

@@ -3022,8 +3022,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
 	unsigned char name_assign_type = NET_NAME_USER;
 	struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
-	const struct rtnl_link_ops *m_ops = NULL;
-	struct net_device *master_dev = NULL;
+	const struct rtnl_link_ops *m_ops;
+	struct net_device *master_dev;
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
 	struct nlattr *tb[IFLA_MAX + 1];
@@ -3063,6 +3063,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			dev = NULL;
 	}
 
+	master_dev = NULL;
+	m_ops = NULL;
 	if (dev) {
 		master_dev = netdev_master_upper_dev_get(dev);
 		if (master_dev)

net/packet/af_packet.c

@@ -1728,7 +1728,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		err = -ENOSPC;
 		if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
 			__dev_remove_pack(&po->prot_hook);
-			po->fanout = match;
+
+			/* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
+			WRITE_ONCE(po->fanout, match);
+
 			po->rollover = rollover;
 			rollover = NULL;
 			refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
@@ -3874,7 +3877,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 	}
 	case PACKET_FANOUT_DATA:
 	{
-		if (!po->fanout)
+		/* Paired with the WRITE_ONCE() in fanout_add() */
+		if (!READ_ONCE(po->fanout))
 			return -EINVAL;
 
 		return fanout_set_data(po, optval, optlen);

net/sched/cls_api.c

@@ -1928,9 +1928,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	bool prio_allocate;
 	u32 parent;
 	u32 chain_index;
-	struct Qdisc *q = NULL;
+	struct Qdisc *q;
 	struct tcf_chain_info chain_info;
-	struct tcf_chain *chain = NULL;
+	struct tcf_chain *chain;
 	struct tcf_block *block;
 	struct tcf_proto *tp;
 	unsigned long cl;
@@ -1958,6 +1958,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	tp = NULL;
 	cl = 0;
 	block = NULL;
+	q = NULL;
+	chain = NULL;
 
 	if (prio == 0) {
 		/* If no priority is provided by the user,
@@ -2764,8 +2766,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
 	struct tcmsg *t;
 	u32 parent;
 	u32 chain_index;
-	struct Qdisc *q = NULL;
-	struct tcf_chain *chain = NULL;
+	struct Qdisc *q;
+	struct tcf_chain *chain;
 	struct tcf_block *block;
 	unsigned long cl;
 	int err;
@@ -2775,6 +2777,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
 		return -EPERM;
 
 replay:
+	q = NULL;
 	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
 				     rtm_tca_policy, extack);
 	if (err < 0)