Merge tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf.

  Current release - regressions:

   - vhost_net: fix OoB on sendmsg() failure

   - mlx5: bridge, fix uninitialized variable usage

   - bnxt_en: fix error recovery regression

  Current release - new code bugs:

   - bpf, mm: fix lockdep warning triggered by stack_map_get_build_id_offset()

  Previous releases - regressions:

   - r6040: restore MDIO clock frequency after MAC reset

   - tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()

   - dsa: flush switchdev workqueue before tearing down CPU/DSA ports

  Previous releases - always broken:

   - ptp: dp83640: don't define PAGE0, avoid compiler warning

   - igc: fix tunnel segmentation offloads

   - phylink: update SFP selected interface on advertising changes

   - stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume

   - mlx5e: fix mutual exclusion between CQE compression and HW TS

  Misc:

   - bpf, cgroups: fix cgroup v2 fallback on v1/v2 mixed mode

   - sfc: fallback for lack of xdp tx queues

   - hns3: add option to turn off page pool feature"

* tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
  mlxbf_gige: clear valid_polarity upon open
  igc: fix tunnel offloading
  net/{mlx5|nfp|bnxt}: Remove unnecessary RTNL lock assert
  net: wan: wanxl: define CROSS_COMPILE_M68K
  selftests: nci: replace unsigned int with int
  net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports
  Revert "net: phy: Uniform PHY driver access"
  net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup
  ptp: dp83640: don't define PAGE0
  bnx2x: Fix enabling network interfaces without VFs
  Revert "Revert "ipv4: fix memory leaks in ip_cmsg_send() callers""
  tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()
  net-caif: avoid user-triggerable WARN_ON(1)
  bpf, selftests: Add test case for mixed cgroup v1/v2
  bpf, selftests: Add cgroup v1 net_cls classid helpers
  bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode
  bpf: Add oversize check before call kvcalloc()
  net: hns3: fix the timing issue of VF clearing interrupt sources
  net: hns3: fix the exception when query imp info
  net: hns3: disable mac in flr process
  ...

kernel/bpf/disasm.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2016 Facebook
  */

kernel/bpf/disasm.h

@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2016 Facebook
  */

kernel/bpf/stackmap.c

@@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	 * with build_id.
 	 */
 	if (!user || !current || !current->mm || irq_work_busy ||
-	    !mmap_read_trylock_non_owner(current->mm)) {
+	    !mmap_read_trylock(current->mm)) {
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
@@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 
 	if (!work) {
-		mmap_read_unlock_non_owner(current->mm);
+		mmap_read_unlock(current->mm);
 	} else {
 		work->mm = current->mm;
+
+		/* The lock will be released once we're out of interrupt
+		 * context. Tell lockdep that we've released it now so
+		 * it doesn't complain that we forgot to release it.
+		 */
+		rwsem_release(&current->mm->mmap_lock.dep_map, _RET_IP_);
 		irq_work_queue(&work->irq_work);
 	}
 }

kernel/bpf/verifier.c

@@ -9912,6 +9912,8 @@ static int check_btf_line(struct bpf_verifier_env *env,
 	nr_linfo = attr->line_info_cnt;
 	if (!nr_linfo)
 		return 0;
+	if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info))
+		return -EINVAL;
 
 	rec_size = attr->line_info_rec_size;
 	if (rec_size < MIN_BPF_LINEINFO_SIZE ||

kernel/cgroup/cgroup.c

@@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v)
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-
-DEFINE_SPINLOCK(cgroup_sk_update_lock);
-static bool cgroup_sk_alloc_disabled __read_mostly;
-
-void cgroup_sk_alloc_disable(void)
-{
-	if (cgroup_sk_alloc_disabled)
-		return;
-	pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n");
-	cgroup_sk_alloc_disabled = true;
-}
-
-#else
-
-#define cgroup_sk_alloc_disabled	false
-
-#endif
-
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled) {
-		skcd->no_refcnt = 1;
-		return;
-	}
-
 	/* Don't associate the sock with unrelated interrupted task's cgroup. */
 	if (in_interrupt())
 		return;
 
 	rcu_read_lock();
-
 	while (true) {
 		struct css_set *cset;
 
 		cset = task_css_set(current);
 		if (likely(cgroup_tryget(cset->dfl_cgrp))) {
-			skcd->val = (unsigned long)cset->dfl_cgrp;
+			skcd->cgroup = cset->dfl_cgrp;
 			cgroup_bpf_get(cset->dfl_cgrp);
 			break;
 		}
 		cpu_relax();
 	}
-
 	rcu_read_unlock();
 }
 
 void cgroup_sk_clone(struct sock_cgroup_data *skcd)
 {
-	if (skcd->val) {
-		if (skcd->no_refcnt)
-			return;
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
-	}
+	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
+
+	/*
+	 * We might be cloning a socket which is left in an empty
+	 * cgroup and the cgroup might have already been rmdir'd.
+	 * Don't use cgroup_get_live().
+	 */
+	cgroup_get(cgrp);
+	cgroup_bpf_get(cgrp);
 }
 
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
-	if (skcd->no_refcnt)
-		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }