Merge tag 'net-6.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bluetooth.

  Quite calm week. No new regression under investigation.

  Current release - regressions:

   - eth: revert "igb: Disable threaded IRQ for igb_msix_other"

  Current release - new code bugs:

   - bluetooth: btintel: direct exception event to bluetooth stack

  Previous releases - regressions:

   - core: fix data-races around sk->sk_forward_alloc

   - netlink: terminate outstanding dump on socket close

   - mptcp: error out earlier on disconnect

   - vsock: fix accept_queue memory leak

   - phylink: ensure PHY momentary link-fails are handled

   - eth: mlx5:
      - fix null-ptr-deref in add rule err flow
      - lock FTE when checking if active

   - eth: dwmac-mediatek: fix inverted handling of mediatek,mac-wol

  Previous releases - always broken:

   - sched: fix u32's systematic failure to free IDR entries for hnodes.

   - sctp: fix possible UAF in sctp_v6_available()

   - eth: bonding: add ns target multicast address to slave device

   - eth: mlx5: fix msix vectors to respect platform limit

   - eth: icssg-prueth: fix 1 PPS sync"

* tag 'net-6.12-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (38 commits)
  net: sched: u32: Add test case for systematic hnode IDR leaks
  selftests: bonding: add ns multicast group testing
  bonding: add ns target multicast address to slave device
  net: ti: icssg-prueth: Fix 1 PPS sync
  stmmac: dwmac-intel-plat: fix call balance of tx_clk handling routines
  net: Make copy_safe_from_sockptr() match documentation
  net: stmmac: dwmac-mediatek: Fix inverted handling of mediatek,mac-wol
  ipmr: Fix access to mfc_cache_list without lock held
  samples: pktgen: correct dev to DEV
  net: phylink: ensure PHY momentary link-fails are handled
  mptcp: pm: use _rcu variant under rcu_read_lock
  mptcp: hold pm lock when deleting entry
  mptcp: update local address flags when setting it
  net: sched: cls_u32: Fix u32's systematic failure to free IDR entries for hnodes.
  MAINTAINERS: Re-add cancelled Renesas driver sections
  Revert "igb: Disable threaded IRQ for igb_msix_other"
  Bluetooth: btintel: Direct exception event to bluetooth stack
  Bluetooth: hci_core: Fix calling mgmt_device_connected
  virtio/vsock: Improve MSG_ZEROCOPY error handling
  vsock: Fix sk_error_queue memory leak
  ...

1 files changed, 24 insertions, 18 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 039be95c40cf..da50df485090 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1052,32 +1052,34 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 
 #ifdef CONFIG_PAGE_POOL
 
-/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
- * 1 syscall. The limit exists to limit the amount of memory the kernel
- * allocates to copy these tokens.
+/* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED
+ * in 1 syscall. The limit exists to limit the amount of memory the kernel
+ * allocates to copy these tokens, and to prevent looping over the frags for
+ * too long.
  */
 #define MAX_DONTNEED_TOKENS 128
+#define MAX_DONTNEED_FRAGS 1024
 
 static noinline_for_stack int
 sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
 	unsigned int num_tokens, i, j, k, netmem_num = 0;
 	struct dmabuf_token *tokens;
+	int ret = 0, num_frags = 0;
 	netmem_ref netmems[16];
-	int ret = 0;
 
 	if (!sk_is_tcp(sk))
 		return -EBADF;
 
-	if (optlen % sizeof(struct dmabuf_token) ||
+	if (optlen % sizeof(*tokens) ||
 	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
 		return -EINVAL;
 
-	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+	num_tokens = optlen / sizeof(*tokens);
+	tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL);
 	if (!tokens)
 		return -ENOMEM;
 
-	num_tokens = optlen / sizeof(struct dmabuf_token);
 	if (copy_from_sockptr(tokens, optval, optlen)) {
 		kvfree(tokens);
 		return -EFAULT;
@@ -1086,24 +1088,28 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 	xa_lock_bh(&sk->sk_user_frags);
 	for (i = 0; i < num_tokens; i++) {
 		for (j = 0; j < tokens[i].token_count; j++) {
+			if (++num_frags > MAX_DONTNEED_FRAGS)
+				goto frag_limit_reached;
+
 			netmem_ref netmem = (__force netmem_ref)__xa_erase(
 				&sk->sk_user_frags, tokens[i].token_start + j);
 
-			if (netmem &&
-			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
-				netmems[netmem_num++] = netmem;
-				if (netmem_num == ARRAY_SIZE(netmems)) {
-					xa_unlock_bh(&sk->sk_user_frags);
-					for (k = 0; k < netmem_num; k++)
-						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
-					netmem_num = 0;
-					xa_lock_bh(&sk->sk_user_frags);
-				}
-				ret++;
+			if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+				continue;
+
+			netmems[netmem_num++] = netmem;
+			if (netmem_num == ARRAY_SIZE(netmems)) {
+				xa_unlock_bh(&sk->sk_user_frags);
+				for (k = 0; k < netmem_num; k++)
+					WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+				netmem_num = 0;
+				xa_lock_bh(&sk->sk_user_frags);
 			}
+			ret++;
 		}
 	}
 
+frag_limit_reached:
 	xa_unlock_bh(&sk->sk_user_frags);
 	for (k = 0; k < netmem_num; k++)
 		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));