Merge tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can, bpf and netfilter.

  There are a bunch of regressions addressed here, but hopefully nothing
  spectacular. We are still waiting the driver fix from Intel, mentioned
  by Jakub in the previous networking pull.

  Current release - regressions:

   - core: add softirq safety to netdev_rename_lock

   - tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed
     TFO

   - batman-adv: fix RCU race at module unload time

  Previous releases - regressions:

   - openvswitch: get related ct labels from its master if it is not
     confirmed

   - eth: bonding: fix incorrect software timestamping report

   - eth: mlxsw: fix memory corruptions on spectrum-4 systems

   - eth: ionic: use dev_consume_skb_any outside of napi

  Previous releases - always broken:

   - netfilter: fully validate NFT_DATA_VALUE on store to data registers

   - unix: several fixes for OoB data

   - tcp: fix race for duplicate reqsk on identical SYN

   - bpf:
       - fix may_goto with negative offset
       - fix the corner case with may_goto and jump to the 1st insn
       - fix overrunning reservations in ringbuf

   - can:
       - j1939: recover socket queue on CAN bus error during BAM
         transmission
       - mcp251xfd: fix infinite loop when xmit fails

   - dsa: microchip: monitor potential faults in half-duplex mode

   - eth: vxlan: pull inner IP header in vxlan_xmit_one()

   - eth: ionic: fix kernel panic due to multi-buffer handling

  Misc:

   - selftest: unix tests refactor and a lot of new cases added"

* tag 'net-6.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (61 commits)
  net: mana: Fix possible double free in error handling path
  selftest: af_unix: Check SIOCATMARK after every send()/recv() in msg_oob.c.
  af_unix: Fix wrong ioctl(SIOCATMARK) when consumed OOB skb is at the head.
  selftest: af_unix: Check EPOLLPRI after every send()/recv() in msg_oob.c
  selftest: af_unix: Check SIGURG after every send() in msg_oob.c
  selftest: af_unix: Add SO_OOBINLINE test cases in msg_oob.c
  af_unix: Don't stop recv() at consumed ex-OOB skb.
  selftest: af_unix: Add non-TCP-compliant test cases in msg_oob.c.
  af_unix: Don't stop recv(MSG_DONTWAIT) if consumed OOB skb is at the head.
  af_unix: Stop recv(MSG_PEEK) at consumed OOB skb.
  selftest: af_unix: Add msg_oob.c.
  selftest: af_unix: Remove test_unix_oob.c.
  tracing/net_sched: NULL pointer dereference in perf_trace_qdisc_reset()
  netfilter: nf_tables: fully validate NFT_DATA_VALUE on store to data registers
  net: usb: qmi_wwan: add Telit FN912 compositions
  tcp: fix tcp_rcv_fastopen_synack() to enter TCP_CA_Loss for failed TFO
  ionic: use dev_consume_skb_any outside of napi
  net: dsa: microchip: fix wrong register write when masking interrupt
  Fix race for duplicate reqsk on identical SYN
  ibmvnic: Add tx check to prevent skb leak
  ...

1 files changed, 25 insertions, 6 deletions

diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 0ee653a936ea..e20b90c36131 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -51,7 +51,8 @@ struct bpf_ringbuf {
 	 * This prevents a user-space application from modifying the
 	 * position and ruining in-kernel tracking. The permissions of the
 	 * pages depend on who is producing samples: user-space or the
-	 * kernel.
+	 * kernel. Note that the pending counter is placed in the same
+	 * page as the producer, so that it shares the same cache line.
 	 *
 	 * Kernel-producer
 	 * ---------------
@@ -70,6 +71,7 @@ struct bpf_ringbuf {
 	 */
 	unsigned long consumer_pos __aligned(PAGE_SIZE);
 	unsigned long producer_pos __aligned(PAGE_SIZE);
+	unsigned long pending_pos;
 	char data[] __aligned(PAGE_SIZE);
 };
 
@@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	rb->mask = data_sz - 1;
 	rb->consumer_pos = 0;
 	rb->producer_pos = 0;
+	rb->pending_pos = 0;
 
 	return rb;
 }
@@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr)
 
 static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 {
-	unsigned long cons_pos, prod_pos, new_prod_pos, flags;
-	u32 len, pg_off;
+	unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags;
 	struct bpf_ringbuf_hdr *hdr;
+	u32 len, pg_off, tmp_size, hdr_len;
 
 	if (unlikely(size > RINGBUF_MAX_RECORD_SZ))
 		return NULL;
@@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 		spin_lock_irqsave(&rb->spinlock, flags);
 	}
 
+	pend_pos = rb->pending_pos;
 	prod_pos = rb->producer_pos;
 	new_prod_pos = prod_pos + len;
 
-	/* check for out of ringbuf space by ensuring producer position
-	 * doesn't advance more than (ringbuf_size - 1) ahead
+	while (pend_pos < prod_pos) {
+		hdr = (void *)rb->data + (pend_pos & rb->mask);
+		hdr_len = READ_ONCE(hdr->len);
+		if (hdr_len & BPF_RINGBUF_BUSY_BIT)
+			break;
+		tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT;
+		tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8);
+		pend_pos += tmp_size;
+	}
+	rb->pending_pos = pend_pos;
+
+	/* check for out of ringbuf space:
+	 * - by ensuring producer position doesn't advance more than
+	 *   (ringbuf_size - 1) ahead
+	 * - by ensuring oldest not yet committed record until newest
+	 *   record does not span more than (ringbuf_size - 1)
 	 */
-	if (new_prod_pos - cons_pos > rb->mask) {
+	if (new_prod_pos - cons_pos > rb->mask ||
+	    new_prod_pos - pend_pos > rb->mask) {
 		spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}