Merge tag 'net-6.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - veth: fix packet segmentation in veth_convert_skb_to_xdp_buff

  Current release - new code bugs:

   - tcp: assorted fixes to the new Auth Option support

  Older releases - regressions:

   - tcp: fix mid stream window clamp

   - tls: fix incorrect splice handling

   - ipv4: ip_gre: handle skb_pull() failure in ipgre_xmit()

   - dsa: mv88e6xxx: restore USXGMII support for 6393X

   - arcnet: restore support for multiple Sohard Arcnet cards

  Older releases - always broken:

   - tcp: do not accept ACK of bytes we never sent

   - require admin privileges to receive packet traces via netlink

   - packet: move reference count in packet_sock to atomic_long_t

   - bpf:
      - fix incorrect branch offset comparison with cpu=v4
      - fix prog_array_map_poke_run map poke update

   - netfilter:
      - three fixes for crashes on bad admin commands
      - xt_owner: fix race accessing sk->sk_socket, TOCTOU null-deref
      - nf_tables: fix 'exist' matching on bigendian arches

   - leds: netdev: fix RTNL handling to prevent potential deadlock

   - eth: tg3: prevent races in error/reset handling

   - eth: r8169: fix rtl8125b PAUSE storm when suspended

   - eth: r8152: improve reset and surprise removal handling

   - eth: hns: fix race between changing features and sending

   - eth: nfp: fix sleep in atomic for bonding offload"

* tag 'net-6.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (62 commits)
  vsock/virtio: fix "comparison of distinct pointer types lacks a cast" warning
  net/smc: fix missing byte order conversion in CLC handshake
  net: dsa: microchip: provide a list of valid protocols for xmit handler
  drop_monitor: Require 'CAP_SYS_ADMIN' when joining "events" group
  psample: Require 'CAP_NET_ADMIN' when joining "packets" group
  bpf: sockmap, updating the sg structure should also update curr
  net: tls, update curr on splice as well
  nfp: flower: fix for take a mutex lock in soft irq context and rcu lock
  net: dsa: mv88e6xxx: Restore USXGMII support for 6393X
  tcp: do not accept ACK of bytes we never sent
  selftests/bpf: Add test for early update in prog_array_map_poke_run
  bpf: Fix prog_array_map_poke_run map poke update
  netfilter: xt_owner: Fix for unsafe access of sk->sk_socket
  netfilter: nf_tables: validate family when identifying table via handle
  netfilter: nf_tables: bail out on mismatching dynset and set expressions
  netfilter: nf_tables: fix 'exist' matching on bigendian arches
  netfilter: nft_set_pipapo: skip inactive elements during set walk
  netfilter: bpf: fix bad registration on nf_defrag
  leds: trigger: netdev: fix RTNL handling to prevent potential deadlock
  octeontx2-af: Update Tx link register range
  ...

2 files changed, 18 insertions, 52 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..c85ff9162a5c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
 	mutex_unlock(&aux->poke_mutex);
 }
 
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+				      struct bpf_prog *new, struct bpf_prog *old)
+{
+	WARN_ON_ONCE(1);
+}
+
 static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
-	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 
 	list_for_each_entry(elem, &aux->poke_progs, list) {
 		struct bpf_jit_poke_descriptor *poke;
-		int i, ret;
+		int i;
 
 		for (i = 0; i < elem->aux->size_poke_tab; i++) {
 			poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    activated, so tail call updates can arrive from here
 			 *    while JIT is still finishing its final fixup for
 			 *    non-activated poke entries.
-			 * 3) On program teardown, the program's kallsym entry gets
-			 *    removed out of RCU callback, but we can only untrack
-			 *    from sleepable context, therefore bpf_arch_text_poke()
-			 *    might not see that this is in BPF text section and
-			 *    bails out with -EINVAL. As these are unreachable since
-			 *    RCU grace period already passed, we simply skip them.
-			 * 4) Also programs reaching refcount of zero while patching
+			 * 3) Also programs reaching refcount of zero while patching
 			 *    is in progress is okay since we're protected under
 			 *    poke_mutex and untrack the programs before the JIT
-			 *    buffer is freed. When we're still in the middle of
-			 *    patching and suddenly kallsyms entry of the program
-			 *    gets evicted, we just skip the rest which is fine due
-			 *    to point 3).
-			 * 5) Any other error happening below from bpf_arch_text_poke()
-			 *    is a unexpected bug.
+			 *    buffer is freed.
 			 */
 			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
@@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			old_bypass_addr = old ? NULL : poke->bypass_addr;
-			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
-			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
-			if (new) {
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, new_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				if (!old) {
-					ret = bpf_arch_text_poke(poke->tailcall_bypass,
-								 BPF_MOD_JUMP,
-								 poke->bypass_addr,
-								 NULL);
-					BUG_ON(ret < 0 && ret != -EINVAL);
-				}
-			} else {
-				ret = bpf_arch_text_poke(poke->tailcall_bypass,
-							 BPF_MOD_JUMP,
-							 old_bypass_addr,
-							 poke->bypass_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				/* let other CPUs finish the execution of program
-				 * so that it will not possible to expose them
-				 * to invalid nop, stack unwind, nop state
-				 */
-				if (!ret)
-					synchronize_rcu();
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, NULL);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-			}
+			bpf_arch_poke_desc_update(poke, new, old);
 		}
 	}
 }
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index cd3afe57ece3..fe254ae035fe 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -371,14 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
 static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
 				s32 end_new, s32 curr, const bool probe_pass)
 {
-	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s64 off_min, off_max, off;
 	s32 delta = end_new - end_old;
-	s32 off;
 
-	if (insn->code == (BPF_JMP32 | BPF_JA))
+	if (insn->code == (BPF_JMP32 | BPF_JA)) {
 		off = insn->imm;
-	else
+		off_min = S32_MIN;
+		off_max = S32_MAX;
+	} else {
 		off = insn->off;
+		off_min = S16_MIN;
+		off_max = S16_MAX;
+	}
 
 	if (curr < pos && curr + off + 1 >= end_old)
 		off += delta;