Merge tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from BPF and netfilter.

  Current release - regressions:

   - core: fix undefined behavior in netdev name allocation

   - bpf: do not allocate percpu memory at init stage

   - netfilter: nf_tables: split async and sync catchall in two
     functions

   - mptcp: fix possible NULL pointer dereference on close

  Current release - new code bugs:

   - eth: ice: dpll: fix initial lock status of dpll

  Previous releases - regressions:

   - bpf: fix precision backtracking instruction iteration

   - af_unix: fix use-after-free in unix_stream_read_actor()

   - tipc: fix kernel-infoleak due to uninitialized TLV value

   - eth: bonding: stop the device in bond_setup_by_slave()

   - eth: mlx5:
      - fix double free of encap_header
      - avoid referencing skb after free-ing in drop path

   - eth: hns3: fix VF reset

   - eth: mvneta: fix calls to page_pool_get_stats

  Previous releases - always broken:

   - core: set SOCK_RCU_FREE before inserting socket into hashtable

   - bpf: fix control-flow graph checking in privileged mode

   - eth: ppp: limit MRU to 64K

   - eth: stmmac: avoid rx queue overrun

   - eth: icssg-prueth: fix error cleanup on failing initialization

   - eth: hns3: fix out-of-bounds access may occur when coalesce info is
     read via debugfs

   - eth: cortina: handle large frames

  Misc:

   - selftests: gso: support CONFIG_MAX_SKB_FRAGS up to 45"

* tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (78 commits)
  macvlan: Don't propagate promisc change to lower dev in passthru
  net: sched: do not offload flows with a helper in act_ct
  net/mlx5e: Check return value of snprintf writing to fw_version buffer for representors
  net/mlx5e: Check return value of snprintf writing to fw_version buffer
  net/mlx5e: Reduce the size of icosq_str
  net/mlx5: Increase size of irq name buffer
  net/mlx5e: Update doorbell for port timestamping CQ before the software counter
  net/mlx5e: Track xmit submission to PTP WQ after populating metadata map
  net/mlx5e: Avoid referencing skb after free-ing in drop path of mlx5e_sq_xmit_wqe
  net/mlx5e: Don't modify the peer sent-to-vport rules for IPSec offload
  net/mlx5e: Fix pedit endianness
  net/mlx5e: fix double free of encap_header in update funcs
  net/mlx5e: fix double free of encap_header
  net/mlx5: Decouple PHC .adjtime and .adjphase implementations
  net/mlx5: DR, Allow old devices to use multi destination FTE
  net/mlx5: Free used cpus mask when an IRQ is released
  Revert "net/mlx5: DR, Supporting inline WQE when possible"
  bpf: Do not allocate percpu memory at init stage
  net: Fix undefined behavior in netdev name allocation
  dt-bindings: net: ethernet-controller: Fix formatting error
  ...

2 files changed, 66 insertions, 29 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 08626b519ce2..cd3afe57ece3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -64,8 +64,8 @@
 #define OFF	insn->off
 #define IMM	insn->imm
 
-struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+struct bpf_mem_alloc bpf_global_ma;
+bool bpf_global_ma_set;
 
 /* No hurry in this branch
  *
@@ -2934,9 +2934,7 @@ static int __init bpf_global_ma_init(void)
 
 	ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false);
 	bpf_global_ma_set = !ret;
-	ret = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-	bpf_global_percpu_ma_set = !ret;
-	return !bpf_global_ma_set || !bpf_global_percpu_ma_set;
+	return ret;
 }
 late_initcall(bpf_global_ma_init);
 #endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bd1c42eb540f..6da370a047fe 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
 #include <linux/poison.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
 #include <net/xdp.h>
 
 #include "disasm.h"
@@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
 #undef BPF_LINK_TYPE
 };
 
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
 /* bpf_check() is a static code analyzer that walks eBPF program
  * instruction by instruction and updates register/stack state.
  * All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -336,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
 struct btf *btf_vmlinux;
 
 static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
 
 static const struct bpf_line_info *
 find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -3516,12 +3521,29 @@ static int push_jmp_history(struct bpf_verifier_env *env,
 
 /* Backtrack one insn at a time. If idx is not at the top of recorded
  * history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
  */
 static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 			     u32 *history)
 {
 	u32 cnt = *history;
 
+	if (i == st->first_insn_idx) {
+		if (cnt == 0)
+			return -ENOENT;
+		if (cnt == 1 && st->jmp_history[0].idx == i)
+			return -ENOENT;
+	}
+
 	if (cnt && st->jmp_history[cnt - 1].idx == i) {
 		i = st->jmp_history[cnt - 1].prev_idx;
 		(*history)--;
@@ -4401,10 +4423,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				 * Nothing to be tracked further in the parent state.
 				 */
 				return 0;
-			if (i == first_idx)
-				break;
 			subseq_idx = i;
 			i = get_prev_insn_idx(st, i, &history);
+			if (i == -ENOENT)
+				break;
 			if (i >= env->prog->len) {
 				/* This can happen if backtracking reached insn 0
 				 * and there are still reg_mask or stack_mask
@@ -12074,8 +12096,19 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && !bpf_global_percpu_ma_set)
-					return -ENOMEM;
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+				}
 
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
@@ -15386,8 +15419,7 @@ enum {
  * w - next instruction
  * e - edge
  */
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
-		     bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 {
 	int *insn_stack = env->cfg.insn_stack;
 	int *insn_state = env->cfg.insn_state;
@@ -15419,7 +15451,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
 		insn_stack[env->cfg.cur_stack++] = w;
 		return KEEP_EXPLORING;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
-		if (loop_ok && env->bpf_capable)
+		if (env->bpf_capable)
 			return DONE_EXPLORING;
 		verbose_linfo(env, t, "%d: ", t);
 		verbose_linfo(env, w, "%d: ", w);
@@ -15439,24 +15471,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 				struct bpf_verifier_env *env,
 				bool visit_callee)
 {
-	int ret;
+	int ret, insn_sz;
 
-	ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+	insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+	ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
 	if (ret)
 		return ret;
 
-	mark_prune_point(env, t + 1);
+	mark_prune_point(env, t + insn_sz);
 	/* when we exit from subprog, we need to record non-linear history */
-	mark_jmp_point(env, t + 1);
+	mark_jmp_point(env, t + insn_sz);
 
 	if (visit_callee) {
 		mark_prune_point(env, t);
-		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
-				/* It's ok to allow recursion from CFG point of
-				 * view. __check_func_call() will do the actual
-				 * check.
-				 */
-				bpf_pseudo_func(insns + t));
+		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
 	}
 	return ret;
 }
@@ -15469,15 +15497,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 static int visit_insn(int t, struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
-	int ret, off;
+	int ret, off, insn_sz;
 
 	if (bpf_pseudo_func(insn))
 		return visit_func_call_insn(t, insns, env, true);
 
 	/* All non-branch instructions have a single fall-through edge. */
 	if (BPF_CLASS(insn->code) != BPF_JMP &&
-	    BPF_CLASS(insn->code) != BPF_JMP32)
-		return push_insn(t, t + 1, FALLTHROUGH, env, false);
+	    BPF_CLASS(insn->code) != BPF_JMP32) {
+		insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+		return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+	}
 
 	switch (BPF_OP(insn->code)) {
 	case BPF_EXIT:
@@ -15523,8 +15553,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			off = insn->imm;
 
 		/* unconditional jump with single edge */
-		ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
-				true);
+		ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
@@ -15537,11 +15566,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 		/* conditional jump with two edges */
 		mark_prune_point(env, t);
 
-		ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+		ret = push_insn(t, t + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
-		return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+		return push_insn(t, t + insn->off + 1, BRANCH, env);
 	}
 }
 
@@ -15607,11 +15636,21 @@ walk_cfg:
 	}
 
 	for (i = 0; i < insn_cnt; i++) {
+		struct bpf_insn *insn = &env->prog->insnsi[i];
+
 		if (insn_state[i] != EXPLORED) {
 			verbose(env, "unreachable insn %d\n", i);
 			ret = -EINVAL;
 			goto err_free;
 		}
+		if (bpf_is_ldimm64(insn)) {
+			if (insn_state[i + 1] != 0) {
+				verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+				ret = -EINVAL;
+				goto err_free;
+			}
+			i++; /* skip second half of ldimm64 */
+		}
 	}
 	ret = 0; /* cfg looks good */