Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
bpf 2023-01-16

We've added 6 non-merge commits during the last 8 day(s) which contain
a total of 6 files changed, 22 insertions(+), 24 deletions(-).

The main changes are:

1) Mitigate a Spectre v4 leak in unprivileged BPF from speculative
   pointer-as-scalar type confusion, from Luis Gerhorst.

2) Fix a splat when pid 1 attaches a BPF program that attempts to
   send killing signal to itself, from Hao Sun.

3) Fix BPF program ID information in BPF_AUDIT_UNLOAD as well as
   PERF_BPF_EVENT_PROG_UNLOAD events, from Paul Moore.

4) Fix BPF verifier warning triggered from invalid kfunc call in
   backtrack_insn, also from Hao Sun.

5) Fix potential deadlock in htab_lock_bucket from same bucket index
   but different map_locked index, from Tonghao Zhang.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Fix pointer-leak due to insufficient speculative store bypass mitigation
  bpf: hash map, avoid deadlock with suitable hash mask
  bpf: remove the do_idr_lock parameter from bpf_prog_free_id()
  bpf: restore the ebpf program ID for BPF_AUDIT_UNLOAD and PERF_BPF_EVENT_PROG_UNLOAD
  bpf: Skip task with pid=1 in send_signal_common()
  bpf: Skip invalid kfunc call in backtrack_insn
====================

Link: https://lore.kernel.org/r/20230116230745.21742-1-daniel@iogearbox.netSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/bpf.h

@@ -1832,7 +1832,7 @@ void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
+void bpf_prog_free_id(struct bpf_prog *prog);
 void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 
 struct btf_field *btf_record_find(const struct btf_record *rec,

kernel/bpf/hashtab.c

@@ -152,7 +152,7 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
 {
 	unsigned long flags;
 
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
 
 	preempt_disable();
 	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
@@ -171,7 +171,7 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
 				      struct bucket *b, u32 hash,
 				      unsigned long flags)
 {
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
 	raw_spin_unlock_irqrestore(&b->raw_lock, flags);
 	__this_cpu_dec(*(htab->map_locked[hash]));
 	preempt_enable();

kernel/bpf/offload.c

@@ -216,9 +216,6 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 	if (offload->dev_state)
 		offload->offdev->ops->destroy(prog);
 
-	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
-	bpf_prog_free_id(prog, true);
-
 	list_del_init(&offload->offloads);
 	kfree(offload);
 	prog->aux->offload = NULL;

kernel/bpf/syscall.c

@@ -1972,7 +1972,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
 		return;
 	if (audit_enabled == AUDIT_OFF)
 		return;
-	if (op == BPF_AUDIT_LOAD)
+	if (!in_irq() && !irqs_disabled())
 		ctx = audit_context();
 	ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
 	if (unlikely(!ab))
@@ -2001,7 +2001,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
 	return id > 0 ? 0 : id;
 }
 
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog)
 {
 	unsigned long flags;
 
@@ -2013,18 +2013,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
 	if (!prog->aux->id)
 		return;
 
-	if (do_idr_lock)
 	spin_lock_irqsave(&prog_idr_lock, flags);
-	else
-		__acquire(&prog_idr_lock);
-
 	idr_remove(&prog_idr, prog->aux->id);
 	prog->aux->id = 0;
-
-	if (do_idr_lock)
 	spin_unlock_irqrestore(&prog_idr_lock, flags);
-	else
-		__release(&prog_idr_lock);
 }
 
 static void __bpf_prog_put_rcu(struct rcu_head *rcu)
@@ -2067,17 +2059,15 @@ static void bpf_prog_put_deferred(struct work_struct *work)
 	prog = aux->prog;
 	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 	bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
+	bpf_prog_free_id(prog);
 	__bpf_prog_put_noref(prog, true);
 }
 
-static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+static void __bpf_prog_put(struct bpf_prog *prog)
 {
 	struct bpf_prog_aux *aux = prog->aux;
 
 	if (atomic64_dec_and_test(&aux->refcnt)) {
-		/* bpf_prog_free_id() must be called first */
-		bpf_prog_free_id(prog, do_idr_lock);
-
 		if (in_irq() || irqs_disabled()) {
 			INIT_WORK(&aux->work, bpf_prog_put_deferred);
 			schedule_work(&aux->work);
@@ -2089,7 +2079,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 
 void bpf_prog_put(struct bpf_prog *prog)
 {
-	__bpf_prog_put(prog, true);
+	__bpf_prog_put(prog);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 

kernel/bpf/verifier.c

@@ -2748,6 +2748,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			 */
 			if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
 				return -ENOTSUPP;
+			/* kfunc with imm==0 is invalid and fixup_kfunc_call will
+			 * catch this error later. Make backtracking conservative
+			 * with ENOTSUPP.
+			 */
+			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
+				return -ENOTSUPP;
 			/* regular helper call sets R0 */
 			*reg_mask &= ~1;
 			if (*reg_mask & 0x3f) {
@@ -3289,7 +3295,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		bool sanitize = reg && is_spillable_regtype(reg->type);
 
 		for (i = 0; i < size; i++) {
-			if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+			u8 type = state->stack[spi].slot_type[i];
+
+			if (type != STACK_MISC && type != STACK_ZERO) {
 				sanitize = true;
 				break;
 			}

kernel/trace/bpf_trace.c

@@ -848,6 +848,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
+	/* Task should not be pid=1 to avoid kernel panic. */
+	if (unlikely(is_global_init(current)))
+		return -EPERM;
 
 	if (irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,