Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/intel/ice/ice_main.c
  c9663f79cd82 ("ice: adjust switchdev rebuild path")
  7758017911a4 ("ice: restore timestamp configuration after device reset")
https://lore.kernel.org/all/20231121211259.3348630-1-anthony.l.nguyen@intel.com/

Adjacent changes:

kernel/bpf/verifier.c
  bb124da69c47 ("bpf: keep track of max number of bpf_loop callback iterations")
  5f99f312bd3b ("bpf: add register bounds sanity checks and sanitization")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 448 insertions, 200 deletions

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 91e82e34b51e..7a98cd176a12 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -531,7 +531,7 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	if (tsk != current)
 		return 0;
 
-	if (WARN_ON_ONCE(!current->mm))
+	if (!current->mm)
 		return 0;
 	exe_file = get_mm_exe_file(current->mm);
 	if (!exe_file)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1340921ea311..405da1f9e724 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -465,13 +465,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_dynptr_data;
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_sync_callback_calling_kfunc(u32 btf_id);
 static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
 
-static bool is_callback_calling_function(enum bpf_func_id func_id)
+static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_for_each_map_elem ||
-	       func_id == BPF_FUNC_timer_set_callback ||
 	       func_id == BPF_FUNC_find_vma ||
 	       func_id == BPF_FUNC_loop ||
 	       func_id == BPF_FUNC_user_ringbuf_drain;
@@ -482,6 +481,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_timer_set_callback;
 }
 
+static bool is_callback_calling_function(enum bpf_func_id func_id)
+{
+	return is_sync_callback_calling_function(func_id) ||
+	       is_async_callback_calling_function(func_id);
+}
+
+static bool is_sync_callback_calling_insn(struct bpf_insn *insn)
+{
+	return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
+	       (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
+}
+
 static bool is_storage_get_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_storage_get ||
@@ -1348,6 +1359,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->first_insn_idx = src->first_insn_idx;
 	dst_state->last_insn_idx = src->last_insn_idx;
 	dst_state->dfs_depth = src->dfs_depth;
+	dst_state->callback_unroll_depth = src->callback_unroll_depth;
 	dst_state->used_as_loop_entry = src->used_as_loop_entry;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
@@ -3131,13 +3143,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env,
 	reg->subreg_def = DEF_NOT_SUBREG;
 }
 
-static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
-			 enum reg_arg_type t)
+static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
+			   enum reg_arg_type t)
 {
-	struct bpf_verifier_state *vstate = env->cur_state;
-	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
-	struct bpf_reg_state *reg, *regs = state->regs;
+	struct bpf_reg_state *reg;
 	bool rw64;
 
 	if (regno >= MAX_BPF_REG) {
@@ -3178,6 +3188,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 	return 0;
 }
 
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+			 enum reg_arg_type t)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+
+	return __check_reg_arg(env, state->regs, regno, t);
+}
+
 static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
 {
 	env->insn_aux_data[idx].jmp_point = true;
@@ -3416,6 +3435,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
 	}
 }
 
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
@@ -3591,16 +3612,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					return -EFAULT;
 				return 0;
 			}
-		} else if ((bpf_helper_call(insn) &&
-			    is_callback_calling_function(insn->imm) &&
-			    !is_async_callback_calling_function(insn->imm)) ||
-			   (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
-			/* callback-calling helper or kfunc call, which means
-			 * we are exiting from subprog, but unlike the subprog
-			 * call handling above, we shouldn't propagate
-			 * precision of r1-r5 (if any requested), as they are
-			 * not actually arguments passed directly to callback
-			 * subprogs
+		} else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) {
+			/* exit from callback subprog to callback-calling helper or
+			 * kfunc call. Use idx/subseq_idx check to discern it from
+			 * straight line code backtracking.
+			 * Unlike the subprog call handling above, we shouldn't
+			 * propagate precision of r1-r5 (if any requested), as they are
+			 * not actually arguments passed directly to callback subprogs
 			 */
 			if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
@@ -3635,10 +3653,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		} else if (opcode == BPF_EXIT) {
 			bool r0_precise;
 
+			/* Backtracking to a nested function call, 'idx' is a part of
+			 * the inner frame 'subseq_idx' is a part of the outer frame.
+			 * In case of a regular function call, instructions giving
+			 * precision to registers R1-R5 should have been found already.
+			 * In case of a callback, it is ok to have R1-R5 marked for
+			 * backtracking, as these registers are set by the function
+			 * invoking callback.
+			 */
+			if (subseq_idx >= 0 && calls_callback(env, subseq_idx))
+				for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+					bt_clear_reg(bt, i);
 			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-				/* if backtracing was looking for registers R1-R5
-				 * they should have been found already.
-				 */
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
@@ -9090,7 +9116,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env,
 	/* after the call registers r0 - r5 were scratched */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
-		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+		__check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
 	}
 }
 
@@ -9103,11 +9129,10 @@ static int set_callee_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *caller,
 			    struct bpf_func_state *callee, int insn_idx);
 
-static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			     int *insn_idx, int subprog,
-			     set_callee_state_fn set_callee_state_cb)
+static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
+			    set_callee_state_fn set_callee_state_cb,
+			    struct bpf_verifier_state *state)
 {
-	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_func_state *caller, *callee;
 	int err;
 
@@ -9117,54 +9142,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		return -E2BIG;
 	}
 
-	caller = state->frame[state->curframe];
 	if (state->frame[state->curframe + 1]) {
 		verbose(env, "verifier bug. Frame %d already allocated\n",
 			state->curframe + 1);
 		return -EFAULT;
 	}
 
+	caller = state->frame[state->curframe];
+	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+	if (!callee)
+		return -ENOMEM;
+	state->frame[state->curframe + 1] = callee;
+
+	/* callee cannot access r0, r6 - r9 for reading and has to write
+	 * into its own stack before reading from it.
+	 * callee can read/write into caller's stack
+	 */
+	init_func_state(env, callee,
+			/* remember the callsite, it will be used by bpf_exit */
+			callsite,
+			state->curframe + 1 /* frameno within this callchain */,
+			subprog /* subprog number within this prog */);
+	/* Transfer references to the callee */
+	err = copy_reference_state(callee, caller);
+	err = err ?: set_callee_state_cb(env, caller, callee, callsite);
+	if (err)
+		goto err_out;
+
+	/* only increment it after check_reg_arg() finished */
+	state->curframe++;
+
+	return 0;
+
+err_out:
+	free_func_state(callee);
+	state->frame[state->curframe + 1] = NULL;
+	return err;
+}
+
+static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			      int insn_idx, int subprog,
+			      set_callee_state_fn set_callee_state_cb)
+{
+	struct bpf_verifier_state *state = env->cur_state, *callback_state;
+	struct bpf_func_state *caller, *callee;
+	int err;
+
+	caller = state->frame[state->curframe];
 	err = btf_check_subprog_call(env, subprog, caller->regs);
 	if (err == -EFAULT)
 		return err;
-	if (subprog_is_global(env, subprog)) {
-		if (err) {
-			verbose(env, "Caller passes invalid args into func#%d\n",
-				subprog);
-			return err;
-		} else {
-			if (env->log.level & BPF_LOG_LEVEL)
-				verbose(env,
-					"Func#%d is global and valid. Skipping.\n",
-					subprog);
-			clear_caller_saved_regs(env, caller->regs);
-
-			/* All global functions return a 64-bit SCALAR_VALUE */
-			mark_reg_unknown(env, caller->regs, BPF_REG_0);
-			caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
-
-			/* continue with next insn after call */
-			return 0;
-		}
-	}
 
 	/* set_callee_state is used for direct subprog calls, but we are
 	 * interested in validating only BPF helpers that can call subprogs as
 	 * callbacks
 	 */
-	if (set_callee_state_cb != set_callee_state) {
-		env->subprog_info[subprog].is_cb = true;
-		if (bpf_pseudo_kfunc_call(insn) &&
-		    !is_callback_calling_kfunc(insn->imm)) {
-			verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		} else if (!bpf_pseudo_kfunc_call(insn) &&
-			   !is_callback_calling_function(insn->imm)) { /* helper */
-			verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		}
+	env->subprog_info[subprog].is_cb = true;
+	if (bpf_pseudo_kfunc_call(insn) &&
+	    !is_sync_callback_calling_kfunc(insn->imm)) {
+		verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
+	} else if (!bpf_pseudo_kfunc_call(insn) &&
+		   !is_callback_calling_function(insn->imm)) { /* helper */
+		verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
 	}
 
 	if (insn->code == (BPF_JMP | BPF_CALL) &&
@@ -9175,53 +9218,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		/* there is no real recursion here. timer callbacks are async */
 		env->subprog_info[subprog].is_async_cb = true;
 		async_cb = push_async_cb(env, env->subprog_info[subprog].start,
-					 *insn_idx, subprog);
+					 insn_idx, subprog);
 		if (!async_cb)
 			return -EFAULT;
 		callee = async_cb->frame[0];
 		callee->async_entry_cnt = caller->async_entry_cnt + 1;
 
 		/* Convert bpf_timer_set_callback() args into timer callback args */
-		err = set_callee_state_cb(env, caller, callee, *insn_idx);
+		err = set_callee_state_cb(env, caller, callee, insn_idx);
 		if (err)
 			return err;
 
+		return 0;
+	}
+
+	/* for callback functions enqueue entry to callback and
+	 * proceed with next instruction within current frame.
+	 */
+	callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
+	if (!callback_state)
+		return -ENOMEM;
+
+	err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
+			       callback_state);
+	if (err)
+		return err;
+
+	callback_state->callback_unroll_depth++;
+	callback_state->frame[callback_state->curframe - 1]->callback_depth++;
+	caller->callback_depth = 0;
+	return 0;
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			   int *insn_idx)
+{
+	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_func_state *caller;
+	int err, subprog, target_insn;
+
+	target_insn = *insn_idx + insn->imm + 1;
+	subprog = find_subprog(env, target_insn);
+	if (subprog < 0) {
+		verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+		return -EFAULT;
+	}
+
+	caller = state->frame[state->curframe];
+	err = btf_check_subprog_call(env, subprog, caller->regs);
+	if (err == -EFAULT)
+		return err;
+	if (subprog_is_global(env, subprog)) {
+		if (err) {
+			verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+			return err;
+		}
+
+		if (env->log.level & BPF_LOG_LEVEL)
+			verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
 		clear_caller_saved_regs(env, caller->regs);
+
+		/* All global functions return a 64-bit SCALAR_VALUE */
 		mark_reg_unknown(env, caller->regs, BPF_REG_0);
 		caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
 		/* continue with next insn after call */
 		return 0;
 	}
 
-	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
-	if (!callee)
-		return -ENOMEM;
-	state->frame[state->curframe + 1] = callee;
-
-	/* callee cannot access r0, r6 - r9 for reading and has to write
-	 * into its own stack before reading from it.
-	 * callee can read/write into caller's stack
+	/* for regular function entry setup new frame and continue
+	 * from that frame.
 	 */
-	init_func_state(env, callee,
-			/* remember the callsite, it will be used by bpf_exit */
-			*insn_idx /* callsite */,
-			state->curframe + 1 /* frameno within this callchain */,
-			subprog /* subprog number within this prog */);
-
-	/* Transfer references to the callee */
-	err = copy_reference_state(callee, caller);
+	err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
 	if (err)
-		goto err_out;
-
-	err = set_callee_state_cb(env, caller, callee, *insn_idx);
-	if (err)
-		goto err_out;
+		return err;
 
 	clear_caller_saved_regs(env, caller->regs);
 
-	/* only increment it after check_reg_arg() finished */
-	state->curframe++;
-
 	/* and go analyze first insn of the callee */
 	*insn_idx = env->subprog_info[subprog].start - 1;
 
@@ -9229,14 +9302,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		verbose(env, "caller:\n");
 		print_verifier_state(env, caller, true);
 		verbose(env, "callee:\n");
-		print_verifier_state(env, callee, true);
+		print_verifier_state(env, state->frame[state->curframe], true);
 	}
-	return 0;
 
-err_out:
-	free_func_state(callee);
-	state->frame[state->curframe + 1] = NULL;
-	return err;
+	return 0;
 }
 
 int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -9280,22 +9349,6 @@ static int set_callee_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			   int *insn_idx)
-{
-	int subprog, target_insn;
-
-	target_insn = *insn_idx + insn->imm + 1;
-	subprog = find_subprog(env, target_insn);
-	if (subprog < 0) {
-		verbose(env, "verifier bug. No program starts at insn %d\n",
-			target_insn);
-		return -EFAULT;
-	}
-
-	return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
-}
-
 static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 				       struct bpf_func_state *caller,
 				       struct bpf_func_state *callee,
@@ -9488,9 +9541,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
 
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
-	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state, *prev_st;
 	struct bpf_func_state *caller, *callee;
 	struct bpf_reg_state *r0;
+	bool in_callback_fn;
 	int err;
 
 	callee = state->frame[state->curframe];
@@ -9519,6 +9573,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 			verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
 			return -EINVAL;
 		}
+		if (!calls_callback(env, callee->callsite)) {
+			verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n",
+				*insn_idx, callee->callsite);
+			return -EFAULT;
+		}
 	} else {
 		/* return to the caller whatever r0 had in the callee */
 		caller->regs[BPF_REG_0] = *r0;
@@ -9536,7 +9595,16 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 			return err;
 	}
 
-	*insn_idx = callee->callsite + 1;
+	/* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
+	 * there function call logic would reschedule callback visit. If iteration
+	 * converges is_state_visited() would prune that visit eventually.
+	 */
+	in_callback_fn = callee->in_callback_fn;
+	if (in_callback_fn)
+		*insn_idx = callee->callsite;
+	else
+		*insn_idx = callee->callsite + 1;
+
 	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
 		print_verifier_state(env, callee, true);
@@ -9547,6 +9615,24 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	 * bpf_throw, this will be done by copy_verifier_state for extra frames. */
 	free_func_state(callee);
 	state->frame[state->curframe--] = NULL;
+
+	/* for callbacks widen imprecise scalars to make programs like below verify:
+	 *
+	 *   struct ctx { int i; }
+	 *   void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
+	 *   ...
+	 *   struct ctx = { .i = 0; }
+	 *   bpf_loop(100, cb, &ctx, 0);
+	 *
+	 * This is similar to what is done in process_iter_next_call() for open
+	 * coded iterators.
+	 */
+	prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
+	if (prev_st) {
+		err = widen_imprecise_scalars(env, prev_st, state);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -9952,24 +10038,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		break;
 	case BPF_FUNC_for_each_map_elem:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_map_elem_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_map_elem_callback_state);
 		break;
 	case BPF_FUNC_timer_set_callback:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_timer_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_timer_callback_state);
 		break;
 	case BPF_FUNC_find_vma:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_find_vma_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_find_vma_callback_state);
 		break;
 	case BPF_FUNC_snprintf:
 		err = check_bpf_snprintf_call(env, regs);
 		break;
 	case BPF_FUNC_loop:
 		update_loop_inline_state(env, meta.subprogno);
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_loop_callback_state);
+		/* Verifier relies on R1 value to determine if bpf_loop() iteration
+		 * is finished, thus mark it precise.
+		 */
+		err = mark_chain_precision(env, BPF_REG_1);
+		if (err)
+			return err;
+		if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) {
+			err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+						 set_loop_callback_state);
+		} else {
+			cur_func(env)->callback_depth = 0;
+			if (env->log.level & BPF_LOG_LEVEL2)
+				verbose(env, "frame%d bpf_loop iteration limit reached\n",
+					env->cur_state->curframe);
+		}
 		break;
 	case BPF_FUNC_dynptr_from_mem:
 		if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
@@ -10065,8 +10164,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		break;
 	}
 	case BPF_FUNC_user_ringbuf_drain:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_user_ringbuf_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_user_ringbuf_callback_state);
 		break;
 	}
 
@@ -10965,7 +11064,7 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id)
 	       btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id)
+static bool is_sync_callback_calling_kfunc(u32 btf_id)
 {
 	return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
 }
@@ -11727,6 +11826,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EACCES;
 	}
 
+	/* Check the arguments */
+	err = check_kfunc_args(env, &meta, insn_idx);
+	if (err < 0)
+		return err;
+
+	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_rbtree_add_callback_state);
+		if (err) {
+			verbose(env, "kfunc %s#%d failed callback verification\n",
+				func_name, meta.func_id);
+			return err;
+		}
+	}
+
 	rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
 	rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
 
@@ -11762,10 +11876,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EINVAL;
 	}
 
-	/* Check the arguments */
-	err = check_kfunc_args(env, &meta, insn_idx);
-	if (err < 0)
-		return err;
 	/* In case of release function, we get register number of refcounted
 	 * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
 	 */
@@ -11799,16 +11909,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
-	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_rbtree_add_callback_state);
-		if (err) {
-			verbose(env, "kfunc %s#%d failed callback verification\n",
-				func_name, meta.func_id);
-			return err;
-		}
-	}
-
 	if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
 		if (!bpf_jit_supports_exceptions()) {
 			verbose(env, "JIT does not support calling kfunc %s#%d\n",
@@ -15079,6 +15179,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx)
 	return env->insn_aux_data[insn_idx].force_checkpoint;
 }
 
+static void mark_calls_callback(struct bpf_verifier_env *env, int idx)
+{
+	env->insn_aux_data[idx].calls_callback = true;
+}
+
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx)
+{
+	return env->insn_aux_data[insn_idx].calls_callback;
+}
 
 enum {
 	DONE_EXPLORING = 0,
@@ -15192,6 +15301,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			 * async state will be pushed for further exploration.
 			 */
 			mark_prune_point(env, t);
+		/* For functions that invoke callbacks it is not known how many times
+		 * callback would be called. Verifier models callback calling functions
+		 * by repeatedly visiting callback bodies and returning to origin call
+		 * instruction.
+		 * In order to stop such iteration verifier needs to identify when a
+		 * state identical some state from a previous iteration is reached.
+		 * Check below forces creation of checkpoint before callback calling
+		 * instruction to allow search for such identical states.
+		 */
+		if (is_sync_callback_calling_insn(insn)) {
+			mark_calls_callback(env, t);
+			mark_force_checkpoint(env, t);
+			mark_prune_point(env, t);
+			mark_jmp_point(env, t);
+		}
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 			struct bpf_kfunc_call_arg_meta meta;
 
@@ -16661,10 +16785,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				}
 				goto skip_inf_loop_check;
 			}
+			if (calls_callback(env, insn_idx)) {
+				if (states_equal(env, &sl->state, cur, true))
+					goto hit;
+				goto skip_inf_loop_check;
+			}
 			/* attempt to detect infinite loop to avoid unnecessary doomed work */
 			if (states_maybe_looping(&sl->state, cur) &&
 			    states_equal(env, &sl->state, cur, false) &&
-			    !iter_active_depths_differ(&sl->state, cur)) {
+			    !iter_active_depths_differ(&sl->state, cur) &&
+			    sl->state.callback_unroll_depth == cur->callback_unroll_depth) {
 				verbose_linfo(env, insn_idx, "; ");
 				verbose(env, "infinite loop detected at insn %d\n", insn_idx);
 				verbose(env, "cur state:");
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4e610863cc37..8f3cef1a4d8a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3898,14 +3898,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
-static int cgroup_pressure_open(struct kernfs_open_file *of)
-{
-	if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return 0;
-}
-
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
@@ -5312,7 +5304,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "io.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5321,7 +5312,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "memory.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5330,7 +5320,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "cpu.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5340,7 +5329,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "irq.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9e4c6780adde..a86972a91991 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2113,7 +2113,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_HRTIMERS_PREPARE] = {
 		.name			= "hrtimers:prepare",
 		.startup.single		= hrtimers_prepare_cpu,
-		.teardown.single	= hrtimers_dead_cpu,
+		.teardown.single	= NULL,
 	},
 	[CPUHP_SMPCFD_PREPARE] = {
 		.name			= "smpcfd:prepare",
@@ -2205,6 +2205,12 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= NULL,
 		.teardown.single	= smpcfd_dying_cpu,
 	},
+	[CPUHP_AP_HRTIMERS_DYING] = {
+		.name			= "hrtimers:dying",
+		.startup.single		= NULL,
+		.teardown.single	= hrtimers_cpu_dying,
+	},
+
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
 	[CPUHP_AP_ONLINE] = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 683dc086ef10..b704d83a28b2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4828,6 +4828,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
+		/*
+		 * perf_pmu_migrate_context() / __perf_pmu_install_event()
+		 * relies on the fact that find_get_pmu_context() cannot fail
+		 * for CPU contexts.
+		 */
 		struct perf_cpu_pmu_context *cpc;
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
@@ -12889,6 +12894,9 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 				     int cpu, struct perf_event *event)
 {
 	struct perf_event_pmu_context *epc;
+	struct perf_event_context *old_ctx = event->ctx;
+
+	get_ctx(ctx); /* normally find_get_context() */
 
 	event->cpu = cpu;
 	epc = find_get_pmu_context(pmu, ctx, event);
@@ -12897,6 +12905,11 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
 	perf_install_in_context(ctx, event, cpu);
+
+	/*
+	 * Now that event->ctx is updated and visible, put the old ctx.
+	 */
+	put_ctx(old_ctx);
 }
 
 static void __perf_pmu_install(struct perf_event_context *ctx,
@@ -12935,6 +12948,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	struct perf_event_context *src_ctx, *dst_ctx;
 	LIST_HEAD(events);
 
+	/*
+	 * Since per-cpu context is persistent, no need to grab an extra
+	 * reference.
+	 */
 	src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx;
 	dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx;
 
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 52695c59d041..dad981a865b8 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -700,7 +700,8 @@ retry:
 	owner = uval & FUTEX_TID_MASK;
 
 	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
 		return 0;
 	}
 
@@ -752,8 +753,10 @@ retry:
 	 * Wake robust non-PI futexes here. The wakeup of
 	 * PI futexes happens in exit_pi_state():
 	 */
-	if (!pi && (uval & FUTEX_WAITERS))
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+	if (!pi && (uval & FUTEX_WAITERS)) {
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
+	}
 
 	return 0;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2048138ce54b..d7a3c63a2171 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3666,41 +3666,140 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			   unsigned long weight)
+{
+	unsigned long old_weight = se->load.weight;
+	u64 avruntime = avg_vruntime(cfs_rq);
+	s64 vlag, vslice;
+
+	/*
+	 * VRUNTIME
+	 * ========
+	 *
+	 * COROLLARY #1: The virtual runtime of the entity needs to be
+	 * adjusted if re-weight at !0-lag point.
+	 *
+	 * Proof: For contradiction assume this is not true, so we can
+	 * re-weight without changing vruntime at !0-lag point.
+	 *
+	 *             Weight	VRuntime   Avg-VRuntime
+	 *     before    w          v            V
+	 *      after    w'         v'           V'
+	 *
+	 * Since lag needs to be preserved through re-weight:
+	 *
+	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
+	 *	==>	V' = (V - v)*w/w' + v		(1)
+	 *
+	 * Let W be the total weight of the entities before reweight,
+	 * since V' is the new weighted average of entities:
+	 *
+	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
+	 *
+	 * by using (1) & (2) we obtain:
+	 *
+	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+	 *
+	 * Since we are doing at !0-lag point which means V != v, we
+	 * can simplify (3):
+	 *
+	 *	==>	W / (W + w' - w) = w / w'
+	 *	==>	Ww' = Ww + ww' - ww
+	 *	==>	W * (w' - w) = w * (w' - w)
+	 *	==>	W = w	(re-weight indicates w' != w)
+	 *
+	 * So the cfs_rq contains only one entity, hence vruntime of
+	 * the entity @v should always equal to the cfs_rq's weighted
+	 * average vruntime @V, which means we will always re-weight
+	 * at 0-lag point, thus breach assumption. Proof completed.
+	 *
+	 *
+	 * COROLLARY #2: Re-weight does NOT affect weighted average
+	 * vruntime of all the entities.
+	 *
+	 * Proof: According to corollary #1, Eq. (1) should be:
+	 *
+	 *	(V - v)*w = (V' - v')*w'
+	 *	==>    v' = V' - (V - v)*w/w'		(4)
+	 *
+	 * According to the weighted average formula, we have:
+	 *
+	 *	V' = (WV - wv + w'v') / (W - w + w')
+	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+	 *	   = (WV + w'V' - Vw) / (W - w + w')
+	 *
+	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
+	 *	==>	V' * (W - w) = (W - w) * V	(5)
+	 *
+	 * If the entity is the only one in the cfs_rq, then reweight
+	 * always occurs at 0-lag point, so V won't change. Or else
+	 * there are other entities, hence W != w, then Eq. (5) turns
+	 * into V' = V. So V won't change in either case, proof done.
+	 *
+	 *
+	 * So according to corollary #1 & #2, the effect of re-weight
+	 * on vruntime should be:
+	 *
+	 *	v' = V' - (V - v) * w / w'		(4)
+	 *	   = V  - (V - v) * w / w'
+	 *	   = V  - vl * w / w'
+	 *	   = V  - vl'
+	 */
+	if (avruntime != se->vruntime) {
+		vlag = (s64)(avruntime - se->vruntime);
+		vlag = div_s64(vlag * old_weight, weight);
+		se->vruntime = avruntime - vlag;
+	}
+
+	/*
+	 * DEADLINE
+	 * ========
+	 *
+	 * When the weight changes, the virtual time slope changes and
+	 * we should adjust the relative virtual deadline accordingly.
+	 *
+	 *	d' = v' + (d - v)*w/w'
+	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  + (d - V)*w/w'
+	 */
+	vslice = (s64)(se->deadline - avruntime);
+	vslice = div_s64(vslice * old_weight, weight);
+	se->deadline = avruntime + vslice;
+}
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
-	unsigned long old_weight = se->load.weight;
+	bool curr = cfs_rq->curr == se;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
-		if (cfs_rq->curr == se)
+		if (curr)
 			update_curr(cfs_rq);
 		else
-			avg_vruntime_sub(cfs_rq, se);
+			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	update_load_set(&se->load, weight);
-
 	if (!se->on_rq) {
 		/*
 		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
 		 * we need to scale se->vlag when w_i changes.
 		 */
-		se->vlag = div_s64(se->vlag * old_weight, weight);
+		se->vlag = div_s64(se->vlag * se->load.weight, weight);
 	} else {
-		s64 deadline = se->deadline - se->vruntime;
-		/*
-		 * When the weight changes, the virtual time slope changes and
-		 * we should adjust the relative virtual deadline accordingly.
-		 */
-		deadline = div_s64(deadline * old_weight, weight);
-		se->deadline = se->vruntime + deadline;
-		if (se != cfs_rq->curr)
-			min_deadline_cb_propagate(&se->run_node, NULL);
+		reweight_eevdf(cfs_rq, se, weight);
 	}
 
+	update_load_set(&se->load, weight);
+
 #ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
@@ -3712,8 +3811,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
-		if (cfs_rq->curr != se)
-			avg_vruntime_add(cfs_rq, se);
+		if (!curr) {
+			/*
+			 * The entity's vruntime has been adjusted, so let's check
+			 * whether the rq-wide min_vruntime needs updated too. Since
+			 * the calculations above require stable min_vruntime rather
+			 * than up-to-date one, we do the update at the end of the
+			 * reweight process.
+			 */
+			__enqueue_entity(cfs_rq, se);
+			update_min_vruntime(cfs_rq);
+		}
 	}
 }
 
@@ -3857,14 +3965,11 @@ static void update_cfs_group(struct sched_entity *se)
 
 #ifndef CONFIG_SMP
 	shares = READ_ONCE(gcfs_rq->tg->shares);
-
-	if (likely(se->load.weight == shares))
-		return;
 #else
-	shares   = calc_group_shares(gcfs_rq);
+	shares = calc_group_shares(gcfs_rq);
 #endif
-
-	reweight_entity(cfs_rq_of(se), se, shares);
+	if (unlikely(se->load.weight != shares))
+		reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -11079,12 +11184,16 @@ static int should_we_balance(struct lb_env *env)
 			continue;
 		}
 
-		/* Are we the first idle CPU? */
+		/*
+		 * Are we the first idle core in a non-SMT domain or higher,
+		 * or the first idle CPU in a SMT domain?
+		 */
 		return cpu == env->dst_cpu;
 	}
 
-	if (idle_smt == env->dst_cpu)
-		return true;
+	/* Are we the first idle CPU with busy siblings? */
+	if (idle_smt != -1)
+		return idle_smt == env->dst_cpu;
 
 	/* Are we the first CPU of this group ? */
 	return group_balance_cpu(sg) == env->dst_cpu;
diff --git a/kernel/sys.c b/kernel/sys.c
index 420d9cb9cc8e..e219fcfa112d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2394,6 +2394,10 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
+	/* PARISC cannot allow mdwe as it needs writable stacks */
+	if (IS_ENABLED(CONFIG_PARISC))
+		return -EINVAL;
+
 	current_bits = get_current_mdwe();
 	if (current_bits && current_bits != bits)
 		return -EPERM; /* Cannot unset the flags */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 238262e4aba7..760793998cdd 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 	}
 }
 
-int hrtimers_dead_cpu(unsigned int scpu)
+int hrtimers_cpu_dying(unsigned int dying_cpu)
 {
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i;
+	int i, ncpu = cpumask_first(cpu_active_mask);
 
-	BUG_ON(cpu_online(scpu));
-	tick_cancel_sched_timer(scpu);
+	tick_cancel_sched_timer(dying_cpu);
+
+	old_base = this_cpu_ptr(&hrtimer_bases);
+	new_base = &per_cpu(hrtimer_bases, ncpu);
 
-	/*
-	 * this BH disable ensures that raise_softirq_irqoff() does
-	 * not wakeup ksoftirqd (and acquire the pi-lock) while
-	 * holding the cpu_base lock
-	 */
-	local_bh_disable();
-	local_irq_disable();
-	old_base = &per_cpu(hrtimer_bases, scpu);
-	new_base = this_cpu_ptr(&hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
 	 */
-	raw_spin_lock(&new_base->lock);
-	raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+	raw_spin_lock(&old_base->lock);
+	raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		migrate_hrtimer_list(&old_base->clock_base[i],
@@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu)
 	 * The migration might have changed the first expiring softirq
 	 * timer on this CPU. Update it.
 	 */
-	hrtimer_update_softirq_timer(new_base, false);
+	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
+	/* Tell the other CPU to retrigger the next event */
+	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
-	raw_spin_unlock(&old_base->lock);
 	raw_spin_unlock(&new_base->lock);
+	raw_spin_unlock(&old_base->lock);
 
-	/* Check, if we got expired work to do */
-	__hrtimer_peek_ahead_timers();
-	local_irq_enable();
-	local_bh_enable();
 	return 0;
 }