Expose c0 and SW encap ICM for RDMA

These two series from Mark and Shun extend RDMA mlx5 API.

Mark's series provides c0 register used to match egress
traffic sent by local device.

Shun's series adds new type for ICM area.

Link: https://lore.kernel.org/all/cover.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>

21 files changed, 682 insertions, 438 deletions

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 7aff28ded2f4..1cc3b1c595d7 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -97,7 +97,6 @@ config CRASH_DUMP
 	depends on ARCH_SUPPORTS_KEXEC
 	select CRASH_CORE
 	select KEXEC_CORE
-	select KEXEC
 	help
 	  Generate crash dump after being started by kexec.
 	  This should be normally only set in special crash dump kernels
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/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 08626b519ce2..fe254ae035fe 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
  *
@@ -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;
@@ -2934,9 +2938,7 @@ 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/memalloc.c b/kernel/bpf/memalloc.c
index 63b909d277d4..6a51cfe4c2d6 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -978,6 +978,8 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 		memcg = get_memcg(c);
 		old_memcg = set_active_memcg(memcg);
 		ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (ret)
+			*(struct bpf_mem_cache **)ret = c;
 		set_active_memcg(old_memcg);
 		mem_cgroup_put(memcg);
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bd1c42eb540f..af2819d5c8ee 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)
@@ -542,13 +547,12 @@ 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;
@@ -559,6 +563,18 @@ 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 ||
@@ -1803,6 +1819,7 @@ 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];
@@ -3434,13 +3451,11 @@ 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) {
@@ -3481,6 +3496,15 @@ 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;
@@ -3516,12 +3540,29 @@ 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)--;
@@ -3702,6 +3743,8 @@ 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.
@@ -3877,16 +3920,13 @@ 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));
@@ -3921,10 +3961,18 @@ 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;
@@ -4401,10 +4449,10 @@ 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
@@ -9328,7 +9376,7 @@ 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);
 	}
 }
 
@@ -9341,11 +9389,10 @@ 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;
 
@@ -9355,54 +9402,72 @@ 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) &&
@@ -9413,53 +9478,83 @@ 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);
-	if (err)
-		goto err_out;
-
-	err = set_callee_state_cb(env, caller, callee, *insn_idx);
+	err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
 	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;
 
@@ -9467,14 +9562,10 @@ 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,
@@ -9518,22 +9609,6 @@ 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,
@@ -9726,9 +9801,10 @@ 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];
@@ -9757,6 +9833,11 @@ 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;
@@ -9774,7 +9855,16 @@ 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);
@@ -9785,6 +9875,24 @@ 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;
 }
 
@@ -10187,24 +10295,37 @@ 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) {
@@ -10300,8 +10421,8 @@ 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;
 	}
 
@@ -11189,7 +11310,7 @@ 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];
 }
@@ -11941,6 +12062,21 @@ 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);
 
@@ -11976,10 +12112,6 @@ 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.
 	 */
@@ -12013,16 +12145,6 @@ 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",
@@ -12074,8 +12196,19 @@ 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");
@@ -15375,6 +15508,15 @@ 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,
@@ -15386,8 +15528,7 @@ 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 +15560,7 @@ 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 +15580,20 @@ 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 +15606,17 @@ 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:
@@ -15491,6 +15630,21 @@ 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;
 
@@ -15523,8 +15677,7 @@ 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 +15690,11 @@ 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 +15760,21 @@ 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 */
 
@@ -16951,10 +17114,16 @@ 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 1d5b9de3b1b9..4b9ff41ca603 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3885,14 +3885,6 @@ 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;
@@ -5299,7 +5291,6 @@ 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,
@@ -5308,7 +5299,6 @@ 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,
@@ -5317,7 +5307,6 @@ 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,
@@ -5327,7 +5316,6 @@ 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/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 122dacb3a443..66d1708042a7 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -66,9 +66,15 @@ static struct freezer *parent_freezer(struct freezer *freezer)
 bool cgroup_freezing(struct task_struct *task)
 {
 	bool ret;
+	unsigned int state;
 
 	rcu_read_lock();
-	ret = task_freezer(task)->state & CGROUP_FREEZING;
+	/* Check if the cgroup is still FREEZING, but not FROZEN. The extra
+	 * !FROZEN check is required, because the FREEZING bit is not cleared
+	 * when the state FROZEN is reached.
+	 */
+	state = task_freezer(task)->state;
+	ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN);
 	rcu_read_unlock();
 
 	return ret;
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..c9d123e13b57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1814,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
 	int nr = 1;
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_ID)
+	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_LOST)
+	if (read_format & PERF_FORMAT_LOST)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
-	size += entry * nr;
-	event->read_size = size;
+	/*
+	 * Since perf_event_validate_size() limits this to 16k and inhibits
+	 * adding more siblings, this will never overflow.
+	 */
+	return size + nr * entry;
 }
 
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1888,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
  */
 static void perf_event__header_size(struct perf_event *event)
 {
-	__perf_event_read_size(event,
-			       event->group_leader->nr_siblings);
+	event->read_size =
+		__perf_event_read_size(event->attr.read_format,
+				       event->group_leader->nr_siblings);
 	__perf_event_header_size(event, event->attr.sample_type);
 }
 
@@ -1920,24 +1924,35 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
 static bool perf_event_validate_size(struct perf_event *event)
 {
-	/*
-	 * The values computed here will be over-written when we actually
-	 * attach the event.
-	 */
-	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
-	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
-	perf_event__id_header_size(event);
+	struct perf_event *sibling, *group_leader = event->group_leader;
 
-	/*
-	 * Sum the lot; should not exceed the 64k limit we have on records.
-	 * Conservative limit to allow for callchains and other variable fields.
-	 */
-	if (event->read_size + event->header_size +
-	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+	if (__perf_event_read_size(event->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
+
+	if (__perf_event_read_size(group_leader->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
 		return false;
 
+	for_each_sibling_event(sibling, group_leader) {
+		if (__perf_event_read_size(sibling->attr.read_format,
+					   group_leader->nr_siblings + 1) > 16*1024)
+			return false;
+	}
+
 	return true;
 }
 
@@ -4828,6 +4843,11 @@ 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 +12909,9 @@ 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 +12920,11 @@ 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 +12963,10 @@ 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/freezer.c b/kernel/freezer.c
index c450fa8b8b5e..759006a9a910 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -201,7 +201,7 @@ void __thaw_task(struct task_struct *p)
 	if (WARN_ON_ONCE(freezing(p)))
 		goto unlock;
 
-	if (task_call_func(p, __restore_freezer_state, NULL))
+	if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL))
 		goto unlock;
 
 	wake_up_state(p, TASK_FROZEN);
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/kprobes.c b/kernel/kprobes.c
index 075a632e6c7c..d5a0ee40bf66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2252,7 +2252,7 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->rph = NULL;
 		return -ENOMEM;
 	}
-	rp->rph->rp = rp;
+	rcu_assign_pointer(rp->rph->rp, rp);
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
 	ret = register_kprobe(&rp->kp);
@@ -2300,7 +2300,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 		rethook_free(rps[i]->rh);
 #else
-		rps[i]->rph->rp = NULL;
+		rcu_assign_pointer(rps[i]->rph->rp, NULL);
 #endif
 	}
 	mutex_unlock(&kprobe_mutex);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e85b5ad3e206..151bd3de5936 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3497,7 +3497,8 @@ static int alloc_chain_hlocks(int req)
 		size = chain_block_size(curr);
 		if (likely(size >= req)) {
 			del_chain_block(0, size, chain_block_next(curr));
-			add_chain_block(curr + req, size - req);
+			if (size > req)
+				add_chain_block(curr + req, size - req);
 			return curr;
 		}
 	}
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;
 }
 
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 6fd7d4ecbbc6..fa03094e9e69 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -48,7 +48,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_stop(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rcu_assign_pointer(rh->handler, NULL);
 }
 
 /**
@@ -63,7 +63,7 @@ void rethook_stop(struct rethook *rh)
  */
 void rethook_free(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rethook_stop(rh);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }
@@ -82,6 +82,12 @@ static int rethook_fini_pool(struct objpool_head *head, void *context)
 	return 0;
 }
 
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+	return (rethook_handler_t)rcu_dereference_check(rh->handler,
+							rcu_read_lock_any_held());
+}
+
 /**
  * rethook_alloc() - Allocate struct rethook.
  * @data: a data to pass the @handler when hooking the return.
@@ -107,7 +113,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
 		return ERR_PTR(-ENOMEM);
 
 	rh->data = data;
-	rh->handler = handler;
+	rcu_assign_pointer(rh->handler, handler);
 
 	/* initialize the objpool for rethook nodes */
 	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
@@ -135,9 +141,10 @@ static void free_rethook_node_rcu(struct rcu_head *head)
  */
 void rethook_recycle(struct rethook_node *node)
 {
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler;
 
-	if (likely(READ_ONCE(node->rethook->handler)))
+	handler = rethook_get_handler(node->rethook);
+	if (likely(handler))
 		objpool_push(node, &node->rethook->pool);
 	else
 		call_rcu(&node->rcu, free_rethook_node_rcu);
@@ -153,9 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
  */
 struct rethook_node *rethook_try_get(struct rethook *rh)
 {
-	rethook_handler_t handler = READ_ONCE(rh->handler);
-
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler = rethook_get_handler(rh);
 
 	/* Check whether @rh is going to be freed. */
 	if (unlikely(!handler))
@@ -300,7 +305,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 		rhn = container_of(first, struct rethook_node, llist);
 		if (WARN_ON_ONCE(rhn->frame != frame))
 			break;
-		handler = READ_ONCE(rhn->rethook->handler);
+		handler = rethook_get_handler(rhn->rethook);
 		if (handler)
 			handler(rhn, rhn->rethook->data,
 				correct_ret_addr, regs);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 43cc47d7faaf..8d2a4f00eca9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 
 	*cnt = rb_time_cnt(top);
 
-	/* If top and bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(bottom))
+	/* If top and msb counts don't match, this interrupted a write */
+	if (*cnt != rb_time_cnt(msb))
 		return false;
 
 	/* The shift to msb will lose its cnt bits */
@@ -3030,23 +3030,20 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		unsigned long event_length = rb_event_length(event);
 
+		/*
+		 * For the before_stamp to be different than the write_stamp
+		 * to make sure that the next event adds an absolute
+		 * value and does not rely on the saved write stamp, which
+		 * is now going to be bogus.
+		 */
+		rb_time_set(&cpu_buffer->before_stamp, 0);
+
 		/* Something came in, can't discard */
 		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
 				       write_stamp, write_stamp - delta))
 			return false;
 
 		/*
-		 * It's possible that the event time delta is zero
-		 * (has the same time stamp as the previous event)
-		 * in which case write_stamp and before_stamp could
-		 * be the same. In such a case, force before_stamp
-		 * to be different than write_stamp. It doesn't
-		 * matter what it is, as long as its different.
-		 */
-		if (!delta)
-			rb_time_set(&cpu_buffer->before_stamp, 0);
-
-		/*
 		 * If an event were to come in now, it would see that the
 		 * write_stamp and the before_stamp are different, and assume
 		 * that this event just added itself before updating
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9aebf904ff97..fbcd3bafb93e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2360,13 +2360,7 @@ int is_tracing_stopped(void)
 	return global_trace.stop_count;
 }
 
-/**
- * tracing_start - quick start of the tracer
- *
- * If tracing is enabled but was stopped by tracing_stop,
- * this will start the tracer back up.
- */
-void tracing_start(void)
+static void tracing_start_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
@@ -2374,119 +2368,83 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (--global_trace.stop_count) {
-		if (global_trace.stop_count < 0) {
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (--tr->stop_count) {
+		if (WARN_ON_ONCE(tr->stop_count < 0)) {
 			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			global_trace.stop_count = 0;
+			tr->stop_count = 0;
 		}
 		goto out;
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
-
- out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
-}
-
-static void tracing_start_tr(struct trace_array *tr)
-{
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	if (tracing_disabled)
-		return;
-
-	/* If global, we need to also start the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_start();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-
-	if (--tr->stop_count) {
-		if (tr->stop_count < 0) {
-			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			tr->stop_count = 0;
-		}
-		goto out;
-	}
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_enable(buffer);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 /**
- * tracing_stop - quick stop of the tracer
+ * tracing_start - quick start of the tracer
  *
- * Light weight way to stop tracing. Use in conjunction with
- * tracing_start.
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
  */
-void tracing_stop(void)
+void tracing_start(void)
+
+{
+	return tracing_start_tr(&global_trace);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (global_trace.stop_count++)
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (tr->stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
-static void tracing_stop_tr(struct trace_array *tr)
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
 {
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	/* If global, we need to also stop the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_stop();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-	if (tr->stop_count++)
-		goto out;
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_disable(buffer);
-
- out:
-	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
+	return tracing_stop_tr(&global_trace);
 }
 
 static int trace_save_cmdline(struct task_struct *tsk)
@@ -2770,8 +2728,11 @@ void trace_buffered_event_enable(void)
 	for_each_tracing_cpu(cpu) {
 		page = alloc_pages_node(cpu_to_node(cpu),
 					GFP_KERNEL | __GFP_NORETRY, 0);
-		if (!page)
-			goto failed;
+		/* This is just an optimization and can handle failures */
+		if (!page) {
+			pr_err("Failed to allocate event buffer\n");
+			break;
+		}
 
 		event = page_address(page);
 		memset(event, 0, sizeof(*event));
@@ -2785,10 +2746,6 @@ void trace_buffered_event_enable(void)
 			WARN_ON_ONCE(1);
 		preempt_enable();
 	}
-
-	return;
- failed:
-	trace_buffered_event_disable();
 }
 
 static void enable_trace_buffered_event(void *data)
@@ -2823,11 +2780,9 @@ void trace_buffered_event_disable(void)
 	if (--trace_buffered_event_ref)
 		return;
 
-	preempt_disable();
 	/* For each CPU, set the buffer as used. */
-	smp_call_function_many(tracing_buffer_mask,
-			       disable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event,
+			 NULL, true);
 
 	/* Wait for all current users to finish */
 	synchronize_rcu();
@@ -2836,17 +2791,19 @@ void trace_buffered_event_disable(void)
 		free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
 		per_cpu(trace_buffered_event, cpu) = NULL;
 	}
+
 	/*
-	 * Make sure trace_buffered_event is NULL before clearing
-	 * trace_buffered_event_cnt.
+	 * Wait for all CPUs that potentially started checking if they can use
+	 * their event buffer only after the previous synchronize_rcu() call and
+	 * they still read a valid pointer from trace_buffered_event. It must be
+	 * ensured they don't see cleared trace_buffered_event_cnt else they
+	 * could wrongly decide to use the pointed-to buffer which is now freed.
 	 */
-	smp_wmb();
+	synchronize_rcu();
 
-	preempt_disable();
-	/* Do the work on each cpu */
-	smp_call_function_many(tracing_buffer_mask,
-			       enable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	/* For each CPU, relinquish the buffer */
+	on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL,
+			 true);
 }
 
 static struct trace_buffer *temp_buffer;
@@ -6387,13 +6344,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 	if (!tr->array_buffer.buffer)
 		return 0;
 
+	/* Do not allow tracing while resizng ring buffer */
+	tracing_stop_tr(tr);
+
 	ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
 	if (ret < 0)
-		return ret;
+		goto out_start;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
-	    !tr->current_trace->use_max_tr)
+	if (!tr->current_trace->use_max_tr)
 		goto out;
 
 	ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
@@ -6418,7 +6377,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 			WARN_ON(1);
 			tracing_disabled = 1;
 		}
-		return ret;
+		goto out_start;
 	}
 
 	update_buffer_entries(&tr->max_buffer, cpu);
@@ -6427,7 +6386,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 	update_buffer_entries(&tr->array_buffer, cpu);
-
+ out_start:
+	tracing_start_tr(tr);
 	return ret;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6e578f576a6f..2989b57e154a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1684,9 +1684,6 @@ static int wq_select_unbound_cpu(int cpu)
 		pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n");
 	}
 
-	if (cpumask_empty(wq_unbound_cpumask))
-		return cpu;
-
 	new_cpu = __this_cpu_read(wq_rr_cpu_last);
 	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
 	if (unlikely(new_cpu >= nr_cpu_ids)) {
@@ -6515,6 +6512,17 @@ static inline void wq_watchdog_init(void) { }
 
 #endif	/* CONFIG_WQ_WATCHDOG */
 
+static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
+{
+	if (!cpumask_intersects(wq_unbound_cpumask, mask)) {
+		pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n",
+			cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask));
+		return;
+	}
+
+	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
+}
+
 /**
  * workqueue_init_early - early init for workqueue subsystem
  *
@@ -6534,11 +6542,11 @@ void __init workqueue_init_early(void)
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
-	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
-	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
-
+	cpumask_copy(wq_unbound_cpumask, cpu_possible_mask);
+	restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ));
+	restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN));
 	if (!cpumask_empty(&wq_cmdline_cpumask))
-		cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask);
+		restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);