Merge tag 'v5.5-rc7' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

24 files changed, 249 insertions, 162 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 4fb20ab179fe..9e43b72eb619 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp)
  */
 static void cgroup_bpf_release(struct work_struct *work)
 {
-	struct cgroup *cgrp = container_of(work, struct cgroup,
-					   bpf.release_work);
+	struct cgroup *p, *cgrp = container_of(work, struct cgroup,
+					       bpf.release_work);
 	enum bpf_cgroup_storage_type stype;
 	struct bpf_prog_array *old_array;
 	unsigned int type;
@@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work)
 
 	mutex_unlock(&cgroup_mutex);
 
+	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+		cgroup_bpf_put(p);
+
 	percpu_ref_exit(&cgrp->bpf.refcnt);
 	cgroup_put(cgrp);
 }
@@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
  */
 #define	NR ARRAY_SIZE(cgrp->bpf.effective)
 	struct bpf_prog_array *arrays[NR] = {};
+	struct cgroup *p;
 	int ret, i;
 
 	ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0,
@@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
 	if (ret)
 		return ret;
 
+	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+		cgroup_bpf_get(p);
+
 	for (i = 0; i < NR; i++)
 		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
 
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index ca52b9642943..d4f335a9a899 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift)
 	return TNUM(a.value >> shift, a.mask >> shift);
 }
 
-struct tnum tnum_arshift(struct tnum a, u8 min_shift)
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
 {
 	/* if a.value is negative, arithmetic shifting by minimum shift
 	 * will have larger negative offset compared to more shifting.
 	 * If a.value is nonnegative, arithmetic shifting by minimum shift
 	 * will have larger positive offset compare to more shifting.
 	 */
-	return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift);
+	if (insn_bitness == 32)
+		return TNUM((u32)(((s32)a.value) >> min_shift),
+			    (u32)(((s32)a.mask)  >> min_shift));
+	else
+		return TNUM((s64)a.value >> min_shift,
+			    (s64)a.mask  >> min_shift);
 }
 
 struct tnum tnum_add(struct tnum a, struct tnum b)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4983940cbdca..7d530ce8719d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = {
 	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
 };
 
-static void __mark_reg_not_init(struct bpf_reg_state *reg);
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+				struct bpf_reg_state *reg);
 
 /* Mark the unknown part of a register (variable offset or scalar value) as
  * known to have the value @imm.
@@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
 		verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs */
 		for (regno = 0; regno < MAX_BPF_REG; regno++)
-			__mark_reg_not_init(regs + regno);
+			__mark_reg_not_init(env, regs + regno);
 		return;
 	}
 	__mark_reg_known_zero(regs + regno);
@@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg)
 }
 
 /* Mark a register as having a completely unknown (scalar) value. */
-static void __mark_reg_unknown(struct bpf_reg_state *reg)
+static void __mark_reg_unknown(const struct bpf_verifier_env *env,
+			       struct bpf_reg_state *reg)
 {
 	/*
 	 * Clear type, id, off, and union(map_ptr, range) and
@@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg)
 	reg->type = SCALAR_VALUE;
 	reg->var_off = tnum_unknown;
 	reg->frameno = 0;
+	reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
+		       true : false;
 	__mark_reg_unbounded(reg);
 }
 
@@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env,
 		verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs except FP */
 		for (regno = 0; regno < BPF_REG_FP; regno++)
-			__mark_reg_not_init(regs + regno);
+			__mark_reg_not_init(env, regs + regno);
 		return;
 	}
-	regs += regno;
-	__mark_reg_unknown(regs);
-	/* constant backtracking is enabled for root without bpf2bpf calls */
-	regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
-			true : false;
+	__mark_reg_unknown(env, regs + regno);
 }
 
-static void __mark_reg_not_init(struct bpf_reg_state *reg)
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+				struct bpf_reg_state *reg)
 {
-	__mark_reg_unknown(reg);
+	__mark_reg_unknown(env, reg);
 	reg->type = NOT_INIT;
 }
 
@@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
 		verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
 		/* Something bad happened, let's kill all regs except FP */
 		for (regno = 0; regno < BPF_REG_FP; regno++)
-			__mark_reg_not_init(regs + regno);
+			__mark_reg_not_init(env, regs + regno);
 		return;
 	}
-	__mark_reg_not_init(regs + regno);
+	__mark_reg_not_init(env, regs + regno);
 }
 
 #define DEF_NOT_SUBREG	(0)
@@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		}
 		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
 		    state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
-			__mark_reg_unknown(&state->stack[spi].spilled_ptr);
+			__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
 			for (j = 0; j < BPF_REG_SIZE; j++)
 				state->stack[spi].slot_type[j] = STACK_MISC;
 			goto mark;
@@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
 		if (!reg)
 			continue;
 		if (reg_is_pkt_pointer_any(reg))
-			__mark_reg_unknown(reg);
+			__mark_reg_unknown(env, reg);
 	}
 }
 
@@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env,
 		if (!reg)
 			continue;
 		if (reg->ref_obj_id == ref_obj_id)
-			__mark_reg_unknown(reg);
+			__mark_reg_unknown(env, reg);
 	}
 }
 
@@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		/* Taint dst register if offset had invalid bounds derived from
 		 * e.g. dead branches.
 		 */
-		__mark_reg_unknown(dst_reg);
+		__mark_reg_unknown(env, dst_reg);
 		return 0;
 	}
 
@@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		/* Taint dst register if offset had invalid bounds derived from
 		 * e.g. dead branches.
 		 */
-		__mark_reg_unknown(dst_reg);
+		__mark_reg_unknown(env, dst_reg);
 		return 0;
 	}
 
 	if (!src_known &&
 	    opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
-		__mark_reg_unknown(dst_reg);
+		__mark_reg_unknown(env, dst_reg);
 		return 0;
 	}
 
@@ -5048,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		/* Upon reaching here, src_known is true and
 		 * umax_val is equal to umin_val.
 		 */
-		dst_reg->smin_value >>= umin_val;
-		dst_reg->smax_value >>= umin_val;
-		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val);
+		if (insn_bitness == 32) {
+			dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+			dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+		} else {
+			dst_reg->smin_value >>= umin_val;
+			dst_reg->smax_value >>= umin_val;
+		}
+
+		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+						insn_bitness);
 
 		/* blow away the dst_reg umin_value/umax_value and rely on
 		 * dst_reg var_off to refine the result.
@@ -6263,6 +6271,7 @@ static bool may_access_skb(enum bpf_prog_type type)
 static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
+	static const int ctx_reg = BPF_REG_6;
 	u8 mode = BPF_MODE(insn->code);
 	int i, err;
 
@@ -6296,7 +6305,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	}
 
 	/* check whether implicit source operand (register R6) is readable */
-	err = check_reg_arg(env, BPF_REG_6, SRC_OP);
+	err = check_reg_arg(env, ctx_reg, SRC_OP);
 	if (err)
 		return err;
 
@@ -6315,7 +6324,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+	if (regs[ctx_reg].type != PTR_TO_CTX) {
 		verbose(env,
 			"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
 		return -EINVAL;
@@ -6328,6 +6337,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return err;
 	}
 
+	err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+	if (err < 0)
+		return err;
+
 	/* reset caller saved regs to unreadable */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
@@ -6982,7 +6995,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
 			/* since the register is unused, clear its state
 			 * to make further comparison simpler
 			 */
-			__mark_reg_not_init(&st->regs[i]);
+			__mark_reg_not_init(env, &st->regs[i]);
 	}
 
 	for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
@@ -6990,7 +7003,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
 		/* liveness must not touch this stack slot anymore */
 		st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
 		if (!(live & REG_LIVE_READ)) {
-			__mark_reg_not_init(&st->stack[i].spilled_ptr);
+			__mark_reg_not_init(env, &st->stack[i].spilled_ptr);
 			for (j = 0; j < BPF_REG_SIZE; j++)
 				st->stack[i].slot_type[j] = STACK_INVALID;
 		}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59cc980adad..4dc279ed3b2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1909,6 +1909,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
 
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
+	cpu_maps_update_done();
+	return ret;
+}
+#endif
+
 #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
 static ssize_t show_cpuhp_state(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -2063,77 +2135,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 
 #ifdef CONFIG_HOTPLUG_SMT
 
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
-	struct device *dev = get_cpu_device(cpu);
-
-	dev->offline = true;
-	/* Tell user space about the state change */
-	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
-	struct device *dev = get_cpu_device(cpu);
-
-	dev->offline = false;
-	/* Tell user space about the state change */
-	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
-	int cpu, ret = 0;
-
-	cpu_maps_update_begin();
-	for_each_online_cpu(cpu) {
-		if (topology_is_primary_thread(cpu))
-			continue;
-		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
-		if (ret)
-			break;
-		/*
-		 * As this needs to hold the cpu maps lock it's impossible
-		 * to call device_offline() because that ends up calling
-		 * cpu_down() which takes cpu maps lock. cpu maps lock
-		 * needs to be held as this might race against in kernel
-		 * abusers of the hotplug machinery (thermal management).
-		 *
-		 * So nothing would update device:offline state. That would
-		 * leave the sysfs entry stale and prevent onlining after
-		 * smt control has been changed to 'off' again. This is
-		 * called under the sysfs hotplug lock, so it is properly
-		 * serialized against the regular offline usage.
-		 */
-		cpuhp_offline_cpu_device(cpu);
-	}
-	if (!ret)
-		cpu_smt_control = ctrlval;
-	cpu_maps_update_done();
-	return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
-	int cpu, ret = 0;
-
-	cpu_maps_update_begin();
-	cpu_smt_control = CPU_SMT_ENABLED;
-	for_each_present_cpu(cpu) {
-		/* Skip online CPUs and CPUs on offline nodes */
-		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
-			continue;
-		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
-		if (ret)
-			break;
-		/* See comment in cpuhp_smt_disable() */
-		cpuhp_online_cpu_device(cpu);
-	}
-	cpu_maps_update_done();
-	return ret;
-}
-
-
 static ssize_t
 __store_smt_control(struct device *dev, struct device_attribute *attr,
 		    const char *buf, size_t count)
diff --git a/kernel/cred.c b/kernel/cred.c
index c0a4c12d38b2..809a985b1793 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk)
 	put_cred(cred);
 
 #ifdef CONFIG_KEYS_REQUEST_CACHE
-	key_put(current->cached_requested_key);
-	current->cached_requested_key = NULL;
+	key_put(tsk->cached_requested_key);
+	tsk->cached_requested_key = NULL;
 #endif
 }
 
@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
 	new->magic = CRED_MAGIC;
 #endif
 
-	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
 	new->security = NULL;
 #endif
 
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 	validate_creds(new);
 	return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 #ifdef CONFIG_SECURITY
 	new->security = NULL;
 #endif
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	put_cred(old);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a1f8bde19b56..2173c23c25b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11465,8 +11465,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader))
+	if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) {
+		err = -EINVAL;
 		goto err_locked;
+	}
 
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
diff --git a/kernel/exit.c b/kernel/exit.c
index bcbd59888e67..2833ffb0c211 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	if (unlikely(pid_ns == &init_pid_ns)) {
-		panic("Attempted to kill init! exitcode=0x%08x\n",
-			father->signal->group_exit_code ?: father->exit_code);
-	}
 
 	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
 		list_del_init(&p->ptrace_entry);
@@ -766,6 +762,14 @@ void __noreturn do_exit(long code)
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
+		/*
+		 * If the last thread of global init has exited, panic
+		 * immediately to get a useable coredump.
+		 */
+		if (unlikely(is_global_init(tsk)))
+			panic("Attempted to kill init! exitcode=0x%08x\n",
+				tsk->signal->group_exit_code ?: (int)code);
+
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2508a4f238a3..080809560072 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #endif
 
 #ifdef __ARCH_WANT_SYS_CLONE3
+
+/*
+ * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
+ * the registers containing the syscall arguments for clone. This doesn't work
+ * with clone3 since the TLS value is passed in clone_args instead.
+ */
+#ifndef CONFIG_HAVE_COPY_THREAD_TLS
+#error clone3 requires copy_thread_tls support in arch
+#endif
+
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)
diff --git a/kernel/futex.c b/kernel/futex.c
index 03c518e9747e..0cf84c8664f2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1178,6 +1178,7 @@ out_error:
 
 /**
  * wait_for_owner_exiting - Block until the owner has exited
+ * @ret: owner's current futex lock status
  * @exiting:	Pointer to the exiting task
  *
  * Caller must hold a refcount on @exiting.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32282e7112d3..32406ef0d6a2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void)
 	struct lock_trace *trace, *t2;
 	struct hlist_head *hash_head;
 	u32 hash;
-	unsigned int max_entries;
+	int max_entries;
 
 	BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE);
 	BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES);
@@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void)
 	trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries);
 	max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries -
 		LOCK_TRACE_SIZE_IN_LONGS;
-	trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
 
-	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES -
-	    LOCK_TRACE_SIZE_IN_LONGS - 1) {
+	if (max_entries <= 0) {
 		if (!debug_locks_off_graph_unlock())
 			return NULL;
 
@@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void)
 
 		return NULL;
 	}
+	trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3);
 
 	hash = jhash(trace->entries, trace->nr_entries *
 		     sizeof(trace->entries[0]), 0);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 44e68761f432..0d9b6be9ecc8 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1226,8 +1226,8 @@ wait:
 		 * In this case, we attempt to acquire the lock again
 		 * without sleeping.
 		 */
-		if ((wstate == WRITER_HANDOFF) &&
-		    (rwsem_spin_on_owner(sem, 0) == OWNER_NULL))
+		if (wstate == WRITER_HANDOFF &&
+		    rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL)
 			goto trylock_again;
 
 		/* Block until there are no active lockers. */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index cb9ddcc08119..43d6179508d6 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	return ret;
 }
 
-static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
+			   unsigned int mode)
 {
+	int ret;
+
 	if (mode & PTRACE_MODE_NOAUDIT)
-		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
 	else
-		return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+		ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
+
+	return ret == 0;
 }
 
 /* Returns 0 on success, -errno on denial. */
@@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	    gid_eq(caller_gid, tcred->sgid) &&
 	    gid_eq(caller_gid, tcred->gid))
 		goto ok;
-	if (ptrace_has_cap(tcred->user_ns, mode))
+	if (ptrace_has_cap(cred, tcred->user_ns, mode))
 		goto ok;
 	rcu_read_unlock();
 	return -EPERM;
@@ -340,7 +345,7 @@ ok:
 	mm = task->mm;
 	if (mm &&
 	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
-	     !ptrace_has_cap(mm->user_ns, mode)))
+	     !ptrace_has_cap(cred, mm->user_ns, mode)))
 	    return -EPERM;
 
 	return security_ptrace_access_check(task, mode);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 27c48eb7de40..a4f86a9d6937 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	int ret;
 
 	if (flags & RSEQ_FLAG_UNREGISTER) {
+		if (flags & ~RSEQ_FLAG_UNREGISTER)
+			return -EINVAL;
 		/* Unregister rseq for current thread. */
 		if (current->rseq != rseq || !current->rseq)
 			return -EINVAL;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 12d2227e5786..b6ea3dcb57bf 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 	struct seccomp_notif unotif;
 	ssize_t ret;
 
+	/* Verify that we're not given garbage to keep struct extensible. */
+	ret = check_zeroed_user(buf, sizeof(unotif));
+	if (ret < 0)
+		return ret;
+	if (!ret)
+		return -EINVAL;
+
 	memset(&unotif, 0, sizeof(unotif));
 
 	ret = down_interruptible(&filter->notif->request);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..e2ac0e37c4ae 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
-	struct taskstats *stats;
+	struct taskstats *stats_new, *stats;
 
-	if (sig->stats || thread_group_empty(tsk))
-		goto ret;
+	/* Pairs with smp_store_release() below. */
+	stats = smp_load_acquire(&sig->stats);
+	if (stats || thread_group_empty(tsk))
+		return stats;
 
 	/* No problem if kmem_cache_zalloc() fails */
-	stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+	stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
 
 	spin_lock_irq(&tsk->sighand->siglock);
-	if (!sig->stats) {
-		sig->stats = stats;
-		stats = NULL;
+	stats = sig->stats;
+	if (!stats) {
+		/*
+		 * Pairs with smp_store_release() above and order the
+		 * kmem_cache_zalloc().
+		 */
+		smp_store_release(&sig->stats, stats_new);
+		stats = stats_new;
+		stats_new = NULL;
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	if (stats)
-		kmem_cache_free(taskstats_cache, stats);
-ret:
-	return sig->stats;
+	if (stats_new)
+		kmem_cache_free(taskstats_cache, stats_new);
+
+	return stats;
 }
 
 /* Send pid data out on exit */
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ec960bb939fd..200fb2d3be99 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -14,8 +14,6 @@
 
 #include "posix-timers.h"
 
-static void delete_clock(struct kref *kref);
-
 /*
  * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
  */
@@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		err = 0;
 
 	if (!err) {
-		kref_get(&clk->kref);
+		get_device(clk->dev);
 		fp->private_data = clk;
 	}
 out:
@@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
 	if (clk->ops.release)
 		err = clk->ops.release(clk);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 
 	fp->private_data = NULL;
 
@@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = {
 #endif
 };
 
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
 {
 	int err;
 
-	kref_init(&clk->kref);
 	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	err = cdev_device_add(&clk->cdev, dev);
+	if (err) {
+		pr_err("%s unable to add device %d:%d\n",
+			dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+		return err;
+	}
 	clk->cdev.owner = clk->ops.owner;
-	err = cdev_add(&clk->cdev, devid, 1);
+	clk->dev = dev;
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
-static void delete_clock(struct kref *kref)
-{
-	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
-	if (clk->release)
-		clk->release(clk);
-}
-
 void posix_clock_unregister(struct posix_clock *clk)
 {
-	cdev_del(&clk->cdev);
+	cdev_device_del(&clk->cdev, clk->dev);
 
 	down_write(&clk->rwsem);
 	clk->zombie = true;
 	up_write(&clk->rwsem);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 }
 EXPORT_SYMBOL_GPL(posix_clock_unregister);
 
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 67df65f887ac..20c65a7d4e3a 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -151,6 +151,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 
 #ifdef CONFIG_COMPAT
 COMPAT_SYS_NI(timer_create);
+#endif
+
+#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
 COMPAT_SYS_NI(getitimer);
 COMPAT_SYS_NI(setitimer);
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8b192e67aabc..a792d21cac64 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 
 	/*
 	 * Do a quick check without holding jiffies_lock:
+	 * The READ_ONCE() pairs with two updates done later in this function.
 	 */
-	delta = ktime_sub(now, last_jiffies_update);
+	delta = ktime_sub(now, READ_ONCE(last_jiffies_update));
 	if (delta < tick_period)
 		return;
 
@@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 	if (delta >= tick_period) {
 
 		delta = ktime_sub(delta, tick_period);
-		last_jiffies_update = ktime_add(last_jiffies_update,
-						tick_period);
+		/* Pairs with the lockless read in this function. */
+		WRITE_ONCE(last_jiffies_update,
+			   ktime_add(last_jiffies_update, tick_period));
 
 		/* Slow path for long timeouts */
 		if (unlikely(delta >= tick_period)) {
@@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now)
 
 			ticks = ktime_divns(delta, incr);
 
-			last_jiffies_update = ktime_add_ns(last_jiffies_update,
-							   incr * ticks);
+			/* Pairs with the lockless read in this function. */
+			WRITE_ONCE(last_jiffies_update,
+				   ktime_add_ns(last_jiffies_update,
+						incr * ticks));
 		}
 		do_timer(++ticks);
 
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index a2659735db73..1af321dec0f1 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -96,6 +96,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 	return 0;
 }
 
+/*
+ * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct
+ * functions. But those archs currently don't support direct functions
+ * anyway, and ftrace_find_rec_direct() is just a stub for them.
+ * Define MCOUNT_INSN_SIZE to keep those archs compiling.
+ */
+#ifndef MCOUNT_INSN_SIZE
+/* Make sure this only works without direct calls */
+# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+#  error MCOUNT_INSN_SIZE not defined with direct calls enabled
+# endif
+# define MCOUNT_INSN_SIZE 0
+#endif
+
 int function_graph_enter(unsigned long ret, unsigned long func,
 			 unsigned long frame_pointer, unsigned long *retp)
 {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ac99a3500076..9bf1f2cd515e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v)
 	}
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	avg = rec->time;
-	do_div(avg, rec->counter);
+	avg = div64_ul(rec->time, rec->counter);
 	if (tracing_thresh && (avg < tracing_thresh))
 		goto out;
 #endif
@@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v)
 		 * Divide only 1000 for ns^2 -> us^2 conversion.
 		 * trace_print_graph_duration will divide 1000 again.
 		 */
-		do_div(stddev, rec->counter * (rec->counter - 1) * 1000);
+		stddev = div64_ul(stddev,
+				  rec->counter * (rec->counter - 1) * 1000);
 	}
 
 	trace_seq_init(&s);
diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
index d45079ee62f8..22bcf7c51d1e 100644
--- a/kernel/trace/trace_events_inject.c
+++ b/kernel/trace/trace_events_inject.c
@@ -195,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry)
 	unsigned long irq_flags;
 	void *entry = NULL;
 	int entry_size;
-	u64 val;
+	u64 val = 0;
 	int len;
 
 	entry = trace_alloc_entry(call, &entry_size);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5e43b9664eca..617e297f46dc 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
 	if (ret) {
 		pr_info("wakeup trace: Couldn't activate tracepoint"
 			" probe to kernel_sched_migrate_task\n");
-		return;
+		goto fail_deprobe_sched_switch;
 	}
 
 	wakeup_reset(tr);
@@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
 		printk(KERN_ERR "failed to start wakeup tracer\n");
 
 	return;
+fail_deprobe_sched_switch:
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 fail_deprobe_wake_new:
 	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 fail_deprobe:
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 344e4c1aa09c..87de6edafd14 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str,
 		       int prefix_type, int rowsize, int groupsize,
 		       const void *buf, size_t len, bool ascii)
 {
-		unsigned int save_len = s->seq.len;
+	unsigned int save_len = s->seq.len;
 
 	if (s->full)
 		return 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 4df9a209f7ca..c557f42a9397 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack)
 	local_irq_restore(flags);
 }
 
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		 struct ftrace_ops *op, struct pt_regs *pt_regs)