Merge branch 'linus' into irq/core, to fix conflict

Conflicts:
	drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c

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

23 files changed, 237 insertions, 114 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 121d37e700a6..4cebadb5f30d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
 {
 	int rc = 0;
 	struct sk_buff *skb;
-	static unsigned int failed = 0;
+	unsigned int failed = 0;
 
 	/* NOTE: kauditd_thread takes care of all our locking, we just use
 	 *       the netlink info passed to us (e.g. sk and portid) */
@@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
 			continue;
 		}
 
+retry:
 		/* grab an extra skb reference in case of error */
 		skb_get(skb);
 		rc = netlink_unicast(sk, skb, portid, 0);
 		if (rc < 0) {
-			/* fatal failure for our queue flush attempt? */
+			/* send failed - try a few times unless fatal error */
 			if (++failed >= retry_limit ||
 			    rc == -ECONNREFUSED || rc == -EPERM) {
-				/* yes - error processing for the queue */
 				sk = NULL;
 				if (err_hook)
 					(*err_hook)(skb);
-				if (!skb_hook)
-					goto out;
-				/* keep processing with the skb_hook */
+				if (rc == -EAGAIN)
+					rc = 0;
+				/* continue to drain the queue */
 				continue;
 			} else
-				/* no - requeue to preserve ordering */
-				skb_queue_head(queue, skb);
+				goto retry;
 		} else {
-			/* it worked - drop the extra reference and continue */
+			/* skb sent - drop the extra reference and continue */
 			consume_skb(skb);
 			failed = 0;
 		}
 	}
 
-out:
 	return (rc >= 0 ? 0 : rc);
 }
 
@@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net)
 		audit_panic("cannot initialize netlink socket in namespace");
 		return -ENOMEM;
 	}
-	aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	/* limit the timeout in case auditd is blocked/stopped */
+	aunet->sk->sk_sndtimeo = HZ / 10;
 
 	return 0;
 }
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dbc3ad07e21b..9bdb03767db5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
 
 /* BTF ID set registration API for modules */
 
-struct kfunc_btf_id_list {
-	struct list_head list;
-	struct mutex mutex;
-};
-
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 
 void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -6376,8 +6371,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 {
 	struct kfunc_btf_id_set *s;
 
-	if (!owner)
-		return false;
 	mutex_lock(&klist->mutex);
 	list_for_each_entry(s, &klist->list, list) {
 		if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
@@ -6389,8 +6382,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 	return false;
 }
 
-#endif
-
 #define DEFINE_KFUNC_BTF_ID_LIST(name)                                         \
 	struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list),           \
 					  __MUTEX_INITIALIZER(name.mutex) };   \
@@ -6398,3 +6389,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 
 DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
 DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+
+#endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 50efda51515b..b532f1058d35 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1366,22 +1366,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
 
+static bool __reg32_bound_s64(s32 a)
+{
+	return a >= 0 && a <= S32_MAX;
+}
+
 static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 {
 	reg->umin_value = reg->u32_min_value;
 	reg->umax_value = reg->u32_max_value;
-	/* Attempt to pull 32-bit signed bounds into 64-bit bounds
-	 * but must be positive otherwise set to worse case bounds
-	 * and refine later from tnum.
+
+	/* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+	 * be positive otherwise set to worse case bounds and refine later
+	 * from tnum.
 	 */
-	if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
-		reg->smax_value = reg->s32_max_value;
-	else
-		reg->smax_value = U32_MAX;
-	if (reg->s32_min_value >= 0)
+	if (__reg32_bound_s64(reg->s32_min_value) &&
+	    __reg32_bound_s64(reg->s32_max_value)) {
 		reg->smin_value = reg->s32_min_value;
-	else
+		reg->smax_value = reg->s32_max_value;
+	} else {
 		reg->smin_value = 0;
+		reg->smax_value = U32_MAX;
+	}
 }
 
 static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -2379,8 +2385,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		 */
 		if (insn->src_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
@@ -2403,8 +2407,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		/* scalars can only be spilled into stack */
 		if (insn->dst_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 		spi = (-insn->off - 1) / BPF_REG_SIZE;
 		if (spi >= 64) {
 			verbose(env, "BUG spi %d\n", spi);
@@ -4551,9 +4553,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 
 	if (insn->imm == BPF_CMPXCHG) {
 		/* Check comparison of R0 with memory location */
-		err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+		const u32 aux_reg = BPF_REG_0;
+
+		err = check_reg_arg(env, aux_reg, SRC_OP);
 		if (err)
 			return err;
+
+		if (is_pointer_value(env, aux_reg)) {
+			verbose(env, "R%d leaks addr into mem\n", aux_reg);
+			return -EACCES;
+		}
 	}
 
 	if (is_pointer_value(env, insn->src_reg)) {
@@ -4588,13 +4597,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 		load_reg = -1;
 	}
 
-	/* check whether we can read the memory */
+	/* Check whether we can read the memory, with second call for fetch
+	 * case to simulate the register fill.
+	 */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, load_reg, true);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true);
+	if (!err && load_reg >= 0)
+		err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+				       BPF_SIZE(insn->code), BPF_READ, load_reg,
+				       true);
 	if (err)
 		return err;
 
-	/* check whether we can write into the same memory */
+	/* Check whether we can write into the same memory. */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 	if (err)
@@ -8308,6 +8323,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 							 insn->dst_reg);
 				}
 				zext_32_to_64(dst_reg);
+
+				__update_reg_bounds(dst_reg);
+				__reg_deduce_bounds(dst_reg);
+				__reg_bound_offset(dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -8422,7 +8441,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 
 	new_range = dst_reg->off;
 	if (range_right_open)
-		new_range--;
+		new_range++;
 
 	/* Examples for register markings:
 	 *
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index bfbeabc17a9d..6e36e854b512 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -65,6 +65,25 @@ static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc)
 	return container_of(kfc, struct cgroup_fs_context, kfc);
 }
 
+struct cgroup_pidlist;
+
+struct cgroup_file_ctx {
+	struct cgroup_namespace	*ns;
+
+	struct {
+		void			*trigger;
+	} psi;
+
+	struct {
+		bool			started;
+		struct css_task_iter	iter;
+	} procs;
+
+	struct {
+		struct cgroup_pidlist	*pidlist;
+	} procs1;
+};
+
 /*
  * A cgroup can be associated with multiple css_sets as different tasks may
  * belong to different cgroups on different hierarchies.  In the other
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 81c9e0685948..41e0837a5a0b 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -394,6 +394,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 	 * next pid to display, if any
 	 */
 	struct kernfs_open_file *of = s->private;
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *cgrp = seq_css(s)->cgroup;
 	struct cgroup_pidlist *l;
 	enum cgroup_filetype type = seq_cft(s)->private;
@@ -403,25 +404,24 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 	mutex_lock(&cgrp->pidlist_mutex);
 
 	/*
-	 * !NULL @of->priv indicates that this isn't the first start()
-	 * after open.  If the matching pidlist is around, we can use that.
-	 * Look for it.  Note that @of->priv can't be used directly.  It
-	 * could already have been destroyed.
+	 * !NULL @ctx->procs1.pidlist indicates that this isn't the first
+	 * start() after open. If the matching pidlist is around, we can use
+	 * that. Look for it. Note that @ctx->procs1.pidlist can't be used
+	 * directly. It could already have been destroyed.
 	 */
-	if (of->priv)
-		of->priv = cgroup_pidlist_find(cgrp, type);
+	if (ctx->procs1.pidlist)
+		ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type);
 
 	/*
 	 * Either this is the first start() after open or the matching
 	 * pidlist has been destroyed inbetween.  Create a new one.
 	 */
-	if (!of->priv) {
-		ret = pidlist_array_load(cgrp, type,
-					 (struct cgroup_pidlist **)&of->priv);
+	if (!ctx->procs1.pidlist) {
+		ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist);
 		if (ret)
 			return ERR_PTR(ret);
 	}
-	l = of->priv;
+	l = ctx->procs1.pidlist;
 
 	if (pid) {
 		int end = l->length;
@@ -449,7 +449,8 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
 	struct kernfs_open_file *of = s->private;
-	struct cgroup_pidlist *l = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
+	struct cgroup_pidlist *l = ctx->procs1.pidlist;
 
 	if (l)
 		mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork,
@@ -460,7 +461,8 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct kernfs_open_file *of = s->private;
-	struct cgroup_pidlist *l = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
+	struct cgroup_pidlist *l = ctx->procs1.pidlist;
 	pid_t *p = v;
 	pid_t *end = l->list + l->length;
 	/*
@@ -504,10 +506,11 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of,
 		goto out_unlock;
 
 	/*
-	 * Even if we're attaching all tasks in the thread group, we only
-	 * need to check permissions on one of them.
+	 * Even if we're attaching all tasks in the thread group, we only need
+	 * to check permissions on one of them. Check permissions using the
+	 * credentials from file open to protect against inherited fd attacks.
 	 */
-	cred = current_cred();
+	cred = of->file->f_cred;
 	tcred = get_task_cred(task);
 	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
 	    !uid_eq(cred->euid, tcred->uid) &&
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 919194de39c8..cafb8c114a21 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3630,6 +3630,7 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 					  size_t nbytes, enum psi_res res)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
@@ -3648,7 +3649,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 		return PTR_ERR(new);
 	}
 
-	psi_trigger_replace(&of->priv, new);
+	psi_trigger_replace(&ctx->psi.trigger, new);
 
 	cgroup_put(cgrp);
 
@@ -3679,12 +3680,16 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
 static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 					  poll_table *pt)
 {
-	return psi_trigger_poll(&of->priv, of->file, pt);
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
-	psi_trigger_replace(&of->priv, NULL);
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	psi_trigger_replace(&ctx->psi.trigger, NULL);
 }
 
 bool cgroup_psi_enabled(void)
@@ -3811,24 +3816,43 @@ static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf,
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of_cft(of);
+	struct cgroup_file_ctx *ctx;
+	int ret;
 
-	if (cft->open)
-		return cft->open(of);
-	return 0;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ns = current->nsproxy->cgroup_ns;
+	get_cgroup_ns(ctx->ns);
+	of->priv = ctx;
+
+	if (!cft->open)
+		return 0;
+
+	ret = cft->open(of);
+	if (ret) {
+		put_cgroup_ns(ctx->ns);
+		kfree(ctx);
+	}
+	return ret;
 }
 
 static void cgroup_file_release(struct kernfs_open_file *of)
 {
 	struct cftype *cft = of_cft(of);
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (cft->release)
 		cft->release(of);
+	put_cgroup_ns(ctx->ns);
+	kfree(ctx);
 }
 
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *cgrp = of->kn->parent->priv;
 	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
@@ -3845,7 +3869,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
-	    ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp)
+	    ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp)
 		return -EPERM;
 
 	if (cft->write)
@@ -4751,21 +4775,21 @@ void css_task_iter_end(struct css_task_iter *it)
 
 static void cgroup_procs_release(struct kernfs_open_file *of)
 {
-	if (of->priv) {
-		css_task_iter_end(of->priv);
-		kfree(of->priv);
-	}
+	struct cgroup_file_ctx *ctx = of->priv;
+
+	if (ctx->procs.started)
+		css_task_iter_end(&ctx->procs.iter);
 }
 
 static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct kernfs_open_file *of = s->private;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
 
 	if (pos)
 		(*pos)++;
 
-	return css_task_iter_next(it);
+	return css_task_iter_next(&ctx->procs.iter);
 }
 
 static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
@@ -4773,21 +4797,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos,
 {
 	struct kernfs_open_file *of = s->private;
 	struct cgroup *cgrp = seq_css(s)->cgroup;
-	struct css_task_iter *it = of->priv;
+	struct cgroup_file_ctx *ctx = of->priv;
+	struct css_task_iter *it = &ctx->procs.iter;
 
 	/*
 	 * When a seq_file is seeked, it's always traversed sequentially
 	 * from position 0, so we can simply keep iterating on !0 *pos.
 	 */
-	if (!it) {
+	if (!ctx->procs.started) {
 		if (WARN_ON_ONCE((*pos)))
 			return ERR_PTR(-EINVAL);
-
-		it = kzalloc(sizeof(*it), GFP_KERNEL);
-		if (!it)
-			return ERR_PTR(-ENOMEM);
-		of->priv = it;
 		css_task_iter_start(&cgrp->self, iter_flags, it);
+		ctx->procs.started = true;
 	} else if (!(*pos)) {
 		css_task_iter_end(it);
 		css_task_iter_start(&cgrp->self, iter_flags, it);
@@ -4838,9 +4859,9 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
 
 static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 					 struct cgroup *dst_cgrp,
-					 struct super_block *sb)
+					 struct super_block *sb,
+					 struct cgroup_namespace *ns)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *com_cgrp = src_cgrp;
 	int ret;
 
@@ -4869,11 +4890,12 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 
 static int cgroup_attach_permissions(struct cgroup *src_cgrp,
 				     struct cgroup *dst_cgrp,
-				     struct super_block *sb, bool threadgroup)
+				     struct super_block *sb, bool threadgroup,
+				     struct cgroup_namespace *ns)
 {
 	int ret = 0;
 
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb);
+	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns);
 	if (ret)
 		return ret;
 
@@ -4890,8 +4912,10 @@ static int cgroup_attach_permissions(struct cgroup *src_cgrp,
 static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 				    bool threadgroup)
 {
+	struct cgroup_file_ctx *ctx = of->priv;
 	struct cgroup *src_cgrp, *dst_cgrp;
 	struct task_struct *task;
+	const struct cred *saved_cred;
 	ssize_t ret;
 	bool locked;
 
@@ -4909,9 +4933,16 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
-	/* process and thread migrations follow same delegation rule */
+	/*
+	 * Process and thread migrations follow same delegation rule. Check
+	 * permissions using the credentials from file open to protect against
+	 * inherited fd attacks.
+	 */
+	saved_cred = override_creds(of->file->f_cred);
 	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
-					of->file->f_path.dentry->d_sb, threadgroup);
+					of->file->f_path.dentry->d_sb,
+					threadgroup, ctx->ns);
+	revert_creds(saved_cred);
 	if (ret)
 		goto out_finish;
 
@@ -6130,7 +6161,8 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 		goto err;
 
 	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
-					!(kargs->flags & CLONE_THREAD));
+					!(kargs->flags & CLONE_THREAD),
+					current->nsproxy->cgroup_ns);
 	if (ret)
 		goto err;
 
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index eb53f5ec62c9..256cf6db573c 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -6,6 +6,7 @@
 
 #include <linux/buildid.h>
 #include <linux/crash_core.h>
+#include <linux/init.h>
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
 
@@ -295,6 +296,16 @@ int __init parse_crashkernel_low(char *cmdline,
 				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
 }
 
+/*
+ * Add a dummy early_param handler to mark crashkernel= as a known command line
+ * parameter and suppress incorrect warnings in init/main.c.
+ */
+static int __init parse_crashkernel_dummy(char *arg)
+{
+	return 0;
+}
+early_param("crashkernel", parse_crashkernel_dummy);
+
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len)
 {
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e9db0c810554..21eccc961bba 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp)
 		}
 	}
 
+	if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+		return -E2BIG;
+
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0c6a48dfcecb..1f25a4d7de27 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock,
 		 *  - the VCPU on which owner runs is preempted
 		 */
 		if (!owner->on_cpu || need_resched() ||
-		    rt_mutex_waiter_is_top_waiter(lock, waiter) ||
+		    !rt_mutex_waiter_is_top_waiter(lock, waiter) ||
 		    vcpu_is_preempted(task_cpu(owner))) {
 			res = false;
 			break;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 76f9deeaa942..77563109c0ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq)
 		};
 	}
 
-	rq->uclamp_flags = 0;
+	rq->uclamp_flags = UCLAMP_FLAG_IDLE;
 }
 
 static void __init init_uclamp(void)
@@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str)
 	int mode = sched_dynamic_mode(str);
 	if (mode < 0) {
 		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-		return 1;
+		return 0;
 	}
 
 	sched_dynamic_update(mode);
-	return 0;
+	return 1;
 }
 __setup("preempt=", setup_preempt_mode);
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 872e481d5098..9392aea1804e 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
-	task_cputime(p, &cputime.utime, &cputime.stime);
+	if (task_cputime(p, &cputime.utime, &cputime.stime))
+		cputime.sum_exec_runtime = task_sched_runtime(p);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
 	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 delta;
+	int ret;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
 		*stime = t->stime;
-		return;
+		return false;
 	}
 
 	do {
+		ret = false;
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*utime = t->utime;
@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		if (vtime->state < VTIME_SYS)
 			continue;
 
+		ret = true;
 		delta = vtime_delta(vtime);
 
 		/*
@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		else
 			*utime += vtime->utime + delta;
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return ret;
 }
 
 static int vtime_state_fetch(struct vtime *vtime, int cpu)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 76577d1642a5..eca38107b32f 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	__wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+	/* POLLFREE must have cleared the queue. */
+	WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
 /*
  * Note: we use "set_current_state()" _after_ the wait-queue add,
  * because we need a memory barrier there on SMP, so that any
diff --git a/kernel/signal.c b/kernel/signal.c
index a629b11bf3e0..dfcee3888b00 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4185,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
 				ss_mode != 0))
 			return -EINVAL;
 
+		/*
+		 * Return before taking any locks if no actual
+		 * sigaltstack changes were requested.
+		 */
+		if (t->sas_ss_sp == (unsigned long)ss_sp &&
+		    t->sas_ss_size == ss_size &&
+		    t->sas_ss_flags == ss_flags)
+			return 0;
+
 		sigaltstack_lock();
 		if (ss_mode == SS_DISABLE) {
 			ss_size = 0;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 322b65d45676..41f470929e99 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -595,7 +595,8 @@ void irq_enter_rcu(void)
 {
 	__irq_enter_raw();
 
-	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
+	if (tick_nohz_full_cpu(smp_processor_id()) ||
+	    (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
 		tick_irq_enter();
 
 	account_hardirq_enter(current);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6bffe5af8cb1..17a283ce2b20 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void)
 	now = ktime_get();
 	if (ts->idle_active)
 		tick_nohz_stop_idle(ts, now);
+	/*
+	 * If all CPUs are idle. We may need to update a stale jiffies value.
+	 * Note nohz_full is a special case: a timekeeper is guaranteed to stay
+	 * alive but it might be busy looping with interrupts disabled in some
+	 * rare case (typically stop machine). So we must make sure we have a
+	 * last resort.
+	 */
 	if (ts->tick_stopped)
 		tick_nohz_update_jiffies(now);
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b348749a9fc6..dcdcb85121e4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts)
 	timekeeping_forward_now(tk);
 
 	xt = tk_xtime(tk);
-	ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
-	ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;
+	ts_delta = timespec64_sub(*ts, xt);
 
 	if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) {
 		ret = -EINVAL;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e3d2c23c413d..85f1021ad459 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs)
 EXPORT_SYMBOL(msleep_interruptible);
 
 /**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min:	Minimum time in usecs to sleep
+ * @max:	Maximum time in usecs to sleep
+ * @state:	State of the current task that will be while sleeping
  *
  * In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay().  The sleep improves responsiveness
+ * usleep_range_state() instead of udelay().  The sleep improves responsiveness
  * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
  * power usage by allowing hrtimers to take advantage of an already-
  * scheduled interrupt instead of scheduling a new one just for this sleep.
  */
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+				unsigned int state)
 {
 	ktime_t exp = ktime_add_us(ktime_get(), min);
 	u64 delta = (u64)(max - min) * NSEC_PER_USEC;
 
 	for (;;) {
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(state);
 		/* Do not return before the requested sleep time has elapsed */
 		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
 			break;
 	}
 }
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 30bc880c3849..be5f6b32a012 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 {
 	struct ftrace_direct_func *direct;
 	struct ftrace_func_entry *entry;
+	struct ftrace_hash *hash;
 	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
@@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 	if (!entry)
 		goto out_unlock;
 
-	if (direct_functions->count == 1)
+	hash = direct_ops.func_hash->filter_hash;
+	if (hash->count == 1)
 		unregister_ftrace_function(&direct_ops);
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
@@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	err = unregister_ftrace_function(ops);
 	remove_direct_functions_hash(hash, addr);
 	mutex_unlock(&direct_mutex);
+
+	/* cleanup for possible another register call */
+	ops->func = NULL;
+	ops->trampoline = 0;
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 88de94da596b..78ea542ce3bc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3207,7 +3207,7 @@ struct trace_buffer_struct {
 	char buffer[4][TRACE_BUF_SIZE];
 };
 
-static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct __percpu *trace_percpu_buffer;
 
 /*
  * This allows for lockless recording.  If we're nested too deeply, then
@@ -3217,7 +3217,7 @@ static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
 
-	if (!buffer || buffer->nesting >= 4)
+	if (!trace_percpu_buffer || buffer->nesting >= 4)
 		return NULL;
 
 	buffer->nesting++;
@@ -3236,7 +3236,7 @@ static void put_trace_buf(void)
 
 static int alloc_percpu_trace_buffer(void)
 {
-	struct trace_buffer_struct *buffers;
+	struct trace_buffer_struct __percpu *buffers;
 
 	if (trace_percpu_buffer)
 		return 0;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 9555b8e1d1e3..319f9c8ca7e7 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3757,7 +3757,7 @@ static int check_synth_field(struct synth_event *event,
 
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
-		    field->is_signed != hist_field->is_signed)
+		    (!field->is_string && field->is_signed != hist_field->is_signed))
 			return -EINVAL;
 	}
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 22db3ce95e74..ca9c13b2ecf4 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 						  argv + consumed, &consumed,
 						  &field_version);
 			if (IS_ERR(field)) {
-				argv_free(argv);
 				ret = PTR_ERR(field);
-				goto err;
+				goto err_free_arg;
 			}
 
 			/*
@@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			if (cmd_version > 1 && n_fields_this_loop >= 1) {
 				synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str));
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			fields[n_fields++] = field;
 			if (n_fields == SYNTH_FIELDS_MAX) {
 				synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			n_fields_this_loop++;
 		}
+		argv_free(argv);
 
 		if (consumed < argc) {
 			synth_err(SYNTH_ERR_INVALID_CMD, 0);
@@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			goto err;
 		}
 
-		argv_free(argv);
 	}
 
 	if (n_fields == 0) {
@@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 	kfree(saved_fields);
 
 	return ret;
+ err_free_arg:
+	argv_free(argv);
  err:
 	for (i = 0; i < n_fields; i++)
 		free_synth_field(fields[i]);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 39bb56d2dcbe..9628b5571846 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -15,6 +15,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/kmemleak.h>
 
 #include "tracing_map.h"
 #include "trace.h"
@@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a)
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
+		kmemleak_free(a->pages[i]);
 		free_page((unsigned long)a->pages[i]);
 	}
 
@@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 		a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!a->pages[i])
 			goto free;
+		kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL);
 	}
  out:
 	return a;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 4f5613dac227..7b32c356ebc5 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -264,15 +264,16 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
 {
 	struct ucounts *iter;
+	long max = LONG_MAX;
 	long ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long max = READ_ONCE(iter->ns->ucount_max[type]);
 		long new = atomic_long_add_return(v, &iter->ucount[type]);
 		if (new < 0 || new > max)
 			ret = LONG_MAX;
 		else if (iter == ucounts)
 			ret = new;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 	}
 	return ret;
 }
@@ -312,15 +313,16 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
 {
 	/* Caller must hold a reference to ucounts */
 	struct ucounts *iter;
+	long max = LONG_MAX;
 	long dec, ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long max = READ_ONCE(iter->ns->ucount_max[type]);
 		long new = atomic_long_add_return(1, &iter->ucount[type]);
 		if (new < 0 || new > max)
 			goto unwind;
 		if (iter == ucounts)
 			ret = new;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -339,15 +341,16 @@ unwind:
 	return 0;
 }
 
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
 {
 	struct ucounts *iter;
-	if (get_ucounts_value(ucounts, type) > max)
-		return true;
+	long max = rlimit;
+	if (rlimit > LONG_MAX)
+		max = LONG_MAX;
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		max = READ_ONCE(iter->ns->ucount_max[type]);
 		if (get_ucounts_value(iter, type) > max)
 			return true;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 	}
 	return false;
 }