Merge tag 'v5.16' into rdma.git for-next

To resolve minor conflict in:
        drivers/infiniband/hw/mlx5/mlx5_ib.h

By merging both hunks.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

11 files changed, 177 insertions, 83 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/verifier.c b/kernel/bpf/verifier.c
index f3001937bbb9..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
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/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/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/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/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/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;
 }