Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 206 insertions, 0 deletions

diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c
new file mode 100644
index 000000000..64212b39b
--- /dev/null
+++ b/security/apparmor/resource.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor resource mediation and attachment
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/audit.h>
+#include <linux/security.h>
+
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/resource.h"
+#include "include/policy.h"
+
+/*
+ * Table of rlimit names: we generate it from resource.h.
+ */
+#include "rlim_names.h"
+
+struct aa_sfs_entry aa_sfs_entry_rlimit[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_RLIMIT_MASK),
+	{ }
+};
+
+/* audit callback for resource specific fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	audit_log_format(ab, " rlimit=%s value=%lu",
+			 rlim_names[ad->rlim.rlim], ad->rlim.max);
+	if (ad->peer) {
+		audit_log_format(ab, " peer=");
+		aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+				FLAGS_NONE, GFP_ATOMIC);
+	}
+}
+
+/**
+ * audit_resource - audit setting resource limit
+ * @subj_cred: cred setting the resource
+ * @profile: profile being enforced  (NOT NULL)
+ * @resource: rlimit being auditing
+ * @value: value being set
+ * @peer: aa_albel of the task being set
+ * @info: info being auditing
+ * @error: error value
+ *
+ * Returns: 0 or ad->error else other error code on failure
+ */
+static int audit_resource(const struct cred *subj_cred,
+			  struct aa_profile *profile, unsigned int resource,
+			  unsigned long value, struct aa_label *peer,
+			  const char *info, int error)
+{
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_RLIMITS,
+			  OP_SETRLIMIT);
+
+	ad.subj_cred = subj_cred;
+	ad.rlim.rlim = resource;
+	ad.rlim.max = value;
+	ad.peer = peer;
+	ad.info = info;
+	ad.error = error;
+
+	return aa_audit(AUDIT_APPARMOR_AUTO, profile, &ad, audit_cb);
+}
+
+/**
+ * aa_map_resource - map compiled policy resource to internal #
+ * @resource: flattened policy resource number
+ *
+ * Returns: resource # for the current architecture.
+ *
+ * rlimit resource can vary based on architecture, map the compiled policy
+ * resource # to the internal representation for the architecture.
+ */
+int aa_map_resource(int resource)
+{
+	return rlim_map[resource];
+}
+
+static int profile_setrlimit(const struct cred *subj_cred,
+			     struct aa_profile *profile, unsigned int resource,
+			     struct rlimit *new_rlim)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	int e = 0;
+
+	if (rules->rlimits.mask & (1 << resource) && new_rlim->rlim_max >
+	    rules->rlimits.limits[resource].rlim_max)
+		e = -EACCES;
+	return audit_resource(subj_cred, profile, resource, new_rlim->rlim_max,
+			      NULL, NULL, e);
+}
+
+/**
+ * aa_task_setrlimit - test permission to set an rlimit
+ * @subj_cred: cred setting the limit
+ * @label: label confining the task  (NOT NULL)
+ * @task: task the resource is being set on
+ * @resource: the resource being set
+ * @new_rlim: the new resource limit  (NOT NULL)
+ *
+ * Control raising the processes hard limit.
+ *
+ * Returns: 0 or error code if setting resource failed
+ */
+int aa_task_setrlimit(const struct cred *subj_cred, struct aa_label *label,
+		      struct task_struct *task,
+		      unsigned int resource, struct rlimit *new_rlim)
+{
+	struct aa_profile *profile;
+	struct aa_label *peer;
+	int error = 0;
+
+	rcu_read_lock();
+	peer = aa_get_newest_cred_label(__task_cred(task));
+	rcu_read_unlock();
+
+	/* TODO: extend resource control to handle other (non current)
+	 * profiles.  AppArmor rules currently have the implicit assumption
+	 * that the task is setting the resource of a task confined with
+	 * the same profile or that the task setting the resource of another
+	 * task has CAP_SYS_RESOURCE.
+	 */
+
+	if (label != peer &&
+	    aa_capable(subj_cred, label, CAP_SYS_RESOURCE, CAP_OPT_NOAUDIT) != 0)
+		error = fn_for_each(label, profile,
+				audit_resource(subj_cred, profile, resource,
+					       new_rlim->rlim_max, peer,
+					       "cap_sys_resource", -EACCES));
+	else
+		error = fn_for_each_confined(label, profile,
+				profile_setrlimit(subj_cred, profile, resource,
+						  new_rlim));
+	aa_put_label(peer);
+
+	return error;
+}
+
+/**
+ * __aa_transition_rlimits - apply new profile rlimits
+ * @old_l: old label on task  (NOT NULL)
+ * @new_l: new label with rlimits to apply  (NOT NULL)
+ */
+void __aa_transition_rlimits(struct aa_label *old_l, struct aa_label *new_l)
+{
+	unsigned int mask = 0;
+	struct rlimit *rlim, *initrlim;
+	struct aa_profile *old, *new;
+	struct label_it i;
+
+	old = labels_profile(old_l);
+	new = labels_profile(new_l);
+
+	/* for any rlimits the profile controlled, reset the soft limit
+	 * to the lesser of the tasks hard limit and the init tasks soft limit
+	 */
+	label_for_each_confined(i, old_l, old) {
+		struct aa_ruleset *rules = old->label.rules[0];
+		if (rules->rlimits.mask) {
+			int j;
+
+			for (j = 0, mask = 1; j < RLIM_NLIMITS; j++,
+				     mask <<= 1) {
+				if (rules->rlimits.mask & mask) {
+					rlim = current->signal->rlim + j;
+					initrlim = init_task.signal->rlim + j;
+					rlim->rlim_cur = min(rlim->rlim_max,
+							    initrlim->rlim_cur);
+				}
+			}
+		}
+	}
+
+	/* set any new hard limits as dictated by the new profile */
+	label_for_each_confined(i, new_l, new) {
+		struct aa_ruleset *rules = new->label.rules[0];
+		int j;
+
+		if (!rules->rlimits.mask)
+			continue;
+		for (j = 0, mask = 1; j < RLIM_NLIMITS; j++, mask <<= 1) {
+			if (!(rules->rlimits.mask & mask))
+				continue;
+
+			rlim = current->signal->rlim + j;
+			rlim->rlim_max = min(rlim->rlim_max,
+					     rules->rlimits.limits[j].rlim_max);
+			/* soft limit should not exceed hard limit */
+			rlim->rlim_cur = min(rlim->rlim_cur, rlim->rlim_max);
+			if (j == RLIMIT_CPU &&
+			    rlim->rlim_cur != RLIM_INFINITY &&
+			    IS_ENABLED(CONFIG_POSIX_TIMERS))
+				(void) update_rlimit_cpu(current->group_leader,
+							 rlim->rlim_cur);
+		}
+	}
+}