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, 223 insertions, 0 deletions

diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c
new file mode 100644
index 000000000..2f3c6c843
--- /dev/null
+++ b/security/apparmor/capability.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor capability mediation functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/security.h>
+#include <linux/timekeeping.h>
+
+#include "include/apparmor.h"
+#include "include/capability.h"
+#include "include/cred.h"
+#include "include/policy.h"
+#include "include/audit.h"
+
+/*
+ * Table of capability names: we generate it from capabilities.h.
+ */
+#include "capability_names.h"
+
+struct aa_sfs_entry aa_sfs_entry_caps[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_CAPS_MASK),
+	AA_SFS_FILE_BOOLEAN("extended", 1),
+	{ }
+};
+
+struct audit_cache {
+	const struct cred *ad_subj_cred;
+	/* Capabilities go from 0 to CAP_LAST_CAP */
+	u64 ktime_ns_expiration[CAP_LAST_CAP+1];
+};
+
+static DEFINE_PER_CPU(struct audit_cache, audit_cache);
+
+/**
+ * audit_cb - call back for capability components of audit struct
+ * @ab: audit buffer   (NOT NULL)
+ * @va: audit struct to audit data from  (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+
+	audit_log_format(ab, " capname=");
+	audit_log_untrustedstring(ab, capability_names[sa->u.cap]);
+}
+
+/**
+ * audit_caps - audit a capability
+ * @ad: audit data
+ * @profile: profile being tested for confinement (NOT NULL)
+ * @cap: capability tested
+ * @error: error code returned by test
+ *
+ * Do auditing of capability and handle, audit/complain/kill modes switching
+ * and duplicate message elimination.
+ *
+ * Returns: 0 or ad->error on success,  error code on failure
+ */
+static int audit_caps(struct apparmor_audit_data *ad, struct aa_profile *profile,
+		      int cap, int error)
+{
+	const u64 AUDIT_CACHE_TIMEOUT_NS = 1000*1000*1000; /* 1 second */
+
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct audit_cache *ent;
+	int type = AUDIT_APPARMOR_AUTO;
+
+	ad->error = error;
+
+	if (likely(!error)) {
+		/* test if auditing is being forced */
+		if (likely((AUDIT_MODE(profile) != AUDIT_ALL) &&
+			   !cap_raised(rules->caps.audit, cap)))
+			return 0;
+		type = AUDIT_APPARMOR_AUDIT;
+	} else if (KILL_MODE(profile) ||
+		   cap_raised(rules->caps.kill, cap)) {
+		type = AUDIT_APPARMOR_KILL;
+	} else if (cap_raised(rules->caps.quiet, cap) &&
+		   AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		   AUDIT_MODE(profile) != AUDIT_ALL) {
+		/* quiet auditing */
+		return error;
+	}
+
+	/* Do simple duplicate message elimination */
+	ent = &get_cpu_var(audit_cache);
+	/* If the capability was never raised the timestamp check would also catch that */
+	if (ad->subj_cred == ent->ad_subj_cred && ktime_get_ns() <= ent->ktime_ns_expiration[cap]) {
+		put_cpu_var(audit_cache);
+		if (COMPLAIN_MODE(profile))
+			return complain_error(error);
+		return error;
+	} else {
+		put_cred(ent->ad_subj_cred);
+		ent->ad_subj_cred = get_cred(ad->subj_cred);
+		ent->ktime_ns_expiration[cap] = ktime_get_ns() + AUDIT_CACHE_TIMEOUT_NS;
+	}
+	put_cpu_var(audit_cache);
+
+	return aa_audit(type, profile, ad, audit_cb);
+}
+
+/**
+ * profile_capable - test if profile allows use of capability @cap
+ * @profile: profile being enforced    (NOT NULL, NOT unconfined)
+ * @cap: capability to test if allowed
+ * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated
+ * @ad: audit data (NOT NULL)
+ *
+ * Returns: 0 if allowed else -EPERM
+ */
+static int profile_capable(struct aa_profile *profile, int cap,
+			   unsigned int opts, struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state;
+	int error;
+
+	state = RULE_MEDIATES(rules, ad->class);
+	if (state) {
+		struct aa_perms perms = { };
+		u32 request;
+
+		/* caps broken into 256 x 32 bit permission chunks */
+		state = aa_dfa_next(rules->policy->dfa, state, cap >> 5);
+		request = 1 << (cap & 0x1f);
+		perms = *aa_lookup_perms(rules->policy, state);
+		aa_apply_modes_to_perms(profile, &perms);
+
+		if (opts & CAP_OPT_NOAUDIT) {
+			if (perms.complain & request)
+				ad->info = "optional: no audit";
+			else
+				ad = NULL;
+		}
+		return aa_check_perms(profile, &perms, request, ad,
+				      audit_cb);
+	}
+
+	/* fallback to old caps mediation that doesn't support conditionals */
+	if (cap_raised(rules->caps.allow, cap) &&
+	    !cap_raised(rules->caps.denied, cap))
+		error = 0;
+	else
+		error = -EPERM;
+
+	if (opts & CAP_OPT_NOAUDIT) {
+		if (!COMPLAIN_MODE(profile))
+			return error;
+		/* audit the cap request in complain mode but note that it
+		 * should be optional.
+		 */
+		ad->info = "optional: no audit";
+	}
+
+	return audit_caps(ad, profile, cap, error);
+}
+
+/**
+ * aa_capable - test permission to use capability
+ * @subj_cred: cred we are testing capability against
+ * @label: label being tested for capability (NOT NULL)
+ * @cap: capability to be tested
+ * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated
+ *
+ * Look up capability in profile capability set.
+ *
+ * Returns: 0 on success, or else an error code.
+ */
+int aa_capable(const struct cred *subj_cred, struct aa_label *label,
+	       int cap, unsigned int opts)
+{
+	struct aa_profile *profile;
+	int error = 0;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_CAP, AA_CLASS_CAP, OP_CAPABLE);
+
+	ad.subj_cred = subj_cred;
+	ad.common.u.cap = cap;
+	error = fn_for_each_confined(label, profile,
+			profile_capable(profile, cap, opts, &ad));
+
+	return error;
+}
+
+kernel_cap_t aa_profile_capget(const struct aa_profile *profile)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state;
+
+	state = RULE_MEDIATES(rules, AA_CLASS_CAP);
+	if (state) {
+		kernel_cap_t caps = CAP_EMPTY_SET;
+		int i;
+
+		/* caps broken into up to 256, 32 bit permission chunks */
+		for (i = 0; i < (CAP_LAST_CAP >> 5); i++) {
+			struct aa_perms perms = { };
+			aa_state_t tmp;
+
+			tmp = aa_dfa_next(rules->policy->dfa, state, i);
+			perms = *aa_lookup_perms(rules->policy, tmp);
+			aa_apply_modes_to_perms(profile, &perms);
+			caps.val |= ((u64)(perms.allow)) << (i * 5);
+			caps.val |= ((u64)(perms.complain)) << (i * 5);
+		}
+		return caps;
+	}
+
+	/* fallback to old caps */
+	if (COMPLAIN_MODE(profile))
+		return CAP_FULL_SET;
+
+	return rules->caps.allow;
+}