summary refs log tree commit diff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c11
-rw-r--r--kernel/kcsan/debugfs.c3
-rw-r--r--kernel/locking/lockdep.c4
-rw-r--r--kernel/locking/mutex-debug.c4
-rw-r--r--kernel/locking/mutex-debug.h2
-rw-r--r--kernel/locking/mutex.c18
-rw-r--r--kernel/locking/mutex.h4
-rw-r--r--kernel/module.c17
-rw-r--r--kernel/signal.c59
-rw-r--r--kernel/watchdog.c34
10 files changed, 88 insertions, 68 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2e947a485898..6fee4a7e88d7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6389,8 +6389,6 @@ void perf_event_wakeup(struct perf_event *event)
 
 static void perf_sigtrap(struct perf_event *event)
 {
-	struct kernel_siginfo info;
-
 	/*
 	 * We'd expect this to only occur if the irq_work is delayed and either
 	 * ctx->task or current has changed in the meantime. This can be the
@@ -6405,13 +6403,8 @@ static void perf_sigtrap(struct perf_event *event)
 	if (current->flags & PF_EXITING)
 		return;
 
-	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_PERF;
-	info.si_errno = event->attr.type;
-	info.si_perf = event->attr.sig_data;
-	info.si_addr = (void __user *)event->pending_addr;
-	force_sig_info(&info);
+	force_sig_perf((void __user *)event->pending_addr,
+		       event->attr.type, event->attr.sig_data);
 }
 
 static void perf_pending_event_disable(struct perf_event *event)
diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c
index c1dd02f3be8b..e65de172ccf7 100644
--- a/kernel/kcsan/debugfs.c
+++ b/kernel/kcsan/debugfs.c
@@ -266,9 +266,10 @@ static const struct file_operations debugfs_ops =
 	.release = single_release
 };
 
-static void __init kcsan_debugfs_init(void)
+static int __init kcsan_debugfs_init(void)
 {
 	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
+	return 0;
 }
 
 late_initcall(kcsan_debugfs_init);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 48d736aa03b2..7641bd407239 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -5736,7 +5736,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_acquired(lock, ip);
+	trace_lock_contended(lock, ip);
 
 	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
@@ -5754,7 +5754,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_contended(lock, ip);
+	trace_lock_acquired(lock, ip);
 
 	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index a7276aaf2abc..db9301591e3f 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -57,7 +57,7 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 	task->blocked_on = waiter;
 }
 
-void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
@@ -65,7 +65,7 @@ void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
 	task->blocked_on = NULL;
 
-	list_del_init(&waiter->list);
+	INIT_LIST_HEAD(&waiter->list);
 	waiter->task = NULL;
 }
 
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 1edd3f45a4ec..53e631e1d76d 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -22,7 +22,7 @@ extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
 extern void debug_mutex_add_waiter(struct mutex *lock,
 				   struct mutex_waiter *waiter,
 				   struct task_struct *task);
-extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 				struct task_struct *task);
 extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index cb6b112ce155..013e1b08a1bf 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -194,7 +194,7 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
  * Add @waiter to a given location in the lock wait_list and set the
  * FLAG_WAITERS flag if it's the first waiter.
  */
-static void __sched
+static void
 __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 		   struct list_head *list)
 {
@@ -205,6 +205,16 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
 }
 
+static void
+__mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
+{
+	list_del(&waiter->list);
+	if (likely(list_empty(&lock->wait_list)))
+		__mutex_clear_flag(lock, MUTEX_FLAGS);
+
+	debug_mutex_remove_waiter(lock, waiter, current);
+}
+
 /*
  * Give up ownership to a specific task, when @task = NULL, this is equivalent
  * to a regular unlock. Sets PICKUP on a handoff, clears HANDOFF, preserves
@@ -1061,9 +1071,7 @@ acquired:
 			__ww_mutex_check_waiters(lock, ww_ctx);
 	}
 
-	mutex_remove_waiter(lock, &waiter, current);
-	if (likely(list_empty(&lock->wait_list)))
-		__mutex_clear_flag(lock, MUTEX_FLAGS);
+	__mutex_remove_waiter(lock, &waiter);
 
 	debug_mutex_free_waiter(&waiter);
 
@@ -1080,7 +1088,7 @@ skip_wait:
 
 err:
 	__set_current_state(TASK_RUNNING);
-	mutex_remove_waiter(lock, &waiter, current);
+	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
 	spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 1c2287d3fa71..f0c710b1d192 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -10,12 +10,10 @@
  * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs:
  */
 
-#define mutex_remove_waiter(lock, waiter, task) \
-		__list_del((waiter)->list.prev, (waiter)->list.next)
-
 #define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
 #define debug_mutex_free_waiter(waiter)			do { } while (0)
 #define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)
+#define debug_mutex_remove_waiter(lock, waiter, ti)     do { } while (0)
 #define debug_mutex_unlock(lock)			do { } while (0)
 #define debug_mutex_init(lock, name, key)		do { } while (0)
 
diff --git a/kernel/module.c b/kernel/module.c
index b5dd92e35b02..7e78dfabca97 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2401,6 +2401,15 @@ static long get_offset(struct module *mod, unsigned int *size,
 	return ret;
 }
 
+static bool module_init_layout_section(const char *sname)
+{
+#ifndef CONFIG_MODULE_UNLOAD
+	if (module_exit_section(sname))
+		return true;
+#endif
+	return module_init_section(sname);
+}
+
 /*
  * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld
  * might -- code, read-only data, read-write data, small data.  Tally
@@ -2435,7 +2444,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || module_init_section(sname))
+			    || module_init_layout_section(sname))
 				continue;
 			s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i);
 			pr_debug("\t%s\n", sname);
@@ -2468,7 +2477,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || !module_init_section(sname))
+			    || !module_init_layout_section(sname))
 				continue;
 			s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i)
 					 | INIT_OFFSET_MASK);
@@ -2807,11 +2816,7 @@ void * __weak module_alloc(unsigned long size)
 
 bool __weak module_init_section(const char *name)
 {
-#ifndef CONFIG_MODULE_UNLOAD
-	return strstarts(name, ".init") || module_exit_section(name);
-#else
 	return strstarts(name, ".init");
-#endif
 }
 
 bool __weak module_exit_section(const char *name)
diff --git a/kernel/signal.c b/kernel/signal.c
index 66e88649cf74..f7c6ffcbd044 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1236,6 +1236,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info)
 	case SIL_TIMER:
 	case SIL_POLL:
 	case SIL_FAULT:
+	case SIL_FAULT_TRAPNO:
 	case SIL_FAULT_MCEERR:
 	case SIL_FAULT_BNDERR:
 	case SIL_FAULT_PKUERR:
@@ -1804,6 +1805,21 @@ int force_sig_pkuerr(void __user *addr, u32 pkey)
 }
 #endif
 
+int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo     = SIGTRAP;
+	info.si_errno     = 0;
+	info.si_code      = TRAP_PERF;
+	info.si_addr      = addr;
+	info.si_perf_data = sig_data;
+	info.si_perf_type = type;
+
+	return force_sig_info(&info);
+}
+
 /* For the crazy architectures that include trap information in
  * the errno field, instead of an actual errno value.
  */
@@ -2564,6 +2580,7 @@ static void hide_si_addr_tag_bits(struct ksignal *ksig)
 {
 	switch (siginfo_layout(ksig->sig, ksig->info.si_code)) {
 	case SIL_FAULT:
+	case SIL_FAULT_TRAPNO:
 	case SIL_FAULT_MCEERR:
 	case SIL_FAULT_BNDERR:
 	case SIL_FAULT_PKUERR:
@@ -3251,6 +3268,10 @@ enum siginfo_layout siginfo_layout(unsigned sig, int si_code)
 #endif
 			else if ((sig == SIGTRAP) && (si_code == TRAP_PERF))
 				layout = SIL_PERF_EVENT;
+#ifdef __ARCH_SI_TRAPNO
+			else if (layout == SIL_FAULT)
+				layout = SIL_FAULT_TRAPNO;
+#endif
 		}
 		else if (si_code <= NSIGPOLL)
 			layout = SIL_POLL;
@@ -3354,35 +3375,28 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
 		break;
 	case SIL_FAULT:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
+		break;
+	case SIL_FAULT_TRAPNO:
+		to->si_addr = ptr_to_compat(from->si_addr);
 		to->si_trapno = from->si_trapno;
-#endif
 		break;
 	case SIL_FAULT_MCEERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_addr_lsb = from->si_addr_lsb;
 		break;
 	case SIL_FAULT_BNDERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_lower = ptr_to_compat(from->si_lower);
 		to->si_upper = ptr_to_compat(from->si_upper);
 		break;
 	case SIL_FAULT_PKUERR:
 		to->si_addr = ptr_to_compat(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_pkey = from->si_pkey;
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = ptr_to_compat(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid = from->si_pid;
@@ -3438,35 +3452,28 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
 		break;
 	case SIL_FAULT:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
+		break;
+	case SIL_FAULT_TRAPNO:
+		to->si_addr = compat_ptr(from->si_addr);
 		to->si_trapno = from->si_trapno;
-#endif
 		break;
 	case SIL_FAULT_MCEERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_addr_lsb = from->si_addr_lsb;
 		break;
 	case SIL_FAULT_BNDERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_lower = compat_ptr(from->si_lower);
 		to->si_upper = compat_ptr(from->si_upper);
 		break;
 	case SIL_FAULT_PKUERR:
 		to->si_addr = compat_ptr(from->si_addr);
-#ifdef __ARCH_SI_TRAPNO
-		to->si_trapno = from->si_trapno;
-#endif
 		to->si_pkey = from->si_pkey;
 		break;
 	case SIL_PERF_EVENT:
 		to->si_addr = compat_ptr(from->si_addr);
-		to->si_perf = from->si_perf;
+		to->si_perf_data = from->si_perf_data;
+		to->si_perf_type = from->si_perf_type;
 		break;
 	case SIL_CHLD:
 		to->si_pid    = from->si_pid;
@@ -4644,11 +4651,13 @@ static inline void siginfo_buildtime_checks(void)
 
 	/* sigfault */
 	CHECK_OFFSET(si_addr);
+	CHECK_OFFSET(si_trapno);
 	CHECK_OFFSET(si_addr_lsb);
 	CHECK_OFFSET(si_lower);
 	CHECK_OFFSET(si_upper);
 	CHECK_OFFSET(si_pkey);
-	CHECK_OFFSET(si_perf);
+	CHECK_OFFSET(si_perf_data);
+	CHECK_OFFSET(si_perf_type);
 
 	/* sigpoll */
 	CHECK_OFFSET(si_band);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7c397907d0e9..92d3bcc5a5e0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -302,10 +302,10 @@ void touch_softlockup_watchdog_sync(void)
 	__this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
 }
 
-static int is_softlockup(unsigned long touch_ts, unsigned long period_ts)
+static int is_softlockup(unsigned long touch_ts,
+			 unsigned long period_ts,
+			 unsigned long now)
 {
-	unsigned long now = get_timestamp();
-
 	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
 		/* Warn about unreasonable delays. */
 		if (time_after(now, period_ts + get_softlockup_thresh()))
@@ -353,8 +353,7 @@ static int softlockup_fn(void *data)
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
-	unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
-	unsigned long period_ts = __this_cpu_read(watchdog_report_ts);
+	unsigned long touch_ts, period_ts, now;
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
@@ -377,11 +376,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
 
 	/*
+	 * Read the current timestamp first. It might become invalid anytime
+	 * when a virtual machine is stopped by the host or when the watchog
+	 * is touched from NMI.
+	 */
+	now = get_timestamp();
+	/*
 	 * If a virtual machine is stopped by the host it can look to
-	 * the watchdog like a soft lockup. Check to see if the host
-	 * stopped the vm before we process the timestamps.
+	 * the watchdog like a soft lockup. This function touches the watchdog.
 	 */
 	kvm_check_and_clear_guest_paused();
+	/*
+	 * The stored timestamp is comparable with @now only when not touched.
+	 * It might get touched anytime from NMI. Make sure that is_softlockup()
+	 * uses the same (valid) value.
+	 */
+	period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts));
 
 	/* Reset the interval when touched by known problematic code. */
 	if (period_ts == SOFTLOCKUP_DELAY_REPORT) {
@@ -398,13 +408,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		return HRTIMER_RESTART;
 	}
 
-	/* check for a softlockup
-	 * This is done by making sure a high priority task is
-	 * being scheduled.  The task touches the watchdog to
-	 * indicate it is getting cpu time.  If it hasn't then
-	 * this is a good indication some task is hogging the cpu
-	 */
-	duration = is_softlockup(touch_ts, period_ts);
+	/* Check for a softlockup. */
+	touch_ts = __this_cpu_read(watchdog_touch_ts);
+	duration = is_softlockup(touch_ts, period_ts, now);
 	if (unlikely(duration)) {
 		/*
 		 * Prevent multiple soft-lockup reports if one cpu is already
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-06 16:23:43 +0000