[to-be-updated] mm-kmemleak-add-cond_resched-to-kmemleak_free_percpu.patch removed from -mm tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The quilt patch titled
     Subject: mm/kmemleak: add cond_resched() to kmemleak_free_percpu()
has been removed from the -mm tree.  Its filename was
     mm-kmemleak-add-cond_resched-to-kmemleak_free_percpu.patch

This patch was dropped because an updated version will be merged

------------------------------------------------------
From: Waiman Long <longman@xxxxxxxxxx>
Subject: mm/kmemleak: add cond_resched() to kmemleak_free_percpu()
Date: Mon, 27 Nov 2023 14:41:53 -0500

It was found that on systems with large number of CPUs, the following soft
lockup splat might sometimes happen:

[ 2656.001617] watchdog: BUG: soft lockup - CPU#364 stuck for 21s! [ksoftirqd/364:2206]
  :
[ 2656.141194] RIP: 0010:_raw_spin_unlock_irqrestore+0x3d/0x70
  :
 2656.241214] Call Trace:
[ 2656.243971]  <IRQ>
[ 2656.246237]  ? show_trace_log_lvl+0x1c4/0x2df
[ 2656.251152]  ? show_trace_log_lvl+0x1c4/0x2df
[ 2656.256066]  ? kmemleak_free_percpu+0x11f/0x1f0
[ 2656.261173]  ? watchdog_timer_fn+0x379/0x470
[ 2656.265984]  ? __pfx_watchdog_timer_fn+0x10/0x10
[ 2656.271179]  ? __hrtimer_run_queues+0x5f3/0xd00
[ 2656.276283]  ? __pfx___hrtimer_run_queues+0x10/0x10
[ 2656.281783]  ? ktime_get_update_offsets_now+0x95/0x2c0
[ 2656.287573]  ? ktime_get_update_offsets_now+0xdd/0x2c0
[ 2656.293380]  ? hrtimer_interrupt+0x2e9/0x780
[ 2656.298221]  ? __sysvec_apic_timer_interrupt+0x184/0x640
[ 2656.304211]  ? sysvec_apic_timer_interrupt+0x8e/0xc0
[ 2656.309807]  </IRQ>
[ 2656.312169]  <TASK>
[ 2656.326110]  kmemleak_free_percpu+0x11f/0x1f0
[ 2656.331015]  free_percpu.part.0+0x1b/0xe70
[ 2656.335635]  free_vfsmnt+0xb9/0x100
[ 2656.339567]  rcu_do_batch+0x3c8/0xe30
[ 2656.363693]  rcu_core+0x3de/0x5a0
[ 2656.367433]  __do_softirq+0x2d0/0x9a8
[ 2656.381119]  run_ksoftirqd+0x36/0x60
[ 2656.385145]  smpboot_thread_fn+0x556/0x910
[ 2656.394971]  kthread+0x2a4/0x350
[ 2656.402826]  ret_from_fork+0x29/0x50
[ 2656.406861]  </TASK>

Fix this by adding a cond_resched() call in the percpu freeing loop
and defer the freeing of percpu kmemleak objects to a workqueue if it
is being called from a non-task context.

Link: https://lkml.kernel.org/r/20231127194153.289626-1-longman@xxxxxxxxxx
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 mm/kmemleak.c |   59 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 52 insertions(+), 7 deletions(-)

--- a/mm/kmemleak.c~mm-kmemleak-add-cond_resched-to-kmemleak_free_percpu
+++ a/mm/kmemleak.c
@@ -168,6 +168,14 @@ struct kmemleak_object {
 	char comm[TASK_COMM_LEN];	/* executable name */
 };
 
+/*
+ * A percpu address to be submitted to a workqueue for being freed.
+ */
+struct kmemleak_percpu_addr {
+	struct work_struct work;
+	const void __percpu *ptr;
+};
+
 /* flag representing the memory block allocation status */
 #define OBJECT_ALLOCATED	(1 << 0)
 /* flag set after the first reporting of an unreference object */
@@ -1120,23 +1128,60 @@ void __ref kmemleak_free_part(const void
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
 
+static void __kmemleak_free_percpu(const void __percpu *ptr)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		delete_object_full((unsigned long)per_cpu_ptr(ptr, cpu));
+		if (in_task())
+			cond_resched();
+	}
+}
+
+/*
+ * Work function for deferred freeing of kmemleak objects associated with
+ * a freed percpu memory block.
+ */
+static void kmemleak_free_percpu_workfn(struct work_struct *work)
+{
+	struct kmemleak_percpu_addr *addr;
+
+	addr = container_of(work, struct kmemleak_percpu_addr, work);
+	__kmemleak_free_percpu(addr->ptr);
+	kfree(addr);
+}
+
 /**
  * kmemleak_free_percpu - unregister a previously registered __percpu object
  * @ptr:	__percpu pointer to beginning of the object
  *
  * This function is called from the kernel percpu allocator when an object
- * (memory block) is freed (free_percpu).
+ * (memory block) is freed (free_percpu). Since this function is inherently
+ * slow especially on systems with a large number of CPUs, defer the actual
+ * removal of kmemleak objects associated with the percpu pointer to a
+ * workqueue if it is not in a task context.
  */
 void __ref kmemleak_free_percpu(const void __percpu *ptr)
 {
-	unsigned int cpu;
-
 	pr_debug("%s(0x%px)\n", __func__, ptr);
 
-	if (kmemleak_free_enabled && ptr && !IS_ERR(ptr))
-		for_each_possible_cpu(cpu)
-			delete_object_full((unsigned long)per_cpu_ptr(ptr,
-								      cpu));
+	if (!kmemleak_free_enabled || !ptr || IS_ERR(ptr))
+		return;
+
+	if (!in_task()) {
+		struct kmemleak_percpu_addr *addr;
+
+		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
+		if (addr) {
+			INIT_WORK(&addr->work, kmemleak_free_percpu_workfn);
+			addr->ptr = ptr;
+			queue_work(system_long_wq, &addr->work);
+			return;
+		}
+		/* Fallback to do direct deletion */
+	}
+	__kmemleak_free_percpu(ptr);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
 
_

Patches currently in -mm which might be from longman@xxxxxxxxxx are





[Index of Archives]     [Kernel Archive]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux