tracing: kdb: Fix ftdump to not sleep

[mirror_ubuntu-bionic-kernel.git] / kernel / trace / ring_buffer.c

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ab18995ff1ebeea0e862f48b43f64924c87e127..69a09f0907ef232422b92670947329a22af0559f 100644 (file)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1136,6 +1136,11 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
        struct buffer_page *bpage, *tmp;
        long i;
 
+       /* Check if the available memory is there first */
+       i = si_mem_available();
+       if (i < nr_pages)
+               return -ENOMEM;
+
        for (i = 0; i < nr_pages; i++) {
                struct page *page;
                /*
@@ -1474,6 +1479,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
        tmp_iter_page = first_page;
 
        do {
+               cond_resched();
+
                to_remove_page = tmp_iter_page;
                rb_inc_page(cpu_buffer, &tmp_iter_page);
 
@@ -2534,29 +2541,58 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * The lock and unlock are done within a preempt disable section.
  * The current_context per_cpu variable can only be modified
  * by the current task between lock and unlock. But it can
- * be modified more than once via an interrupt. There are four
- * different contexts that we need to consider.
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
  *
- *  Normal context.
- *  SoftIRQ context
- *  IRQ context
- *  NMI context
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
  *
- * If for some reason the ring buffer starts to recurse, we
- * only allow that to happen at most 4 times (one for each
- * context). If it happens 5 times, then we consider this a
- * recusive loop and do not let it go further.
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
+ *
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
  */
 
 static __always_inline int
 trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-       if (cpu_buffer->current_context >= 4)
+       unsigned int val = cpu_buffer->current_context;
+       unsigned long pc = preempt_count();
+       int bit;
+
+       if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+               bit = RB_CTX_NORMAL;
+       else
+               bit = pc & NMI_MASK ? RB_CTX_NMI :
+                       pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
+
+       if (unlikely(val & (1 << bit)))
                return 1;
 
-       cpu_buffer->current_context++;
-       /* Interrupts must see this update */
-       barrier();
+       val |= (1 << bit);
+       cpu_buffer->current_context = val;
 
        return 0;
 }
@@ -2564,9 +2600,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 static __always_inline void
 trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-       /* Don't let the dec leak out */
-       barrier();
-       cpu_buffer->current_context--;
+       cpu_buffer->current_context &= cpu_buffer->current_context - 1;
 }
 
 /**
@@ -3068,6 +3102,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
        return !atomic_read(&buffer->record_disabled);
 }
 
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+       return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
 /**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.
@@ -3951,6 +4001,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
  * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
  * @buffer: The ring buffer to read from
  * @cpu: The cpu buffer to iterate over
+ * @flags: gfp flags to use for memory allocation
  *
  * This performs the initial preparations necessary to iterate
  * through the buffer.  Memory is allocated, buffer recording
@@ -3968,7 +4019,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
  * This overall must be paired with ring_buffer_read_finish.
  */
 struct ring_buffer_iter *
-ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags)
 {
        struct ring_buffer_per_cpu *cpu_buffer;
        struct ring_buffer_iter *iter;
@@ -3976,7 +4027,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                return NULL;
 
-       iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+       iter = kmalloc(sizeof(*iter), flags);
        if (!iter)
                return NULL;