tracing: Create a sparse bitmask for pid filtering

When the trace_pid_list was created, the default pid max was 32768.
Creating a bitmask that can hold one bit for all 32768 took up 4096 (one
page). Having a one page bitmask was not much of a problem, and that was
used for mapping pids. But today, systems are bigger and can run more
tasks, and now the default pid_max is usually set to 4194304. Which means
to handle that many pids requires 524288 bytes. Worse yet, the pid_max can
be set to 2^30 (1073741824 or 1G) which would take 134217728 (128M) of
memory to store this array.

Since the pid_list array is very sparsely populated, it is a huge waste of
memory to store all possible bits for each pid when most will not be set.

Instead, use a page table scheme to store the array, and allow this to
handle up to 30 bit pids.

The pid_mask will start out with 256 entries for the first 8 MSB bits.
This will cost 1K for 32 bit architectures and 2K for 64 bit. Each of
these will have a 256 array to store the next 8 bits of the pid (another
1 or 2K). These will hold an 2K byte bitmask (which will cover the LSB
14 bits or 16384 pids).

When the trace_pid_list is allocated, it will have the 1/2K upper bits
allocated, and then it will allocate a cache for the next upper chunks and
the lower chunks (default 6 of each). Then when a bit is "set", these
chunks will be pulled from the free list and added to the array. If the
free list gets down to a lever (default 2), it will trigger an irqwork
that will refill the cache back up.

On clearing a bit, if the clear causes the bitmask to be zero, that chunk
will then be placed back into the free cache for later use, keeping the
need to allocate more down to a minimum.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

1 files changed, 77 insertions, 2 deletions

diff --git a/kernel/trace/pid_list.h b/kernel/trace/pid_list.h
index 80d0ecfe1536..62e73f1ac85f 100644
--- a/kernel/trace/pid_list.h
+++ b/kernel/trace/pid_list.h
@@ -5,9 +5,84 @@
 #ifndef _TRACE_INTERNAL_PID_LIST_H
 #define _TRACE_INTERNAL_PID_LIST_H
 
+/*
+ * In order to keep track of what pids to trace, a tree is created much
+ * like page tables are used. This creates a sparse bit map, where
+ * the tree is filled in when needed. A PID is at most 30 bits (see
+ * linux/thread.h), and is broken up into 3 sections based on the bit map
+ * of the bits. The 8 MSB is the "upper1" section. The next 8 MSB is the
+ * "upper2" section and the 14 LSB is the "lower" section.
+ *
+ * A trace_pid_list structure holds the "upper1" section, in an
+ * array of 256 pointers (1 or 2K in size) to "upper_chunk" unions, where
+ * each has an array of 256 pointers (1 or 2K in size) to the "lower_chunk"
+ * structures, where each has an array of size 2K bytes representing a bitmask
+ * of the 14 LSB of the PID (256 * 8 = 2048)
+ *
+ * When a trace_pid_list is allocated, it includes the 256 pointer array
+ * of the upper1 unions. Then a "cache" of upper and lower is allocated
+ * where these will be assigned as needed.
+ *
+ * When a bit is set in the pid_list bitmask, the pid to use has
+ * the 8 MSB masked, and this is used to index the array in the
+ * pid_list to find the next upper union. If the element is NULL,
+ * then one is retrieved from the upper_list cache. If none is
+ * available, then -ENOMEM is returned.
+ *
+ * The next 8 MSB is used to index into the "upper2" section. If this
+ * element is NULL, then it is retrieved from the lower_list cache.
+ * Again, if one is not available -ENOMEM is returned.
+ *
+ * Finally the 14 LSB of the PID is used to set the bit in the 16384
+ * bitmask (made up of 2K bytes).
+ *
+ * When the second upper section or the lower section has their last
+ * bit cleared, they are added back to the free list to be reused
+ * when needed.
+ */
+
+#define UPPER_BITS	8
+#define UPPER_MAX	(1 << UPPER_BITS)
+#define UPPER1_SIZE	(1 << UPPER_BITS)
+#define UPPER2_SIZE	(1 << UPPER_BITS)
+
+#define LOWER_BITS	14
+#define LOWER_MAX	(1 << LOWER_BITS)
+#define LOWER_SIZE	(LOWER_MAX / BITS_PER_LONG)
+
+#define UPPER1_SHIFT	(LOWER_BITS + UPPER_BITS)
+#define UPPER2_SHIFT	LOWER_BITS
+#define LOWER_MASK	(LOWER_MAX - 1)
+
+#define UPPER_MASK	(UPPER_MAX - 1)
+
+/* According to linux/thread.h pids can not be bigger than or equal to 1 << 30 */
+#define MAX_PID		(1 << 30)
+
+/* Just keep 6 chunks of both upper and lower in the cache on alloc */
+#define CHUNK_ALLOC 6
+
+/* Have 2 chunks free, trigger a refill of the cache */
+#define CHUNK_REALLOC 2
+
+union lower_chunk {
+	union lower_chunk		*next;
+	unsigned long			data[LOWER_SIZE]; // 2K in size
+};
+
+union upper_chunk {
+	union upper_chunk		*next;
+	union lower_chunk		*data[UPPER2_SIZE]; // 1 or 2K in size
+};
+
 struct trace_pid_list {
-	int			pid_max;
-	unsigned long		*pids;
+	raw_spinlock_t			lock;
+	struct irq_work			refill_irqwork;
+	union upper_chunk		*upper[UPPER1_SIZE]; // 1 or 2K in size
+	union upper_chunk		*upper_list;
+	union lower_chunk		*lower_list;
+	int				free_upper_chunks;
+	int				free_lower_chunks;
 };
 
 #endif /* _TRACE_INTERNAL_PID_LIST_H */