[PATCH v11 08/28] tracing: Add lock-free tracing_map

[Tom Zanussi]

Add tracing_map, a special-purpose lock-free map for tracing.

tracing_map is designed to aggregate or 'sum' one or more values
associated with a specific object of type tracing_map_elt, which
is associated by the map to a given key.

It provides various hooks allowing per-tracer customization and is
separated out into a separate file in order to allow it to be shared
between multiple tracers, but isn't meant to be generally used outside
of that context.

The tracing_map implementation was inspired by lock-free map
algorithms originated by Dr. Cliff Click:

 http://www.azulsystems.com/blog/cliff/2007-03-26-non-blocking-hashtable
 http://www.azulsystems.com/events/javaone_2007/2007_LockFreeHash.pdf

Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
---
 kernel/trace/Kconfig       |   13 +
 kernel/trace/Makefile      |    1 +
 kernel/trace/tracing_map.c | 1005 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/tracing_map.h |  277 ++++++++++++
 4 files changed, 1296 insertions(+)
 create mode 100644 kernel/trace/tracing_map.c
 create mode 100644 kernel/trace/tracing_map.h

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8d6363f..0c61e98 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -528,6 +528,19 @@ config MMIOTRACE
 	  See Documentation/trace/mmiotrace.txt.
 	  If you are not helping to develop drivers, say N.
 
+config TRACING_MAP
+	bool
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	default n
+	help
+	  tracing_map is a special-purpose lock-free map for tracing,
+	  separated out as a stand-alone facility in order to allow it
+	  to be shared between multiple tracers.  It isn't meant to be
+	  generally used outside of that context, and is normally
+	  selected by tracers that use it.
+
+	  If in doubt, say N.
+
 config MMIOTRACE_TEST
 	tristate "Test module for mmiotrace"
 	depends on MMIOTRACE && m
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 9b1044e..4255c40 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_seq.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
new file mode 100644
index 0000000..c67ef12
--- /dev/null
+++ b/kernel/trace/tracing_map.c
@@ -0,0 +1,1005 @@
+/*
+ * tracing_map - lock-free map for tracing
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
+ *
+ * tracing_map implementation inspired by lock-free map algorithms
+ * originated by Dr. Cliff Click:
+ *
+ * http://www.azulsystems.com/blog/cliff/2007-03-26-non-blocking-hashtable
+ * http://www.azulsystems.com/events/javaone_2007/2007_LockFreeHash.pdf
+ */
+
+#include <linux/vmalloc.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+
+#include "tracing_map.h"
+#include "trace.h"
+
+/*
+ * NOTE: For a detailed description of the data structures used by
+ * these functions (such as tracing_map_elt) please see the overview
+ * of tracing_map data structures at the beginning of tracing_map.h.
+ */
+
+/**
+ * tracing_map_update_sum - Add a value to a tracing_map_elt's sum field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given sum associated with the tracing_map_elt
+ * @n: The value to add to the sum
+ *
+ * Add n to sum i associated with the specified tracing_map_elt
+ * instance.  The index i is the index returned by the call to
+ * tracing_map_add_sum_field() when the tracing map was set up.
+ */
+void tracing_map_update_sum(struct tracing_map_elt *elt, unsigned int i, u64 n)
+{
+	atomic64_add(n, &elt->fields[i].sum);
+}
+
+/**
+ * tracing_map_read_sum - Return the value of a tracing_map_elt's sum field
+ * @elt: The tracing_map_elt
+ * @i: The index of the given sum associated with the tracing_map_elt
+ *
+ * Retrieve the value of the sum i associated with the specified
+ * tracing_map_elt instance.  The index i is the index returned by the
+ * call to tracing_map_add_sum_field() when the tracing map was set
+ * up.
+ *
+ * Return: The sum associated with field i for elt.
+ */
+u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i)
+{
+	return (u64)atomic64_read(&elt->fields[i].sum);
+}
+
+int tracing_map_cmp_string(void *val_a, void *val_b)
+{
+	char *a = val_a;
+	char *b = val_b;
+
+	return strcmp(a, b);
+}
+
+int tracing_map_cmp_none(void *val_a, void *val_b)
+{
+	return 0;
+}
+
+static int tracing_map_cmp_atomic64(void *val_a, void *val_b)
+{
+	u64 a = atomic64_read((atomic64_t *)val_a);
+	u64 b = atomic64_read((atomic64_t *)val_b);
+
+	return (a > b) ? 1 : ((a < b) ? -1 : 0);
+}
+
+#define DEFINE_TRACING_MAP_CMP_FN(type)					\
+static int tracing_map_cmp_##type(void *val_a, void *val_b)		\
+{									\
+	type a = *(type *)val_a;					\
+	type b = *(type *)val_b;					\
+									\
+	return (a > b) ? 1 : ((a < b) ? -1 : 0);			\
+}
+
+DEFINE_TRACING_MAP_CMP_FN(s64);
+DEFINE_TRACING_MAP_CMP_FN(u64);
+DEFINE_TRACING_MAP_CMP_FN(s32);
+DEFINE_TRACING_MAP_CMP_FN(u32);
+DEFINE_TRACING_MAP_CMP_FN(s16);
+DEFINE_TRACING_MAP_CMP_FN(u16);
+DEFINE_TRACING_MAP_CMP_FN(s8);
+DEFINE_TRACING_MAP_CMP_FN(u8);
+
+tracing_map_cmp_fn_t tracing_map_cmp_num(int field_size,
+					 int field_is_signed)
+{
+	tracing_map_cmp_fn_t fn = tracing_map_cmp_none;
+
+	switch (field_size) {
+	case 8:
+		if (field_is_signed)
+			fn = tracing_map_cmp_s64;
+		else
+			fn = tracing_map_cmp_u64;
+		break;
+	case 4:
+		if (field_is_signed)
+			fn = tracing_map_cmp_s32;
+		else
+			fn = tracing_map_cmp_u32;
+		break;
+	case 2:
+		if (field_is_signed)
+			fn = tracing_map_cmp_s16;
+		else
+			fn = tracing_map_cmp_u16;
+		break;
+	case 1:
+		if (field_is_signed)
+			fn = tracing_map_cmp_s8;
+		else
+			fn = tracing_map_cmp_u8;
+		break;
+	}
+
+	return fn;
+}
+
+static int tracing_map_add_field(struct tracing_map *map,
+				 tracing_map_cmp_fn_t cmp_fn)
+{
+	int ret = -EINVAL;
+
+	if (map->n_fields < TRACING_MAP_FIELDS_MAX) {
+		ret = map->n_fields;
+		map->fields[map->n_fields++].cmp_fn = cmp_fn;
+	}
+
+	return ret;
+}
+
+/**
+ * tracing_map_add_sum_field - Add a field describing a tracing_map sum
+ * @map: The tracing_map
+ *
+ * Add a sum field to the key and return the index identifying it in
+ * the map and associated tracing_map_elts.  This is the index used
+ * for instance to update a sum for a particular tracing_map_elt using
+ * tracing_map_update_sum() or reading it via tracing_map_read_sum().
+ *
+ * Return: The index identifying the field in the map and associated
+ * tracing_map_elts.
+ */
+int tracing_map_add_sum_field(struct tracing_map *map)
+{
+	return tracing_map_add_field(map, tracing_map_cmp_atomic64);
+}
+
+/**
+ * tracing_map_add_key_field - Add a field describing a tracing_map key
+ * @map: The tracing_map
+ * @offset: The offset within the key
+ * @cmp_fn: The comparison function that will be used to sort on the key
+ *
+ * Let the map know there is a key and that if it's used as a sort key
+ * to use cmp_fn.
+ *
+ * A key can be a subset of a compound key; for that purpose, the
+ * offset param is used to describe where within the the compound key
+ * the key referenced by this key field resides.
+ *
+ * Return: The index identifying the field in the map and associated
+ * tracing_map_elts.
+ */
+int tracing_map_add_key_field(struct tracing_map *map,
+			      unsigned int offset,
+			      tracing_map_cmp_fn_t cmp_fn)
+
+{
+	int idx = tracing_map_add_field(map, cmp_fn);
+
+	if (idx < 0)
+		return idx;
+
+	map->fields[idx].offset = offset;
+
+	map->key_idx[map->n_keys++] = idx;
+
+	return idx;
+}
+
+void tracing_map_array_clear(struct tracing_map_array *a)
+{
+	unsigned int i;
+
+	if (!a->pages)
+		return;
+
+	for (i = 0; i < a->n_pages; i++)
+		memset(a->pages[i], 0, PAGE_SIZE);
+}
+
+void tracing_map_array_free(struct tracing_map_array *a)
+{
+	unsigned int i;
+
+	if (!a->pages)
+		return;
+
+	for (i = 0; i < a->n_pages; i++)
+		free_page((unsigned long)a->pages[i]);
+
+	kfree(a);
+}
+
+struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
+						  unsigned int entry_size)
+{
+	struct tracing_map_array *a;
+	unsigned int i;
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a)
+		return NULL;
+
+	a->entry_size_shift = fls(roundup_pow_of_two(entry_size) - 1);
+	a->entries_per_page = PAGE_SIZE / (1 << a->entry_size_shift);
+	a->n_pages = n_elts / a->entries_per_page;
+	if (!a->n_pages)
+		a->n_pages = 1;
+	a->entry_shift = fls(a->entries_per_page) - 1;
+	a->entry_mask = (1 << a->entry_shift) - 1;
+
+	a->pages = kcalloc(a->n_pages, sizeof(void *), GFP_KERNEL);
+	if (!a->pages)
+		goto free;
+
+	for (i = 0; i < a->n_pages; i++) {
+		a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!a->pages)
+			goto free;
+	}
+ out:
+	return a;
+ free:
+	tracing_map_array_free(a);
+	a = NULL;
+
+	goto out;
+}
+
+static void tracing_map_elt_clear(struct tracing_map_elt *elt)
+{
+	unsigned i;
+
+	for (i = 0; i < elt->map->n_fields; i++)
+		if (elt->fields[i].cmp_fn == tracing_map_cmp_atomic64)
+			atomic64_set(&elt->fields[i].sum, 0);
+
+	if (elt->map->ops && elt->map->ops->elt_clear)
+		elt->map->ops->elt_clear(elt);
+}
+
+static void tracing_map_elt_init_fields(struct tracing_map_elt *elt)
+{
+	unsigned int i;
+
+	tracing_map_elt_clear(elt);
+
+	for (i = 0; i < elt->map->n_fields; i++) {
+		elt->fields[i].cmp_fn = elt->map->fields[i].cmp_fn;
+
+		if (elt->fields[i].cmp_fn != tracing_map_cmp_atomic64)
+			elt->fields[i].offset = elt->map->fields[i].offset;
+	}
+}
+
+static void tracing_map_elt_free(struct tracing_map_elt *elt)
+{
+	if (!elt)
+		return;
+
+	if (elt->map->ops && elt->map->ops->elt_free)
+		elt->map->ops->elt_free(elt);
+	kfree(elt->fields);
+	kfree(elt->key);
+	kfree(elt);
+}
+
+static struct tracing_map_elt *tracing_map_elt_alloc(struct tracing_map *map)
+{
+	struct tracing_map_elt *elt;
+	int err = 0;
+
+	elt = kzalloc(sizeof(*elt), GFP_KERNEL);
+	if (!elt)
+		return ERR_PTR(-ENOMEM);
+
+	elt->map = map;
+
+	elt->key = kzalloc(map->key_size, GFP_KERNEL);
+	if (!elt->key) {
+		err = -ENOMEM;
+		goto free;
+	}
+
+	elt->fields = kcalloc(map->n_fields, sizeof(*elt->fields), GFP_KERNEL);
+	if (!elt->fields) {
+		err = -ENOMEM;
+		goto free;
+	}
+
+	tracing_map_elt_init_fields(elt);
+
+	if (map->ops && map->ops->elt_alloc) {
+		err = map->ops->elt_alloc(elt);
+		if (err)
+			goto free;
+	}
+	return elt;
+ free:
+	tracing_map_elt_free(elt);
+
+	return ERR_PTR(err);
+}
+
+static struct tracing_map_elt *get_free_elt(struct tracing_map *map)
+{
+	struct tracing_map_elt *elt = NULL;
+	int idx;
+
+	idx = atomic_inc_return(&map->next_elt);
+	if (idx < map->max_elts) {
+		elt = *(TRACING_MAP_ELT(map->elts, idx));
+		if (map->ops && map->ops->elt_init)
+			map->ops->elt_init(elt);
+	}
+
+	return elt;
+}
+
+static void tracing_map_free_elts(struct tracing_map *map)
+{
+	unsigned int i;
+
+	if (!map->elts)
+		return;
+
+	for (i = 0; i < map->max_elts; i++)
+		tracing_map_elt_free(*(TRACING_MAP_ELT(map->elts, i)));
+
+	tracing_map_array_free(map->elts);
+}
+
+static int tracing_map_alloc_elts(struct tracing_map *map)
+{
+	unsigned int i;
+
+	map->elts = tracing_map_array_alloc(map->max_elts,
+					    sizeof(struct tracing_map_elt *));
+	if (!map->elts)
+		return -ENOMEM;
+
+	for (i = 0; i < map->max_elts; i++) {
+		*(TRACING_MAP_ELT(map->elts, i)) = tracing_map_elt_alloc(map);
+		if (!(*(TRACING_MAP_ELT(map->elts, i)))) {
+			tracing_map_free_elts(map);
+
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static inline bool keys_match(void *key, void *test_key, unsigned key_size)
+{
+	bool match = true;
+
+	if (memcmp(key, test_key, key_size))
+		match = false;
+
+	return match;
+}
+
+/**
+ * tracing_map_insert - Insert key and/or retrieve val from a tracing_map
+ * @map: The tracing_map to insert into
+ * @key: The key to insert
+ *
+ * Inserts a key into a tracing_map and creates and returns a new
+ * tracing_map_elt for it, or if the key has already been inserted by
+ * a previous call, returns the tracing_map_elt already associated
+ * with it.  When the map was created, the number of elements to be
+ * allocated for the map was specified (internally maintained as
+ * 'max_elts' in struct tracing_map), and that number of
+ * tracing_map_elts was created by tracing_map_init().  This is the
+ * pre-allocated pool of tracing_map_elts that tracing_map_insert()
+ * will allocate from when adding new keys.  Once that pool is
+ * exhausted, tracing_map_insert() is useless and will return NULL to
+ * signal that state.
+ *
+ * This is a lock-free tracing map insertion function implementing a
+ * modified form of Cliff Click's basic insertion algorithm.  It
+ * requires the table size be a power of two.  To prevent any
+ * possibility of an infinite loop we always make the internal table
+ * size double the size of the requested table size (max_elts * 2).
+ * Likewise, we never reuse a slot or resize or delete elements - when
+ * we've reached max_elts entries, we simply return NULL once we've
+ * run out of entries.  Readers can at any point in time traverse the
+ * tracing map and safely access the key/val pairs.
+ *
+ * Return: the tracing_map_elt pointer val associated with the key.
+ * If this was a newly inserted key, the val will be a newly allocated
+ * and associated tracing_map_elt pointer val.  If the key wasn't
+ * found and the pool of tracing_map_elts has been exhausted, NULL is
+ * returned and no further insertions will succeed.
+ */
+struct tracing_map_elt *tracing_map_insert(struct tracing_map *map, void *key)
+{
+	u32 idx, key_hash, test_key;
+	struct tracing_map_entry *entry;
+
+	key_hash = jhash(key, map->key_size, 0);
+	if (key_hash == 0)
+		key_hash = 1;
+	idx = key_hash >> (32 - (map->map_bits + 1));
+
+	while (1) {
+		idx &= (map->map_size - 1);
+		entry = TRACING_MAP_ENTRY(map->map, idx);
+		test_key = entry->key;
+
+		if (test_key && test_key == key_hash && entry->val &&
+		    keys_match(key, entry->val->key, map->key_size))
+			return entry->val;
+
+		if (!test_key && !cmpxchg(&entry->key, 0, key_hash)) {
+			struct tracing_map_elt *elt;
+
+			elt = get_free_elt(map);
+			if (!elt)
+				break;
+			memcpy(elt->key, key, map->key_size);
+			entry->val = elt;
+
+			return entry->val;
+		}
+		idx++;
+	}
+
+	return NULL;
+}
+
+/**
+ * tracing_map_destroy - Destroy a tracing_map
+ * @map: The tracing_map to destroy
+ *
+ * Frees a tracing_map along with its associated array of
+ * tracing_map_elts.
+ *
+ * Callers should make sure there are no readers or writers actively
+ * reading or inserting into the map before calling this.
+ */
+void tracing_map_destroy(struct tracing_map *map)
+{
+	if (!map)
+		return;
+
+	tracing_map_free_elts(map);
+
+	tracing_map_array_free(map->map);
+	kfree(map);
+}
+
+/**
+ * tracing_map_clear - Clear a tracing_map
+ * @map: The tracing_map to clear
+ *
+ * Resets the tracing map to a cleared or initial state.  The
+ * tracing_map_elts are all cleared, and the array of struct
+ * tracing_map_entry is reset to an initialized state.
+ *
+ * Callers should make sure there are no writers actively inserting
+ * into the map before calling this.
+ */
+void tracing_map_clear(struct tracing_map *map)
+{
+	unsigned int i;
+
+	atomic_set(&map->next_elt, -1);
+
+	tracing_map_array_clear(map->map);
+
+	for (i = 0; i < map->max_elts; i++)
+		tracing_map_elt_clear(*(TRACING_MAP_ELT(map->elts, i)));
+}
+
+static void set_sort_key(struct tracing_map *map,
+			 struct tracing_map_sort_key *sort_key)
+{
+	map->sort_key = *sort_key;
+}
+
+/**
+ * tracing_map_create - Create a lock-free map and element pool
+ * @map_bits: The size of the map (2 ** map_bits)
+ * @key_size: The size of the key for the map in bytes
+ * @ops: Optional client-defined tracing_map_ops instance
+ * @private_data: Client data associated with the map
+ *
+ * Creates and sets up a map to contain 2 ** map_bits number of
+ * elements (internally maintained as 'max_elts' in struct
+ * tracing_map).  Before using, map fields should be added to the map
+ * with tracing_map_add_sum_field() and tracing_map_add_key_field().
+ * tracing_map_init() should then be called to allocate the array of
+ * tracing_map_elts, in order to avoid allocating anything in the map
+ * insertion path.  The user-specified map size reflects the maximum
+ * number of elements that can be contained in the table requested by
+ * the user - internally we double that in order to keep the table
+ * sparse and keep collisions manageable.
+ *
+ * A tracing_map is a special-purpose map designed to aggregate or
+ * 'sum' one or more values associated with a specific object of type
+ * tracing_map_elt, which is attached by the map to a given key.
+ *
+ * tracing_map_create() sets up the map itself, and provides
+ * operations for inserting tracing_map_elts, but doesn't allocate the
+ * tracing_map_elts themselves, or provide a means for describing the
+ * keys or sums associated with the tracing_map_elts.  All
+ * tracing_map_elts for a given map have the same set of sums and
+ * keys, which are defined by the client using the functions
+ * tracing_map_add_key_field() and tracing_map_add_sum_field().  Once
+ * the fields are defined, the pool of elements allocated for the map
+ * can be created, which occurs when the client code calls
+ * tracing_map_init().
+ *
+ * When tracing_map_init() returns, tracing_map_elt elements can be
+ * inserted into the map using tracing_map_insert().  When called,
+ * tracing_map_insert() grabs a free tracing_map_elt from the pool, or
+ * finds an existing match in the map and in either case returns it.
+ * The client can then use tracing_map_update_sum() and
+ * tracing_map_read_sum() to update or read a given sum field for the
+ * tracing_map_elt.
+ *
+ * The client can at any point retrieve and traverse the current set
+ * of inserted tracing_map_elts in a tracing_map, via
+ * tracing_map_sort_entries().  Sorting can be done on any field,
+ * including keys.
+ *
+ * See tracing_map.h for a description of tracing_map_ops.
+ *
+ * Return: the tracing_map pointer if successful, ERR_PTR if not.
+ */
+struct tracing_map *tracing_map_create(unsigned int map_bits,
+				       unsigned int key_size,
+				       struct tracing_map_ops *ops,
+				       void *private_data)
+{
+	struct tracing_map *map;
+	unsigned int i;
+
+	if (map_bits < TRACING_MAP_BITS_MIN ||
+	    map_bits > TRACING_MAP_BITS_MAX)
+		return ERR_PTR(-EINVAL);
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->map_bits = map_bits;
+	map->max_elts = (1 << map_bits);
+	atomic_set(&map->next_elt, -1);
+
+	map->map_size = (1 << (map_bits + 1));
+	map->ops = ops;
+
+	map->private_data = private_data;
+
+	map->map = tracing_map_array_alloc(map->map_size,
+					   sizeof(struct tracing_map_entry));
+	if (!map->map)
+		goto free;
+
+	map->key_size = key_size;
+	for (i = 0; i < TRACING_MAP_KEYS_MAX; i++)
+		map->key_idx[i] = -1;
+ out:
+	return map;
+ free:
+	tracing_map_destroy(map);
+	map = ERR_PTR(-ENOMEM);
+
+	goto out;
+}
+
+/**
+ * tracing_map_init - Allocate and clear a map's tracing_map_elts
+ * @map: The tracing_map to initialize
+ *
+ * Allocates a clears a pool of tracing_map_elts equal to the
+ * user-specified size of 2 ** map_bits (internally maintained as
+ * 'max_elts' in struct tracing_map).  Before using, the map fields
+ * should be added to the map with tracing_map_add_sum_field() and
+ * tracing_map_add_key_field().  tracing_map_init() should then be
+ * called to allocate the array of tracing_map_elts, in order to avoid
+ * allocating anything in the map insertion path.  The user-specified
+ * map size reflects the max number of elements requested by the user
+ * - internally we double that in order to keep the table sparse and
+ * keep collisions manageable.
+ *
+ * See tracing_map.h for a description of tracing_map_ops.
+ *
+ * Return: the tracing_map pointer if successful, ERR_PTR if not.
+ */
+int tracing_map_init(struct tracing_map *map)
+{
+	int err;
+
+	if (map->n_fields < 2)
+		return -EINVAL; /* need at least 1 key and 1 val */
+
+	err = tracing_map_alloc_elts(map);
+	if (err)
+		return err;
+
+	tracing_map_clear(map);
+
+	return err;
+}
+
+static int cmp_entries_dup(const struct tracing_map_sort_entry **a,
+			   const struct tracing_map_sort_entry **b)
+{
+	int ret = 0;
+
+	if (memcmp((*a)->key, (*b)->key, (*a)->elt->map->key_size))
+		ret = 1;
+
+	return ret;
+}
+
+static int cmp_entries_sum(const struct tracing_map_sort_entry **a,
+			   const struct tracing_map_sort_entry **b)
+{
+	const struct tracing_map_elt *elt_a, *elt_b;
+	struct tracing_map_sort_key *sort_key;
+	struct tracing_map_field *field;
+	tracing_map_cmp_fn_t cmp_fn;
+	void *val_a, *val_b;
+	int ret = 0;
+
+	elt_a = (*a)->elt;
+	elt_b = (*b)->elt;
+
+	sort_key = &elt_a->map->sort_key;
+
+	field = &elt_a->fields[sort_key->field_idx];
+	cmp_fn = field->cmp_fn;
+
+	val_a = &elt_a->fields[sort_key->field_idx].sum;
+	val_b = &elt_b->fields[sort_key->field_idx].sum;
+
+	ret = cmp_fn(val_a, val_b);
+	if (sort_key->descending)
+		ret = -ret;
+
+	return ret;
+}
+
+static int cmp_entries_key(const struct tracing_map_sort_entry **a,
+			   const struct tracing_map_sort_entry **b)
+{
+	const struct tracing_map_elt *elt_a, *elt_b;
+	struct tracing_map_sort_key *sort_key;
+	struct tracing_map_field *field;
+	tracing_map_cmp_fn_t cmp_fn;
+	void *val_a, *val_b;
+	int ret = 0;
+
+	elt_a = (*a)->elt;
+	elt_b = (*b)->elt;
+
+	sort_key = &elt_a->map->sort_key;
+
+	field = &elt_a->fields[sort_key->field_idx];
+
+	cmp_fn = field->cmp_fn;
+
+	val_a = elt_a->key + field->offset;
+	val_b = elt_b->key + field->offset;
+
+	ret = cmp_fn(val_a, val_b);
+	if (sort_key->descending)
+		ret = -ret;
+
+	return ret;
+}
+
+static void destroy_sort_entry(struct tracing_map_sort_entry *entry)
+{
+	if (!entry)
+		return;
+
+	if (entry->elt_copied)
+		tracing_map_elt_free(entry->elt);
+
+	kfree(entry);
+}
+
+/**
+ * tracing_map_destroy_sort_entries - Destroy an array of sort entries
+ * @entries: The entries to destroy
+ * @n_entries: The number of entries in the array
+ *
+ * Destroy the elements returned by a tracing_map_sort_entries() call.
+ */
+void tracing_map_destroy_sort_entries(struct tracing_map_sort_entry **entries,
+				      unsigned int n_entries)
+{
+	unsigned int i;
+
+	for (i = 0; i < n_entries; i++)
+		destroy_sort_entry(entries[i]);
+
+	vfree(entries);
+}
+
+static struct tracing_map_sort_entry *
+create_sort_entry(void *key, struct tracing_map_elt *elt)
+{
+	struct tracing_map_sort_entry *sort_entry;
+
+	sort_entry = kzalloc(sizeof(*sort_entry), GFP_KERNEL);
+	if (!sort_entry)
+		return NULL;
+
+	sort_entry->key = key;
+	sort_entry->elt = elt;
+
+	return sort_entry;
+}
+
+static struct tracing_map_elt *copy_elt(struct tracing_map_elt *elt)
+{
+	struct tracing_map_elt *dup_elt;
+	unsigned int i;
+
+	dup_elt = tracing_map_elt_alloc(elt->map);
+	if (!dup_elt)
+		return NULL;
+
+	if (elt->map->ops && elt->map->ops->elt_copy)
+		elt->map->ops->elt_copy(dup_elt, elt);
+
+	dup_elt->private_data = elt->private_data;
+	memcpy(dup_elt->key, elt->key, elt->map->key_size);
+
+	for (i = 0; i < elt->map->n_fields; i++) {
+		atomic64_set(&dup_elt->fields[i].sum,
+			     atomic64_read(&elt->fields[i].sum));
+		dup_elt->fields[i].cmp_fn = elt->fields[i].cmp_fn;
+	}
+
+	return dup_elt;
+}
+
+static int merge_dup(struct tracing_map_sort_entry **sort_entries,
+		     unsigned int target, unsigned int dup)
+{
+	struct tracing_map_elt *target_elt, *elt;
+	bool first_dup = (target - dup) == 1;
+	int i;
+
+	if (first_dup) {
+		elt = sort_entries[target]->elt;
+		target_elt = copy_elt(elt);
+		if (!target_elt)
+			return -ENOMEM;
+		sort_entries[target]->elt = target_elt;
+		sort_entries[target]->elt_copied = true;
+	} else
+		target_elt = sort_entries[target]->elt;
+
+	elt = sort_entries[dup]->elt;
+
+	for (i = 0; i < elt->map->n_fields; i++)
+		atomic64_add(atomic64_read(&elt->fields[i].sum),
+			     &target_elt->fields[i].sum);
+
+	sort_entries[dup]->dup = true;
+
+	return 0;
+}
+
+static int merge_dups(struct tracing_map_sort_entry **sort_entries,
+		      int n_entries, unsigned int key_size)
+{
+	unsigned int dups = 0, total_dups = 0;
+	int err, i, j;
+	void *key;
+
+	if (n_entries < 2)
+		return total_dups;
+
+	sort(sort_entries, n_entries, sizeof(struct tracing_map_sort_entry *),
+	     (int (*)(const void *, const void *))cmp_entries_dup, NULL);
+
+	key = sort_entries[0]->key;
+	for (i = 1; i < n_entries; i++) {
+		if (!memcmp(sort_entries[i]->key, key, key_size)) {
+			dups++; total_dups++;
+			err = merge_dup(sort_entries, i - dups, i);
+			if (err)
+				return err;
+			continue;
+		}
+		key = sort_entries[i]->key;
+		dups = 0;
+	}
+
+	if (!total_dups)
+		return total_dups;
+
+	for (i = 0, j = 0; i < n_entries; i++) {
+		if (!sort_entries[i]->dup) {
+			sort_entries[j] = sort_entries[i];
+			if (j++ != i)
+				sort_entries[i] = NULL;
+		} else {
+			destroy_sort_entry(sort_entries[i]);
+			sort_entries[i] = NULL;
+		}
+	}
+
+	return total_dups;
+}
+
+static bool is_key(struct tracing_map *map, unsigned int field_idx)
+{
+	unsigned int i;
+
+	for (i = 0; i < map->n_keys; i++)
+		if (map->key_idx[i] == field_idx)
+			return true;
+	return false;
+}
+
+static void sort_secondary(struct tracing_map *map,
+			   const struct tracing_map_sort_entry **entries,
+			   unsigned int n_entries,
+			   struct tracing_map_sort_key *primary_key,
+			   struct tracing_map_sort_key *secondary_key)
+{
+	int (*primary_fn)(const struct tracing_map_sort_entry **,
+			  const struct tracing_map_sort_entry **);
+	int (*secondary_fn)(const struct tracing_map_sort_entry **,
+			    const struct tracing_map_sort_entry **);
+	unsigned i, start = 0, n_sub = 1;
+
+	if (is_key(map, primary_key->field_idx))
+		primary_fn = cmp_entries_key;
+	else
+		primary_fn = cmp_entries_sum;
+
+	if (is_key(map, secondary_key->field_idx))
+		secondary_fn = cmp_entries_key;
+	else
+		secondary_fn = cmp_entries_sum;
+
+	for (i = 0; i < n_entries - 1; i++) {
+		const struct tracing_map_sort_entry **a = &entries[i];
+		const struct tracing_map_sort_entry **b = &entries[i + 1];
+
+		if (primary_fn(a, b) == 0) {
+			n_sub++;
+			if (i < n_entries - 2)
+				continue;
+		}
+
+		if (n_sub < 2) {
+			start = i + 1;
+			n_sub = 1;
+			continue;
+		}
+
+		set_sort_key(map, secondary_key);
+		sort(&entries[start], n_sub,
+		     sizeof(struct tracing_map_sort_entry *),
+		     (int (*)(const void *, const void *))secondary_fn, NULL);
+		set_sort_key(map, primary_key);
+
+		start = i + 1;
+		n_sub = 1;
+	}
+}
+
+/**
+ * tracing_map_sort_entries - Sort the current set of tracing_map_elts in a map
+ * @map: The tracing_map
+ * @sort_key: The sort key to use for sorting
+ * @sort_entries: outval: pointer to allocated and sorted array of entries
+ *
+ * tracing_map_sort_entries() sorts the current set of entries in the
+ * map and returns the list of tracing_map_sort_entries containing
+ * them to the client in the sort_entries param.  The client can
+ * access the struct tracing_map_elt element of interest directly as
+ * the 'elt' field of a returned struct tracing_map_sort_entry object.
+ *
+ * The sort_key has only two fields: idx and descending.  'idx' refers
+ * to the index of the field added via tracing_map_add_sum_field() or
+ * tracing_map_add_key_field() when the tracing_map was initialized.
+ * 'descending' is a flag that if set reverses the sort order, which
+ * by default is ascending.
+ *
+ * The client should not hold on to the returned array but should use
+ * it and call tracing_map_destroy_sort_entries() when done.
+ *
+ * Return: the number of sort_entries in the struct tracing_map_sort_entry
+ * array, negative on error
+ */
+int tracing_map_sort_entries(struct tracing_map *map,
+			     struct tracing_map_sort_key *sort_keys,
+			     unsigned int n_sort_keys,
+			     struct tracing_map_sort_entry ***sort_entries)
+{
+	int (*cmp_entries_fn)(const struct tracing_map_sort_entry **,
+			      const struct tracing_map_sort_entry **);
+	struct tracing_map_sort_entry *sort_entry, **entries;
+	int i, n_entries, ret;
+
+	entries = vmalloc(map->max_elts * sizeof(sort_entry));
+	if (!entries)
+		return -ENOMEM;
+
+	for (i = 0, n_entries = 0; i < map->map_size; i++) {
+		struct tracing_map_entry *entry;
+
+		entry = TRACING_MAP_ENTRY(map->map, i);
+
+		if (!entry->key || !entry->val)
+			continue;
+
+		entries[n_entries] = create_sort_entry(entry->val->key,
+						       entry->val);
+		if (!entries[n_entries++]) {
+			ret = -ENOMEM;
+			goto free;
+		}
+	}
+
+	if (n_entries == 0) {
+		ret = 0;
+		goto free;
+	}
+
+	if (n_entries == 1) {
+		*sort_entries = entries;
+		return 1;
+	}
+
+	ret = merge_dups(entries, n_entries, map->key_size);
+	if (ret < 0)
+		goto free;
+	n_entries -= ret;
+
+	if (is_key(map, sort_keys[0].field_idx))
+		cmp_entries_fn = cmp_entries_key;
+	else
+		cmp_entries_fn = cmp_entries_sum;
+
+	set_sort_key(map, &sort_keys[0]);
+
+	sort(entries, n_entries, sizeof(struct tracing_map_sort_entry *),
+	     (int (*)(const void *, const void *))cmp_entries_fn, NULL);
+
+	if (n_sort_keys > 1)
+		sort_secondary(map,
+			       (const struct tracing_map_sort_entry **)entries,
+			       n_entries,
+			       &sort_keys[0],
+			       &sort_keys[1]);
+
+	*sort_entries = entries;
+
+	return n_entries;
+ free:
+	tracing_map_destroy_sort_entries(entries, n_entries);
+
+	return ret;
+}
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
new file mode 100644
index 0000000..a115d84
--- /dev/null
+++ b/kernel/trace/tracing_map.h
@@ -0,0 +1,277 @@
+#ifndef __TRACING_MAP_H
+#define __TRACING_MAP_H
+
+#define TRACING_MAP_BITS_DEFAULT	11
+#define TRACING_MAP_BITS_MAX		17
+#define TRACING_MAP_BITS_MIN		7
+
+#define TRACING_MAP_FIELDS_MAX		4
+#define TRACING_MAP_KEYS_MAX		2
+
+#define TRACING_MAP_SORT_KEYS_MAX	2
+
+typedef int (*tracing_map_cmp_fn_t) (void *val_a, void *val_b);
+
+/*
+ * This is an overview of the tracing_map data structures and how they
+ * relate to the tracing_map API.  The details of the algorithms
+ * aren't discussed here - this is just a general overview of the data
+ * structures and how they interact with the API.
+ *
+ * The central data structure of the tracing_map is an initially
+ * zeroed array of struct tracing_map_entry (stored in the map field
+ * of struct tracing_map).  tracing_map_entry is a very simple data
+ * structure containing only two fields: a 32-bit unsigned 'key'
+ * variable and a pointer named 'val'.  This array of struct
+ * tracing_map_entry is essentially a hash table which will be
+ * modified by a single function, tracing_map_insert(), but which can
+ * be traversed and read by a user at any time (though the user does
+ * this indirectly via an array of tracing_map_sort_entry - see the
+ * explanation of that data structure in the discussion of the
+ * sorting-related data structures below).
+ *
+ * The central function of the tracing_map API is
+ * tracing_map_insert().  tracing_map_insert() hashes the
+ * arbitrarily-sized key passed into it into a 32-bit unsigned key.
+ * It then uses this key, truncated to the array size, as an index
+ * into the array of tracing_map_entries.  If the value of the 'key'
+ * field of the tracing_map_entry found at that location is 0, then
+ * that entry is considered to be free and can be claimed, by
+ * replacing the 0 in the 'key' field of the tracing_map_entry with
+ * the new 32-bit hashed key.  Once claimed, that tracing_map_entry's
+ * 'val' field is then used to store a unique element which will be
+ * forever associated with that 32-bit hashed key in the
+ * tracing_map_entry.
+ *
+ * That unique element now in the tracing_map_entry's 'val' field is
+ * an instance of tracing_map_elt, where 'elt' in the latter part of
+ * that variable name is short for 'element'.  The purpose of a
+ * tracing_map_elt is to hold values specific to the the particular
+ * 32-bit hashed key it's assocated with.  Things such as the unique
+ * set of aggregated sums associated with the 32-bit hashed key, along
+ * with a copy of the full key associated with the entry, and which
+ * was used to produce the 32-bit hashed key.
+ *
+ * When tracing_map_create() is called to create the tracing map, the
+ * user specifies (indirectly via the map_bits param, the details are
+ * unimportant for this discussion) the maximum number of elements
+ * that the map can hold (stored in the max_elts field of struct
+ * tracing_map).  This is the maximum possible number of
+ * tracing_map_entries in the tracing_map_entry array which can be
+ * 'claimed' as described in the above discussion, and therefore is
+ * also the maximum number of tracing_map_elts that can be associated
+ * with the tracing_map_entry array in the tracing_map.  Because of
+ * the way the insertion algorithm works, the size of the allocated
+ * tracing_map_entry array is always twice the maximum number of
+ * elements (2 * max_elts).  This value is stored in the map_size
+ * field of struct tracing_map.
+ *
+ * Because tracing_map_insert() needs to work from any context,
+ * including from within the memory allocation functions themselves,
+ * both the tracing_map_entry array and a pool of max_elts
+ * tracing_map_elts are pre-allocated before any call is made to
+ * tracing_map_insert().
+ *
+ * The tracing_map_entry array is allocated as a single block by
+ * tracing_map_create().
+ *
+ * Because the tracing_map_elts are much larger objects and can't
+ * generally be allocated together as a single large array without
+ * failure, they're allocated individually, by tracing_map_init().
+ *
+ * The pool of tracing_map_elts are allocated by tracing_map_init()
+ * rather than by tracing_map_create() because at the time
+ * tracing_map_create() is called, there isn't enough information to
+ * create the tracing_map_elts.  Specifically,the user first needs to
+ * tell the tracing_map implementation how many fields the
+ * tracing_map_elts contain, and which types of fields they are (key
+ * or sum).  The user does this via the tracing_map_add_sum_field()
+ * and tracing_map_add_key_field() functions, following which the user
+ * calls tracing_map_init() to finish up the tracing map setup.  The
+ * array holding the pointers which make up the pre-allocated pool of
+ * tracing_map_elts is allocated as a single block and is stored in
+ * the elts field of struct tracing_map.
+ *
+ * There is also a set of structures used for sorting that might
+ * benefit from some minimal explanation.
+ *
+ * struct tracing_map_sort_key is used to drive the sort at any given
+ * time.  By 'any given time' we mean that a different
+ * tracing_map_sort_key will be used at different times depending on
+ * whether the sort currently being performed is a primary or a
+ * secondary sort.
+ *
+ * The sort key is very simple, consisting of the field index of the
+ * tracing_map_elt field to sort on (which the user saved when adding
+ * the field), and whether the sort should be done in an ascending or
+ * descending order.
+ *
+ * For the convenience of the sorting code, a tracing_map_sort_entry
+ * is created for each tracing_map_elt, again individually allocated
+ * to avoid failures that might be expected if allocated as a single
+ * large array of struct tracing_map_sort_entry.
+ * tracing_map_sort_entry instances are the objects expected by the
+ * various internal sorting functions, and are also what the user
+ * ultimately receives after calling tracing_map_sort_entries().
+ * Because it doesn't make sense for users to access an unordered and
+ * sparsely populated tracing_map directly, the
+ * tracing_map_sort_entries() function is provided so that users can
+ * retrieve a sorted list of all existing elements.  In addition to
+ * the associated tracing_map_elt 'elt' field contained within the
+ * tracing_map_sort_entry, which is the object of interest to the
+ * user, tracing_map_sort_entry objects contain a number of additional
+ * fields which are used for caching and internal purposes and can
+ * safely be ignored.
+*/
+
+struct tracing_map_field {
+	tracing_map_cmp_fn_t		cmp_fn;
+	union {
+		atomic64_t			sum;
+		unsigned int			offset;
+	};
+};
+
+struct tracing_map_elt {
+	struct tracing_map		*map;
+	struct tracing_map_field	*fields;
+	void				*key;
+	void				*private_data;
+};
+
+struct tracing_map_entry {
+	u32				key;
+	struct tracing_map_elt		*val;
+};
+
+struct tracing_map_sort_key {
+	unsigned int			field_idx;
+	bool				descending;
+};
+
+struct tracing_map_sort_entry {
+	void				*key;
+	struct tracing_map_elt		*elt;
+	bool				elt_copied;
+	bool				dup;
+};
+
+struct tracing_map_array {
+	unsigned int entries_per_page;
+	unsigned int entry_size_shift;
+	unsigned int entry_shift;
+	unsigned int entry_mask;
+	unsigned int n_pages;
+	void **pages;
+};
+
+#define TRACING_MAP_ARRAY_ELT(array, idx)				\
+	(array->pages[idx >> array->entry_shift] +			\
+	 ((idx & array->entry_mask) << array->entry_size_shift))
+
+#define TRACING_MAP_ENTRY(array, idx)					\
+	((struct tracing_map_entry *)TRACING_MAP_ARRAY_ELT(array, idx))
+
+#define TRACING_MAP_ELT(array, idx)					\
+	((struct tracing_map_elt **)TRACING_MAP_ARRAY_ELT(array, idx))
+
+struct tracing_map {
+	unsigned int			key_size;
+	unsigned int			map_bits;
+	unsigned int			map_size;
+	unsigned int			max_elts;
+	atomic_t			next_elt;
+	struct tracing_map_array	*elts;
+	struct tracing_map_array	*map;
+	struct tracing_map_ops		*ops;
+	void				*private_data;
+	struct tracing_map_field	fields[TRACING_MAP_FIELDS_MAX];
+	unsigned int			n_fields;
+	int				key_idx[TRACING_MAP_KEYS_MAX];
+	unsigned int			n_keys;
+	struct tracing_map_sort_key	sort_key;
+};
+
+/**
+ * struct tracing_map_ops - callbacks for tracing_map
+ *
+ * The methods in this structure define callback functions for various
+ * operations on a tracing_map or objects related to a tracing_map.
+ *
+ * For a detailed description of tracing_map_elt objects please see
+ * the overview of tracing_map data structures at the beginning of
+ * this file.
+ *
+ * All the methods below are optional.
+ *
+ * @elt_alloc: When a tracing_map_elt is allocated, this function, if
+ *	defined, will be called and gives clients the opportunity to
+ *	allocate additional data and attach it to the element
+ *	(tracing_map_elt->private_data is meant for that purpose).
+ *	Element allocation occurs before tracing begins, when the
+ *	tracing_map_init() call is made by client code.
+ *
+ * @elt_copy: At certain points in the lifetime of an element, it may
+ *	need to be copied.  The copy should include a copy of the
+ *	client-allocated data, which can be copied into the 'to'
+ *	element from the 'from' element.
+ *
+ * @elt_free: When a tracing_map_elt is freed, this function is called
+ *	and allows client-allocated per-element data to be freed.
+ *
+ * @elt_clear: This callback allows per-element client-defined data to
+ *	be cleared, if applicable.
+ *
+ * @elt_init: This callback allows per-element client-defined data to
+ *	be initialized when used i.e. when the element is actually
+ *	claimed by tracing_map_insert() in the context of the map
+ *	insertion.
+ */
+struct tracing_map_ops {
+	int			(*elt_alloc)(struct tracing_map_elt *elt);
+	void			(*elt_copy)(struct tracing_map_elt *to,
+					    struct tracing_map_elt *from);
+	void			(*elt_free)(struct tracing_map_elt *elt);
+	void			(*elt_clear)(struct tracing_map_elt *elt);
+	void			(*elt_init)(struct tracing_map_elt *elt);
+};
+
+extern struct tracing_map *tracing_map_create(unsigned int map_bits,
+					      unsigned int key_size,
+					      struct tracing_map_ops *ops,
+					      void *private_data);
+extern int tracing_map_init(struct tracing_map *map);
+
+extern int tracing_map_add_sum_field(struct tracing_map *map);
+extern int tracing_map_add_key_field(struct tracing_map *map,
+				     unsigned int offset,
+				     tracing_map_cmp_fn_t cmp_fn);
+
+extern void tracing_map_destroy(struct tracing_map *map);
+extern void tracing_map_clear(struct tracing_map *map);
+
+extern struct tracing_map_elt *
+tracing_map_insert(struct tracing_map *map, void *key);
+
+extern tracing_map_cmp_fn_t tracing_map_cmp_num(int field_size,
+						int field_is_signed);
+extern int tracing_map_cmp_string(void *val_a, void *val_b);
+extern int tracing_map_cmp_none(void *val_a, void *val_b);
+
+extern void tracing_map_update_sum(struct tracing_map_elt *elt,
+				   unsigned int i, u64 n);
+extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
+extern void tracing_map_set_field_descr(struct tracing_map *map,
+					unsigned int i,
+					unsigned int key_offset,
+					tracing_map_cmp_fn_t cmp_fn);
+extern int
+tracing_map_sort_entries(struct tracing_map *map,
+			 struct tracing_map_sort_key *sort_keys,
+			 unsigned int n_sort_keys,
+			 struct tracing_map_sort_entry ***sort_entries);
+
+extern void
+tracing_map_destroy_sort_entries(struct tracing_map_sort_entry **entries,
+				 unsigned int n_entries);
+#endif /* __TRACING_MAP_H */
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/