jump label: Base patch for jump label

base patch to implement 'jump labeling'. Based on a new 'asm goto' inline
assembly gcc mechanism, we can now branch to labels from an 'asm goto'
statment. This allows us to create a 'no-op' fastpath, which can subsequently
be patched with a jump to the slowpath code. This is useful for code which
might be rarely used, but which we'd like to be able to call, if needed.
Tracepoints are the current usecase that these are being implemented for.

Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jason Baron <jbaron@redhat.com>
LKML-Reference: <ee8b3595967989fdaf84e698dc7447d315ce972a.1284733808.git.jbaron@redhat.com>

[ cleaned up some formating ]

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

4 files changed, 354 insertions, 1 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 0b72d1a74be0..d52b473c99a1 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o
+	    async.o range.o jump_label.o
 obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
new file mode 100644
index 000000000000..460fd40112b3
--- /dev/null
+++ b/kernel/jump_label.c
@@ -0,0 +1,346 @@
+/*
+ * jump label support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/err.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+#define JUMP_LABEL_HASH_BITS 6
+#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS)
+static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE];
+
+/* mutex to protect coming/going of the the jump_label table */
+static DEFINE_MUTEX(jump_label_mutex);
+
+struct jump_label_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	/* hang modules off here */
+	struct hlist_head modules;
+	unsigned long key;
+};
+
+struct jump_label_module_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	struct module *mod;
+};
+
+static int jump_label_cmp(const void *a, const void *b)
+{
+	const struct jump_entry *jea = a;
+	const struct jump_entry *jeb = b;
+
+	if (jea->key < jeb->key)
+		return -1;
+
+	if (jea->key > jeb->key)
+		return 1;
+
+	return 0;
+}
+
+static void
+sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop)
+{
+	unsigned long size;
+
+	size = (((unsigned long)stop - (unsigned long)start)
+					/ sizeof(struct jump_entry));
+	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
+}
+
+static struct jump_label_entry *get_jump_label_entry(jump_label_t key)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct jump_label_entry *e;
+	u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (key == e->key)
+			return e;
+	}
+	return NULL;
+}
+
+static struct jump_label_entry *
+add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table)
+{
+	struct hlist_head *head;
+	struct jump_label_entry *e;
+	u32 hash;
+
+	e = get_jump_label_entry(key);
+	if (e)
+		return ERR_PTR(-EEXIST);
+
+	e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+
+	hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	e->key = key;
+	e->table = table;
+	e->nr_entries = nr_entries;
+	INIT_HLIST_HEAD(&(e->modules));
+	hlist_add_head(&e->hlist, head);
+	return e;
+}
+
+static int
+build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	int count;
+
+	sort_jump_label_entries(start, stop);
+	iter = start;
+	while (iter < stop) {
+		entry = get_jump_label_entry(iter->key);
+		if (!entry) {
+			iter_begin = iter;
+			count = 0;
+			while ((iter < stop) &&
+				(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+			}
+			entry = add_jump_label_entry(iter_begin->key,
+							count, iter_begin);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		 } else {
+			WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n");
+			return -1;
+		}
+	}
+	return 0;
+}
+
+/***
+ * jump_label_update - update jump label text
+ * @key -  key value associated with a a jump label
+ * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE
+ *
+ * Will enable/disable the jump for jump label @key, depending on the
+ * value of @type.
+ *
+ */
+
+void jump_label_update(unsigned long key, enum jump_label_type type)
+{
+	struct jump_entry *iter;
+	struct jump_label_entry *entry;
+	struct hlist_node *module_node;
+	struct jump_label_module_entry *e_module;
+	int count;
+
+	mutex_lock(&jump_label_mutex);
+	entry = get_jump_label_entry((jump_label_t)key);
+	if (entry) {
+		count = entry->nr_entries;
+		iter = entry->table;
+		while (count--) {
+			if (kernel_text_address(iter->code))
+				arch_jump_label_transform(iter, type);
+			iter++;
+		}
+		/* eanble/disable jump labels in modules */
+		hlist_for_each_entry(e_module, module_node, &(entry->modules),
+							hlist) {
+			count = e_module->nr_entries;
+			iter = e_module->table;
+			while (count--) {
+				if (kernel_text_address(iter->code))
+					arch_jump_label_transform(iter, type);
+				iter++;
+			}
+		}
+	}
+	mutex_unlock(&jump_label_mutex);
+}
+
+static __init int init_jump_label(void)
+{
+	int ret;
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_entry *iter;
+
+	mutex_lock(&jump_label_mutex);
+	ret = build_jump_label_hashtable(__start___jump_table,
+					 __stop___jump_table);
+	iter = iter_start;
+	while (iter < iter_stop) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+	mutex_unlock(&jump_label_mutex);
+	return ret;
+}
+early_initcall(init_jump_label);
+
+#ifdef CONFIG_MODULES
+
+static struct jump_label_module_entry *
+add_jump_label_module_entry(struct jump_label_entry *entry,
+			    struct jump_entry *iter_begin,
+			    int count, struct module *mod)
+{
+	struct jump_label_module_entry *e;
+
+	e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+	e->mod = mod;
+	e->nr_entries = count;
+	e->table = iter_begin;
+	hlist_add_head(&e->hlist, &entry->modules);
+	return e;
+}
+
+static int add_jump_label_module(struct module *mod)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	struct jump_label_module_entry *module_entry;
+	int count;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return 0;
+
+	sort_jump_label_entries(mod->jump_entries,
+				mod->jump_entries + mod->num_jump_entries);
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		entry = get_jump_label_entry(iter->key);
+		iter_begin = iter;
+		count = 0;
+		while ((iter < mod->jump_entries + mod->num_jump_entries) &&
+			(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+		}
+		if (!entry) {
+			entry = add_jump_label_entry(iter_begin->key, 0, NULL);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		}
+		module_entry = add_jump_label_module_entry(entry, iter_begin,
+							   count, mod);
+		if (IS_ERR(module_entry))
+			return PTR_ERR(module_entry);
+	}
+	return 0;
+}
+
+static void remove_jump_label_module(struct module *mod)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	int i;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+						  module_node_next,
+						  &(e->modules), hlist) {
+				if (e_module->mod == mod) {
+					hlist_del(&e_module->hlist);
+					kfree(e_module);
+				}
+			}
+			if (hlist_empty(&e->modules) && (e->nr_entries == 0)) {
+				hlist_del(&e->hlist);
+				kfree(e);
+			}
+		}
+	}
+}
+
+static int
+jump_label_module_notify(struct notifier_block *self, unsigned long val,
+			 void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		mutex_lock(&jump_label_mutex);
+		ret = add_jump_label_module(mod);
+		if (ret)
+			remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	case MODULE_STATE_GOING:
+		mutex_lock(&jump_label_mutex);
+		remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	}
+	return ret;
+}
+
+/***
+ * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
+ * @mod: module to patch
+ *
+ * Allow for run-time selection of the optimal nops. Before the module
+ * loads patch these with arch_get_jump_label_nop(), which is specified by
+ * the arch specific jump label code.
+ */
+void jump_label_apply_nops(struct module *mod)
+{
+	struct jump_entry *iter;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+}
+
+struct notifier_block jump_label_module_nb = {
+	.notifier_call = jump_label_module_notify,
+	.priority = 0,
+};
+
+static __init int init_jump_label_module(void)
+{
+	return register_module_notifier(&jump_label_module_nb);
+}
+early_initcall(init_jump_label_module);
+
+#endif /* CONFIG_MODULES */
+
+#endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 6dd5359e1f0e..18904e42a918 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -47,6 +47,7 @@
 #include <linux/memory.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/jump_label.h>
 
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
diff --git a/kernel/module.c b/kernel/module.c
index d0b5f8db11b4..eba134157ef6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -55,6 +55,7 @@
 #include <linux/async.h>
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
+#include <linux/jump_label.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
@@ -2308,6 +2309,11 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 					sizeof(*mod->tracepoints),
 					&mod->num_tracepoints);
 #endif
+#ifdef HAVE_JUMP_LABEL
+	mod->jump_entries = section_objs(info, "__jump_table",
+					sizeof(*mod->jump_entries),
+					&mod->num_jump_entries);
+#endif
 #ifdef CONFIG_EVENT_TRACING
 	mod->trace_events = section_objs(info, "_ftrace_events",
 					 sizeof(*mod->trace_events),