1 files changed, 248 insertions, 182 deletions

diff --git a/net/core/flow.c b/net/core/flow.c
index 96015871ece..127c8a7ffd6 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -26,120 +26,161 @@
 #include <linux/security.h>
 
 struct flow_cache_entry {
-	struct flow_cache_entry	*next;
-	u16			family;
-	u8			dir;
-	u32			genid;
-	struct flowi		key;
-	void			*object;
-	atomic_t		*object_ref;
+	union {
+		struct hlist_node	hlist;
+		struct list_head	gc_list;
+	} u;
+	u16				family;
+	u8				dir;
+	u32				genid;
+	struct flowi			key;
+	struct flow_cache_object	*object;
 };
 
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-
-static u32 flow_hash_shift;
-#define flow_hash_size	(1 << flow_hash_shift)
-static DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL };
-
-#define flow_table(cpu) (per_cpu(flow_tables, cpu))
-
-static struct kmem_cache *flow_cachep __read_mostly;
-
-static int flow_lwm, flow_hwm;
-
-struct flow_percpu_info {
-	int hash_rnd_recalc;
-	u32 hash_rnd;
-	int count;
+struct flow_cache_percpu {
+	struct hlist_head		*hash_table;
+	int				hash_count;
+	u32				hash_rnd;
+	int				hash_rnd_recalc;
+	struct tasklet_struct		flush_tasklet;
 };
-static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 };
 
-#define flow_hash_rnd_recalc(cpu) \
-	(per_cpu(flow_hash_info, cpu).hash_rnd_recalc)
-#define flow_hash_rnd(cpu) \
-	(per_cpu(flow_hash_info, cpu).hash_rnd)
-#define flow_count(cpu) \
-	(per_cpu(flow_hash_info, cpu).count)
+struct flow_flush_info {
+	struct flow_cache		*cache;
+	atomic_t			cpuleft;
+	struct completion		completion;
+};
 
-static struct timer_list flow_hash_rnd_timer;
+struct flow_cache {
+	u32				hash_shift;
+	struct flow_cache_percpu __percpu *percpu;
+	struct notifier_block		hotcpu_notifier;
+	int				low_watermark;
+	int				high_watermark;
+	struct timer_list		rnd_timer;
+};
 
-#define FLOW_HASH_RND_PERIOD	(10 * 60 * HZ)
+atomic_t flow_cache_genid = ATOMIC_INIT(0);
+EXPORT_SYMBOL(flow_cache_genid);
+static struct flow_cache flow_cache_global;
+static struct kmem_cache *flow_cachep __read_mostly;
 
-struct flow_flush_info {
-	atomic_t cpuleft;
-	struct completion completion;
-};
-static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL };
+static DEFINE_SPINLOCK(flow_cache_gc_lock);
+static LIST_HEAD(flow_cache_gc_list);
 
-#define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu))
+#define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
+#define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
 static void flow_cache_new_hashrnd(unsigned long arg)
 {
+	struct flow_cache *fc = (void *) arg;
 	int i;
 
 	for_each_possible_cpu(i)
-		flow_hash_rnd_recalc(i) = 1;
+		per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1;
 
-	flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
-	add_timer(&flow_hash_rnd_timer);
+	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
+	add_timer(&fc->rnd_timer);
 }
 
-static void flow_entry_kill(int cpu, struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle)
+{
+	if (atomic_read(&flow_cache_genid) != fle->genid)
+		return 0;
+	if (fle->object && !fle->object->ops->check(fle->object))
+		return 0;
+	return 1;
+}
+
+static void flow_entry_kill(struct flow_cache_entry *fle)
 {
 	if (fle->object)
-		atomic_dec(fle->object_ref);
+		fle->object->ops->delete(fle->object);
 	kmem_cache_free(flow_cachep, fle);
-	flow_count(cpu)--;
 }
 
-static void __flow_cache_shrink(int cpu, int shrink_to)
+static void flow_cache_gc_task(struct work_struct *work)
 {
-	struct flow_cache_entry *fle, **flp;
-	int i;
+	struct list_head gc_list;
+	struct flow_cache_entry *fce, *n;
 
-	for (i = 0; i < flow_hash_size; i++) {
-		int k = 0;
+	INIT_LIST_HEAD(&gc_list);
+	spin_lock_bh(&flow_cache_gc_lock);
+	list_splice_tail_init(&flow_cache_gc_list, &gc_list);
+	spin_unlock_bh(&flow_cache_gc_lock);
 
-		flp = &flow_table(cpu)[i];
-		while ((fle = *flp) != NULL && k < shrink_to) {
-			k++;
-			flp = &fle->next;
-		}
-		while ((fle = *flp) != NULL) {
-			*flp = fle->next;
-			flow_entry_kill(cpu, fle);
-		}
+	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
+		flow_entry_kill(fce);
+}
+static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
+
+static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
+				     int deleted, struct list_head *gc_list)
+{
+	if (deleted) {
+		fcp->hash_count -= deleted;
+		spin_lock_bh(&flow_cache_gc_lock);
+		list_splice_tail(gc_list, &flow_cache_gc_list);
+		spin_unlock_bh(&flow_cache_gc_lock);
+		schedule_work(&flow_cache_gc_work);
 	}
 }
 
-static void flow_cache_shrink(int cpu)
+static void __flow_cache_shrink(struct flow_cache *fc,
+				struct flow_cache_percpu *fcp,
+				int shrink_to)
 {
-	int shrink_to = flow_lwm / flow_hash_size;
+	struct flow_cache_entry *fle;
+	struct hlist_node *entry, *tmp;
+	LIST_HEAD(gc_list);
+	int i, deleted = 0;
+
+	for (i = 0; i < flow_cache_hash_size(fc); i++) {
+		int saved = 0;
+
+		hlist_for_each_entry_safe(fle, entry, tmp,
+					  &fcp->hash_table[i], u.hlist) {
+			if (saved < shrink_to &&
+			    flow_entry_valid(fle)) {
+				saved++;
+			} else {
+				deleted++;
+				hlist_del(&fle->u.hlist);
+				list_add_tail(&fle->u.gc_list, &gc_list);
+			}
+		}
+	}
 
-	__flow_cache_shrink(cpu, shrink_to);
+	flow_cache_queue_garbage(fcp, deleted, &gc_list);
 }
 
-static void flow_new_hash_rnd(int cpu)
+static void flow_cache_shrink(struct flow_cache *fc,
+			      struct flow_cache_percpu *fcp)
 {
-	get_random_bytes(&flow_hash_rnd(cpu), sizeof(u32));
-	flow_hash_rnd_recalc(cpu) = 0;
+	int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+
+	__flow_cache_shrink(fc, fcp, shrink_to);
+}
 
-	__flow_cache_shrink(cpu, 0);
+static void flow_new_hash_rnd(struct flow_cache *fc,
+			      struct flow_cache_percpu *fcp)
+{
+	get_random_bytes(&fcp->hash_rnd, sizeof(u32));
+	fcp->hash_rnd_recalc = 0;
+	__flow_cache_shrink(fc, fcp, 0);
 }
 
-static u32 flow_hash_code(struct flowi *key, int cpu)
+static u32 flow_hash_code(struct flow_cache *fc,
+			  struct flow_cache_percpu *fcp,
+			  struct flowi *key)
 {
 	u32 *k = (u32 *) key;
 
-	return (jhash2(k, (sizeof(*key) / sizeof(u32)), flow_hash_rnd(cpu)) &
-		(flow_hash_size - 1));
+	return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd)
+		& (flow_cache_hash_size(fc) - 1);
 }
 
-#if (BITS_PER_LONG == 64)
-typedef u64 flow_compare_t;
-#else
-typedef u32 flow_compare_t;
-#endif
+typedef unsigned long flow_compare_t;
 
 /* I hear what you're saying, use memcmp.  But memcmp cannot make
  * important assumptions that we can here, such as alignment and
@@ -165,114 +206,118 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2)
 	return 0;
 }
 
-void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir,
-			flow_resolve_t resolver)
+struct flow_cache_object *
+flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir,
+		  flow_resolve_t resolver, void *ctx)
 {
-	struct flow_cache_entry *fle, **head;
+	struct flow_cache *fc = &flow_cache_global;
+	struct flow_cache_percpu *fcp;
+	struct flow_cache_entry *fle, *tfle;
+	struct hlist_node *entry;
+	struct flow_cache_object *flo;
 	unsigned int hash;
-	int cpu;
 
 	local_bh_disable();
-	cpu = smp_processor_id();
+	fcp = this_cpu_ptr(fc->percpu);
 
 	fle = NULL;
+	flo = NULL;
 	/* Packet really early in init?  Making flow_cache_init a
 	 * pre-smp initcall would solve this.  --RR */
-	if (!flow_table(cpu))
+	if (!fcp->hash_table)
 		goto nocache;
 
-	if (flow_hash_rnd_recalc(cpu))
-		flow_new_hash_rnd(cpu);
-	hash = flow_hash_code(key, cpu);
-
-	head = &flow_table(cpu)[hash];
-	for (fle = *head; fle; fle = fle->next) {
-		if (fle->family == family &&
-		    fle->dir == dir &&
-		    flow_key_compare(key, &fle->key) == 0) {
-			if (fle->genid == atomic_read(&flow_cache_genid)) {
-				void *ret = fle->object;
+	if (fcp->hash_rnd_recalc)
+		flow_new_hash_rnd(fc, fcp);
 
-				if (ret)
-					atomic_inc(fle->object_ref);
-				local_bh_enable();
-
-				return ret;
-			}
+	hash = flow_hash_code(fc, fcp, key);
+	hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) {
+		if (tfle->family == family &&
+		    tfle->dir == dir &&
+		    flow_key_compare(key, &tfle->key) == 0) {
+			fle = tfle;
 			break;
 		}
 	}
 
-	if (!fle) {
-		if (flow_count(cpu) > flow_hwm)
-			flow_cache_shrink(cpu);
+	if (unlikely(!fle)) {
+		if (fcp->hash_count > fc->high_watermark)
+			flow_cache_shrink(fc, fcp);
 
 		fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
 		if (fle) {
-			fle->next = *head;
-			*head = fle;
 			fle->family = family;
 			fle->dir = dir;
 			memcpy(&fle->key, key, sizeof(*key));
 			fle->object = NULL;
-			flow_count(cpu)++;
+			hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
+			fcp->hash_count++;
 		}
+	} else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+		flo = fle->object;
+		if (!flo)
+			goto ret_object;
+		flo = flo->ops->get(flo);
+		if (flo)
+			goto ret_object;
+	} else if (fle->object) {
+	        flo = fle->object;
+	        flo->ops->delete(flo);
+	        fle->object = NULL;
 	}
 
 nocache:
-	{
-		int err;
-		void *obj;
-		atomic_t *obj_ref;
-
-		err = resolver(net, key, family, dir, &obj, &obj_ref);
-
-		if (fle && !err) {
-			fle->genid = atomic_read(&flow_cache_genid);
-
-			if (fle->object)
-				atomic_dec(fle->object_ref);
-
-			fle->object = obj;
-			fle->object_ref = obj_ref;
-			if (obj)
-				atomic_inc(fle->object_ref);
-		}
-		local_bh_enable();
-
-		if (err)
-			obj = ERR_PTR(err);
-		return obj;
+	flo = NULL;
+	if (fle) {
+		flo = fle->object;
+		fle->object = NULL;
+	}
+	flo = resolver(net, key, family, dir, flo, ctx);
+	if (fle) {
+		fle->genid = atomic_read(&flow_cache_genid);
+		if (!IS_ERR(flo))
+			fle->object = flo;
+		else
+			fle->genid--;
+	} else {
+		if (flo && !IS_ERR(flo))
+			flo->ops->delete(flo);
 	}
+ret_object:
+	local_bh_enable();
+	return flo;
 }
+EXPORT_SYMBOL(flow_cache_lookup);
 
 static void flow_cache_flush_tasklet(unsigned long data)
 {
 	struct flow_flush_info *info = (void *)data;
-	int i;
-	int cpu;
-
-	cpu = smp_processor_id();
-	for (i = 0; i < flow_hash_size; i++) {
-		struct flow_cache_entry *fle;
-
-		fle = flow_table(cpu)[i];
-		for (; fle; fle = fle->next) {
-			unsigned genid = atomic_read(&flow_cache_genid);
-
-			if (!fle->object || fle->genid == genid)
+	struct flow_cache *fc = info->cache;
+	struct flow_cache_percpu *fcp;
+	struct flow_cache_entry *fle;
+	struct hlist_node *entry, *tmp;
+	LIST_HEAD(gc_list);
+	int i, deleted = 0;
+
+	fcp = this_cpu_ptr(fc->percpu);
+	for (i = 0; i < flow_cache_hash_size(fc); i++) {
+		hlist_for_each_entry_safe(fle, entry, tmp,
+					  &fcp->hash_table[i], u.hlist) {
+			if (flow_entry_valid(fle))
 				continue;
 
-			fle->object = NULL;
-			atomic_dec(fle->object_ref);
+			deleted++;
+			hlist_del(&fle->u.hlist);
+			list_add_tail(&fle->u.gc_list, &gc_list);
 		}
 	}
 
+	flow_cache_queue_garbage(fcp, deleted, &gc_list);
+
 	if (atomic_dec_and_test(&info->cpuleft))
 		complete(&info->completion);
 }
 
-static void flow_cache_flush_per_cpu(void *) __attribute__((__unused__));
 static void flow_cache_flush_per_cpu(void *data)
 {
 	struct flow_flush_info *info = data;
@@ -280,8 +325,7 @@ static void flow_cache_flush_per_cpu(void *data)
 	struct tasklet_struct *tasklet;
 
 	cpu = smp_processor_id();
-
-	tasklet = flow_flush_tasklet(cpu);
+	tasklet = &per_cpu_ptr(info->cache->percpu, cpu)->flush_tasklet;
 	tasklet->data = (unsigned long)info;
 	tasklet_schedule(tasklet);
 }
@@ -294,6 +338,7 @@ void flow_cache_flush(void)
 	/* Don't want cpus going down or up during this. */
 	get_online_cpus();
 	mutex_lock(&flow_flush_sem);
+	info.cache = &flow_cache_global;
 	atomic_set(&info.cpuleft, num_online_cpus());
 	init_completion(&info.completion);
 
@@ -307,62 +352,83 @@ void flow_cache_flush(void)
 	put_online_cpus();
 }
 
-static void __init flow_cache_cpu_prepare(int cpu)
+static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 {
-	struct tasklet_struct *tasklet;
-	unsigned long order;
-
-	for (order = 0;
-	     (PAGE_SIZE << order) <
-		     (sizeof(struct flow_cache_entry *)*flow_hash_size);
-	     order++)
-		/* NOTHING */;
-
-	flow_table(cpu) = (struct flow_cache_entry **)
-		__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
-	if (!flow_table(cpu))
-		panic("NET: failed to allocate flow cache order %lu\n", order);
-
-	flow_hash_rnd_recalc(cpu) = 1;
-	flow_count(cpu) = 0;
-
-	tasklet = flow_flush_tasklet(cpu);
-	tasklet_init(tasklet, flow_cache_flush_tasklet, 0);
+	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
+	size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+
+	if (!fcp->hash_table) {
+		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
+		if (!fcp->hash_table) {
+			pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+			return -ENOMEM;
+		}
+		fcp->hash_rnd_recalc = 1;
+		fcp->hash_count = 0;
+		tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0);
+	}
+	return 0;
 }
 
-static int flow_cache_cpu(struct notifier_block *nfb,
+static int __cpuinit flow_cache_cpu(struct notifier_block *nfb,
 			  unsigned long action,
 			  void *hcpu)
 {
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
-		__flow_cache_shrink((unsigned long)hcpu, 0);
+	struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+	int res, cpu = (unsigned long) hcpu;
+	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		res = flow_cache_cpu_prepare(fc, cpu);
+		if (res)
+			return notifier_from_errno(res);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		__flow_cache_shrink(fc, fcp, 0);
+		break;
+	}
 	return NOTIFY_OK;
 }
 
-static int __init flow_cache_init(void)
+static int __init flow_cache_init(struct flow_cache *fc)
 {
 	int i;
 
-	flow_cachep = kmem_cache_create("flow_cache",
-					sizeof(struct flow_cache_entry),
-					0, SLAB_PANIC,
-					NULL);
-	flow_hash_shift = 10;
-	flow_lwm = 2 * flow_hash_size;
-	flow_hwm = 4 * flow_hash_size;
+	fc->hash_shift = 10;
+	fc->low_watermark = 2 * flow_cache_hash_size(fc);
+	fc->high_watermark = 4 * flow_cache_hash_size(fc);
 
-	setup_timer(&flow_hash_rnd_timer, flow_cache_new_hashrnd, 0);
-	flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
-	add_timer(&flow_hash_rnd_timer);
+	fc->percpu = alloc_percpu(struct flow_cache_percpu);
+	if (!fc->percpu)
+		return -ENOMEM;
 
-	for_each_possible_cpu(i)
-		flow_cache_cpu_prepare(i);
+	for_each_online_cpu(i) {
+		if (flow_cache_cpu_prepare(fc, i))
+			return -ENOMEM;
+	}
+	fc->hotcpu_notifier = (struct notifier_block){
+		.notifier_call = flow_cache_cpu,
+	};
+	register_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
+		    (unsigned long) fc);
+	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
+	add_timer(&fc->rnd_timer);
 
-	hotcpu_notifier(flow_cache_cpu, 0);
 	return 0;
 }
 
-module_init(flow_cache_init);
+static int __init flow_cache_init_global(void)
+{
+	flow_cachep = kmem_cache_create("flow_cache",
+					sizeof(struct flow_cache_entry),
+					0, SLAB_PANIC, NULL);
 
-EXPORT_SYMBOL(flow_cache_genid);
-EXPORT_SYMBOL(flow_cache_lookup);
+	return flow_cache_init(&flow_cache_global);
+}
+
+module_init(flow_cache_init_global);