968 lines · 23.0 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (c) 2007-2014 Nicira, Inc. */ #include "flow.h"#include "datapath.h"#include "flow_netlink.h"#include <linux/uaccess.h>#include <linux/netdevice.h>#include <linux/etherdevice.h>#include <linux/if_ether.h>#include <linux/if_vlan.h>#include <net/llc_pdu.h>#include <linux/kernel.h>#include <linux/jhash.h>#include <linux/jiffies.h>#include <linux/llc.h>#include <linux/module.h>#include <linux/in.h>#include <linux/rcupdate.h>#include <linux/cpumask.h>#include <linux/if_arp.h>#include <linux/ip.h>#include <linux/ipv6.h>#include <linux/sctp.h>#include <linux/tcp.h>#include <linux/udp.h>#include <linux/icmp.h>#include <linux/icmpv6.h>#include <linux/rculist.h>#include <net/ip.h>#include <net/ipv6.h>#include <net/ndisc.h> #define TBL_MIN_BUCKETS		1024#define MASK_ARRAY_SIZE_MIN	16#define REHASH_INTERVAL		(10 * 60 * HZ) #define MC_HASH_SHIFT		8#define MC_HASH_ENTRIES		(1u << MC_HASH_SHIFT)#define MC_HASH_SEGS		((sizeof(uint32_t) * 8) / MC_HASH_SHIFT) static struct kmem_cache *flow_cache;struct kmem_cache *flow_stats_cache __read_mostly; static u16 range_n_bytes(const struct sw_flow_key_range *range){	return range->end - range->start;} void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,		       bool full, const struct sw_flow_mask *mask){	int start = full ? 0 : mask->range.start;	int len = full ? sizeof *dst : range_n_bytes(&mask->range);	const long *m = (const long *)((const u8 *)&mask->key + start);	const long *s = (const long *)((const u8 *)src + start);	long *d = (long *)((u8 *)dst + start);	int i; 	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,	 * if 'full' is false the memory outside of the 'mask->range' is left	 * uninitialized. This can be used as an optimization when further	 * operations on 'dst' only use contents within 'mask->range'.	 */	for (i = 0; i < len; i += sizeof(long))		*d++ = *s++ & *m++;} struct sw_flow *ovs_flow_alloc(void){	struct sw_flow *flow;	struct sw_flow_stats *stats; 	flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);	if (!flow)		return ERR_PTR(-ENOMEM); 	flow->stats_last_writer = -1; 	/* Initialize the default stat node. */	stats = kmem_cache_alloc_node(flow_stats_cache,				      GFP_KERNEL | __GFP_ZERO,				      node_online(0) ? 0 : NUMA_NO_NODE);	if (!stats)		goto err; 	spin_lock_init(&stats->lock); 	RCU_INIT_POINTER(flow->stats[0], stats); 	cpumask_set_cpu(0, &flow->cpu_used_mask); 	return flow;err:	kmem_cache_free(flow_cache, flow);	return ERR_PTR(-ENOMEM);} int ovs_flow_tbl_count(const struct flow_table *table){	return table->count;} static void flow_free(struct sw_flow *flow){	int cpu; 	if (ovs_identifier_is_key(&flow->id))		kfree(flow->id.unmasked_key);	if (flow->sf_acts)		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);	/* We open code this to make sure cpu 0 is always considered */	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))		if (flow->stats[cpu])			kmem_cache_free(flow_stats_cache,					(struct sw_flow_stats __force *)flow->stats[cpu]);	kmem_cache_free(flow_cache, flow);} static void rcu_free_flow_callback(struct rcu_head *rcu){	struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu); 	flow_free(flow);} void ovs_flow_free(struct sw_flow *flow, bool deferred){	if (!flow)		return; 	if (deferred)		call_rcu(&flow->rcu, rcu_free_flow_callback);	else		flow_free(flow);} static void __table_instance_destroy(struct table_instance *ti){	kvfree(ti->buckets);	kfree(ti);} static struct table_instance *table_instance_alloc(int new_size){	struct table_instance *ti = kmalloc(sizeof(*ti), GFP_KERNEL);	int i; 	if (!ti)		return NULL; 	ti->buckets = kvmalloc_array(new_size, sizeof(struct hlist_head),				     GFP_KERNEL);	if (!ti->buckets) {		kfree(ti);		return NULL;	} 	for (i = 0; i < new_size; i++)		INIT_HLIST_HEAD(&ti->buckets[i]); 	ti->n_buckets = new_size;	ti->node_ver = 0;	ti->keep_flows = false;	get_random_bytes(&ti->hash_seed, sizeof(u32)); 	return ti;} static struct mask_array *tbl_mask_array_alloc(int size){	struct mask_array *new; 	size = max(MASK_ARRAY_SIZE_MIN, size);	new = kzalloc(sizeof(struct mask_array) +		      sizeof(struct sw_flow_mask *) * size, GFP_KERNEL);	if (!new)		return NULL; 	new->count = 0;	new->max = size; 	return new;} static int tbl_mask_array_realloc(struct flow_table *tbl, int size){	struct mask_array *old;	struct mask_array *new; 	new = tbl_mask_array_alloc(size);	if (!new)		return -ENOMEM; 	old = ovsl_dereference(tbl->mask_array);	if (old) {		int i; 		for (i = 0; i < old->max; i++) {			if (ovsl_dereference(old->masks[i]))				new->masks[new->count++] = old->masks[i];		}	} 	rcu_assign_pointer(tbl->mask_array, new);	kfree_rcu(old, rcu); 	return 0;} static int tbl_mask_array_add_mask(struct flow_table *tbl,				   struct sw_flow_mask *new){	struct mask_array *ma = ovsl_dereference(tbl->mask_array);	int err, ma_count = READ_ONCE(ma->count); 	if (ma_count >= ma->max) {		err = tbl_mask_array_realloc(tbl, ma->max +					      MASK_ARRAY_SIZE_MIN);		if (err)			return err; 		ma = ovsl_dereference(tbl->mask_array);	} 	BUG_ON(ovsl_dereference(ma->masks[ma_count])); 	rcu_assign_pointer(ma->masks[ma_count], new);	WRITE_ONCE(ma->count, ma_count +1); 	return 0;} static void tbl_mask_array_del_mask(struct flow_table *tbl,				    struct sw_flow_mask *mask){	struct mask_array *ma = ovsl_dereference(tbl->mask_array);	int i, ma_count = READ_ONCE(ma->count); 	/* Remove the deleted mask pointers from the array */	for (i = 0; i < ma_count; i++) {		if (mask == ovsl_dereference(ma->masks[i]))			goto found;	} 	BUG();	return; found:	WRITE_ONCE(ma->count, ma_count -1); 	rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]);	RCU_INIT_POINTER(ma->masks[ma_count -1], NULL); 	kfree_rcu(mask, rcu); 	/* Shrink the mask array if necessary. */	if (ma->max >= (MASK_ARRAY_SIZE_MIN * 2) &&	    ma_count <= (ma->max / 3))		tbl_mask_array_realloc(tbl, ma->max / 2);} /* Remove 'mask' from the mask list, if it is not needed any more. */static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask){	if (mask) {		/* ovs-lock is required to protect mask-refcount and		 * mask list.		 */		ASSERT_OVSL();		BUG_ON(!mask->ref_count);		mask->ref_count--; 		if (!mask->ref_count)			tbl_mask_array_del_mask(tbl, mask);	}} int ovs_flow_tbl_init(struct flow_table *table){	struct table_instance *ti, *ufid_ti;	struct mask_array *ma; 	table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) *					   MC_HASH_ENTRIES,					   __alignof__(struct mask_cache_entry));	if (!table->mask_cache)		return -ENOMEM; 	ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN);	if (!ma)		goto free_mask_cache; 	ti = table_instance_alloc(TBL_MIN_BUCKETS);	if (!ti)		goto free_mask_array; 	ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);	if (!ufid_ti)		goto free_ti; 	rcu_assign_pointer(table->ti, ti);	rcu_assign_pointer(table->ufid_ti, ufid_ti);	rcu_assign_pointer(table->mask_array, ma);	table->last_rehash = jiffies;	table->count = 0;	table->ufid_count = 0;	return 0; free_ti:	__table_instance_destroy(ti);free_mask_array:	kfree(ma);free_mask_cache:	free_percpu(table->mask_cache);	return -ENOMEM;} static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu){	struct table_instance *ti = container_of(rcu, struct table_instance, rcu); 	__table_instance_destroy(ti);} static void table_instance_flow_free(struct flow_table *table,				  struct table_instance *ti,				  struct table_instance *ufid_ti,				  struct sw_flow *flow,				  bool count){	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);	if (count)		table->count--; 	if (ovs_identifier_is_ufid(&flow->id)) {		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); 		if (count)			table->ufid_count--;	} 	flow_mask_remove(table, flow->mask);} static void table_instance_destroy(struct flow_table *table,				   struct table_instance *ti,				   struct table_instance *ufid_ti,				   bool deferred){	int i; 	if (!ti)		return; 	BUG_ON(!ufid_ti);	if (ti->keep_flows)		goto skip_flows; 	for (i = 0; i < ti->n_buckets; i++) {		struct sw_flow *flow;		struct hlist_head *head = &ti->buckets[i];		struct hlist_node *n; 		hlist_for_each_entry_safe(flow, n, head,					  flow_table.node[ti->node_ver]) { 			table_instance_flow_free(table, ti, ufid_ti,						 flow, false);			ovs_flow_free(flow, deferred);		}	} skip_flows:	if (deferred) {		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);		call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);	} else {		__table_instance_destroy(ti);		__table_instance_destroy(ufid_ti);	}} /* No need for locking this function is called from RCU callback or * error path. */void ovs_flow_tbl_destroy(struct flow_table *table){	struct table_instance *ti = rcu_dereference_raw(table->ti);	struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti); 	free_percpu(table->mask_cache);	kfree_rcu(rcu_dereference_raw(table->mask_array), rcu);	table_instance_destroy(table, ti, ufid_ti, false);} struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,				       u32 *bucket, u32 *last){	struct sw_flow *flow;	struct hlist_head *head;	int ver;	int i; 	ver = ti->node_ver;	while (*bucket < ti->n_buckets) {		i = 0;		head = &ti->buckets[*bucket];		hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {			if (i < *last) {				i++;				continue;			}			*last = i + 1;			return flow;		}		(*bucket)++;		*last = 0;	} 	return NULL;} static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash){	hash = jhash_1word(hash, ti->hash_seed);	return &ti->buckets[hash & (ti->n_buckets - 1)];} static void table_instance_insert(struct table_instance *ti,				  struct sw_flow *flow){	struct hlist_head *head; 	head = find_bucket(ti, flow->flow_table.hash);	hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);} static void ufid_table_instance_insert(struct table_instance *ti,				       struct sw_flow *flow){	struct hlist_head *head; 	head = find_bucket(ti, flow->ufid_table.hash);	hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);} static void flow_table_copy_flows(struct table_instance *old,				  struct table_instance *new, bool ufid){	int old_ver;	int i; 	old_ver = old->node_ver;	new->node_ver = !old_ver; 	/* Insert in new table. */	for (i = 0; i < old->n_buckets; i++) {		struct sw_flow *flow;		struct hlist_head *head = &old->buckets[i]; 		if (ufid)			hlist_for_each_entry_rcu(flow, head,						 ufid_table.node[old_ver],						 lockdep_ovsl_is_held())				ufid_table_instance_insert(new, flow);		else			hlist_for_each_entry_rcu(flow, head,						 flow_table.node[old_ver],						 lockdep_ovsl_is_held())				table_instance_insert(new, flow);	} 	old->keep_flows = true;} static struct table_instance *table_instance_rehash(struct table_instance *ti,						    int n_buckets, bool ufid){	struct table_instance *new_ti; 	new_ti = table_instance_alloc(n_buckets);	if (!new_ti)		return NULL; 	flow_table_copy_flows(ti, new_ti, ufid); 	return new_ti;} int ovs_flow_tbl_flush(struct flow_table *flow_table){	struct table_instance *old_ti, *new_ti;	struct table_instance *old_ufid_ti, *new_ufid_ti; 	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);	if (!new_ti)		return -ENOMEM;

Lines 1–500 of 968.