* [PATCH v3 net-next 08/12] inet: frags: use rhashtables for reassembly units
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.
It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)
A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.
This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.
Then there is the problem of sharing this hash table for all netns.
It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.
Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.
Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.
After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)
$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608
A followup patch will change the limits for 64bit arches.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
---
Documentation/networking/ip-sysctl.txt | 7 +-
include/net/inet_frag.h | 81 +++---
include/net/ipv6.h | 16 +-
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 93 +++----
net/ipv4/inet_fragment.c | 354 +++++-------------------
net/ipv4/ip_fragment.c | 112 ++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +---
net/ipv6/reassembly.c | 110 ++++----
9 files changed, 271 insertions(+), 579 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 33f35f049ad57ad6c06ed6e089966e346d72d108..6f2a3670e44b6662ce53c16cb7ca1e4f61274c15 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -134,13 +134,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
- Maximum memory used to reassemble IP fragments. When
- ipfrag_high_thresh bytes of memory is allocated for this purpose,
- the fragment handler will toss packets until ipfrag_low_thresh
- is reached. This also serves as a maximum limit to namespaces
- different from the initial one.
+ Maximum memory used to reassemble IP fragments.
ipfrag_low_thresh - INTEGER
+ (Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
The kernel still accepts new fragments for defragmentation.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 69e531ed81894393e07cac9e953825fcb55ef42a..3fec0d3a0d0186e98afb951784e1fe7329ba6d77 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -2,7 +2,11 @@
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
+#include <linux/rhashtable.h>
+
struct netns_frags {
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
@@ -26,12 +30,30 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
+struct frag_v4_compare_key {
+ __be32 saddr;
+ __be32 daddr;
+ u32 user;
+ u32 vif;
+ __be16 id;
+ u16 protocol;
+};
+
+struct frag_v6_compare_key {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 user;
+ __be32 id;
+ u32 iif;
+};
+
/**
* struct inet_frag_queue - fragment queue
*
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
* @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
* @fragments_tail: received fragments tail
@@ -41,12 +63,16 @@ enum {
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
- spinlock_t lock;
+ struct rhash_head node;
+ union {
+ struct frag_v4_compare_key v4;
+ struct frag_v6_compare_key v6;
+ } key;
struct timer_list timer;
- struct hlist_node list;
+ spinlock_t lock;
refcount_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments_tail;
@@ -55,51 +81,20 @@ struct inet_frag_queue {
int meat;
__u8 flags;
u16 max_size;
- struct netns_frags *net;
- struct hlist_node list_evictor;
-};
-
-#define INETFRAGS_HASHSZ 1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- * struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH 128
-
-struct inet_frag_bucket {
- struct hlist_head chain;
- spinlock_t chain_lock;
+ struct netns_frags *net;
+ struct rcu_head rcu;
};
struct inet_frags {
- struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
-
- struct work_struct frags_work;
- unsigned int next_bucket;
- unsigned long last_rebuild_jiffies;
- bool rebuild;
-
- /* The first call to hashfn is responsible to initialize
- * rnd. This is best done with net_get_random_once.
- *
- * rnd_seqlock is used to let hash insertion detect
- * when it needs to re-lookup the hash chain to use.
- */
- u32 rnd;
- seqlock_t rnd_seqlock;
unsigned int qsize;
- unsigned int (*hashfn)(const struct inet_frag_queue *);
- bool (*match)(const struct inet_frag_queue *q,
- const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
+ struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
@@ -108,15 +103,13 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
- return 0;
+ return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key, unsigned int hash);
-
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
@@ -128,7 +121,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
{
- return !hlist_unhashed(&q->list_evictor);
+ return false;
}
/* Memory Tracking Functions. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 57b7fe43d2ab8e0ef3d663b7a5ee201affd5ca1f..6fa9a2bc589665dfa9ce84813f33e5e86e12fd74 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -579,17 +579,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
-struct ip6_create_arg {
- __be32 id;
- u32 user;
- const struct in6_addr *src;
- const struct in6_addr *dst;
- int iif;
- u8 ecn;
-};
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
@@ -597,11 +588,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
- __be32 id; /* fragment id */
- u32 user;
- struct in6_addr saddr;
- struct in6_addr daddr;
-
int iif;
__u16 nhoffset;
u8 ecn;
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index d8de3bcfb1032a1133402cb2a4c50a2448133846..b8d95cb71c25dd69c8a88b2c886a3f0d2ce1174f 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -17,37 +17,19 @@ typedef unsigned __bitwise lowpan_rx_result;
#define LOWPAN_DISPATCH_FRAG1 0xc0
#define LOWPAN_DISPATCH_FRAGN 0xe0
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr *src;
- const struct ieee802154_addr *dst;
+ const struct ieee802154_addr src;
+ const struct ieee802154_addr dst;
};
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
*/
struct lowpan_frag_queue {
struct inet_frag_queue q;
-
- u16 tag;
- u16 d_size;
- struct ieee802154_addr saddr;
- struct ieee802154_addr daddr;
};
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
- switch (a->mode) {
- case IEEE802154_ADDR_LONG:
- return (((__force u64)a->extended_addr) >> 32) ^
- (((__force u64)a->extended_addr) & 0xffffffff);
- case IEEE802154_ADDR_SHORT:
- return (__force u32)(a->short_addr + (a->pan_id << 16));
- default:
- return 0;
- }
-}
-
int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
void lowpan_net_frag_exit(void);
int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index ddada12a044de293f904a1dc7a5ff398d089d101..dd743c287bc229b1ba354e834af7bec34dcb8643 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
struct sk_buff *prev, struct net_device *ldev);
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
- const struct ieee802154_addr *saddr,
- const struct ieee802154_addr *daddr)
-{
- net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
- return jhash_3words(ieee802154_addr_hash(saddr),
- ieee802154_addr_hash(daddr),
- (__force u32)(tag + (d_size << 16)),
- lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
- const struct lowpan_frag_queue *fq;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct lowpan_frag_queue *fq;
- const struct lowpan_create_arg *arg = a;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return fq->tag == arg->tag && fq->d_size == arg->d_size &&
- ieee802154_addr_equal(&fq->saddr, arg->src) &&
- ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
{
- const struct lowpan_create_arg *arg = a;
+ const struct frag_lowpan_compare_key *key = a;
struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
- fq->tag = arg->tag;
- fq->d_size = arg->d_size;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
+ BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+ memcpy(&q->key, key, sizeof(*key));
}
static void lowpan_frag_expire(struct timer_list *t)
@@ -105,21 +73,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
const struct ieee802154_addr *src,
const struct ieee802154_addr *dst)
{
+ struct netns_ieee802154_lowpan *ieee802154_lowpan =
+ net_ieee802154_lowpan(net);
+ struct frag_lowpan_compare_key key = {
+ .tag = cb->d_tag,
+ .d_size = cb->d_size,
+ .src = *src,
+ .dst = *dst,
+ };
struct inet_frag_queue *q;
- struct lowpan_create_arg arg;
- unsigned int hash;
- struct netns_ieee802154_lowpan *ieee802154_lowpan =
- net_ieee802154_lowpan(net);
- arg.tag = cb->d_tag;
- arg.d_size = cb->d_size;
- arg.src = src;
- arg.dst = dst;
-
- hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
-
- q = inet_frag_find(&ieee802154_lowpan->frags,
- &lowpan_frags, &arg, hash);
+ q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -611,17 +575,46 @@ static struct pernet_operations lowpan_frags_ops = {
.exit = lowpan_frags_exit_net,
};
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_lowpan_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params lowpan_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = lowpan_key_hashfn,
+ .obj_hashfn = lowpan_obj_hashfn,
+ .obj_cmpfn = lowpan_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int __init lowpan_net_frag_init(void)
{
int ret;
- lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
lowpan_frags.qsize = sizeof(struct frag_queue);
- lowpan_frags.match = lowpan_frag_match;
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+ lowpan_frags.rhash_params = lowpan_rhash_params;
ret = inet_frags_init(&lowpan_frags);
if (ret)
goto out;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 1ac69f65d0dee600d0ab4db20ff5942952932c40..ebb8f411e0db16478e861105b1926e97fbf07b06 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
-#define INETFRAGS_EVICT_BUCKETS 128
-#define INETFRAGS_EVICT_MAX 512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
};
EXPORT_SYMBOL(ip_frag_ecn_table);
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
- return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
- return time_after(jiffies,
- f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
- int i;
-
- write_seqlock_bh(&f->rnd_seqlock);
-
- if (!inet_frag_may_rebuild(f))
- goto out;
-
- get_random_bytes(&f->rnd, sizeof(u32));
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- struct hlist_node *n;
-
- hb = &f->hash[i];
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(q, n, &hb->chain, list) {
- unsigned int hval = inet_frag_hashfn(f, q);
-
- if (hval != i) {
- struct inet_frag_bucket *hb_dest;
-
- hlist_del(&q->list);
-
- /* Relink to new hash chain. */
- hb_dest = &f->hash[hval];
-
- /* This is the only place where we take
- * another chain_lock while already holding
- * one. As this will not run concurrently,
- * we cannot deadlock on hb_dest lock below, if its
- * already locked it will be released soon since
- * other caller cannot be waiting for hb lock
- * that we've taken above.
- */
- spin_lock_nested(&hb_dest->chain_lock,
- SINGLE_DEPTH_NESTING);
- hlist_add_head(&q->list, &hb_dest->chain);
- spin_unlock(&hb_dest->chain_lock);
- }
- }
- spin_unlock(&hb->chain_lock);
- }
-
- f->rebuild = false;
- f->last_rebuild_jiffies = jiffies;
-out:
- write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
- if (!hlist_unhashed(&q->list_evictor))
- return false;
-
- return q->net->low_thresh == 0 ||
- frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
- struct inet_frag_queue *fq;
- struct hlist_node *n;
- unsigned int evicted = 0;
- HLIST_HEAD(expired);
-
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
- if (!inet_fragq_should_evict(fq))
- continue;
-
- if (!del_timer(&fq->timer))
- continue;
-
- hlist_add_head(&fq->list_evictor, &expired);
- ++evicted;
- }
-
- spin_unlock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire(&fq->timer);
-
- return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
- unsigned int budget = INETFRAGS_EVICT_BUCKETS;
- unsigned int i, evicted = 0;
- struct inet_frags *f;
-
- f = container_of(work, struct inet_frags, frags_work);
-
- BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
- local_bh_disable();
-
- for (i = READ_ONCE(f->next_bucket); budget; --budget) {
- evicted += inet_evict_bucket(f, &f->hash[i]);
- i = (i + 1) & (INETFRAGS_HASHSZ - 1);
- if (evicted > INETFRAGS_EVICT_MAX)
- break;
- }
-
- f->next_bucket = i;
-
- local_bh_enable();
-
- if (f->rebuild && inet_frag_may_rebuild(f))
- inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
- if (unlikely(!work_pending(&f->frags_work)))
- schedule_work(&f->frags_work);
-}
-
int inet_frags_init(struct inet_frags *f)
{
- int i;
-
- INIT_WORK(&f->frags_work, inet_frag_worker);
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb = &f->hash[i];
-
- spin_lock_init(&hb->chain_lock);
- INIT_HLIST_HEAD(&hb->chain);
- }
-
- seqlock_init(&f->rnd_seqlock);
- f->last_rebuild_jiffies = 0;
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
@@ -214,79 +59,69 @@ EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
- cancel_work_sync(&f->frags_work);
+ /* We must wait that all inet_frag_destroy_rcu() have completed. */
+ rcu_barrier();
+
kmem_cache_destroy(f->frags_cachep);
+ f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
+static void inet_frags_free_cb(void *ptr, void *arg)
+{
+ struct inet_frag_queue *fq = ptr;
+
+ /* If we can not cancel the timer, it means this frag_queue
+ * is already disappearing, we have nothing to do.
+ * Otherwise, we own a refcount until the end of this function.
+ */
+ if (!del_timer(&fq->timer))
+ return;
+
+ spin_lock_bh(&fq->lock);
+ if (!(fq->flags & INET_FRAG_COMPLETE)) {
+ fq->flags |= INET_FRAG_COMPLETE;
+ refcount_dec(&fq->refcnt);
+ }
+ spin_unlock_bh(&fq->lock);
+
+ inet_frag_put(fq);
+}
+
void inet_frags_exit_net(struct netns_frags *nf)
{
- struct inet_frags *f =nf->f;
- unsigned int seq;
- int i;
+ nf->low_thresh = 0; /* prevent creation of new frags */
- nf->low_thresh = 0;
-
-evict_again:
- local_bh_disable();
- seq = read_seqbegin(&f->rnd_seqlock);
-
- for (i = 0; i < INETFRAGS_HASHSZ ; i++)
- inet_evict_bucket(f, &f->hash[i]);
-
- local_bh_enable();
- cond_resched();
-
- if (read_seqretry(&f->rnd_seqlock, seq) ||
- sum_frag_mem_limit(nf))
- goto evict_again;
+ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
EXPORT_SYMBOL(inet_frags_exit_net);
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
-{
- struct inet_frag_bucket *hb;
- unsigned int seq, hash;
-
- restart:
- seq = read_seqbegin(&f->rnd_seqlock);
-
- hash = inet_frag_hashfn(f, fq);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- if (read_seqretry(&f->rnd_seqlock, seq)) {
- spin_unlock(&hb->chain_lock);
- goto restart;
- }
-
- return hb;
-}
-
-static inline void fq_unlink(struct inet_frag_queue *fq)
-{
- struct inet_frag_bucket *hb;
-
- hb = get_frag_bucket_locked(fq, fq->net->f);
- hlist_del(&fq->list);
- fq->flags |= INET_FRAG_COMPLETE;
- spin_unlock(&hb->chain_lock);
-}
-
void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq);
+ struct netns_frags *nf = fq->net;
+
+ fq->flags |= INET_FRAG_COMPLETE;
+ rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+ struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+ rcu);
+ struct inet_frags *f = q->net->f;
+
+ if (f->destructor)
+ f->destructor(q);
+ kmem_cache_free(f->frags_cachep, q);
+}
+
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
@@ -310,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q)
}
sum = sum_truesize + f->qsize;
- if (f->destructor)
- f->destructor(q);
- kmem_cache_free(f->frags_cachep, q);
+ call_rcu(&q->rcu, inet_frag_destroy_rcu);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
- struct inet_frag_queue *qp_in,
- struct inet_frags *f,
- void *arg)
-{
- struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
- struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
- /* With SMP race we have to recheck hash table, because
- * such entry could have been created on other cpu before
- * we acquired hash bucket lock.
- */
- hlist_for_each_entry(qp, &hb->chain, list) {
- if (qp->net == nf && f->match(qp, arg)) {
- refcount_inc(&qp->refcnt);
- spin_unlock(&hb->chain_lock);
- qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in);
- return qp;
- }
- }
-#endif
- qp = qp_in;
- if (!mod_timer(&qp->timer, jiffies + nf->timeout))
- refcount_inc(&qp->refcnt);
-
- refcount_inc(&qp->refcnt);
- hlist_add_head(&qp->list, &hb->chain);
-
- spin_unlock(&hb->chain_lock);
-
- return qp;
-}
-
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
- inet_frag_schedule_worker(f);
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
return NULL;
- }
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
@@ -374,59 +170,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
- refcount_set(&q->refcnt, 1);
+ refcount_set(&q->refcnt, 3);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
- struct inet_frags *f,
void *arg)
{
+ struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
+ int err;
q = inet_frag_alloc(nf, f, arg);
if (!q)
return NULL;
- return inet_frag_intern(nf, q, f, arg);
+ mod_timer(&q->timer, jiffies + nf->timeout);
+
+ err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+ f->rhash_params);
+ if (err < 0) {
+ q->flags |= INET_FRAG_COMPLETE;
+ inet_frag_kill(q);
+ inet_frag_destroy(q);
+ return NULL;
+ }
+ return q;
}
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key,
- unsigned int hash)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- int depth = 0;
+ struct inet_frag_queue *fq;
- if (frag_mem_limit(nf) > nf->low_thresh)
- inet_frag_schedule_worker(f);
+ rcu_read_lock();
- hash &= (INETFRAGS_HASHSZ - 1);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- hlist_for_each_entry(q, &hb->chain, list) {
- if (q->net == nf && f->match(q, key)) {
- refcount_inc(&q->refcnt);
- spin_unlock(&hb->chain_lock);
- return q;
- }
- depth++;
- }
- spin_unlock(&hb->chain_lock);
-
- if (depth <= INETFRAGS_MAXDEPTH)
- return inet_frag_create(nf, f, key);
-
- if (inet_frag_may_rebuild(f)) {
- if (!f->rebuild)
- f->rebuild = true;
- inet_frag_schedule_worker(f);
+ fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+ if (fq) {
+ if (!refcount_inc_not_zero(&fq->refcnt))
+ fq = NULL;
+ rcu_read_unlock();
+ return fq;
}
+ rcu_read_unlock();
- return ERR_PTR(-ENOBUFS);
+ return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
@@ -434,8 +223,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix)
{
static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
- ". Dropping fragment.\n";
+ " list length grew over limit. Dropping fragment.\n";
if (PTR_ERR(q) == -ENOBUFS)
net_dbg_ratelimited("%s%s", prefix, msg);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1a3bc85d6f5ea8f36b8f3d221cad632906b317a2..4021820db6f291b255cc53aeca91dd74aef29934 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -69,15 +69,9 @@ struct ipfrag_skb_cb
struct ipq {
struct inet_frag_queue q;
- u32 user;
- __be32 saddr;
- __be32 daddr;
- __be16 id;
- u8 protocol;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
- int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
@@ -97,41 +91,6 @@ int ip_frag_mem(struct net *net)
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
-struct ip4_create_arg {
- struct iphdr *iph;
- u32 user;
- int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
- net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
- return jhash_3words((__force u32)id << 16 | prot,
- (__force u32)saddr, (__force u32)daddr,
- ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
- const struct ipq *ipq;
-
- ipq = container_of(q, struct ipq, q);
- return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct ipq *qp;
- const struct ip4_create_arg *arg = a;
-
- qp = container_of(q, struct ipq, q);
- return qp->id == arg->iph->id &&
- qp->saddr == arg->iph->saddr &&
- qp->daddr == arg->iph->daddr &&
- qp->protocol == arg->iph->protocol &&
- qp->user == arg->user &&
- qp->vif == arg->vif;
-}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
@@ -140,17 +99,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
- const struct ip4_create_arg *arg = a;
+ const struct frag_v4_compare_key *key = a;
- qp->protocol = arg->iph->protocol;
- qp->id = arg->iph->id;
- qp->ecn = ip4_frag_ecn(arg->iph->tos);
- qp->saddr = arg->iph->saddr;
- qp->daddr = arg->iph->daddr;
- qp->vif = arg->vif;
- qp->user = arg->user;
+ q->key.v4 = *key;
+ qp->ecn = 0;
qp->peer = q->net->max_dist ?
- inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+ inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
@@ -234,7 +188,7 @@ static void ip_expire(struct timer_list *t)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
- if (frag_expire_skip_icmp(qp->user) &&
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
@@ -262,17 +216,17 @@ static void ip_expire(struct timer_list *t)
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
+ struct frag_v4_compare_key key = {
+ .saddr = iph->saddr,
+ .daddr = iph->daddr,
+ .user = user,
+ .vif = vif,
+ .id = iph->id,
+ .protocol = iph->protocol,
+ };
struct inet_frag_queue *q;
- struct ip4_create_arg arg;
- unsigned int hash;
- arg.iph = iph;
- arg.user = user;
- arg.vif = vif;
-
- hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
- q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv4.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -656,7 +610,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
err = -ENOMEM;
goto out_fail;
out_oversize:
- net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+ net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
@@ -894,15 +848,47 @@ static struct pernet_operations ip4_frags_ops = {
.exit = ipv4_frags_exit_net,
};
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v4,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v4_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .key_offset = offsetof(struct inet_frag_queue, key),
+ .key_len = sizeof(struct frag_v4_compare_key),
+ .hashfn = ip4_key_hashfn,
+ .obj_hashfn = ip4_obj_hashfn,
+ .obj_cmpfn = ip4_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
void __init ipfrag_init(void)
{
- ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
- ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
+ ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c4b40fdee838300f3723cece1e6b5b9d03fa9249..0ad3df551d9884ba30f2d40658ee81a61720e947 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -152,23 +152,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *nq;
-
- nq = container_of(q, struct frag_queue, q);
- return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
static void nf_ct_frag6_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -182,26 +165,19 @@ static void nf_ct_frag6_expire(struct timer_list *t)
}
/* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
- u32 user, struct in6_addr *src,
- struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+ const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = user,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = user;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
-
- local_bh_disable();
- hash = nf_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
- local_bh_enable();
+ q = inet_frag_find(&net->nf_frag.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -593,8 +569,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
fhdr = (struct frag_hdr *)skb_transport_header(skb);
skb_orphan(skb);
- fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ fq = fq_find(net, fhdr->identification, user, hdr,
+ skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
return -ENOMEM;
@@ -660,13 +636,12 @@ int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.hashfn = nf_hashfn;
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
- nf_frags.match = ip6_frag_match;
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
+ nf_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f0071b113a92fcff15ac57610170c12b17cb59ba..3fc853e4492abb109062d662296c0b470763042a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *fq;
-
- fq = container_of(q, struct frag_queue, q);
- return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct frag_queue *fq;
- const struct ip6_create_arg *arg = a;
-
- fq = container_of(q, struct frag_queue, q);
- return fq->id == arg->id &&
- fq->user == arg->user &&
- ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst) &&
- (arg->iif == fq->iif ||
- !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
- IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct ip6_create_arg *arg = a;
+ const struct frag_v6_compare_key *key = a;
- fq->id = arg->id;
- fq->user = arg->user;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
- fq->ecn = arg->ecn;
+ q->key.v6 = *key;
+ fq->ecn = 0;
}
EXPORT_SYMBOL(ip6_frag_init);
@@ -182,23 +143,22 @@ static void ip6_frag_expire(struct timer_list *t)
}
static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = IP6_DEFRAG_LOCAL_DELIVER,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = IP6_DEFRAG_LOCAL_DELIVER;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
- hash = inet6_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv6.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -530,6 +490,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
@@ -558,13 +519,14 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ iif = skb->dev ? skb->dev->ifindex : 0;
+ fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
int ret;
spin_lock(&fq->q.lock);
+ fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
@@ -738,17 +700,47 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6_key_hashfn,
+ .obj_hashfn = ip6_obj_hashfn,
+ .obj_cmpfn = ip6_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
- ip6_frags.match = ip6_frag_match;
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
+ ip6_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&ip6_frags);
if (ret)
goto out;
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 07/12] rhashtable: add schedule points
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
Rehashing and destroying large hash table takes a lot of time,
and happens in process context. It is safe to add cond_resched()
in rhashtable_rehash_table() and rhashtable_free_and_destroy()
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
lib/rhashtable.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 47de025b624520f75e521bef46dc9b28baa6a1a0..2b2b79974b614a94e5325e8c2271804cb27069aa 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -333,6 +333,7 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
err = rhashtable_rehash_chain(ht, old_hash);
if (err)
return err;
+ cond_resched();
}
/* Publish the new table pointer. */
@@ -1112,6 +1113,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
for (i = 0; i < tbl->size; i++) {
struct rhash_head *pos, *next;
+ cond_resched();
for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL;
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 06/12] inet: frags: refactor ipfrag_init()
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
We need to call inet_frags_init() before register_pernet_subsys(),
as a prereq for following patch ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/ip_fragment.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cd2b4c9419fc1552d367b572926e314b11cb6c00..1a3bc85d6f5ea8f36b8f3d221cad632906b317a2 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -896,8 +896,6 @@ static struct pernet_operations ip4_frags_ops = {
void __init ipfrag_init(void)
{
- ip4_frags_ctl_register();
- register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
@@ -907,4 +905,6 @@ void __init ipfrag_init(void)
ip4_frags.frags_cache_name = ip_frag_cache_name;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
+ ip4_frags_ctl_register();
+ register_pernet_subsys(&ip4_frags_ops);
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 05/12] inet: frags: refactor lowpan_net_frag_init()
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
We want to call lowpan_net_frag_init() earlier.
Similar to commit "inet: frags: refactor ipv6_frag_init()"
This is a prereq to "inet: frags: use rhashtables for reassembly units"
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ieee802154/6lowpan/reassembly.c | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 6badc055555b7baedac2051a1aaea15f9e9b180c..ddada12a044de293f904a1dc7a5ff398d089d101 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -615,14 +615,6 @@ int __init lowpan_net_frag_init(void)
{
int ret;
- ret = lowpan_frags_sysctl_register();
- if (ret)
- return ret;
-
- ret = register_pernet_subsys(&lowpan_frags_ops);
- if (ret)
- goto err_pernet;
-
lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
@@ -631,12 +623,22 @@ int __init lowpan_net_frag_init(void)
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
ret = inet_frags_init(&lowpan_frags);
+ if (ret)
+ goto out;
+
+ ret = lowpan_frags_sysctl_register();
+ if (ret)
+ goto err_sysctl;
+
+ ret = register_pernet_subsys(&lowpan_frags_ops);
if (ret)
goto err_pernet;
-
+out:
return ret;
err_pernet:
lowpan_frags_sysctl_unregister();
+err_sysctl:
+ inet_frags_fini(&lowpan_frags);
return ret;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 04/12] inet: frags: refactor ipv6_frag_init()
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
We want to call inet_frags_init() earlier.
This is a prereq to "inet: frags: use rhashtables for reassembly units"
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/reassembly.c | 27 +++++++++++++++------------
1 file changed, 15 insertions(+), 12 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 4855de6f673a4753526679ca29dcdaebecb5777f..f0071b113a92fcff15ac57610170c12b17cb59ba 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -742,18 +742,6 @@ int __init ipv6_frag_init(void)
{
int ret;
- ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
- if (ret)
- goto out;
-
- ret = ip6_frags_sysctl_register();
- if (ret)
- goto err_sysctl;
-
- ret = register_pernet_subsys(&ip6_frags_ops);
- if (ret)
- goto err_pernet;
-
ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
@@ -762,8 +750,21 @@ int __init ipv6_frag_init(void)
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
ret = inet_frags_init(&ip6_frags);
+ if (ret)
+ goto out;
+
+ ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ if (ret)
+ goto err_protocol;
+
+ ret = ip6_frags_sysctl_register();
+ if (ret)
+ goto err_sysctl;
+
+ ret = register_pernet_subsys(&ip6_frags_ops);
if (ret)
goto err_pernet;
+
out:
return ret;
@@ -771,6 +772,8 @@ int __init ipv6_frag_init(void)
ip6_frags_sysctl_unregister();
err_sysctl:
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+err_protocol:
+ inet_frags_fini(&ip6_frags);
goto out;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 03/12] inet: frags: add a pointer to struct netns_frags
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
In order to simplify the API, add a pointer to struct inet_frags.
This will allow us to make things less complex.
These functions no longer have a struct inet_frags parameter :
inet_frag_destroy(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_put(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_kill(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frags_exit_net(struct netns_frags *nf /*, struct inet_frags *f */)
ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 11 ++++++-----
include/net/ipv6.h | 3 +--
net/ieee802154/6lowpan/reassembly.c | 13 +++++++------
net/ipv4/inet_fragment.c | 17 ++++++++++-------
net/ipv4/ip_fragment.c | 9 +++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 16 +++++++++-------
net/ipv6/reassembly.c | 20 ++++++++++----------
7 files changed, 48 insertions(+), 41 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index b1d62176f3b4fcf100bd263e8eae0db656a3d9b6..69e531ed81894393e07cac9e953825fcb55ef42a 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -10,6 +10,7 @@ struct netns_frags {
int high_thresh;
int low_thresh;
int max_dist;
+ struct inet_frags *f;
};
/**
@@ -109,20 +110,20 @@ static inline int inet_frags_init_net(struct netns_frags *nf)
atomic_set(&nf->mem, 0);
return 0;
}
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key, unsigned int hash);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
{
if (refcount_dec_and_test(&q->refcnt))
- inet_frag_destroy(q, f);
+ inet_frag_destroy(q);
}
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 5c18836672e9d1c560cdce15f5b34928c337abfd..57b7fe43d2ab8e0ef3d663b7a5ee201affd5ca1f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -607,8 +607,7 @@ struct frag_queue {
u8 ecn;
};
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 2aaab4bba42961647a4d3d1c0b8497917d5065ce..6badc055555b7baedac2051a1aaea15f9e9b180c 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -94,10 +94,10 @@ static void lowpan_frag_expire(struct timer_list *t)
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
}
static inline struct lowpan_frag_queue *
@@ -230,7 +230,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
struct sk_buff *fp, *head = fq->q.fragments;
int sum_truesize;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
/* Make the one we just received the head. */
if (prev) {
@@ -438,7 +438,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
ret = lowpan_frag_queue(fq, skb, frag_type);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -586,13 +586,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+ ieee802154_lowpan->frags.f = &lowpan_frags;
res = inet_frags_init_net(&ieee802154_lowpan->frags);
if (res < 0)
return res;
res = lowpan_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
return res;
}
@@ -602,7 +603,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
net_ieee802154_lowpan(net);
lowpan_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
}
static struct pernet_operations lowpan_frags_ops = {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index e8ec28999f5ce0c5d496e9a97ca1748b18db0cf0..1ac69f65d0dee600d0ab4db20ff5942952932c40 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -219,8 +219,9 @@ void inet_frags_fini(struct inet_frags *f)
}
EXPORT_SYMBOL(inet_frags_fini);
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
{
+ struct inet_frags *f =nf->f;
unsigned int seq;
int i;
@@ -264,33 +265,34 @@ __acquires(hb->chain_lock)
return hb;
}
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+static inline void fq_unlink(struct inet_frag_queue *fq)
{
struct inet_frag_bucket *hb;
- hb = get_frag_bucket_locked(fq, f);
+ hb = get_frag_bucket_locked(fq, fq->net->f);
hlist_del(&fq->list);
fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq, f);
+ fq_unlink(fq);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
struct netns_frags *nf;
unsigned int sum, sum_truesize = 0;
+ struct inet_frags *f;
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
@@ -298,6 +300,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
/* Release all fragment data. */
fp = q->fragments;
nf = q->net;
+ f = nf->f;
while (fp) {
struct sk_buff *xp = fp->next;
@@ -333,7 +336,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
refcount_inc(&qp->refcnt);
spin_unlock(&hb->chain_lock);
qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in, f);
+ inet_frag_put(qp_in);
return qp;
}
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e0b39d4ecbd411ff4bb72d1ed973e45bd6da9ef1..cd2b4c9419fc1552d367b572926e314b11cb6c00 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -168,7 +168,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
static void ipq_put(struct ipq *ipq)
{
- inet_frag_put(&ipq->q, &ip4_frags);
+ inet_frag_put(&ipq->q);
}
/* Kill ipq entry. It is not destroyed immediately,
@@ -176,7 +176,7 @@ static void ipq_put(struct ipq *ipq)
*/
static void ipq_kill(struct ipq *ipq)
{
- inet_frag_kill(&ipq->q, &ip4_frags);
+ inet_frag_kill(&ipq->q);
}
static bool frag_expire_skip_icmp(u32 user)
@@ -872,20 +872,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.timeout = IP_FRAG_TIME;
net->ipv4.frags.max_dist = 64;
+ net->ipv4.frags.f = &ip4_frags;
res = inet_frags_init_net(&net->ipv4.frags);
if (res < 0)
return res;
res = ip4_frags_ns_ctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
{
ip4_frags_ns_ctl_unregister(net);
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
}
static struct pernet_operations ip4_frags_ops = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6ff41569134ae36809a8b42d8e46d50d19ffde53..c4b40fdee838300f3723cece1e6b5b9d03fa9249 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,7 +178,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6_expire_frag_queue(net, fq, &nf_frags);
+ ip6_expire_frag_queue(net, fq);
}
/* Creation primitives. */
@@ -264,7 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
* this case. -DaveM
*/
pr_debug("end of fragment not rounded to 8 bytes.\n");
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
return -EPROTO;
}
if (end > fq->q.len) {
@@ -357,7 +357,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
return 0;
discard_fq:
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
err:
return -EINVAL;
}
@@ -379,7 +379,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
int payload_len;
u8 ecn;
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
WARN_ON(head == NULL);
WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -622,7 +622,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
out_unlock:
spin_unlock_bh(&fq->q.lock);
- inet_frag_put(&fq->q, &nf_frags);
+ inet_frag_put(&fq->q);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
@@ -634,19 +634,21 @@ static int nf_ct_net_init(struct net *net)
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->nf_frag.frags.f = &nf_frags;
+
res = inet_frags_init_net(&net->nf_frag.frags);
if (res < 0)
return res;
res = nf_ct_frag6_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
return res;
}
static void nf_ct_net_exit(struct net *net)
{
nf_ct_frags6_sysctl_unregister(net);
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
}
static struct pernet_operations nf_ct_net_ops = {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index a8f7a5f0251a7af0b14cc6de5006b924d9d05672..4855de6f673a4753526679ca29dcdaebecb5777f 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -128,8 +128,7 @@ void ip6_frag_init(struct inet_frag_queue *q, const void *a)
}
EXPORT_SYMBOL(ip6_frag_init);
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
@@ -138,7 +137,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, frags);
+ inet_frag_kill(&fq->q);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
@@ -166,7 +165,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
rcu_read_unlock();
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, frags);
+ inet_frag_put(&fq->q);
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
@@ -179,7 +178,7 @@ static void ip6_frag_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6_expire_frag_queue(net, fq, &ip6_frags);
+ ip6_expire_frag_queue(net, fq);
}
static struct frag_queue *
@@ -364,7 +363,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
return -1;
discard_fq:
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
err:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
@@ -391,7 +390,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
int sum_truesize;
u8 ecn;
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
@@ -569,7 +568,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &ip6_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -716,6 +715,7 @@ static int __net_init ipv6_frags_init_net(struct net *net)
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->ipv6.frags.f = &ip6_frags;
res = inet_frags_init_net(&net->ipv6.frags);
if (res < 0)
@@ -723,14 +723,14 @@ static int __net_init ipv6_frags_init_net(struct net *net)
res = ip6_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
}
static struct pernet_operations ip6_frags_ops = {
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 02/12] inet: frags: change inet_frags_init_net() return value
From: Eric Dumazet @ 2018-03-31 0:52 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
We will soon initialize one rhashtable per struct netns_frags
in inet_frags_init_net().
This patch changes the return value to eventually propagate an
error.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 3 ++-
net/ieee802154/6lowpan/reassembly.c | 11 ++++++++---
net/ipv4/ip_fragment.c | 12 +++++++++---
net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++++++++---
net/ipv6/reassembly.c | 11 +++++++++--
5 files changed, 37 insertions(+), 12 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 351f0c3cdcd9df16078a40f07963fb605eeaa882..b1d62176f3b4fcf100bd263e8eae0db656a3d9b6 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -104,9 +104,10 @@ struct inet_frags {
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
+ return 0;
}
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 85bf86ad6b1801066a4252af18b5b511070a9e08..2aaab4bba42961647a4d3d1c0b8497917d5065ce 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -581,14 +581,19 @@ static int __net_init lowpan_frags_init_net(struct net *net)
{
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
+ int res;
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&ieee802154_lowpan->frags);
-
- return lowpan_frags_ns_sysctl_register(net);
+ res = inet_frags_init_net(&ieee802154_lowpan->frags);
+ if (res < 0)
+ return res;
+ res = lowpan_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ return res;
}
static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbf1b94942c0ed53d1ddb87e4ee63833c08f2684..e0b39d4ecbd411ff4bb72d1ed973e45bd6da9ef1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -846,6 +846,8 @@ static void __init ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
+ int res;
+
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
@@ -871,9 +873,13 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.max_dist = 64;
- inet_frags_init_net(&net->ipv4.frags);
-
- return ip4_frags_ns_ctl_register(net);
+ res = inet_frags_init_net(&net->ipv4.frags);
+ if (res < 0)
+ return res;
+ res = ip4_frags_ns_ctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b84ce3e6d728a5b8af65b91faf42ec640ff03910..6ff41569134ae36809a8b42d8e46d50d19ffde53 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -629,12 +629,18 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
static int nf_ct_net_init(struct net *net)
{
+ int res;
+
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->nf_frag.frags);
-
- return nf_ct_frag6_sysctl_register(net);
+ res = inet_frags_init_net(&net->nf_frag.frags);
+ if (res < 0)
+ return res;
+ res = nf_ct_frag6_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ return res;
}
static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 08a139f14d0f6fa8ca326088cce1144411e09bf5..a8f7a5f0251a7af0b14cc6de5006b924d9d05672 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -711,13 +711,20 @@ static void ip6_frags_sysctl_unregister(void)
static int __net_init ipv6_frags_init_net(struct net *net)
{
+ int res;
+
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->ipv6.frags);
+ res = inet_frags_init_net(&net->ipv6.frags);
+ if (res < 0)
+ return res;
- return ip6_frags_ns_sysctl_register(net);
+ res = ip6_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 01/12] ipv6: frag: remove unused field
From: Eric Dumazet @ 2018-03-31 0:52 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
csum field in struct frag_queue is not used, remove it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/ipv6.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 50a6f0ddb8780f6c9169f4ae0b3b35af2d66cd4b..5c18836672e9d1c560cdce15f5b34928c337abfd 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -603,7 +603,6 @@ struct frag_queue {
struct in6_addr daddr;
int iif;
- unsigned int csum;
__u16 nhoffset;
u8 ecn;
};
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 00/12] inet: frags: bring rhashtables to IP defrag
From: Eric Dumazet @ 2018-03-31 0:52 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
IP defrag processing is one of the remaining problematic layer in linux.
It uses static hash tables of 1024 buckets, and up to 128 items per bucket.
A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.
This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.
Then there is the problem of sharing this hash table for all netns.
It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.
Lookup is now using RCU, and 64bit hosts can now provision whatever amount
of memory needed to handle the expected workloads.
v2: Addressed Herbert and Kirill feedbacks
(Use rhashtable_free_and_destroy(), and split the big patch into small units)
v3: Removed the extra add_frag_mem_limit(...) from inet_frag_create()
Removed the refcount_inc_not_zero() call from inet_frags_free_cb(),
as we can exploit del_timer() return value.
Eric Dumazet (12):
ipv6: frag: remove unused field
inet: frags: change inet_frags_init_net() return value
inet: frags: add a pointer to struct netns_frags
inet: frags: refactor ipv6_frag_init()
inet: frags: refactor lowpan_net_frag_init()
inet: frags: refactor ipfrag_init()
rhashtable: add schedule points
inet: frags: use rhashtables for reassembly units
inet: frags: remove some helpers
inet: frags: get rif of inet_frag_evicting()
inet: frags: remove inet_frag_maybe_warn_overflow()
inet: frags: break the 2GB limit for frags storage
Documentation/networking/ip-sysctl.txt | 11 +-
include/net/inet_frag.h | 123 ++++----
include/net/ip.h | 1 -
include/net/ipv6.h | 27 +-
lib/rhashtable.c | 2 +
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 150 +++++-----
net/ipv4/inet_fragment.c | 362 +++++-------------------
net/ipv4/ip_fragment.c | 214 +++++++-------
net/ipv4/proc.c | 6 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 90 +++---
net/ipv6/proc.c | 5 +-
net/ipv6/reassembly.c | 181 ++++++------
13 files changed, 442 insertions(+), 756 deletions(-)
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply
* [net-next 14/15] net/mlx5e: Keep single pre-initialized UMR WQE per RQ
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
All UMR WQEs of an RQ share many common fields. We use
pre-initialized structures to save calculations in datapath.
One field (xlt_offset) was the only reason we saved a pre-initialized
copy per WQE index.
Here we remove its initialization (move its calculation to datapath),
and reduce the number of copies to one-per-RQ.
A very small datapath calculation is added, it occurs once per a MPWQE
(i.e. once every 256KB), but reduces memory consumption and gives
better cache utilization.
Performance testing:
Tested packet rate, no degradation sensed.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 8 ++------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 20 ++++++++------------
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +++-
3 files changed, 13 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5853de4e4fc7..30cad07be2b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -84,6 +84,7 @@
#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS))
#define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS)
#define MLX5E_MAX_RQ_NUM_MTTS \
((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
@@ -450,7 +451,6 @@ struct mlx5e_wqe_frag_info {
struct mlx5e_umr_dma_info {
struct mlx5e_dma_info dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
- struct mlx5e_umr_wqe wqe;
};
struct mlx5e_mpw_info {
@@ -496,6 +496,7 @@ struct mlx5e_rq {
};
} wqe;
struct {
+ struct mlx5e_umr_wqe umr_wqe;
struct mlx5e_mpw_info *info;
mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
u16 num_strides;
@@ -978,11 +979,6 @@ static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
}
-static inline u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix)
-{
- return wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
-}
-
extern const struct ethtool_ops mlx5e_ethtool_ops;
#ifdef CONFIG_MLX5_CORE_EN_DCB
extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b03a2327356a..0339609cfa56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -306,13 +306,11 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
struct mlx5e_icosq *sq,
- struct mlx5e_umr_wqe *wqe,
- u16 ix)
+ struct mlx5e_umr_wqe *wqe)
{
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
u8 ds_cnt = DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_DS);
- u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix);
cseg->qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
ds_cnt);
@@ -322,8 +320,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
ucseg->xlt_octowords =
cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
- ucseg->bsf_octowords =
- cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
}
@@ -331,18 +327,13 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
struct mlx5e_channel *c)
{
int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
- int i;
rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->mpwqe.info)
return -ENOMEM;
- for (i = 0; i < wq_sz; i++) {
- struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
- mlx5e_build_umr_wqe(rq, &c->icosq, &wi->umr.wqe, i);
- }
+ mlx5e_build_umr_wqe(rq, &c->icosq, &rq->mpwqe.umr_wqe);
return 0;
}
@@ -388,6 +379,11 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
}
+static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+{
+ return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+}
+
static int mlx5e_alloc_rq(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_rq_param *rqp,
@@ -520,7 +516,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
- u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT;
+ u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9bb47a6d40f1..682f9ff9da34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -373,6 +373,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_umr_wqe *umr_wqe;
int cpy = offsetof(struct mlx5e_umr_wqe, inline_mtts);
+ u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
int err;
u16 pi;
int i;
@@ -384,7 +385,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
}
umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- memcpy(umr_wqe, &wi->umr.wqe, cpy);
+ memcpy(umr_wqe, &rq->mpwqe.umr_wqe, cpy);
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
err = mlx5e_page_alloc_mapped(rq, dma_info);
if (unlikely(err))
@@ -400,6 +401,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
umr_wqe->ctrl.opmod_idx_opcode =
cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
MLX5_OPCODE_UMR);
+ umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->pc += MLX5E_UMR_WQEBBS;
--
2.14.3
^ permalink raw reply related
* [net-next 15/15] net/mlx5e: RX, Recycle buffer of UMR WQEs
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Upon a new UMR post, check if the WQE buffer contains
a previous UMR WQE. If so, modify the dynamic fields
instead of a whole WQE overwrite. This saves a memcpy.
In current setting, after 2 WQ cycles (12 UMR posts),
this will always be the case.
No degradation sensed.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 682f9ff9da34..176645762e49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -365,6 +365,11 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
mlx5_wq_ll_update_db_record(wq);
}
+static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
+{
+ return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+}
+
static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
@@ -372,7 +377,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_umr_wqe *umr_wqe;
- int cpy = offsetof(struct mlx5e_umr_wqe, inline_mtts);
u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
int err;
u16 pi;
@@ -385,7 +389,10 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
}
umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- memcpy(umr_wqe, &rq->mpwqe.umr_wqe, cpy);
+ if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2))
+ memcpy(umr_wqe, &rq->mpwqe.umr_wqe,
+ offsetof(struct mlx5e_umr_wqe, inline_mtts));
+
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
err = mlx5e_page_alloc_mapped(rq, dma_info);
if (unlikely(err))
--
2.14.3
^ permalink raw reply related
* [net-next 13/15] net/mlx5e: Remove page_ref bulking in Striding RQ
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
When many packets reside on the same page, the bulking of
page_ref modifications reduces the total number of atomic
operations executed.
Besides the necessary 2 operations on page alloc/free, we
have the following extra ops per page:
- one on WQE allocation (bump refcnt to maximum possible),
- zero ops for SKBs,
- one on WQE free,
a constant of two operations in total, no matter how many
packets/SKBs actually populate the page.
Without this bulking, we have:
- no ops on WQE allocation or free,
- one op per SKB,
Comparing the two methods when PAGE_SIZE is 4K:
- As mentioned above, bulking method always executes 2 operations,
not more, but not less.
- In the default MTU configuration (1500, stride size is 2K),
the non-bulking method execute 2 ops as well.
- For larger MTUs with stride size of 4K, non-bulking method
executes only a single op.
- For XDP (stride size of 4K, no SKBs), non-bulking method
executes no ops at all!
Hence, to optimize the flows with linear SKB and XDP over Striding RQ,
we here remove the page_ref bulking method.
Performance testing:
ConnectX-5, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz.
Single core packet rate (64 bytes).
Early drop in TC: no degradation.
XDP_DROP:
before: 14,270,188 pps
after: 20,503,603 pps, 43% improvement.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 -
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 47 +++++++++----------------
2 files changed, 16 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 7997d7c159db..5853de4e4fc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -456,7 +456,6 @@ struct mlx5e_umr_dma_info {
struct mlx5e_mpw_info {
struct mlx5e_umr_dma_info umr;
u16 consumed_strides;
- u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
DECLARE_BITMAP(xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1da79cab1838..9bb47a6d40f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -296,37 +296,28 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
mlx5e_free_rx_wqe(rq, wi);
}
-static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
-{
- return rq->mpwqe.num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
-}
-
static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
struct sk_buff *skb,
- struct mlx5e_mpw_info *wi,
- u32 page_idx, u32 frag_offset,
- u32 len)
+ struct mlx5e_dma_info *di,
+ u32 frag_offset, u32 len)
{
unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz));
dma_sync_single_for_cpu(rq->pdev,
- wi->umr.dma_info[page_idx].addr + frag_offset,
+ di->addr + frag_offset,
len, DMA_FROM_DEVICE);
- wi->skbs_frags[page_idx]++;
+ page_ref_inc(di->page);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- wi->umr.dma_info[page_idx].page, frag_offset,
- len, truesize);
+ di->page, frag_offset, len, truesize);
}
static inline void
mlx5e_copy_skb_header_mpwqe(struct device *pdev,
struct sk_buff *skb,
- struct mlx5e_mpw_info *wi,
- u32 page_idx, u32 offset,
- u32 headlen)
+ struct mlx5e_dma_info *dma_info,
+ u32 offset, u32 headlen)
{
u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
- struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[page_idx];
unsigned int len;
/* Aligning len to sizeof(long) optimizes memcpy performance */
@@ -351,15 +342,12 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
{
const bool no_xdp_xmit =
bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
- int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
int i;
- for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
- page_ref_sub(dma_info[i].page, pg_strides - wi->skbs_frags[i]);
+ for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
mlx5e_page_release(rq, &dma_info[i], true);
- }
}
static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
@@ -380,7 +368,6 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
- int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
@@ -403,10 +390,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
if (unlikely(err))
goto err_unmap;
umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
- page_ref_add(dma_info->page, pg_strides);
}
- memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
bitmap_zero(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
wi->consumed_strides = 0;
@@ -425,7 +410,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
err_unmap:
while (--i >= 0) {
dma_info--;
- page_ref_sub(dma_info->page, pg_strides);
mlx5e_page_release(rq, dma_info, true);
}
rq->stats.buff_alloc_err++;
@@ -987,9 +971,10 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
u16 cqe_bcnt, u32 head_offset, u32 page_idx)
{
u16 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt);
+ struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
u32 frag_offset = head_offset + headlen;
- u16 byte_cnt = cqe_bcnt - headlen;
- u32 head_page_idx = page_idx;
+ u32 byte_cnt = cqe_bcnt - headlen;
+ struct mlx5e_dma_info *head_di = di;
struct sk_buff *skb;
skb = napi_alloc_skb(rq->cq.napi,
@@ -1002,7 +987,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
prefetchw(skb->data);
if (unlikely(frag_offset >= PAGE_SIZE)) {
- page_idx++;
+ di++;
frag_offset -= PAGE_SIZE;
}
@@ -1010,14 +995,14 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
u32 pg_consumed_bytes =
min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
- mlx5e_add_skb_frag_mpwqe(rq, skb, wi, page_idx, frag_offset,
+ mlx5e_add_skb_frag_mpwqe(rq, skb, di, frag_offset,
pg_consumed_bytes);
byte_cnt -= pg_consumed_bytes;
frag_offset = 0;
- page_idx++;
+ di++;
}
/* copy header */
- mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, wi, head_page_idx,
+ mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, head_di,
head_offset, headlen);
/* skb linear part was allocated with headlen and aligned to long */
skb->tail += headlen;
@@ -1060,7 +1045,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
return NULL;
/* queue up for recycling/reuse */
- wi->skbs_frags[page_idx]++;
+ page_ref_inc(di->page);
return skb;
}
--
2.14.3
^ permalink raw reply related
* [net-next 12/15] net/mlx5e: Support XDP over Striding RQ
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Add XDP support over Striding RQ.
Now that linear SKB is supported over Striding RQ,
we can support XDP by setting stride size to PAGE_SIZE
and headroom to XDP_PACKET_HEADROOM.
Upon a MPWQE free, do not release pages that are being
XDP xmit, they will be released upon completions.
Striding RQ is capable of a higher packet-rate than
conventional RQ.
A performance gain is expected for all cases that had
a HW packet-rate bottleneck. This is the case whenever
using many flows that distribute to many cores.
Performance testing:
ConnectX-5, 24 rings, default MTU.
CQE compression ON (to reduce completions BW in PCI).
XDP_DROP packet rate:
--------------------------------------------------
| pkt size | XDP rate | 100GbE linerate | pct% |
--------------------------------------------------
| 64byte | 126.2 Mpps | 148.0 Mpps | 85% |
| 128byte | 80.0 Mpps | 84.8 Mpps | 94% |
| 256byte | 42.7 Mpps | 42.7 Mpps | 100% |
| 512byte | 23.4 Mpps | 23.4 Mpps | 100% |
--------------------------------------------------
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 30 +++++++++++++++++------
3 files changed, 26 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a6ca54393bb6..7997d7c159db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -457,6 +457,7 @@ struct mlx5e_mpw_info {
struct mlx5e_umr_dma_info umr;
u16 consumed_strides;
u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
+ DECLARE_BITMAP(xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
};
/* a single cache unit is capable to serve one napi call (for non-striding rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bba2fa0aa15f..b03a2327356a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -200,7 +200,8 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
{
return mlx5e_check_fragmented_striding_rq_cap(mdev) &&
- !params->xdp_prog && !MLX5_IPSEC_DEV(mdev);
+ !MLX5_IPSEC_DEV(mdev) &&
+ !(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params));
}
void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a827571deb85..1da79cab1838 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -349,13 +349,16 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
{
+ const bool no_xdp_xmit =
+ bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
- struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
+ struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
int i;
- for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
- page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
- mlx5e_page_release(rq, dma_info, true);
+ for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
+ page_ref_sub(dma_info[i].page, pg_strides - wi->skbs_frags[i]);
+ if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
+ mlx5e_page_release(rq, &dma_info[i], true);
}
}
@@ -404,6 +407,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
}
memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
+ bitmap_zero(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
wi->consumed_strides = 0;
rq->mpwqe.umr_in_progress = true;
@@ -1028,18 +1032,30 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
{
struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
u16 rx_headroom = rq->buff.headroom;
+ u32 cqe_bcnt32 = cqe_bcnt;
struct sk_buff *skb;
void *va, *data;
u32 frag_size;
+ bool consumed;
va = page_address(di->page) + head_offset;
data = va + rx_headroom;
- frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
+ frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
frag_size, DMA_FROM_DEVICE);
prefetch(data);
- skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
+
+ rcu_read_lock();
+ consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32);
+ rcu_read_unlock();
+ if (consumed) {
+ if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+ __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
+ return NULL; /* page/packet was consumed by XDP */
+ }
+
+ skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32);
if (unlikely(!skb))
return NULL;
@@ -1078,7 +1094,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
skb = rq->mpwqe.skb_from_cqe_mpwrq(rq, wi, cqe_bcnt, head_offset,
page_idx);
- if (unlikely(!skb))
+ if (!skb)
goto mpwrq_cqe_out;
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
--
2.14.3
^ permalink raw reply related
* [net-next 11/15] net/mlx5e: Refactor RQ XDP_TX indication
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Make the xdp_xmit indication available for Striding RQ
by taking it out of the type-specific union.
This refactor is a preparation for a downstream patch that
adds XDP support over Striding RQ.
In addition, use a bitmap instead of a boolean for possible
future flags.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 +++++-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 8 +++-----
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d26dd4bc89f4..a6ca54393bb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -479,6 +479,10 @@ typedef struct sk_buff *
typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
+enum mlx5e_rq_flag {
+ MLX5E_RQ_FLAG_XDP_XMIT = BIT(0),
+};
+
struct mlx5e_rq {
/* data path */
struct mlx5_wq_ll wq;
@@ -489,7 +493,6 @@ struct mlx5e_rq {
u32 frag_sz; /* max possible skb frag_sz */
union {
bool page_reuse;
- bool xdp_xmit;
};
} wqe;
struct {
@@ -528,6 +531,7 @@ struct mlx5e_rq {
struct bpf_prog *xdp_prog;
unsigned int hw_mtu;
struct mlx5e_xdpsq xdpsq;
+ DECLARE_BITMAP(flags, 8);
/* control */
struct mlx5_wq_ctrl wq_ctrl;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 07db8a58d0a2..a827571deb85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -788,7 +788,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
/* move page to reference to sq responsibility,
* and mark so it's not put back in page-cache.
*/
- rq->wqe.xdp_xmit = true;
+ __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
sq->db.di[pi] = *di;
sq->pc++;
@@ -913,9 +913,8 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
if (!skb) {
/* probably for XDP */
- if (rq->wqe.xdp_xmit) {
+ if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
wi->di.page = NULL;
- rq->wqe.xdp_xmit = false;
/* do not return page to cache, it will be returned on XDP_TX completion */
goto wq_ll_pop;
}
@@ -955,9 +954,8 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt);
if (!skb) {
- if (rq->wqe.xdp_xmit) {
+ if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
wi->di.page = NULL;
- rq->wqe.xdp_xmit = false;
/* do not return page to cache, it will be returned on XDP_TX completion */
goto wq_ll_pop;
}
--
2.14.3
^ permalink raw reply related
* [net-next 09/15] net/mlx5e: Use inline MTTs in UMR WQEs
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
When modifying the page mapping of a HW memory region
(via a UMR post), post the new values inlined in WQE,
instead of using a data pointer.
This is a micro-optimization, inline UMR WQEs of different
rings scale better in HW.
In addition, this obsoletes a few control flows and helps
delete ~50 LOC.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 16 ++---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 82 +++++------------------
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 28 ++++----
3 files changed, 38 insertions(+), 88 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 1f89e2194b61..c1d3a29388bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -105,7 +105,6 @@
#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2
-#define MLX5_UMR_ALIGN (2048)
#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256)
#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024)
@@ -130,8 +129,13 @@
#define MLX5E_UPDATE_STATS_INTERVAL 200 /* msecs */
#define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */
-#define MLX5E_ICOSQ_MAX_WQEBBS \
- (DIV_ROUND_UP(sizeof(struct mlx5e_umr_wqe), MLX5_SEND_WQE_BB))
+#define MLX5E_UMR_WQE_INLINE_SZ \
+ (sizeof(struct mlx5e_umr_wqe) + \
+ ALIGN(MLX5_MPWRQ_PAGES_PER_WQE * sizeof(struct mlx5_mtt), \
+ MLX5_UMR_MTT_ALIGNMENT))
+#define MLX5E_UMR_WQEBBS \
+ (DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
+#define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
#define MLX5E_XDP_TX_DS_COUNT \
@@ -183,7 +187,7 @@ struct mlx5e_umr_wqe {
struct mlx5_wqe_ctrl_seg ctrl;
struct mlx5_wqe_umr_ctrl_seg uctrl;
struct mlx5_mkey_seg mkc;
- struct mlx5_wqe_data_seg data;
+ struct mlx5_mtt inline_mtts[0];
};
extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
@@ -421,7 +425,6 @@ struct mlx5e_icosq {
void __iomem *uar_map;
u32 sqn;
u16 edge;
- __be32 mkey_be;
unsigned long state;
/* control path */
@@ -446,8 +449,6 @@ struct mlx5e_wqe_frag_info {
};
struct mlx5e_umr_dma_info {
- __be64 *mtt;
- dma_addr_t mtt_addr;
struct mlx5e_dma_info dma_info[MLX5_MPWRQ_PAGES_PER_WQE];
struct mlx5e_umr_wqe wqe;
};
@@ -490,7 +491,6 @@ struct mlx5e_rq {
} wqe;
struct {
struct mlx5e_mpw_info *info;
- void *mtt_no_align;
u16 num_strides;
u8 log_stride_sz;
bool umr_in_progress;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e627b81cebe9..42dc350c5ab1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -73,9 +73,20 @@ struct mlx5e_channel_param {
bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
{
- return MLX5_CAP_GEN(mdev, striding_rq) &&
+ bool striding_rq_umr = MLX5_CAP_GEN(mdev, striding_rq) &&
MLX5_CAP_GEN(mdev, umr_ptr_rlky) &&
MLX5_CAP_ETH(mdev, reg_umr_sq);
+ u16 max_wqe_sz_cap = MLX5_CAP_GEN(mdev, max_wqe_sz_sq);
+ bool inline_umr = MLX5E_UMR_WQE_INLINE_SZ <= max_wqe_sz_cap;
+
+ if (!striding_rq_umr)
+ return false;
+ if (!inline_umr) {
+ mlx5_core_warn(mdev, "Cannot support Striding RQ: UMR WQE size (%d) exceeds maximum supported (%d).\n",
+ (int)MLX5E_UMR_WQE_INLINE_SZ, max_wqe_sz_cap);
+ return false;
+ }
+ return true;
}
static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
@@ -258,16 +269,6 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
}
-static inline int mlx5e_get_wqe_mtt_sz(void)
-{
- /* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes.
- * To avoid copying garbage after the mtt array, we allocate
- * a little more.
- */
- return ALIGN(MLX5_MPWRQ_PAGES_PER_WQE * sizeof(__be64),
- MLX5_UMR_MTT_ALIGNMENT);
-}
-
static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
struct mlx5e_icosq *sq,
struct mlx5e_umr_wqe *wqe,
@@ -275,9 +276,7 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
{
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
- struct mlx5_wqe_data_seg *dseg = &wqe->data;
- struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
- u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
+ u8 ds_cnt = DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_DS);
u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix);
cseg->qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
@@ -285,80 +284,32 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
cseg->imm = rq->mkey_be;
- ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN;
+ ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
ucseg->xlt_octowords =
cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
ucseg->bsf_octowords =
cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
-
- dseg->lkey = sq->mkey_be;
- dseg->addr = cpu_to_be64(wi->umr.mtt_addr);
}
static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
struct mlx5e_channel *c)
{
int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
- int mtt_sz = mlx5e_get_wqe_mtt_sz();
- int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
int i;
rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->mpwqe.info)
- goto err_out;
-
- /* We allocate more than mtt_sz as we will align the pointer */
- rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
- cpu_to_node(c->cpu));
- if (unlikely(!rq->mpwqe.mtt_no_align))
- goto err_free_wqe_info;
+ return -ENOMEM;
for (i = 0; i < wq_sz; i++) {
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
- wi->umr.mtt = PTR_ALIGN(rq->mpwqe.mtt_no_align + i * mtt_alloc,
- MLX5_UMR_ALIGN);
- wi->umr.mtt_addr = dma_map_single(c->pdev, wi->umr.mtt, mtt_sz,
- PCI_DMA_TODEVICE);
- if (unlikely(dma_mapping_error(c->pdev, wi->umr.mtt_addr)))
- goto err_unmap_mtts;
-
mlx5e_build_umr_wqe(rq, &c->icosq, &wi->umr.wqe, i);
}
return 0;
-
-err_unmap_mtts:
- while (--i >= 0) {
- struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
- dma_unmap_single(c->pdev, wi->umr.mtt_addr, mtt_sz,
- PCI_DMA_TODEVICE);
- }
- kfree(rq->mpwqe.mtt_no_align);
-err_free_wqe_info:
- kfree(rq->mpwqe.info);
-
-err_out:
- return -ENOMEM;
-}
-
-static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
-{
- int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
- int mtt_sz = mlx5e_get_wqe_mtt_sz();
- int i;
-
- for (i = 0; i < wq_sz; i++) {
- struct mlx5e_mpw_info *wi = &rq->mpwqe.info[i];
-
- dma_unmap_single(rq->pdev, wi->umr.mtt_addr, mtt_sz,
- PCI_DMA_TODEVICE);
- }
- kfree(rq->mpwqe.mtt_no_align);
- kfree(rq->mpwqe.info);
}
static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
@@ -579,7 +530,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- mlx5e_rq_free_mpwqe_info(rq);
+ kfree(rq->mpwqe.info);
mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
@@ -918,7 +869,6 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
struct mlx5_core_dev *mdev = c->mdev;
int err;
- sq->mkey_be = c->mkey_be;
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.bfreg.map;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8eb9e7e89b09..539dbe9382ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -381,17 +381,25 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
- struct mlx5e_umr_wqe *wqe;
- u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
+ struct mlx5e_umr_wqe *umr_wqe;
+ int cpy = offsetof(struct mlx5e_umr_wqe, inline_mtts);
int err;
u16 pi;
int i;
+ /* fill sq edge with nops to avoid wqe wrap around */
+ while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
+ sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+ mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+ }
+
+ umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+ memcpy(umr_wqe, &wi->umr.wqe, cpy);
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
err = mlx5e_page_alloc_mapped(rq, dma_info);
if (unlikely(err))
goto err_unmap;
- wi->umr.mtt[i] = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
+ umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
page_ref_add(dma_info->page, pg_strides);
}
@@ -400,21 +408,13 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
rq->mpwqe.umr_in_progress = true;
- /* fill sq edge with nops to avoid wqe wrap around */
- while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
- sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
- mlx5e_post_nop(wq, sq->sqn, &sq->pc);
- }
-
- wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- memcpy(wqe, &wi->umr.wqe, sizeof(*wqe));
- wqe->ctrl.opmod_idx_opcode =
+ umr_wqe->ctrl.opmod_idx_opcode =
cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
MLX5_OPCODE_UMR);
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
- sq->pc += num_wqebbs;
- mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
+ sq->pc += MLX5E_UMR_WQEBBS;
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
return 0;
--
2.14.3
^ permalink raw reply related
* [net-next 10/15] net/mlx5e: Use linear SKB in Striding RQ
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Current Striding RQ HW feature utilizes the RX buffers so that
there is no wasted room between the strides. This maximises
the memory utilization.
This prevents the use of build_skb() (which requires headroom
and tailroom), and demands to memcpy the packets headers into
the skb linear part.
In this patch, whenever a set of conditions holds, we apply
an RQ configuration that allows combining the use of linear SKB
on top of a Striding RQ.
To use build_skb() with Striding RQ, the following must hold:
1. packet does not cross a page boundary.
2. there is enough headroom and tailroom surrounding the packet.
We can satisfy 1 and 2 by configuring:
stride size = MTU + headroom + tailoom.
This is possible only when:
a. (MTU - headroom - tailoom) does not exceed PAGE_SIZE.
b. HW LRO is turned off.
Using linear SKB has many advantages:
- Saves a memcpy of the headers.
- No page-boundary checks in datapath.
- No filler CQEs.
- Significantly smaller CQ.
- SKB data continuously resides in linear part, and not split to
small amount (linear part) and large amount (fragment).
This saves datapath cycles in driver and improves utilization
of SKB fragments in GRO.
- The fragments of a resulting GRO SKB follow the IP forwarding
assumption of equal-size fragments.
Some implementation details:
HW writes the packets to the beginning of a stride,
i.e. does not keep headroom. To overcome this we make sure we can
extend backwards and use the last bytes of stride i-1.
Extra care is needed for stride 0 as it has no preceding stride.
We make sure headroom bytes are available by shifting the buffer
pointer passed to HW by headroom bytes.
This configuration now becomes default, whenever capable.
Of course, this implies turning LRO off.
Performance testing:
ConnectX-5, single core, single RX ring, default MTU.
UDP packet rate, early drop in TC layer:
--------------------------------------------
| pkt size | before | after | ratio |
--------------------------------------------
| 1500byte | 4.65 Mpps | 5.96 Mpps | 1.28x |
| 500byte | 5.23 Mpps | 5.97 Mpps | 1.14x |
| 64byte | 5.94 Mpps | 5.96 Mpps | 1.00x |
--------------------------------------------
TCP streams: ~20% gain
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 10 +++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 76 +++++++++++++---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 102 ++++++++++++++++------
include/linux/mlx5/device.h | 3 +
include/linux/mlx5/mlx5_ifc.h | 7 +-
5 files changed, 153 insertions(+), 45 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c1d3a29388bd..d26dd4bc89f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -473,6 +473,9 @@ struct mlx5e_page_cache {
struct mlx5e_rq;
typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
+typedef struct sk_buff *
+(*mlx5e_fp_skb_from_cqe_mpwrq)(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+ u16 cqe_bcnt, u32 head_offset, u32 page_idx);
typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
@@ -491,6 +494,7 @@ struct mlx5e_rq {
} wqe;
struct {
struct mlx5e_mpw_info *info;
+ mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
u16 num_strides;
u8 log_stride_sz;
bool umr_in_progress;
@@ -834,6 +838,12 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+ u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+ u16 cqe_bcnt, u32 head_offset, u32 page_idx);
void mlx5e_update_stats(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 42dc350c5ab1..bba2fa0aa15f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -91,9 +91,14 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
{
- u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ if (!params->xdp_prog) {
+ u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN;
- return hw_mtu;
+ return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu);
+ }
+
+ return PAGE_SIZE;
}
static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
@@ -103,6 +108,26 @@ static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
}
+static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params)
+{
+ u32 frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+ s8 signed_log_num_strides_param;
+ u8 log_num_strides;
+
+ if (params->lro_en || frag_sz > PAGE_SIZE)
+ return false;
+
+ if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
+ return true;
+
+ log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
+ signed_log_num_strides_param =
+ (s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
+
+ return signed_log_num_strides_param >= 0;
+}
+
static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
{
if (params->log_rq_mtu_frames <
@@ -115,6 +140,9 @@ static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
{
+ if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+ return order_base_2(mlx5e_mpwqe_get_linear_frag_sz(params));
+
return MLX5E_MPWQE_STRIDE_SZ(mdev,
MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
}
@@ -126,7 +154,8 @@ static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
mlx5e_mpwqe_get_log_stride_size(mdev, params);
}
-static u16 mlx5e_get_rq_headroom(struct mlx5e_params *params)
+static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params)
{
u16 linear_rq_headroom = params->xdp_prog ?
XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
@@ -136,6 +165,9 @@ static u16 mlx5e_get_rq_headroom(struct mlx5e_params *params)
if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST)
return linear_rq_headroom;
+ if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+ return linear_rq_headroom;
+
return 0;
}
@@ -151,12 +183,14 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
/* Extra room needed for build_skb */
- params->lro_wqe_sz -= mlx5e_get_rq_headroom(params) +
+ params->lro_wqe_sz -= mlx5e_get_rq_headroom(mdev, params) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
}
mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
+ params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
+ BIT(mlx5e_mpwqe_get_log_rq_size(params)) :
BIT(params->log_rq_mtu_frames),
BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
@@ -400,11 +434,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
goto err_rq_wq_destroy;
rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
- rq->buff.headroom = mlx5e_get_rq_headroom(params);
+ rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params);
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-
rq->post_wqes = mlx5e_post_rx_mpwqes;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
@@ -422,6 +455,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
goto err_rq_wq_destroy;
}
+ rq->mpwqe.skb_from_cqe_mpwrq =
+ mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ?
+ mlx5e_skb_from_cqe_mpwrq_linear :
+ mlx5e_skb_from_cqe_mpwrq_nonlinear;
rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params);
rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params));
@@ -484,7 +521,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT;
- wqe->data.addr = cpu_to_be64(dma_offset);
+ wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom);
}
wqe->data.byte_count = cpu_to_be32(byte_count);
@@ -1834,9 +1871,11 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
MLX5_SET(wq, wq, log_wqe_num_of_strides,
- mlx5e_mpwqe_get_log_num_strides(mdev, params) - 9);
+ mlx5e_mpwqe_get_log_num_strides(mdev, params) -
+ MLX5_MPWQE_LOG_NUM_STRIDES_BASE);
MLX5_SET(wq, wq, log_wqe_stride_size,
- mlx5e_mpwqe_get_log_stride_size(mdev, params) - 6);
+ mlx5e_mpwqe_get_log_stride_size(mdev, params) -
+ MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
break;
@@ -3193,20 +3232,28 @@ typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
static int set_feature_lro(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_channels new_channels = {};
+ struct mlx5e_params *old_params;
int err = 0;
bool reset;
mutex_lock(&priv->state_lock);
- reset = (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST);
- reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
+ old_params = &priv->channels.params;
+ reset = test_bit(MLX5E_STATE_OPENED, &priv->state);
- new_channels.params = priv->channels.params;
+ new_channels.params = *old_params;
new_channels.params.lro_en = enable;
+ if (old_params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+ if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
+ mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
+ reset = false;
+ }
+
if (!reset) {
- priv->channels.params = new_channels.params;
+ *old_params = new_channels.params;
err = mlx5e_modify_tirs_lro(priv);
goto out;
}
@@ -4121,7 +4168,8 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
- params->lro_en = !slow_pci_heuristic(mdev);
+ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+ params->lro_en = !slow_pci_heuristic(mdev);
params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
/* CQ moderation params */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 539dbe9382ee..07db8a58d0a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -836,6 +836,24 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
}
}
+static inline
+struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
+ u32 frag_size, u16 headroom,
+ u32 cqe_bcnt)
+{
+ struct sk_buff *skb = build_skb(va, frag_size);
+
+ if (unlikely(!skb)) {
+ rq->stats.buff_alloc_err++;
+ return NULL;
+ }
+
+ skb_reserve(skb, headroom);
+ skb_put(skb, cqe_bcnt);
+
+ return skb;
+}
+
static inline
struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
@@ -867,18 +885,13 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
if (consumed)
return NULL; /* page/packet was consumed by XDP */
- skb = build_skb(va, frag_size);
- if (unlikely(!skb)) {
- rq->stats.buff_alloc_err++;
+ skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
+ if (unlikely(!skb))
return NULL;
- }
/* queue up for recycling/reuse */
page_ref_inc(di->page);
- skb_reserve(skb, rx_headroom);
- skb_put(skb, cqe_bcnt);
-
return skb;
}
@@ -967,20 +980,24 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
}
#endif
-static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
- struct mlx5_cqe64 *cqe,
- struct mlx5e_mpw_info *wi,
- u32 cqe_bcnt,
- struct sk_buff *skb)
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+ u16 cqe_bcnt, u32 head_offset, u32 page_idx)
{
- u16 stride_ix = mpwrq_get_cqe_stride_index(cqe);
- u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz;
- u32 head_offset = wqe_offset & (PAGE_SIZE - 1);
- u32 page_idx = wqe_offset >> PAGE_SHIFT;
- u32 head_page_idx = page_idx;
u16 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt);
u32 frag_offset = head_offset + headlen;
u16 byte_cnt = cqe_bcnt - headlen;
+ u32 head_page_idx = page_idx;
+ struct sk_buff *skb;
+
+ skb = napi_alloc_skb(rq->cq.napi,
+ ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, sizeof(long)));
+ if (unlikely(!skb)) {
+ rq->stats.buff_alloc_err++;
+ return NULL;
+ }
+
+ prefetchw(skb->data);
if (unlikely(frag_offset >= PAGE_SIZE)) {
page_idx++;
@@ -1003,6 +1020,35 @@ static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
/* skb linear part was allocated with headlen and aligned to long */
skb->tail += headlen;
skb->len += headlen;
+
+ return skb;
+}
+
+struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+ u16 cqe_bcnt, u32 head_offset, u32 page_idx)
+{
+ struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
+ u16 rx_headroom = rq->buff.headroom;
+ struct sk_buff *skb;
+ void *va, *data;
+ u32 frag_size;
+
+ va = page_address(di->page) + head_offset;
+ data = va + rx_headroom;
+ frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
+
+ dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
+ frag_size, DMA_FROM_DEVICE);
+ prefetch(data);
+ skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
+ if (unlikely(!skb))
+ return NULL;
+
+ /* queue up for recycling/reuse */
+ wi->skbs_frags[page_idx]++;
+
+ return skb;
}
void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -1010,7 +1056,11 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe);
u16 wqe_id = be16_to_cpu(cqe->wqe_id);
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[wqe_id];
- struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
+ u16 stride_ix = mpwrq_get_cqe_stride_index(cqe);
+ u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz;
+ u32 head_offset = wqe_offset & (PAGE_SIZE - 1);
+ u32 page_idx = wqe_offset >> PAGE_SHIFT;
+ struct mlx5e_rx_wqe *wqe;
struct sk_buff *skb;
u16 cqe_bcnt;
@@ -1026,18 +1076,13 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
goto mpwrq_cqe_out;
}
- skb = napi_alloc_skb(rq->cq.napi,
- ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD,
- sizeof(long)));
- if (unlikely(!skb)) {
- rq->stats.buff_alloc_err++;
- goto mpwrq_cqe_out;
- }
-
- prefetchw(skb->data);
cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
- mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
+ skb = rq->mpwqe.skb_from_cqe_mpwrq(rq, wi, cqe_bcnt, head_offset,
+ page_idx);
+ if (unlikely(!skb))
+ goto mpwrq_cqe_out;
+
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
napi_gro_receive(rq->cq.napi, skb);
@@ -1045,6 +1090,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
return;
+ wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
mlx5e_free_rx_mpwqe(rq, wi);
mlx5_wq_ll_pop(&rq->wq, cqe->wqe_id, &wqe->next.next_wqe_index);
}
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 4b5939c78cdd..12758595459b 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -782,6 +782,9 @@ static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe)
return (u64)lo | ((u64)hi << 32);
}
+#define MLX5_MPWQE_LOG_NUM_STRIDES_BASE (9)
+#define MLX5_MPWQE_LOG_STRIDE_SZ_BASE (6)
+
struct mpwrq_cqe_bc {
__be16 filler_consumed_strides;
__be16 byte_cnt;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c19e611d2782..d25011f84815 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1038,7 +1038,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_398[0x3];
u8 log_max_tis_per_sq[0x5];
- u8 reserved_at_3a0[0x3];
+ u8 ext_stride_num_range[0x1];
+ u8 reserved_at_3a1[0x2];
u8 log_max_stride_sz_rq[0x5];
u8 reserved_at_3a8[0x3];
u8 log_min_stride_sz_rq[0x5];
@@ -1205,9 +1206,9 @@ struct mlx5_ifc_wq_bits {
u8 log_hairpin_num_packets[0x5];
u8 reserved_at_128[0x3];
u8 log_hairpin_data_sz[0x5];
- u8 reserved_at_130[0x5];
- u8 log_wqe_num_of_strides[0x3];
+ u8 reserved_at_130[0x4];
+ u8 log_wqe_num_of_strides[0x4];
u8 two_byte_shift_en[0x1];
u8 reserved_at_139[0x4];
u8 log_wqe_stride_size[0x3];
--
2.14.3
^ permalink raw reply related
* [net-next 06/15] net/mlx5e: Derive Striding RQ size from MTU
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
In Striding RQ, each WQE serves multiple packets
(hence called Multi-Packet WQE, MPWQE).
The size of a MPWQE is constant (currently 256KB).
Upon a ringparam set operation, we calculate the number of
MPWQEs per RQ. For this, first it is needed to determine the
number of packets that can reside within a single MPWQE.
In this patch we use the actual MTU size instead of ETH_DATA_LEN
for this calculation.
This implies that a change in MTU might require a change
in Striding RQ ring size.
In addition, this obsoletes some WQEs-to-packets translation
functions and helps delete ~60 LOC.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 63 ++++++-----------
.../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 79 ++--------------------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 71 ++++++++++++-------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +-
.../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +-
.../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 2 +-
6 files changed, 80 insertions(+), 139 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 823876bfd6ab..1f89e2194b61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -63,18 +63,6 @@
#define MLX5E_MAX_DSCP 64
#define MLX5E_MAX_NUM_TC 8
-#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE 0x6
-#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE 0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE 0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE 0x1
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE 0xa
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE 0xd
-
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2
-#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW 0x3
-#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW 0x6
-
#define MLX5_RX_HEADROOM NET_SKB_PAD
#define MLX5_SKB_FRAG_SZ(len) (SKB_DATA_ALIGN(len) + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -95,9 +83,27 @@
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
-#define MLX5E_REQUIRED_MTTS(wqes) \
- (wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
-#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
+#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS)
+#define MLX5E_MAX_RQ_NUM_MTTS \
+ ((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
+#define MLX5E_ORDER2_MAX_PACKET_MTU (order_base_2(10 * 1024))
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW \
+ (ilog2(MLX5E_MAX_RQ_NUM_MTTS / MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW \
+ (MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW + \
+ (MLX5_MPWRQ_LOG_WQE_SZ - MLX5E_ORDER2_MAX_PACKET_MTU))
+
+#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE 0x6
+#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE 0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE 0xd
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE 0x1
+#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE 0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE min_t(u8, 0xd, \
+ MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW)
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2
#define MLX5_UMR_ALIGN (2048)
#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256)
@@ -155,26 +161,6 @@ static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
}
}
-static inline int mlx5_min_log_rq_size(int wq_type)
-{
- switch (wq_type) {
- case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
- default:
- return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
- }
-}
-
-static inline int mlx5_max_log_rq_size(int wq_type)
-{
- switch (wq_type) {
- case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW;
- default:
- return MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
- }
-}
-
static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
{
return is_kdump_kernel() ?
@@ -233,7 +219,7 @@ enum mlx5e_priv_flag {
struct mlx5e_params {
u8 log_sq_size;
u8 rq_wq_type;
- u8 log_rq_size;
+ u8 log_rq_mtu_frames;
u16 num_channels;
u8 num_tc;
bool rx_cqe_compress_def;
@@ -849,11 +835,6 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
-u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params);
-u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params);
-
void mlx5e_update_stats(struct mlx5e_priv *priv);
int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c57c929d7973..a87d46bc2299 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -220,60 +220,12 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
mlx5e_ethtool_get_ethtool_stats(priv, stats, data);
}
-static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
- int num_wqe)
-{
- int packets_per_wqe;
- int stride_size;
- int num_strides;
- int wqe_size;
-
- if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
- return num_wqe;
-
- stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
- num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
- wqe_size = stride_size * num_strides;
-
- packets_per_wqe = wqe_size /
- ALIGN(ETH_DATA_LEN, stride_size);
- return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1));
-}
-
-static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
- int num_packets)
-{
- int packets_per_wqe;
- int stride_size;
- int num_strides;
- int wqe_size;
- int num_wqes;
-
- if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
- return num_packets;
-
- stride_size = 1 << mlx5e_mpwqe_get_log_stride_size(priv->mdev, &priv->channels.params);
- num_strides = 1 << mlx5e_mpwqe_get_log_num_strides(priv->mdev, &priv->channels.params);
- wqe_size = stride_size * num_strides;
-
- num_packets = (1 << order_base_2(num_packets));
-
- packets_per_wqe = wqe_size /
- ALIGN(ETH_DATA_LEN, stride_size);
- num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe);
- return 1 << (order_base_2(num_wqes));
-}
-
void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
struct ethtool_ringparam *param)
{
- int rq_wq_type = priv->channels.params.rq_wq_type;
-
- param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
- 1 << mlx5_max_log_rq_size(rq_wq_type));
+ param->rx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
- param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
- 1 << priv->channels.params.log_rq_size);
+ param->rx_pending = 1 << priv->channels.params.log_rq_mtu_frames;
param->tx_pending = 1 << priv->channels.params.log_sq_size;
}
@@ -288,13 +240,9 @@ static void mlx5e_get_ringparam(struct net_device *dev,
int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
struct ethtool_ringparam *param)
{
- int rq_wq_type = priv->channels.params.rq_wq_type;
struct mlx5e_channels new_channels = {};
- u32 rx_pending_wqes;
- u32 min_rq_size;
u8 log_rq_size;
u8 log_sq_size;
- u32 num_mtts;
int err = 0;
if (param->rx_jumbo_pending) {
@@ -308,23 +256,10 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
return -EINVAL;
}
- min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
- 1 << mlx5_min_log_rq_size(rq_wq_type));
- rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
- param->rx_pending);
-
- if (param->rx_pending < min_rq_size) {
+ if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) {
netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n",
__func__, param->rx_pending,
- min_rq_size);
- return -EINVAL;
- }
-
- num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
- if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
- !MLX5E_VALID_NUM_MTTS(num_mtts)) {
- netdev_info(priv->netdev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
- __func__, param->rx_pending);
+ 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
return -EINVAL;
}
@@ -335,17 +270,17 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
return -EINVAL;
}
- log_rq_size = order_base_2(rx_pending_wqes);
+ log_rq_size = order_base_2(param->rx_pending);
log_sq_size = order_base_2(param->tx_pending);
- if (log_rq_size == priv->channels.params.log_rq_size &&
+ if (log_rq_size == priv->channels.params.log_rq_mtu_frames &&
log_sq_size == priv->channels.params.log_sq_size)
return 0;
mutex_lock(&priv->state_lock);
new_channels.params = priv->channels.params;
- new_channels.params.log_rq_size = log_rq_size;
+ new_channels.params.log_rq_mtu_frames = log_rq_size;
new_channels.params.log_sq_size = log_sq_size;
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index af345323b2ce..e627b81cebe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -78,15 +78,38 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
MLX5_CAP_ETH(mdev, reg_umr_sq);
}
-u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params)
+static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params)
+{
+ u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+
+ return hw_mtu;
+}
+
+static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
+{
+ u32 linear_frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params);
+
+ return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+}
+
+static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
+{
+ if (params->log_rq_mtu_frames <
+ mlx5e_mpwqe_log_pkts_per_wqe(params) + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
+ return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
+
+ return params->log_rq_mtu_frames - mlx5e_mpwqe_log_pkts_per_wqe(params);
+}
+
+static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params)
{
return MLX5E_MPWQE_STRIDE_SZ(mdev,
MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
}
-u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params)
+static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params)
{
return MLX5_MPWRQ_LOG_WQE_SZ -
mlx5e_mpwqe_get_log_stride_size(mdev, params);
@@ -109,17 +132,13 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
{
params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+ params->log_rq_mtu_frames = is_kdump_kernel() ?
+ MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
+ MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- params->log_rq_size = is_kdump_kernel() ?
- MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
- MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
- params->log_rq_size = is_kdump_kernel() ?
- MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
- MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
-
/* Extra room needed for build_skb */
params->lro_wqe_sz -= mlx5e_get_rq_headroom(params) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -127,7 +146,7 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
- BIT(params->log_rq_size),
+ BIT(params->log_rq_mtu_frames),
BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
}
@@ -351,9 +370,6 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
u32 *in;
int err;
- if (!MLX5E_VALID_NUM_MTTS(npages))
- return -EINVAL;
-
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
return -ENOMEM;
@@ -1872,14 +1888,15 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
MLX5_SET(wq, wq, log_wqe_stride_size,
mlx5e_mpwqe_get_log_stride_size(mdev, params) - 6);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+ MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
+ MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
}
MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
- MLX5_SET(wq, wq, log_wq_sz, params->log_rq_size);
MLX5_SET(wq, wq, pd, mdev->mlx5e_res.pdn);
MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter);
MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable);
@@ -1939,16 +1956,17 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_cq_param *param)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
void *cqc = param->cqc;
u8 log_cq_size;
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- log_cq_size = params->log_rq_size +
- mlx5e_mpwqe_get_log_num_strides(priv->mdev, params);
+ log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
+ mlx5e_mpwqe_get_log_num_strides(mdev, params);
break;
default: /* MLX5_WQ_TYPE_LINKED_LIST */
- log_cq_size = params->log_rq_size;
+ log_cq_size = params->log_rq_mtu_frames;
}
MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
@@ -3421,11 +3439,20 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
mutex_lock(&priv->state_lock);
params = &priv->channels.params;
- reset = !params->lro_en &&
- (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+ reset = !params->lro_en;
reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
+ new_channels.params = *params;
+ new_channels.params.sw_mtu = new_mtu;
+
+ if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) {
+ u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
+ u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+
+ reset = reset && (ppw_old != ppw_new);
+ }
+
if (!reset) {
params->sw_mtu = new_mtu;
mlx5e_set_dev_port_mtu(priv);
@@ -3433,8 +3460,6 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
goto out;
}
- new_channels.params = *params;
- new_channels.params.sw_mtu = new_mtu;
err = mlx5e_open_channels(priv, &new_channels);
if (err)
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index cd884829cb30..8e70fa9ef39a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -880,7 +880,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
params->hard_mtu = MLX5E_ETH_HARD_MTU;
params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
- params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+ params->log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index dc5e9e706362..af3bb2f7a504 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -61,7 +61,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
mlx5e_init_rq_type_params(mdev, params);
/* RQ size in ipoib by default is 512 */
- params->log_rq_size = is_kdump_kernel() ?
+ params->log_rq_mtu_frames = is_kdump_kernel() ?
MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index b69e9d847a6b..54a188f41f90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -290,7 +290,7 @@ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev,
netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops;
/* Use dummy rqs */
- priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+ priv->channels.params.log_rq_mtu_frames = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
}
/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */
--
2.14.3
^ permalink raw reply related
* [net-next 08/15] net/mlx5e: Do not busy-wait for UMR completion in Striding RQ
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Do not busy-wait a pending UMR completion. Under high HW load,
busy-waiting a delayed completion would fully utilize the CPU core
and mistakenly indicate a SW bottleneck.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8aa94d3cff59..8eb9e7e89b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -527,7 +527,7 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
if (!rq->mpwqe.umr_in_progress)
mlx5e_alloc_rx_mpwqe(rq, wq->head);
- return true;
+ return false;
}
static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
--
2.14.3
^ permalink raw reply related
* [net-next 04/15] net/mlx5e: IPoIB, Fix spelling mistake
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Talat Batheesh,
Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Talat Batheesh <talatb@mellanox.com>
Fix spelling mistake in debug message text.
"dettaching" -> "detaching"
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index a35608faf8d2..4899de74e252 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -540,7 +540,7 @@ static int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
err = mlx5_core_detach_mcg(mdev, gid, ipriv->qp.qpn);
if (err)
- mlx5_core_dbg(mdev, "failed dettaching QPN 0x%x, MGID %pI6\n",
+ mlx5_core_dbg(mdev, "failed detaching QPN 0x%x, MGID %pI6\n",
ipriv->qp.qpn, gid->raw);
return err;
--
2.14.3
^ permalink raw reply related
* [net-next 07/15] net/mlx5e: Code movements in RX UMR WQE post
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Gets the process of a UMR WQE post in one function,
in preparation for a downstream patch that inlines
the WQE data.
No functional change here.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 107 ++++++++++--------------
1 file changed, 45 insertions(+), 62 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index c0d528f2131b..8aa94d3cff59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -347,39 +347,44 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
}
}
-static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
+void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
{
- struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
- struct mlx5e_icosq *sq = &rq->channel->icosq;
- struct mlx5_wq_cyc *wq = &sq->wq;
- struct mlx5e_umr_wqe *wqe;
- u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
- u16 pi;
+ int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
+ struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
+ int i;
- /* fill sq edge with nops to avoid wqe wrap around */
- while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
- sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
- mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+ for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
+ page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
+ mlx5e_page_release(rq, dma_info, true);
}
+}
- wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- memcpy(wqe, &wi->umr.wqe, sizeof(*wqe));
- wqe->ctrl.opmod_idx_opcode =
- cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
- MLX5_OPCODE_UMR);
+static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
+{
+ struct mlx5_wq_ll *wq = &rq->wq;
+ struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
- sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
- sq->pc += num_wqebbs;
- mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
+ rq->mpwqe.umr_in_progress = false;
+
+ mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+
+ /* ensure wqes are visible to device before updating doorbell record */
+ dma_wmb();
+
+ mlx5_wq_ll_update_db_record(wq);
}
-static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
- u16 ix)
+static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
+ struct mlx5e_icosq *sq = &rq->channel->icosq;
+ struct mlx5_wq_cyc *wq = &sq->wq;
+ struct mlx5e_umr_wqe *wqe;
+ u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
int err;
+ u16 pi;
int i;
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
@@ -393,6 +398,24 @@ static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
wi->consumed_strides = 0;
+ rq->mpwqe.umr_in_progress = true;
+
+ /* fill sq edge with nops to avoid wqe wrap around */
+ while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
+ sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+ mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+ }
+
+ wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+ memcpy(wqe, &wi->umr.wqe, sizeof(*wqe));
+ wqe->ctrl.opmod_idx_opcode =
+ cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
+ MLX5_OPCODE_UMR);
+
+ sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+ sq->pc += num_wqebbs;
+ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
+
return 0;
err_unmap:
@@ -401,51 +424,11 @@ static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
page_ref_sub(dma_info->page, pg_strides);
mlx5e_page_release(rq, dma_info, true);
}
+ rq->stats.buff_alloc_err++;
return err;
}
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
-{
- int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
- struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
- int i;
-
- for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
- page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
- mlx5e_page_release(rq, dma_info, true);
- }
-}
-
-static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
-{
- struct mlx5_wq_ll *wq = &rq->wq;
- struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
-
- rq->mpwqe.umr_in_progress = false;
-
- mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
-
- /* ensure wqes are visible to device before updating doorbell record */
- dma_wmb();
-
- mlx5_wq_ll_update_db_record(wq);
-}
-
-static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
-{
- int err;
-
- err = mlx5e_alloc_rx_umr_mpwqe(rq, ix);
- if (unlikely(err)) {
- rq->stats.buff_alloc_err++;
- return err;
- }
- rq->mpwqe.umr_in_progress = true;
- mlx5e_post_umr_wqe(rq, ix);
- return 0;
-}
-
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
--
2.14.3
^ permalink raw reply related
* [net-next 05/15] net/mlx5e: Save MTU in channels params
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Knowing the MTU is required for RQ creation flow.
By our design, channels creation flow is totally isolated
from priv/netdev, and can be completed with access to
channels params and mdev.
Adding the MTU to the channels params helps preserving that.
In addition, we save it in RQ to make its access faster in
datapath checks.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 10 ++--
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 58 ++++++++++++----------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +-
.../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 23 +++++----
5 files changed, 52 insertions(+), 45 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 353ac6daa3dc..823876bfd6ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -57,8 +57,8 @@
#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
-#define MLX5E_HW2SW_MTU(priv, hwmtu) ((hwmtu) - ((priv)->hard_mtu))
-#define MLX5E_SW2HW_MTU(priv, swmtu) ((swmtu) + ((priv)->hard_mtu))
+#define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
+#define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
#define MLX5E_MAX_DSCP 64
#define MLX5E_MAX_NUM_TC 8
@@ -251,6 +251,8 @@ struct mlx5e_params {
u32 lro_timeout;
u32 pflags;
struct bpf_prog *xdp_prog;
+ unsigned int sw_mtu;
+ int hard_mtu;
};
#ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -534,6 +536,7 @@ struct mlx5e_rq {
/* XDP */
struct bpf_prog *xdp_prog;
+ unsigned int hw_mtu;
struct mlx5e_xdpsq xdpsq;
/* control */
@@ -767,7 +770,6 @@ struct mlx5e_priv {
struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS];
u32 tx_rates[MLX5E_MAX_NUM_SQS];
- int hard_mtu;
struct mlx5e_flow_steering fs;
struct mlx5e_vxlan_db vxlan;
@@ -1111,7 +1113,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv);
void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
- u16 max_channels);
+ u16 max_channels, u16 mtu);
u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
void mlx5e_rx_dim_work(struct work_struct *work);
#endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2aff4db9bdaa..af345323b2ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -419,6 +419,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
rq->channel = c;
rq->ix = c->ix;
rq->mdev = mdev;
+ rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
if (IS_ERR(rq->xdp_prog)) {
@@ -494,7 +495,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
byte_count = params->lro_en ?
params->lro_wqe_sz :
- MLX5E_SW2HW_MTU(c->priv, c->netdev->mtu);
+ MLX5E_SW2HW_MTU(params, params->sw_mtu);
#ifdef CONFIG_MLX5_EN_IPSEC
if (MLX5_IPSEC_DEV(mdev))
byte_count += MLX5E_METADATA_ETHER_LEN;
@@ -2498,10 +2499,10 @@ static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
}
-static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
+static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params, u16 mtu)
{
- struct mlx5_core_dev *mdev = priv->mdev;
- u16 hw_mtu = MLX5E_SW2HW_MTU(priv, mtu);
+ u16 hw_mtu = MLX5E_SW2HW_MTU(params, mtu);
int err;
err = mlx5_set_port_mtu(mdev, hw_mtu, 1);
@@ -2513,9 +2514,9 @@ static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
return 0;
}
-static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
+static void mlx5e_query_mtu(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params, u16 *mtu)
{
- struct mlx5_core_dev *mdev = priv->mdev;
u16 hw_mtu = 0;
int err;
@@ -2523,25 +2524,27 @@ static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
if (err || !hw_mtu) /* fallback to port oper mtu */
mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1);
- *mtu = MLX5E_HW2SW_MTU(priv, hw_mtu);
+ *mtu = MLX5E_HW2SW_MTU(params, hw_mtu);
}
static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
{
+ struct mlx5e_params *params = &priv->channels.params;
struct net_device *netdev = priv->netdev;
+ struct mlx5_core_dev *mdev = priv->mdev;
u16 mtu;
int err;
- err = mlx5e_set_mtu(priv, netdev->mtu);
+ err = mlx5e_set_mtu(mdev, params, params->sw_mtu);
if (err)
return err;
- mlx5e_query_mtu(priv, &mtu);
- if (mtu != netdev->mtu)
+ mlx5e_query_mtu(mdev, params, &mtu);
+ if (mtu != params->sw_mtu)
netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
- __func__, mtu, netdev->mtu);
+ __func__, mtu, params->sw_mtu);
- netdev->mtu = mtu;
+ params->sw_mtu = mtu;
return 0;
}
@@ -3411,34 +3414,33 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_channels new_channels = {};
- int curr_mtu;
+ struct mlx5e_params *params;
int err = 0;
bool reset;
mutex_lock(&priv->state_lock);
- reset = !priv->channels.params.lro_en &&
- (priv->channels.params.rq_wq_type !=
- MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+ params = &priv->channels.params;
+ reset = !params->lro_en &&
+ (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
reset = reset && test_bit(MLX5E_STATE_OPENED, &priv->state);
- curr_mtu = netdev->mtu;
- netdev->mtu = new_mtu;
-
if (!reset) {
+ params->sw_mtu = new_mtu;
mlx5e_set_dev_port_mtu(priv);
+ netdev->mtu = params->sw_mtu;
goto out;
}
- new_channels.params = priv->channels.params;
+ new_channels.params = *params;
+ new_channels.params.sw_mtu = new_mtu;
err = mlx5e_open_channels(priv, &new_channels);
- if (err) {
- netdev->mtu = curr_mtu;
+ if (err)
goto out;
- }
mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu);
+ netdev->mtu = new_channels.params.sw_mtu;
out:
mutex_unlock(&priv->state_lock);
@@ -4111,10 +4113,12 @@ static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeo
void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
- u16 max_channels)
+ u16 max_channels, u16 mtu)
{
u8 cq_period_mode = 0;
+ params->sw_mtu = mtu;
+ params->hard_mtu = MLX5E_ETH_HARD_MTU;
params->num_channels = max_channels;
params->num_tc = 1;
@@ -4175,9 +4179,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
priv->profile = profile;
priv->ppriv = ppriv;
priv->msglevel = MLX5E_MSG_LEVEL;
- priv->hard_mtu = MLX5E_ETH_HARD_MTU;
- mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+ mlx5e_build_nic_params(mdev, &priv->channels.params,
+ profile->max_nch(mdev), netdev->mtu);
mutex_init(&priv->state_lock);
@@ -4454,7 +4458,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
/* MTU range: 68 - hw-specific max */
netdev->min_mtu = ETH_MIN_MTU;
mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
- netdev->max_mtu = MLX5E_HW2SW_MTU(priv, max_mtu);
+ netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
mlx5e_set_dev_port_mtu(priv);
mlx5_lag_add(mdev, netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index dd32f3e390ff..cd884829cb30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -877,6 +877,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+ params->hard_mtu = MLX5E_ETH_HARD_MTU;
params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
@@ -926,8 +927,6 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
priv->channels.params.num_channels = profile->max_nch(mdev);
- priv->hard_mtu = MLX5E_ETH_HARD_MTU;
-
mlx5e_build_rep_params(mdev, &priv->channels.params);
mlx5e_build_rep_netdev(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 781b8f21d6d1..c0d528f2131b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -766,8 +766,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
prefetchw(wqe);
- if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
- MLX5E_SW2HW_MTU(rq->channel->priv, rq->netdev->mtu) < dma_len)) {
+ if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
rq->stats.xdp_drop++;
return false;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 4899de74e252..dc5e9e706362 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -66,6 +66,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
params->lro_en = false;
+ params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
}
/* Called directly after IPoIB netdevice was created to initialize SW structs */
@@ -81,10 +82,10 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
priv->netdev = netdev;
priv->profile = profile;
priv->ppriv = ppriv;
- priv->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
mutex_init(&priv->state_lock);
- mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+ mlx5e_build_nic_params(mdev, &priv->channels.params,
+ profile->max_nch(mdev), netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
mlx5e_timestamp_init(priv);
@@ -368,25 +369,27 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu)
{
struct mlx5e_priv *priv = mlx5i_epriv(netdev);
struct mlx5e_channels new_channels = {};
- int curr_mtu;
+ struct mlx5e_params *params;
int err = 0;
mutex_lock(&priv->state_lock);
- curr_mtu = netdev->mtu;
- netdev->mtu = new_mtu;
+ params = &priv->channels.params;
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ params->sw_mtu = new_mtu;
+ netdev->mtu = params->sw_mtu;
goto out;
+ }
- new_channels.params = priv->channels.params;
+ new_channels.params = *params;
+ new_channels.params.sw_mtu = new_mtu;
err = mlx5e_open_channels(priv, &new_channels);
- if (err) {
- netdev->mtu = curr_mtu;
+ if (err)
goto out;
- }
mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+ netdev->mtu = new_channels.params.sw_mtu;
out:
mutex_unlock(&priv->state_lock);
--
2.14.3
^ permalink raw reply related
* [net-next 02/15] net/mlx5: Eliminate query xsrq dead code
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
1. This function is not used anywhere in mlx5 driver
2. It has a memcpy statement that makes no sense and produces build
warning with gcc8
drivers/net/ethernet/mellanox/mlx5/core/transobj.c: In function 'mlx5_core_query_xsrq':
drivers/net/ethernet/mellanox/mlx5/core/transobj.c:347:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]
Fixes: 01949d0109ee ("net/mlx5_core: Enable XRCs and SRQs when using ISSI > 0")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 21 ---------------------
include/linux/mlx5/transobj.h | 1 -
2 files changed, 22 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index c64957b5ef47..dae1c5c5d27c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -354,27 +354,6 @@ int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
-int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u32 *out)
-{
- u32 in[MLX5_ST_SZ_DW(query_xrc_srq_in)] = {0};
- void *srqc;
- void *xrc_srqc;
- int err;
-
- MLX5_SET(query_xrc_srq_in, in, opcode, MLX5_CMD_OP_QUERY_XRC_SRQ);
- MLX5_SET(query_xrc_srq_in, in, xrc_srqn, xsrqn);
- err = mlx5_cmd_exec(dev, in, sizeof(in), out,
- MLX5_ST_SZ_BYTES(query_xrc_srq_out));
- if (!err) {
- xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, out,
- xrc_srq_context_entry);
- srqc = MLX5_ADDR_OF(query_srq_out, out, srq_context_entry);
- memcpy(srqc, xrc_srqc, MLX5_ST_SZ_BYTES(srqc));
- }
-
- return err;
-}
-
int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
{
u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0};
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 80d7aa8b2831..83a33a1873a6 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -67,7 +67,6 @@ int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
u32 *rmpn);
int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn);
-int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
--
2.14.3
^ permalink raw reply related
* [pull request][net-next 00/15] Mellanox, mlx5 updates 2018-03-30
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
Hi Dave,
This series contains updates to mlx5 core and mlx5e netdev drivers.
The main highlight of this series is the RX optimizations for striding RQ path,
introduced by Tariq.
For more information please see tag log below.
Please pull and let me know if there's any problem.
Thanks,
Saeed.
---
The following changes since commit c0b6edef0bf0e33c12eaf80c676ff09def011518:
tc-testing: Add newline when writing test case files (2018-03-30 14:22:51 -0400)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5-updates-2018-03-30
for you to fetch changes up to ab966d7e4ff988a48b3ad72e7abf903aa840afd1:
net/mlx5e: RX, Recycle buffer of UMR WQEs (2018-03-30 16:55:07 -0700)
----------------------------------------------------------------
mlx5-updates-2018-03-30
This series contains updates to mlx5 core and mlx5e netdev drivers.
The main highlight of this series is the RX optimizations for striding RQ path,
introduced by Tariq.
First Four patches are trivial misc cleanups.
- Spelling mistake fix
- Dead code removal
- Warning messages
RX optimizations for striding RQ:
1) RX refactoring, cleanups and micro optimizations
- MTU calculation simplifications, obsoletes some WQEs-to-packets translation
functions and helps delete ~60 LOC.
- Do not busy-wait a pending UMR completion.
- post the new values of UMR WQE inline, instead of using a data pointer.
- use pre-initialized structures to save calculations in datapath.
2) Use linear SKB in Striding RQ "build_skb", (Using linear SKB has many advantages):
- Saves a memcpy of the headers.
- No page-boundary checks in datapath.
- No filler CQEs.
- Significantly smaller CQ.
- SKB data continuously resides in linear part, and not split to
small amount (linear part) and large amount (fragment).
This saves datapath cycles in driver and improves utilization
of SKB fragments in GRO.
- The fragments of a resulting GRO SKB follow the IP forwarding
assumption of equal-size fragments.
implementation details:
HW writes the packets to the beginning of a stride,
i.e. does not keep headroom. To overcome this we make sure we can
extend backwards and use the last bytes of stride i-1.
Extra care is needed for stride 0 as it has no preceding stride.
We make sure headroom bytes are available by shifting the buffer
pointer passed to HW by headroom bytes.
This configuration now becomes default, whenever capable.
Of course, this implies turning LRO off.
Performance testing:
ConnectX-5, single core, single RX ring, default MTU.
UDP packet rate, early drop in TC layer:
--------------------------------------------
| pkt size | before | after | ratio |
--------------------------------------------
| 1500byte | 4.65 Mpps | 5.96 Mpps | 1.28x |
| 500byte | 5.23 Mpps | 5.97 Mpps | 1.14x |
| 64byte | 5.94 Mpps | 5.96 Mpps | 1.00x |
--------------------------------------------
TCP streams: ~20% gain
3) Support XDP over Striding RQ:
Now that linear SKB is supported over Striding RQ,
we can support XDP by setting stride size to PAGE_SIZE
and headroom to XDP_PACKET_HEADROOM.
Striding RQ is capable of a higher packet-rate than
conventional RQ.
Performance testing:
ConnectX-5, 24 rings, default MTU.
CQE compression ON (to reduce completions BW in PCI).
XDP_DROP packet rate:
--------------------------------------------------
| pkt size | XDP rate | 100GbE linerate | pct% |
--------------------------------------------------
| 64byte | 126.2 Mpps | 148.0 Mpps | 85% |
| 128byte | 80.0 Mpps | 84.8 Mpps | 94% |
| 256byte | 42.7 Mpps | 42.7 Mpps | 100% |
| 512byte | 23.4 Mpps | 23.4 Mpps | 100% |
--------------------------------------------------
4) Remove mlx5 page_ref bulking in Striding RQ and use page_ref_inc only when needed.
Without this bulking, we have:
- no atomic ops on WQE allocation or free
- one atomic op per SKB
- In the default MTU configuration (1500, stride size is 2K),
the non-bulking method execute 2 atomic ops as before
- For larger MTUs with stride size of 4K, non-bulking method
executes only a single op.
- For XDP (stride size of 4K, no SKBs), non-bulking have no atomic ops per packet at all.
Performance testing:
ConnectX-5, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz.
Single core packet rate (64 bytes).
Early drop in TC: no degradation.
XDP_DROP:
before: 14,270,188 pps
after: 20,503,603 pps, 43% improvement.
Thanks,
saeed.
----------------------------------------------------------------
Alaa Hleihel (1):
net/mlx5: Change teardown with force mode failure message to warning
Saeed Mahameed (2):
net/mlx5e: Use eq ptr from cq
net/mlx5: Eliminate query xsrq dead code
Talat Batheesh (1):
net/mlx5e: IPoIB, Fix spelling mistake
Tariq Toukan (11):
net/mlx5e: Save MTU in channels params
net/mlx5e: Derive Striding RQ size from MTU
net/mlx5e: Code movements in RX UMR WQE post
net/mlx5e: Do not busy-wait for UMR completion in Striding RQ
net/mlx5e: Use inline MTTs in UMR WQEs
net/mlx5e: Use linear SKB in Striding RQ
net/mlx5e: Refactor RQ XDP_TX indication
net/mlx5e: Support XDP over Striding RQ
net/mlx5e: Remove page_ref bulking in Striding RQ
net/mlx5e: Keep single pre-initialized UMR WQE per RQ
net/mlx5e: RX, Recycle buffer of UMR WQEs
drivers/net/ethernet/mellanox/mlx5/core/en.h | 115 ++++----
.../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 79 +-----
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 310 +++++++++++----------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 284 ++++++++++---------
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 2 +-
.../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 27 +-
.../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 21 --
include/linux/mlx5/device.h | 3 +
include/linux/mlx5/mlx5_ifc.h | 7 +-
include/linux/mlx5/transobj.h | 1 -
12 files changed, 409 insertions(+), 447 deletions(-)
^ permalink raw reply
* [net-next 03/15] net/mlx5: Change teardown with force mode failure message to warning
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Alaa Hleihel,
Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
From: Alaa Hleihel <alaa@mellanox.com>
With ConnectX-4, we expect the force teardown to fail in case that
DC was enabled, therefore change the message from error to warning.
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index d7bb10ab2173..70066975f1b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -245,7 +245,7 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev)
force_state = MLX5_GET(teardown_hca_out, out, force_state);
if (force_state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) {
- mlx5_core_err(dev, "teardown with force mode failed\n");
+ mlx5_core_warn(dev, "teardown with force mode failed, doing normal teardown\n");
return -EIO;
}
--
2.14.3
^ permalink raw reply related
* [net-next 01/15] net/mlx5e: Use eq ptr from cq
From: Saeed Mahameed @ 2018-03-31 0:02 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Jesper Dangaard Brouer, Saeed Mahameed
In-Reply-To: <20180331000252.30480-1-saeedm@mellanox.com>
Instead of looking for the EQ of the CQ, remove that redundant code and
use the eq pointer stored in the cq struct.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 14 ++------------
1 file changed, 2 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1b48dec67abf..2aff4db9bdaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3728,21 +3728,11 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
struct mlx5e_txqsq *sq)
{
- struct mlx5e_priv *priv = netdev_priv(dev);
- struct mlx5_core_dev *mdev = priv->mdev;
- int irqn_not_used, eqn;
- struct mlx5_eq *eq;
+ struct mlx5_eq *eq = sq->cq.mcq.eq;
u32 eqe_count;
- if (mlx5_vector2eqn(mdev, sq->cq.mcq.vector, &eqn, &irqn_not_used))
- return false;
-
- eq = mlx5_eqn2eq(mdev, eqn);
- if (IS_ERR(eq))
- return false;
-
netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
- eqn, eq->cons_index, eq->irqn);
+ eq->eqn, eq->cons_index, eq->irqn);
eqe_count = mlx5_eq_poll_irq_disabled(eq);
if (!eqe_count)
--
2.14.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox