summaryrefslogtreecommitdiff
path: root/net/core/gro.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/gro.c')
-rw-r--r--net/core/gro.c327
1 files changed, 179 insertions, 148 deletions
diff --git a/net/core/gro.c b/net/core/gro.c
index 506f83d715f8..76f9c3712422 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -1,18 +1,14 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+#include <net/psp.h>
#include <net/gro.h>
#include <net/dst_metadata.h>
#include <net/busy_poll.h>
#include <trace/events/net.h>
+#include <linux/skbuff_ref.h>
#define MAX_GRO_SKBS 8
-/* This should be increased if a protocol with a bigger head is added. */
-#define GRO_MAX_HEAD (MAX_HEADER + 128)
-
static DEFINE_SPINLOCK(offload_lock);
-static struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base);
-/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */
-int gro_normal_batch __read_mostly = 8;
/**
* dev_add_offload - register offload handlers
@@ -31,7 +27,7 @@ void dev_add_offload(struct packet_offload *po)
struct packet_offload *elem;
spin_lock(&offload_lock);
- list_for_each_entry(elem, &offload_base, list) {
+ list_for_each_entry(elem, &net_hotdata.offload_base, list) {
if (po->priority < elem->priority)
break;
}
@@ -55,7 +51,7 @@ EXPORT_SYMBOL(dev_add_offload);
*/
static void __dev_remove_offload(struct packet_offload *po)
{
- struct list_head *head = &offload_base;
+ struct list_head *head = &net_hotdata.offload_base;
struct packet_offload *po1;
spin_lock(&offload_lock);
@@ -92,63 +88,6 @@ void dev_remove_offload(struct packet_offload *po)
}
EXPORT_SYMBOL(dev_remove_offload);
-/**
- * skb_eth_gso_segment - segmentation handler for ethernet protocols.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- * @type: Ethernet Protocol ID
- */
-struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb,
- netdev_features_t features, __be16 type)
-{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
-
- rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
- if (ptype->type == type && ptype->callbacks.gso_segment) {
- segs = ptype->callbacks.gso_segment(skb, features);
- break;
- }
- }
- rcu_read_unlock();
-
- return segs;
-}
-EXPORT_SYMBOL(skb_eth_gso_segment);
-
-/**
- * skb_mac_gso_segment - mac layer segmentation handler.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- */
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
-{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
- int vlan_depth = skb->mac_len;
- __be16 type = skb_network_protocol(skb, &vlan_depth);
-
- if (unlikely(!type))
- return ERR_PTR(-EINVAL);
-
- __skb_pull(skb, vlan_depth);
-
- rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
- if (ptype->type == type && ptype->callbacks.gso_segment) {
- segs = ptype->callbacks.gso_segment(skb, features);
- break;
- }
- }
- rcu_read_unlock();
-
- __skb_push(skb, skb->data - skb_mac_header(skb));
-
- return segs;
-}
-EXPORT_SYMBOL(skb_mac_gso_segment);
int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
{
@@ -157,21 +96,27 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
unsigned int headlen = skb_headlen(skb);
unsigned int len = skb_gro_len(skb);
unsigned int delta_truesize;
- unsigned int gro_max_size;
unsigned int new_truesize;
struct sk_buff *lp;
int segs;
- /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */
- gro_max_size = READ_ONCE(p->dev->gro_max_size);
+ /* Do not splice page pool based packets w/ non-page pool
+ * packets. This can result in reference count issues as page
+ * pool pages will not decrement the reference count and will
+ * instead be immediately returned to the pool or have frag
+ * count decremented.
+ */
+ if (p->pp_recycle != skb->pp_recycle)
+ return -ETOOMANYREFS;
- if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
+ if (unlikely(p->len + len >= netif_get_gro_max_size(p->dev, p) ||
+ NAPI_GRO_CB(skb)->flush))
return -E2BIG;
if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
- if (p->protocol != htons(ETH_P_IPV6) ||
- skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
- ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+ if (NAPI_GRO_CB(skb)->proto != IPPROTO_TCP ||
+ (p->protocol == htons(ETH_P_IPV6) &&
+ skb_headroom(p) < sizeof(struct hop_jumbo_hdr)) ||
p->encapsulation)
return -E2BIG;
}
@@ -228,9 +173,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags;
- __skb_frag_set_page(frag, page);
- skb_frag_off_set(frag, first_offset);
- skb_frag_size_set(frag, first_size);
+ skb_frag_fill_page_desc(frag, page, first_offset, first_size);
memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
/* We dont need to clear skbinfo->nr_frags here */
@@ -243,8 +186,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
}
merge:
- /* sk owenrship - if any - completely transferred to the aggregated packet */
+ /* sk ownership - if any - completely transferred to the aggregated packet */
skb->destructor = NULL;
+ skb->sk = NULL;
delta_truesize = skb->truesize;
if (offset > headlen) {
unsigned int eat = offset - headlen;
@@ -280,12 +224,38 @@ done:
return 0;
}
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
+{
+ if (unlikely(p->len + skb->len >= 65536))
+ return -E2BIG;
+
+ if (NAPI_GRO_CB(p)->last == p)
+ skb_shinfo(p)->frag_list = skb;
+ else
+ NAPI_GRO_CB(p)->last->next = skb;
+
+ skb_pull(skb, skb_gro_offset(skb));
+
+ NAPI_GRO_CB(p)->last = skb;
+ NAPI_GRO_CB(p)->count++;
+ p->data_len += skb->len;
+
+ /* sk ownership - if any - completely transferred to the aggregated packet */
+ skb->destructor = NULL;
+ skb->sk = NULL;
+ p->truesize += skb->truesize;
+ p->len += skb->len;
+
+ NAPI_GRO_CB(skb)->same_flow = 1;
+
+ return 0;
+}
-static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
+static void gro_complete(struct gro_node *gro, struct sk_buff *skb)
{
+ struct list_head *head = &net_hotdata.offload_base;
struct packet_offload *ptype;
__be16 type = skb->protocol;
- struct list_head *head = &offload_base;
int err = -ENOENT;
BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb));
@@ -314,43 +284,61 @@ static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
}
out:
- gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count);
+ gro_normal_one(gro, skb, NAPI_GRO_CB(skb)->count);
}
-static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
- bool flush_old)
+static void __gro_flush_chain(struct gro_node *gro, u32 index, bool flush_old)
{
- struct list_head *head = &napi->gro_hash[index].list;
+ struct list_head *head = &gro->hash[index].list;
struct sk_buff *skb, *p;
list_for_each_entry_safe_reverse(skb, p, head, list) {
if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
return;
skb_list_del_init(skb);
- napi_gro_complete(napi, skb);
- napi->gro_hash[index].count--;
+ gro_complete(gro, skb);
+ gro->hash[index].count--;
}
- if (!napi->gro_hash[index].count)
- __clear_bit(index, &napi->gro_bitmask);
+ if (!gro->hash[index].count)
+ __clear_bit(index, &gro->bitmask);
}
-/* napi->gro_hash[].list contains packets ordered by age.
+/*
+ * gro->hash[].list contains packets ordered by age.
* youngest packets at the head of it.
* Complete skbs in reverse order to reduce latencies.
*/
-void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+void __gro_flush(struct gro_node *gro, bool flush_old)
{
- unsigned long bitmask = napi->gro_bitmask;
+ unsigned long bitmask = gro->bitmask;
unsigned int i, base = ~0U;
while ((i = ffs(bitmask)) != 0) {
bitmask >>= i;
base += i;
- __napi_gro_flush_chain(napi, base, flush_old);
+ __gro_flush_chain(gro, base, flush_old);
}
}
-EXPORT_SYMBOL(napi_gro_flush);
+EXPORT_SYMBOL(__gro_flush);
+
+static unsigned long gro_list_prepare_tc_ext(const struct sk_buff *skb,
+ const struct sk_buff *p,
+ unsigned long diffs)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ struct tc_skb_ext *skb_ext;
+ struct tc_skb_ext *p_ext;
+
+ skb_ext = skb_ext_find(skb, TC_SKB_EXT);
+ p_ext = skb_ext_find(p, TC_SKB_EXT);
+
+ diffs |= (!!p_ext) ^ (!!skb_ext);
+ if (!diffs && unlikely(skb_ext))
+ diffs |= p_ext->chain ^ skb_ext->chain;
+#endif
+ return diffs;
+}
static void gro_list_prepare(const struct list_head *head,
const struct sk_buff *skb)
@@ -362,8 +350,6 @@ static void gro_list_prepare(const struct list_head *head,
list_for_each_entry(p, head, list) {
unsigned long diffs;
- NAPI_GRO_CB(p)->flush = 0;
-
if (hash != skb_get_hash_raw(p)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
@@ -380,29 +366,18 @@ static void gro_list_prepare(const struct list_head *head,
skb_mac_header(skb),
maclen);
- /* in most common scenarions 'slow_gro' is 0
+ /* in most common scenarios 'slow_gro' is 0
* otherwise we are already on some slower paths
* either skip all the infrequent tests altogether or
* avoid trying too hard to skip each of them individually
*/
if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) {
-#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- struct tc_skb_ext *skb_ext;
- struct tc_skb_ext *p_ext;
-#endif
-
diffs |= p->sk != skb->sk;
diffs |= skb_metadata_dst_cmp(p, skb);
diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
-#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- skb_ext = skb_ext_find(skb, TC_SKB_EXT);
- p_ext = skb_ext_find(p, TC_SKB_EXT);
-
- diffs |= (!!p_ext) ^ (!!skb_ext);
- if (!diffs && unlikely(skb_ext))
- diffs |= p_ext->chain ^ skb_ext->chain;
-#endif
+ diffs |= gro_list_prepare_tc_ext(skb, p, diffs);
+ diffs |= __psp_skb_coalesce_diff(skb, p, diffs);
}
NAPI_GRO_CB(p)->same_flow = !diffs;
@@ -411,14 +386,22 @@ static void gro_list_prepare(const struct list_head *head,
static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
{
- const struct skb_shared_info *pinfo = skb_shinfo(skb);
- const skb_frag_t *frag0 = &pinfo->frags[0];
+ const struct skb_shared_info *pinfo;
+ const skb_frag_t *frag0;
+ unsigned int headlen;
+ NAPI_GRO_CB(skb)->network_offset = 0;
NAPI_GRO_CB(skb)->data_offset = 0;
- NAPI_GRO_CB(skb)->frag0 = NULL;
- NAPI_GRO_CB(skb)->frag0_len = 0;
+ headlen = skb_headlen(skb);
+ NAPI_GRO_CB(skb)->frag0 = skb->data;
+ NAPI_GRO_CB(skb)->frag0_len = headlen;
+ if (headlen)
+ return;
+
+ pinfo = skb_shinfo(skb);
+ frag0 = &pinfo->frags[0];
- if (!skb_headlen(skb) && pinfo->nr_frags &&
+ if (pinfo->nr_frags && skb_frag_page(frag0) &&
!PageHighMem(skb_frag_page(frag0)) &&
(!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
@@ -449,7 +432,15 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
}
}
-static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
+static void gro_try_pull_from_frag0(struct sk_buff *skb)
+{
+ int grow = skb_gro_offset(skb) - skb_headlen(skb);
+
+ if (grow > 0)
+ gro_pull_from_frag0(skb, grow);
+}
+
+static void gro_flush_oldest(struct gro_node *gro, struct list_head *head)
{
struct sk_buff *oldest;
@@ -465,20 +456,20 @@ static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
* SKB to the chain.
*/
skb_list_del_init(oldest);
- napi_gro_complete(napi, oldest);
+ gro_complete(gro, oldest);
}
-static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static enum gro_result dev_gro_receive(struct gro_node *gro,
+ struct sk_buff *skb)
{
u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
- struct gro_list *gro_list = &napi->gro_hash[bucket];
- struct list_head *head = &offload_base;
+ struct list_head *head = &net_hotdata.offload_base;
+ struct gro_list *gro_list = &gro->hash[bucket];
struct packet_offload *ptype;
__be16 type = skb->protocol;
struct sk_buff *pp = NULL;
enum gro_result ret;
int same_flow;
- int grow;
if (netif_elide_gro(skb->dev))
goto normal;
@@ -501,7 +492,6 @@ found_ptype:
sizeof(u32))); /* Avoid slow unaligned acc */
*(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0;
NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb);
- NAPI_GRO_CB(skb)->is_atomic = 1;
NAPI_GRO_CB(skb)->count = 1;
if (unlikely(skb_is_gso(skb))) {
NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
@@ -538,7 +528,7 @@ found_ptype:
if (pp) {
skb_list_del_init(pp);
- napi_gro_complete(napi, pp);
+ gro_complete(gro, pp);
gro_list->count--;
}
@@ -549,39 +539,37 @@ found_ptype:
goto normal;
if (unlikely(gro_list->count >= MAX_GRO_SKBS))
- gro_flush_oldest(napi, &gro_list->list);
+ gro_flush_oldest(gro, &gro_list->list);
else
gro_list->count++;
+ /* Must be called before setting NAPI_GRO_CB(skb)->{age|last} */
+ gro_try_pull_from_frag0(skb);
NAPI_GRO_CB(skb)->age = jiffies;
NAPI_GRO_CB(skb)->last = skb;
if (!skb_is_gso(skb))
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
list_add(&skb->list, &gro_list->list);
ret = GRO_HELD;
-
-pull:
- grow = skb_gro_offset(skb) - skb_headlen(skb);
- if (grow > 0)
- gro_pull_from_frag0(skb, grow);
ok:
if (gro_list->count) {
- if (!test_bit(bucket, &napi->gro_bitmask))
- __set_bit(bucket, &napi->gro_bitmask);
- } else if (test_bit(bucket, &napi->gro_bitmask)) {
- __clear_bit(bucket, &napi->gro_bitmask);
+ if (!test_bit(bucket, &gro->bitmask))
+ __set_bit(bucket, &gro->bitmask);
+ } else if (test_bit(bucket, &gro->bitmask)) {
+ __clear_bit(bucket, &gro->bitmask);
}
return ret;
normal:
ret = GRO_NORMAL;
- goto pull;
+ gro_try_pull_from_frag0(skb);
+ goto ok;
}
struct packet_offload *gro_find_receive_by_type(__be16 type)
{
- struct list_head *offload_head = &offload_base;
+ struct list_head *offload_head = &net_hotdata.offload_base;
struct packet_offload *ptype;
list_for_each_entry_rcu(ptype, offload_head, list) {
@@ -595,7 +583,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type);
struct packet_offload *gro_find_complete_by_type(__be16 type)
{
- struct list_head *offload_head = &offload_base;
+ struct list_head *offload_head = &net_hotdata.offload_base;
struct packet_offload *ptype;
list_for_each_entry_rcu(ptype, offload_head, list) {
@@ -607,13 +595,12 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
}
EXPORT_SYMBOL(gro_find_complete_by_type);
-static gro_result_t napi_skb_finish(struct napi_struct *napi,
- struct sk_buff *skb,
- gro_result_t ret)
+static gro_result_t gro_skb_finish(struct gro_node *gro, struct sk_buff *skb,
+ gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
- gro_normal_one(napi, skb, 1);
+ gro_normal_one(gro, skb, 1);
break;
case GRO_MERGED_FREE:
@@ -622,7 +609,7 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
else if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
__kfree_skb(skb);
else
- __kfree_skb_defer(skb);
+ __napi_kfree_skb(skb, SKB_CONSUMED);
break;
case GRO_HELD:
@@ -634,24 +621,26 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
return ret;
}
-gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb)
{
gro_result_t ret;
- skb_mark_napi_id(skb, napi);
+ __skb_mark_napi_id(skb, gro);
trace_napi_gro_receive_entry(skb);
skb_gro_reset_offset(skb, 0);
- ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
+ ret = gro_skb_finish(gro, skb, dev_gro_receive(gro, skb));
trace_napi_gro_receive_exit(ret);
return ret;
}
-EXPORT_SYMBOL(napi_gro_receive);
+EXPORT_SYMBOL(gro_receive_skb);
static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
+ struct skb_shared_info *shinfo;
+
if (unlikely(skb->pfmemalloc)) {
consume_skb(skb);
return;
@@ -667,8 +656,13 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0;
- skb_shinfo(skb)->gso_type = 0;
- skb_shinfo(skb)->gso_size = 0;
+ skb->ip_summed = CHECKSUM_NONE;
+
+ shinfo = skb_shinfo(skb);
+ shinfo->gso_type = 0;
+ shinfo->gso_size = 0;
+ shinfo->hwtstamps.hwtstamp = 0;
+
if (unlikely(skb->slow_gro)) {
skb_orphan(skb);
skb_ext_reset(skb);
@@ -704,7 +698,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
__skb_push(skb, ETH_HLEN);
skb->protocol = eth_type_trans(skb, skb->dev);
if (ret == GRO_NORMAL)
- gro_normal_one(napi, skb, 1);
+ gro_normal_one(&napi->gro, skb, 1);
break;
case GRO_MERGED_FREE:
@@ -737,7 +731,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
skb_reset_mac_header(skb);
skb_gro_reset_offset(skb, hlen);
- if (unlikely(skb_gro_header_hard(skb, hlen))) {
+ if (unlikely(!skb_gro_may_pull(skb, hlen))) {
eth = skb_gro_header_slow(skb, hlen, 0);
if (unlikely(!eth)) {
net_warn_ratelimited("%s: dropping impossible skb from %s\n",
@@ -747,7 +741,10 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
}
} else {
eth = (const struct ethhdr *)skb->data;
- gro_pull_from_frag0(skb, hlen);
+
+ if (NAPI_GRO_CB(skb)->frag0 != skb->data)
+ gro_pull_from_frag0(skb, hlen);
+
NAPI_GRO_CB(skb)->frag0 += hlen;
NAPI_GRO_CB(skb)->frag0_len -= hlen;
}
@@ -770,7 +767,7 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
trace_napi_gro_frags_entry(skb);
- ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+ ret = napi_frags_finish(napi, skb, dev_gro_receive(&napi->gro, skb));
trace_napi_gro_frags_exit(ret);
return ret;
@@ -802,3 +799,37 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
return sum;
}
EXPORT_SYMBOL(__skb_gro_checksum_complete);
+
+void gro_init(struct gro_node *gro)
+{
+ for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) {
+ INIT_LIST_HEAD(&gro->hash[i].list);
+ gro->hash[i].count = 0;
+ }
+
+ gro->bitmask = 0;
+ gro->cached_napi_id = 0;
+
+ INIT_LIST_HEAD(&gro->rx_list);
+ gro->rx_count = 0;
+}
+
+void gro_cleanup(struct gro_node *gro)
+{
+ struct sk_buff *skb, *n;
+
+ for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) {
+ list_for_each_entry_safe(skb, n, &gro->hash[i].list, list)
+ kfree_skb(skb);
+
+ gro->hash[i].count = 0;
+ }
+
+ gro->bitmask = 0;
+ gro->cached_napi_id = 0;
+
+ list_for_each_entry_safe(skb, n, &gro->rx_list, list)
+ kfree_skb(skb);
+
+ gro->rx_count = 0;
+}