/*
* The rps_sock_flow_table contains mappings of flows to the last CPU
* on which they were processed by the application (set in recvmsg).
+ * Each entry is a 32bit value. Upper part is the high order bits
+ * of flow hash, lower part is cpu number.
+ * rps_cpu_mask is used to partition the space, depending on number of
+ * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
+ * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f,
+ * meaning we use 32-6=26 bits for the hash.
*/
struct rps_sock_flow_table {
- unsigned int mask;
- u16 ents[0];
+ u32 mask;
+
+ u32 ents[0] ____cacheline_aligned_in_smp;
};
-#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
- ((_num) * sizeof(u16)))
+#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
#define RPS_NO_CPU 0xffff
+extern u32 rps_cpu_mask;
+extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
+
static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
u32 hash)
{
if (table && hash) {
- unsigned int cpu, index = hash & table->mask;
+ unsigned int index = hash & table->mask;
+ u32 val = hash & ~rps_cpu_mask;
/* We only give a hint, preemption can change cpu under us */
- cpu = raw_smp_processor_id();
+ val |= raw_smp_processor_id();
- if (table->ents[index] != cpu)
- table->ents[index] = cpu;
+ if (table->ents[index] != val)
+ table->ents[index] = val;
}
}
-static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
- u32 hash)
-{
- if (table && hash)
- table->ents[hash & table->mask] = RPS_NO_CPU;
-}
-
-extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
-
#ifdef CONFIG_RFS_ACCEL
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
u16 filter_id);
bool zero_okay,
__sum16 check)
{
- return (skb->ip_summed != CHECKSUM_PARTIAL &&
+ return ((skb->ip_summed != CHECKSUM_PARTIAL ||
+ skb_checksum_start_offset(skb) <
+ skb_gro_offset(skb)) &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
(!zero_okay || check));
}
compute_pseudo(skb, proto)); \
} while (0)
+struct gro_remcsum {
+ int offset;
+ __wsum delta;
+};
+
+static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
+{
+ grc->delta = 0;
+}
+
static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
- int start, int offset)
+ int start, int offset,
+ struct gro_remcsum *grc)
{
__wsum delta;
delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);
/* Adjust skb->csum since we changed the packet */
- skb->csum = csum_add(skb->csum, delta);
NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+ grc->offset = (ptr + offset) - (void *)skb->head;
+ grc->delta = delta;
}
+static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
+ struct gro_remcsum *grc)
+{
+ if (!grc->delta)
+ return;
+
+ remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta);
+}
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,