net: thunderx: Adjust nicvf structure to reduce cache misses

Adjusted nicvf structure such that all elements used in hot
path like napi, xmit e.t.c fall into same cache line. This reduced
no of cache misses and resulted in ~2% increase in no of packets
handled on a core.

Also modified elements with :1 notation to boolean, to be
consistent with other element definitions.

Signed-off-by: Sunil Goutham <sgoutham@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 872b22d831ee69f3b91ad62c5c7be83b6ed8eb26..83025bb4737c47c44b2056190b68c0acc5461ed9 100644 (file)
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -272,46 +272,54 @@ struct nicvf {
        struct nicvf            *pnicvf;
        struct net_device       *netdev;
        struct pci_dev          *pdev;
+       void __iomem            *reg_base;
+       struct queue_set        *qs;
+       struct nicvf_cq_poll    *napi[8];
        u8                      vf_id;
-       u8                      node;
-       u8                      tns_mode:1;
-       u8                      sqs_mode:1;
-       u8                      loopback_supported:1;
+       u8                      sqs_id;
+       bool                    sqs_mode;
        bool                    hw_tso;
-       u16                     mtu;
-       struct queue_set        *qs;
+
+       /* Receive buffer alloc */
+       u32                     rb_page_offset;
+       u16                     rb_pageref;
+       bool                    rb_alloc_fail;
+       bool                    rb_work_scheduled;
+       struct page             *rb_page;
+       struct delayed_work     rbdr_work;
+       struct tasklet_struct   rbdr_task;
+
+       /* Secondary Qset */
+       u8                      sqs_count;
 #define        MAX_SQS_PER_VF_SINGLE_NODE              5
 #define        MAX_SQS_PER_VF                          11
-       u8                      sqs_id;
-       u8                      sqs_count; /* Secondary Qset count */
        struct nicvf            *snicvf[MAX_SQS_PER_VF];
+
+       /* Queue count */
        u8                      rx_queues;
        u8                      tx_queues;
        u8                      max_queues;
-       void __iomem            *reg_base;
+
+       u8                      node;
+       u8                      cpi_alg;
+       u16                     mtu;
        bool                    link_up;
        u8                      duplex;
        u32                     speed;
-       struct page             *rb_page;
-       u32                     rb_page_offset;
-       u16                     rb_pageref;
-       bool                    rb_alloc_fail;
-       bool                    rb_work_scheduled;
-       struct delayed_work     rbdr_work;
-       struct tasklet_struct   rbdr_task;
-       struct tasklet_struct   qs_err_task;
-       struct tasklet_struct   cq_task;
-       struct nicvf_cq_poll    *napi[8];
+       bool                    tns_mode;
+       bool                    loopback_supported;
        struct nicvf_rss_info   rss_info;
-       u8                      cpi_alg;
+       struct tasklet_struct   qs_err_task;
+       struct work_struct      reset_task;
+
        /* Interrupt coalescing settings */
        u32                     cq_coalesce_usecs;
-
        u32                     msg_enable;
+
+       /* Stats */
        struct nicvf_hw_stats   hw_stats;
        struct nicvf_drv_stats  drv_stats;
        struct bgx_stats        bgx_stats;
-       struct work_struct      reset_task;
 
        /* MSI-X  */
        bool                    msix_enabled;