提交 cdcfeb0f 编写于 作者: Y Yan Markman 提交者: David S. Miller

net: mvpp2: Use relaxed I/O in data path

Use relaxed I/O on the hot path. This achieves significant performance
improvements. On a 10G link, this makes a basic iperf TCP test go from
an average of 4.5 Gbits/sec to about 9.40 Gbits/sec.
Signed-off-by: NYan Markman <ymarkman@marvell.com>
[Maxime: Commit message, cosmetic changes]
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 5f75a186
master alk-4.19.24 alk-4.19.30 alk-4.19.34 alk-4.19.36 alk-4.19.43 alk-4.19.48 alk-4.19.57 ck-4.19.67 ck-4.19.81 ck-4.19.91 github/fork/deepanshu1422/fix-typo-in-comment github/fork/haosdent/fix-typo linux-next v4.19.91 v4.19.90 v4.19.89 v4.19.88 v4.19.87 v4.19.86 v4.19.85 v4.19.84 v4.19.83 v4.19.82 v4.19.81 v4.19.80 v4.19.79 v4.19.78 v4.19.77 v4.19.76 v4.19.75 v4.19.74 v4.19.73 v4.19.72 v4.19.71 v4.19.70 v4.19.69 v4.19.68 v4.19.67 v4.19.66 v4.19.65 v4.19.64 v4.19.63 v4.19.62 v4.19.61 v4.19.60 v4.19.59 v4.19.58 v4.19.57 v4.19.56 v4.19.55 v4.19.54 v4.19.53 v4.19.52 v4.19.51 v4.19.50 v4.19.49 v4.19.48 v4.19.47 v4.19.46 v4.19.45 v4.19.44 v4.19.43 v4.19.42 v4.19.41 v4.19.40 v4.19.39 v4.19.38 v4.19.37 v4.19.36 v4.19.35 v4.19.34 v4.19.33 v4.19.32 v4.19.31 v4.19.30 v4.19.29 v4.19.28 v4.19.27 v4.19.26 v4.19.25 v4.19.24 v4.19.23 v4.19.22 v4.19.21 v4.19.20 v4.19.19 v4.19.18 v4.19.17 v4.19.16 v4.19.15 v4.19.14 v4.19.13 v4.19.12 v4.19.11 v4.19.10 v4.19.9 v4.19.8 v4.19.7 v4.19.6 v4.19.5 v4.19.4 v4.19.3 v4.19.2 v4.19.1 v4.19 v4.19-rc8 v4.19-rc7 v4.19-rc6 v4.19-rc5 v4.19-rc4 v4.19-rc3 v4.19-rc2 v4.19-rc1 ck-release-21 ck-release-20 ck-release-19.2 ck-release-19.1 ck-release-19 ck-release-18 ck-release-17.2 ck-release-17.1 ck-release-17 ck-release-16 ck-release-15.1 ck-release-15 ck-release-14 ck-release-13.2 ck-release-13 ck-release-12 ck-release-11 ck-release-10 ck-release-9 ck-release-7 alk-release-15 alk-release-14 alk-release-13.2 alk-release-13 alk-release-12 alk-release-11 alk-release-10 alk-release-9 alk-release-7
无相关合并请求
......@@ -1359,6 +1359,10 @@ static u32 mvpp2_read(struct mvpp2 *priv, u32 offset)
return readl(priv->swth_base[0] + offset);
}
static u32 mvpp2_read_relaxed(struct mvpp2 *priv, u32 offset)
{
return readl_relaxed(priv->swth_base[0] + offset);
}
/* These accessors should be used to access:
*
* - per-CPU registers, where each CPU has its own copy of the
......@@ -1407,6 +1411,18 @@ static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu,
return readl(priv->swth_base[cpu] + offset);
}
static void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu,
u32 offset, u32 data)
{
writel_relaxed(data, priv->swth_base[cpu] + offset);
}
static u32 mvpp2_percpu_read_relaxed(struct mvpp2 *priv, int cpu,
u32 offset)
{
return readl_relaxed(priv->swth_base[cpu] + offset);
}
static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
struct mvpp2_tx_desc *tx_desc)
{
......@@ -4442,8 +4458,8 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool,
<< MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT) &
MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK;
mvpp2_percpu_write(port->priv, cpu,
MVPP22_BM_ADDR_HIGH_RLS_REG, val);
mvpp2_percpu_write_relaxed(port->priv, cpu,
MVPP22_BM_ADDR_HIGH_RLS_REG, val);
}
/* MVPP2_BM_VIRT_RLS_REG is not interpreted by HW, and simply
......@@ -4451,10 +4467,10 @@ static inline void mvpp2_bm_pool_put(struct mvpp2_port *port, int pool,
* descriptor. Instead of storing the virtual address, we
* store the physical address
*/
mvpp2_percpu_write(port->priv, cpu,
MVPP2_BM_VIRT_RLS_REG, buf_phys_addr);
mvpp2_percpu_write(port->priv, cpu,
MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr);
mvpp2_percpu_write_relaxed(port->priv, cpu,
MVPP2_BM_VIRT_RLS_REG, buf_phys_addr);
mvpp2_percpu_write_relaxed(port->priv, cpu,
MVPP2_BM_PHY_RLS_REG(pool), buf_dma_addr);
put_cpu();
}
......@@ -5546,7 +5562,8 @@ static int mvpp2_aggr_desc_num_check(struct mvpp2 *priv,
if ((aggr_txq->count + num) > MVPP2_AGGR_TXQ_SIZE) {
/* Update number of occupied aggregated Tx descriptors */
int cpu = smp_processor_id();
u32 val = mvpp2_read(priv, MVPP2_AGGR_TXQ_STATUS_REG(cpu));
u32 val = mvpp2_read_relaxed(priv,
MVPP2_AGGR_TXQ_STATUS_REG(cpu));
aggr_txq->count = val & MVPP2_AGGR_TXQ_PENDING_MASK;
}
......@@ -5570,9 +5587,9 @@ static int mvpp2_txq_alloc_reserved_desc(struct mvpp2 *priv,
int cpu = smp_processor_id();
val = (txq->id << MVPP2_TXQ_RSVD_REQ_Q_OFFSET) | num;
mvpp2_percpu_write(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val);
mvpp2_percpu_write_relaxed(priv, cpu, MVPP2_TXQ_RSVD_REQ_REG, val);
val = mvpp2_percpu_read(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG);
val = mvpp2_percpu_read_relaxed(priv, cpu, MVPP2_TXQ_RSVD_RSLT_REG);
return val & MVPP2_TXQ_RSVD_RSLT_MASK;
}
......@@ -5677,8 +5694,8 @@ static inline int mvpp2_txq_sent_desc_proc(struct mvpp2_port *port,
u32 val;
/* Reading status reg resets transmitted descriptor counter */
val = mvpp2_percpu_read(port->priv, smp_processor_id(),
MVPP2_TXQ_SENT_REG(txq->id));
val = mvpp2_percpu_read_relaxed(port->priv, smp_processor_id(),
MVPP2_TXQ_SENT_REG(txq->id));
return (val & MVPP2_TRANSMITTED_COUNT_MASK) >>
MVPP2_TRANSMITTED_COUNT_OFFSET;
......@@ -7044,8 +7061,8 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
*
* Each CPU has its own Rx/Tx cause register
*/
cause_rx_tx = mvpp2_percpu_read(port->priv, qv->sw_thread_id,
MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
cause_rx_tx = mvpp2_percpu_read_relaxed(port->priv, qv->sw_thread_id,
MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
if (cause_misc) {
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部