| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 10 Sep 2012 09:38:04 +0200
From: Giuseppe CAVALLARO <peppe.cavallaro@...com>
To: netdev@...r.kernel.org
Cc: bhutchings@...arflare.com, davem@...emloft.net,
Giuseppe Cavallaro <peppe.cavallaro@...com>
Subject: [net-next.git 3/8 (V2)] stmmac: add the initial tx coalesce schema
This patch adds a new schema used for mitigating the
number of transmit interrupts.
It is based on a sw timer and a threshold value.
The timer is used to periodically call the stmmac_tx
function that can be invoked by the ISR but only for
the descriptors where the interrupt on completion
field has been set. This is tuned by a threshold.
Next step is to add the ability to tune these coalesce
values by ethtool.
Till now I have put a default that showed a real gain
on all the platforms ARM/SH4 where I performed benchmarks.
V2: review the logic to manage the IC bit in the TDESC
that was bugged because it didn't take care about the
fragments. Also fix the tx_count_frames that has not to be
limited to TX DMA ring. Thanks to Ben Hutchings.
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@...com>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 8 +-
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 4 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 9 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 92 ++++++++++++--------
4 files changed, 69 insertions(+), 44 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index bd32fe6..1d6bd3e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -95,11 +95,13 @@ struct stmmac_extra_stats {
unsigned long threshold;
unsigned long tx_pkt_n;
unsigned long rx_pkt_n;
- unsigned long rx_napi_poll;
+ unsigned long normal_irq_n;
unsigned long rx_normal_irq_n;
+ unsigned long rx_napi_poll;
unsigned long tx_normal_irq_n;
- unsigned long sched_timer_n;
- unsigned long normal_irq_n;
+ unsigned long txtimer;
+ unsigned long tx_clean;
+ unsigned long tx_reset_ic_bit;
unsigned long mmc_tx_irq_n;
unsigned long mmc_rx_irq_n;
unsigned long mmc_rx_csum_offload_irq_n;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 9f35769..0f5ab28 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -88,6 +88,10 @@ struct stmmac_priv {
int eee_enabled;
int eee_active;
int tx_lpi_timer;
+ struct timer_list txtimer;
+ u32 tx_count_frames;
+ u32 tx_coal_frames;
+ u32 tx_coal_timer;
};
extern int phyaddr;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 505fe71..48ad0bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -90,12 +90,13 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
STMMAC_STAT(threshold),
STMMAC_STAT(tx_pkt_n),
STMMAC_STAT(rx_pkt_n),
- STMMAC_STAT(rx_napi_poll),
+ STMMAC_STAT(normal_irq_n),
STMMAC_STAT(rx_normal_irq_n),
+ STMMAC_STAT(rx_napi_poll),
STMMAC_STAT(tx_normal_irq_n),
- STMMAC_STAT(sched_timer_n),
- STMMAC_STAT(normal_irq_n),
- STMMAC_STAT(normal_irq_n),
+ STMMAC_STAT(txtimer),
+ STMMAC_STAT(tx_clean),
+ STMMAC_STAT(tx_reset_ic_bit),
STMMAC_STAT(mmc_tx_irq_n),
STMMAC_STAT(mmc_rx_irq_n),
STMMAC_STAT(mmc_rx_csum_offload_irq_n),
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8e1e53e..3df3c3b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -77,6 +77,8 @@
#define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x)
#define JUMBO_LEN 9000
+#define STMMAC_TX_TM 40000
+#define STMMAC_TX_MAX_FRAMES 32 /* Max coalesced frame */
/* Module parameters */
#define TX_TIMEO 5000 /* default 5 seconds */
@@ -695,8 +697,11 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
static void stmmac_tx(struct stmmac_priv *priv)
{
unsigned int txsize = priv->dma_tx_size;
+ unsigned long flags;
+
+ spin_lock_irqsave(&priv->tx_lock, flags);
- spin_lock(&priv->tx_lock);
+ priv->xstats.tx_clean++;
while (priv->dirty_tx != priv->cur_tx) {
int last;
@@ -741,7 +746,7 @@ static void stmmac_tx(struct stmmac_priv *priv)
skb_recycle_check(skb, priv->dma_buf_sz))
__skb_queue_head(&priv->rx_recycle, skb);
else
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
priv->tx_skbuff[entry] = NULL;
}
@@ -765,7 +770,7 @@ static void stmmac_tx(struct stmmac_priv *priv)
stmmac_enable_eee_mode(priv);
mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
}
- spin_unlock(&priv->tx_lock);
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
}
static inline void stmmac_enable_irq(struct stmmac_priv *priv)
@@ -778,29 +783,12 @@ static inline void stmmac_disable_irq(struct stmmac_priv *priv)
priv->hw->dma->disable_dma_irq(priv->ioaddr);
}
-static int stmmac_has_work(struct stmmac_priv *priv)
+static void stmmac_txtimer(unsigned long data)
{
- unsigned int has_work = 0;
- int rxret, tx_work = 0;
-
- rxret = priv->hw->desc->get_rx_owner(priv->dma_rx +
- (priv->cur_rx % priv->dma_rx_size));
-
- if (priv->dirty_tx != priv->cur_tx)
- tx_work = 1;
-
- if (likely(!rxret || tx_work))
- has_work = 1;
+ struct stmmac_priv *priv = (struct stmmac_priv *)data;
- return has_work;
-}
-
-static inline void _stmmac_schedule(struct stmmac_priv *priv)
-{
- if (likely(stmmac_has_work(priv))) {
- stmmac_disable_irq(priv);
- napi_schedule(&priv->napi);
- }
+ priv->xstats.txtimer++;
+ stmmac_tx(priv);
}
/**
@@ -824,7 +812,7 @@ static void stmmac_tx_err(struct stmmac_priv *priv)
netif_wake_queue(priv->dev);
}
-static inline void stmmac_rx_schedule(struct stmmac_priv *priv)
+static void stmmac_rx_schedule(struct stmmac_priv *priv)
{
if (likely(napi_schedule_prep(&priv->napi))) {
stmmac_disable_irq(priv);
@@ -1001,6 +989,18 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
priv->dma_rx_phy);
}
+static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
+{
+ /* Set Tx coalesce parameters and timers */
+ priv->tx_coal_frames = STMMAC_TX_MAX_FRAMES;
+ priv->tx_coal_timer = jiffies + usecs_to_jiffies(STMMAC_TX_TM);
+ init_timer(&priv->txtimer);
+ priv->txtimer.expires = priv->tx_coal_timer;
+ priv->txtimer.data = (unsigned long)priv;
+ priv->txtimer.function = stmmac_txtimer;
+ add_timer(&priv->txtimer);
+}
+
/**
* stmmac_open - open entry point of the driver
* @dev : pointer to the device structure.
@@ -1113,6 +1113,8 @@ static int stmmac_open(struct net_device *dev)
priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS_TIMER;
priv->eee_enabled = stmmac_eee_init(priv);
+ stmmac_init_tx_coalesce(priv);
+
napi_enable(&priv->napi);
skb_queue_head_init(&priv->rx_recycle);
netif_start_queue(dev);
@@ -1160,6 +1162,8 @@ static int stmmac_release(struct net_device *dev)
napi_disable(&priv->napi);
skb_queue_purge(&priv->rx_recycle);
+ del_timer_sync(&priv->txtimer);
+
/* Free the IRQ lines */
free_irq(dev->irq, dev);
if (priv->wol_irq != dev->irq)
@@ -1202,6 +1206,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
int nfrags = skb_shinfo(skb)->nr_frags;
struct dma_desc *desc, *first;
unsigned int nopaged_len = skb_headlen(skb);
+ unsigned long flags;
if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
if (!netif_queue_stopped(dev)) {
@@ -1213,7 +1218,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_BUSY;
}
- spin_lock(&priv->tx_lock);
+ spin_lock_irqsave(&priv->tx_lock, flags);
if (priv->tx_path_in_lpi_mode)
stmmac_disable_eee_mode(priv);
@@ -1222,11 +1227,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
#ifdef STMMAC_XMIT_DEBUG
if ((skb->len > ETH_FRAME_LEN) || nfrags)
- pr_info("stmmac xmit:\n"
- "\tskb addr %p - len: %d - nopaged_len: %d\n"
- "\tn_frags: %d - ip_summed: %d - %s gso\n",
- skb, skb->len, nopaged_len, nfrags, skb->ip_summed,
- !skb_is_gso(skb) ? "isn't" : "is");
+ pr_debug("stmmac xmit: [entry %d]\n"
+ "\tskb addr %p - len: %d - nopaged_len: %d\n"
+ "\tn_frags: %d - ip_summed: %d - %s gso\n"
+ "\ttx_count_frames %d\n", entry,
+ skb, skb->len, nopaged_len, nfrags, skb->ip_summed,
+ !skb_is_gso(skb) ? "isn't" : "is",
+ priv->tx_count_frames);
#endif
csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL);
@@ -1236,9 +1243,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
#ifdef STMMAC_XMIT_DEBUG
if ((nfrags > 0) || (skb->len > ETH_FRAME_LEN))
- pr_debug("stmmac xmit: skb len: %d, nopaged_len: %d,\n"
- "\t\tn_frags: %d, ip_summed: %d\n",
- skb->len, nopaged_len, nfrags, skb->ip_summed);
+ pr_debug("\tskb len: %d, nopaged_len: %d,\n"
+ "\t\tn_frags: %d, ip_summed: %d\n",
+ skb->len, nopaged_len, nfrags, skb->ip_summed);
#endif
priv->tx_skbuff[entry] = skb;
@@ -1269,10 +1276,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
wmb();
}
- /* Interrupt on completition only for the latest segment */
+ /* Finalize the latest segment. */
priv->hw->desc->close_tx_desc(desc);
wmb();
+ /* According to the coalesce parameter the IC bit for the latest
+ * segment could be reset and the timer re-started to invoke the
+ * stmmac_tx function. This approach takes care about the fragments. */
+ priv->tx_count_frames += nfrags + 1;
+ if (priv->tx_coal_frames > priv->tx_count_frames) {
+ priv->hw->desc->clear_tx_ic(desc);
+ priv->xstats.tx_reset_ic_bit++;
+ TX_DBG("\t[entry %d]: tx_count_frames %d\n", entry,
+ priv->tx_count_frames);
+ mod_timer(&priv->txtimer, priv->tx_coal_timer);
+ } else
+ priv->tx_count_frames = 0;
/* To avoid raise condition */
priv->hw->desc->set_tx_owner(first);
@@ -1302,7 +1321,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
priv->hw->dma->enable_dma_transmission(priv->ioaddr);
- spin_unlock(&priv->tx_lock);
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
return NETDEV_TX_OK;
}
@@ -1447,7 +1466,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
* all interfaces.
* Description :
* This function implements the the reception process.
- * Also it runs the TX completion thread
*/
static int stmmac_poll(struct napi_struct *napi, int budget)
{
--
1.7.4.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists