Messages in this thread | | | Date | Mon, 29 Apr 2024 11:24:02 +0530 | Subject | Re: [PATCH net-next] net: ti: icssg_prueth: Add SW TX / RX Coalescing based on hrtimers | From | MD Danish Anwar <> |
| |
On 27/04/24 7:11 pm, Simon Horman wrote: > On Wed, Apr 24, 2024 at 02:48:23PM +0530, MD Danish Anwar wrote: >> Add SW IRQ coalescing based on hrtimers for RX and TX data path for ICSSG >> driver, which can be enabled by ethtool commands: >> >> - RX coalescing >> ethtool -C eth1 rx-usecs 50 >> >> - TX coalescing can be enabled per TX queue >> >> - by default enables coalesing for TX0 >> ethtool -C eth1 tx-usecs 50 >> - configure TX0 >> ethtool -Q eth0 queue_mask 1 --coalesce tx-usecs 100 >> - configure TX1 >> ethtool -Q eth0 queue_mask 2 --coalesce tx-usecs 100 >> - configure TX0 and TX1 >> ethtool -Q eth0 queue_mask 3 --coalesce tx-usecs 100 --coalesce >> tx-usecs 100 >> >> Minimum value for both rx-usecs and tx-usecs is 20us. >> >> Comapared to gro_flush_timeout and napi_defer_hard_irqs this patch > > nit: Compared > >> allows to enable IRQ coalescing for RX path separately. >> >> Signed-off-by: MD Danish Anwar <danishanwar@ti.com> > > ... > >> @@ -190,19 +191,35 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn, >> return num_tx; >> } >> >> +static enum hrtimer_restart emac_tx_timer_callback(struct hrtimer *timer) >> +{ >> + struct prueth_tx_chn *tx_chns = >> + container_of(timer, struct prueth_tx_chn, tx_hrtimer); >> + >> + enable_irq(tx_chns->irq); >> + return HRTIMER_NORESTART; >> +} >> + >> static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget) >> { >> struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx); >> struct prueth_emac *emac = tx_chn->emac; >> + bool tdown = false; >> int num_tx_packets; >> >> - num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget); >> + num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget, &tdown); > > Please consider limiting lines to 80 columns wide in Networking code. > >> >> if (num_tx_packets >= budget) >> return budget; >> >> - if (napi_complete_done(napi_tx, num_tx_packets)) >> - enable_irq(tx_chn->irq); >> + if (napi_complete_done(napi_tx, num_tx_packets)) { >> + if (unlikely(tx_chn->tx_pace_timeout_ns && !tdown)) >> + hrtimer_start(&tx_chn->tx_hrtimer, >> + ns_to_ktime(tx_chn->tx_pace_timeout_ns), >> + HRTIMER_MODE_REL_PINNED); >> + else >> + enable_irq(tx_chn->irq); >> + } >> >> return num_tx_packets; >> } > > ... > >> @@ -870,7 +889,12 @@ int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget) >> } >> >> if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) >> - enable_irq(emac->rx_chns.irq[rx_flow]); >> + if (unlikely(emac->rx_pace_timeout_ns)) >> + hrtimer_start(&emac->rx_hrtimer, >> + ns_to_ktime(emac->rx_pace_timeout_ns), >> + HRTIMER_MODE_REL_PINNED); >> + else >> + enable_irq(emac->rx_chns.irq[rx_flow]); > > clang-18 and gcc-13 both complain about the if/else logic above. > I think it would be best to add {} to the outer if statement. > >> >> return num_rx; >> } > > ...
Sure Simon, I'll fix all this and send v2.
-- Thanks and Regards, Danish
| |