octeontx2-pf: Add support for adaptive interrupt coalescing
PATCH 1/1 octeontx2-pf: Add support for adaptive interrupt coalescing
Added support for adaptive IRQ coalescing. It uses net_dim algorithm to find the suitable delay/IRQ count based on the current packet rate.
Reviewed-on: https://sj1git1.cavium.com/c/IP/SW/kernel/linux/+/73558
--- .../net/ethernet/marvell/octeontx2/Kconfig | 1 + .../marvell/octeontx2/nic/otx2_common.c | 5 --- .../marvell/octeontx2/nic/otx2_common.h | 10 +++++ .../marvell/octeontx2/nic/otx2_ethtool.c | 43 ++++++++++++++++--- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 22 ++++++++++ .../marvell/octeontx2/nic/otx2_txrx.c | 28 ++++++++++++ .../marvell/octeontx2/nic/otx2_txrx.h | 1 + 7 files changed, 99 insertions(+), 11 deletions(-)
drivers/net/ethernet/marvell/octeontx2/Kconfig +1 -0
@@ -30,6 +30,7 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK + select DIMLIB depends on PCI help This driver supports Marvell's OcteonTX2 Resource Virtualization
drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +0 -5
@@ -103,11 +103,6 @@ void otx2_get_dev_stats(struct otx2_nic *pfvf) {struct otx2_dev_stats *dev_stats = &pfvf->hw.dev_stats; -#define OTX2_GET_RX_STATS (reg) \ - otx2_read64(pfvf, NIX_LF_RX_STATX(reg)) -#define OTX2_GET_TX_STATS (reg) \ - otx2_read64(pfvf, NIX_LF_TX_STATX(reg)) - dev_stats->rx_bytes =OTX2_GET_RX_STATS (RX_OCTS ); dev_stats->rx_drops =OTX2_GET_RX_STATS (RX_DROP ); dev_stats->rx_bcast_frames =OTX2_GET_RX_STATS (RX_BCAST );
drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +10 -0
@@ -16,6 +16,7 @@#include <net/pkt_cls.h> #include <net/devlink.h> #include <linux/time64.h> +#include <linux/dim.h> #include <mbox.h> #include <npc.h>
@@ -54,6 +55,11 @@ enum arua_mapped_qtypes {/* Send skid of 2000 packets required for CQ size of 4K CQEs. */ #define SEND_CQ_SKID 2000 +#define OTX2_GET_RX_STATS (reg) \ + otx2_read64(pfvf, NIX_LF_RX_STATX(reg)) +#define OTX2_GET_TX_STATS (reg) \ + otx2_read64(pfvf, NIX_LF_TX_STATX(reg)) +struct otx2_lmt_info {u64 lmt_addr;u16 lmt_id;
@@ -363,6 +369,7 @@ struct otx2_nic {#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13)#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14)#define OTX2_FLAG_PTP_ONESTEP_SYNC BIT_ULL(15) +#define OTX2_FLAG_ADPTV_INT_COAL_ENABLED BIT_ULL(16)u64 flags;u64 *cq_op_addr;
@@ -442,6 +449,9 @@ struct otx2_nic {#endif /* qos */ struct otx2_qos qos; + +/* napi event count. It is needed for adaptive irq coalescing */ +u32 napi_events; };static inline bool is_otx2_lbkvf (struct pci_dev *pdev)
drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +37 -6
78 lines not on this page · raw message
drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +22 -0
@@ -1279,6 +1279,7 @@ static irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq)otx2_write64 (pf,NIX_LF_CINTX_ENA_W1C (qidx),BIT_ULL (0 ));/* Schedule NAPI */ + pf->napi_events++;napi_schedule_irqoff (&cq_poll->napi);return IRQ_HANDLED ;
@@ -1292,6 +1293,7 @@ static void otx2_disable_napi(struct otx2_nic *pf)for (qidx =0 ; qidx < pf->hw.cint_cnt; qidx++) { cq_poll = &qset->napi[qidx]; +cancel_work_sync (&cq_poll->dim.work);napi_disable (&cq_poll->napi);netif_napi_del (&cq_poll->napi); }
@@ -1538,6 +1540,24 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)mutex_unlock (&mbox->lock); } +static void otx2_dim_work (struct work_struct *w) +{ +struct dim_cq_moder cur_moder; +struct otx2_cq_poll *cq_poll; +struct otx2_nic *pfvf; +struct dim *dim; + + dim = container_of(w, struct dim, work); + cur_moder =net_dim_get_rx_moderation (dim->mode, dim->profile_ix); + cq_poll = container_of(dim, struct otx2_cq_poll, dim); + pfvf = (struct otx2_nic *)cq_poll->dev; + pfvf->hw.cq_time_wait = (cur_moder.usec >CQ_TIMER_THRESH_MAX ) ? +CQ_TIMER_THRESH_MAX : cur_moder.usec; + pfvf->hw.cq_ecount_wait = (cur_moder.pkts >NAPI_POLL_WEIGHT ) ? +NAPI_POLL_WEIGHT : cur_moder.pkts; + dim->state =DIM_START_MEASURE ; +} +int otx2_open (struct net_device *netdev) {struct otx2_nic *pf =netdev_priv (netdev);
@@ -1611,6 +1631,8 @@ int otx2_open(struct net_device *netdev)CINT_INVALID_CQ ; cq_poll->dev = (void *)pf; + cq_poll->dim.mode =DIM_CQ_PERIOD_MODE_START_FROM_CQE ; +INIT_WORK (&cq_poll->dim.work, otx2_dim_work);netif_napi_add (netdev, &cq_poll->napi, otx2_napi_handler,NAPI_POLL_WEIGHT );napi_enable (&cq_poll->napi);
drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +28 -0
@@ -512,6 +512,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,return 0 ; } +static void otx2_adjust_adaptive_coalese (struct otx2_nic *pfvf,struct otx2_cq_poll *cq_poll) +{ +struct dim_sample dim_sample; +u64 rx_frames, rx_bytes; + + rx_frames =OTX2_GET_RX_STATS (RX_BCAST ) +OTX2_GET_RX_STATS (RX_MCAST ) + +OTX2_GET_RX_STATS (RX_UCAST ); + rx_bytes =OTX2_GET_RX_STATS (RX_OCTS ); +dim_update_sample (pfvf->napi_events, + rx_frames, + rx_bytes, + &dim_sample); + +net_dim (&cq_poll->dim, dim_sample); +} +int otx2_napi_handler (struct napi_struct *napi,int budget) {struct otx2_cq_queue *rx_cq =NULL ;
@@ -549,6 +565,18 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)if (pfvf->flags &OTX2_FLAG_INTF_DOWN )return workdone; +/* Check for adaptive interrupt coalesce */ +if (workdone !=0 && + ((pfvf->flags &OTX2_FLAG_ADPTV_INT_COAL_ENABLED ) == +OTX2_FLAG_ADPTV_INT_COAL_ENABLED )) { +/* Adjust irq coalese using net_dim */ +otx2_adjust_adaptive_coalese (pfvf, cq_poll); + +/* Update irq coalescing */ +for (i =0 ; i < pfvf->hw.cint_cnt; i++) +otx2_config_irq_coalescing (pfvf, i); + } +/* Re-enable interrupts */ otx2_write64 (pfvf,NIX_LF_CINTX_ENA_W1S (cq_poll->cint_idx),BIT_ULL (0 ));
drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +1 -0
@@ -107,6 +107,7 @@ struct otx2_cq_poll {#define CINT_INVALID_CQ 255u8 cint_idx;u8 cq_ids[CQS_PER_CINT ]; +struct dim dim;struct napi_struct napi; };
Signature · 1 line
2.25.1
Please ignore this. I will resend.
Regards,
Suman
-----Original Message-----
From: Suman Ghosh <[email protected]>
Sent: Wednesday, April 13, 2022 12:51 PM
To: [email protected]; Sunil Kovvuri Goutham <[email protected]>; Hariprasad Kelam <[email protected]>; Subbaraya Sundeep Bhatta <[email protected]>; Naveen Mamindlapalli <[email protected]>; Rakesh Babu Saladi <[email protected]>; Geethasowjanya Akula <[email protected]>; [email protected]
Cc: Suman Ghosh <[email protected]>; sa_ip-sw-jenkins <[email protected]>
Subject: [PATCH] octeontx2-pf: Add support for adaptive interrupt coalescing
Added support for adaptive IRQ coalescing. It uses net_dim algorithm to find the suitable delay/IRQ count based on the current packet rate.
Reviewed-on: https://sj1git1.cavium.com/c/IP/SW/kernel/linux/+/73558
--- .../net/ethernet/marvell/octeontx2/Kconfig | 1 + .../marvell/octeontx2/nic/otx2_common.c | 5 --- .../marvell/octeontx2/nic/otx2_common.h | 10 +++++ .../marvell/octeontx2/nic/otx2_ethtool.c | 43 ++++++++++++++++--- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 22 ++++++++++ .../marvell/octeontx2/nic/otx2_txrx.c | 28 ++++++++++++ .../marvell/octeontx2/nic/otx2_txrx.h | 1 + 7 files changed, 99 insertions(+), 11 deletions(-)
drivers/net/ethernet/marvell/octeontx2/Kconfig +1 -0
@@ -30,6 +30,7 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK + select DIMLIB depends on PCI help This driver supports Marvell's OcteonTX2 Resource Virtualization diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 033fd79d35b0..c28850d815c2 100644
drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +0 -5
@@ -103,11 +103,6 @@ void otx2_get_dev_stats(struct otx2_nic *pfvf) {struct otx2_dev_stats *dev_stats = &pfvf->hw.dev_stats; -#define OTX2_GET_RX_STATS (reg) \ - otx2_read64(pfvf, NIX_LF_RX_STATX(reg)) -#define OTX2_GET_TX_STATS (reg) \ - otx2_read64(pfvf, NIX_LF_TX_STATX(reg)) - dev_stats->rx_bytes =OTX2_GET_RX_STATS (RX_OCTS ); dev_stats->rx_drops =OTX2_GET_RX_STATS (RX_DROP ); dev_stats->rx_bcast_frames = OTX2_GET_RX_STATS(RX_BCAST); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index d9f4b085b2a4..6abf5c28921f 100644
drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +10 -0
@@ -16,6 +16,7 @@#include <net/pkt_cls.h> #include <net/devlink.h> #include <linux/time64.h> +#include <linux/dim.h> #include <mbox.h> #include <npc.h>
@@ -54,6 +55,11 @@ enum arua_mapped_qtypes {/* Send skid of 2000 packets required for CQ size of 4K CQEs. */ #define SEND_CQ_SKID 2000 +#define OTX2_GET_RX_STATS (reg) \ + otx2_read64(pfvf, NIX_LF_RX_STATX(reg)) #define +OTX2_GET_TX_STATS (reg) \ +otx2_read64 (pfvf ,NIX_LF_TX_STATX (reg )) + struct otx2_lmt_info {u64 lmt_addr;u16 lmt_id;
@@ -363,6 +369,7 @@ struct otx2_nic {#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13)#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14)#define OTX2_FLAG_PTP_ONESTEP_SYNC BIT_ULL(15) +#define OTX2_FLAG_ADPTV_INT_COAL_ENABLED BIT_ULL(16)u64 flags;u64 *cq_op_addr;
@@ -442,6 +449,9 @@ struct otx2_nic {#endif /* qos */ struct otx2_qos qos; + +/* napi event count. It is needed for adaptive irq coalescing */ +u32 napi_events; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 72d0b02da3cc..8ed282991f05 100644
drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +10 -2
@@ -477,6 +477,14 @@ static int otx2_get_coalesce(struct net_device *netdev, cmd->rx_max_coalesced_frames = hw->cq_ecount_wait; cmd->tx_coalesce_usecs = hw->cq_time_wait; cmd->tx_max_coalesced_frames = hw->cq_ecount_wait; +if ((pfvf->flags &OTX2_FLAG_ADPTV_INT_COAL_ENABLED ) == +OTX2_FLAG_ADPTV_INT_COAL_ENABLED ) { + cmd->use_adaptive_rx_coalesce =1 ; + cmd->use_adaptive_tx_coalesce =1 ; + }else { + cmd->use_adaptive_rx_coalesce =0 ; + cmd->use_adaptive_tx_coalesce =0 ; + }return 0 ; }
@@ -486,10 +494,10 @@ static int otx2_set_coalesce(struct net_device *netdev, {struct otx2_nic *pfvf =netdev_priv (netdev);struct otx2_hw *hw = &pfvf->hw; +u8 priv_coalesce_status;int qidx; -if (ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce || - ec->rx_coalesce_usecs_irq || ec->rx_max_coalesced_frames_irq || +if (ec->rx_coalesce_usecs_irq || ec->rx_max_coalesced_frames_irq || ec->tx_coalesce_usecs_irq || ec->tx_max_coalesced_frames_irq || ec->stats_block_coalesce_usecs || ec->pkt_rate_low || ec->rx_coalesce_usecs_low || ec->rx_max_coalesced_frames_low || @@ -502,6 +510,18 @@ static int otx2_set_coalesce(struct net_device *netdev, if (!ec->rx_max_coalesced_frames || !ec->tx_max_coalesced_frames)
return 0;
+ /* Check and update coalesce status */
+ if ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) ==
+ OTX2_FLAG_ADPTV_INT_COAL_ENABLED) {
+ priv_coalesce_status = 1;
+ if (!ec->use_adaptive_rx_coalesce || !ec->use_adaptive_tx_coalesce)
+ pfvf->flags &= ~OTX2_FLAG_ADPTV_INT_COAL_ENABLED;
+ } else {
+ priv_coalesce_status = 0;
+ if (ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce)
+ pfvf->flags |= OTX2_FLAG_ADPTV_INT_COAL_ENABLED;
+ }
+
/* 'cq_time_wait' is 8bit and is in multiple of 100ns,
* so clamp the user given value to the range of 1 to 25usec. */
@@ -521,13 +541,13 @@ static int otx2_set_coalesce(struct net_device *netdev,
hw->cq_time_wait = min_t(u8, ec->rx_coalesce_usecs,
ec->tx_coalesce_usecs);
- /* Max ecount_wait supported is 16bit,
- * so clamp the user given value to the range of 1 to 64k.
+ /* Max packet budget per napi is 64,
+ * so clamp the user given value to the range of 1 to 64.
*/
ec->rx_max_coalesced_frames = clamp_t(u32, ec->rx_max_coalesced_frames,
- 1, U16_MAX);
+ 1, NAPI_POLL_WEIGHT);
ec->tx_max_coalesced_frames = clamp_t(u32, ec->tx_max_coalesced_frames,
- 1, U16_MAX);
+ 1, NAPI_POLL_WEIGHT);
/* Rx and Tx are mapped to same CQ, check which one
* is changed, if both then choose the min.
@@ -540,6 +560,17 @@ static int otx2_set_coalesce(struct net_device *netdev,
hw->cq_ecount_wait = min_t(u16, ec->rx_max_coalesced_frames,
ec->tx_max_coalesced_frames);
+ /* Reset 'cq_time_wait' and 'cq_ecount_wait' to
+ * default values if coalesce status changed from
+ * 'on' to 'off'.
+ */
+ if (priv_coalesce_status &&
+ ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) !=
+ OTX2_FLAG_ADPTV_INT_COAL_ENABLED)) {
+ hw->cq_time_wait = CQ_TIMER_THRESH_DEFAULT;
+ hw->cq_ecount_wait = CQ_CQE_THRESH_DEFAULT;
+ }
+
if (netif_running(netdev)) {
for (qidx = 0; qidx < pfvf->hw.cint_cnt; qidx++)
otx2_config_irq_coalescing(pfvf, qidx); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index f18c9a9a50d0..94aaafbeb365 100644
drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +19 -0
@@ -1279,6 +1279,7 @@ static irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq)otx2_write64 (pf,NIX_LF_CINTX_ENA_W1C (qidx),BIT_ULL (0 ));/* Schedule NAPI */ + pf->napi_events++;napi_schedule_irqoff (&cq_poll->napi);return IRQ_HANDLED ;
@@ -1292,6 +1293,7 @@ static void otx2_disable_napi(struct otx2_nic *pf)for (qidx =0 ; qidx < pf->hw.cint_cnt; qidx++) { cq_poll = &qset->napi[qidx]; +cancel_work_sync (&cq_poll->dim.work);napi_disable (&cq_poll->napi);netif_napi_del (&cq_poll->napi); }
@@ -1538,6 +1540,24 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)mutex_unlock (&mbox->lock); } +static void otx2_dim_work (struct work_struct *w) { +struct dim_cq_moder cur_moder; +struct otx2_cq_poll *cq_poll; +struct otx2_nic *pfvf; +struct dim *dim; + + dim = container_of(w, struct dim, work); + cur_moder =net_dim_get_rx_moderation (dim->mode, dim->profile_ix); + cq_poll = container_of(dim, struct otx2_cq_poll, dim); + pfvf = (struct otx2_nic *)cq_poll->dev; + pfvf->hw.cq_time_wait = (cur_moder.usec >CQ_TIMER_THRESH_MAX ) ? +CQ_TIMER_THRESH_MAX : cur_moder.usec; + pfvf->hw.cq_ecount_wait = (cur_moder.pkts >NAPI_POLL_WEIGHT ) ? +NAPI_POLL_WEIGHT : cur_moder.pkts; + dim->state =DIM_START_MEASURE ; +} +int otx2_open (struct net_device *netdev) { struct otx2_nic *pf = netdev_priv(netdev); @@ -1611,6 +1631,8 @@ int otx2_open(struct net_device *netdev) CINT_INVALID_CQ;
cq_poll->dev = (void *)pf;
+ cq_poll->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
+ INIT_WORK(&cq_poll->dim.work, otx2_dim_work);
netif_napi_add(netdev, &cq_poll->napi,
otx2_napi_handler, NAPI_POLL_WEIGHT);
napi_enable(&cq_poll->napi);
drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +28 -0
@@ -512,6 +512,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,return 0 ; } +static void otx2_adjust_adaptive_coalese (struct otx2_nic *pfvf,struct +otx2_cq_poll *cq_poll) { +struct dim_sample dim_sample; +u64 rx_frames, rx_bytes; + + rx_frames =OTX2_GET_RX_STATS (RX_BCAST ) +OTX2_GET_RX_STATS (RX_MCAST ) + +OTX2_GET_RX_STATS (RX_UCAST ); + rx_bytes =OTX2_GET_RX_STATS (RX_OCTS ); +dim_update_sample (pfvf->napi_events, + rx_frames, + rx_bytes, + &dim_sample); + +net_dim (&cq_poll->dim, dim_sample); +} +int otx2_napi_handler (struct napi_struct *napi,int budget) {struct otx2_cq_queue *rx_cq =NULL ;
@@ -549,6 +565,18 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)if (pfvf->flags &OTX2_FLAG_INTF_DOWN )return workdone; +/* Check for adaptive interrupt coalesce */ +if (workdone !=0 && + ((pfvf->flags &OTX2_FLAG_ADPTV_INT_COAL_ENABLED ) == +OTX2_FLAG_ADPTV_INT_COAL_ENABLED )) { +/* Adjust irq coalese using net_dim */ +otx2_adjust_adaptive_coalese (pfvf, cq_poll); + +/* Update irq coalescing */ +for (i =0 ; i < pfvf->hw.cint_cnt; i++) +otx2_config_irq_coalescing (pfvf, i); + } +/* Re-enable interrupts */ otx2_write64 (pfvf,NIX_LF_CINTX_ENA_W1S (cq_poll->cint_idx),BIT_ULL (0 ));
drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +1 -0
@@ -107,6 +107,7 @@ struct otx2_cq_poll {#define CINT_INVALID_CQ 255u8 cint_idx;u8 cq_ids[CQS_PER_CINT ]; +struct dim dim;struct napi_struct napi; };
--
2.25.1