Merge branch 'sfc-SFN8000-support-improvements'

Bert Kenward says:

====================
sfc: SFN8000 support improvements

This series improves support for the recently released SFN8000 series
of adapters. Specifically, it retrieves interrupt moderation timer
settings directly from the adapter and uses those settings. It also
uses a new event queue initialisation interface, allowing specification
of a performance objective rather than enabling individual flags.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/sfc/ef10.c

@@ -177,7 +177,7 @@ static int efx_ef10_get_vf_index(struct efx_nic *efx)
 
 static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 {
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V2_OUT_LEN);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	size_t outlen;
 	int rc;
@@ -188,7 +188,7 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 			  outbuf, sizeof(outbuf), &outlen);
 	if (rc)
 		return rc;
-	if (outlen < sizeof(outbuf)) {
+	if (outlen < MC_CMD_GET_CAPABILITIES_OUT_LEN) {
 		netif_err(efx, drv, efx->net_dev,
 			  "unable to read datapath firmware capabilities\n");
 		return -EIO;
@@ -197,6 +197,12 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 	nic_data->datapath_caps =
 		MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1);
 
+	if (outlen >= MC_CMD_GET_CAPABILITIES_V2_OUT_LEN)
+		nic_data->datapath_caps2 = MCDI_DWORD(outbuf,
+				GET_CAPABILITIES_V2_OUT_FLAGS2);
+	else
+		nic_data->datapath_caps2 = 0;
+
 	/* record the DPCPU firmware IDs to determine VEB vswitching support.
 	 */
 	nic_data->rx_dpcpu_fw_id =
@@ -227,6 +233,116 @@ static int efx_ef10_get_sysclk_freq(struct efx_nic *efx)
 	return rc > 0 ? rc : -ERANGE;
 }
 
+static int efx_ef10_get_timer_workarounds(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	unsigned int implemented;
+	unsigned int enabled;
+	int rc;
+
+	nic_data->workaround_35388 = false;
+	nic_data->workaround_61265 = false;
+
+	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);
+
+	if (rc == -ENOSYS) {
+		/* Firmware without GET_WORKAROUNDS - not a problem. */
+		rc = 0;
+	} else if (rc == 0) {
+		/* Bug61265 workaround is always enabled if implemented. */
+		if (enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG61265)
+			nic_data->workaround_61265 = true;
+
+		if (enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG35388) {
+			nic_data->workaround_35388 = true;
+		} else if (implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG35388) {
+			/* Workaround is implemented but not enabled.
+			 * Try to enable it.
+			 */
+			rc = efx_mcdi_set_workaround(efx,
+						     MC_CMD_WORKAROUND_BUG35388,
+						     true, NULL);
+			if (rc == 0)
+				nic_data->workaround_35388 = true;
+			/* If we failed to set the workaround just carry on. */
+			rc = 0;
+		}
+	}
+
+	netif_dbg(efx, probe, efx->net_dev,
+		  "workaround for bug 35388 is %sabled\n",
+		  nic_data->workaround_35388 ? "en" : "dis");
+	netif_dbg(efx, probe, efx->net_dev,
+		  "workaround for bug 61265 is %sabled\n",
+		  nic_data->workaround_61265 ? "en" : "dis");
+
+	return rc;
+}
+
+static void efx_ef10_process_timer_config(struct efx_nic *efx,
+					  const efx_dword_t *data)
+{
+	unsigned int max_count;
+
+	if (EFX_EF10_WORKAROUND_61265(efx)) {
+		efx->timer_quantum_ns = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_MCDI_TMR_STEP_NS);
+		efx->timer_max_ns = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_MCDI_TMR_MAX_NS);
+	} else if (EFX_EF10_WORKAROUND_35388(efx)) {
+		efx->timer_quantum_ns = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT);
+		max_count = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT);
+		efx->timer_max_ns = max_count * efx->timer_quantum_ns;
+	} else {
+		efx->timer_quantum_ns = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_TMR_REG_NS_PER_COUNT);
+		max_count = MCDI_DWORD(data,
+			GET_EVQ_TMR_PROPERTIES_OUT_TMR_REG_MAX_COUNT);
+		efx->timer_max_ns = max_count * efx->timer_quantum_ns;
+	}
+
+	netif_dbg(efx, probe, efx->net_dev,
+		  "got timer properties from MC: quantum %u ns; max %u ns\n",
+		  efx->timer_quantum_ns, efx->timer_max_ns);
+}
+
+static int efx_ef10_get_timer_config(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_LEN);
+	int rc;
+
+	rc = efx_ef10_get_timer_workarounds(efx);
+	if (rc)
+		return rc;
+
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_EVQ_TMR_PROPERTIES, NULL, 0,
+				outbuf, sizeof(outbuf), NULL);
+
+	if (rc == 0) {
+		efx_ef10_process_timer_config(efx, outbuf);
+	} else if (rc == -ENOSYS || rc == -EPERM) {
+		/* Not available - fall back to Huntington defaults. */
+		unsigned int quantum;
+
+		rc = efx_ef10_get_sysclk_freq(efx);
+		if (rc < 0)
+			return rc;
+
+		quantum = 1536000 / rc; /* 1536 cycles */
+		efx->timer_quantum_ns = quantum;
+		efx->timer_max_ns = efx->type->timer_period_max * quantum;
+		rc = 0;
+	} else {
+		efx_mcdi_display_error(efx, MC_CMD_GET_EVQ_TMR_PROPERTIES,
+				       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_LEN,
+				       NULL, 0, rc);
+	}
+
+	return rc;
+}
+
 static int efx_ef10_get_mac_address_pf(struct efx_nic *efx, u8 *mac_address)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN);
@@ -527,33 +643,11 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	if (rc)
 		goto fail5;
 
-	rc = efx_ef10_get_sysclk_freq(efx);
+	rc = efx_ef10_get_timer_config(efx);
 	if (rc < 0)
 		goto fail5;
 	efx->timer_quantum_ns = 1536000 / rc; /* 1536 cycles */
 
-	/* Check whether firmware supports bug 35388 workaround.
-	 * First try to enable it, then if we get EPERM, just
-	 * ask if it's already enabled
-	 */
-	rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true, NULL);
-	if (rc == 0) {
-		nic_data->workaround_35388 = true;
-	} else if (rc == -EPERM) {
-		unsigned int enabled;
-
-		rc = efx_mcdi_get_workarounds(efx, NULL, &enabled);
-		if (rc)
-			goto fail3;
-		nic_data->workaround_35388 = enabled &
-			MC_CMD_GET_WORKAROUNDS_OUT_BUG35388;
-	} else if (rc != -ENOSYS && rc != -ENOENT) {
-		goto fail5;
-	}
-	netif_dbg(efx, probe, efx->net_dev,
-		  "workaround for bug 35388 is %sabled\n",
-		  nic_data->workaround_35388 ? "en" : "dis");
-
 	rc = efx_mcdi_mon_probe(efx);
 	if (rc && rc != -EPERM)
 		goto fail5;
@@ -1743,27 +1837,43 @@ static size_t efx_ef10_update_stats_vf(struct efx_nic *efx, u64 *full_stats,
 static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
 {
 	struct efx_nic *efx = channel->efx;
-	unsigned int mode, value;
+	unsigned int mode, usecs;
 	efx_dword_t timer_cmd;
 
-	if (channel->irq_moderation) {
+	if (channel->irq_moderation_us) {
 		mode = 3;
-		value = channel->irq_moderation - 1;
+		usecs = channel->irq_moderation_us;
 	} else {
 		mode = 0;
-		value = 0;
+		usecs = 0;
 	}
 
-	if (EFX_EF10_WORKAROUND_35388(efx)) {
+	if (EFX_EF10_WORKAROUND_61265(efx)) {
+		MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_EVQ_TMR_IN_LEN);
+		unsigned int ns = usecs * 1000;
+
+		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_INSTANCE,
+			       channel->channel);
+		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_LOAD_REQ_NS, ns);
+		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_RELOAD_REQ_NS, ns);
+		MCDI_SET_DWORD(inbuf, SET_EVQ_TMR_IN_TMR_MODE, mode);
+
+		efx_mcdi_rpc_async(efx, MC_CMD_SET_EVQ_TMR,
+				   inbuf, sizeof(inbuf), 0, NULL, 0);
+	} else if (EFX_EF10_WORKAROUND_35388(efx)) {
+		unsigned int ticks = efx_usecs_to_ticks(efx, usecs);
+
 		EFX_POPULATE_DWORD_3(timer_cmd, ERF_DD_EVQ_IND_TIMER_FLAGS,
 				     EFE_DD_EVQ_IND_TIMER_FLAGS,
 				     ERF_DD_EVQ_IND_TIMER_MODE, mode,
-				     ERF_DD_EVQ_IND_TIMER_VAL, value);
+				     ERF_DD_EVQ_IND_TIMER_VAL, ticks);
 		efx_writed_page(efx, &timer_cmd, ER_DD_EVQ_INDIRECT,
 				channel->channel);
 	} else {
+		unsigned int ticks = efx_usecs_to_ticks(efx, usecs);
+
 		EFX_POPULATE_DWORD_2(timer_cmd, ERF_DZ_TC_TIMER_MODE, mode,
-				     ERF_DZ_TC_TIMER_VAL, value);
+				     ERF_DZ_TC_TIMER_VAL, ticks);
 		efx_writed_page(efx, &timer_cmd, ER_DZ_EVQ_TMR,
 				channel->channel);
 	}
@@ -2535,13 +2645,12 @@ static void efx_ef10_ev_fini(struct efx_channel *channel)
 static int efx_ef10_ev_init(struct efx_channel *channel)
 {
 	MCDI_DECLARE_BUF(inbuf,
-			 MC_CMD_INIT_EVQ_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
+			 MC_CMD_INIT_EVQ_V2_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
 						   EFX_BUF_SIZE));
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_V2_OUT_LEN);
 	size_t entries = channel->eventq.buf.len / EFX_BUF_SIZE;
 	struct efx_nic *efx = channel->efx;
 	struct efx_ef10_nic_data *nic_data;
-	bool supports_rx_merge;
 	size_t inlen, outlen;
 	unsigned int enabled, implemented;
 	dma_addr_t dma_addr;
@@ -2549,9 +2658,6 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 	int i;
 
 	nic_data = efx->nic_data;
-	supports_rx_merge =
-		!!(nic_data->datapath_caps &
-		   1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
 
 	/* Fill event queue with all ones (i.e. empty events) */
 	memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
@@ -2560,11 +2666,6 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_INSTANCE, channel->channel);
 	/* INIT_EVQ expects index in vector table, not absolute */
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_IRQ_NUM, channel->channel);
-	MCDI_POPULATE_DWORD_4(inbuf, INIT_EVQ_IN_FLAGS,
-			      INIT_EVQ_IN_FLAG_INTERRUPTING, 1,
-			      INIT_EVQ_IN_FLAG_RX_MERGE, 1,
-			      INIT_EVQ_IN_FLAG_TX_MERGE, 1,
-			      INIT_EVQ_IN_FLAG_CUT_THRU, !supports_rx_merge);
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_MODE,
 		       MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS);
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_LOAD, 0);
@@ -2573,6 +2674,27 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 		       MC_CMD_INIT_EVQ_IN_COUNT_MODE_DIS);
 	MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_THRSHLD, 0);
 
+	if (nic_data->datapath_caps2 &
+	    1 << MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN) {
+		/* Use the new generic approach to specifying event queue
+		 * configuration, requesting lower latency or higher throughput.
+		 * The options that actually get used appear in the output.
+		 */
+		MCDI_POPULATE_DWORD_2(inbuf, INIT_EVQ_V2_IN_FLAGS,
+				      INIT_EVQ_V2_IN_FLAG_INTERRUPTING, 1,
+				      INIT_EVQ_V2_IN_FLAG_TYPE,
+				      MC_CMD_INIT_EVQ_V2_IN_FLAG_TYPE_AUTO);
+	} else {
+		bool cut_thru = !(nic_data->datapath_caps &
+			1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
+
+		MCDI_POPULATE_DWORD_4(inbuf, INIT_EVQ_IN_FLAGS,
+				      INIT_EVQ_IN_FLAG_INTERRUPTING, 1,
+				      INIT_EVQ_IN_FLAG_RX_MERGE, 1,
+				      INIT_EVQ_IN_FLAG_TX_MERGE, 1,
+				      INIT_EVQ_IN_FLAG_CUT_THRU, cut_thru);
+	}
+
 	dma_addr = channel->eventq.buf.dma_addr;
 	for (i = 0; i < entries; ++i) {
 		MCDI_SET_ARRAY_QWORD(inbuf, INIT_EVQ_IN_DMA_ADDR, i, dma_addr);
@@ -2583,6 +2705,13 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen,
 			  outbuf, sizeof(outbuf), &outlen);
+
+	if (outlen >= MC_CMD_INIT_EVQ_V2_OUT_LEN)
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Channel %d using event queue flags %08x\n",
+			  channel->channel,
+			  MCDI_DWORD(outbuf, INIT_EVQ_V2_OUT_FLAGS));
+
 	/* IRQ return is ignored */
 	if (channel->channel || rc)
 		return rc;
@@ -2590,8 +2719,8 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 	/* Successfully created event queue on channel 0 */
 	rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled);
 	if (rc == -ENOSYS) {
-		/* GET_WORKAROUNDS was implemented before the bug26807
-		 * workaround, thus the latter must be unavailable in this fw
+		/* GET_WORKAROUNDS was implemented before this workaround,
+		 * thus it must be unavailable in this firmware.
 		 */
 		nic_data->workaround_26807 = false;
 		rc = 0;

drivers/net/ethernet/sfc/efx.c

@@ -281,6 +281,27 @@ static int efx_process_channel(struct efx_channel *channel, int budget)
  * NAPI guarantees serialisation of polls of the same device, which
  * provides the guarantee required by efx_process_channel().
  */
+static void efx_update_irq_mod(struct efx_nic *efx, struct efx_channel *channel)
+{
+	int step = efx->irq_mod_step_us;
+
+	if (channel->irq_mod_score < irq_adapt_low_thresh) {
+		if (channel->irq_moderation_us > step) {
+			channel->irq_moderation_us -= step;
+			efx->type->push_irq_moderation(channel);
+		}
+	} else if (channel->irq_mod_score > irq_adapt_high_thresh) {
+		if (channel->irq_moderation_us <
+		    efx->irq_rx_moderation_us) {
+			channel->irq_moderation_us += step;
+			efx->type->push_irq_moderation(channel);
+		}
+	}
+
+	channel->irq_count = 0;
+	channel->irq_mod_score = 0;
+}
+
 static int efx_poll(struct napi_struct *napi, int budget)
 {
 	struct efx_channel *channel =
@@ -301,22 +322,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		if (efx_channel_has_rx_queue(channel) &&
 		    efx->irq_rx_adaptive &&
 		    unlikely(++channel->irq_count == 1000)) {
-			if (unlikely(channel->irq_mod_score <
-				     irq_adapt_low_thresh)) {
-				if (channel->irq_moderation > 1) {
-					channel->irq_moderation -= 1;
-					efx->type->push_irq_moderation(channel);
-				}
-			} else if (unlikely(channel->irq_mod_score >
-					    irq_adapt_high_thresh)) {
-				if (channel->irq_moderation <
-				    efx->irq_rx_moderation) {
-					channel->irq_moderation += 1;
-					efx->type->push_irq_moderation(channel);
-				}
-			}
-			channel->irq_count = 0;
-			channel->irq_mod_score = 0;
+			efx_update_irq_mod(efx, channel);
 		}
 
 		efx_filter_rfs_expire(channel);
@@ -1703,6 +1709,7 @@ static int efx_probe_nic(struct efx_nic *efx)
 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
 
 	/* Initialise the interrupt moderation settings */
+	efx->irq_mod_step_us = DIV_ROUND_UP(efx->timer_quantum_ns, 1000);
 	efx_init_irq_moderation(efx, tx_irq_mod_usec, rx_irq_mod_usec, true,
 				true);
 
@@ -1949,14 +1956,21 @@ static void efx_remove_all(struct efx_nic *efx)
  * Interrupt moderation
  *
  **************************************************************************/
-
-static unsigned int irq_mod_ticks(unsigned int usecs, unsigned int quantum_ns)
+unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs)
 {
 	if (usecs == 0)
 		return 0;
-	if (usecs * 1000 < quantum_ns)
+	if (usecs * 1000 < efx->timer_quantum_ns)
 		return 1; /* never round down to 0 */
-	return usecs * 1000 / quantum_ns;
+	return usecs * 1000 / efx->timer_quantum_ns;
+}
+
+unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks)
+{
+	/* We must round up when converting ticks to microseconds
+	 * because we round down when converting the other way.
+	 */
+	return DIV_ROUND_UP(ticks * efx->timer_quantum_ns, 1000);
 }
 
 /* Set interrupt moderation parameters */
@@ -1965,21 +1979,16 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 			    bool rx_may_override_tx)
 {
 	struct efx_channel *channel;
-	unsigned int irq_mod_max = DIV_ROUND_UP(efx->type->timer_period_max *
-						efx->timer_quantum_ns,
-						1000);
-	unsigned int tx_ticks;
-	unsigned int rx_ticks;
+	unsigned int timer_max_us;
 
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
-	if (tx_usecs > irq_mod_max || rx_usecs > irq_mod_max)
-		return -EINVAL;
+	timer_max_us = efx->timer_max_ns / 1000;
 
-	tx_ticks = irq_mod_ticks(tx_usecs, efx->timer_quantum_ns);
-	rx_ticks = irq_mod_ticks(rx_usecs, efx->timer_quantum_ns);
+	if (tx_usecs > timer_max_us || rx_usecs > timer_max_us)
+		return -EINVAL;
 
-	if (tx_ticks != rx_ticks && efx->tx_channel_offset == 0 &&
+	if (tx_usecs != rx_usecs && efx->tx_channel_offset == 0 &&
 	    !rx_may_override_tx) {
 		netif_err(efx, drv, efx->net_dev, "Channels are shared. "
 			  "RX and TX IRQ moderation must be equal\n");
@@ -1987,12 +1996,12 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 	}
 
 	efx->irq_rx_adaptive = rx_adaptive;
-	efx->irq_rx_moderation = rx_ticks;
+	efx->irq_rx_moderation_us = rx_usecs;
 	efx_for_each_channel(channel, efx) {
 		if (efx_channel_has_rx_queue(channel))
-			channel->irq_moderation = rx_ticks;
+			channel->irq_moderation_us = rx_usecs;
 		else if (efx_channel_has_tx_queues(channel))
-			channel->irq_moderation = tx_ticks;
+			channel->irq_moderation_us = tx_usecs;
 	}
 
 	return 0;
@@ -2001,26 +2010,21 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
 			    unsigned int *rx_usecs, bool *rx_adaptive)
 {
-	/* We must round up when converting ticks to microseconds
-	 * because we round down when converting the other way.
-	 */
-
 	*rx_adaptive = efx->irq_rx_adaptive;
-	*rx_usecs = DIV_ROUND_UP(efx->irq_rx_moderation *
-				 efx->timer_quantum_ns,
-				 1000);
+	*rx_usecs = efx->irq_rx_moderation_us;
 
 	/* If channels are shared between RX and TX, so is IRQ
 	 * moderation.  Otherwise, IRQ moderation is the same for all
 	 * TX channels and is not adaptive.
 	 */
-	if (efx->tx_channel_offset == 0)
+	if (efx->tx_channel_offset == 0) {
 		*tx_usecs = *rx_usecs;
-	else
-		*tx_usecs = DIV_ROUND_UP(
-			efx->channel[efx->tx_channel_offset]->irq_moderation *
-			efx->timer_quantum_ns,
-			1000);
+	} else {
+		struct efx_channel *tx_channel;
+
+		tx_channel = efx->channel[efx->tx_channel_offset];
+		*tx_usecs = tx_channel->irq_moderation_us;
+	}
 }
 
 /**************************************************************************

drivers/net/ethernet/sfc/efx.h

@@ -204,6 +204,8 @@ int efx_try_recovery(struct efx_nic *efx);
 
 /* Global */
 void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
+unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs);
+unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks);
 int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 			    unsigned int rx_usecs, bool rx_adaptive,
 			    bool rx_may_override_tx);

drivers/net/ethernet/sfc/falcon.c

@@ -378,12 +378,15 @@ static void falcon_push_irq_moderation(struct efx_channel *channel)
 	struct efx_nic *efx = channel->efx;
 
 	/* Set timer register */
-	if (channel->irq_moderation) {
+	if (channel->irq_moderation_us) {
+		unsigned int ticks;
+
+		ticks = efx_usecs_to_ticks(efx, channel->irq_moderation_us);
 		EFX_POPULATE_DWORD_2(timer_cmd,
 				     FRF_AB_TC_TIMER_MODE,
 				     FFE_BB_TIMER_MODE_INT_HLDOFF,
 				     FRF_AB_TC_TIMER_VAL,
-				     channel->irq_moderation - 1);
+				     ticks - 1);
 	} else {
 		EFX_POPULATE_DWORD_2(timer_cmd,
 				     FRF_AB_TC_TIMER_MODE,
@@ -2373,6 +2376,8 @@ static int falcon_probe_nic(struct efx_nic *efx)
 			     EFX_MAX_CHANNELS);
 	efx->max_tx_channels = efx->max_channels;
 	efx->timer_quantum_ns = 4968; /* 621 cycles */
+	efx->timer_max_ns = efx->type->timer_period_max *
+			    efx->timer_quantum_ns;
 
 	/* Initialise I2C adapter */
 	board = falcon_board(efx);

drivers/net/ethernet/sfc/mcdi.c

@@ -548,7 +548,10 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
 		efx_mcdi_display_error(efx, async->cmd, async->inlen, errbuf,
 				       err_len, rc);
 	}
-	async->complete(efx, async->cookie, rc, outbuf, data_len);
+
+	if (async->complete)
+		async->complete(efx, async->cookie, rc, outbuf,
+				min(async->outlen, data_len));
 	kfree(async);
 
 	efx_mcdi_release(mcdi);

drivers/net/ethernet/sfc/net_driver.h

@@ -392,7 +392,7 @@ enum efx_sync_events_state {
  * @eventq_init: Event queue initialised flag
  * @enabled: Channel enabled indicator
  * @irq: IRQ number (MSI and MSI-X only)
- * @irq_moderation: IRQ moderation value (in hardware ticks)
+ * @irq_moderation_us: IRQ moderation value (in microseconds)
  * @napi_dev: Net device used with NAPI
  * @napi_str: NAPI control structure
  * @state: state for NAPI vs busy polling
@@ -433,7 +433,7 @@ struct efx_channel {
 	bool eventq_init;
 	bool enabled;
 	int irq;
-	unsigned int irq_moderation;
+	unsigned int irq_moderation_us;
 	struct net_device *napi_dev;
 	struct napi_struct napi_str;
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -810,8 +810,10 @@ struct vfdi_status;
  * @membase: Memory BAR value
  * @interrupt_mode: Interrupt mode
  * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds
+ * @timer_max_ns: Interrupt timer maximum value, in nanoseconds
  * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues
- * @irq_rx_moderation: IRQ moderation time for RX event queues
+ * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues
+ * @irq_rx_moderation_us: IRQ moderation time for RX event queues
  * @msg_enable: Log message enable flags
  * @state: Device state number (%STATE_*). Serialised by the rtnl_lock.
  * @reset_pending: Bitmask for pending resets
@@ -940,8 +942,10 @@ struct efx_nic {
 
 	enum efx_int_mode interrupt_mode;
 	unsigned int timer_quantum_ns;
+	unsigned int timer_max_ns;
 	bool irq_rx_adaptive;
-	unsigned int irq_rx_moderation;
+	unsigned int irq_mod_step_us;
+	unsigned int irq_rx_moderation_us;
 	u32 msg_enable;
 
 	enum nic_state state;

drivers/net/ethernet/sfc/nic.h

@@ -507,10 +507,13 @@ enum {
  * @stats: Hardware statistics
  * @workaround_35388: Flag: firmware supports workaround for bug 35388
  * @workaround_26807: Flag: firmware supports workaround for bug 26807
+ * @workaround_61265: Flag: firmware supports workaround for bug 61265
  * @must_check_datapath_caps: Flag: @datapath_caps needs to be revalidated
  *	after MC reboot
  * @datapath_caps: Capabilities of datapath firmware (FLAGS1 field of
  *	%MC_CMD_GET_CAPABILITIES response)
+ * @datapath_caps2: Further Capabilities of datapath firmware (FLAGS2 field of
+ * %MC_CMD_GET_CAPABILITIES response)
  * @rx_dpcpu_fw_id: Firmware ID of the RxDPCPU
  * @tx_dpcpu_fw_id: Firmware ID of the TxDPCPU
  * @vport_id: The function's vport ID, only relevant for PFs
@@ -540,8 +543,10 @@ struct efx_ef10_nic_data {
 	u64 stats[EF10_STAT_COUNT];
 	bool workaround_35388;
 	bool workaround_26807;
+	bool workaround_61265;
 	bool must_check_datapath_caps;
 	u32 datapath_caps;
+	u32 datapath_caps2;
 	unsigned int rx_dpcpu_fw_id;
 	unsigned int tx_dpcpu_fw_id;
 	unsigned int vport_id;

drivers/net/ethernet/sfc/ptp.c

@@ -1306,7 +1306,7 @@ static int efx_ptp_probe_channel(struct efx_channel *channel)
 {
 	struct efx_nic *efx = channel->efx;
 
-	channel->irq_moderation = 0;
+	channel->irq_moderation_us = 0;
 	channel->rx_queue.core_index = 0;
 
 	return efx_ptp_probe(efx, channel);

drivers/net/ethernet/sfc/siena.c

@@ -34,19 +34,24 @@ static void siena_init_wol(struct efx_nic *efx);
 
 static void siena_push_irq_moderation(struct efx_channel *channel)
 {
+	struct efx_nic *efx = channel->efx;
 	efx_dword_t timer_cmd;
 
-	if (channel->irq_moderation)
+	if (channel->irq_moderation_us) {
+		unsigned int ticks;
+
+		ticks = efx_usecs_to_ticks(efx, channel->irq_moderation_us);
 		EFX_POPULATE_DWORD_2(timer_cmd,
 				     FRF_CZ_TC_TIMER_MODE,
 				     FFE_CZ_TIMER_MODE_INT_HLDOFF,
 				     FRF_CZ_TC_TIMER_VAL,
-				     channel->irq_moderation - 1);
-	else
+				     ticks - 1);
+	} else {
 		EFX_POPULATE_DWORD_2(timer_cmd,
 				     FRF_CZ_TC_TIMER_MODE,
 				     FFE_CZ_TIMER_MODE_DIS,
 				     FRF_CZ_TC_TIMER_VAL, 0);
+	}
 	efx_writed_page_locked(channel->efx, &timer_cmd, FR_BZ_TIMER_COMMAND_P0,
 			       channel->channel);
 }
@@ -222,6 +227,9 @@ static int siena_probe_nvconfig(struct efx_nic *efx)
 	efx->timer_quantum_ns =
 		(caps & (1 << MC_CMD_CAPABILITIES_TURBO_ACTIVE_LBN)) ?
 		3072 : 6144; /* 768 cycles */
+	efx->timer_max_ns = efx->type->timer_period_max *
+			    efx->timer_quantum_ns;
+
 	return rc;
 }
 

drivers/net/ethernet/sfc/workarounds.h

@@ -50,4 +50,8 @@
 #define EFX_WORKAROUND_35388(efx)					\
 	(efx_nic_rev(efx) == EFX_REV_HUNT_A0 && EFX_EF10_WORKAROUND_35388(efx))
 
+/* Moderation timer access must go through MCDI */
+#define EFX_EF10_WORKAROUND_61265(efx)					\
+	(((struct efx_ef10_nic_data *)efx->nic_data)->workaround_61265)
+
 #endif /* EFX_WORKAROUNDS_H */