[PATCH 01/17] sfc: Ignore parity errors in the other port's SRAM

[PATCH 01/17] sfc: Ignore parity errors in the other port's SRAM

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

Siena has a separate SRAM bank for each port.  On single-port boards
these can be merged together, so each port has an interrupt flag for
parity errors in the other port's SRAM.  Currently we do not enable
such merging and should mask this interrupt source.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/nic.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index b06f8e3..664fd6c 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -1563,6 +1563,8 @@ void efx_nic_init_common(struct efx_nic *efx)
 			     FRF_AZ_ILL_ADR_INT_KER_EN, 1,
 			     FRF_AZ_RBUF_OWN_INT_KER_EN, 1,
 			     FRF_AZ_TBUF_OWN_INT_KER_EN, 1);
+	if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
+		EFX_SET_OWORD_FIELD(temp, FRF_CZ_SRAM_PERR_INT_P_KER_EN, 1);
 	EFX_INVERT_OWORD(temp);
 	efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER);
 
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

[PATCH 02/17] sfc: Consistently report short MCDI responses as EIO

[Ben Hutchings]

In some cases failing functions were returning 0 which is obviously wrong.
In other cases they were returning inappropriate error codes.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/mcdi.c     |   22 ++++++++++++++--------
 drivers/net/sfc/mcdi_phy.c |    6 +++---
 2 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/net/sfc/mcdi.c b/drivers/net/sfc/mcdi.c
index c48669c..1344afa 100644
--- a/drivers/net/sfc/mcdi.c
+++ b/drivers/net/sfc/mcdi.c
@@ -613,7 +613,7 @@ int efx_mcdi_fwver(struct efx_nic *efx, u64 *version, u32 *build)
 	}
 
 	if (outlength < MC_CMD_GET_VERSION_V1_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
@@ -647,8 +647,10 @@ int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 			  outbuf, sizeof(outbuf), &outlen);
 	if (rc)
 		goto fail;
-	if (outlen < MC_CMD_DRV_ATTACH_OUT_LEN)
+	if (outlen < MC_CMD_DRV_ATTACH_OUT_LEN) {
+		rc = -EIO;
 		goto fail;
+	}
 
 	if (was_attached != NULL)
 		*was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE);
@@ -676,7 +678,7 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 		goto fail;
 
 	if (outlen < MC_CMD_GET_BOARD_CFG_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
@@ -738,8 +740,10 @@ int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out)
 			  outbuf, sizeof(outbuf), &outlen);
 	if (rc)
 		goto fail;
-	if (outlen < MC_CMD_NVRAM_TYPES_OUT_LEN)
+	if (outlen < MC_CMD_NVRAM_TYPES_OUT_LEN) {
+		rc = -EIO;
 		goto fail;
+	}
 
 	*nvram_types_out = MCDI_DWORD(outbuf, NVRAM_TYPES_OUT_TYPES);
 	return 0;
@@ -765,8 +769,10 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 			  outbuf, sizeof(outbuf), &outlen);
 	if (rc)
 		goto fail;
-	if (outlen < MC_CMD_NVRAM_INFO_OUT_LEN)
+	if (outlen < MC_CMD_NVRAM_INFO_OUT_LEN) {
+		rc = -EIO;
 		goto fail;
+	}
 
 	*size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_SIZE);
 	*erase_size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_ERASESIZE);
@@ -968,7 +974,7 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
 	if (rc)
 		return rc;
 	if (outlen < MC_CMD_GET_ASSERTS_OUT_LEN)
-		return -EINVAL;
+		return -EIO;
 
 	/* Print out any recorded assertion state */
 	flags = MCDI_DWORD(outbuf, GET_ASSERTS_OUT_GLOBAL_FLAGS);
@@ -1086,7 +1092,7 @@ int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type,
 		goto fail;
 
 	if (outlen < MC_CMD_WOL_FILTER_SET_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
@@ -1121,7 +1127,7 @@ int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out)
 		goto fail;
 
 	if (outlen < MC_CMD_WOL_FILTER_GET_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
diff --git a/drivers/net/sfc/mcdi_phy.c b/drivers/net/sfc/mcdi_phy.c
index 2f23546..5d34487 100644
--- a/drivers/net/sfc/mcdi_phy.c
+++ b/drivers/net/sfc/mcdi_phy.c
@@ -48,7 +48,7 @@ efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_cfg *cfg)
 		goto fail;
 
 	if (outlen < MC_CMD_GET_PHY_CFG_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
@@ -111,7 +111,7 @@ static int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes)
 		goto fail;
 
 	if (outlen < MC_CMD_GET_LOOPBACK_MODES_OUT_LEN) {
-		rc = -EMSGSIZE;
+		rc = -EIO;
 		goto fail;
 	}
 
@@ -587,7 +587,7 @@ static int efx_mcdi_phy_test_alive(struct efx_nic *efx)
 		return rc;
 
 	if (outlen < MC_CMD_GET_PHY_STATE_OUT_LEN)
-		return -EMSGSIZE;
+		return -EIO;
 	if (MCDI_DWORD(outbuf, GET_PHY_STATE_STATE) != MC_CMD_PHY_STATE_OK)
 		return -EINVAL;
 
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 02/17] sfc: Consistently report short MCDI responses as EIO

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:27:14 +0100

> In some cases failing functions were returning 0 which is obviously wrong.
> In other cases they were returning inappropriate error codes.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 03/17] sfc: Handle serious errors in exactly one interrupt handler

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

'Fatal' errors set an interrupt flag associated with a specific event
queue; only read the syndrome vector if we see that queue's flag set
(legacy interrupts) or in the interrupt handler for that queue (MSI).

Do not ignore an interrupt if the fatal error flag is set but specific
error flags are all zero.  Even if we don't schedule a reset, we must
respect the queue mask and rearm the appropriate event queues.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/falcon.c     |   13 ++++++++-----
 drivers/net/sfc/net_driver.h |    2 ++
 drivers/net/sfc/nic.c        |   35 +++++++++++++++++++----------------
 3 files changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c
index d294d66..d09ad1b 100644
--- a/drivers/net/sfc/falcon.c
+++ b/drivers/net/sfc/falcon.c
@@ -175,16 +175,19 @@ irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
 	EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n",
 		  irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
 
-	/* Check to see if we have a serious error condition */
-	syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
-	if (unlikely(syserr))
-		return efx_nic_fatal_interrupt(efx);
-
 	/* Determine interrupting queues, clear interrupt status
 	 * register and acknowledge the device interrupt.
 	 */
 	BUILD_BUG_ON(FSF_AZ_NET_IVEC_INT_Q_WIDTH > EFX_MAX_CHANNELS);
 	queues = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_INT_Q);
+
+	/* Check to see if we have a serious error condition */
+	if (queues & (1U << efx->fatal_irq_level)) {
+		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+		if (unlikely(syserr))
+			return efx_nic_fatal_interrupt(efx);
+	}
+
 	EFX_ZERO_OWORD(*int_ker);
 	wmb(); /* Ensure the vector is cleared before interrupt ack */
 	falcon_irq_ack_a1(efx);
diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index cb018e2..70aea3a 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -672,6 +672,7 @@ union efx_multicast_hash {
  *	This register is written with the SMP processor ID whenever an
  *	interrupt is handled.  It is used by efx_nic_test_interrupt()
  *	to verify that an interrupt has occurred.
+ * @fatal_irq_level: IRQ level (bit number) used for serious errors
  * @spi_flash: SPI flash device
  *	This field will be %NULL if no flash device is present (or for Siena).
  * @spi_eeprom: SPI EEPROM device
@@ -756,6 +757,7 @@ struct efx_nic {
 	struct efx_buffer irq_status;
 	volatile signed int last_irq_cpu;
 	unsigned long irq_zero_count;
+	unsigned fatal_irq_level;
 
 	struct efx_spi_device *spi_flash;
 	struct efx_spi_device *spi_eeprom;
diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index 664fd6c..23738f8 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -1229,15 +1229,9 @@ static inline void efx_nic_interrupts(struct efx_nic *efx,
 				      bool enabled, bool force)
 {
 	efx_oword_t int_en_reg_ker;
-	unsigned int level = 0;
-
-	if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx))
-		/* Set the level always even if we're generating a test
-		 * interrupt, because our legacy interrupt handler is safe */
-		level = 0x1f;
 
 	EFX_POPULATE_OWORD_3(int_en_reg_ker,
-			     FRF_AZ_KER_INT_LEVE_SEL, level,
+			     FRF_AZ_KER_INT_LEVE_SEL, efx->fatal_irq_level,
 			     FRF_AZ_KER_INT_KER, force,
 			     FRF_AZ_DRV_INT_EN_KER, enabled);
 	efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER);
@@ -1291,8 +1285,6 @@ irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx)
 		EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker),
 		EFX_OWORD_VAL(fatal_intr),
 		error ? "disabling bus mastering" : "no recognised error");
-	if (error == 0)
-		goto out;
 
 	/* If this is a memory parity error dump which blocks are offending */
 	mem_perr = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER);
@@ -1324,7 +1316,7 @@ irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx)
 			"NIC will be disabled\n");
 		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
 	}
-out:
+
 	return IRQ_HANDLED;
 }
 
@@ -1346,9 +1338,11 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 	queues = EFX_EXTRACT_DWORD(reg, 0, 31);
 
 	/* Check to see if we have a serious error condition */
-	syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
-	if (unlikely(syserr))
-		return efx_nic_fatal_interrupt(efx);
+	if (queues & (1U << efx->fatal_irq_level)) {
+		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+		if (unlikely(syserr))
+			return efx_nic_fatal_interrupt(efx);
+	}
 
 	if (queues != 0) {
 		if (EFX_WORKAROUND_15783(efx))
@@ -1413,9 +1407,11 @@ static irqreturn_t efx_msi_interrupt(int irq, void *dev_id)
 		  irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
 
 	/* Check to see if we have a serious error condition */
-	syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
-	if (unlikely(syserr))
-		return efx_nic_fatal_interrupt(efx);
+	if (channel->channel == efx->fatal_irq_level) {
+		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+		if (unlikely(syserr))
+			return efx_nic_fatal_interrupt(efx);
+	}
 
 	/* Schedule processing of the channel */
 	efx_schedule_channel(channel);
@@ -1553,6 +1549,13 @@ void efx_nic_init_common(struct efx_nic *efx)
 			     FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr);
 	efx_writeo(efx, &temp, FR_AZ_INT_ADR_KER);
 
+	if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx))
+		/* Use an interrupt level unused by event queues */
+		efx->fatal_irq_level = 0x1f;
+	else
+		/* Use a valid MSI-X vector */
+		efx->fatal_irq_level = 0;
+
 	/* Enable all the genuinely fatal interrupts.  (They are still
 	 * masked by the overall interrupt mask, controlled by
 	 * falcon_interrupts()).
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 03/17] sfc: Handle serious errors in exactly one interrupt handler

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:27:36 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> 'Fatal' errors set an interrupt flag associated with a specific event
> queue; only read the syndrome vector if we see that queue's flag set
> (legacy interrupts) or in the interrupt handler for that queue (MSI).
> 
> Do not ignore an interrupt if the fatal error flag is set but specific
> error flags are all zero.  Even if we don't schedule a reset, we must
> respect the queue mask and rearm the appropriate event queues.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 04/17] sfc: Stop masking out XGMII faults over reconfigures

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

The aim of this code was to avoid a spurious XGMII fault over a MAC
reconfigure. It's less relevant now that the PHY reconfigure isn't
called from the MAC reconfigure.

After applying this patch, our link stress test passed 48 hours of
testing without ever resetting the PHY.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/falcon_xmac.c |   20 +++++---------------
 1 files changed, 5 insertions(+), 15 deletions(-)

diff --git a/drivers/net/sfc/falcon_xmac.c b/drivers/net/sfc/falcon_xmac.c
index 8ccab2c..3d65abf 100644
--- a/drivers/net/sfc/falcon_xmac.c
+++ b/drivers/net/sfc/falcon_xmac.c
@@ -85,14 +85,14 @@ int falcon_reset_xaui(struct efx_nic *efx)
 	return -ETIMEDOUT;
 }
 
-static void falcon_mask_status_intr(struct efx_nic *efx, bool enable)
+static void falcon_ack_status_intr(struct efx_nic *efx)
 {
 	efx_oword_t reg;
 
 	if ((efx_nic_rev(efx) != EFX_REV_FALCON_B0) || LOOPBACK_INTERNAL(efx))
 		return;
 
-	/* We expect xgmii faults if the wireside link is up */
+	/* We expect xgmii faults if the wireside link is down */
 	if (!EFX_WORKAROUND_5147(efx) || !efx->link_state.up)
 		return;
 
@@ -101,14 +101,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, bool enable)
 	if (efx->xmac_poll_required)
 		return;
 
-	/* Flush the ISR */
-	if (enable)
-		efx_reado(efx, &reg, FR_AB_XM_MGT_INT_MSK);
-
-	EFX_POPULATE_OWORD_2(reg,
-			     FRF_AB_XM_MSK_RMTFLT, !enable,
-			     FRF_AB_XM_MSK_LCLFLT, !enable);
-	efx_writeo(efx, &reg, FR_AB_XM_MGT_INT_MASK);
+	efx_reado(efx, &reg, FR_AB_XM_MGT_INT_MSK);
 }
 
 static bool falcon_xgxs_link_ok(struct efx_nic *efx)
@@ -283,15 +276,13 @@ static bool falcon_xmac_check_fault(struct efx_nic *efx)
 
 static int falcon_reconfigure_xmac(struct efx_nic *efx)
 {
-	falcon_mask_status_intr(efx, false);
-
 	falcon_reconfigure_xgxs_core(efx);
 	falcon_reconfigure_xmac_core(efx);
 
 	falcon_reconfigure_mac_wrapper(efx);
 
 	efx->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 5);
-	falcon_mask_status_intr(efx, true);
+	falcon_ack_status_intr(efx);
 
 	return 0;
 }
@@ -362,9 +353,8 @@ void falcon_poll_xmac(struct efx_nic *efx)
 	    !efx->xmac_poll_required)
 		return;
 
-	falcon_mask_status_intr(efx, false);
 	efx->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 1);
-	falcon_mask_status_intr(efx, true);
+	falcon_ack_status_intr(efx);
 }
 
 struct efx_mac_operations falcon_xmac_operations = {
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 04/17] sfc: Stop masking out XGMII faults over reconfigures

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:27:54 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> The aim of this code was to avoid a spurious XGMII fault over a MAC
> reconfigure. It's less relevant now that the PHY reconfigure isn't
> called from the MAC reconfigure.
> 
> After applying this patch, our link stress test passed 48 hours of
> testing without ever resetting the PHY.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 05/17] sfc: Reconfigure the XAUI serdes after an EM reset

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

Fix a regression introduced in d3245b28ef2a45ec4e115062a38100bd06229289
"sfc: Refactor link configuration".

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/falcon.c      |    3 +++
 drivers/net/sfc/falcon_xmac.c |    2 +-
 drivers/net/sfc/nic.h         |    1 +
 3 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c
index d09ad1b..f7df24d 100644
--- a/drivers/net/sfc/falcon.c
+++ b/drivers/net/sfc/falcon.c
@@ -507,6 +507,9 @@ static void falcon_reset_macs(struct efx_nic *efx)
 	/* Ensure the correct MAC is selected before statistics
 	 * are re-enabled by the caller */
 	efx_writeo(efx, &mac_ctrl, FR_AB_MAC_CTRL);
+
+	/* This can run even when the GMAC is selected */
+	falcon_setup_xaui(efx);
 }
 
 void falcon_drain_tx_fifo(struct efx_nic *efx)
diff --git a/drivers/net/sfc/falcon_xmac.c b/drivers/net/sfc/falcon_xmac.c
index 3d65abf..c84a2ce 100644
--- a/drivers/net/sfc/falcon_xmac.c
+++ b/drivers/net/sfc/falcon_xmac.c
@@ -26,7 +26,7 @@
  *************************************************************************/
 
 /* Configure the XAUI driver that is an output from Falcon */
-static void falcon_setup_xaui(struct efx_nic *efx)
+void falcon_setup_xaui(struct efx_nic *efx)
 {
 	efx_oword_t sdctl, txdrv;
 
diff --git a/drivers/net/sfc/nic.h b/drivers/net/sfc/nic.h
index 9351c03..7e3bec8 100644
--- a/drivers/net/sfc/nic.h
+++ b/drivers/net/sfc/nic.h
@@ -203,6 +203,7 @@ extern void falcon_irq_ack_a1(struct efx_nic *efx);
 extern int efx_nic_flush_queues(struct efx_nic *efx);
 extern void falcon_start_nic_stats(struct efx_nic *efx);
 extern void falcon_stop_nic_stats(struct efx_nic *efx);
+extern void falcon_setup_xaui(struct efx_nic *efx);
 extern int falcon_reset_xaui(struct efx_nic *efx);
 extern void efx_nic_init_common(struct efx_nic *efx);
 
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 05/17] sfc: Reconfigure the XAUI serdes after an EM reset

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:28:10 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> Fix a regression introduced in d3245b28ef2a45ec4e115062a38100bd06229289
> "sfc: Refactor link configuration".
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 06/17] sfc: Extend the legacy interrupt workarounds

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

Siena has two problems with legacy interrupts:
  1. There is no synchronisation between the ISR read completion,
     and the interrupt deassert message.
  2. A downstream read at the "wrong" moment can return 0, and
     suppress generating the next interrupt.

Falcon should suffer from both of these, and it appears it does.
Enable EFX_WORKAROUND_15783 on Falcon as well.

Also, when we see queues == 0, ensure we always schedule or rearm
every event queue.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/nic.c         |   23 +++++++++--------------
 drivers/net/sfc/workarounds.h |    2 +-
 2 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index 23738f8..b61674c 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -1356,33 +1356,28 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 		}
 		result = IRQ_HANDLED;
 
-	} else if (EFX_WORKAROUND_15783(efx) &&
-		   efx->irq_zero_count++ == 0) {
+	} else if (EFX_WORKAROUND_15783(efx)) {
 		efx_qword_t *event;
 
-		/* Ensure we rearm all event queues */
+		/* We can't return IRQ_HANDLED more than once on seeing ISR=0
+		 * because this might be a shared interrupt. */
+		if (efx->irq_zero_count++ == 0)
+			result = IRQ_HANDLED;
+
+		/* Ensure we schedule or rearm all event queues */
 		efx_for_each_channel(channel, efx) {
 			event = efx_event(channel, channel->eventq_read_ptr);
 			if (efx_event_present(event))
 				efx_schedule_channel(channel);
+			else
+				efx_nic_eventq_read_ack(channel);
 		}
-
-		result = IRQ_HANDLED;
 	}
 
 	if (result == IRQ_HANDLED) {
 		efx->last_irq_cpu = raw_smp_processor_id();
 		EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n",
 			  irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg));
-	} else if (EFX_WORKAROUND_15783(efx)) {
-		/* We can't return IRQ_HANDLED more than once on seeing ISR0=0
-		 * because this might be a shared interrupt, but we do need to
-		 * check the channel every time and preemptively rearm it if
-		 * it's idle. */
-		efx_for_each_channel(channel, efx) {
-			if (!channel->work_pending)
-				efx_nic_eventq_read_ack(channel);
-		}
 	}
 
 	return result;
diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h
index acd9c73..518f7fc 100644
--- a/drivers/net/sfc/workarounds.h
+++ b/drivers/net/sfc/workarounds.h
@@ -37,7 +37,7 @@
 /* Truncated IPv4 packets can confuse the TX packet parser */
 #define EFX_WORKAROUND_15592 EFX_WORKAROUND_FALCON_AB
 /* Legacy ISR read can return zero once */
-#define EFX_WORKAROUND_15783 EFX_WORKAROUND_SIENA
+#define EFX_WORKAROUND_15783 EFX_WORKAROUND_ALWAYS
 /* Legacy interrupt storm when interrupt fifo fills */
 #define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA
 
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 06/17] sfc: Extend the legacy interrupt workarounds

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:28:27 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> Siena has two problems with legacy interrupts:
>   1. There is no synchronisation between the ISR read completion,
>      and the interrupt deassert message.
>   2. A downstream read at the "wrong" moment can return 0, and
>      suppress generating the next interrupt.
> 
> Falcon should suffer from both of these, and it appears it does.
> Enable EFX_WORKAROUND_15783 on Falcon as well.
> 
> Also, when we see queues == 0, ensure we always schedule or rearm
> every event queue.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 07/17] sfc: Log specific message for failure of NVRAM self-test

[Ben Hutchings]

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/mcdi.c |   10 ++++++++--
 1 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/sfc/mcdi.c b/drivers/net/sfc/mcdi.c
index 1344afa..93cc3c1 100644
--- a/drivers/net/sfc/mcdi.c
+++ b/drivers/net/sfc/mcdi.c
@@ -932,20 +932,26 @@ int efx_mcdi_nvram_test_all(struct efx_nic *efx)
 
 	rc = efx_mcdi_nvram_types(efx, &nvram_types);
 	if (rc)
-		return rc;
+		goto fail1;
 
 	type = 0;
 	while (nvram_types != 0) {
 		if (nvram_types & 1) {
 			rc = efx_mcdi_nvram_test(efx, type);
 			if (rc)
-				return rc;
+				goto fail2;
 		}
 		type++;
 		nvram_types >>= 1;
 	}
 
 	return 0;
+
+fail2:
+	EFX_ERR(efx, "%s: failed type=%u\n", __func__, type);
+fail1:
+	EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc);
+	return rc;
 }
 
 static int efx_mcdi_read_assertion(struct efx_nic *efx)
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 07/17] sfc: Log specific message for failure of NVRAM self-test

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:28:36 +0100

> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 08/17] sfc: Read MEM_STAT for SRM_PERR as well as MEM_PERR errors

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

Parity errors in different blocks of SRAM may set one of two different
interrupt flags.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/nic.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index b61674c..4105f90 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -1287,7 +1287,8 @@ irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx)
 		error ? "disabling bus mastering" : "no recognised error");
 
 	/* If this is a memory parity error dump which blocks are offending */
-	mem_perr = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER);
+	mem_perr = (EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER) ||
+		    EFX_OWORD_FIELD(fatal_intr, FRF_AZ_SRM_PERR_INT_KER));
 	if (mem_perr) {
 		efx_oword_t reg;
 		efx_reado(efx, &reg, FR_AZ_MEM_STAT);
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 08/17] sfc: Read MEM_STAT for SRM_PERR as well as MEM_PERR errors

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:28:52 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> Parity errors in different blocks of SRAM may set one of two different
> interrupt flags.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 09/17] sfc: Enable IPv6 RSS using random key for Toeplitz hash

[Ben Hutchings]

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/nic.h   |    2 ++
 drivers/net/sfc/siena.c |   19 +++++++++++++++++++
 2 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/drivers/net/sfc/nic.h b/drivers/net/sfc/nic.h
index 7e3bec8..5825f37 100644
--- a/drivers/net/sfc/nic.h
+++ b/drivers/net/sfc/nic.h
@@ -135,12 +135,14 @@ static inline struct falcon_board *falcon_board(struct efx_nic *efx)
  * @fw_build: Firmware build number
  * @mcdi: Management-Controller-to-Driver Interface
  * @wol_filter_id: Wake-on-LAN packet filter id
+ * @ipv6_rss_key: Toeplitz hash key for IPv6 RSS
  */
 struct siena_nic_data {
 	u64 fw_version;
 	u32 fw_build;
 	struct efx_mcdi_iface mcdi;
 	int wol_filter_id;
+	u8 ipv6_rss_key[40];
 };
 
 extern void siena_print_fwver(struct efx_nic *efx, char *buf, size_t len);
diff --git a/drivers/net/sfc/siena.c b/drivers/net/sfc/siena.c
index 38dcc42..7bf93fa 100644
--- a/drivers/net/sfc/siena.c
+++ b/drivers/net/sfc/siena.c
@@ -13,6 +13,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/random.h>
 #include "net_driver.h"
 #include "bitfield.h"
 #include "efx.h"
@@ -274,6 +275,9 @@ static int siena_probe_nic(struct efx_nic *efx)
 		goto fail5;
 	}
 
+	get_random_bytes(&nic_data->ipv6_rss_key,
+			 sizeof(nic_data->ipv6_rss_key));
+
 	return 0;
 
 fail5:
@@ -293,6 +297,7 @@ fail1:
  */
 static int siena_init_nic(struct efx_nic *efx)
 {
+	struct siena_nic_data *nic_data = efx->nic_data;
 	efx_oword_t temp;
 	int rc;
 
@@ -319,6 +324,20 @@ static int siena_init_nic(struct efx_nic *efx)
 	EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_INGR_EN, 1);
 	efx_writeo(efx, &temp, FR_AZ_RX_CFG);
 
+	/* Enable IPv6 RSS */
+	BUILD_BUG_ON(sizeof(nic_data->ipv6_rss_key) !=
+		     2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 ||
+		     FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0);
+	memcpy(&temp, nic_data->ipv6_rss_key, sizeof(temp));
+	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1);
+	memcpy(&temp, nic_data->ipv6_rss_key + sizeof(temp), sizeof(temp));
+	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2);
+	EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1,
+			     FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1);
+	memcpy(&temp, nic_data->ipv6_rss_key + 2 * sizeof(temp),
+	       FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
+	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
+
 	if (efx_nic_rx_xoff_thresh >= 0 || efx_nic_rx_xon_thresh >= 0)
 		/* No MCDI operation has been defined to set thresholds */
 		EFX_ERR(efx, "ignoring RX flow control thresholds\n");
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 09/17] sfc: Enable IPv6 RSS using random key for Toeplitz hash

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:29:02 +0100

> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 10/17] sfc: Update MCDI protocol definitions

[Ben Hutchings]

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/mcdi_pcol.h |   71 +++++++++++++++++++++++++++++++++----------
 1 files changed, 55 insertions(+), 16 deletions(-)

diff --git a/drivers/net/sfc/mcdi_pcol.h b/drivers/net/sfc/mcdi_pcol.h
index bd59302..90359e6 100644
--- a/drivers/net/sfc/mcdi_pcol.h
+++ b/drivers/net/sfc/mcdi_pcol.h
@@ -863,7 +863,7 @@
  * bist output. The driver should only consume the BIST output
  * after validating OUTLEN and PHY_CFG.PHY_TYPE.
  *
- * If a driver can't succesfully parse the BIST output, it should
+ * If a driver can't successfully parse the BIST output, it should
  * still respect the pass/Fail in OUT.RESULT
  *
  * Locks required: PHY_LOCK if doing a  PHY BIST
@@ -872,7 +872,7 @@
 #define MC_CMD_POLL_BIST 0x26
 #define MC_CMD_POLL_BIST_IN_LEN 0
 #define MC_CMD_POLL_BIST_OUT_LEN UNKNOWN
-#define MC_CMD_POLL_BIST_OUT_SFT9001_LEN 40
+#define MC_CMD_POLL_BIST_OUT_SFT9001_LEN 36
 #define MC_CMD_POLL_BIST_OUT_MRSFP_LEN 8
 #define MC_CMD_POLL_BIST_OUT_RESULT_OFST 0
 #define MC_CMD_POLL_BIST_RUNNING 1
@@ -882,15 +882,14 @@
 /* Generic: */
 #define MC_CMD_POLL_BIST_OUT_PRIVATE_OFST 4
 /* SFT9001-specific: */
-/* (offset 4 unused?) */
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A_OFST 8
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_B_OFST 12
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_C_OFST 16
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_D_OFST 20
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_A_OFST 24
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_B_OFST 28
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_C_OFST 32
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_D_OFST 36
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A_OFST 4
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_B_OFST 8
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_C_OFST 12
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_D_OFST 16
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_A_OFST 20
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_B_OFST 24
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_C_OFST 28
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_D_OFST 32
 #define MC_CMD_POLL_BIST_SFT9001_PAIR_OK 1
 #define MC_CMD_POLL_BIST_SFT9001_PAIR_OPEN 2
 #define MC_CMD_POLL_BIST_SFT9001_INTRA_PAIR_SHORT 3
@@ -1054,9 +1053,13 @@
 /* MC_CMD_PHY_STATS:
  * Get generic PHY statistics
  *
- * This call returns the statistics for a generic PHY, by direct DMA
- * into host memory, in a sparse array (indexed by the enumerate).
- * Each value is represented by a 32bit number.
+ * This call returns the statistics for a generic PHY in a sparse
+ * array (indexed by the enumerate). Each value is represented by
+ * a 32bit number.
+ *
+ * If the DMA_ADDR is 0, then no DMA is performed, and the statistics
+ * may be read directly out of shared memory. If DMA_ADDR != 0, then
+ * the statistics are dmad to that (page-aligned location)
  *
  * Locks required: None
  * Returns: 0, ETIME
@@ -1066,7 +1069,8 @@
 #define MC_CMD_PHY_STATS_IN_LEN 8
 #define MC_CMD_PHY_STATS_IN_DMA_ADDR_LO_OFST 0
 #define MC_CMD_PHY_STATS_IN_DMA_ADDR_HI_OFST 4
-#define MC_CMD_PHY_STATS_OUT_LEN 0
+#define MC_CMD_PHY_STATS_OUT_DMA_LEN 0
+#define MC_CMD_PHY_STATS_OUT_NO_DMA_LEN (MC_CMD_PHY_NSTATS * 4)
 
 /* Unified MAC statistics enumeration */
 #define MC_CMD_MAC_GENERATION_START 0
@@ -1158,11 +1162,13 @@
 #define MC_CMD_MAC_STATS_CMD_CLEAR_WIDTH 1
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_LBN 2
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_WIDTH 1
-/* Fields only relevent when PERIODIC_CHANGE is set */
+/* Remaining PERIOD* fields only relevent when PERIODIC_CHANGE is set */
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_LBN 3
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_WIDTH 1
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_LBN 4
 #define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_WIDTH 1
+#define MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT_LBN 5
+#define MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT_WIDTH 1
 #define MC_CMD_MAC_STATS_CMD_PERIOD_MS_LBN 16
 #define MC_CMD_MAC_STATS_CMD_PERIOD_MS_WIDTH 16
 #define MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12
@@ -1729,6 +1735,39 @@
 #define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_OFST 4    /* output bits */
 #define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OFST 8  /* dirs: 0=out, 1=in */
 
+/* MC_CMD_TEST_HACK: (debug (unsurprisingly))
+  * Change bits of network port state for test purposes in ways that would never be
+  * useful in normal operation and so need a special command to change. */
+#define MC_CMD_TEST_HACK 0x2f
+#define MC_CMD_TEST_HACK_IN_LEN 8
+#define MC_CMD_TEST_HACK_IN_TXPAD_OFST 0
+#define   MC_CMD_TEST_HACK_IN_TXPAD_AUTO  0 /* Let the MC manage things */
+#define   MC_CMD_TEST_HACK_IN_TXPAD_ON    1 /* Force on */
+#define   MC_CMD_TEST_HACK_IN_TXPAD_OFF   2 /* Force on */
+#define MC_CMD_TEST_HACK_IN_IPG_OFST   4 /* Takes a value in bits */
+#define   MC_CMD_TEST_HACK_IN_IPG_AUTO    0 /* The MC picks the value */
+#define MC_CMD_TEST_HACK_OUT_LEN 0
+
+/* MC_CMD_SENSOR_SET_LIMS: (debug) (mostly) adjust the sensor limits. This
+ * is a warranty-voiding operation.
+  *
+ * IN: sensor identifier (one of the enumeration starting with MC_CMD_SENSOR_CONTROLLER_TEMP
+ * followed by 4 32-bit values: min(warning) max(warning), min(fatal), max(fatal). Which
+ * of these limits are meaningful and what their interpretation is is sensor-specific.
+ *
+ * OUT: nothing
+ *
+ * Returns: ENOENT if the sensor specified does not exist, EINVAL if the limits are
+  * out of range.
+ */
+#define MC_CMD_SENSOR_SET_LIMS 0x4e
+#define MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
+#define MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
+#define MC_CMD_SENSOR_SET_LIMS_IN_LOW0_OFST 4
+#define MC_CMD_SENSOR_SET_LIMS_IN_HI0_OFST  8
+#define MC_CMD_SENSOR_SET_LIMS_IN_LOW1_OFST 12
+#define MC_CMD_SENSOR_SET_LIMS_IN_HI1_OFST  16
+
 /* Do NOT add new commands beyond 0x4f as part of 3.0 : 0x50 - 0x7f will be
  * used for post-3.0 extensions. If you run out of space, look for gaps or
  * commands that are unused in the existing range. */
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 10/17] sfc: Update MCDI protocol definitions

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:29:14 +0100

> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 11/17] sfc: Set PERIODIC_NOEVENT flag for MC_CMD_MAC_STATS

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

When set, an event is not sent whenever periodic MAC statistics are
raised.  This avoids unnecessary wake-ups.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/mcdi_mac.c |   25 +++++++++----------------
 1 files changed, 9 insertions(+), 16 deletions(-)

diff --git a/drivers/net/sfc/mcdi_mac.c b/drivers/net/sfc/mcdi_mac.c
index 06d24a1..3918263 100644
--- a/drivers/net/sfc/mcdi_mac.c
+++ b/drivers/net/sfc/mcdi_mac.c
@@ -80,7 +80,7 @@ int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr,
 	u8 inbuf[MC_CMD_MAC_STATS_IN_LEN];
 	int rc;
 	efx_dword_t *cmd_ptr;
-	int period = 1000;
+	int period = enable ? 1000 : 0;
 	u32 addr_hi;
 	u32 addr_lo;
 
@@ -92,21 +92,14 @@ int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr,
 	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_LO, addr_lo);
 	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_HI, addr_hi);
 	cmd_ptr = (efx_dword_t *)MCDI_PTR(inbuf, MAC_STATS_IN_CMD);
-	if (enable)
-		EFX_POPULATE_DWORD_6(*cmd_ptr,
-				     MC_CMD_MAC_STATS_CMD_DMA, 1,
-				     MC_CMD_MAC_STATS_CMD_CLEAR, clear,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, 1,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0,
-				     MC_CMD_MAC_STATS_CMD_PERIOD_MS, period);
-	else
-		EFX_POPULATE_DWORD_5(*cmd_ptr,
-				     MC_CMD_MAC_STATS_CMD_DMA, 0,
-				     MC_CMD_MAC_STATS_CMD_CLEAR, clear,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, 0,
-				     MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0);
+	EFX_POPULATE_DWORD_7(*cmd_ptr,
+			     MC_CMD_MAC_STATS_CMD_DMA, !!enable,
+			     MC_CMD_MAC_STATS_CMD_CLEAR, clear,
+			     MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1,
+			     MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, !!enable,
+			     MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0,
+			     MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT, 1,
+			     MC_CMD_MAC_STATS_CMD_PERIOD_MS, period);
 	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 11/17] sfc: Set PERIODIC_NOEVENT flag for MC_CMD_MAC_STATS

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:29:32 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> When set, an event is not sent whenever periodic MAC statistics are
> raised.  This avoids unnecessary wake-ups.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 12/17] sfc: Break NAPI processing after one ring-full of TX completions

[Ben Hutchings]

Currently TX completions do not count towards the NAPI budget.  This
means a continuous stream of TX completions can cause the polling
function to loop indefinitely with scheduling disabled.  To avoid
this, follow the common practice of reporting the budget spent after
processing one ring-full of TX completions.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/efx.c |   18 +++++++++---------
 drivers/net/sfc/nic.c |   39 ++++++++++++++++++++++++---------------
 2 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 1ad61b7..5e3f944 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -225,17 +225,17 @@ static void efx_fini_channels(struct efx_nic *efx);
  * never be concurrently called more than once on the same channel,
  * though different channels may be being processed concurrently.
  */
-static int efx_process_channel(struct efx_channel *channel, int rx_quota)
+static int efx_process_channel(struct efx_channel *channel, int budget)
 {
 	struct efx_nic *efx = channel->efx;
-	int rx_packets;
+	int spent;
 
 	if (unlikely(efx->reset_pending != RESET_TYPE_NONE ||
 		     !channel->enabled))
 		return 0;
 
-	rx_packets = efx_nic_process_eventq(channel, rx_quota);
-	if (rx_packets == 0)
+	spent = efx_nic_process_eventq(channel, budget);
+	if (spent == 0)
 		return 0;
 
 	/* Deliver last RX packet. */
@@ -249,7 +249,7 @@ static int efx_process_channel(struct efx_channel *channel, int rx_quota)
 
 	efx_fast_push_rx_descriptors(&efx->rx_queue[channel->channel]);
 
-	return rx_packets;
+	return spent;
 }
 
 /* Mark channel as finished processing
@@ -278,14 +278,14 @@ static int efx_poll(struct napi_struct *napi, int budget)
 {
 	struct efx_channel *channel =
 		container_of(napi, struct efx_channel, napi_str);
-	int rx_packets;
+	int spent;
 
 	EFX_TRACE(channel->efx, "channel %d NAPI poll executing on CPU %d\n",
 		  channel->channel, raw_smp_processor_id());
 
-	rx_packets = efx_process_channel(channel, budget);
+	spent = efx_process_channel(channel, budget);
 
-	if (rx_packets < budget) {
+	if (spent < budget) {
 		struct efx_nic *efx = channel->efx;
 
 		if (channel->used_flags & EFX_USED_BY_RX &&
@@ -318,7 +318,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		efx_channel_processed(channel);
 	}
 
-	return rx_packets;
+	return spent;
 }
 
 /* Process the eventq of the specified channel immediately on this CPU
diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index 4105f90..f3226bb 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -654,22 +654,23 @@ void efx_generate_event(struct efx_channel *channel, efx_qword_t *event)
  * The NIC batches TX completion events; the message we receive is of
  * the form "complete all TX events up to this index".
  */
-static void
+static int
 efx_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
 {
 	unsigned int tx_ev_desc_ptr;
 	unsigned int tx_ev_q_label;
 	struct efx_tx_queue *tx_queue;
 	struct efx_nic *efx = channel->efx;
+	int tx_packets = 0;
 
 	if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) {
 		/* Transmit completion */
 		tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR);
 		tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
 		tx_queue = &efx->tx_queue[tx_ev_q_label];
-		channel->irq_mod_score +=
-			(tx_ev_desc_ptr - tx_queue->read_count) &
-			EFX_TXQ_MASK;
+		tx_packets = ((tx_ev_desc_ptr - tx_queue->read_count) &
+			      EFX_TXQ_MASK);
+		channel->irq_mod_score += tx_packets;
 		efx_xmit_done(tx_queue, tx_ev_desc_ptr);
 	} else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) {
 		/* Rewrite the FIFO write pointer */
@@ -689,6 +690,8 @@ efx_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
 			EFX_QWORD_FMT"\n", channel->channel,
 			EFX_QWORD_VAL(*event));
 	}
+
+	return tx_packets;
 }
 
 /* Detect errors included in the rx_evt_pkt_ok bit. */
@@ -947,16 +950,17 @@ efx_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
 	}
 }
 
-int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota)
+int efx_nic_process_eventq(struct efx_channel *channel, int budget)
 {
 	unsigned int read_ptr;
 	efx_qword_t event, *p_event;
 	int ev_code;
-	int rx_packets = 0;
+	int tx_packets = 0;
+	int spent = 0;
 
 	read_ptr = channel->eventq_read_ptr;
 
-	do {
+	for (;;) {
 		p_event = efx_event(channel, read_ptr);
 		event = *p_event;
 
@@ -970,15 +974,23 @@ int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota)
 		/* Clear this event by marking it all ones */
 		EFX_SET_QWORD(*p_event);
 
+		/* Increment read pointer */
+		read_ptr = (read_ptr + 1) & EFX_EVQ_MASK;
+
 		ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE);
 
 		switch (ev_code) {
 		case FSE_AZ_EV_CODE_RX_EV:
 			efx_handle_rx_event(channel, &event);
-			++rx_packets;
+			if (++spent == budget)
+				goto out;
 			break;
 		case FSE_AZ_EV_CODE_TX_EV:
-			efx_handle_tx_event(channel, &event);
+			tx_packets += efx_handle_tx_event(channel, &event);
+			if (tx_packets >= EFX_TXQ_SIZE) {
+				spent = budget;
+				goto out;
+			}
 			break;
 		case FSE_AZ_EV_CODE_DRV_GEN_EV:
 			channel->eventq_magic = EFX_QWORD_FIELD(
@@ -1001,14 +1013,11 @@ int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota)
 				" (data " EFX_QWORD_FMT ")\n", channel->channel,
 				ev_code, EFX_QWORD_VAL(event));
 		}
+	}
 
-		/* Increment read pointer */
-		read_ptr = (read_ptr + 1) & EFX_EVQ_MASK;
-
-	} while (rx_packets < rx_quota);
-
+out:
 	channel->eventq_read_ptr = read_ptr;
-	return rx_packets;
+	return spent;
 }
 

-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 12/17] sfc: Break NAPI processing after one ring-full of TX completions

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:29:42 +0100

> Currently TX completions do not count towards the NAPI budget.  This
> means a continuous stream of TX completions can cause the polling
> function to loop indefinitely with scheduling disabled.  To avoid
> this, follow the common practice of reporting the budget spent after
> processing one ring-full of TX completions.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 13/17] sfc: Add necessary parentheses to macro definitions in net_driver.h

[Ben Hutchings]

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/net_driver.h |   22 +++++++++++-----------
 1 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index 70aea3a..bdea03c 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -926,8 +926,8 @@ struct efx_nic_type {
 
 /* Iterate over all used channels */
 #define efx_for_each_channel(_channel, _efx)				\
-	for (_channel = &_efx->channel[0];				\
-	     _channel < &_efx->channel[EFX_MAX_CHANNELS];		\
+	for (_channel = &((_efx)->channel[0]);				\
+	     _channel < &((_efx)->channel[EFX_MAX_CHANNELS]);		\
 	     _channel++)						\
 		if (!_channel->used_flags)				\
 			continue;					\
@@ -935,31 +935,31 @@ struct efx_nic_type {
 
 /* Iterate over all used TX queues */
 #define efx_for_each_tx_queue(_tx_queue, _efx)				\
-	for (_tx_queue = &_efx->tx_queue[0];				\
-	     _tx_queue < &_efx->tx_queue[EFX_TX_QUEUE_COUNT];		\
+	for (_tx_queue = &((_efx)->tx_queue[0]);			\
+	     _tx_queue < &((_efx)->tx_queue[EFX_TX_QUEUE_COUNT]);	\
 	     _tx_queue++)
 
 /* Iterate over all TX queues belonging to a channel */
 #define efx_for_each_channel_tx_queue(_tx_queue, _channel)		\
-	for (_tx_queue = &_channel->efx->tx_queue[0];			\
-	     _tx_queue < &_channel->efx->tx_queue[EFX_TX_QUEUE_COUNT];	\
+	for (_tx_queue = &((_channel)->efx->tx_queue[0]);		\
+	     _tx_queue < &((_channel)->efx->tx_queue[EFX_TX_QUEUE_COUNT]); \
 	     _tx_queue++)						\
-		if (_tx_queue->channel != _channel)			\
+		if (_tx_queue->channel != (_channel))			\
 			continue;					\
 		else
 
 /* Iterate over all used RX queues */
 #define efx_for_each_rx_queue(_rx_queue, _efx)				\
-	for (_rx_queue = &_efx->rx_queue[0];				\
-	     _rx_queue < &_efx->rx_queue[_efx->n_rx_queues];		\
+	for (_rx_queue = &((_efx)->rx_queue[0]);			\
+	     _rx_queue < &((_efx)->rx_queue[(_efx)->n_rx_queues]);	\
 	     _rx_queue++)
 
 /* Iterate over all RX queues belonging to a channel */
 #define efx_for_each_channel_rx_queue(_rx_queue, _channel)		\
-	for (_rx_queue = &_channel->efx->rx_queue[_channel->channel];	\
+	for (_rx_queue = &((_channel)->efx->rx_queue[(_channel)->channel]); \
 	     _rx_queue;							\
 	     _rx_queue = NULL)						\
-		if (_rx_queue->channel != _channel)			\
+		if (_rx_queue->channel != (_channel))			\
 			continue;					\
 		else
 
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 13/17] sfc: Add necessary parentheses to macro definitions in net_driver.h

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:29:50 +0100

> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 14/17] sfc: Clean up efx_nic::irq_zero_count

[Ben Hutchings]

There is no need for this to be unsigned long; make it unsigned int.
It does need a line in kernel-doc, so add that.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/net_driver.h |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index bdea03c..d68331c 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -672,6 +672,7 @@ union efx_multicast_hash {
  *	This register is written with the SMP processor ID whenever an
  *	interrupt is handled.  It is used by efx_nic_test_interrupt()
  *	to verify that an interrupt has occurred.
+ * @irq_zero_count: Number of legacy IRQs seen with queue flags == 0
  * @fatal_irq_level: IRQ level (bit number) used for serious errors
  * @spi_flash: SPI flash device
  *	This field will be %NULL if no flash device is present (or for Siena).
@@ -756,7 +757,7 @@ struct efx_nic {
 
 	struct efx_buffer irq_status;
 	volatile signed int last_irq_cpu;
-	unsigned long irq_zero_count;
+	unsigned irq_zero_count;
 	unsigned fatal_irq_level;
 
 	struct efx_spi_device *spi_flash;
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 14/17] sfc: Clean up efx_nic::irq_zero_count

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:30:00 +0100

> There is no need for this to be unsigned long; make it unsigned int.
> It does need a line in kernel-doc, so add that.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 15/17] sfc: Add Siena PHY BIST and cable diagnostic support

[Ben Hutchings]

From: Steve Hodgson <shodgson@solarflare.com>

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/mcdi_phy.c |  146 +++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 144 insertions(+), 2 deletions(-)

diff --git a/drivers/net/sfc/mcdi_phy.c b/drivers/net/sfc/mcdi_phy.c
index 5d34487..6032c0e 100644
--- a/drivers/net/sfc/mcdi_phy.c
+++ b/drivers/net/sfc/mcdi_phy.c
@@ -17,6 +17,8 @@
 #include "mcdi.h"
 #include "mcdi_pcol.h"
 #include "mdio_10g.h"
+#include "nic.h"
+#include "selftest.h"
 
 struct efx_mcdi_phy_cfg {
 	u32 flags;
@@ -594,6 +596,146 @@ static int efx_mcdi_phy_test_alive(struct efx_nic *efx)
 	return 0;
 }
 
+static const char *const mcdi_sft9001_cable_diag_names[] = {
+	"cable.pairA.length",
+	"cable.pairB.length",
+	"cable.pairC.length",
+	"cable.pairD.length",
+	"cable.pairA.status",
+	"cable.pairB.status",
+	"cable.pairC.status",
+	"cable.pairD.status",
+};
+
+static int efx_mcdi_bist(struct efx_nic *efx, unsigned int bist_mode,
+			 int *results)
+{
+	unsigned int retry, i, count = 0;
+	size_t outlen;
+	u32 status;
+	u8 *buf, *ptr;
+	int rc;
+
+	buf = kzalloc(0x100, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	BUILD_BUG_ON(MC_CMD_START_BIST_OUT_LEN != 0);
+	MCDI_SET_DWORD(buf, START_BIST_IN_TYPE, bist_mode);
+	rc = efx_mcdi_rpc(efx, MC_CMD_START_BIST, buf, MC_CMD_START_BIST_IN_LEN,
+			  NULL, 0, NULL);
+	if (rc)
+		goto out;
+
+	/* Wait up to 10s for BIST to finish */
+	for (retry = 0; retry < 100; ++retry) {
+		BUILD_BUG_ON(MC_CMD_POLL_BIST_IN_LEN != 0);
+		rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0,
+				  buf, 0x100, &outlen);
+		if (rc)
+			goto out;
+
+		status = MCDI_DWORD(buf, POLL_BIST_OUT_RESULT);
+		if (status != MC_CMD_POLL_BIST_RUNNING)
+			goto finished;
+
+		msleep(100);
+	}
+
+	rc = -ETIMEDOUT;
+	goto out;
+
+finished:
+	results[count++] = (status == MC_CMD_POLL_BIST_PASSED) ? 1 : -1;
+
+	/* SFT9001 specific cable diagnostics output */
+	if (efx->phy_type == PHY_TYPE_SFT9001B &&
+	    (bist_mode == MC_CMD_PHY_BIST_CABLE_SHORT ||
+	     bist_mode == MC_CMD_PHY_BIST_CABLE_LONG)) {
+		ptr = MCDI_PTR(buf, POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A);
+		if (status == MC_CMD_POLL_BIST_PASSED &&
+		    outlen >= MC_CMD_POLL_BIST_OUT_SFT9001_LEN) {
+			for (i = 0; i < 8; i++) {
+				results[count + i] =
+					EFX_DWORD_FIELD(((efx_dword_t *)ptr)[i],
+							EFX_DWORD_0);
+			}
+		}
+		count += 8;
+	}
+	rc = count;
+
+out:
+	kfree(buf);
+
+	return rc;
+}
+
+static int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results,
+				  unsigned flags)
+{
+	struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data;
+	u32 mode;
+	int rc;
+
+	if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_LBN)) {
+		rc = efx_mcdi_bist(efx, MC_CMD_PHY_BIST, results);
+		if (rc < 0)
+			return rc;
+
+		results += rc;
+	}
+
+	/* If we support both LONG and SHORT, then run each in response to
+	 * break or not. Otherwise, run the one we support */
+	mode = 0;
+	if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_LBN)) {
+		if ((flags & ETH_TEST_FL_OFFLINE) &&
+		    (phy_cfg->flags &
+		     (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN)))
+			mode = MC_CMD_PHY_BIST_CABLE_LONG;
+		else
+			mode = MC_CMD_PHY_BIST_CABLE_SHORT;
+	} else if (phy_cfg->flags &
+		   (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN))
+		mode = MC_CMD_PHY_BIST_CABLE_LONG;
+
+	if (mode != 0) {
+		rc = efx_mcdi_bist(efx, mode, results);
+		if (rc < 0)
+			return rc;
+		results += rc;
+	}
+
+	return 0;
+}
+
+const char *efx_mcdi_phy_test_name(struct efx_nic *efx, unsigned int index)
+{
+	struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data;
+
+	if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_LBN)) {
+		if (index == 0)
+			return "bist";
+		--index;
+	}
+
+	if (phy_cfg->flags & ((1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_LBN) |
+			      (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN))) {
+		if (index == 0)
+			return "cable";
+		--index;
+
+		if (efx->phy_type == PHY_TYPE_SFT9001B) {
+			if (index < ARRAY_SIZE(mcdi_sft9001_cable_diag_names))
+				return mcdi_sft9001_cable_diag_names[index];
+			index -= ARRAY_SIZE(mcdi_sft9001_cable_diag_names);
+		}
+	}
+
+	return NULL;
+}
+
 struct efx_phy_operations efx_mcdi_phy_ops = {
 	.probe		= efx_mcdi_phy_probe,
 	.init 	 	= efx_port_dummy_op_int,
@@ -604,6 +746,6 @@ struct efx_phy_operations efx_mcdi_phy_ops = {
 	.get_settings	= efx_mcdi_phy_get_settings,
 	.set_settings	= efx_mcdi_phy_set_settings,
 	.test_alive	= efx_mcdi_phy_test_alive,
-	.run_tests	= NULL,
-	.test_name	= NULL,
+	.run_tests	= efx_mcdi_phy_run_tests,
+	.test_name	= efx_mcdi_phy_test_name,
 };
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 15/17] sfc: Add Siena PHY BIST and cable diagnostic support

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:30:22 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 16/17] sfc: Test only the first pair of TX queues

[Ben Hutchings]

This makes no immediate difference, but we definitely do not want
to test all TX queues once we allocate a pair of TX queues to each
channel.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/ethtool.c  |    2 +-
 drivers/net/sfc/selftest.c |    4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c
index d9f9c02..cbe9319 100644
--- a/drivers/net/sfc/ethtool.c
+++ b/drivers/net/sfc/ethtool.c
@@ -304,7 +304,7 @@ static int efx_fill_loopback_test(struct efx_nic *efx,
 {
 	struct efx_tx_queue *tx_queue;
 
-	efx_for_each_tx_queue(tx_queue, efx) {
+	efx_for_each_channel_tx_queue(tx_queue, &efx->channel[0]) {
 		efx_fill_test(test_index++, strings, data,
 			      &lb_tests->tx_sent[tx_queue->queue],
 			      EFX_TX_QUEUE_NAME(tx_queue),
diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c
index 0106b1d..3a16e06 100644
--- a/drivers/net/sfc/selftest.c
+++ b/drivers/net/sfc/selftest.c
@@ -616,8 +616,8 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests,
 			goto out;
 		}
 
-		/* Test every TX queue */
-		efx_for_each_tx_queue(tx_queue, efx) {
+		/* Test both types of TX queue */
+		efx_for_each_channel_tx_queue(tx_queue, &efx->channel[0]) {
 			state->offload_csum = (tx_queue->queue ==
 					       EFX_TX_QUEUE_OFFLOAD_CSUM);
 			rc = efx_test_loopback(tx_queue,
-- 
1.6.2.5


-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 16/17] sfc: Test only the first pair of TX queues

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:30:30 +0100

> This makes no immediate difference, but we definitely do not want
> to test all TX queues once we allocate a pair of TX queues to each
> channel.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

[PATCH 17/17] sfc: Create multiple TX queues

[Ben Hutchings]

Create a core TX queue and 2 hardware TX queues for each channel.
If separate_tx_channels is set, create equal numbers of RX and TX
channels instead.

Rewrite the channel and queue iteration macros accordingly.
Eliminate efx_channel::used_flags as redundant.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/sfc/efx.c        |  113 ++++++++++++++++++++++-------------------
 drivers/net/sfc/efx.h        |    4 +-
 drivers/net/sfc/ethtool.c    |    4 +-
 drivers/net/sfc/net_driver.h |   61 ++++++++++------------
 drivers/net/sfc/nic.c        |   12 ++--
 drivers/net/sfc/selftest.c   |    4 +-
 drivers/net/sfc/selftest.h   |    4 +-
 drivers/net/sfc/tx.c         |   61 ++++++++++++++---------
 8 files changed, 140 insertions(+), 123 deletions(-)

diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 5e3f944..bc75ef6 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -288,7 +288,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 	if (spent < budget) {
 		struct efx_nic *efx = channel->efx;
 
-		if (channel->used_flags & EFX_USED_BY_RX &&
+		if (channel->channel < efx->n_rx_channels &&
 		    efx->irq_rx_adaptive &&
 		    unlikely(++channel->irq_count == 1000)) {
 			if (unlikely(channel->irq_mod_score <
@@ -333,7 +333,6 @@ void efx_process_channel_now(struct efx_channel *channel)
 {
 	struct efx_nic *efx = channel->efx;
 
-	BUG_ON(!channel->used_flags);
 	BUG_ON(!channel->enabled);
 
 	/* Disable interrupts and wait for ISRs to complete */
@@ -446,12 +445,12 @@ static void efx_set_channel_names(struct efx_nic *efx)
 
 	efx_for_each_channel(channel, efx) {
 		number = channel->channel;
-		if (efx->n_channels > efx->n_rx_queues) {
-			if (channel->channel < efx->n_rx_queues) {
+		if (efx->n_channels > efx->n_rx_channels) {
+			if (channel->channel < efx->n_rx_channels) {
 				type = "-rx";
 			} else {
 				type = "-tx";
-				number -= efx->n_rx_queues;
+				number -= efx->n_rx_channels;
 			}
 		}
 		snprintf(channel->name, sizeof(channel->name),
@@ -585,8 +584,6 @@ static void efx_remove_channel(struct efx_channel *channel)
 	efx_for_each_channel_tx_queue(tx_queue, channel)
 		efx_remove_tx_queue(tx_queue);
 	efx_remove_eventq(channel);
-
-	channel->used_flags = 0;
 }
 
 void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue, int delay)
@@ -956,10 +953,9 @@ static void efx_fini_io(struct efx_nic *efx)
 	pci_disable_device(efx->pci_dev);
 }
 
-/* Get number of RX queues wanted.  Return number of online CPU
- * packages in the expectation that an IRQ balancer will spread
- * interrupts across them. */
-static int efx_wanted_rx_queues(void)
+/* Get number of channels wanted.  Each channel will have its own IRQ,
+ * 1 RX queue and/or 2 TX queues. */
+static int efx_wanted_channels(void)
 {
 	cpumask_var_t core_mask;
 	int count;
@@ -995,34 +991,39 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 
 	if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
 		struct msix_entry xentries[EFX_MAX_CHANNELS];
-		int wanted_ints;
-		int rx_queues;
+		int n_channels;
 
-		/* We want one RX queue and interrupt per CPU package
-		 * (or as specified by the rss_cpus module parameter).
-		 * We will need one channel per interrupt.
-		 */
-		rx_queues = rss_cpus ? rss_cpus : efx_wanted_rx_queues();
-		wanted_ints = rx_queues + (separate_tx_channels ? 1 : 0);
-		wanted_ints = min(wanted_ints, max_channels);
+		n_channels = efx_wanted_channels();
+		if (separate_tx_channels)
+			n_channels *= 2;
+		n_channels = min(n_channels, max_channels);
 
-		for (i = 0; i < wanted_ints; i++)
+		for (i = 0; i < n_channels; i++)
 			xentries[i].entry = i;
-		rc = pci_enable_msix(efx->pci_dev, xentries, wanted_ints);
+		rc = pci_enable_msix(efx->pci_dev, xentries, n_channels);
 		if (rc > 0) {
 			EFX_ERR(efx, "WARNING: Insufficient MSI-X vectors"
-				" available (%d < %d).\n", rc, wanted_ints);
+				" available (%d < %d).\n", rc, n_channels);
 			EFX_ERR(efx, "WARNING: Performance may be reduced.\n");
-			EFX_BUG_ON_PARANOID(rc >= wanted_ints);
-			wanted_ints = rc;
+			EFX_BUG_ON_PARANOID(rc >= n_channels);
+			n_channels = rc;
 			rc = pci_enable_msix(efx->pci_dev, xentries,
-					     wanted_ints);
+					     n_channels);
 		}
 
 		if (rc == 0) {
-			efx->n_rx_queues = min(rx_queues, wanted_ints);
-			efx->n_channels = wanted_ints;
-			for (i = 0; i < wanted_ints; i++)
+			efx->n_channels = n_channels;
+			if (separate_tx_channels) {
+				efx->n_tx_channels =
+					max(efx->n_channels / 2, 1U);
+				efx->n_rx_channels =
+					max(efx->n_channels -
+					    efx->n_tx_channels, 1U);
+			} else {
+				efx->n_tx_channels = efx->n_channels;
+				efx->n_rx_channels = efx->n_channels;
+			}
+			for (i = 0; i < n_channels; i++)
 				efx->channel[i].irq = xentries[i].vector;
 		} else {
 			/* Fall back to single channel MSI */
@@ -1033,8 +1034,9 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 
 	/* Try single interrupt MSI */
 	if (efx->interrupt_mode == EFX_INT_MODE_MSI) {
-		efx->n_rx_queues = 1;
 		efx->n_channels = 1;
+		efx->n_rx_channels = 1;
+		efx->n_tx_channels = 1;
 		rc = pci_enable_msi(efx->pci_dev);
 		if (rc == 0) {
 			efx->channel[0].irq = efx->pci_dev->irq;
@@ -1046,8 +1048,9 @@ static void efx_probe_interrupts(struct efx_nic *efx)
 
 	/* Assume legacy interrupts */
 	if (efx->interrupt_mode == EFX_INT_MODE_LEGACY) {
-		efx->n_rx_queues = 1;
 		efx->n_channels = 1 + (separate_tx_channels ? 1 : 0);
+		efx->n_rx_channels = 1;
+		efx->n_tx_channels = 1;
 		efx->legacy_irq = efx->pci_dev->irq;
 	}
 }
@@ -1068,21 +1071,24 @@ static void efx_remove_interrupts(struct efx_nic *efx)
 
 static void efx_set_channels(struct efx_nic *efx)
 {
+	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
+	unsigned tx_channel_offset =
+		separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0;
 
-	efx_for_each_tx_queue(tx_queue, efx) {
-		if (separate_tx_channels)
-			tx_queue->channel = &efx->channel[efx->n_channels-1];
-		else
-			tx_queue->channel = &efx->channel[0];
-		tx_queue->channel->used_flags |= EFX_USED_BY_TX;
+	efx_for_each_channel(channel, efx) {
+		if (channel->channel - tx_channel_offset < efx->n_tx_channels) {
+			channel->tx_queue = &efx->tx_queue[
+				(channel->channel - tx_channel_offset) *
+				EFX_TXQ_TYPES];
+			efx_for_each_channel_tx_queue(tx_queue, channel)
+				tx_queue->channel = channel;
+		}
 	}
 
-	efx_for_each_rx_queue(rx_queue, efx) {
+	efx_for_each_rx_queue(rx_queue, efx)
 		rx_queue->channel = &efx->channel[rx_queue->queue];
-		rx_queue->channel->used_flags |= EFX_USED_BY_RX;
-	}
 }
 
 static int efx_probe_nic(struct efx_nic *efx)
@@ -1096,11 +1102,12 @@ static int efx_probe_nic(struct efx_nic *efx)
 	if (rc)
 		return rc;
 
-	/* Determine the number of channels and RX queues by trying to hook
+	/* Determine the number of channels and queues by trying to hook
 	 * in MSI-X interrupts. */
 	efx_probe_interrupts(efx);
 
 	efx_set_channels(efx);
+	efx->net_dev->real_num_tx_queues = efx->n_tx_channels;
 
 	/* Initialise the interrupt moderation settings */
 	efx_init_irq_moderation(efx, tx_irq_mod_usec, rx_irq_mod_usec, true);
@@ -1187,11 +1194,12 @@ static void efx_start_all(struct efx_nic *efx)
 	/* Mark the port as enabled so port reconfigurations can start, then
 	 * restart the transmit interface early so the watchdog timer stops */
 	efx_start_port(efx);
-	if (efx_dev_registered(efx))
-		efx_wake_queue(efx);
 
-	efx_for_each_channel(channel, efx)
+	efx_for_each_channel(channel, efx) {
+		if (efx_dev_registered(efx))
+			efx_wake_queue(channel);
 		efx_start_channel(channel);
+	}
 
 	efx_nic_enable_interrupts(efx);
 
@@ -1282,7 +1290,9 @@ static void efx_stop_all(struct efx_nic *efx)
 	/* Stop the kernel transmit interface late, so the watchdog
 	 * timer isn't ticking over the flush */
 	if (efx_dev_registered(efx)) {
-		efx_stop_queue(efx);
+		struct efx_channel *channel;
+		efx_for_each_channel(channel, efx)
+			efx_stop_queue(channel);
 		netif_tx_lock_bh(efx->net_dev);
 		netif_tx_unlock_bh(efx->net_dev);
 	}
@@ -1537,9 +1547,8 @@ static void efx_watchdog(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d:"
-		" resetting channels\n",
-		atomic_read(&efx->netif_stop_count), efx->port_enabled);
+	EFX_ERR(efx, "TX stuck with port_enabled=%d: resetting channels\n",
+		efx->port_enabled);
 
 	efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG);
 }
@@ -2014,22 +2023,22 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type,
 
 	efx->net_dev = net_dev;
 	efx->rx_checksum_enabled = true;
-	spin_lock_init(&efx->netif_stop_lock);
 	spin_lock_init(&efx->stats_lock);
 	mutex_init(&efx->mac_lock);
 	efx->mac_op = type->default_mac_ops;
 	efx->phy_op = &efx_dummy_phy_operations;
 	efx->mdio.dev = net_dev;
 	INIT_WORK(&efx->mac_work, efx_mac_work);
-	atomic_set(&efx->netif_stop_count, 1);
 
 	for (i = 0; i < EFX_MAX_CHANNELS; i++) {
 		channel = &efx->channel[i];
 		channel->efx = efx;
 		channel->channel = i;
 		channel->work_pending = false;
+		spin_lock_init(&channel->tx_stop_lock);
+		atomic_set(&channel->tx_stop_count, 1);
 	}
-	for (i = 0; i < EFX_TX_QUEUE_COUNT; i++) {
+	for (i = 0; i < EFX_MAX_TX_QUEUES; i++) {
 		tx_queue = &efx->tx_queue[i];
 		tx_queue->efx = efx;
 		tx_queue->queue = i;
@@ -2201,7 +2210,7 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	int i, rc;
 
 	/* Allocate and initialise a struct net_device and struct efx_nic */
-	net_dev = alloc_etherdev(sizeof(*efx));
+	net_dev = alloc_etherdev_mq(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES);
 	if (!net_dev)
 		return -ENOMEM;
 	net_dev->features |= (type->offload_features | NETIF_F_SG |
diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h
index 7eff0a6..ffd708c 100644
--- a/drivers/net/sfc/efx.h
+++ b/drivers/net/sfc/efx.h
@@ -35,8 +35,8 @@ efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev);
 extern netdev_tx_t
 efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb);
 extern void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
-extern void efx_stop_queue(struct efx_nic *efx);
-extern void efx_wake_queue(struct efx_nic *efx);
+extern void efx_stop_queue(struct efx_channel *channel);
+extern void efx_wake_queue(struct efx_channel *channel);
 #define EFX_TXQ_SIZE 1024
 #define EFX_TXQ_MASK (EFX_TXQ_SIZE - 1)
 
diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c
index cbe9319..22026bf 100644
--- a/drivers/net/sfc/ethtool.c
+++ b/drivers/net/sfc/ethtool.c
@@ -647,7 +647,7 @@ static int efx_ethtool_get_coalesce(struct net_device *net_dev,
 	efx_for_each_tx_queue(tx_queue, efx) {
 		channel = tx_queue->channel;
 		if (channel->irq_moderation < coalesce->tx_coalesce_usecs_irq) {
-			if (channel->used_flags != EFX_USED_BY_RX_TX)
+			if (channel->channel < efx->n_rx_channels)
 				coalesce->tx_coalesce_usecs_irq =
 					channel->irq_moderation;
 			else
@@ -690,7 +690,7 @@ static int efx_ethtool_set_coalesce(struct net_device *net_dev,
 
 	/* If the channel is shared only allow RX parameters to be set */
 	efx_for_each_tx_queue(tx_queue, efx) {
-		if ((tx_queue->channel->used_flags == EFX_USED_BY_RX_TX) &&
+		if ((tx_queue->channel->channel < efx->n_rx_channels) &&
 		    tx_usecs) {
 			EFX_ERR(efx, "Channel is shared. "
 				"Only RX coalescing may be set\n");
diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h
index d68331c..2e6fd89 100644
--- a/drivers/net/sfc/net_driver.h
+++ b/drivers/net/sfc/net_driver.h
@@ -85,9 +85,13 @@ do {if (net_ratelimit()) EFX_LOG(efx, fmt, ##args); } while (0)
 #define EFX_MAX_CHANNELS 32
 #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
 
-#define EFX_TX_QUEUE_OFFLOAD_CSUM	0
-#define EFX_TX_QUEUE_NO_CSUM		1
-#define EFX_TX_QUEUE_COUNT		2
+/* Checksum generation is a per-queue option in hardware, so each
+ * queue visible to the networking core is backed by two hardware TX
+ * queues. */
+#define EFX_MAX_CORE_TX_QUEUES	EFX_MAX_CHANNELS
+#define EFX_TXQ_TYPE_OFFLOAD	1
+#define EFX_TXQ_TYPES		2
+#define EFX_MAX_TX_QUEUES	(EFX_TXQ_TYPES * EFX_MAX_CORE_TX_QUEUES)
 
 /**
  * struct efx_special_buffer - An Efx special buffer
@@ -187,7 +191,7 @@ struct efx_tx_buffer {
 struct efx_tx_queue {
 	/* Members which don't change on the fast path */
 	struct efx_nic *efx ____cacheline_aligned_in_smp;
-	int queue;
+	unsigned queue;
 	struct efx_channel *channel;
 	struct efx_nic *nic;
 	struct efx_tx_buffer *buffer;
@@ -306,11 +310,6 @@ struct efx_buffer {
 };
 

-/* Flags for channel->used_flags */
-#define EFX_USED_BY_RX 1
-#define EFX_USED_BY_TX 2
-#define EFX_USED_BY_RX_TX (EFX_USED_BY_RX | EFX_USED_BY_TX)
-
 enum efx_rx_alloc_method {
 	RX_ALLOC_METHOD_AUTO = 0,
 	RX_ALLOC_METHOD_SKB = 1,
@@ -327,7 +326,6 @@ enum efx_rx_alloc_method {
  * @efx: Associated Efx NIC
  * @channel: Channel instance number
  * @name: Name for channel and IRQ
- * @used_flags: Channel is used by net driver
  * @enabled: Channel enabled indicator
  * @irq: IRQ number (MSI and MSI-X only)
  * @irq_moderation: IRQ moderation value (in hardware ticks)
@@ -352,12 +350,14 @@ enum efx_rx_alloc_method {
  * @n_rx_frm_trunc: Count of RX_FRM_TRUNC errors
  * @n_rx_overlength: Count of RX_OVERLENGTH errors
  * @n_skbuff_leaks: Count of skbuffs leaked due to RX overrun
+ * @tx_queue: Pointer to first TX queue, or %NULL if not used for TX
+ * @tx_stop_count: Core TX queue stop count
+ * @tx_stop_lock: Core TX queue stop lock
  */
 struct efx_channel {
 	struct efx_nic *efx;
 	int channel;
 	char name[IFNAMSIZ + 6];
-	int used_flags;
 	bool enabled;
 	int irq;
 	unsigned int irq_moderation;
@@ -389,6 +389,9 @@ struct efx_channel {
 	struct efx_rx_buffer *rx_pkt;
 	bool rx_pkt_csummed;
 
+	struct efx_tx_queue *tx_queue;
+	atomic_t tx_stop_count;
+	spinlock_t tx_stop_lock;
 };
 
 enum efx_led_mode {
@@ -661,8 +664,9 @@ union efx_multicast_hash {
  * @rx_queue: RX DMA queues
  * @channel: Channels
  * @next_buffer_table: First available buffer table id
- * @n_rx_queues: Number of RX queues
  * @n_channels: Number of channels in use
+ * @n_rx_channels: Number of channels used for RX (= number of RX queues)
+ * @n_tx_channels: Number of channels used for TX
  * @rx_buffer_len: RX buffer length
  * @rx_buffer_order: Order (log2) of number of pages for each RX buffer
  * @int_error_count: Number of internal errors seen recently
@@ -693,8 +697,6 @@ union efx_multicast_hash {
  * @port_initialized: Port initialized?
  * @net_dev: Operating system network device. Consider holding the rtnl lock
  * @rx_checksum_enabled: RX checksumming enabled
- * @netif_stop_count: Port stop count
- * @netif_stop_lock: Port stop lock
  * @mac_stats: MAC statistics. These include all statistics the MACs
  *	can provide.  Generic code converts these into a standard
  *	&struct net_device_stats.
@@ -742,13 +744,14 @@ struct efx_nic {
 	enum nic_state state;
 	enum reset_type reset_pending;
 
-	struct efx_tx_queue tx_queue[EFX_TX_QUEUE_COUNT];
+	struct efx_tx_queue tx_queue[EFX_MAX_TX_QUEUES];
 	struct efx_rx_queue rx_queue[EFX_MAX_RX_QUEUES];
 	struct efx_channel channel[EFX_MAX_CHANNELS];
 
 	unsigned next_buffer_table;
-	int n_rx_queues;
-	int n_channels;
+	unsigned n_channels;
+	unsigned n_rx_channels;
+	unsigned n_tx_channels;
 	unsigned int rx_buffer_len;
 	unsigned int rx_buffer_order;
 
@@ -780,9 +783,6 @@ struct efx_nic {
 	struct net_device *net_dev;
 	bool rx_checksum_enabled;
 
-	atomic_t netif_stop_count;
-	spinlock_t netif_stop_lock;
-
 	struct efx_mac_stats mac_stats;
 	struct efx_buffer stats_buffer;
 	spinlock_t stats_lock;
@@ -928,31 +928,26 @@ struct efx_nic_type {
 /* Iterate over all used channels */
 #define efx_for_each_channel(_channel, _efx)				\
 	for (_channel = &((_efx)->channel[0]);				\
-	     _channel < &((_efx)->channel[EFX_MAX_CHANNELS]);		\
-	     _channel++)						\
-		if (!_channel->used_flags)				\
-			continue;					\
-		else
+	     _channel < &((_efx)->channel[(efx)->n_channels]);		\
+	     _channel++)
 
 /* Iterate over all used TX queues */
 #define efx_for_each_tx_queue(_tx_queue, _efx)				\
 	for (_tx_queue = &((_efx)->tx_queue[0]);			\
-	     _tx_queue < &((_efx)->tx_queue[EFX_TX_QUEUE_COUNT]);	\
+	     _tx_queue < &((_efx)->tx_queue[EFX_TXQ_TYPES *		\
+					    (_efx)->n_tx_channels]);	\
 	     _tx_queue++)
 
 /* Iterate over all TX queues belonging to a channel */
 #define efx_for_each_channel_tx_queue(_tx_queue, _channel)		\
-	for (_tx_queue = &((_channel)->efx->tx_queue[0]);		\
-	     _tx_queue < &((_channel)->efx->tx_queue[EFX_TX_QUEUE_COUNT]); \
-	     _tx_queue++)						\
-		if (_tx_queue->channel != (_channel))			\
-			continue;					\
-		else
+	for (_tx_queue = (_channel)->tx_queue;				\
+	     _tx_queue && _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES; \
+	     _tx_queue++)
 
 /* Iterate over all used RX queues */
 #define efx_for_each_rx_queue(_rx_queue, _efx)				\
 	for (_rx_queue = &((_efx)->rx_queue[0]);			\
-	     _rx_queue < &((_efx)->rx_queue[(_efx)->n_rx_queues]);	\
+	     _rx_queue < &((_efx)->rx_queue[(_efx)->n_rx_channels]);	\
 	     _rx_queue++)
 
 /* Iterate over all RX queues belonging to a channel */
diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c
index f3226bb..5d3aaec 100644
--- a/drivers/net/sfc/nic.c
+++ b/drivers/net/sfc/nic.c
@@ -418,7 +418,7 @@ void efx_nic_init_tx(struct efx_tx_queue *tx_queue)
 			      FRF_BZ_TX_NON_IP_DROP_DIS, 1);
 
 	if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
-		int csum = tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM;
+		int csum = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
 		EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_IP_CHKSM_DIS, !csum);
 		EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_TCP_CHKSM_DIS,
 				    !csum);
@@ -431,10 +431,10 @@ void efx_nic_init_tx(struct efx_tx_queue *tx_queue)
 		efx_oword_t reg;
 
 		/* Only 128 bits in this register */
-		BUILD_BUG_ON(EFX_TX_QUEUE_COUNT >= 128);
+		BUILD_BUG_ON(EFX_MAX_TX_QUEUES > 128);
 
 		efx_reado(efx, &reg, FR_AA_TX_CHKSM_CFG);
-		if (tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM)
+		if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
 			clear_bit_le(tx_queue->queue, (void *)&reg);
 		else
 			set_bit_le(tx_queue->queue, (void *)&reg);
@@ -1132,7 +1132,7 @@ static void efx_poll_flush_events(struct efx_nic *efx)
 		    ev_sub_code == FSE_AZ_TX_DESCQ_FLS_DONE_EV) {
 			ev_queue = EFX_QWORD_FIELD(*event,
 						   FSF_AZ_DRIVER_EV_SUBDATA);
-			if (ev_queue < EFX_TX_QUEUE_COUNT) {
+			if (ev_queue < EFX_TXQ_TYPES * efx->n_tx_channels) {
 				tx_queue = efx->tx_queue + ev_queue;
 				tx_queue->flushed = FLUSH_DONE;
 			}
@@ -1142,7 +1142,7 @@ static void efx_poll_flush_events(struct efx_nic *efx)
 				*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
 			ev_failed = EFX_QWORD_FIELD(
 				*event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
-			if (ev_queue < efx->n_rx_queues) {
+			if (ev_queue < efx->n_rx_channels) {
 				rx_queue = efx->rx_queue + ev_queue;
 				rx_queue->flushed =
 					ev_failed ? FLUSH_FAILED : FLUSH_DONE;
@@ -1441,7 +1441,7 @@ static void efx_setup_rss_indir_table(struct efx_nic *efx)
 	     offset < FR_BZ_RX_INDIRECTION_TBL + 0x800;
 	     offset += 0x10) {
 		EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
-				     i % efx->n_rx_queues);
+				     i % efx->n_rx_channels);
 		efx_writed(efx, &dword, offset);
 		i++;
 	}
diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c
index 3a16e06..371e86c 100644
--- a/drivers/net/sfc/selftest.c
+++ b/drivers/net/sfc/selftest.c
@@ -618,8 +618,8 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests,
 
 		/* Test both types of TX queue */
 		efx_for_each_channel_tx_queue(tx_queue, &efx->channel[0]) {
-			state->offload_csum = (tx_queue->queue ==
-					       EFX_TX_QUEUE_OFFLOAD_CSUM);
+			state->offload_csum = (tx_queue->queue &
+					       EFX_TXQ_TYPE_OFFLOAD);
 			rc = efx_test_loopback(tx_queue,
 					       &tests->loopback[mode]);
 			if (rc)
diff --git a/drivers/net/sfc/selftest.h b/drivers/net/sfc/selftest.h
index 643bef7..aed495a 100644
--- a/drivers/net/sfc/selftest.h
+++ b/drivers/net/sfc/selftest.h
@@ -18,8 +18,8 @@
  */
 
 struct efx_loopback_self_tests {
-	int tx_sent[EFX_TX_QUEUE_COUNT];
-	int tx_done[EFX_TX_QUEUE_COUNT];
+	int tx_sent[EFX_TXQ_TYPES];
+	int tx_done[EFX_TXQ_TYPES];
 	int rx_good;
 	int rx_bad;
 };
diff --git a/drivers/net/sfc/tx.c b/drivers/net/sfc/tx.c
index be0e110..6bb12a8 100644
--- a/drivers/net/sfc/tx.c
+++ b/drivers/net/sfc/tx.c
@@ -30,32 +30,46 @@
  */
 #define EFX_TXQ_THRESHOLD (EFX_TXQ_MASK / 2u)
 
-/* We want to be able to nest calls to netif_stop_queue(), since each
- * channel can have an individual stop on the queue.
- */
-void efx_stop_queue(struct efx_nic *efx)
+/* We need to be able to nest calls to netif_tx_stop_queue(), partly
+ * because of the 2 hardware queues associated with each core queue,
+ * but also so that we can inhibit TX for reasons other than a full
+ * hardware queue. */
+void efx_stop_queue(struct efx_channel *channel)
 {
-	spin_lock_bh(&efx->netif_stop_lock);
+	struct efx_nic *efx = channel->efx;
+
+	if (!channel->tx_queue)
+		return;
+
+	spin_lock_bh(&channel->tx_stop_lock);
 	EFX_TRACE(efx, "stop TX queue\n");
 
-	atomic_inc(&efx->netif_stop_count);
-	netif_stop_queue(efx->net_dev);
+	atomic_inc(&channel->tx_stop_count);
+	netif_tx_stop_queue(
+		netdev_get_tx_queue(
+			efx->net_dev,
+			channel->tx_queue->queue / EFX_TXQ_TYPES));
 
-	spin_unlock_bh(&efx->netif_stop_lock);
+	spin_unlock_bh(&channel->tx_stop_lock);
 }
 
-/* Wake netif's TX queue
- * We want to be able to nest calls to netif_stop_queue(), since each
- * channel can have an individual stop on the queue.
- */
-void efx_wake_queue(struct efx_nic *efx)
+/* Decrement core TX queue stop count and wake it if the count is 0 */
+void efx_wake_queue(struct efx_channel *channel)
 {
+	struct efx_nic *efx = channel->efx;
+
+	if (!channel->tx_queue)
+		return;
+
 	local_bh_disable();
-	if (atomic_dec_and_lock(&efx->netif_stop_count,
-				&efx->netif_stop_lock)) {
+	if (atomic_dec_and_lock(&channel->tx_stop_count,
+				&channel->tx_stop_lock)) {
 		EFX_TRACE(efx, "waking TX queue\n");
-		netif_wake_queue(efx->net_dev);
-		spin_unlock(&efx->netif_stop_lock);
+		netif_tx_wake_queue(
+			netdev_get_tx_queue(
+				efx->net_dev,
+				channel->tx_queue->queue / EFX_TXQ_TYPES));
+		spin_unlock(&channel->tx_stop_lock);
 	}
 	local_bh_enable();
 }
@@ -298,7 +312,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	rc = NETDEV_TX_BUSY;
 
 	if (tx_queue->stopped == 1)
-		efx_stop_queue(efx);
+		efx_stop_queue(tx_queue->channel);
 
  unwind:
 	/* Work backwards until we hit the original insert pointer value */
@@ -374,10 +388,9 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
 	if (unlikely(efx->port_inhibited))
 		return NETDEV_TX_BUSY;
 
+	tx_queue = &efx->tx_queue[EFX_TXQ_TYPES * skb_get_queue_mapping(skb)];
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL))
-		tx_queue = &efx->tx_queue[EFX_TX_QUEUE_OFFLOAD_CSUM];
-	else
-		tx_queue = &efx->tx_queue[EFX_TX_QUEUE_NO_CSUM];
+		tx_queue += EFX_TXQ_TYPE_OFFLOAD;
 
 	return efx_enqueue_skb(tx_queue, skb);
 }
@@ -405,7 +418,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
 			netif_tx_lock(efx->net_dev);
 			if (tx_queue->stopped) {
 				tx_queue->stopped = 0;
-				efx_wake_queue(efx);
+				efx_wake_queue(tx_queue->channel);
 			}
 			netif_tx_unlock(efx->net_dev);
 		}
@@ -488,7 +501,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 	/* Release queue's stop on port, if any */
 	if (tx_queue->stopped) {
 		tx_queue->stopped = 0;
-		efx_wake_queue(tx_queue->efx);
+		efx_wake_queue(tx_queue->channel);
 	}
 }
 
@@ -1120,7 +1133,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 
 	/* Stop the queue if it wasn't stopped before. */
 	if (tx_queue->stopped == 1)
-		efx_stop_queue(efx);
+		efx_stop_queue(tx_queue->channel);
 
  unwind:
 	/* Free the DMA mapping we were in the process of writing out */
-- 
1.6.2.5

-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

Re: [PATCH 17/17] sfc: Create multiple TX queues

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:30:43 +0100

> Create a core TX queue and 2 hardware TX queues for each channel.
> If separate_tx_channels is set, create equal numbers of RX and TX
> channels instead.
> 
> Rewrite the channel and queue iteration macros accordingly.
> Eliminate efx_channel::used_flags as redundant.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.

Re: [PATCH 01/17] sfc: Ignore parity errors in the other port's SRAM

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Wed, 28 Apr 2010 20:25:22 +0100

> From: Steve Hodgson <shodgson@solarflare.com>
> 
> Siena has a separate SRAM bank for each port.  On single-port boards
> these can be merged together, so each port has an interrupt flag for
> parity errors in the other port's SRAM.  Currently we do not enable
> such merging and should mask this interrupt source.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

Applied.