Pull request: sfc-next 2013-06-24

Pull request: sfc-next 2013-06-24

[Ben Hutchings]

The following changes since commit 37173488400704f1a05656616cd12baa9e03173b:

  bnx2x: Fix compilation with no IOV support (2013-06-24 01:47:47 -0700)

are available in the git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next.git for-davem

for you to fetch changes up to 636d73da27e83ce4882f8823f79063bb37980961:

  sfc: Improve test for IOMMU in use (2013-06-24 20:02:53 +0100)

1. Make EEH recovery work when using legacy interrupts, from Alexandre
   Rames.

2. Enable accelerated RFS for VLAN-tagged flows, from Andy Lutomirski.

3. Improve performance for non-TCP (and particularly UDP) traffic, which
   regressed in 3.10 when we switched to always allocating paged RX
   buffers.  Partly by Jon Cooper.

4. Some minor bug fixes to IOMMU detection, timestamping capabilities,
   and IRQ cleanup on the probe failure path.

I've dropped the RX skb cache, which improved some benchmarks but
perhaps needs some reworking to be more generally useful.

Ben.

----------------------------------------------------------------
Alexandre Rames (1):
      sfc: Fix EEH with legacy interrupts.

Andy Lutomirski (1):
      sfc: Enable accelerated RFS on vlans

Ben Hutchings (5):
      sfc: Report software timestamping capabilities
      sfc: Define and set RX buffer flag for packets parsed as TCP
      sfc: Do not pass non-TCP packets into GRO code
      sfc: Fix IRQ cleanup in case of a probe failure
      sfc: Improve test for IOMMU in use

Jon Cooper (2):
      sfc: Enable RX checksum offload for packets not handled by GRO
      sfc: Increase size of RX SKB header area

 drivers/net/ethernet/sfc/efx.c        | 40 +++----------------
 drivers/net/ethernet/sfc/efx.h        |  1 +
 drivers/net/ethernet/sfc/ethtool.c    | 16 +++++++-
 drivers/net/ethernet/sfc/filter.c     | 15 ++++++-
 drivers/net/ethernet/sfc/net_driver.h |  2 +
 drivers/net/ethernet/sfc/nic.c        | 74 ++++++++++++++++++++++++++++++-----
 drivers/net/ethernet/sfc/nic.h        |  4 +-
 drivers/net/ethernet/sfc/ptp.c        | 13 +++---
 drivers/net/ethernet/sfc/rx.c         |  8 ++--
 9 files changed, 114 insertions(+), 59 deletions(-)

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

[PATCH net-next 1/9] sfc: Fix EEH with legacy interrupts.

[Ben Hutchings]

From: Alexandre Rames <arames@solarflare.com>

PCI legacy interrupts are level-triggered, and we cannot mask them up
on an isolated device.  Instead, disable the IRQ at the controller
until we have recovered.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/efx.c        |  7 ++++++-
 drivers/net/ethernet/sfc/efx.h        |  1 +
 drivers/net/ethernet/sfc/net_driver.h |  1 +
 drivers/net/ethernet/sfc/nic.c        | 10 ++++++++++
 4 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 46cc11d..787c9eb 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -23,6 +23,7 @@
 #include <linux/gfp.h>
 #include <linux/cpu_rmap.h>
 #include <linux/aer.h>
+#include <linux/interrupt.h>
 #include "net_driver.h"
 #include "efx.h"
 #include "nic.h"
@@ -1427,6 +1428,10 @@ static void efx_start_interrupts(struct efx_nic *efx, bool may_keep_eventq)
 
 	BUG_ON(efx->state == STATE_DISABLED);
 
+	if (efx->eeh_disabled_legacy_irq) {
+		enable_irq(efx->legacy_irq);
+		efx->eeh_disabled_legacy_irq = false;
+	}
 	if (efx->legacy_irq)
 		efx->legacy_irq_enabled = true;
 	efx_nic_enable_interrupts(efx);
@@ -2365,7 +2370,7 @@ out:
  * Returns 0 if the recovery mechanisms are unsuccessful.
  * Returns a non-zero value otherwise.
  */
-static int efx_try_recovery(struct efx_nic *efx)
+int efx_try_recovery(struct efx_nic *efx)
 {
 #ifdef CONFIG_EEH
 	/* A PCI error can occur and not be seen by EEH because nothing
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 8372da2..bdb30bb 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -124,6 +124,7 @@ extern const struct ethtool_ops efx_ethtool_ops;
 extern int efx_reset(struct efx_nic *efx, enum reset_type method);
 extern void efx_reset_down(struct efx_nic *efx, enum reset_type method);
 extern int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok);
+extern int efx_try_recovery(struct efx_nic *efx);
 
 /* Global */
 extern void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 9a2914c..2dec48b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -788,6 +788,7 @@ struct efx_nic {
 	const struct efx_nic_type *type;
 	int legacy_irq;
 	bool legacy_irq_enabled;
+	bool eeh_disabled_legacy_irq;
 	struct workqueue_struct *workqueue;
 	char workqueue_name[16];
 	struct work_struct reset_work;
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index b0503cd..39432d3 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1579,6 +1579,16 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 	efx_readd(efx, &reg, FR_BZ_INT_ISR0);
 	queues = EFX_EXTRACT_DWORD(reg, 0, 31);
 
+	/* Legacy interrupts are disabled too late by the EEH kernel
+	 * code. Disable them earlier.
+	 * If an EEH error occurred, the read will have returned all ones.
+	 */
+	if (EFX_DWORD_IS_ALL_ONES(reg) && efx_try_recovery(efx) &&
+	    !efx->eeh_disabled_legacy_irq) {
+		disable_irq_nosync(efx->legacy_irq);
+		efx->eeh_disabled_legacy_irq = true;
+	}
+
 	/* Handle non-event-queue sources */
 	if (queues & (1U << efx->irq_level)) {
 		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);


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

[PATCH net-next 2/9] sfc: Enable RX checksum offload for packets not handled by GRO

[Ben Hutchings]

From: Jon Cooper <jcooper@solarflare.com>

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

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index a7dfe36..b915e09 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -598,6 +598,8 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 
 	/* Set the SKB flags */
 	skb_checksum_none_assert(skb);
+	if (likely(rx_buf->flags & EFX_RX_PKT_CSUMMED))
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (channel->type->receive_skb)
 		if (channel->type->receive_skb(channel, skb))


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

[PATCH net-next 3/9] sfc: Increase size of RX SKB header area

[Ben Hutchings]

From: Jon Cooper <jcooper@solarflare.com>

This allows the SKB to hold the headers without reallocation more often.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index b915e09..6efff3d 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -36,7 +36,7 @@
 #define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
 
 /* Size of buffer allocated for skb header area. */
-#define EFX_SKB_HEADERS  64u
+#define EFX_SKB_HEADERS  128u
 
 /* This is the percentage fill level below which new RX descriptors
  * will be added to the RX descriptor ring.


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

[PATCH net-next 4/9] sfc: Report software timestamping capabilities

[Ben Hutchings]

The kernel can generate software receive timestamps and we should
report those for all ports regardless of hardware capabilities.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/ethtool.c | 16 +++++++++++++++-
 drivers/net/ethernet/sfc/nic.h     |  4 ++--
 drivers/net/ethernet/sfc/ptp.c     | 13 +++++--------
 3 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 6e76817..1fc2145 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1114,6 +1114,20 @@ static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
 	return 0;
 }
 
+int efx_ethtool_get_ts_info(struct net_device *net_dev,
+			    struct ethtool_ts_info *ts_info)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	/* Software capabilities */
+	ts_info->so_timestamping = (SOF_TIMESTAMPING_RX_SOFTWARE |
+				    SOF_TIMESTAMPING_SOFTWARE);
+	ts_info->phc_index = -1;
+
+	efx_ptp_get_ts_info(efx, ts_info);
+	return 0;
+}
+
 static int efx_ethtool_get_module_eeprom(struct net_device *net_dev,
 					 struct ethtool_eeprom *ee,
 					 u8 *data)
@@ -1176,7 +1190,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_indir		= efx_ethtool_get_rxfh_indir,
 	.set_rxfh_indir		= efx_ethtool_set_rxfh_indir,
-	.get_ts_info		= efx_ptp_get_ts_info,
+	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
 };
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 1b00033..d63c299 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -254,8 +254,8 @@ extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
 struct ethtool_ts_info;
 extern void efx_ptp_probe(struct efx_nic *efx);
 extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd);
-extern int efx_ptp_get_ts_info(struct net_device *net_dev,
-			       struct ethtool_ts_info *ts_info);
+extern void efx_ptp_get_ts_info(struct efx_nic *efx,
+				struct ethtool_ts_info *ts_info);
 extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 9a95abf..b495394 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1203,18 +1203,16 @@ static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
 	return 0;
 }
 
-int
-efx_ptp_get_ts_info(struct net_device *net_dev, struct ethtool_ts_info *ts_info)
+void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info)
 {
-	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_ptp_data *ptp = efx->ptp_data;
 
 	if (!ptp)
-		return -EOPNOTSUPP;
+		return;
 
-	ts_info->so_timestamping = (SOF_TIMESTAMPING_TX_HARDWARE |
-				    SOF_TIMESTAMPING_RX_HARDWARE |
-				    SOF_TIMESTAMPING_RAW_HARDWARE);
+	ts_info->so_timestamping |= (SOF_TIMESTAMPING_TX_HARDWARE |
+				     SOF_TIMESTAMPING_RX_HARDWARE |
+				     SOF_TIMESTAMPING_RAW_HARDWARE);
 	ts_info->phc_index = ptp_clock_index(ptp->phc_clock);
 	ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON;
 	ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE |
@@ -1224,7 +1222,6 @@ efx_ptp_get_ts_info(struct net_device *net_dev, struct ethtool_ts_info *ts_info)
 			       1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT |
 			       1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC |
 			       1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ);
-	return 0;
 }
 
 int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)


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

[PATCH net-next 5/9] sfc: Enable accelerated RFS on vlans

[Ben Hutchings]

From: Andy Lutomirski <luto@amacapital.net>

As far as I know, the hardware doesn't support matching on both IP
fields and vlan tag, but it can at least match on the IP fields.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/filter.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
index 2397f0e..b74a60a 100644
--- a/drivers/net/ethernet/sfc/filter.c
+++ b/drivers/net/ethernet/sfc/filter.c
@@ -1185,8 +1185,21 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
 
 	nhoff = skb_network_offset(skb);
 
-	if (skb->protocol != htons(ETH_P_IP))
+	if (skb->protocol == htons(ETH_P_8021Q)) {
+		EFX_BUG_ON_PARANOID(skb_headlen(skb) <
+				    nhoff + sizeof(struct vlan_hdr));
+		if (((const struct vlan_hdr *)skb->data + nhoff)->
+		    h_vlan_encapsulated_proto != htons(ETH_P_IP))
+			return -EPROTONOSUPPORT;
+
+		/* This is IP over 802.1q VLAN.  We can't filter on the
+		 * IP 5-tuple and the vlan together, so just strip the
+		 * vlan header and filter on the IP part.
+		 */
+		nhoff += sizeof(struct vlan_hdr);
+	} else if (skb->protocol != htons(ETH_P_IP)) {
 		return -EPROTONOSUPPORT;
+	}
 
 	/* RFS must validate the IP header length before calling us */
 	EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));


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

[PATCH net-next 6/9] sfc: Define and set RX buffer flag for packets parsed as TCP

[Ben Hutchings]

This will be useful for shortcutting some software packet parsing.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/net_driver.h |  1 +
 drivers/net/ethernet/sfc/nic.c        | 19 ++++++++++++++-----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 2dec48b..f4c7e6b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -243,6 +243,7 @@ struct efx_rx_buffer {
 #define EFX_RX_BUF_LAST_IN_PAGE	0x0001
 #define EFX_RX_PKT_CSUMMED	0x0002
 #define EFX_RX_PKT_DISCARD	0x0004
+#define EFX_RX_PKT_TCP		0x0040
 
 /**
  * struct efx_rx_page_state - Page-based rx buffer state
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 39432d3..f2b864c 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1080,12 +1080,21 @@ efx_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
 	rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
 
 	if (likely(rx_ev_pkt_ok)) {
-		/* If packet is marked as OK and packet type is TCP/IP or
-		 * UDP/IP, then we can rely on the hardware checksum.
+		/* If packet is marked as OK then we can rely on the
+		 * hardware checksum and classification.
 		 */
-		flags = (rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP ||
-			 rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP) ?
-			EFX_RX_PKT_CSUMMED : 0;
+		flags = 0;
+		switch (rx_ev_hdr_type) {
+		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP:
+			flags |= EFX_RX_PKT_TCP;
+			/* fall through */
+		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP:
+			flags |= EFX_RX_PKT_CSUMMED;
+			/* fall through */
+		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
+		case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
+			break;
+		}
 	} else {
 		flags = efx_handle_rx_not_ok(rx_queue, event);
 	}


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

[PATCH net-next 7/9] sfc: Do not pass non-TCP packets into GRO code

[Ben Hutchings]

GRO can handle non-TCP packets and pass them up without coalescing,
but it has to do some extra work to parse the packet which we can
bypass using the hardware parse result.  (This condition yields a
false negative for TCP/IPv6 packets received by Falcon, but its
performance is already poor in that case due to lack of checksum
offload.)

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 6efff3d..5c45118 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -629,7 +629,7 @@ void __efx_rx_packet(struct efx_channel *channel)
 	if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM)))
 		rx_buf->flags &= ~EFX_RX_PKT_CSUMMED;
 
-	if (!channel->type->receive_skb)
+	if ((rx_buf->flags & EFX_RX_PKT_TCP) && !channel->type->receive_skb)
 		efx_rx_packet_gro(channel, rx_buf, channel->rx_pkt_n_frags, eh);
 	else
 		efx_rx_deliver(channel, eh, rx_buf, channel->rx_pkt_n_frags);


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

[PATCH net-next 8/9] sfc: Fix IRQ cleanup in case of a probe failure

[Ben Hutchings]

The lifetime of an irq_cpu_rmap is odd: we have to allocate it before
installing IRQ handlers and free it before removing the IRQ handlers.
As a result of this asymmetry, it was omitted from some failure paths.

On another failure path, we could try to remove IRQ handlers we
had not yet installed.

Move the irq_cpu_rmap allocation and freeing alongside IRQ handler
installation and removal, in efx_nic_{init,fini}_interrupts().
Count the number of IRQ handlers successfully installed and only
remove those on the failure path.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/efx.c | 33 -------------------------------
 drivers/net/ethernet/sfc/nic.c | 45 +++++++++++++++++++++++++++++++++++++-----
 2 files changed, 40 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 787c9eb..e7284a2 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -21,7 +21,6 @@
 #include <linux/ethtool.h>
 #include <linux/topology.h>
 #include <linux/gfp.h>
-#include <linux/cpu_rmap.h>
 #include <linux/aer.h>
 #include <linux/interrupt.h>
 #include "net_driver.h"
@@ -1284,29 +1283,6 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 	return count;
 }
 
-static int
-efx_init_rx_cpu_rmap(struct efx_nic *efx, struct msix_entry *xentries)
-{
-#ifdef CONFIG_RFS_ACCEL
-	unsigned int i;
-	int rc;
-
-	efx->net_dev->rx_cpu_rmap = alloc_irq_cpu_rmap(efx->n_rx_channels);
-	if (!efx->net_dev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < efx->n_rx_channels; i++) {
-		rc = irq_cpu_rmap_add(efx->net_dev->rx_cpu_rmap,
-				      xentries[i].vector);
-		if (rc) {
-			free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
-			efx->net_dev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif
-	return 0;
-}
-
 /* Probe the number and type of interrupts we are able to obtain, and
  * the resulting numbers of channels and RX queues.
  */
@@ -1360,11 +1336,6 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 				efx->n_tx_channels = n_channels;
 				efx->n_rx_channels = n_channels;
 			}
-			rc = efx_init_rx_cpu_rmap(efx, xentries);
-			if (rc) {
-				pci_disable_msix(efx->pci_dev);
-				return rc;
-			}
 			for (i = 0; i < efx->n_channels; i++)
 				efx_get_channel(efx, i)->irq =
 					xentries[i].vector;
@@ -2608,10 +2579,6 @@ static void efx_pci_remove_main(struct efx_nic *efx)
 	BUG_ON(efx->state == STATE_READY);
 	cancel_work_sync(&efx->reset_work);
 
-#ifdef CONFIG_RFS_ACCEL
-	free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
-	efx->net_dev->rx_cpu_rmap = NULL;
-#endif
 	efx_stop_interrupts(efx, false);
 	efx_nic_fini_interrupt(efx);
 	efx_fini_port(efx);
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index f2b864c..56ed3bc 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/cpu_rmap.h>
 #include "net_driver.h"
 #include "bitfield.h"
 #include "efx.h"
@@ -1706,6 +1707,7 @@ void efx_nic_push_rx_indir_table(struct efx_nic *efx)
 int efx_nic_init_interrupt(struct efx_nic *efx)
 {
 	struct efx_channel *channel;
+	unsigned int n_irqs;
 	int rc;
 
 	if (!EFX_INT_MODE_USE_MSI(efx)) {
@@ -1726,7 +1728,19 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
 		return 0;
 	}
 
+#ifdef CONFIG_RFS_ACCEL
+	if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
+		efx->net_dev->rx_cpu_rmap =
+			alloc_irq_cpu_rmap(efx->n_rx_channels);
+		if (!efx->net_dev->rx_cpu_rmap) {
+			rc = -ENOMEM;
+			goto fail1;
+		}
+	}
+#endif
+
 	/* Hook MSI or MSI-X interrupt */
+	n_irqs = 0;
 	efx_for_each_channel(channel, efx) {
 		rc = request_irq(channel->irq, efx_msi_interrupt,
 				 IRQF_PROBE_SHARED, /* Not shared */
@@ -1737,13 +1751,31 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
 				  "failed to hook IRQ %d\n", channel->irq);
 			goto fail2;
 		}
+		++n_irqs;
+
+#ifdef CONFIG_RFS_ACCEL
+		if (efx->interrupt_mode == EFX_INT_MODE_MSIX &&
+		    channel->channel < efx->n_rx_channels) {
+			rc = irq_cpu_rmap_add(efx->net_dev->rx_cpu_rmap,
+					      channel->irq);
+			if (rc)
+				goto fail2;
+		}
+#endif
 	}
 
 	return 0;
 
  fail2:
-	efx_for_each_channel(channel, efx)
+#ifdef CONFIG_RFS_ACCEL
+	free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
+	efx->net_dev->rx_cpu_rmap = NULL;
+#endif
+	efx_for_each_channel(channel, efx) {
+		if (n_irqs-- == 0)
+			break;
 		free_irq(channel->irq, &efx->channel[channel->channel]);
+	}
  fail1:
 	return rc;
 }
@@ -1753,11 +1785,14 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 	struct efx_channel *channel;
 	efx_oword_t reg;
 
+#ifdef CONFIG_RFS_ACCEL
+	free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
+	efx->net_dev->rx_cpu_rmap = NULL;
+#endif
+
 	/* Disable MSI/MSI-X interrupts */
-	efx_for_each_channel(channel, efx) {
-		if (channel->irq)
-			free_irq(channel->irq, &efx->channel[channel->channel]);
-	}
+	efx_for_each_channel(channel, efx)
+		free_irq(channel->irq, &efx->channel[channel->channel]);
 
 	/* ACK legacy interrupt */
 	if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)


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

[PATCH net-next 9/9] sfc: Improve test for IOMMU in use

[Ben Hutchings]

The device::iommu_group field may be set even if no IOMMU is in use.
iommu_present() is still a better indicator, although it doesn't tell
us whether *our* device is affected.

Reported-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 5c45118..65646cd 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -677,7 +677,7 @@ static void efx_init_rx_recycle_ring(struct efx_nic *efx,
 #ifdef CONFIG_PPC64
 	bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
 #else
-	if (efx->pci_dev->dev.iommu_group)
+	if (iommu_present(&pci_bus_type))
 		bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
 	else
 		bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU;

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

Re: Pull request: sfc-next 2013-06-24

[David Miller]

From: Ben Hutchings <bhutchings@solarflare.com>
Date: Mon, 24 Jun 2013 21:11:48 +0100

> The following changes since commit 37173488400704f1a05656616cd12baa9e03173b:
> 
>   bnx2x: Fix compilation with no IOV support (2013-06-24 01:47:47 -0700)
> 
> are available in the git repository at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next.git for-davem
> 
> for you to fetch changes up to 636d73da27e83ce4882f8823f79063bb37980961:
> 
>   sfc: Improve test for IOMMU in use (2013-06-24 20:02:53 +0100)
> 
> 1. Make EEH recovery work when using legacy interrupts, from Alexandre
>    Rames.
> 
> 2. Enable accelerated RFS for VLAN-tagged flows, from Andy Lutomirski.
> 
> 3. Improve performance for non-TCP (and particularly UDP) traffic, which
>    regressed in 3.10 when we switched to always allocating paged RX
>    buffers.  Partly by Jon Cooper.
> 
> 4. Some minor bug fixes to IOMMU detection, timestamping capabilities,
>    and IRQ cleanup on the probe failure path.
> 
> I've dropped the RX skb cache, which improved some benchmarks but
> perhaps needs some reworking to be more generally useful.

Pulled, thanks Ben.

Re: [PATCH net-next 3/9] sfc: Increase size of RX SKB header area

[Eric Dumazet]

On Mon, 2013-06-24 at 21:13 +0100, Ben Hutchings wrote:
> From: Jon Cooper <jcooper@solarflare.com>
> 
> This allows the SKB to hold the headers without reallocation more often.
> 
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
> ---
>  drivers/net/ethernet/sfc/rx.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
> index b915e09..6efff3d 100644
> --- a/drivers/net/ethernet/sfc/rx.c
> +++ b/drivers/net/ethernet/sfc/rx.c
> @@ -36,7 +36,7 @@
>  #define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
>  
>  /* Size of buffer allocated for skb header area. */
> -#define EFX_SKB_HEADERS  64u
> +#define EFX_SKB_HEADERS  128u
>  
>  /* This is the percentage fill level below which new RX descriptors
>   * will be added to the RX descriptor ring.
> 

This patch brings performance decrease for tunnels, because it pulls
into skb->head 128 bytes worth of data.

This includes TCP payload, so GRO or TCP coalescing code is less
effective. Each MSS spans 2 memory areas (small part on skb->head,
remaining on the fragment) : GRO packets have only 8 MSS worth of data,
instead of 16.

The fix would be to allocate 128 bytes in skb->head to prevent future
reallocations of skb->head, but pull 64 bytes only.

Re: [PATCH net-next 3/9] sfc: Increase size of RX SKB header area

[Ben Hutchings]

On Tue, 2013-07-16 at 10:33 -0700, Eric Dumazet wrote:
> On Mon, 2013-06-24 at 21:13 +0100, Ben Hutchings wrote:
> > From: Jon Cooper <jcooper@solarflare.com>
> > 
> > This allows the SKB to hold the headers without reallocation more often.
> > 
> > Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
> > ---
> >  drivers/net/ethernet/sfc/rx.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
> > index b915e09..6efff3d 100644
> > --- a/drivers/net/ethernet/sfc/rx.c
> > +++ b/drivers/net/ethernet/sfc/rx.c
> > @@ -36,7 +36,7 @@
> >  #define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
> >  
> >  /* Size of buffer allocated for skb header area. */
> > -#define EFX_SKB_HEADERS  64u
> > +#define EFX_SKB_HEADERS  128u
> >  
> >  /* This is the percentage fill level below which new RX descriptors
> >   * will be added to the RX descriptor ring.
> > 
> 
> This patch brings performance decrease for tunnels, because it pulls
> into skb->head 128 bytes worth of data.
>
> This includes TCP payload, so GRO or TCP coalescing code is less
> effective. Each MSS spans 2 memory areas (small part on skb->head,
> remaining on the fragment) : GRO packets have only 8 MSS worth of data,
> instead of 16.
> 
> The fix would be to allocate 128 bytes in skb->head to prevent future
> reallocations of skb->head, but pull 64 bytes only.

Perhaps, yes.  I also thought of using some of the other parser status
from RX completions to estimate the length of headers.

Ben.

-- 
Ben Hutchings, Staff Engineer, Solarflare
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 net-next 3/9] sfc: Increase size of RX SKB header area

[Eric Dumazet]

On Tue, 2013-07-16 at 18:53 +0100, Ben Hutchings wrote:

> Perhaps, yes.  I also thought of using some of the other parser status
> from RX completions to estimate the length of headers.

That would be ideal indeed, I can provide a patch.

Re: [PATCH net-next 3/9] sfc: Increase size of RX SKB header area

[Ben Hutchings]

On Tue, 2013-07-16 at 13:22 -0700, Eric Dumazet wrote:
> On Tue, 2013-07-16 at 18:53 +0100, Ben Hutchings wrote:
> 
> > Perhaps, yes.  I also thought of using some of the other parser status
> > from RX completions to estimate the length of headers.
> 
> That would be ideal indeed, I can provide a patch.

This is what I was intending to do, but it's untested.  It doesn't allow
for a VLAN tag, but that can be done by reading the RX_EV_PKT_TYPE field
in completions.

Ben.

Subject: WIP: sfc: Pull less data into header area in efx_rx_mk_skb()

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
 drivers/net/ethernet/sfc/net_driver.h |  2 ++
 drivers/net/ethernet/sfc/nic.c        |  3 +++
 drivers/net/ethernet/sfc/rx.c         | 34 ++++++++++++++++++++++++----------
 3 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index f4c7e6b..cbcf709 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -243,6 +243,8 @@ struct efx_rx_buffer {
 #define EFX_RX_BUF_LAST_IN_PAGE	0x0001
 #define EFX_RX_PKT_CSUMMED	0x0002
 #define EFX_RX_PKT_DISCARD	0x0004
+#define EFX_RX_PKT_IPV4		0x0010
+#define EFX_RX_PKT_IPV6		0x0020
 #define EFX_RX_PKT_TCP		0x0040
 
 /**
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 56ed3bc..b6ae31b 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1093,6 +1093,9 @@ efx_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
 			flags |= EFX_RX_PKT_CSUMMED;
 			/* fall through */
 		case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
+			flags |= EFX_QWORD_FIELD(*event, FSF_CZ_RX_EV_IPV6_PKT)
+				? EFX_RX_PKT_IPV6 : EFX_RX_PKT_IPV4;
+			break;
 		case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
 			break;
 		}
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 65646cd..80bb7a5 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -451,25 +451,27 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
 static struct sk_buff *efx_rx_mk_skb(struct efx_channel *channel,
 				     struct efx_rx_buffer *rx_buf,
 				     unsigned int n_frags,
-				     u8 *eh, int hdr_len)
+				     u8 *eh, int min_hdr_len,
+				     int max_hdr_len)
 {
 	struct efx_nic *efx = channel->efx;
 	struct sk_buff *skb;
 
 	/* Allocate an SKB to store the headers */
-	skb = netdev_alloc_skb(efx->net_dev, hdr_len + EFX_PAGE_SKB_ALIGN);
+	skb = netdev_alloc_skb(efx->net_dev, max_hdr_len + EFX_PAGE_SKB_ALIGN);
 	if (unlikely(skb == NULL))
 		return NULL;
 
-	EFX_BUG_ON_PARANOID(rx_buf->len < hdr_len);
+	EFX_BUG_ON_PARANOID(rx_buf->len < min_hdr_len);
+	EFX_BUG_ON_PARANOID(max_hdr_len < min_hdr_len);
 
 	skb_reserve(skb, EFX_PAGE_SKB_ALIGN);
-	memcpy(__skb_put(skb, hdr_len), eh, hdr_len);
+	memcpy(__skb_put(skb, min_hdr_len), eh, min_hdr_len);
 
 	/* Append the remaining page(s) onto the frag list */
-	if (rx_buf->len > hdr_len) {
-		rx_buf->page_offset += hdr_len;
-		rx_buf->len -= hdr_len;
+	if (rx_buf->len > min_hdr_len) {
+		rx_buf->page_offset += min_hdr_len;
+		rx_buf->len -= min_hdr_len;
 
 		for (;;) {
 			skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
@@ -587,9 +589,21 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 			   unsigned int n_frags)
 {
 	struct sk_buff *skb;
-	u16 hdr_len = min_t(u16, rx_buf->len, EFX_SKB_HEADERS);
-
-	skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len);
+	int min_hdr_len = ETH_HLEN;
+ 
+	/* If the RX parser found an IPv4 or IPv6 header, assume we'll
+	 * need to pull that and at least another 8 bytes of transport
+	 * header.  TODO: should handle VLAN tag too
+	 */
+	if (rx_buf->flags & EFX_RX_PKT_IPV4)
+		min_hdr_len += sizeof(struct iphdr) + 8;
+	else if (rx_buf->flags & EFX_RX_PKT_IPV6)
+		min_hdr_len += sizeof(struct ipv6hdr) + 8;
+	if (unlikely(min_hdr_len) > rx_buf->len)
+		min_hdr_len = rx_buf->len;
+
+	skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh,
+			    min_hdr_len, EFX_SKB_HEADERS);
 	if (unlikely(skb == NULL)) {
 		efx_free_rx_buffer(rx_buf);
 		return;

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