* Re: strange routing issue--packets stop getting forwarded for a live connection
From: Julian Anastasov @ 2011-08-21 6:35 UTC (permalink / raw)
To: Corey Hickey; +Cc: Linux Netdev List
In-Reply-To: <4E506A46.6060407@fatooh.org>
Hello,
On Sat, 20 Aug 2011, Corey Hickey wrote:
> Hi,
>
> Please forgive me for asking a user question on a dev list; does the
> linux-net list no longer exist? Majordomo wouldn't subscribe me and I
> see no recent history in the archives. If there's a better place for
> this question, please tell me. Anyway:
>
> I have a strange issue where, reliably, certain conditions cause my
> Linux router to stop forwarding packets for a connection.
>
> ----------------------------------------------------------------------
>
> This is my setup:
>
> client --> linux router --> vpn --> work desktop
> 198.18.0.3 198.18.0.1 (eth0) 192.168.10.88
> 192.168.6.230 (tun0)
>
> All hosts are running Debian Sid with the stock Debian 3.0.0-1-amd64
> kernel. tun0 is set up by openconnect (open-source client for cisco
> anyconnnect), which has been historically reliable for me.
>
> I noticed this problem happening when I replaced the router with a new
> host. The old host was 32-bit, running Linux 2.6.38, and configured
> identically (I think) with respect to routing and iptables. I didn't
> have a problem then.
>
> ----------------------------------------------------------------------
>
> I have seen this problem happen with http, sometimes, but the easiest
> way to reproduce the issue every time is to use SSH with X11 forwarding
> (I have no idea why). I can SSH, through my router and VPN connection,
> to my desktop at work. I can log in, poke around, do whatever; as soon
> as I run some particular X11 programs, the connection hangs. xlogo and
> xeyes are fine, but rxvt and jconsole are not.
>
> So, my baseline test is to run rxvt directly. This command always hangs:
>
> $ ssh -X chickey@192.168.10.88 rxvt
>
> I have run simultaneous tcpdumps on the router: one on eth0 and the
> other on tun0. I see the tcp connection and ssh sessions get set up,
> then many encrypted packets go back and forth. At a certain, reliably
> reproducible point, a 1368 byte packet comes in on eth0 and does not
> leave tun0; the retransmissions do not get forwarded either.
>
> I have not been able to figure out the cause of this. Here's what I have
> investigated:
>
> 1. Number of packets on the connection; doesn't seem to matter, because
> I can use SSH for other purposes just fine.
>
> 2. Transmission rate; doesn't seem to matter, because I can do
> $ ssh -X chickey@192.168.10.88 cat /dev/zero > /dev/null
>
> 3. MTU size; 1500 on eth0 and 1406 on tun0. Bigger packets have been
> transferred fine.
Lower MTU, it can be PMTUD problem. At 04:50:24.112658
I see 7801:9169 is 1420 bytes and no ICMP FRAG NEEDED is generated.
May be these two regressions explain it:
http://marc.info/?l=linux-netdev&m=131342172722536&w=2
There are 2 fixes you can try or more recent kernel
tree, for example 3.1-rc2 has the fixes.
Regards
--
Julian Anastasov <ja@ssi.bg>
^ permalink raw reply
* [net-next 00/10][pull request] Intel Wired LAN Driver Update
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo
The following series contains updates to ixgbe.
The following are changes since commit ca1ba7caa68520864e4b9227e67f3bbc6fed373b:
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next
and are available in the git repository at:
master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next master
Alexander Duyck (10):
ixgbe: Simplify transmit cleanup path
ixgbe: convert rings from q_vector bit indexed array to linked list
ixgbe: Drop the TX work limit and instead just leave it to budget
ixgbe: consolidate all MSI-X ring interrupts and poll routines into
one
ixgbe: cleanup allocation and freeing of IRQ affinity hint
ixgbe: Use ring->dev instead of adapter->pdev->dev when updating DCA
ixgbe: commonize ixgbe_map_rings_to_vectors to work for all interrupt
types
ixgbe: Drop unnecessary adapter->hw dereference in loopback test
setup
ixgbe: combine PCI_VDEVICE and board declaration to same line
ixgbe: Update TXDCTL configuration to correctly handle WTHRESH
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 11 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 25 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 738 +++++++---------------
3 files changed, 239 insertions(+), 535 deletions(-)
--
1.7.6
^ permalink raw reply
* [net-next 01/10] ixgbe: Simplify transmit cleanup path
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch helps to simplify the work being done by the transmit path by
removing the unnecessary compares between count and the work limit. Instead
we can simplify this by just adding a budget value that will act as a count
down from the work limit value.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 10 +++++-----
1 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e8aad76..e5a4eb6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -804,13 +804,13 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
+ u16 budget = q_vector->tx.work_limit;
u16 i = tx_ring->next_to_clean;
- u16 count;
tx_buffer = &tx_ring->tx_buffer_info[i];
tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i);
- for (count = 0; count < q_vector->tx.work_limit; count++) {
+ for (; budget; budget--) {
union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch;
/* if next_to_watch is not set then there is no work pending */
@@ -891,11 +891,11 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
ixgbe_tx_timeout_reset(adapter);
/* the adapter is about to reset, no point in enabling stuff */
- return true;
+ return budget;
}
#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
- if (unlikely(count && netif_carrier_ok(tx_ring->netdev) &&
+ if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
(ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
@@ -908,7 +908,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
}
}
- return count < q_vector->tx.work_limit;
+ return budget;
}
#ifdef CONFIG_IXGBE_DCA
--
1.7.6
^ permalink raw reply related
* [net-next 02/10] ixgbe: convert rings from q_vector bit indexed array to linked list
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change converts the current bit array into a linked list so that the
q_vectors can simply go through ring by ring and locate each ring needing
to be cleaned.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 7 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 192 ++++++++-----------------
2 files changed, 60 insertions(+), 139 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 378ce46..dc3b12e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -209,6 +209,7 @@ enum ixbge_ring_state_t {
#define clear_ring_rsc_enabled(ring) \
clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
struct ixgbe_ring {
+ struct ixgbe_ring *next; /* pointer to next ring in q_vector */
void *desc; /* descriptor ring memory */
struct device *dev; /* device for DMA mapping */
struct net_device *netdev; /* netdev ring belongs to */
@@ -277,11 +278,7 @@ struct ixgbe_ring_feature {
} ____cacheline_internodealigned_in_smp;
struct ixgbe_ring_container {
-#if MAX_RX_QUEUES > MAX_TX_QUEUES
- DECLARE_BITMAP(idx, MAX_RX_QUEUES);
-#else
- DECLARE_BITMAP(idx, MAX_TX_QUEUES);
-#endif
+ struct ixgbe_ring *ring; /* pointer to linked list of rings */
unsigned int total_bytes; /* total bytes processed this int */
unsigned int total_packets; /* total packets processed this int */
u16 work_limit; /* total work allowed per interrupt */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e5a4eb6..bb54d3d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -974,26 +974,17 @@ static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
+ struct ixgbe_ring *ring;
int cpu = get_cpu();
- long r_idx;
- int i;
if (q_vector->cpu == cpu)
goto out_no_update;
- r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
- for (i = 0; i < q_vector->tx.count; i++) {
- ixgbe_update_tx_dca(adapter, adapter->tx_ring[r_idx], cpu);
- r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
- r_idx + 1);
- }
+ for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
+ ixgbe_update_tx_dca(adapter, ring, cpu);
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- for (i = 0; i < q_vector->rx.count; i++) {
- ixgbe_update_rx_dca(adapter, adapter->rx_ring[r_idx], cpu);
- r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
- r_idx + 1);
- }
+ for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next)
+ ixgbe_update_rx_dca(adapter, ring, cpu);
q_vector->cpu = cpu;
out_no_update:
@@ -1546,7 +1537,7 @@ static int ixgbe_clean_rxonly(struct napi_struct *, int);
static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
{
struct ixgbe_q_vector *q_vector;
- int i, q_vectors, v_idx, r_idx;
+ int q_vectors, v_idx;
u32 mask;
q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
@@ -1556,33 +1547,19 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
* corresponding register.
*/
for (v_idx = 0; v_idx < q_vectors; v_idx++) {
+ struct ixgbe_ring *ring;
q_vector = adapter->q_vector[v_idx];
- /* XXX for_each_set_bit(...) */
- r_idx = find_first_bit(q_vector->rx.idx,
- adapter->num_rx_queues);
-
- for (i = 0; i < q_vector->rx.count; i++) {
- u8 reg_idx = adapter->rx_ring[r_idx]->reg_idx;
- ixgbe_set_ivar(adapter, 0, reg_idx, v_idx);
- r_idx = find_next_bit(q_vector->rx.idx,
- adapter->num_rx_queues,
- r_idx + 1);
- }
- r_idx = find_first_bit(q_vector->tx.idx,
- adapter->num_tx_queues);
-
- for (i = 0; i < q_vector->tx.count; i++) {
- u8 reg_idx = adapter->tx_ring[r_idx]->reg_idx;
- ixgbe_set_ivar(adapter, 1, reg_idx, v_idx);
- r_idx = find_next_bit(q_vector->tx.idx,
- adapter->num_tx_queues,
- r_idx + 1);
- }
- if (q_vector->tx.count && !q_vector->rx.count)
+ for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next)
+ ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx);
+
+ for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
+ ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx);
+
+ if (q_vector->tx.ring && !q_vector->rx.ring)
/* tx only */
q_vector->eitr = adapter->tx_eitr_param;
- else if (q_vector->rx.count)
+ else if (q_vector->rx.ring)
/* rx or mixed */
q_vector->eitr = adapter->rx_eitr_param;
@@ -2006,20 +1983,10 @@ static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
- struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *tx_ring;
- int i, r_idx;
if (!q_vector->tx.count)
return IRQ_HANDLED;
- r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
- for (i = 0; i < q_vector->tx.count; i++) {
- tx_ring = adapter->tx_ring[r_idx];
- r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
- r_idx + 1);
- }
-
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
@@ -2034,22 +2001,6 @@ static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data)
static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
- struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *rx_ring;
- int r_idx;
- int i;
-
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_dca(q_vector);
-#endif
-
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- for (i = 0; i < q_vector->rx.count; i++) {
- rx_ring = adapter->rx_ring[r_idx];
- r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
- r_idx + 1);
- }
if (!q_vector->rx.count)
return IRQ_HANDLED;
@@ -2063,28 +2014,10 @@ static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
static irqreturn_t ixgbe_msix_clean_many(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
- struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *ring;
- int r_idx;
- int i;
if (!q_vector->tx.count && !q_vector->rx.count)
return IRQ_HANDLED;
- r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
- for (i = 0; i < q_vector->tx.count; i++) {
- ring = adapter->tx_ring[r_idx];
- r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
- r_idx + 1);
- }
-
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- for (i = 0; i < q_vector->rx.count; i++) {
- ring = adapter->rx_ring[r_idx];
- r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
- r_idx + 1);
- }
-
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
@@ -2104,19 +2037,14 @@ static int ixgbe_clean_rxonly(struct napi_struct *napi, int budget)
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *rx_ring = NULL;
int work_done = 0;
- long r_idx;
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_dca(q_vector);
#endif
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- rx_ring = adapter->rx_ring[r_idx];
-
- ixgbe_clean_rx_irq(q_vector, rx_ring, &work_done, budget);
+ ixgbe_clean_rx_irq(q_vector, q_vector->rx.ring, &work_done, budget);
/* If all Rx work done, exit the polling mode */
if (work_done < budget) {
@@ -2144,38 +2072,29 @@ static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *ring = NULL;
- int work_done = 0, i;
- long r_idx;
- bool tx_clean_complete = true;
+ struct ixgbe_ring *ring;
+ int work_done = 0;
+ bool clean_complete = true;
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_dca(q_vector);
#endif
- r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
- for (i = 0; i < q_vector->tx.count; i++) {
- ring = adapter->tx_ring[r_idx];
- tx_clean_complete &= ixgbe_clean_tx_irq(q_vector, ring);
- r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
- r_idx + 1);
- }
+ for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
+ clean_complete &= ixgbe_clean_tx_irq(q_vector, ring);
/* attempt to distribute budget to each queue fairly, but don't allow
* the budget to go below 1 because we'll exit polling */
budget /= (q_vector->rx.count ?: 1);
budget = max(budget, 1);
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- for (i = 0; i < q_vector->rx.count; i++) {
- ring = adapter->rx_ring[r_idx];
+
+ for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next)
ixgbe_clean_rx_irq(q_vector, ring, &work_done, budget);
- r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
- r_idx + 1);
- }
- r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
- ring = adapter->rx_ring[r_idx];
+ if (!clean_complete)
+ work_done = budget;
+
/* If all Rx work done, exit the polling mode */
if (work_done < budget) {
napi_complete(napi);
@@ -2203,32 +2122,23 @@ static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *tx_ring = NULL;
- int work_done = 0;
- long r_idx;
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_dca(q_vector);
#endif
- r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
- tx_ring = adapter->tx_ring[r_idx];
-
- if (!ixgbe_clean_tx_irq(q_vector, tx_ring))
- work_done = budget;
+ if (!ixgbe_clean_tx_irq(q_vector, q_vector->tx.ring))
+ return budget;
/* If all Tx work done, exit the polling mode */
- if (work_done < budget) {
- napi_complete(napi);
- if (adapter->tx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter,
- ((u64)1 << q_vector->v_idx));
- }
+ napi_complete(napi);
+ if (adapter->tx_itr_setting & 1)
+ ixgbe_set_itr(q_vector);
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));
- return work_done;
+ return 0;
}
static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx,
@@ -2237,9 +2147,10 @@ static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx,
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
struct ixgbe_ring *rx_ring = a->rx_ring[r_idx];
- set_bit(r_idx, q_vector->rx.idx);
- q_vector->rx.count++;
rx_ring->q_vector = q_vector;
+ rx_ring->next = q_vector->rx.ring;
+ q_vector->rx.ring = rx_ring;
+ q_vector->rx.count++;
}
static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
@@ -2248,9 +2159,10 @@ static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
struct ixgbe_ring *tx_ring = a->tx_ring[t_idx];
- set_bit(t_idx, q_vector->tx.idx);
- q_vector->tx.count++;
tx_ring->q_vector = q_vector;
+ tx_ring->next = q_vector->tx.ring;
+ q_vector->tx.ring = tx_ring;
+ q_vector->tx.count++;
q_vector->tx.work_limit = a->tx_work_limit;
}
@@ -2508,14 +2420,26 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
static inline void ixgbe_reset_q_vectors(struct ixgbe_adapter *adapter)
{
- int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ int i;
+
+ /* legacy and MSI only use one vector */
+ if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
+ q_vectors = 1;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ adapter->rx_ring[i]->q_vector = NULL;
+ adapter->rx_ring[i]->next = NULL;
+ }
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ adapter->tx_ring[i]->q_vector = NULL;
+ adapter->tx_ring[i]->next = NULL;
+ }
for (i = 0; i < q_vectors; i++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[i];
- bitmap_zero(q_vector->rx.idx, MAX_RX_QUEUES);
- bitmap_zero(q_vector->tx.idx, MAX_TX_QUEUES);
- q_vector->rx.count = 0;
- q_vector->tx.count = 0;
+ memset(&q_vector->rx, 0, sizeof(struct ixgbe_ring_container));
+ memset(&q_vector->tx, 0, sizeof(struct ixgbe_ring_container));
}
}
@@ -5923,7 +5847,7 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
/* get one bit for every active tx/rx interrupt vector */
for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) {
struct ixgbe_q_vector *qv = adapter->q_vector[i];
- if (qv->rx.count || qv->tx.count)
+ if (qv->rx.ring || qv->tx.ring)
eics |= ((u64)1 << i);
}
}
--
1.7.6
^ permalink raw reply related
* [net-next 03/10] ixgbe: Drop the TX work limit and instead just leave it to budget
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change makes it so that the TX work limit is now obsolete. Instead of
using it we can instead rely on the NAPI budget for the number of packets
we should clean per interrupt. The advantage to this approach is that it
results in a much more balanced work flow since the same number of RX and
TX packets should be cleaned per interrupts.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 4 ----
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 7 -------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 16 +++++++---------
3 files changed, 7 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index dc3b12e..b85312f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -281,7 +281,6 @@ struct ixgbe_ring_container {
struct ixgbe_ring *ring; /* pointer to linked list of rings */
unsigned int total_bytes; /* total bytes processed this int */
unsigned int total_packets; /* total packets processed this int */
- u16 work_limit; /* total work allowed per interrupt */
u8 count; /* total number of rings in vector */
u8 itr; /* current ITR setting for ring */
};
@@ -416,9 +415,6 @@ struct ixgbe_adapter {
u16 eitr_low;
u16 eitr_high;
- /* Work limits */
- u16 tx_work_limit;
-
/* TX */
struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp;
int num_tx_queues;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 82d4244..16835cc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2005,8 +2005,6 @@ static int ixgbe_get_coalesce(struct net_device *netdev,
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- ec->tx_max_coalesced_frames_irq = adapter->tx_work_limit;
-
/* only valid if in constant ITR mode */
switch (adapter->rx_itr_setting) {
case 0:
@@ -2093,9 +2091,6 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
&& ec->tx_coalesce_usecs)
return -EINVAL;
- if (ec->tx_max_coalesced_frames_irq)
- adapter->tx_work_limit = ec->tx_max_coalesced_frames_irq;
-
if (ec->rx_coalesce_usecs > 1) {
/* check the limits */
if ((1000000/ec->rx_coalesce_usecs > IXGBE_MAX_INT_RATE) ||
@@ -2169,14 +2164,12 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
else
/* rx only or mixed */
q_vector->eitr = adapter->rx_eitr_param;
- q_vector->tx.work_limit = adapter->tx_work_limit;
ixgbe_write_eitr(q_vector);
}
/* Legacy Interrupt Mode */
} else {
q_vector = adapter->q_vector[0];
q_vector->eitr = adapter->rx_eitr_param;
- q_vector->tx.work_limit = adapter->tx_work_limit;
ixgbe_write_eitr(q_vector);
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bb54d3d..2450279 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -796,15 +796,16 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
* ixgbe_clean_tx_irq - Reclaim resources after transmit completes
* @q_vector: structure containing interrupt and ring information
* @tx_ring: tx ring to clean
+ * @budget: amount of work driver is allowed to do this pass, in packets
**/
static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
- struct ixgbe_ring *tx_ring)
+ struct ixgbe_ring *tx_ring,
+ int budget)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_tx_buffer *tx_buffer;
union ixgbe_adv_tx_desc *tx_desc;
unsigned int total_bytes = 0, total_packets = 0;
- u16 budget = q_vector->tx.work_limit;
u16 i = tx_ring->next_to_clean;
tx_buffer = &tx_ring->tx_buffer_info[i];
@@ -2082,7 +2083,7 @@ static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
#endif
for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
- clean_complete &= ixgbe_clean_tx_irq(q_vector, ring);
+ clean_complete &= ixgbe_clean_tx_irq(q_vector, ring, budget);
/* attempt to distribute budget to each queue fairly, but don't allow
* the budget to go below 1 because we'll exit polling */
@@ -2128,7 +2129,7 @@ static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
ixgbe_update_dca(q_vector);
#endif
- if (!ixgbe_clean_tx_irq(q_vector, q_vector->tx.ring))
+ if (!ixgbe_clean_tx_irq(q_vector, q_vector->tx.ring, budget))
return budget;
/* If all Tx work done, exit the polling mode */
@@ -2163,7 +2164,6 @@ static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
tx_ring->next = q_vector->tx.ring;
q_vector->tx.ring = tx_ring;
q_vector->tx.count++;
- q_vector->tx.work_limit = a->tx_work_limit;
}
/**
@@ -4155,7 +4155,8 @@ static int ixgbe_poll(struct napi_struct *napi, int budget)
ixgbe_update_dca(q_vector);
#endif
- tx_clean_complete = ixgbe_clean_tx_irq(q_vector, adapter->tx_ring[0]);
+ tx_clean_complete = ixgbe_clean_tx_irq(q_vector, adapter->tx_ring[0],
+ budget);
ixgbe_clean_rx_irq(q_vector, adapter->rx_ring[0], &work_done, budget);
if (!tx_clean_complete)
@@ -5090,9 +5091,6 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->tx_ring_count = IXGBE_DEFAULT_TXD;
adapter->rx_ring_count = IXGBE_DEFAULT_RXD;
- /* set default work limits */
- adapter->tx_work_limit = adapter->tx_ring_count;
-
/* initialize eeprom parameters */
if (ixgbe_init_eeprom_params_generic(hw)) {
e_dev_err("EEPROM initialization failed\n");
--
1.7.6
^ permalink raw reply related
* [net-next 05/10] ixgbe: cleanup allocation and freeing of IRQ affinity hint
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
The allocation and freeing of the IRQ affinity hint needs some updates
since there are a number of spots where we run into possible issues with
the hint not being correctly updated.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 76 ++++++++++++-------------
1 files changed, 36 insertions(+), 40 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 03432dc..7d745e2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1566,20 +1566,6 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
q_vector->eitr = adapter->rx_eitr_param;
ixgbe_write_eitr(q_vector);
- /* If ATR is enabled, set interrupt affinity */
- if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
- /*
- * Allocate the affinity_hint cpumask, assign the mask
- * for this vector, and set our affinity_hint for
- * this irq.
- */
- if (!alloc_cpumask_var(&q_vector->affinity_mask,
- GFP_KERNEL))
- return;
- cpumask_set_cpu(v_idx, q_vector->affinity_mask);
- irq_set_affinity_hint(adapter->msix_entries[v_idx].vector,
- q_vector->affinity_mask);
- }
}
switch (adapter->hw.mac.type) {
@@ -2093,18 +2079,17 @@ out:
static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
- int i, vector, q_vectors, err;
+ int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ int vector, err;
int ri = 0, ti = 0;
- /* Decrement for Other and TCP Timer vectors */
- q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
-
err = ixgbe_map_rings_to_vectors(adapter);
if (err)
return err;
for (vector = 0; vector < q_vectors; vector++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
+ struct msix_entry *entry = &adapter->msix_entries[vector];
if (q_vector->tx.ring && q_vector->rx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
@@ -2120,14 +2105,19 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
/* skip this unused q_vector */
continue;
}
- err = request_irq(adapter->msix_entries[vector].vector,
- &ixgbe_msix_clean_rings, 0, q_vector->name,
- q_vector);
+ err = request_irq(entry->vector, &ixgbe_msix_clean_rings, 0,
+ q_vector->name, q_vector);
if (err) {
e_err(probe, "request_irq failed for MSIX interrupt "
"Error: %d\n", err);
goto free_queue_irqs;
}
+ /* If Flow Director is enabled, set interrupt affinity */
+ if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
+ /* assign the mask for this irq */
+ irq_set_affinity_hint(entry->vector,
+ q_vector->affinity_mask);
+ }
}
sprintf(adapter->lsc_int_name, "%s:lsc", netdev->name);
@@ -2141,9 +2131,13 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
return 0;
free_queue_irqs:
- for (i = vector - 1; i >= 0; i--)
- free_irq(adapter->msix_entries[--vector].vector,
- adapter->q_vector[i]);
+ while (vector) {
+ vector--;
+ irq_set_affinity_hint(adapter->msix_entries[vector].vector,
+ NULL);
+ free_irq(adapter->msix_entries[vector].vector,
+ adapter->q_vector[vector]);
+ }
adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
pci_disable_msix(adapter->pdev);
kfree(adapter->msix_entries);
@@ -2333,14 +2327,19 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
!adapter->q_vector[i]->tx.ring)
continue;
+ /* clear the affinity_mask in the IRQ descriptor */
+ irq_set_affinity_hint(adapter->msix_entries[i].vector,
+ NULL);
+
free_irq(adapter->msix_entries[i].vector,
adapter->q_vector[i]);
}
-
- ixgbe_reset_q_vectors(adapter);
} else {
free_irq(adapter->pdev->irq, adapter);
}
+
+ /* clear q_vector state information */
+ ixgbe_reset_q_vectors(adapter);
}
/**
@@ -3879,7 +3878,6 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
struct ixgbe_hw *hw = &adapter->hw;
u32 rxctrl;
int i;
- int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
/* signal that we are down to the interrupt handler */
set_bit(__IXGBE_DOWN, &adapter->state);
@@ -3924,15 +3922,6 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
adapter->vfinfo[i].clear_to_send = 0;
}
- /* Cleanup the affinity_hint CPU mask memory and callback */
- for (i = 0; i < num_q_vectors; i++) {
- struct ixgbe_q_vector *q_vector = adapter->q_vector[i];
- /* clear the affinity_mask in the IRQ descriptor */
- irq_set_affinity_hint(adapter->msix_entries[i]. vector, NULL);
- /* release the CPU mask memory */
- free_cpumask_var(q_vector->affinity_mask);
- }
-
/* disable transmits in the hardware now that interrupts are off */
for (i = 0; i < adapter->num_tx_queues; i++) {
u8 reg_idx = adapter->tx_ring[i]->reg_idx;
@@ -4677,6 +4666,11 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
q_vector->adapter = adapter;
q_vector->v_idx = v_idx;
+ /* Allocate the affinity_hint cpumask, configure the mask */
+ if (!alloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
+ goto err_out;
+ cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+
if (q_vector->tx.count && !q_vector->rx.count)
q_vector->eitr = adapter->tx_eitr_param;
else
@@ -4694,6 +4688,7 @@ err_out:
v_idx--;
q_vector = adapter->q_vector[v_idx];
netif_napi_del(&q_vector->napi);
+ free_cpumask_var(q_vector->affinity_mask);
kfree(q_vector);
adapter->q_vector[v_idx] = NULL;
}
@@ -4710,17 +4705,18 @@ err_out:
**/
static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter)
{
- int q_idx, num_q_vectors;
+ int v_idx, num_q_vectors;
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
else
num_q_vectors = 1;
- for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
- struct ixgbe_q_vector *q_vector = adapter->q_vector[q_idx];
- adapter->q_vector[q_idx] = NULL;
+ for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
+ struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx];
+ adapter->q_vector[v_idx] = NULL;
netif_napi_del(&q_vector->napi);
+ free_cpumask_var(q_vector->affinity_mask);
kfree(q_vector);
}
}
--
1.7.6
^ permalink raw reply related
* [net-next 04/10] ixgbe: consolidate all MSI-X ring interrupts and poll routines into one
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change consolidates all of the MSI-X interrupt and polling routines
into two single functions. One for the interrupt and one for the code.
The main advantage to doing this is that the compiler can optimize the
routines into single monolithic functions which should allow all of them
function to occupy a single block of memory and as such avoid jumping
around.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 288 ++++++-------------------
1 files changed, 67 insertions(+), 221 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2450279..03432dc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -798,9 +798,9 @@ static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
* @tx_ring: tx ring to clean
* @budget: amount of work driver is allowed to do this pass, in packets
**/
-static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
- struct ixgbe_ring *tx_ring,
- int budget)
+static int ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *tx_ring,
+ int budget)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_tx_buffer *tx_buffer;
@@ -1298,9 +1298,9 @@ static inline bool ixgbe_get_rsc_state(union ixgbe_adv_rx_desc *rx_desc)
IXGBE_RXDADV_RSCCNT_MASK);
}
-static void ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
- struct ixgbe_ring *rx_ring,
- int *work_done, int work_to_do)
+static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
+ struct ixgbe_ring *rx_ring,
+ int budget)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
@@ -1480,11 +1480,11 @@ static void ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
#endif /* IXGBE_FCOE */
ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
+ budget--;
next_desc:
rx_desc->wb.upper.status_error = 0;
- (*work_done)++;
- if (*work_done >= work_to_do)
+ if (!budget)
break;
/* return some buffers to hardware, one at a time is too slow */
@@ -1525,9 +1525,10 @@ next_desc:
u64_stats_update_end(&rx_ring->syncp);
q_vector->rx.total_packets += total_rx_packets;
q_vector->rx.total_bytes += total_rx_bytes;
+
+ return budget;
}
-static int ixgbe_clean_rxonly(struct napi_struct *, int);
/**
* ixgbe_configure_msix - Configure MSI-X hardware
* @adapter: board private structure
@@ -1981,167 +1982,18 @@ static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
/* skip the flush */
}
-static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data)
+static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
- if (!q_vector->tx.count)
- return IRQ_HANDLED;
-
/* EIAM disabled interrupts (on this vector) for us */
- napi_schedule(&q_vector->napi);
- return IRQ_HANDLED;
-}
-
-/**
- * ixgbe_msix_clean_rx - single unshared vector rx clean (all queues)
- * @irq: unused
- * @data: pointer to our q_vector struct for this interrupt vector
- **/
-static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
-{
- struct ixgbe_q_vector *q_vector = data;
-
- if (!q_vector->rx.count)
- return IRQ_HANDLED;
-
- /* EIAM disabled interrupts (on this vector) for us */
- napi_schedule(&q_vector->napi);
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
}
-static irqreturn_t ixgbe_msix_clean_many(int irq, void *data)
-{
- struct ixgbe_q_vector *q_vector = data;
-
- if (!q_vector->tx.count && !q_vector->rx.count)
- return IRQ_HANDLED;
-
- /* EIAM disabled interrupts (on this vector) for us */
- napi_schedule(&q_vector->napi);
-
- return IRQ_HANDLED;
-}
-
-/**
- * ixgbe_clean_rxonly - msix (aka one shot) rx clean routine
- * @napi: napi struct with our devices info in it
- * @budget: amount of work driver is allowed to do this pass, in packets
- *
- * This function is optimized for cleaning one queue only on a single
- * q_vector!!!
- **/
-static int ixgbe_clean_rxonly(struct napi_struct *napi, int budget)
-{
- struct ixgbe_q_vector *q_vector =
- container_of(napi, struct ixgbe_q_vector, napi);
- struct ixgbe_adapter *adapter = q_vector->adapter;
- int work_done = 0;
-
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_dca(q_vector);
-#endif
-
- ixgbe_clean_rx_irq(q_vector, q_vector->rx.ring, &work_done, budget);
-
- /* If all Rx work done, exit the polling mode */
- if (work_done < budget) {
- napi_complete(napi);
- if (adapter->rx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter,
- ((u64)1 << q_vector->v_idx));
- }
-
- return work_done;
-}
-
-/**
- * ixgbe_clean_rxtx_many - msix (aka one shot) rx clean routine
- * @napi: napi struct with our devices info in it
- * @budget: amount of work driver is allowed to do this pass, in packets
- *
- * This function will clean more than one rx queue associated with a
- * q_vector.
- **/
-static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
-{
- struct ixgbe_q_vector *q_vector =
- container_of(napi, struct ixgbe_q_vector, napi);
- struct ixgbe_adapter *adapter = q_vector->adapter;
- struct ixgbe_ring *ring;
- int work_done = 0;
- bool clean_complete = true;
-
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_dca(q_vector);
-#endif
-
- for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
- clean_complete &= ixgbe_clean_tx_irq(q_vector, ring, budget);
-
- /* attempt to distribute budget to each queue fairly, but don't allow
- * the budget to go below 1 because we'll exit polling */
- budget /= (q_vector->rx.count ?: 1);
- budget = max(budget, 1);
-
- for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next)
- ixgbe_clean_rx_irq(q_vector, ring, &work_done, budget);
-
- if (!clean_complete)
- work_done = budget;
-
- /* If all Rx work done, exit the polling mode */
- if (work_done < budget) {
- napi_complete(napi);
- if (adapter->rx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter,
- ((u64)1 << q_vector->v_idx));
- return 0;
- }
-
- return work_done;
-}
-
-/**
- * ixgbe_clean_txonly - msix (aka one shot) tx clean routine
- * @napi: napi struct with our devices info in it
- * @budget: amount of work driver is allowed to do this pass, in packets
- *
- * This function is optimized for cleaning one queue only on a single
- * q_vector!!!
- **/
-static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
-{
- struct ixgbe_q_vector *q_vector =
- container_of(napi, struct ixgbe_q_vector, napi);
- struct ixgbe_adapter *adapter = q_vector->adapter;
-
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_dca(q_vector);
-#endif
-
- if (!ixgbe_clean_tx_irq(q_vector, q_vector->tx.ring, budget))
- return budget;
-
- /* If all Tx work done, exit the polling mode */
- napi_complete(napi);
- if (adapter->tx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));
-
- return 0;
-}
-
static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx,
int r_idx)
{
@@ -2241,7 +2093,6 @@ out:
static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
- irqreturn_t (*handler)(int, void *);
int i, vector, q_vectors, err;
int ri = 0, ti = 0;
@@ -2252,31 +2103,25 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
if (err)
return err;
-#define SET_HANDLER(_v) (((_v)->rx.count && (_v)->tx.count) \
- ? &ixgbe_msix_clean_many : \
- (_v)->rx.count ? &ixgbe_msix_clean_rx : \
- (_v)->tx.count ? &ixgbe_msix_clean_tx : \
- NULL)
for (vector = 0; vector < q_vectors; vector++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
- handler = SET_HANDLER(q_vector);
- if (handler == &ixgbe_msix_clean_rx) {
+ if (q_vector->tx.ring && q_vector->rx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-%s-%d", netdev->name, "rx", ri++);
- } else if (handler == &ixgbe_msix_clean_tx) {
+ "%s-%s-%d", netdev->name, "TxRx", ri++);
+ ti++;
+ } else if (q_vector->rx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-%s-%d", netdev->name, "tx", ti++);
- } else if (handler == &ixgbe_msix_clean_many) {
+ "%s-%s-%d", netdev->name, "rx", ri++);
+ } else if (q_vector->tx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
- "%s-%s-%d", netdev->name, "TxRx", ri++);
- ti++;
+ "%s-%s-%d", netdev->name, "tx", ti++);
} else {
/* skip this unused q_vector */
continue;
}
err = request_irq(adapter->msix_entries[vector].vector,
- handler, 0, q_vector->name,
+ &ixgbe_msix_clean_rings, 0, q_vector->name,
q_vector);
if (err) {
e_err(probe, "request_irq failed for MSIX interrupt "
@@ -2484,8 +2329,8 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
i--;
for (; i >= 0; i--) {
/* free only the irqs that were actually requested */
- if (!adapter->q_vector[i]->rx.count &&
- !adapter->q_vector[i]->tx.count)
+ if (!adapter->q_vector[i]->rx.ring &&
+ !adapter->q_vector[i]->tx.ring)
continue;
free_irq(adapter->msix_entries[i].vector,
@@ -3478,19 +3323,8 @@ static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter)
q_vectors = 1;
for (q_idx = 0; q_idx < q_vectors; q_idx++) {
- struct napi_struct *napi;
q_vector = adapter->q_vector[q_idx];
- napi = &q_vector->napi;
- if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
- if (!q_vector->rx.count || !q_vector->tx.count) {
- if (q_vector->tx.count == 1)
- napi->poll = &ixgbe_clean_txonly;
- else if (q_vector->rx.count == 1)
- napi->poll = &ixgbe_clean_rxonly;
- }
- }
-
- napi_enable(napi);
+ napi_enable(&q_vector->napi);
}
}
@@ -4148,29 +3982,41 @@ static int ixgbe_poll(struct napi_struct *napi, int budget)
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
- int tx_clean_complete, work_done = 0;
+ struct ixgbe_ring *ring;
+ int per_ring_budget;
+ bool clean_complete = true;
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_dca(q_vector);
#endif
- tx_clean_complete = ixgbe_clean_tx_irq(q_vector, adapter->tx_ring[0],
- budget);
- ixgbe_clean_rx_irq(q_vector, adapter->rx_ring[0], &work_done, budget);
+ for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next)
+ clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring, budget);
- if (!tx_clean_complete)
- work_done = budget;
+ /* attempt to distribute budget to each queue fairly, but don't allow
+ * the budget to go below 1 because we'll exit polling */
+ if (q_vector->rx.count > 1)
+ per_ring_budget = max(budget/q_vector->rx.count, 1);
+ else
+ per_ring_budget = budget;
- /* If budget not fully consumed, exit the polling mode */
- if (work_done < budget) {
- napi_complete(napi);
- if (adapter->rx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter, IXGBE_EIMS_RTX_QUEUE);
- }
- return work_done;
+ for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next)
+ clean_complete &= !!ixgbe_clean_rx_irq(q_vector, ring,
+ per_ring_budget);
+
+ /* If all work not completed, return budget and keep polling */
+ if (!clean_complete)
+ return budget;
+
+ /* all work done, exit the polling mode */
+ napi_complete(napi);
+ if (adapter->rx_itr_setting & 1)
+ ixgbe_set_itr(q_vector);
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));
+
+ return 0;
}
/**
@@ -4811,19 +4657,15 @@ out:
**/
static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
{
- int q_idx, num_q_vectors;
+ int v_idx, num_q_vectors;
struct ixgbe_q_vector *q_vector;
- int (*poll)(struct napi_struct *, int);
- if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
+ if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
- poll = &ixgbe_clean_rxtx_many;
- } else {
+ else
num_q_vectors = 1;
- poll = &ixgbe_poll;
- }
- for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+ for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
q_vector = kzalloc_node(sizeof(struct ixgbe_q_vector),
GFP_KERNEL, adapter->node);
if (!q_vector)
@@ -4831,25 +4673,29 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
GFP_KERNEL);
if (!q_vector)
goto err_out;
+
q_vector->adapter = adapter;
+ q_vector->v_idx = v_idx;
+
if (q_vector->tx.count && !q_vector->rx.count)
q_vector->eitr = adapter->tx_eitr_param;
else
q_vector->eitr = adapter->rx_eitr_param;
- q_vector->v_idx = q_idx;
- netif_napi_add(adapter->netdev, &q_vector->napi, (*poll), 64);
- adapter->q_vector[q_idx] = q_vector;
+
+ netif_napi_add(adapter->netdev, &q_vector->napi,
+ ixgbe_poll, 64);
+ adapter->q_vector[v_idx] = q_vector;
}
return 0;
err_out:
- while (q_idx) {
- q_idx--;
- q_vector = adapter->q_vector[q_idx];
+ while (v_idx) {
+ v_idx--;
+ q_vector = adapter->q_vector[v_idx];
netif_napi_del(&q_vector->napi);
kfree(q_vector);
- adapter->q_vector[q_idx] = NULL;
+ adapter->q_vector[v_idx] = NULL;
}
return -ENOMEM;
}
@@ -6944,7 +6790,7 @@ static void ixgbe_netpoll(struct net_device *netdev)
int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
for (i = 0; i < num_q_vectors; i++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[i];
- ixgbe_msix_clean_many(0, q_vector);
+ ixgbe_msix_clean_rings(0, q_vector);
}
} else {
ixgbe_intr(adapter->pdev->irq, netdev);
--
1.7.6
^ permalink raw reply related
* [net-next 06/10] ixgbe: Use ring->dev instead of adapter->pdev->dev when updating DCA
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change switches us over to using the ring->dev pointer instead of
having to use the adapter->pdev->dev reference. The advantage to this is
that it is a much shorter route to get the to final needed value.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7d745e2..1929d23 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -925,12 +925,12 @@ static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK;
- rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
+ rxctrl |= dca3_get_tag(rx_ring->dev, cpu);
break;
case ixgbe_mac_82599EB:
case ixgbe_mac_X540:
rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599;
- rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
+ rxctrl |= (dca3_get_tag(rx_ring->dev, cpu) <<
IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599);
break;
default:
@@ -954,7 +954,7 @@ static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
case ixgbe_mac_82598EB:
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(reg_idx));
txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK;
- txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
+ txctrl |= dca3_get_tag(tx_ring->dev, cpu);
txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(reg_idx), txctrl);
break;
@@ -962,7 +962,7 @@ static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
case ixgbe_mac_X540:
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx));
txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK_82599;
- txctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
+ txctrl |= (dca3_get_tag(tx_ring->dev, cpu) <<
IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599);
txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx), txctrl);
--
1.7.6
^ permalink raw reply related
* [net-next 07/10] ixgbe: commonize ixgbe_map_rings_to_vectors to work for all interrupt types
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch makes it so that the map_rings_to_vectors call will work with
all interrupt types. The advantage to this is that there will now be a
predictable mapping for all given interrupt types.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 90 ++++++++++---------------
1 files changed, 35 insertions(+), 55 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1929d23..2879a74 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2014,59 +2014,41 @@ static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
* group the rings as "efficiently" as possible. You would add new
* mapping configurations in here.
**/
-static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter)
+static void ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter)
{
- int q_vectors;
+ int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ int rxr_remaining = adapter->num_rx_queues, rxr_idx = 0;
+ int txr_remaining = adapter->num_tx_queues, txr_idx = 0;
int v_start = 0;
- int rxr_idx = 0, txr_idx = 0;
- int rxr_remaining = adapter->num_rx_queues;
- int txr_remaining = adapter->num_tx_queues;
- int i, j;
- int rqpv, tqpv;
- int err = 0;
- /* No mapping required if MSI-X is disabled. */
+ /* only one q_vector if MSI-X is disabled. */
if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
- goto out;
-
- q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ q_vectors = 1;
/*
- * The ideal configuration...
- * We have enough vectors to map one per queue.
+ * If we don't have enough vectors for a 1-to-1 mapping, we'll have to
+ * group them so there are multiple queues per vector.
+ *
+ * Re-adjusting *qpv takes care of the remainder.
*/
- if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) {
- for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
+ for (; v_start < q_vectors && rxr_remaining; v_start++) {
+ int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_start);
+ for (; rqpv; rqpv--, rxr_idx++, rxr_remaining--)
map_vector_to_rxq(adapter, v_start, rxr_idx);
-
- for (; txr_idx < txr_remaining; v_start++, txr_idx++)
- map_vector_to_txq(adapter, v_start, txr_idx);
-
- goto out;
}
/*
- * If we don't have enough vectors for a 1-to-1
- * mapping, we'll have to group them so there are
- * multiple queues per vector.
+ * If there are not enough q_vectors for each ring to have it's own
+ * vector then we must pair up Rx/Tx on a each vector
*/
- /* Re-adjusting *qpv takes care of the remainder. */
- for (i = v_start; i < q_vectors; i++) {
- rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
- for (j = 0; j < rqpv; j++) {
- map_vector_to_rxq(adapter, i, rxr_idx);
- rxr_idx++;
- rxr_remaining--;
- }
- tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
- for (j = 0; j < tqpv; j++) {
- map_vector_to_txq(adapter, i, txr_idx);
- txr_idx++;
- txr_remaining--;
- }
+ if ((v_start + txr_remaining) > q_vectors)
+ v_start = 0;
+
+ for (; v_start < q_vectors && txr_remaining; v_start++) {
+ int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_start);
+ for (; tqpv; tqpv--, txr_idx++, txr_remaining--)
+ map_vector_to_txq(adapter, v_start, txr_idx);
}
-out:
- return err;
}
/**
@@ -2083,10 +2065,6 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
int vector, err;
int ri = 0, ti = 0;
- err = ixgbe_map_rings_to_vectors(adapter);
- if (err)
- return err;
-
for (vector = 0; vector < q_vectors; vector++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
struct msix_entry *entry = &adapter->msix_entries[vector];
@@ -2294,19 +2272,25 @@ static int ixgbe_request_irq(struct ixgbe_adapter *adapter)
struct net_device *netdev = adapter->netdev;
int err;
- if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
+ /* map all of the rings to the q_vectors */
+ ixgbe_map_rings_to_vectors(adapter);
+
+ if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
err = ixgbe_request_msix_irqs(adapter);
- } else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) {
+ else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED)
err = request_irq(adapter->pdev->irq, ixgbe_intr, 0,
netdev->name, adapter);
- } else {
+ else
err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED,
netdev->name, adapter);
- }
- if (err)
+ if (err) {
e_err(probe, "request_irq failed, Error %d\n", err);
+ /* place q_vectors and rings back into a known good state */
+ ixgbe_reset_q_vectors(adapter);
+ }
+
return err;
}
@@ -2316,11 +2300,10 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
int i, q_vectors;
q_vectors = adapter->num_msix_vectors;
-
i = q_vectors - 1;
free_irq(adapter->msix_entries[i].vector, adapter);
-
i--;
+
for (; i >= 0; i--) {
/* free only the irqs that were actually requested */
if (!adapter->q_vector[i]->rx.ring &&
@@ -2387,9 +2370,6 @@ static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter)
ixgbe_set_ivar(adapter, 0, 0, 0);
ixgbe_set_ivar(adapter, 1, 0, 0);
- map_vector_to_rxq(adapter, 0, 0);
- map_vector_to_txq(adapter, 0, 0);
-
e_info(hw, "Legacy interrupt IVAR setup done\n");
}
--
1.7.6
^ permalink raw reply related
* [net-next 08/10] ixgbe: Drop unnecessary adapter->hw dereference in loopback test setup
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch drops a set of unnecessary dereferences to the hardware structure
since we already have a local copy of the hardware pointer.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 18 +++++++++---------
1 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 16835cc..6241e9a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1566,26 +1566,26 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter)
/* X540 needs to set the MACC.FLU bit to force link up */
if (adapter->hw.mac.type == ixgbe_mac_X540) {
- reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_MACC);
+ reg_data = IXGBE_READ_REG(hw, IXGBE_MACC);
reg_data |= IXGBE_MACC_FLU;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_MACC, reg_data);
+ IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data);
}
/* right now we only support MAC loopback in the driver */
- reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_HLREG0);
+ reg_data = IXGBE_READ_REG(hw, IXGBE_HLREG0);
/* Setup MAC loopback */
reg_data |= IXGBE_HLREG0_LPBK;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_HLREG0, reg_data);
+ IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg_data);
- reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_FCTRL);
+ reg_data = IXGBE_READ_REG(hw, IXGBE_FCTRL);
reg_data |= IXGBE_FCTRL_BAM | IXGBE_FCTRL_SBP | IXGBE_FCTRL_MPE;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCTRL, reg_data);
+ IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg_data);
- reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_AUTOC);
+ reg_data = IXGBE_READ_REG(hw, IXGBE_AUTOC);
reg_data &= ~IXGBE_AUTOC_LMS_MASK;
reg_data |= IXGBE_AUTOC_LMS_10G_LINK_NO_AN | IXGBE_AUTOC_FLU;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_AUTOC, reg_data);
- IXGBE_WRITE_FLUSH(&adapter->hw);
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_data);
+ IXGBE_WRITE_FLUSH(hw);
usleep_range(10000, 20000);
/* Disable Atlas Tx lanes; re-enabled in reset path */
--
1.7.6
^ permalink raw reply related
* [net-next 09/10] ixgbe: combine PCI_VDEVICE and board declaration to same line
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch is a minor whitespace cleanup to compress the device ID
declaration and board type declaration onto the same line. It seems to
make sense since all of the combinations of the two are less than 80
characters and it makes the overall layout a bit more readable.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 79 ++++++++-----------------
1 files changed, 26 insertions(+), 53 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2879a74..35f9912 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -79,59 +79,32 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = {
* Class, Class Mask, private data (not used) }
*/
static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX),
- board_82598 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T),
- board_X540 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2),
- board_82599 },
- {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS),
- board_82599 },
-
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 },
/* required last entry */
{0, }
};
--
1.7.6
^ permalink raw reply related
* [net-next 10/10] ixgbe: Update TXDCTL configuration to correctly handle WTHRESH
From: Jeff Kirsher @ 2011-08-21 7:29 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1313911761-11709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change updated the TXDCTL configuration. The main goal is to be much
more explicit about the configuration and avoid a possible fake TX hang
when the interrupt throttle rate is set to 0.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 35 +++++++++++++------------
1 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 35f9912..8cf8670 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2359,13 +2359,11 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
struct ixgbe_hw *hw = &adapter->hw;
u64 tdba = ring->dma;
int wait_loop = 10;
- u32 txdctl;
+ u32 txdctl = IXGBE_TXDCTL_ENABLE;
u8 reg_idx = ring->reg_idx;
/* disable queue to avoid issues while updating state */
- txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
- IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx),
- txdctl & ~IXGBE_TXDCTL_ENABLE);
+ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
IXGBE_WRITE_FLUSH(hw);
IXGBE_WRITE_REG(hw, IXGBE_TDBAL(reg_idx),
@@ -2377,18 +2375,22 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0);
ring->tail = hw->hw_addr + IXGBE_TDT(reg_idx);
- /* configure fetching thresholds */
- if (adapter->rx_itr_setting == 0) {
- /* cannot set wthresh when itr==0 */
- txdctl &= ~0x007F0000;
- } else {
- /* enable WTHRESH=8 descriptors, to encourage burst writeback */
- txdctl |= (8 << 16);
- }
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- /* PThresh workaround for Tx hang with DFP enabled. */
- txdctl |= 32;
- }
+ /*
+ * set WTHRESH to encourage burst writeback, it should not be set
+ * higher than 1 when ITR is 0 as it could cause false TX hangs
+ *
+ * In order to avoid issues WTHRESH + PTHRESH should always be equal
+ * to or less than the number of on chip descriptors, which is
+ * currently 40.
+ */
+ if (!adapter->tx_itr_setting || !adapter->rx_itr_setting)
+ txdctl |= (1 << 16); /* WTHRESH = 1 */
+ else
+ txdctl |= (8 << 16); /* WTHRESH = 8 */
+
+ /* PTHRESH=32 is needed to avoid a Tx hang with DFP enabled. */
+ txdctl |= (1 << 8) | /* HTHRESH = 1 */
+ 32; /* PTHRESH = 32 */
/* reinitialize flowdirector state */
if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
@@ -2403,7 +2405,6 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);
/* enable queue */
- txdctl |= IXGBE_TXDCTL_ENABLE;
IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);
/* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */
--
1.7.6
^ permalink raw reply related
* Nine Hundred And Fifty Thousand Pounds Was Awarded To Your ID In The Benz Cash Offer, Get Bact To Us With Your:
From: letrevino @ 2011-08-21 6:32 UTC (permalink / raw)
1. Full Name:
2. Full Address:
3. Phone number:
4. Country:
^ permalink raw reply
* Re: strange routing issue--packets stop getting forwarded for a live connection
From: Corey Hickey @ 2011-08-21 8:12 UTC (permalink / raw)
To: Julian Anastasov; +Cc: Linux Netdev List
In-Reply-To: <alpine.LFD.2.00.1108210924010.1581@ja.ssi.bg>
On 2011-08-20 23:35, Julian Anastasov wrote:
>> I have a strange issue where, reliably, certain conditions cause my
>> Linux router to stop forwarding packets for a connection.
[...]
>> 3. MTU size; 1500 on eth0 and 1406 on tun0. Bigger packets have been
>> transferred fine.
>
> Lower MTU, it can be PMTUD problem. At 04:50:24.112658
> I see 7801:9169 is 1420 bytes and no ICMP FRAG NEEDED is generated.
> May be these two regressions explain it:
>
> http://marc.info/?l=linux-netdev&m=131342172722536&w=2
>
> There are 2 fixes you can try or more recent kernel
> tree, for example 3.1-rc2 has the fixes.
Many thanks for your reply--it looks like you're on to something. You
didn't specify which interface to lower the MTU on, so I tried them each
in turn, and found that lowering the MTU on the client machine to 1406
(matching tun0 on the router) did indeed solve the problem. That makes
sense in retrospect.
It's a bit late at night for me to be patching my kernel, but I'll see
if I can do it tomorrow.
Thanks again, and I'll let you know how it turns out.
-Corey
^ permalink raw reply
* Re: [PATCH] net: add APIs for manipulating skb page fragments.
From: Ian Campbell @ 2011-08-21 8:23 UTC (permalink / raw)
To: David Miller
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
eric.dumazet@gmail.com, mirq-linux@rere.qmqm.pl
In-Reply-To: <20110820.173133.1612902138924735868.davem@davemloft.net>
On Sun, 2011-08-21 at 01:31 +0100, David Miller wrote:
> From: Ian Campbell <ian.campbell@citrix.com>
> Date: Fri, 19 Aug 2011 17:25:00 +0100
>
> > The primary aim is to add skb_frag_(ref|unref) in order to remove the use of
> > bare get/put_page on SKB pages fragments and to isolate users from subsequent
> > changes to the skb_frag_t data structure.
> >
> > Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
>
> You're going to have to protect all of the things using the interfaces
> from linux/dma-mapping.h with CONFIG_HAS_DMA otherwise it won't build
> on platforms like S390.
s390 is one of the arches which I build tested and I initially saw this
issue too. I did add CONFIG_HAS_DMA but it turns out that
linux/dma-mapping.h takes care of this by including
asm-generic/dma-mapping-broken.h for you so I removed the #ifdef again.
The header defines the prototypes to allow building but causes a link
time failure if anything actually uses the interfaces.
I just tested a s390x defconfig build again and it appears to be fine.
Ian.
^ permalink raw reply
* Re: strange routing issue--packets stop getting forwarded for a live connection
From: Julian Anastasov @ 2011-08-21 9:02 UTC (permalink / raw)
To: Corey Hickey; +Cc: Linux Netdev List
In-Reply-To: <4E50BDFB.7050502@fatooh.org>
Hello,
On Sun, 21 Aug 2011, Corey Hickey wrote:
> >> 3. MTU size; 1500 on eth0 and 1406 on tun0. Bigger packets have been
> >> transferred fine.
> >
> > Lower MTU, it can be PMTUD problem. At 04:50:24.112658
> > I see 7801:9169 is 1420 bytes and no ICMP FRAG NEEDED is generated.
> > May be these two regressions explain it:
> >
> > http://marc.info/?l=linux-netdev&m=131342172722536&w=2
> >
> > There are 2 fixes you can try or more recent kernel
> > tree, for example 3.1-rc2 has the fixes.
>
> Many thanks for your reply--it looks like you're on to something. You
> didn't specify which interface to lower the MTU on, so I tried them each
> in turn, and found that lowering the MTU on the client machine to 1406
> (matching tun0 on the router) did indeed solve the problem. That makes
> sense in retrospect.
I just wanted to note the difference in MTUs
as a possible cause that triggers the problem. And after
your confirmation I think the new/patched kernel should work
without playing with MTUs.
> It's a bit late at night for me to be patching my kernel, but I'll see
> if I can do it tomorrow.
>
> Thanks again, and I'll let you know how it turns out.
>
> -Corey
Regards
--
Julian Anastasov <ja@ssi.bg>
^ permalink raw reply
* Re: Bridge stays down until a port is added
From: Marc Haber @ 2011-08-21 12:13 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev, Sven-Haegar Koch
In-Reply-To: <20110820093059.75c37a1f@nehalam.ftrdhcpuser.net>
On Sat, Aug 20, 2011 at 09:30:59AM -0700, Stephen Hemminger wrote:
> The problem is that IPv6 Duplicate Address Detection needs to
> work. This is not a simple problem. If the bridge asserted
> carrier with no ports then:
>
> 1. IPv6 address assigned and IPv6 decides it is okay.
> 2. Port added later
> 3. Another system has the same address.
> *broke*
Same situation when a system-to-system-link is added after bringing up
an interface. I agree that the issue is not an issue if a real switch
is being used.
> If you want to avoid DAD, then you can configure disable DAD
> by setting /proc/sys/net/ipv6/conf/br0/accept_dad to 0
I'd like to avoid that.
2001:db8::1
Would it acceptable (and clean!) to have:
eth0: 2001:db8:1::100/64 default gw to the internet is 2001:db8:1::1
lo: 127.0.0.1/8, ::1/128, 2001:db8:2::100/64
br0: 2001:db8:2::1/64 (being default gw for the VMs connected to br0,
routing 2001:db8:2::/64 to the Internet)
Note 2001:db8:2::/64 being used both on lo and br0, with 2001:db8:2::100 meant
to be reachable from the Internet even if no VM is already up. my
hostname will be A-Recorded to 2001:db8:2::100 with proper reverse
DNS. The background for doing so is that I cannot control the reverse
DNS for the IP addresses inside 200a:db8:1::/64 in a lot of my setups
(for example, if my IPv6 comes in via Sixxs).
Is this going to work in a clean way?
Greetings
Marc
--
-----------------------------------------------------------------------------
Marc Haber | "I don't trust Computers. They | Mailadresse im Header
Mannheim, Germany | lose things." Winona Ryder | Fon: *49 621 72739834
Nordisch by Nature | How to make an American Quilt | Fax: *49 3221 2323190
^ permalink raw reply
* Re: r8169 hard-freezes the system on big network loads
From: Francois Romieu @ 2011-08-21 12:33 UTC (permalink / raw)
To: Kjun Chen; +Cc: netdev, nic_swsd, Michael Brade
In-Reply-To: <201108141308.28140.kjun-chen@sambodha.org>
(Michael, please don't use the e-mail address of your Solar meditation teacher)
Kjun Chen <kjun-chen@sambodha.org> :
[...]
> If you need any other information or help, please let me know.
The XID line included in any recent kernel dmesg by the r8169 driver would
be welcome.
Thanks.
--
Ueimor
^ permalink raw reply
* Re: r8169 hard-freezes the system on big network loads
From: Michael Brade @ 2011-08-21 13:20 UTC (permalink / raw)
To: Francois Romieu; +Cc: netdev, nic_swsd
In-Reply-To: <20110821123311.GA20605@electric-eye.fr.zoreil.com>
On Sunday 21 August 2011 14:33:11 you wrote:
> (Michael, please don't use the e-mail address of your Solar meditation
> teacher)
Gee...?! that was an accident (and I thought I know what I am doing...)
> > If you need any other information or help, please let me know.
>
> The XID line included in any recent kernel dmesg by the r8169 driver would
> be welcome.
r8169 0000:13:00.0: eth0: RTL8168d/8111d at 0xffffc90000c72000,
f0:4d:a2:b8:ce:62, XID 083000c0 IRQ 52
hope that helps,
Michael
^ permalink raw reply
* Re: [net-next 03/10] ixgbe: Drop the TX work limit and instead just leave it to budget
From: Ben Hutchings @ 2011-08-21 14:01 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, Alexander Duyck, netdev, gospo
In-Reply-To: <1313911761-11709-4-git-send-email-jeffrey.t.kirsher@intel.com>
On Sun, 2011-08-21 at 00:29 -0700, Jeff Kirsher wrote:
> From: Alexander Duyck <alexander.h.duyck@intel.com>
>
> This change makes it so that the TX work limit is now obsolete. Instead of
> using it we can instead rely on the NAPI budget for the number of packets
> we should clean per interrupt. The advantage to this approach is that it
> results in a much more balanced work flow since the same number of RX and
> TX packets should be cleaned per interrupts.
[...]
This seems kind of sensible, but it's not how Dave has been recommending
people to account for TX work in NAPI.
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.
^ permalink raw reply
* [OT]Any open source community in wireless network?
From: hz hanks @ 2011-08-21 15:49 UTC (permalink / raw)
To: netdev
Hi, all
I am looking for some open source communities in wireless network.
This mailing list mainly concentrated on computer networks such as
TCP, but my interests are mainly on embedded wireless system and
mobile phone system. So is there any kind person could provide me with
some open source communities which mainly concentrate on those topics?
Thanks a lot.
^ permalink raw reply
* Re: [OT]Any open source community in wireless network?
From: Sven-Haegar Koch @ 2011-08-21 17:20 UTC (permalink / raw)
To: hz hanks; +Cc: netdev
In-Reply-To: <CAPerbBwowb=5+rOwrf00ZqdmtrtR_39mhvs6jouseOBGz__4Ew@mail.gmail.com>
On Sun, 21 Aug 2011, hz hanks wrote:
> I am looking for some open source communities in wireless network.
> This mailing list mainly concentrated on computer networks such as
> TCP, but my interests are mainly on embedded wireless system and
> mobile phone system. So is there any kind person could provide me with
> some open source communities which mainly concentrate on those topics?
> Thanks a lot.
Like:
linux-wireless@vger.kernel.org (linux wireless driver development)
http://www.openwrt.org (embedded linux distribution, for accesspoints
and more)
http://www.android.com (smartphone foobar)
c'ya
sven-haegar
--
Three may keep a secret, if two of them are dead.
- Ben F.
^ permalink raw reply
* Re: [OT]Any open source community in wireless network?
From: Randy Dunlap @ 2011-08-21 18:40 UTC (permalink / raw)
To: Sven-Haegar Koch; +Cc: hz hanks, netdev
In-Reply-To: <alpine.DEB.2.02.1108211917440.26263@aurora>
On Sun, 21 Aug 2011 19:20:32 +0200 (CEST) Sven-Haegar Koch wrote:
> On Sun, 21 Aug 2011, hz hanks wrote:
>
> > I am looking for some open source communities in wireless network.
> > This mailing list mainly concentrated on computer networks such as
> > TCP, but my interests are mainly on embedded wireless system and
> > mobile phone system. So is there any kind person could provide me with
> > some open source communities which mainly concentrate on those topics?
> > Thanks a lot.
>
> Like:
> linux-wireless@vger.kernel.org (linux wireless driver development)
> http://www.openwrt.org (embedded linux distribution, for accesspoints
> and more)
> http://www.android.com (smartphone foobar)
http://wireless.kernel.org/ (Linux Wireless wiki)
---
~Randy
^ permalink raw reply
* Re: A question about MTUs and TCP stack
From: Eric Dumazet @ 2011-08-21 20:05 UTC (permalink / raw)
To: Pawan Singh; +Cc: netdev@vger.kernel.org
In-Reply-To: <A55791AD2520D54CA92150D16630D03B36116A5B@VA3DIAXVS1F1.RED001.local>
Le mardi 16 août 2011 à 11:33 -0700, Pawan Singh a écrit :
> Hi
>
> I am posting this question to "netdev" mailing list because I could no
> longer find "linux-net" mailing list.
>
> I find that the Linux TCP stack consumes huge amount of CPU if the MTU
> of an interface is set to 2400 and it is receiving 1000 byte Ethernet
> packets. On the other hand, if the MTU is set to 1500, the CPU
> consumption is reduced drastically. Increased CPU usage causes network
> throughput to drop considerably (from 800-900 Mbps to 200 Mbps). My
> kernel version is fedora core 6 and we are using 1 Gig NICs (Intel
> 82546GB and Broadcom NetXtreme BCM5721):
>
> Linux he7700-tg 2.6.22.14-72.fc6 #1 SMP Wed Nov 21 14:10:25 EST 2007
> x86_64 x86_64 x86_64 GNU/Linux
>
> I do not know the TCP buffer management internals and how they are
> affected by MTU. Is there some FAQ/information online or do I have to
> open up the source code and try to identify the source of the problem.
> I guess I can also try newer versions of the kernel and see if the
> issue has been resolved.
>
I suspect you have a CPU problem on the receiver side, not on transmit
one ?
MTU has a direct impact on skb 'truesize'. As the linux tcp stack takes
care of not using too much kernel ram for the sole use of one socket,
you might hit a per socket limit faster with big MTU (and not filled RX
buffers)
When this limit is hit, tcp stack tries to 'collapse' consecutive skbs
to remove the unused parts of skbs. This is a very expensive process.
With a recent kernel, you could use 'perf top' tool and easily spot the
hot paths in kernel.
^ permalink raw reply
* [PATCH] Documentation: RFC 2553bis is now RFC 3493
From: Geoffrey Thomas @ 2011-08-21 20:13 UTC (permalink / raw)
To: netdev; +Cc: Geoffrey Thomas
Signed-off-by: Geoffrey Thomas <geofft@mit.edu>
---
Documentation/networking/ip-sysctl.txt | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index db2a406..8154699 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -992,7 +992,7 @@ bindv6only - BOOLEAN
TRUE: disable IPv4-mapped address feature
FALSE: enable IPv4-mapped address feature
- Default: FALSE (as specified in RFC2553bis)
+ Default: FALSE (as specified in RFC3493)
IPv6 Fragmentation:
--
1.7.2.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox