* Re: [PATCH] sfc: Replace memset with eth_zero_addr
From: David Miller @ 2017-01-16 16:47 UTC (permalink / raw)
To: ecree; +Cc: mayhs11saini, bkenward, netdev, linux-net-drivers
In-Reply-To: <7f1c75ec-3cad-0071-9f41-86773361281e@solarflare.com>
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 16 Jan 2017 09:35:38 +0000
> On 16/01/17 03:56, Shyam Saini wrote:
>> Use eth_zero_addr to assign zero address to the given address array
>> instead of memset when the second argument in memset is address
>> of zero which makes the code clearer and also add header
>> file linux/etherdevice.h
>>
>> Signed-off-by: Shyam Saini <mayhs11saini@gmail.com>
>> ---
> Acked-by: Edward Cree <ecree@solarflare.com>
Applied to net-next.
^ permalink raw reply
* Re: [PATCH net v3] ravb: do not use zero-length alignment DMA descriptor
From: David Miller @ 2017-01-16 16:53 UTC (permalink / raw)
To: sergei.shtylyov
Cc: horms+renesas, magnus.damm, netdev, linux-renesas-soc,
masaru.nagai.vx
In-Reply-To: <96396803-caac-13cd-3e17-f9d10fc608ad@cogentembedded.com>
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 16 Jan 2017 16:01:49 +0300
> On 01/16/2017 01:45 PM, Simon Horman wrote:
>
>> From: Masaru Nagai <masaru.nagai.vx@renesas.com>
>>
>> Due to alignment requirements of the hardware transmissions are split
>> into
>> two DMA descriptors, a small padding descriptor of 0 - 3 bytes in
>> length
>> followed by a descriptor for rest of the packet.
>>
>> In the case of IP packets the first descriptor will never be zero due
>> to
>> the way that the stack aligns buffers for IP packets. However, for
>> non-IP
>> packets it may be zero.
>>
>> In that case it has been reported that timeouts occur, presumably
>> because
>> transmission stops at the first zero-length DMA descriptor and thus
>> the
>> packet is not transmitted. However, in my environment a BUG is
>> triggered as
>> follows:
> [...]
>
>> Fixes: 2f45d1902acf ("ravb: minimize TX data copying")
>> Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com
>> Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
>
> Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Applied and queued up for -stable, thanks.
^ permalink raw reply
* Re: [PATCH] cpmac: remove hopeless #warning
From: David Miller @ 2017-01-16 16:54 UTC (permalink / raw)
To: arnd; +Cc: f.fainelli, tremyfr, netdev, linux-kernel
In-Reply-To: <20170116132113.2056012-1-arnd@arndb.de>
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Jan 2017 14:20:54 +0100
> The #warning was present 10 years ago when the driver first got merged.
> As the platform is rather obsolete by now, it seems very unlikely that
> the warning will cause anyone to fix the code properly.
>
> kernelci.org reports the warning for every build in the meantime, so
> I think it's better to just turn it into a code comment to reduce
> noise.
>
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Agreed, applied, thanks Arnd.
^ permalink raw reply
* RE: [PATCH 1/2] qed: Replace memset with eth_zero_addr
From: Mintz, Yuval @ 2017-01-16 17:05 UTC (permalink / raw)
To: mayhs11saini@gmail.com; +Cc: netdev@vger.kernel.org, David Miller
In-Reply-To: <20170116.114606.1692928906878877115.davem@davemloft.net>
> > On Sun, Jan 15, 2017 at 11:38:30PM -0500, David Miller wrote:
> >>
> >> Please do not ever submit two patches which have the same exact
> >> commit header line, as these two patches do.
> >>
> >> When someone looks into the shortlog of GIT history all they will see
> >> is "qed: Replace memset with eth_zero_addr" twice.
> >>
> >> This gives the reader no idea what might be different between those
> >> two changes.
> >>
> >> Therefore you must give unique a commit header text for each change,
> >> which communicates sufficiently what is different in each change.
> >
> > Thanks a lot for correcting me. I'll take care of this thing.
> >
> > I'm resending these two patches as
> > 1). qed: Replace memset with eth_zero_addr
> > 2). qed: Use eth_zero_addr
> >
> > I hope it resolves same commit header line conflict.
>
> You aren't understanding the point.
>
> Those two lines still say exactly the same thing.
>
> What is different about these two changes? The answer to that question
> must propagate into those lines of text.
Other than the fact these 2 patches change 2 different qed files,
is there any significant difference between what each does?
If not, why not simply do both in a single patch?
^ permalink raw reply
* [PATCH v2 net-next 0/2] mvneta xmit_more and bql support
From: Marcin Wojtas @ 2017-01-16 17:08 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, netdev
Cc: davem, linux, sebastian.hesselbarth, andrew, jason,
thomas.petazzoni, gregory.clement, mw, jaz
Hi,
This is a delayed v2 of short patchset, which introduces xmit_more and BQL
to mvneta driver. The only one change was added in xmit_more support -
condition check preventing excessive descriptors concatenation before
flushing in HW.
Any comments or feedback would be welcome.
Best regards,
Marcin
Changelog:
v1 -> v2:
* Add checking condition that ensures too much descriptors are not
concatenated before flushing in HW.
Marcin Wojtas (1):
net: mvneta: add BQL support
Simon Guinot (1):
net: mvneta: add xmit_more support
drivers/net/ethernet/marvell/mvneta.c | 35 +++++++++++++++++++++++++++++------
1 file changed, 29 insertions(+), 6 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH v2 net-next 1/2] net: mvneta: add xmit_more support
From: Marcin Wojtas @ 2017-01-16 17:08 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, netdev
Cc: davem, linux, sebastian.hesselbarth, andrew, jason,
thomas.petazzoni, gregory.clement, mw, jaz, Simon Guinot
In-Reply-To: <1484586512-16412-1-git-send-email-mw@semihalf.com>
From: Simon Guinot <simon.guinot@sequanux.org>
Basing on xmit_more flag of the skb, TX descriptors can be concatenated
before flushing. This commit delay Tx descriptor flush if the queue is
running and if there is more skb's to send.
A maximum allowed number of descriptors for flushing at once due to
MVNETA_TXQ_UPDATE_REG(q) reqisters limitation, is 255. Because of that
a new macro was added (MVNETA_TXQ_DEC_SENT_MASK) in order to ensure that
concatenated amount of descriptor does not exceed that value.
Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
---
drivers/net/ethernet/marvell/mvneta.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 3607d8f..9624537 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -224,6 +224,7 @@
#define MVNETA_TXQ_SENT_THRESH_MASK(coal) ((coal) << 16)
#define MVNETA_TXQ_UPDATE_REG(q) (0x3c60 + ((q) << 2))
#define MVNETA_TXQ_DEC_SENT_SHIFT 16
+#define MVNETA_TXQ_DEC_SENT_MASK 0xff
#define MVNETA_TXQ_STATUS_REG(q) (0x3c40 + ((q) << 2))
#define MVNETA_TXQ_SENT_DESC_SHIFT 16
#define MVNETA_TXQ_SENT_DESC_MASK 0x3fff0000
@@ -525,6 +526,7 @@ struct mvneta_tx_queue {
* descriptor ring
*/
int count;
+ int pending;
int tx_stop_threshold;
int tx_wake_threshold;
@@ -818,8 +820,9 @@ static void mvneta_txq_pend_desc_add(struct mvneta_port *pp,
/* Only 255 descriptors can be added at once ; Assume caller
* process TX desriptors in quanta less than 256
*/
- val = pend_desc;
+ val = pend_desc + txq->pending;
mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+ txq->pending = 0;
}
/* Get pointer to next TX descriptor to be processed (send) by HW */
@@ -2399,11 +2402,15 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
txq->count += frags;
- mvneta_txq_pend_desc_add(pp, txq, frags);
-
if (txq->count >= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
+ if (!skb->xmit_more || netif_xmit_stopped(nq) ||
+ txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
+ mvneta_txq_pend_desc_add(pp, txq, frags);
+ else
+ txq->pending += frags;
+
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += len;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 net-next 2/2] net: mvneta: add BQL support
From: Marcin Wojtas @ 2017-01-16 17:08 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel, netdev
Cc: davem, linux, sebastian.hesselbarth, andrew, jason,
thomas.petazzoni, gregory.clement, mw, jaz
In-Reply-To: <1484586512-16412-1-git-send-email-mw@semihalf.com>
Tests showed that when whole bandwidth is consumed, the latency for
various kind of traffic can reach high values. With saturated
link (e.g. with iperf from target to host) simple ping could take
significant amount of time. BQL proved to improve this situation
when implemented in mvneta driver. Measurements of ping latency
for 3 link speeds:
Speed | Latency w/o BQL | Latency with BQL
10 | 7-14 ms | 3.5 ms
100 | 2-12 ms | 0.6 ms
1000 | often timeout | up to 2ms
Decreasing latency as above result in sligt performance cost - 4kpps
(-1.4%) when pushing 64B packets via two bridged interfaces of Armada 38x.
For 1500B packets in the same setup, the mpstat tool showed +8% of
CPU occupation (default affinity, second CPU idle). Even though this
cost seems reasonable to take, considering other improvements.
This commit adds byte queue limit mechanism for the mvneta driver.
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
---
drivers/net/ethernet/marvell/mvneta.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 9624537..6dcc951 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1759,8 +1759,10 @@ static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
/* Free tx queue skbuffs */
static void mvneta_txq_bufs_free(struct mvneta_port *pp,
- struct mvneta_tx_queue *txq, int num)
+ struct mvneta_tx_queue *txq, int num,
+ struct netdev_queue *nq)
{
+ unsigned int bytes_compl = 0, pkts_compl = 0;
int i;
for (i = 0; i < num; i++) {
@@ -1768,6 +1770,11 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
txq->txq_get_index;
struct sk_buff *skb = txq->tx_skb[txq->txq_get_index];
+ if (skb) {
+ bytes_compl += skb->len;
+ pkts_compl++;
+ }
+
mvneta_txq_inc_get(txq);
if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
@@ -1778,6 +1785,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
continue;
dev_kfree_skb_any(skb);
}
+
+ netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
}
/* Handle end of transmission */
@@ -1791,7 +1800,7 @@ static void mvneta_txq_done(struct mvneta_port *pp,
if (!tx_done)
return;
- mvneta_txq_bufs_free(pp, txq, tx_done);
+ mvneta_txq_bufs_free(pp, txq, tx_done, nq);
txq->count -= tx_done;
@@ -2401,6 +2410,8 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
+ netdev_tx_sent_queue(nq, len);
+
txq->count += frags;
if (txq->count >= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
@@ -2429,9 +2440,10 @@ static void mvneta_txq_done_force(struct mvneta_port *pp,
struct mvneta_tx_queue *txq)
{
+ struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
int tx_done = txq->count;
- mvneta_txq_bufs_free(pp, txq, tx_done);
+ mvneta_txq_bufs_free(pp, txq, tx_done, nq);
/* reset txq */
txq->count = 0;
@@ -2957,6 +2969,8 @@ static int mvneta_txq_init(struct mvneta_port *pp,
static void mvneta_txq_deinit(struct mvneta_port *pp,
struct mvneta_tx_queue *txq)
{
+ struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
+
kfree(txq->tx_skb);
if (txq->tso_hdrs)
@@ -2968,6 +2982,8 @@ static void mvneta_txq_deinit(struct mvneta_port *pp,
txq->size * MVNETA_DESC_ALIGNED_SIZE,
txq->descs, txq->descs_phys);
+ netdev_tx_reset_queue(nq);
+
txq->descs = NULL;
txq->last_desc = 0;
txq->next_desc_to_proc = 0;
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH 1/2] qed: Replace memset with eth_zero_addr
From: David Miller @ 2017-01-16 17:12 UTC (permalink / raw)
To: Yuval.Mintz; +Cc: mayhs11saini, netdev
In-Reply-To: <BL2PR07MB23069F2EFE839087FF63AC488D7D0@BL2PR07MB2306.namprd07.prod.outlook.com>
From: "Mintz, Yuval" <Yuval.Mintz@cavium.com>
Date: Mon, 16 Jan 2017 17:05:05 +0000
> Other than the fact these 2 patches change 2 different qed files,
That's what I was trying to hint at, the locations within the drivers
were the unique element.
> is there any significant difference between what each does?
> If not, why not simply do both in a single patch?
Also agreed.
^ permalink raw reply
* Re: [PATCH] net: marvell: skge: use new api ethtool_{get|set}_link_ksettings
From: Stephen Hemminger @ 2017-01-16 17:29 UTC (permalink / raw)
To: Philippe Reynes; +Cc: mlindner, davem, netdev, linux-kernel
In-Reply-To: <1484395708-4107-1-git-send-email-tremyfr@gmail.com>
On Sat, 14 Jan 2017 13:08:28 +0100
Philippe Reynes <tremyfr@gmail.com> wrote:
> The ethtool api {get|set}_settings is deprecated.
> We move this driver to new api {get|set}_link_ksettings.
>
> The callback set_link_ksettings no longer update the value
> of advertising, as the struct ethtool_link_ksettings is
> defined as const.
>
> Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Did you test this on real hardware?
^ permalink raw reply
* [PATCH net-next 0/9] mlx4 misc improvements
From: Tariq Toukan @ 2017-01-16 17:29 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Tariq Toukan
Hi Dave,
This patchset contains several improvements and cleanups
from the team to the mlx4 Eth and core drivers.
Series generated against net-next commit:
dbeaa8c2a4ba stmmac: indent an if statement
Thanks,
Tariq.
Alaa Hleihel (1):
net/mlx4_core: Get num_tc using netdev_get_num_tc
Ariel Levkovich (1):
net/mlx4_en: Adding support of turning off link autonegotiation via
ethtool
Daniel Jurgens (1):
net/mlx4_core: Set EQ affinity hint to local NUMA CPUs
Matan Barak (1):
net/mlx4_core: Add resource alloc/dealloc debugging
Shaker Daibes (3):
net/mlx4_en: Pass user MTU value to Firmware at set port command
net/mlx4_en: Check the enabling mtu flag in SET_PORT wrapper flow
net/mlx4_en: Check the enabling pptx/pprx flags in SET_PORT wrapper
flow
Tariq Toukan (1):
net/mlx4: Replace ENOSYS with better fitting error codes
Yishai Hadas (1):
net/mlx4_core: Device revision support
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 28 +++-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 +
drivers/net/ethernet/mellanox/mlx4/en_port.h | 1 -
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/fw.c | 6 +-
drivers/net/ethernet/mellanox/mlx4/main.c | 9 +-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 11 +-
drivers/net/ethernet/mellanox/mlx4/port.c | 170 ++++++++++++++++-----
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 51 ++++++-
include/linux/mlx4/device.h | 8 +-
10 files changed, 230 insertions(+), 64 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next 8/9] net/mlx4_en: Check the enabling mtu flag in SET_PORT wrapper flow
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Shaker Daibes, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Shaker Daibes <shakerd@mellanox.com>
Make sure MTU mask flag is set using new field upon set port
request. In addition, move this code into a helper function for better
code readability.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/port.c | 59 +++++++++++++++++++------------
1 file changed, 37 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index a7b0cdcb358a..57a10575a7aa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -52,6 +52,7 @@
#define MLX4_FLAG2_V_IGNORE_FCS_MASK BIT(1)
#define MLX4_FLAG2_V_USER_MTU_MASK BIT(5)
+#define MLX4_FLAG_V_MTU_MASK BIT(0)
#define MLX4_IGNORE_FCS_MASK 0x1
#define MLX4_TC_MAX_NUMBER 8
@@ -1241,6 +1242,38 @@ void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave)
}
static void
+mlx4_en_set_port_mtu(struct mlx4_dev *dev, int slave, int port,
+ struct mlx4_set_port_general_context *gen_context)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
+ struct mlx4_slave_state *slave_st = &master->slave_state[slave];
+ u16 mtu, prev_mtu;
+
+ /* Mtu is configured as the max USER_MTU among all
+ * the functions on the port.
+ */
+ mtu = be16_to_cpu(gen_context->mtu);
+ mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port] +
+ ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
+ prev_mtu = slave_st->mtu[port];
+ slave_st->mtu[port] = mtu;
+ if (mtu > master->max_mtu[port])
+ master->max_mtu[port] = mtu;
+ if (mtu < prev_mtu && prev_mtu == master->max_mtu[port]) {
+ int i;
+
+ slave_st->mtu[port] = mtu;
+ master->max_mtu[port] = mtu;
+ for (i = 0; i < dev->num_slaves; i++)
+ master->max_mtu[port] =
+ max_t(u16, master->max_mtu[port],
+ master->slave_state[i].mtu[port]);
+ }
+ gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
+}
+
+static void
mlx4_en_set_port_user_mtu(struct mlx4_dev *dev, int slave, int port,
struct mlx4_set_port_general_context *gen_context)
{
@@ -1278,7 +1311,6 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_port_info *port_info;
struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
- struct mlx4_slave_state *slave_st = &master->slave_state[slave];
struct mlx4_set_port_rqp_calc_context *qpn_context;
struct mlx4_set_port_general_context *gen_context;
struct mlx4_roce_gid_entry *gid_entry_tbl, *gid_entry_mbox, *gid_entry_mb1;
@@ -1289,7 +1321,6 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
int base;
u32 in_modifier;
u32 promisc;
- u16 mtu, prev_mtu;
int err;
int i, j;
int offset;
@@ -1332,26 +1363,10 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
break;
case MLX4_SET_PORT_GENERAL:
gen_context = inbox->buf;
- /* Mtu is configured as the max MTU among all the
- * the functions on the port. */
- mtu = be16_to_cpu(gen_context->mtu);
- mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port] +
- ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
- prev_mtu = slave_st->mtu[port];
- slave_st->mtu[port] = mtu;
- if (mtu > master->max_mtu[port])
- master->max_mtu[port] = mtu;
- if (mtu < prev_mtu && prev_mtu ==
- master->max_mtu[port]) {
- slave_st->mtu[port] = mtu;
- master->max_mtu[port] = mtu;
- for (i = 0; i < dev->num_slaves; i++) {
- master->max_mtu[port] =
- max(master->max_mtu[port],
- master->slave_state[i].mtu[port]);
- }
- }
- gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
+
+ if (gen_context->flags & MLX4_FLAG_V_MTU_MASK)
+ mlx4_en_set_port_mtu(dev, slave, port,
+ gen_context);
if (gen_context->flags2 & MLX4_FLAG2_V_USER_MTU_MASK)
mlx4_en_set_port_user_mtu(dev, slave, port,
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 7/9] net/mlx4_en: Pass user MTU value to Firmware at set port command
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Shaker Daibes, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Shaker Daibes <shakerd@mellanox.com>
When starting the port, driver will inform Firmware about the actual MTU
which does not include implicit headers, such as FCS or VLAN tags.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 +++
drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 7 ++-
drivers/net/ethernet/mellanox/mlx4/port.c | 71 ++++++++++++++++++++++++--
include/linux/mlx4/device.h | 1 +
5 files changed, 82 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 12c6686fa43b..4c855087e0af 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1695,6 +1695,14 @@ int mlx4_en_start_port(struct net_device *dev)
priv->port, err);
goto tx_err;
}
+
+ err = mlx4_SET_PORT_user_mtu(mdev->dev, priv->port, dev->mtu);
+ if (err) {
+ en_err(priv, "Failed to pass user MTU(%d) to Firmware for port %d, with error %d\n",
+ dev->mtu, priv->port, err);
+ goto tx_err;
+ }
+
/* Set default qp number */
err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port, priv->base_qpn, 0);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index de39a5db4a6f..3fe885ce1902 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2983,7 +2983,7 @@ static int mlx4_SET_PORT_phv_bit(struct mlx4_dev *dev, u8 port, u8 phv_bit)
return PTR_ERR(mailbox);
context = mailbox->buf;
- context->v_ignore_fcs |= SET_PORT_GEN_PHV_VALID;
+ context->flags2 |= SET_PORT_GEN_PHV_VALID;
if (phv_bit)
context->phv_en |= SET_PORT_GEN_PHV_EN;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 88ee7d8a5923..1132d76ddfdf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -487,6 +487,7 @@ struct mlx4_slave_state {
bool vst_qinq_supported;
u8 function;
dma_addr_t vhcr_dma;
+ u16 user_mtu[MLX4_MAX_PORTS + 1];
u16 mtu[MLX4_MAX_PORTS + 1];
__be32 ib_cap_mask[MLX4_MAX_PORTS + 1];
struct mlx4_slave_eqe eq[MLX4_MFUNC_MAX_EQES];
@@ -590,6 +591,7 @@ struct mlx4_mfunc_master_ctx {
struct mlx4_master_qp0_state qp0_state[MLX4_MAX_PORTS + 1];
int init_port_ref[MLX4_MAX_PORTS + 1];
u16 max_mtu[MLX4_MAX_PORTS + 1];
+ u16 max_user_mtu[MLX4_MAX_PORTS + 1];
u8 pptx;
u8 pprx;
int disable_mcast_ref[MLX4_MAX_PORTS + 1];
@@ -787,7 +789,7 @@ enum {
struct mlx4_set_port_general_context {
u16 reserved1;
- u8 v_ignore_fcs;
+ u8 flags2;
u8 flags;
union {
u8 ignore_fcs;
@@ -803,7 +805,8 @@ struct mlx4_set_port_general_context {
u16 reserved4;
u32 reserved5;
u8 phv_en;
- u8 reserved6[3];
+ u8 reserved6[5];
+ __be16 user_mtu;
};
struct mlx4_set_port_rqp_calc_context {
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index b656dd5772e5..a7b0cdcb358a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -50,7 +50,8 @@
#define MLX4_STATS_ERROR_COUNTERS_MASK 0x1ffc30ULL
#define MLX4_STATS_PORT_COUNTERS_MASK 0x1fe00000ULL
-#define MLX4_FLAG_V_IGNORE_FCS_MASK 0x2
+#define MLX4_FLAG2_V_IGNORE_FCS_MASK BIT(1)
+#define MLX4_FLAG2_V_USER_MTU_MASK BIT(5)
#define MLX4_IGNORE_FCS_MASK 0x1
#define MLX4_TC_MAX_NUMBER 8
@@ -1239,6 +1240,38 @@ void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave)
return;
}
+static void
+mlx4_en_set_port_user_mtu(struct mlx4_dev *dev, int slave, int port,
+ struct mlx4_set_port_general_context *gen_context)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
+ struct mlx4_slave_state *slave_st = &master->slave_state[slave];
+ u16 user_mtu, prev_user_mtu;
+
+ /* User Mtu is configured as the max USER_MTU among all
+ * the functions on the port.
+ */
+ user_mtu = be16_to_cpu(gen_context->user_mtu);
+ user_mtu = min_t(int, user_mtu, dev->caps.eth_mtu_cap[port]);
+ prev_user_mtu = slave_st->user_mtu[port];
+ slave_st->user_mtu[port] = user_mtu;
+ if (user_mtu > master->max_user_mtu[port])
+ master->max_user_mtu[port] = user_mtu;
+ if (user_mtu < prev_user_mtu &&
+ prev_user_mtu == master->max_user_mtu[port]) {
+ int i;
+
+ slave_st->user_mtu[port] = user_mtu;
+ master->max_user_mtu[port] = user_mtu;
+ for (i = 0; i < dev->num_slaves; i++)
+ master->max_user_mtu[port] =
+ max_t(u16, master->max_user_mtu[port],
+ master->slave_state[i].user_mtu[port]);
+ }
+ gen_context->user_mtu = cpu_to_be16(master->max_user_mtu[port]);
+}
+
static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
u8 op_mod, struct mlx4_cmd_mailbox *inbox)
{
@@ -1269,7 +1302,9 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
is_eth = op_mod;
port_info = &priv->port[port];
- /* Slaves cannot perform SET_PORT operations except changing MTU */
+ /* Slaves cannot perform SET_PORT operations,
+ * except for changing MTU and USER_MTU.
+ */
if (is_eth) {
if (slave != dev->caps.function &&
in_modifier != MLX4_SET_PORT_GENERAL &&
@@ -1316,8 +1351,12 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
master->slave_state[i].mtu[port]);
}
}
-
gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
+
+ if (gen_context->flags2 & MLX4_FLAG2_V_USER_MTU_MASK)
+ mlx4_en_set_port_user_mtu(dev, slave, port,
+ gen_context);
+
/* Slave cannot change Global Pause configuration */
if (slave != mlx4_master_func_num(dev) &&
((gen_context->pptx != master->pptx) ||
@@ -1608,6 +1647,30 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
}
EXPORT_SYMBOL(mlx4_SET_PORT_qpn_calc);
+int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_set_port_general_context *context;
+ u32 in_mod;
+ int err;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ context = mailbox->buf;
+ context->flags2 |= MLX4_FLAG2_V_USER_MTU_MASK;
+ context->user_mtu = cpu_to_be16(user_mtu);
+
+ in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, MLX4_SET_PORT_ETH_OPCODE,
+ MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_user_mtu);
+
int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, u8 ignore_fcs_value)
{
struct mlx4_cmd_mailbox *mailbox;
@@ -1619,7 +1682,7 @@ int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, u8 ignore_fcs_value)
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
context = mailbox->buf;
- context->v_ignore_fcs |= MLX4_FLAG_V_IGNORE_FCS_MASK;
+ context->flags2 |= MLX4_FLAG2_V_IGNORE_FCS_MASK;
if (ignore_fcs_value)
context->ignore_fcs |= MLX4_IGNORE_FCS_MASK;
else
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c3ac945b2759..7e66e4f62858 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1374,6 +1374,7 @@ int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx);
+int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu);
int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
u8 promisc);
int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 1/9] net/mlx4: Replace ENOSYS with better fitting error codes
From: Tariq Toukan @ 2017-01-16 17:29 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
Conform the following warning:
WARNING: ENOSYS means 'invalid syscall nr' and nothing else.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/main.c | 6 +++---
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +-
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d9c9f86a30df..63f5b0ab95d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1985,7 +1985,7 @@ static int mlx4_en_get_module_info(struct net_device *dev,
modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
break;
default:
- return -ENOSYS;
+ return -EINVAL;
}
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 84bab9f0732e..25b5b32e958f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -672,7 +672,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
MLX4_GET(field, outbox, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
func_cap->physical_port = field;
if (func_cap->physical_port != gen_or_port) {
- err = -ENOSYS;
+ err = -EINVAL;
goto out;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index bffa6f345f2f..6efd66b0b822 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -838,7 +838,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
*/
if (hca_param.global_caps) {
mlx4_err(dev, "Unknown hca global capabilities\n");
- return -ENOSYS;
+ return -EINVAL;
}
mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;
@@ -896,7 +896,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
PF_CONTEXT_BEHAVIOUR_MASK) {
mlx4_err(dev, "Unknown pf context behaviour %x known flags %x\n",
func_cap.pf_context_behaviour, PF_CONTEXT_BEHAVIOUR_MASK);
- return -ENOSYS;
+ return -EINVAL;
}
dev->caps.num_ports = func_cap.num_ports;
@@ -3492,7 +3492,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
mlx4_enable_msi_x(dev);
if ((mlx4_is_mfunc(dev)) &&
!(dev->flags & MLX4_FLAG_MSI_X)) {
- err = -ENOSYS;
+ err = -ENOTSUPP;
mlx4_err(dev, "INTx is not supported in multi-function mode, aborting\n");
goto err_free_eq;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 56185a0b827d..13cb47363db6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1396,7 +1396,7 @@ static int remove_ok(struct res_common *res, enum mlx4_resource type, int extra)
case RES_MTT:
return remove_mtt_ok((struct res_mtt *)res, extra);
case RES_MAC:
- return -ENOSYS;
+ return -ENOTSUPP;
case RES_EQ:
return remove_eq_ok((struct res_eq *)res);
case RES_COUNTER:
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 6/9] net/mlx4_en: Adding support of turning off link autonegotiation via ethtool
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Ariel Levkovich, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Ariel Levkovich <lariel@mellanox.com>
This feature will allow the user to disable auto negotiation
on the port for mlx4 devices while setting the speed is limited
to 1GbE speeds.
Other speeds will not be accepted in autoneg off mode.
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 24 +++++++++++++++++++-----
include/linux/mlx4/device.h | 7 ++++++-
2 files changed, 25 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 0ab644b6c2e6..5d11433fcc37 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -902,6 +902,7 @@ static __be32 speed_set_ptys_admin(struct mlx4_en_priv *priv, u32 speed,
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_ptys_reg ptys_reg;
__be32 proto_admin;
+ u8 cur_autoneg;
int ret;
u32 ptys_adv = ethtool2ptys_link_modes(
@@ -931,10 +932,21 @@ static __be32 speed_set_ptys_admin(struct mlx4_en_priv *priv, u32 speed,
return 0;
}
- proto_admin = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
- cpu_to_be32(ptys_adv) :
- speed_set_ptys_admin(priv, speed,
- ptys_reg.eth_proto_cap);
+ cur_autoneg = ptys_reg.flags & MLX4_PTYS_AN_DISABLE_ADMIN ?
+ AUTONEG_DISABLE : AUTONEG_ENABLE;
+
+ if (link_ksettings->base.autoneg == AUTONEG_DISABLE) {
+ proto_admin = speed_set_ptys_admin(priv, speed,
+ ptys_reg.eth_proto_cap);
+ if ((be32_to_cpu(proto_admin) &
+ (MLX4_PROT_MASK(MLX4_1000BASE_CX_SGMII) |
+ MLX4_PROT_MASK(MLX4_1000BASE_KX))) &&
+ (ptys_reg.flags & MLX4_PTYS_AN_DISABLE_CAP))
+ ptys_reg.flags |= MLX4_PTYS_AN_DISABLE_ADMIN;
+ } else {
+ proto_admin = cpu_to_be32(ptys_adv);
+ ptys_reg.flags &= ~MLX4_PTYS_AN_DISABLE_ADMIN;
+ }
proto_admin &= ptys_reg.eth_proto_cap;
if (!proto_admin) {
@@ -942,7 +954,9 @@ static __be32 speed_set_ptys_admin(struct mlx4_en_priv *priv, u32 speed,
return -EINVAL; /* nothing to change due to bad input */
}
- if (proto_admin == ptys_reg.eth_proto_admin)
+ if ((proto_admin == ptys_reg.eth_proto_admin) &&
+ ((ptys_reg.flags & MLX4_PTYS_AN_DISABLE_CAP) &&
+ (link_ksettings->base.autoneg == cur_autoneg)))
return 0; /* Nothing to change */
en_dbg(DRV, priv, "mlx4_ACCESS_PTYS_REG SET: ptys_reg.eth_proto_admin = 0x%x\n",
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6533c16e27ad..c3ac945b2759 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1539,8 +1539,13 @@ enum mlx4_ptys_proto {
MLX4_PTYS_EN = 1<<2,
};
+enum mlx4_ptys_flags {
+ MLX4_PTYS_AN_DISABLE_CAP = 1 << 5,
+ MLX4_PTYS_AN_DISABLE_ADMIN = 1 << 6,
+};
+
struct mlx4_ptys_reg {
- u8 resrvd1;
+ u8 flags;
u8 local_port;
u8 resrvd2;
u8 proto_mask;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 4/9] net/mlx4_core: Add resource alloc/dealloc debugging
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Matan Barak, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Matan Barak <matanb@mellanox.com>
In order to aid debugging of functions that take a resource but
don't put it, add the last function name that successfully grabbed
this resource.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 49 ++++++++++++++++++++--
1 file changed, 45 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 13cb47363db6..f7507d676c57 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -77,6 +77,7 @@ struct res_common {
int from_state;
int to_state;
int removing;
+ const char *func_name;
};
enum {
@@ -837,6 +838,36 @@ static int mpt_mask(struct mlx4_dev *dev)
return dev->caps.num_mpts - 1;
}
+static const char *mlx4_resource_type_to_str(enum mlx4_resource t)
+{
+ switch (t) {
+ case RES_QP:
+ return "QP";
+ case RES_CQ:
+ return "CQ";
+ case RES_SRQ:
+ return "SRQ";
+ case RES_XRCD:
+ return "XRCD";
+ case RES_MPT:
+ return "MPT";
+ case RES_MTT:
+ return "MTT";
+ case RES_MAC:
+ return "MAC";
+ case RES_VLAN:
+ return "VLAN";
+ case RES_COUNTER:
+ return "COUNTER";
+ case RES_FS_RULE:
+ return "FS_RULE";
+ case RES_EQ:
+ return "EQ";
+ default:
+ return "INVALID RESOURCE";
+ }
+}
+
static void *find_res(struct mlx4_dev *dev, u64 res_id,
enum mlx4_resource type)
{
@@ -846,9 +877,9 @@ static void *find_res(struct mlx4_dev *dev, u64 res_id,
res_id);
}
-static int get_res(struct mlx4_dev *dev, int slave, u64 res_id,
- enum mlx4_resource type,
- void *res)
+static int _get_res(struct mlx4_dev *dev, int slave, u64 res_id,
+ enum mlx4_resource type,
+ void *res, const char *func_name)
{
struct res_common *r;
int err = 0;
@@ -861,6 +892,10 @@ static int get_res(struct mlx4_dev *dev, int slave, u64 res_id,
}
if (r->state == RES_ANY_BUSY) {
+ mlx4_warn(dev,
+ "%s(%d) trying to get resource %llx of type %s, but it's already taken by %s\n",
+ func_name, slave, res_id, mlx4_resource_type_to_str(type),
+ r->func_name);
err = -EBUSY;
goto exit;
}
@@ -872,6 +907,7 @@ static int get_res(struct mlx4_dev *dev, int slave, u64 res_id,
r->from_state = r->state;
r->state = RES_ANY_BUSY;
+ r->func_name = func_name;
if (res)
*((struct res_common **)res) = r;
@@ -881,6 +917,9 @@ static int get_res(struct mlx4_dev *dev, int slave, u64 res_id,
return err;
}
+#define get_res(dev, slave, res_id, type, res) \
+ _get_res((dev), (slave), (res_id), (type), (res), __func__)
+
int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
enum mlx4_resource type,
u64 res_id, int *slave)
@@ -911,8 +950,10 @@ static void put_res(struct mlx4_dev *dev, int slave, u64 res_id,
spin_lock_irq(mlx4_tlock(dev));
r = find_res(dev, res_id, type);
- if (r)
+ if (r) {
r->state = r->from_state;
+ r->func_name = "";
+ }
spin_unlock_irq(mlx4_tlock(dev));
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 3/9] net/mlx4_core: Set EQ affinity hint to local NUMA CPUs
From: Tariq Toukan @ 2017-01-16 17:29 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Daniel Jurgens, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Daniel Jurgens <danielj@mellanox.com>
Use CPUs on the close NUMA when setting the EQ affinity hints.
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/main.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6efd66b0b822..058531bf7947 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2843,7 +2843,8 @@ static int mlx4_init_affinity_hint(struct mlx4_dev *dev, int port, int eqn)
if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- cpumask_set_cpu(requested_cpu, eq->affinity_mask);
+ cpumask_set_cpu(cpumask_local_spread(requested_cpu, dev->numa_node),
+ eq->affinity_mask);
return 0;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 9/9] net/mlx4_en: Check the enabling pptx/pprx flags in SET_PORT wrapper flow
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Shaker Daibes, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Shaker Daibes <shakerd@mellanox.com>
Make sure pptx/pprx mask flag is set using new fields upon set port
request. In addition, move this code into a helper function for better
code readability.
Signed-off-by: Shaker Daibes <shakerd@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_port.h | 1 -
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 4 ++-
drivers/net/ethernet/mellanox/mlx4/port.c | 42 ++++++++++++++++++----------
3 files changed, 31 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.h b/drivers/net/ethernet/mellanox/mlx4/en_port.h
index 040da4b16b1c..930f961fee42 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.h
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.h
@@ -35,7 +35,6 @@
#define _MLX4_EN_PORT_H_
-#define SET_PORT_GEN_ALL_VALID 0x7
#define SET_PORT_PROMISC_SHIFT 31
#define SET_PORT_MC_PROMISC_SHIFT 30
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 1132d76ddfdf..7a495090b0bc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -776,7 +776,9 @@ struct mlx4_vlan_table {
int max;
};
-#define SET_PORT_GEN_ALL_VALID 0x7
+#define SET_PORT_GEN_ALL_VALID (MLX4_FLAG_V_MTU_MASK | \
+ MLX4_FLAG_V_PPRX_MASK | \
+ MLX4_FLAG_V_PPTX_MASK)
#define SET_PORT_PROMISC_SHIFT 31
#define SET_PORT_MC_PROMISC_SHIFT 30
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 57a10575a7aa..5053c949148f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -53,6 +53,8 @@
#define MLX4_FLAG2_V_IGNORE_FCS_MASK BIT(1)
#define MLX4_FLAG2_V_USER_MTU_MASK BIT(5)
#define MLX4_FLAG_V_MTU_MASK BIT(0)
+#define MLX4_FLAG_V_PPRX_MASK BIT(1)
+#define MLX4_FLAG_V_PPTX_MASK BIT(2)
#define MLX4_IGNORE_FCS_MASK 0x1
#define MLX4_TC_MAX_NUMBER 8
@@ -1305,12 +1307,32 @@ void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave)
gen_context->user_mtu = cpu_to_be16(master->max_user_mtu[port]);
}
+static void
+mlx4_en_set_port_global_pause(struct mlx4_dev *dev, int slave,
+ struct mlx4_set_port_general_context *gen_context)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
+
+ /* Slave cannot change Global Pause configuration */
+ if (slave != mlx4_master_func_num(dev) &&
+ (gen_context->pptx != master->pptx ||
+ gen_context->pprx != master->pprx)) {
+ gen_context->pptx = master->pptx;
+ gen_context->pprx = master->pprx;
+ mlx4_warn(dev, "denying Global Pause change for slave:%d\n",
+ slave);
+ } else {
+ master->pptx = gen_context->pptx;
+ master->pprx = gen_context->pprx;
+ }
+}
+
static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
u8 op_mod, struct mlx4_cmd_mailbox *inbox)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_port_info *port_info;
- struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
struct mlx4_set_port_rqp_calc_context *qpn_context;
struct mlx4_set_port_general_context *gen_context;
struct mlx4_roce_gid_entry *gid_entry_tbl, *gid_entry_mbox, *gid_entry_mb1;
@@ -1372,19 +1394,11 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
mlx4_en_set_port_user_mtu(dev, slave, port,
gen_context);
- /* Slave cannot change Global Pause configuration */
- if (slave != mlx4_master_func_num(dev) &&
- ((gen_context->pptx != master->pptx) ||
- (gen_context->pprx != master->pprx))) {
- gen_context->pptx = master->pptx;
- gen_context->pprx = master->pprx;
- mlx4_warn(dev,
- "denying Global Pause change for slave:%d\n",
- slave);
- } else {
- master->pptx = gen_context->pptx;
- master->pprx = gen_context->pprx;
- }
+ if (gen_context->flags &
+ (MLX4_FLAG_V_PPRX_MASK || MLX4_FLAG_V_PPTX_MASK))
+ mlx4_en_set_port_global_pause(dev, slave,
+ gen_context);
+
break;
case MLX4_SET_PORT_GID_TABLE:
/* change to MULTIPLE entries: number of guest's gids
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 5/9] net/mlx4_core: Get num_tc using netdev_get_num_tc
From: Tariq Toukan @ 2017-01-16 17:30 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Alaa Hleihel, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Alaa Hleihel <alaa@mellanox.com>
Avoid reading num_tc directly from struct net_device, but use
the helper function netdev_get_num_tc.
Fixes: bc6a4744b827 ("net/mlx4_en: num cores tx rings for every UP")
Fixes: f5b6345ba8da ("net/mlx4_en: User prio mapping gets corrupted when changing number of channels")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 63f5b0ab95d6..0ab644b6c2e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1793,7 +1793,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
- if (dev->num_tc)
+ if (netdev_get_num_tc(dev))
mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num[TX]);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 5886ad78058f..3ed42199d3f1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -710,7 +710,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
u16 rings_p_up = priv->num_tx_rings_p_up;
u8 up = 0;
- if (dev->num_tc)
+ if (netdev_get_num_tc(dev))
return skb_tx_hash(dev, skb);
if (skb_vlan_tag_present(skb))
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 2/9] net/mlx4_core: Device revision support
From: Tariq Toukan @ 2017-01-16 17:29 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eran Ben Elisha, Yishai Hadas, Tariq Toukan
In-Reply-To: <1484587805-12666-1-git-send-email-tariqt@mellanox.com>
From: Yishai Hadas <yishaih@mellanox.com>
The device revision field returned by the NodeInfo MAD is incorrect
on ConnectX3 devices.
This patch is driver side handling to complete a FW fix added at 2.11.1172.
INIT_HCA - bit at offset 0x0C.12 is set to 1 so that FW will report
correct device revision.
Older FW versions won't be affected from turning on that bit,
no capability bit is needed.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 25b5b32e958f..de39a5db4a6f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1875,7 +1875,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
*((u8 *) mailbox->buf + INIT_HCA_VERSION_OFFSET) = INIT_HCA_VERSION;
*((u8 *) mailbox->buf + INIT_HCA_CACHELINE_SZ_OFFSET) =
- (ilog2(cache_line_size()) - 4) << 5;
+ ((ilog2(cache_line_size()) - 4) << 5) | (1 << 4);
#if defined(__LITTLE_ENDIAN)
*(inbox + INIT_HCA_FLAGS_OFFSET / 4) &= ~cpu_to_be32(1 << 1);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH] net: marvell: skge: use new api ethtool_{get|set}_link_ksettings
From: David Miller @ 2017-01-16 17:36 UTC (permalink / raw)
To: stephen; +Cc: tremyfr, mlindner, netdev, linux-kernel
In-Reply-To: <20170116092951.3b577463@xeon-e3>
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 16 Jan 2017 09:29:51 -0800
> On Sat, 14 Jan 2017 13:08:28 +0100
> Philippe Reynes <tremyfr@gmail.com> wrote:
>
>> The ethtool api {get|set}_settings is deprecated.
>> We move this driver to new api {get|set}_link_ksettings.
>>
>> The callback set_link_ksettings no longer update the value
>> of advertising, as the struct ethtool_link_ksettings is
>> defined as const.
>>
>> Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
>
> Did you test this on real hardware?
Philippe probably doesn't have physical access to most of the
drivers he is converting.
But, he is the only person working on converting all of the drivers,
and therefore when the change looks straightforward I am going to
reward his work and effort by applying his changes and hope there
isn't any fallout.
Those who really care can test his patches and give a Tested-by:
Thanks.
^ permalink raw reply
* Re: [PATCH 1/2] qed: Replace memset with eth_zero_addr
From: Shyam Saini @ 2017-01-16 17:40 UTC (permalink / raw)
To: David Miller; +Cc: Yuval.Mintz, Ariel.Elior, everest-linux-l2, netdev
In-Reply-To: <20170116.114606.1692928906878877115.davem@davemloft.net>
On Mon, Jan 16, 2017 at 11:46:06AM -0500, David Miller wrote:
> From: Shyam Saini <mayhs11saini@gmail.com>
> Date: Mon, 16 Jan 2017 14:54:35 +0530
>
> > On Sun, Jan 15, 2017 at 11:38:30PM -0500, David Miller wrote:
> >>
> >> Please do not ever submit two patches which have the same exact commit
> >> header line, as these two patches do.
> >>
> >> When someone looks into the shortlog of GIT history all they will see
> >> is "qed: Replace memset with eth_zero_addr" twice.
> >>
> >> This gives the reader no idea what might be different between those
> >> two changes.
> >>
> >> Therefore you must give unique a commit header text for each change,
> >> which communicates sufficiently what is different in each change.
> >
> > Thanks a lot for correcting me. I'll take care of this thing.
> >
> > I'm resending these two patches as
> > 1). qed: Replace memset with eth_zero_addr
> > 2). qed: Use eth_zero_addr
> >
> > I hope it resolves same commit header line conflict.
>
> You aren't understanding the point.
>
> Those two lines still say exactly the same thing.
>
> What is different about these two changes? The answer to that question
> must propagate into those lines of text.
I got your point now. As pointed by you and Mintz, I'll resend it
as a single patch.
I sincerely appreciate your efforts for making things clearer and
correcting me.
Thanks a lot,
Shyam
^ permalink raw reply
* Re: [PATCH net-next 3/3] net: ipv6: Add option to dump multipath routes via RTA_MULTIPATH attribute
From: David Ahern @ 2017-01-16 17:40 UTC (permalink / raw)
To: netdev; +Cc: ddutt, roopa
In-Reply-To: <1484510826-2723-4-git-send-email-dsa@cumulusnetworks.com>
upon further review ...
On 1/15/17 1:07 PM, David Ahern wrote:
> To maintain backwards compatibility, a user has to request the change
> in behavior. Unfortunately, adding a flag to the header similar to a
> previous patch does not work here as the netlink header for route dumps
> can be either rtgenmsg or ifinfomsg. sysctl is the other commonly used
> option for backwards compatibility but it is overly abused and is not
> really appropriate for this situation since each request should be able
> to specify the preference for the RTA_MULTIPATH attribute (e.g, one
> command may understand RTA_MULTIPATH for IPv6 while another may not).
The ancillary header is supposed to be struct rtmsg, so the change in behavior can be done by requiring the rtmsg struct and then passing the RTM_F_ALL_NEXTHOPS flag in rtm_flags. This makes the user api for delete requests and dumps consistent.
...
> @@ -422,9 +436,22 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
> cb->args[2] = (long)w;
> }
>
> + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
> + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
> +
> + if (nlmsg_parse(cb->nlh, hdrlen, nlattr, RTA_MAX, NULL) >= 0) {
> + /* existence of RTA_MULTIPATH attribute in dump
> + * request means user wants multipath routes
> + * returned using RTA_MULTIPATH attribute
> + */
> + if (nlattr[RTA_MULTIPATH])
> + flags |= RTM_F_ALL_NEXTHOPS;
> + }
> +
And the above becomes:
+ /* sadly, the size of the ancillary header can vary: the correct
+ * header is struct rtmsg as passed by libnl. iproute2 sends
+ * ifinfomsg [+ filter]. Technically, passing only rtgenmsg is
+ * sufficient since the header has not been parsed before. Luckily,
+ * the struct sizes sufficiently vary to detect the permutations.
+ * For the dump request to contain flags require rtmsg header.
+ */
+ if (nlmsg_len(cb->nlh) == sizeof(struct rtmsg)) {
+ struct rtmsg *rtm = nlmsg_data(cb->nlh);
+
+ flags = rtm->rtm_flags;
+ }
^ permalink raw reply
* Re: [PATCH net] mld: do not remove mld souce list info when set link down
From: David Miller @ 2017-01-16 17:45 UTC (permalink / raw)
To: liuhangbin; +Cc: netdev
In-Reply-To: <1484227177-7857-1-git-send-email-liuhangbin@gmail.com>
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 12 Jan 2017 21:19:37 +0800
> This is an IPv6 version of commit 24803f38a5c0 ("igmp: do not remove igmp
> souce list..."). In mld_del_delrec(), we will restore back all source filter
> info instead of flush them.
>
> Move mld_clear_delrec() from ipv6_mc_down() to ipv6_mc_destroy_dev() since
> we should not remove source list info when set link down. Remove
> igmp6_group_dropped() in ipv6_mc_destroy_dev() since we have called it in
> ipv6_mc_down().
>
> Also clear all source info after igmp6_group_dropped() instead of in it
> because ipv6_mc_down() will call igmp6_group_dropped().
>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH] net: marvell: skge: use new api ethtool_{get|set}_link_ksettings
From: Stephen Hemminger @ 2017-01-16 17:50 UTC (permalink / raw)
To: David Miller; +Cc: tremyfr, mlindner, netdev, linux-kernel
In-Reply-To: <20170116.123617.1891198374111644473.davem@davemloft.net>
On Mon, 16 Jan 2017 12:36:17 -0500 (EST)
David Miller <davem@davemloft.net> wrote:
> From: Stephen Hemminger <stephen@networkplumber.org>
> Date: Mon, 16 Jan 2017 09:29:51 -0800
>
> > On Sat, 14 Jan 2017 13:08:28 +0100
> > Philippe Reynes <tremyfr@gmail.com> wrote:
> >
> >> The ethtool api {get|set}_settings is deprecated.
> >> We move this driver to new api {get|set}_link_ksettings.
> >>
> >> The callback set_link_ksettings no longer update the value
> >> of advertising, as the struct ethtool_link_ksettings is
> >> defined as const.
> >>
> >> Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
> >
> > Did you test this on real hardware?
>
> Philippe probably doesn't have physical access to most of the
> drivers he is converting.
>
> But, he is the only person working on converting all of the drivers,
> and therefore when the change looks straightforward I am going to
> reward his work and effort by applying his changes and hope there
> isn't any fallout.
>
> Those who really care can test his patches and give a Tested-by:
>
> Thanks.
Yes, it looks mechanical and should be applied. There are lots of pieces of
old hardware that no developer is running, and if we required full test suite runs
on all drivers, then no refactoring would ever be possible.
My preference is to always add commit note that the patch was compile
tested only so that if someone has a problem with real hardware then they know
what to suspect.
^ permalink raw reply
* Re: [PATCH iproute2 1/1] utils: make hex2mem available to all users
From: Stephen Hemminger @ 2017-01-16 17:51 UTC (permalink / raw)
To: Jamal Hadi Salim; +Cc: netdev
In-Reply-To: <b7ca90ca-dd72-3f20-7509-7732742941a7@mojatatu.com>
On Sat, 14 Jan 2017 17:09:58 -0500
Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> Sorry, messed up Stephen's address. Resending..
>
> cheers,
> jamal
No problem. I get almost all patches only from patchwork anyway.
^ permalink raw reply
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