* Re: [RFC 02/10] IB/hfi-vnic: Virtual Network Interface Controller (VNIC) Bus driver
From: Andrew Lunn @ 2016-11-23 0:06 UTC (permalink / raw)
To: Vishwanathapura, Niranjana
Cc: Jason Gunthorpe, Doug Ledford, linux-rdma, netdev,
Dennis Dalessandro
In-Reply-To: <20161122194918.GA69241@knc-06.sc.intel.com>
On Tue, Nov 22, 2016 at 11:49:18AM -0800, Vishwanathapura, Niranjana wrote:
> Ok, I do understand Jason's point that we should probably not put
> this driver under drivers/infiniband/sw/.., as this driver is not a
> HCA.
> It is an ULP similar to ipoib, built on top of Omni-path
> irrespective of whether we register a hfi_vnic_bus or a direct
> custom interface with HFI1.
> This ULP will transmit and recieve Omni-path packets over the
> fabric, and is dependent on IB MAD interface and the HFI1 driver.
>
> Doug,
> Will it be acceptable if we put it under 'drivers/infiniband/ulp/hfi_vnic'?
How about turning this whole discussion around.
This is a network driver. So ask the network Maintainers where he
wants it. Send the patch to David Miller <davem@davemloft.net> and
netdev with the question, where does this code belong?
Andrew
^ permalink raw reply
* Re: [RFC 02/10] IB/hfi-vnic: Virtual Network Interface Controller (VNIC) Bus driver
From: ira.weiny @ 2016-11-23 0:05 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Vishwanathapura, Niranjana, Doug Ledford,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
Dennis Dalessandro
In-Reply-To: <20161122170407.GE3956-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
On Tue, Nov 22, 2016 at 10:04:07AM -0700, Jason Gunthorpe wrote:
> On Mon, Nov 21, 2016 at 05:53:04PM -0800, Vishwanathapura, Niranjana wrote:
> > There are many example drivers in kernel which are using bus_register() in
> > an initcall.
>
> There really are not, certainly not in major subsystems.
I see 2 drivers in the Block subsystem which do this:
19 5354 /nfs/site/home/iweiny/linux-stable/drivers/block/cciss.c <<cciss_init>>
err = bus_register(&cciss_bus_type);
20 6447 /nfs/site/home/iweiny/linux-stable/drivers/block/rbd.c <<rbd_sysfs_init>>
ret = bus_register(&rbd_bus_type);
2 drivers in the drm subsystem which do this:
29 1155 /nfs/site/home/iweiny/linux-stable/drivers/gpu/drm/drm_mipi_dsi.c <<mipi_dsi_bus_init>>
return bus_register(&mipi_dsi_bus_type);
30 242 /nfs/site/home/iweiny/linux-stable/drivers/gpu/host1x/dev.c <<tegra_host1x_init>>
err = bus_register(&host1x_bus_type);
And I think there are a couple others.
I'm not sure what these devices/buses do but they are registering their own bus
while being in another major subsystem. Is what we are doing really so
crazy/wrong?
>
> > We could add a custom Interface between HFI1 driver and hfi_vnic drivers
> > without involving a bus.
>
> hfi is already registering on the infiniband class, just use that.
>
I don't understand what you mean here?
The bus_register provides a really clean way for the hfi1 driver and hfi_vnic
driver to find each other. This includes being able to support hfi1 with or
without hfi_vnic being loaded. Note that without configuration from the "EM"
Ethernet Manager the hfi_vnic does not export a net device.
Why wouldn't we use this core kernel support?[*]
> > But using the existing bus model gave a lot of in-built flexibility in
> > decoupling devices from the drivers.
>
> If you want to have your own bus then you need your own hfi
> subsystem. drivers/infiniband is not a dumping ground..
>
We don't consider drivers/infiniband a "dumping ground". There is a
requirement on ib_mad from the hfi_vnic driver.
Ira
[*] As an aside why does the ib_core not use this methodology? It dawned on
me that this may be a better way to fix our module load problems. However, I
have not looked into details.
> Jason
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net-next] mlx4: reorganize struct mlx4_en_tx_ring
From: Eric Dumazet @ 2016-11-22 23:56 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Tariq Toukan
From: Eric Dumazet <edumazet@google.com>
Goal is to reorganize this critical structure to increase performance.
ndo_start_xmit() should only dirty one cache line, and access as few
cache lines as possible.
Add sp_ (Slow Path) prefix to fields that are not used in fast path,
to make clear what is going on.
After this patch pahole reports something much better, as all
ndo_start_xmit() needed fields are packed into two cache lines instead
of seven or eight
struct mlx4_en_tx_ring {
u32 last_nr_txbb; /* 0 0x4 */
u32 cons; /* 0x4 0x4 */
long unsigned int wake_queue; /* 0x8 0x8 */
struct netdev_queue * tx_queue; /* 0x10 0x8 */
u32 (*free_tx_desc)(struct mlx4_en_priv *, struct mlx4_en_tx_ring *, int, u8, u64, int); /* 0x18 0x8 */
struct mlx4_en_rx_ring * recycle_ring; /* 0x20 0x8 */
/* XXX 24 bytes hole, try to pack */
/* --- cacheline 1 boundary (64 bytes) --- */
u32 prod; /* 0x40 0x4 */
unsigned int tx_dropped; /* 0x44 0x4 */
long unsigned int bytes; /* 0x48 0x8 */
long unsigned int packets; /* 0x50 0x8 */
long unsigned int tx_csum; /* 0x58 0x8 */
long unsigned int tso_packets; /* 0x60 0x8 */
long unsigned int xmit_more; /* 0x68 0x8 */
struct mlx4_bf bf; /* 0x70 0x18 */
/* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
__be32 doorbell_qpn; /* 0x88 0x4 */
__be32 mr_key; /* 0x8c 0x4 */
u32 size; /* 0x90 0x4 */
u32 size_mask; /* 0x94 0x4 */
u32 full_size; /* 0x98 0x4 */
u32 buf_size; /* 0x9c 0x4 */
void * buf; /* 0xa0 0x8 */
struct mlx4_en_tx_info * tx_info; /* 0xa8 0x8 */
int qpn; /* 0xb0 0x4 */
u8 queue_index; /* 0xb4 0x1 */
bool bf_enabled; /* 0xb5 0x1 */
bool bf_alloced; /* 0xb6 0x1 */
u8 hwtstamp_tx_type; /* 0xb7 0x1 */
u8 * bounce_buf; /* 0xb8 0x8 */
/* --- cacheline 3 boundary (192 bytes) --- */
long unsigned int queue_stopped; /* 0xc0 0x8 */
struct mlx4_hwq_resources sp_wqres; /* 0xc8 0x58 */
/* --- cacheline 4 boundary (256 bytes) was 32 bytes ago --- */
struct mlx4_qp sp_qp; /* 0x120 0x30 */
/* --- cacheline 5 boundary (320 bytes) was 16 bytes ago --- */
struct mlx4_qp_context sp_context; /* 0x150 0xf8 */
/* --- cacheline 9 boundary (576 bytes) was 8 bytes ago --- */
cpumask_t sp_affinity_mask; /* 0x248 0x20 */
enum mlx4_qp_state sp_qp_state; /* 0x268 0x4 */
u16 sp_stride; /* 0x26c 0x2 */
u16 sp_cqn; /* 0x26e 0x2 */
/* size: 640, cachelines: 10, members: 36 */
/* sum members: 600, holes: 1, sum holes: 24 */
/* padding: 16 */
};
Instead of this silly placement :
struct mlx4_en_tx_ring {
u32 last_nr_txbb; /* 0 0x4 */
u32 cons; /* 0x4 0x4 */
long unsigned int wake_queue; /* 0x8 0x8 */
/* XXX 48 bytes hole, try to pack */
/* --- cacheline 1 boundary (64 bytes) --- */
u32 prod; /* 0x40 0x4 */
/* XXX 4 bytes hole, try to pack */
long unsigned int bytes; /* 0x48 0x8 */
long unsigned int packets; /* 0x50 0x8 */
long unsigned int tx_csum; /* 0x58 0x8 */
long unsigned int tso_packets; /* 0x60 0x8 */
long unsigned int xmit_more; /* 0x68 0x8 */
unsigned int tx_dropped; /* 0x70 0x4 */
/* XXX 4 bytes hole, try to pack */
struct mlx4_bf bf; /* 0x78 0x18 */
/* --- cacheline 2 boundary (128 bytes) was 16 bytes ago --- */
long unsigned int queue_stopped; /* 0x90 0x8 */
cpumask_t affinity_mask; /* 0x98 0x10 */
struct mlx4_qp qp; /* 0xa8 0x30 */
/* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
struct mlx4_hwq_resources wqres; /* 0xd8 0x58 */
/* --- cacheline 4 boundary (256 bytes) was 48 bytes ago --- */
u32 size; /* 0x130 0x4 */
u32 size_mask; /* 0x134 0x4 */
u16 stride; /* 0x138 0x2 */
/* XXX 2 bytes hole, try to pack */
u32 full_size; /* 0x13c 0x4 */
/* --- cacheline 5 boundary (320 bytes) --- */
u16 cqn; /* 0x140 0x2 */
/* XXX 2 bytes hole, try to pack */
u32 buf_size; /* 0x144 0x4 */
__be32 doorbell_qpn; /* 0x148 0x4 */
__be32 mr_key; /* 0x14c 0x4 */
void * buf; /* 0x150 0x8 */
struct mlx4_en_tx_info * tx_info; /* 0x158 0x8 */
struct mlx4_en_rx_ring * recycle_ring; /* 0x160 0x8 */
u32 (*free_tx_desc)(struct mlx4_en_priv *, struct mlx4_en_tx_ring *, int, u8, u64, int); /* 0x168 0x8 */
u8 * bounce_buf; /* 0x170 0x8 */
struct mlx4_qp_context context; /* 0x178 0xf8 */
/* --- cacheline 9 boundary (576 bytes) was 48 bytes ago --- */
int qpn; /* 0x270 0x4 */
enum mlx4_qp_state qp_state; /* 0x274 0x4 */
u8 queue_index; /* 0x278 0x1 */
bool bf_enabled; /* 0x279 0x1 */
bool bf_alloced; /* 0x27a 0x1 */
/* XXX 5 bytes hole, try to pack */
/* --- cacheline 10 boundary (640 bytes) --- */
struct netdev_queue * tx_queue; /* 0x280 0x8 */
int hwtstamp_tx_type; /* 0x288 0x4 */
/* size: 704, cachelines: 11, members: 36 */
/* sum members: 587, holes: 6, sum holes: 65 */
/* padding: 52 */
};
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 48 +++++++--------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 42 +++++++------
3 files changed, 48 insertions(+), 44 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 9a807e93c9fdd81e61e561208aa1480a244d0bdb..9018bb1b2e12142e048281a9d28ddf95e0023a61 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1305,7 +1305,7 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
continue;
en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
- i, tx_ring->qpn, tx_ring->cqn,
+ i, tx_ring->qpn, tx_ring->sp_cqn,
tx_ring->cons, tx_ring->prod);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 5de3cbe24f2bf467f9a8f7d499e131b6d2a1844c..4b597dca5c52d114344d638895275ed0d378bd96 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,7 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->size = size;
ring->size_mask = size - 1;
- ring->stride = stride;
+ ring->sp_stride = stride;
ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
tmp = size * sizeof(struct mlx4_en_tx_info);
@@ -90,22 +90,22 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
goto err_info;
}
}
- ring->buf_size = ALIGN(size * ring->stride, MLX4_EN_PAGE_SIZE);
+ ring->buf_size = ALIGN(size * ring->sp_stride, MLX4_EN_PAGE_SIZE);
/* Allocate HW buffers on provided NUMA node */
set_dev_node(&mdev->dev->persist->pdev->dev, node);
- err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
+ err = mlx4_alloc_hwq_res(mdev->dev, &ring->sp_wqres, ring->buf_size);
set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
if (err) {
en_err(priv, "Failed allocating hwq resources\n");
goto err_bounce;
}
- ring->buf = ring->wqres.buf.direct.buf;
+ ring->buf = ring->sp_wqres.buf.direct.buf;
en_dbg(DRV, priv, "Allocated TX ring (addr:%p) - buf:%p size:%d buf_size:%d dma:%llx\n",
ring, ring->buf, ring->size, ring->buf_size,
- (unsigned long long) ring->wqres.buf.direct.map);
+ (unsigned long long) ring->sp_wqres.buf.direct.map);
err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn,
MLX4_RESERVE_ETH_BF_QP);
@@ -114,12 +114,12 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
goto err_hwq_res;
}
- err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp, GFP_KERNEL);
+ err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->sp_qp, GFP_KERNEL);
if (err) {
en_err(priv, "Failed allocating qp %d\n", ring->qpn);
goto err_reserve;
}
- ring->qp.event = mlx4_en_sqp_event;
+ ring->sp_qp.event = mlx4_en_sqp_event;
err = mlx4_bf_alloc(mdev->dev, &ring->bf, node);
if (err) {
@@ -141,7 +141,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
if (queue_index < priv->num_tx_rings_p_up)
cpumask_set_cpu(cpumask_local_spread(queue_index,
priv->mdev->dev->numa_node),
- &ring->affinity_mask);
+ &ring->sp_affinity_mask);
*pring = ring;
return 0;
@@ -149,7 +149,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
err_reserve:
mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
err_hwq_res:
- mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
+ mlx4_free_hwq_res(mdev->dev, &ring->sp_wqres, ring->buf_size);
err_bounce:
kfree(ring->bounce_buf);
ring->bounce_buf = NULL;
@@ -171,10 +171,10 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
if (ring->bf_alloced)
mlx4_bf_free(mdev->dev, &ring->bf);
- mlx4_qp_remove(mdev->dev, &ring->qp);
- mlx4_qp_free(mdev->dev, &ring->qp);
+ mlx4_qp_remove(mdev->dev, &ring->sp_qp);
+ mlx4_qp_free(mdev->dev, &ring->sp_qp);
mlx4_qp_release_range(priv->mdev->dev, ring->qpn, 1);
- mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
+ mlx4_free_hwq_res(mdev->dev, &ring->sp_wqres, ring->buf_size);
kfree(ring->bounce_buf);
ring->bounce_buf = NULL;
kvfree(ring->tx_info);
@@ -190,7 +190,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_dev *mdev = priv->mdev;
int err;
- ring->cqn = cq;
+ ring->sp_cqn = cq;
ring->prod = 0;
ring->cons = 0xffffffff;
ring->last_nr_txbb = 1;
@@ -198,21 +198,21 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
memset(ring->buf, 0, ring->buf_size);
ring->free_tx_desc = mlx4_en_free_tx_desc;
- ring->qp_state = MLX4_QP_STATE_RST;
- ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
+ ring->sp_qp_state = MLX4_QP_STATE_RST;
+ ring->doorbell_qpn = cpu_to_be32(ring->sp_qp.qpn << 8);
ring->mr_key = cpu_to_be32(mdev->mr.key);
- mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
- ring->cqn, user_prio, &ring->context);
+ mlx4_en_fill_qp_context(priv, ring->size, ring->sp_stride, 1, 0, ring->qpn,
+ ring->sp_cqn, user_prio, &ring->sp_context);
if (ring->bf_alloced)
- ring->context.usr_page =
+ ring->sp_context.usr_page =
cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev,
ring->bf.uar->index));
- err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
- &ring->qp, &ring->qp_state);
- if (!cpumask_empty(&ring->affinity_mask))
- netif_set_xps_queue(priv->dev, &ring->affinity_mask,
+ err = mlx4_qp_to_ready(mdev->dev, &ring->sp_wqres.mtt, &ring->sp_context,
+ &ring->sp_qp, &ring->sp_qp_state);
+ if (!cpumask_empty(&ring->sp_affinity_mask))
+ netif_set_xps_queue(priv->dev, &ring->sp_affinity_mask,
ring->queue_index);
return err;
@@ -223,8 +223,8 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
{
struct mlx4_en_dev *mdev = priv->mdev;
- mlx4_qp_modify(mdev->dev, NULL, ring->qp_state,
- MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
+ mlx4_qp_modify(mdev->dev, NULL, ring->sp_qp_state,
+ MLX4_QP_STATE_RST, NULL, 0, 0, &ring->sp_qp);
}
static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index eff21651b67308a17fe3d60d236cd0b6800a3fd2..574bcbb1b38fc4758511d8f7bd17a87b0a507a73 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -281,46 +281,50 @@ struct mlx4_en_tx_ring {
u32 last_nr_txbb;
u32 cons;
unsigned long wake_queue;
+ struct netdev_queue *tx_queue;
+ u32 (*free_tx_desc)(struct mlx4_en_priv *priv,
+ struct mlx4_en_tx_ring *ring,
+ int index, u8 owner,
+ u64 timestamp, int napi_mode);
+ struct mlx4_en_rx_ring *recycle_ring;
/* cache line used and dirtied in mlx4_en_xmit() */
u32 prod ____cacheline_aligned_in_smp;
+ unsigned int tx_dropped;
unsigned long bytes;
unsigned long packets;
unsigned long tx_csum;
unsigned long tso_packets;
unsigned long xmit_more;
- unsigned int tx_dropped;
struct mlx4_bf bf;
- unsigned long queue_stopped;
/* Following part should be mostly read */
- cpumask_t affinity_mask;
- struct mlx4_qp qp;
- struct mlx4_hwq_resources wqres;
+ __be32 doorbell_qpn;
+ __be32 mr_key;
u32 size; /* number of TXBBs */
u32 size_mask;
- u16 stride;
u32 full_size;
- u16 cqn; /* index of port CQ associated with this ring */
u32 buf_size;
- __be32 doorbell_qpn;
- __be32 mr_key;
void *buf;
struct mlx4_en_tx_info *tx_info;
- struct mlx4_en_rx_ring *recycle_ring;
- u32 (*free_tx_desc)(struct mlx4_en_priv *priv,
- struct mlx4_en_tx_ring *ring,
- int index, u8 owner,
- u64 timestamp, int napi_mode);
- u8 *bounce_buf;
- struct mlx4_qp_context context;
int qpn;
- enum mlx4_qp_state qp_state;
u8 queue_index;
bool bf_enabled;
bool bf_alloced;
- struct netdev_queue *tx_queue;
- int hwtstamp_tx_type;
+ u8 hwtstamp_tx_type;
+ u8 *bounce_buf;
+
+ /* Not used in fast path
+ * Only queue_stopped might be used if BQL is not properly working.
+ */
+ unsigned long queue_stopped;
+ struct mlx4_hwq_resources sp_wqres;
+ struct mlx4_qp sp_qp;
+ struct mlx4_qp_context sp_context;
+ cpumask_t sp_affinity_mask;
+ enum mlx4_qp_state sp_qp_state;
+ u16 sp_stride;
+ u16 sp_cqn; /* index of port CQ associated with this ring */
} ____cacheline_aligned_in_smp;
struct mlx4_en_rx_desc {
^ permalink raw reply related
* [PATCH ethtool] ethtool: Fix the "advertise" parameter logic.
From: Michael Chan @ 2016-11-22 23:55 UTC (permalink / raw)
To: linville; +Cc: netdev
From: Michael Chan <mchan@broadcom.com>
The current code ignores the value of the advertise parameter. For example,
ethtool -s ethx advertise 0x1000
The full_advertising_wanted parameter of 0x1000 is not passed to the kernel.
The reason is that advertising_wanted is NULL in this case, and ethtool
will think that the user has given no advertisement input and so it will
proceed to pass all supported advertisement speeds to the kernel.
The older legacy ethtool with similar logic worked because
advertising_wanted was an integer and could take on -1 and 0. It would pass
the full_advertising_wanted value if advertising_wanted == -1.
This fix is to pass all supported advertisement speeds only when both
advertising_wanted == NULL && full_advertising_wanted == NULL.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
ethtool.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/ethtool.c b/ethtool.c
index 49ac94e..7715823 100644
--- a/ethtool.c
+++ b/ethtool.c
@@ -2971,7 +2971,8 @@ static int do_sset(struct cmd_context *ctx)
fprintf(stderr, "\n");
}
if (autoneg_wanted == AUTONEG_ENABLE &&
- advertising_wanted == NULL) {
+ advertising_wanted == NULL &&
+ full_advertising_wanted == NULL) {
unsigned int i;
/* Auto negotiation enabled, but with
--
1.8.4.5
^ permalink raw reply related
* Re: [RFC PATCH net-next] net: ethtool: add support for forward error correction modes
From: Casey Leedom @ 2016-11-22 23:41 UTC (permalink / raw)
To: netdev@vger.kernel.org
In-Reply-To: <DM5PR12MB1786073763933EAE09E36978C8B40@DM5PR12MB1786.namprd12.prod.outlook.com>
And by the way, we currently have two ethtool APIs which pump in an Auto-Negotiation indication -- set_link_ksettings() and set_pauseparam(). Now we're talking about adding a third, set_fecparam(). Are all of the calls to these three APIs supposed to agree on the concept of Auto-Negotiations? I.e. what's it mean if set_link_ksettings() gets called with link_ksettings->base.autoneg == AUTONEG_ENABLE but set_pauseparam() gets called with epause->autoneg == AUTONEG_DISABLE? And now adding set_fecparam() into the system with a similar ability to specify the state of Auto-Negotiation is even more confusing.
Casey
^ permalink raw reply
* [PATCH RFC v1] ethtool: implement helper to get flow_type value
From: Jacob Keller @ 2016-11-22 23:44 UTC (permalink / raw)
To: netdev, Intel Wired LAN; +Cc: Jacob Keller
Often a driver wants to store the flow type and thus it must mask the
extra fields. This is a task that could grow more complex as more flags
are added in the future. Add a helper function that masks the flags for
marking additional fields.
Modify drivers in drivers/net/ethernet that currently check for FLOW_EXT
and FLOW_MAC_EXT to use the helper. Currently this is only the mellanox
drivers.
I chose not to modify other drivers as I'm actually unsure whether we
should always mask the flow type even for drivers which don't recognize
the newer flags. On the one hand, today's drivers (generally)
automatically fail when a new flag is used because they won't mask it
and their checks against flow_type will not match. On the other hand, it
means another place that you have to update when you begin implementing
a flag.
An alternative is to have the driver store a set of flags that it knows
about, and then have ethtool core do the check for us to discard frames.
I haven't implemented this quite yet.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
---
I plan on using this helper when fixing the mask code for ntuple filters
in the Intel i40e driver. I wanted to see whether this approach was
acceptable, and whether we should implement additional checks. The
primary reason is that today's drivers are "fail closed" in that a new
flag type will probably fail on drivers due to checking for flow types
they recognize. Since drivers only remove the masked bits they recognize
this works. However, this gets cumbersome if new additional flags get
added in the future. I would like some sort of helper, but if we
encourage its use, and a new flag gets added, the helper will then
unforunately make the driver "fail open" in that a new flag will get
ignored as the driver won't know to return -EINVAL.
I think the right solution will be to add some sort of checks in core
ethtool which we can basically set the recognized flags in some way for
all drivers such that the ethtool core can drop requests for flows with
unknown flag types. I'm unsure how to implement this though.
Thoughts?
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 ++--
drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 6 +++---
include/uapi/linux/ethtool.h | 11 ++++++++---
3 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 487a58f9c192..d8f9839ce2a3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1270,7 +1270,7 @@ static int mlx4_en_validate_flow(struct net_device *dev,
return -EINVAL;
}
- switch (cmd->fs.flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+ switch (ethtool_get_flow_spec_type(cmd->fs.flow_type)) {
case TCP_V4_FLOW:
case UDP_V4_FLOW:
if (cmd->fs.m_u.tcp_ip4_spec.tos)
@@ -1493,7 +1493,7 @@ static int mlx4_en_ethtool_to_net_trans_rule(struct net_device *dev,
if (err)
return err;
- switch (cmd->fs.flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+ switch (ethtool_get_flow_spec_type(cmd->fs.flow_type)) {
case ETHER_FLOW:
spec_l2 = kzalloc(sizeof(*spec_l2), GFP_KERNEL);
if (!spec_l2)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 3691451c728c..066e6c5cf38b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -63,7 +63,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
int table_size;
int prio;
- switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+ switch (ethtool_get_flow_spec_type(fs->flow_type)) {
case TCP_V4_FLOW:
case UDP_V4_FLOW:
max_tuples = ETHTOOL_NUM_L3_L4_FTS;
@@ -147,7 +147,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
outer_headers);
void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
outer_headers);
- u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
+ u32 flow_type = ethtool_get_flow_spec_type(fs->flow_type);
struct ethtool_tcpip4_spec *l4_mask;
struct ethtool_tcpip4_spec *l4_val;
struct ethtool_usrip4_spec *l3_mask;
@@ -393,7 +393,7 @@ static int validate_flow(struct mlx5e_priv *priv,
fs->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
- switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
+ switch (ethtool_get_flow_spec_type(fs->flow_type)) {
case ETHER_FLOW:
eth_mask = &fs->m_u.ether_spec;
if (!is_zero_ether_addr(eth_mask->h_dest))
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f0db7788f887..e6d7d2aea56c 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -880,6 +880,14 @@ struct ethtool_rx_flow_spec {
__u32 location;
};
+/* Flag to enable additional fields in struct ethtool_rx_flow_spec */
+#define FLOW_EXT 0x80000000
+#define FLOW_MAC_EXT 0x40000000
+static inline __u32 ethtool_get_flow_spec_type(__u32 flow_type)
+{
+ return flow_type & (FLOW_EXT | FLOW_MAC_EXT);
+}
+
/* How rings are layed out when accessing virtual functions or
* offloaded queues is device specific. To allow users to do flow
* steering and specify these queues the ring cookie is partitioned
@@ -1579,9 +1587,6 @@ static inline int ethtool_validate_duplex(__u8 duplex)
#define IPV4_FLOW 0x10 /* hash only */
#define IPV6_FLOW 0x11 /* hash only */
#define ETHER_FLOW 0x12 /* spec only (ether_spec) */
-/* Flag to enable additional fields in struct ethtool_rx_flow_spec */
-#define FLOW_EXT 0x80000000
-#define FLOW_MAC_EXT 0x40000000
/* L3-L4 network traffic flow hash options */
#define RXH_L2DA (1 << 1)
--
2.11.0.rc2.152.g4d04e67
^ permalink raw reply related
* Re: [PATCH net-next] net/sched: cls_flower: verify root pointer before dereferncing it
From: John Fastabend @ 2016-11-22 23:36 UTC (permalink / raw)
To: Daniel Borkmann, Cong Wang, Jiri Pirko
Cc: Roi Dayan, David S. Miller, Linux Kernel Network Developers,
Jiri Pirko, Or Gerlitz, Cong Wang
In-Reply-To: <5834AD97.1020600@iogearbox.net>
On 16-11-22 12:41 PM, Daniel Borkmann wrote:
> On 11/22/2016 08:28 PM, Cong Wang wrote:
>> On Tue, Nov 22, 2016 at 8:11 AM, Jiri Pirko <jiri@resnulli.us> wrote:
>>> Tue, Nov 22, 2016 at 05:04:11PM CET, daniel@iogearbox.net wrote:
>>>> Hmm, I don't think we want to have such an additional test in fast
>>>> path for each and every classifier. Can we think of ways to avoid that?
>>>>
>>>> My question is, since we unlink individual instances from such
>>>> tp-internal
>>>> lists through RCU and release the instance through call_rcu() as
>>>> well as
>>>> the head (tp->root) via kfree_rcu() eventually, against what are we
>>>> protecting
>>>> setting RCU_INIT_POINTER(tp->root, NULL) in ->destroy() callback?
>>>> Something
>>>> not respecting grace period?
>>>
>>> If you call tp->ops->destroy in call_rcu, you don't have to set tp->root
>>> to null.
>
> But that's not really an answer to my question. ;)
>
>> We do need to respect the grace period if we touch the globally visible
>> data structure tp in tcf_destroy(). Therefore Roi's patch is not
>> fixing the
>> right place.
>
> I think there may be multiple issues actually.
>
> At the time we go into tc_classify(), from ingress as well as egress side,
> we're under RCU, but BH variant. In cls delete()/destroy() callbacks, we
> everywhere use call_rcu() and kfree_rcu(), same as for tcf_destroy() where
> we use kfree_rcu() on tp, although we iterate tps (and implicitly inner
> filters)
> via rcu_dereference_bh() from reader side. Is there a reason why we don't
> use call_rcu_bh() variant on destruction for all this instead?
I can't think of any if its all under _bh we can convert the call_rcu to
call_rcu_bh it just needs an audit.
>
> Just looking at cls_bpf and others, what protects
> RCU_INIT_POINTER(tp->root,
> NULL) against? The tp is unlinked in tc_ctl_tfilter() from the tp chain in
> tcf_destroy() cases. Still active readers under RCU BH can race against
> this
> (tp->root being NULL), as the commit identified. Only the get() callback
> checks
> for head against NULL, but both are serialized under rtnl, and the only
> place
> we call this is tc_ctl_tfilter(). Even if we create a new tp, head
> should not
> be NULL there, if it was assigned during the init() cb, but contains an
> empty
> list. (It's different for things like cls_cgroup, though.) So, I'm
> wondering
> if the RCU_INIT_POINTER(tp->root, NULL) can just be removed instead
> (unless I'm
> missing something obvious)?
Just took a look at this I think there are a couple possible solutions.
The easiest is likely to fix all the call sites so that 'tp' is unlinked
before calling the destroy() handlers AND not doing the NULL set. I only
see one such call site where destroy is called before unlinking at the
moment. This should enforce that after a grace period there is no path
to reach the classifiers because 'tp' is unlinked. Calling destroy
before unlinking 'tp' however could cause a small race between grace
period of 'tp' and grace period of the filter.
Another would be to only call the destroy path from the call_rcu path
of the 'tp' object so that destroy is only ever called after the object
is guaranteed to be unlinked from the tc_filter path.
I think both solutions would be fine.
Cong were you working on one of these? Or do you have another idea?
>
>> Also I don't know why you blame my commit, this problem should already
>> exist prior to my commit, probably date back to John's RCU patches.
>
> It seems so.
^ permalink raw reply
* Re: [net] 34fad54c25: kernel BUG at include/linux/skbuff.h:1935!
From: Linus Torvalds @ 2016-11-22 23:30 UTC (permalink / raw)
To: Eric Dumazet, Andre Noll
Cc: kernel test robot, David Miller, LKP, LKML, Alexei Starovoitov,
Willem de Bruijn, Alexander Duyck, Network Development
In-Reply-To: <CANn89i+B8F8thJRCdNPHA=BddTTxHCHz+xkvT_wuZ+b8osoTVQ@mail.gmail.com>
On Tue, Nov 22, 2016 at 2:28 PM, Eric Dumazet <edumazet@google.com> wrote:
>
> This is fixed by :
> https://git.kernel.org/cgit/linux/kernel/git/davem/net.git/commit/?id=c9b8af1330198ae241cd545e1f040019010d44d9
Thanks guys. This was one of the less esoteric-looking regressions, so
I'm happy to hear it's solved.
Linus
^ permalink raw reply
* Re: [RFC 02/10] IB/hfi-vnic: Virtual Network Interface Controller (VNIC) Bus driver
From: Christoph Lameter @ 2016-11-22 23:04 UTC (permalink / raw)
To: Vishwanathapura, Niranjana
Cc: Jason Gunthorpe, Doug Ledford, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, Dennis Dalessandro
In-Reply-To: <20161122194918.GA69241-wPcXA7LoDC+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
On Tue, 22 Nov 2016, Vishwanathapura, Niranjana wrote:
> Ok, I do understand Jason's point that we should probably not put this driver
> under drivers/infiniband/sw/.., as this driver is not a HCA.
> It is an ULP similar to ipoib, built on top of Omni-path irrespective of
> whether we register a hfi_vnic_bus or a direct custom interface with HFI1.
> This ULP will transmit and recieve Omni-path packets over the fabric, and is
> dependent on IB MAD interface and the HFI1 driver.
This is something that encapsulates IP (v4 right?) in something else.
Would belong into
linux/net/ipv4
You already have similar implementations there
See f.e. ipip.c, ip_tunnel.c and lots more (try
ls linux/net/ipv4/*tunnel*
)
If this is more like a device then it would belong into
linux/drivers/net/hfi or so (see also linux/drivers/net/ppp, plip,
loopback, etc etc)
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [net] 34fad54c25: kernel BUG at include/linux/skbuff.h:1935!
From: Andre Noll @ 2016-11-22 22:30 UTC (permalink / raw)
To: Linus Torvalds
Cc: kernel test robot, David Miller, Eric Dumazet, LKP, LKML,
Alexei Starovoitov, Willem de Bruijn, Alexander Duyck,
Network Development
In-Reply-To: <CA+55aFxV7Bq583QOdYauuo2jY9EkAmgnceBukrN27ArjzFszYg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 771 bytes --]
On Tue, Nov 22, 14:04, Linus Torvalds wrote
> what's the situation on this issue? The bisection looks a bit odd,
> but the commit in question does end up changing the key_control->thoff
> value for the failure case, so maybe that in turn ends up screwing up
> a later skb_pull.
>
> I'm not seeing anything that might fix this in the last networking
> pull, but I may have missed something.
I think that's the bug Eric has fixed today. See thread
[PATCH net] flow_dissect: call init_default_flow_dissectors() earlier
David has queued up the fix and will send it your way shortly.
Andre
--
Max Planck Institute for Developmental Biology
Spemannstraße 35, 72076 Tübingen, Germany. Phone: (+49) 7071 601 829
http://people.tuebingen.mpg.de/maan/
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 181 bytes --]
^ permalink raw reply
* Re: [net] 34fad54c25: kernel BUG at include/linux/skbuff.h:1935!
From: Eric Dumazet @ 2016-11-22 22:28 UTC (permalink / raw)
To: Linus Torvalds
Cc: kernel test robot, David Miller, LKP, LKML, Alexei Starovoitov,
Willem de Bruijn, Alexander Duyck, Network Development
In-Reply-To: <CA+55aFxV7Bq583QOdYauuo2jY9EkAmgnceBukrN27ArjzFszYg@mail.gmail.com>
On Tue, Nov 22, 2016 at 2:04 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
> David, Eric,
>
> what's the situation on this issue? The bisection looks a bit odd,
> but the commit in question does end up changing the key_control->thoff
> value for the failure case, so maybe that in turn ends up screwing up
> a later skb_pull.
>
> I'm not seeing anything that might fix this in the last networking
> pull, but I may have missed something.
>
> I also noticed that the kernel test robot had screwed up the
> participants list for some reason, and had
>
> "Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>, David S.
> Miller" <davem@davemloft.net>
>
> as one of the participants. So there's some odd commit parsing issue
> there somewhere. But Alexander seems to have seen this report despite
> that, it just never went anywhere that I can tell.
>
> Linus
>
This is fixed by :
https://git.kernel.org/cgit/linux/kernel/git/davem/net.git/commit/?id=c9b8af1330198ae241cd545e1f040019010d44d9
Thanks
^ permalink raw reply
* Re: [PATCH] net: dsa: mv88e6xxx: egress all frames
From: Vivien Didelot @ 2016-11-22 22:15 UTC (permalink / raw)
To: Andrew Lunn, Stefan Eichenberger; +Cc: Stefan Eichenberger, f.fainelli, netdev
In-Reply-To: <20161122190206.GE14947@lunn.ch>
Hi Andrew, Stefan,
Andrew Lunn <andrew@lunn.ch> writes:
> What you might find useful is
>
> https://github.com/vivien/linux.git 161b96bd7d16d21b0f046c935b70c3b2d277ccc2
>
> although it might need some changes for recent commits.
>
> With that, you can see deeper into the switches registers.
FYI, I have rebased it on top of the latest net-next (f9aa9dc7d2d0):
https://github.com/vivien/linux.git dsa/dev
Thanks,
Vivien
^ permalink raw reply
* Re: [PATCH 2/2] net: qcom/emac: add support for the Qualcomm Technologies QDF2400
From: Timur Tabi @ 2016-11-22 22:14 UTC (permalink / raw)
To: David Miller, alokc, netdev
In-Reply-To: <1479769102-27909-3-git-send-email-timur@codeaurora.org>
On 11/21/2016 04:58 PM, Timur Tabi wrote:
> The QDF2432 and the QDF2400 have slightly different internal PHYs,
> so there are some programming differences. Some of the registers in
> the QDF2400 have moved, and some registers require different values
> during initialization.
>
> Because of the differences, the internal PHY on the QDF2400 has a new
> ACPI HID, QCOM8072.
>
> Signed-off-by: Timur Tabi<timur@codeaurora.org>
There seems to be some disagreement internally as to whether a new HID
is the right approach. Please hold off on applying patch [2/2] for now.
Patch [1/2] can be applied, however, if it passes review.
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm
Technologies, Inc. Qualcomm Technologies, Inc. is a member of the
Code Aurora Forum, a Linux Foundation Collaborative Project.
^ permalink raw reply
* Re: [RFC net-next 0/3] net: bridge: Allow CPU port configuration
From: Jiri Pirko @ 2016-11-22 22:08 UTC (permalink / raw)
To: Andrew Lunn
Cc: Ido Schimmel, Florian Fainelli, netdev, davem, bridge, stephen,
vivien.didelot, jiri, idosch
In-Reply-To: <20161122174829.GD14947@lunn.ch>
Tue, Nov 22, 2016 at 06:48:29PM CET, andrew@lunn.ch wrote:
>Hi Ido
>
>> First of all, I want to be sure that when we say "CPU port", we're
>> talking about the same thing. In mlxsw, the CPU port is a pipe between
>> the device and the host, through which all packets trapped to the host
>> go through. So, when a packet is trapped, the driver reads its Rx
>> descriptor, checks through which port it ingressed, resolves its netdev,
>> sets skb->dev accordingly and injects it to the Rx path via
>> netif_receive_skb(). The CPU port itself isn't represented using a
>> netdev.
>
>With DSA, we have a real physical ethernet network interface for the
>'cpu' port. It connects to one of the ports of the switch. Frames on
Every port should be visible as a netdevice, including cpu port.
Would it make sence to have representors for those?
>this interface have an extra header, indicating which switch port it
>came from, and we do a similar resolving it to a slave netdev, strip
>of the header and injecting it into the receiver path via
>netif_receive_skb().
>
> Andrew
^ permalink raw reply
* Re: [net] 34fad54c25: kernel BUG at include/linux/skbuff.h:1935!
From: Linus Torvalds @ 2016-11-22 22:04 UTC (permalink / raw)
To: kernel test robot, David Miller, Eric Dumazet
Cc: LKP, LKML, Alexei Starovoitov, Willem de Bruijn, Alexander Duyck,
Network Development
In-Reply-To: <582b7c30.nXQXP2V4/6pFiYwt%xiaolong.ye@intel.com>
David, Eric,
what's the situation on this issue? The bisection looks a bit odd,
but the commit in question does end up changing the key_control->thoff
value for the failure case, so maybe that in turn ends up screwing up
a later skb_pull.
I'm not seeing anything that might fix this in the last networking
pull, but I may have missed something.
I also noticed that the kernel test robot had screwed up the
participants list for some reason, and had
"Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>, David S.
Miller" <davem@davemloft.net>
as one of the participants. So there's some odd commit parsing issue
there somewhere. But Alexander seems to have seen this report despite
that, it just never went anywhere that I can tell.
Linus
On Tue, Nov 15, 2016 at 1:20 PM, kernel test robot
<xiaolong.ye@intel.com> wrote:
>
> FYI, we noticed the following commit:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> commit 34fad54c2537f7c99d07375e50cb30aa3c23bd83 ("net: __skb_flow_dissect() must cap its return value")
>
> in testcase: pbzip2
> with following parameters:
>
> nr_threads: 25%
> blocksize: 900K
> cpufreq_governor: performance
>
>
>
> on test machine: 48 threads 2 sockets Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 64G memory
>
> caused below changes:
>
>
> +------------------------------------------------------------------+------------+------------+
> | | 79774d6bfa | 34fad54c25 |
> +------------------------------------------------------------------+------------+------------+
> | boot_successes | 0 | 2 |
> | boot_failures | 2 | 20 |
> | invoked_oom-killer:gfp_mask=0x | 2 | 2 |
> | Mem-Info | 2 | 2 |
> | Kernel_panic-not_syncing:Out_of_memory_and_no_killable_processes | 2 | 2 |
> | kernel_BUG_at_include/linux/skbuff.h | 0 | 16 |
> | invalid_opcode:#[##]SMP | 0 | 16 |
> | RIP:eth_type_trans | 0 | 16 |
> | Kernel_panic-not_syncing:Fatal_exception_in_interrupt | 0 | 15 |
> | calltrace:hub_event | 0 | 1 |
> | WARNING:at_fs/sysfs/dir.c:#sysfs_warn_dup | 0 | 2 |
> | calltrace:parport_pc_init | 0 | 2 |
> | calltrace:SyS_finit_module | 0 | 2 |
> | WARNING:at_lib/kobject.c:#kobject_add_internal | 0 | 2 |
> +------------------------------------------------------------------+------------+------------+
>
>
>
> [ 19.375251] IPv6: ADDRCONF(NETDEV_UP): eth1: link is not ready
> [ 19.388892] Sending DHCP requests .
> [ 19.388892] ------------[ cut here ]------------
> [ 19.388894] kernel BUG at include/linux/skbuff.h:1935!
> [ 19.388895] invalid opcode: 0000 [#1] SMP
> [ 19.388896] Modules linked in:
> [ 19.388897] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.9.0-rc3-00320-g34fad54 #1
> [ 19.388898] Hardware name: Intel Corporation S2600WP/S2600WP, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013
> [ 19.388899] task: ffffffff81e0e4c0 task.stack: ffffffff81e00000
> [ 19.388904] RIP: 0010:[<ffffffff81837c48>] [<ffffffff81837c48>] eth_type_trans+0xe8/0x140
> [ 19.388904] RSP: 0000:ffff88081e803db8 EFLAGS: 00010297
> [ 19.388905] RAX: 0000000000000152 RBX: ffff88080221f200 RCX: 0000000000001073
> [ 19.388905] RDX: ffff8808013afdc0 RSI: ffff880801114000 RDI: ffff880819407c00
> [ 19.388906] RBP: ffff88081e803e20 R08: ffff880801114000 R09: 0000000000000800
> [ 19.388907] R10: ffff8808013afec0 R11: ffffea003fd5a880 R12: ffff880819407c00
> [ 19.388907] R13: ffff881033408000 R14: ffffc9000843e000 R15: 0000000000000158
> [ 19.388908] FS: 0000000000000000(0000) GS:ffff88081e800000(0000) knlGS:0000000000000000
> [ 19.388909] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 19.388910] CR2: ffff88103ffff000 CR3: 0000000001e07000 CR4: 00000000001406f0
> [ 19.388910] Stack:
> [ 19.388912] ffffffff816905a7 ffffea003fd5a880 ffffea0000000008 ffff88080221f050
> [ 19.388913] ffff88080221f000 0000004000000160 ffffea003fd5a880 0000000000000000
> [ 19.388915] 0000000000000040 0000000000000000 ffff88080221f050 ffff88100d216000
> [ 19.388915] Call Trace:
> [ 19.388919] <IRQ>
> [ 19.388919] [<ffffffff816905a7>] ? igb_clean_rx_irq+0x6a7/0x7d0
> [ 19.388921] [<ffffffff81690a52>] igb_poll+0x382/0x700
> [ 19.388922] [<ffffffff81690a67>] ? igb_poll+0x397/0x700
> [ 19.388925] [<ffffffff8180f2d7>] net_rx_action+0x217/0x360
> [ 19.388928] [<ffffffff81957fb4>] __do_softirq+0x104/0x2ab
> [ 19.388931] [<ffffffff81086961>] irq_exit+0xf1/0x100
> [ 19.388932] [<ffffffff81957cf4>] do_IRQ+0x54/0xd0
> [ 19.388935] [<ffffffff81955b8c>] common_interrupt+0x8c/0x8c
> [ 19.388938] <EOI>
> [ 19.388938] [<ffffffff817c1d12>] ? cpuidle_enter_state+0x122/0x2e0
> [ 19.388939] [<ffffffff817c1f07>] cpuidle_enter+0x17/0x20
> [ 19.388942] [<ffffffff810c64c3>] call_cpuidle+0x23/0x40
> [ 19.388944] [<ffffffff810c66f4>] cpu_startup_entry+0x114/0x200
> [ 19.388946] [<ffffffff81947675>] rest_init+0x85/0x90
> [ 19.388950] [<ffffffff81ffbf5c>] start_kernel+0x407/0x414
> [ 19.388952] [<ffffffff81ffb120>] ? early_idt_handler_array+0x120/0x120
> [ 19.388953] [<ffffffff81ffb2d6>] x86_64_start_reservations+0x2a/0x2c
> [ 19.388955] [<ffffffff81ffb415>] x86_64_start_kernel+0x13d/0x14c
> [ 19.388968] Code: 00 04 00 00 c9 c3 48 33 86 70 03 00 00 48 c1 e0 10 48 85 c0 0f b6 87 90 00 00 00 75 28 83 e0 f8 83 c8 01 88 87 90 00 00 00 eb 82 <0f> 0b 0f b6 87 90 00 00 00 83 e0 f8 83 c8 03 88 87 90 00 00 00
> [ 19.388970] RIP [<ffffffff81837c48>] eth_type_trans+0xe8/0x140
> [ 19.388970] RSP <ffff88081e803db8>
> [ 19.388996] ---[ end trace 107996155a43a15c ]---
> [ 19.393422] Kernel panic - not syncing: Fatal exception in interrupt
>
>
> To reproduce:
>
> git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
> cd lkp-tests
> bin/lkp install job.yaml # job file is attached in this email
> bin/lkp run job.yaml
>
>
>
> Thanks,
> Kernel Test Robot
^ permalink raw reply
* [PATCH net-next v2] ethtool: Protect {get,set}_phy_tunable with PHY device mutex
From: Florian Fainelli @ 2016-11-22 21:55 UTC (permalink / raw)
To: netdev
Cc: davem, bcm-kernel-feedback-list, andrew, allan.nielsen,
raju.lakkaraju, vivien.didelot, Florian Fainelli
PHY drivers should be able to rely on the caller of {get,set}_tunable to
have acquired the PHY device mutex, in order to both serialize against
concurrent calls of these functions, but also against PHY state machine
changes. All ethtool PHY-level functions do this, except
{get,set}_tunable, so we make them consistent here as well.
We need to update the Microsemi PHY driver in the same commit to avoid
introducing either deadlocks, or lack of proper locking.
Fixes: 968ad9da7e0e ("ethtool: Implements ETHTOOL_PHY_GTUNABLE/ETHTOOL_PHY_STUNABLE")
Fixes: 310d9ad57ae0 ("net: phy: Add downshift get/set support in Microsemi PHYs driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
Changes in v2:
- also patch drivers/net/phy/mscc.c in the same commit
drivers/net/phy/mscc.c | 16 +++++-----------
net/core/ethtool.c | 4 ++++
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 92018ba6209e..7a3740c7bf6d 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -115,10 +115,9 @@ static int vsc85xx_downshift_get(struct phy_device *phydev, u8 *count)
int rc;
u16 reg_val;
- mutex_lock(&phydev->lock);
rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED);
if (rc != 0)
- goto out_unlock;
+ goto out;
reg_val = phy_read(phydev, MSCC_PHY_ACTIPHY_CNTL);
reg_val &= DOWNSHIFT_CNTL_MASK;
@@ -128,9 +127,7 @@ static int vsc85xx_downshift_get(struct phy_device *phydev, u8 *count)
*count = ((reg_val & ~DOWNSHIFT_EN) >> DOWNSHIFT_CNTL_POS) + 2;
rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD);
-out_unlock:
- mutex_unlock(&phydev->lock);
-
+out:
return rc;
}
@@ -150,23 +147,20 @@ static int vsc85xx_downshift_set(struct phy_device *phydev, u8 count)
count = (((count - 2) << DOWNSHIFT_CNTL_POS) | DOWNSHIFT_EN);
}
- mutex_lock(&phydev->lock);
rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED);
if (rc != 0)
- goto out_unlock;
+ goto out;
reg_val = phy_read(phydev, MSCC_PHY_ACTIPHY_CNTL);
reg_val &= ~(DOWNSHIFT_CNTL_MASK);
reg_val |= count;
rc = phy_write(phydev, MSCC_PHY_ACTIPHY_CNTL, reg_val);
if (rc != 0)
- goto out_unlock;
+ goto out;
rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD);
-out_unlock:
- mutex_unlock(&phydev->lock);
-
+out:
return rc;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index e9b4556751ff..0adb3bec5b5a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -2466,7 +2466,9 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
data = kmalloc(tuna.len, GFP_USER);
if (!data)
return -ENOMEM;
+ mutex_lock(&phydev->lock);
ret = phydev->drv->get_tunable(phydev, &tuna, data);
+ mutex_unlock(&phydev->lock);
if (ret)
goto out;
useraddr += sizeof(tuna);
@@ -2501,7 +2503,9 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
ret = -EFAULT;
if (copy_from_user(data, useraddr, tuna.len))
goto out;
+ mutex_lock(&phydev->lock);
ret = phydev->drv->set_tunable(phydev, &tuna, data);
+ mutex_unlock(&phydev->lock);
out:
kfree(data);
--
2.9.3
^ permalink raw reply related
* Re: [PATCH net-next] ethtool: Protect {get,set}_phy_tunable with PHY device mutex
From: Florian Fainelli @ 2016-11-22 21:02 UTC (permalink / raw)
To: netdev
Cc: davem, bcm-kernel-feedback-list, andrew, allan.nielsen,
raju.lakkaraju, vivien.didelot
In-Reply-To: <20161122201316.10830-1-f.fainelli@gmail.com>
On 11/22/2016 12:13 PM, Florian Fainelli wrote:
> PHY drivers should be able to rely on the caller of {get,set}_tunable to
> have acquired the PHY device mutex, in order to both serialize against
> concurrent calls of these functions, but also against PHY state machine
> changes. All ethtool PHY-level functions do this, except
> {get,set}_tunable, so we make them consistent here as well.
>
> Fixes: 968ad9da7e0e ("ethtool: Implements ETHTOOL_PHY_GTUNABLE/ETHTOOL_PHY_STUNABLE")
> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
David, please discard, this is going to create problems for the
Microsemi PHY driver since it also acquires phydev->lock. (patch has
been marked accordingly in patchwork.
Thanks!
--
Florian
^ permalink raw reply
* [PATCH net-next V2 7/7] net/mlx5e: Enforce min inline mode when offloading flows
From: Saeed Mahameed @ 2016-11-22 21:10 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Roi Dayan <roid@mellanox.com>
A flow should be offloaded only if the matches are
allowed according to min inline mode.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 46 +++++++++++++++++++++++--
1 file changed, 44 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4b99112..4d06fab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -279,8 +279,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
return 0;
}
-static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
- struct tc_cls_flower_offload *f)
+static int __parse_cls_flower(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct tc_cls_flower_offload *f,
+ u8 *min_inline)
{
void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
outer_headers);
@@ -289,6 +291,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
u16 addr_type = 0;
u8 ip_proto = 0;
+ *min_inline = MLX5_INLINE_MODE_L2;
+
if (f->dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_BASIC) |
@@ -362,6 +366,9 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
mask->ip_proto);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
key->ip_proto);
+
+ if (mask->ip_proto)
+ *min_inline = MLX5_INLINE_MODE_IP;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
@@ -432,6 +439,9 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
&key->dst, sizeof(key->dst));
+
+ if (mask->src || mask->dst)
+ *min_inline = MLX5_INLINE_MODE_IP;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
@@ -457,6 +467,10 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
&key->dst, sizeof(key->dst));
+
+ if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY ||
+ ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY)
+ *min_inline = MLX5_INLINE_MODE_IP;
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
@@ -497,11 +511,39 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
"Only UDP and TCP transport are supported\n");
return -EINVAL;
}
+
+ if (mask->src || mask->dst)
+ *min_inline = MLX5_INLINE_MODE_TCP_UDP;
}
return 0;
}
+static int parse_cls_flower(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct tc_cls_flower_offload *f)
+{
+ struct mlx5_core_dev *dev = priv->mdev;
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
+ u8 min_inline;
+ int err;
+
+ err = __parse_cls_flower(priv, spec, f, &min_inline);
+
+ if (!err && esw->mode == SRIOV_OFFLOADS &&
+ rep->vport != FDB_UPLINK_VPORT) {
+ if (min_inline > esw->offloads.inline_mode) {
+ netdev_warn(priv->netdev,
+ "Flow is not offloaded due to min inline setting, required %d actual %d\n",
+ min_inline, esw->offloads.inline_mode);
+ return -EOPNOTSUPP;
+ }
+ }
+
+ return err;
+}
+
static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
u32 *action, u32 *flow_tag)
{
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 6/7] net/mlx5: E-Switch, Add control for inline mode
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Roi Dayan <roid@mellanox.com>
Implement devlink show and set of HW inline-mode.
The supported modes: none, link, network, transport.
We currently support one mode for all vports so set is done on all vports.
When eswitch is first initialized the inline-mode is queried from the FW.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 +
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 +
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 141 +++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +
4 files changed, 148 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 9734ac8..d6807c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1798,6 +1798,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
esw->total_vports = total_vports;
esw->enabled_vports = 0;
esw->mode = SRIOV_NONE;
+ esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
dev->priv.eswitch = esw;
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 40482e8..cf1aa56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -200,6 +200,7 @@ struct mlx5_esw_offload {
struct mlx5_flow_group *vport_rx_group;
struct mlx5_eswitch_rep *vport_reps;
DECLARE_HASHTABLE(encap_tbl, 8);
+ u8 inline_mode;
};
struct mlx5_eswitch {
@@ -309,6 +310,9 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode);
int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
+int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode);
+int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
int vport_index,
struct mlx5_eswitch_rep *rep);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 731f286..5c01550 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -657,6 +657,14 @@ static int esw_offloads_start(struct mlx5_eswitch *esw)
if (err1)
esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err);
}
+ if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
+ if (mlx5_eswitch_inline_mode_get(esw,
+ num_vfs,
+ &esw->offloads.inline_mode)) {
+ esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
+ esw_warn(esw->dev, "Inline mode is different between vports\n");
+ }
+ }
return err;
}
@@ -771,6 +779,50 @@ static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
return 0;
}
+static int esw_inline_mode_from_devlink(u8 mode, u8 *mlx5_mode)
+{
+ switch (mode) {
+ case DEVLINK_ESWITCH_INLINE_MODE_NONE:
+ *mlx5_mode = MLX5_INLINE_MODE_NONE;
+ break;
+ case DEVLINK_ESWITCH_INLINE_MODE_LINK:
+ *mlx5_mode = MLX5_INLINE_MODE_L2;
+ break;
+ case DEVLINK_ESWITCH_INLINE_MODE_NETWORK:
+ *mlx5_mode = MLX5_INLINE_MODE_IP;
+ break;
+ case DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT:
+ *mlx5_mode = MLX5_INLINE_MODE_TCP_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
+{
+ switch (mlx5_mode) {
+ case MLX5_INLINE_MODE_NONE:
+ *mode = DEVLINK_ESWITCH_INLINE_MODE_NONE;
+ break;
+ case MLX5_INLINE_MODE_L2:
+ *mode = DEVLINK_ESWITCH_INLINE_MODE_LINK;
+ break;
+ case MLX5_INLINE_MODE_IP:
+ *mode = DEVLINK_ESWITCH_INLINE_MODE_NETWORK;
+ break;
+ case MLX5_INLINE_MODE_TCP_UDP:
+ *mode = DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
{
struct mlx5_core_dev *dev;
@@ -815,6 +867,95 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
return esw_mode_to_devlink(dev->priv.eswitch->mode, mode);
}
+int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+ int num_vports = esw->enabled_vports;
+ int err;
+ int vport;
+ u8 mlx5_mode;
+
+ if (!MLX5_CAP_GEN(dev, vport_group_manager))
+ return -EOPNOTSUPP;
+
+ if (esw->mode == SRIOV_NONE)
+ return -EOPNOTSUPP;
+
+ if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
+ MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+ return -EOPNOTSUPP;
+
+ err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
+ if (err)
+ goto out;
+
+ for (vport = 1; vport < num_vports; vport++) {
+ err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
+ if (err) {
+ esw_warn(dev, "Failed to set min inline on vport %d\n",
+ vport);
+ goto revert_inline_mode;
+ }
+ }
+
+ esw->offloads.inline_mode = mlx5_mode;
+ return 0;
+
+revert_inline_mode:
+ while (--vport > 0)
+ mlx5_modify_nic_vport_min_inline(dev,
+ vport,
+ esw->offloads.inline_mode);
+out:
+ return err;
+}
+
+int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+
+ if (!MLX5_CAP_GEN(dev, vport_group_manager))
+ return -EOPNOTSUPP;
+
+ if (esw->mode == SRIOV_NONE)
+ return -EOPNOTSUPP;
+
+ if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
+ MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+ return -EOPNOTSUPP;
+
+ return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
+}
+
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
+{
+ struct mlx5_core_dev *dev = esw->dev;
+ int vport;
+ u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
+
+ if (!MLX5_CAP_GEN(dev, vport_group_manager))
+ return -EOPNOTSUPP;
+
+ if (esw->mode == SRIOV_NONE)
+ return -EOPNOTSUPP;
+
+ if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
+ MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+ return -EOPNOTSUPP;
+
+ for (vport = 1; vport <= nvfs; vport++) {
+ mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
+ if (vport > 1 && prev_mlx5_mode != mlx5_mode)
+ return -EINVAL;
+ prev_mlx5_mode = mlx5_mode;
+ }
+
+ *mode = mlx5_mode;
+ return 0;
+}
+
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
int vport_index,
struct mlx5_eswitch_rep *__rep)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f28df33..b440a16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1239,6 +1239,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
#ifdef CONFIG_MLX5_CORE_EN
.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
+ .eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
+ .eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get,
#endif
};
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 1/7] net: Add net-device param to the get offloaded stats ndo
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Some drivers would need to check few internal matters for
that. To be used in downstream mlx5 commit.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
include/linux/netdevice.h | 4 ++--
net/core/rtnetlink.c | 4 ++--
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4a1f9d5..e0d7d5a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -857,7 +857,7 @@ mlxsw_sp_port_get_sw_stats64(const struct net_device *dev,
return 0;
}
-static bool mlxsw_sp_port_has_offload_stats(int attr_id)
+static bool mlxsw_sp_port_has_offload_stats(const struct net_device *dev, int attr_id)
{
switch (attr_id) {
case IFLA_OFFLOAD_XSTATS_CPU_HIT:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e84800e..ae32a27 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -925,7 +925,7 @@ struct netdev_xdp {
* 3. Update dev->stats asynchronously and atomically, and define
* neither operation.
*
- * bool (*ndo_has_offload_stats)(int attr_id)
+ * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id)
* Return true if this device supports offload stats of this attr_id.
*
* int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev,
@@ -1165,7 +1165,7 @@ struct net_device_ops {
struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage);
- bool (*ndo_has_offload_stats)(int attr_id);
+ bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id);
int (*ndo_get_offload_stats)(int attr_id,
const struct net_device *dev,
void *attr_data);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index db313ec..f5a8d8a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3665,7 +3665,7 @@ static int rtnl_get_offload_stats(struct sk_buff *skb, struct net_device *dev,
if (!size)
continue;
- if (!dev->netdev_ops->ndo_has_offload_stats(attr_id))
+ if (!dev->netdev_ops->ndo_has_offload_stats(dev, attr_id))
continue;
attr = nla_reserve_64bit(skb, attr_id, size,
@@ -3706,7 +3706,7 @@ static int rtnl_get_offload_stats_size(const struct net_device *dev)
for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST;
attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) {
- if (!dev->netdev_ops->ndo_has_offload_stats(attr_id))
+ if (!dev->netdev_ops->ndo_has_offload_stats(dev, attr_id))
continue;
size = rtnl_get_offload_stats_attr_size(attr_id);
nla_size += nla_total_size_64bit(size);
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 5/7] net/mlx5: Enable to query min inline for a specific vport
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Roi Dayan <roid@mellanox.com>
Also move the inline capablities enum to a shared header vport.h
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 ------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
drivers/net/ethernet/mellanox/mlx5/core/vport.c | 14 ++++++++------
include/linux/mlx5/vport.h | 10 ++++++++--
4 files changed, 21 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ebf5dbc..a2b32ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -150,12 +150,6 @@ static inline int mlx5_max_log_rq_size(int wq_type)
}
}
-enum {
- MLX5E_INLINE_MODE_L2,
- MLX5E_INLINE_MODE_VPORT_CONTEXT,
- MLX5_INLINE_MODE_NOT_REQUIRED,
-};
-
struct mlx5e_tx_wqe {
struct mlx5_wqe_ctrl_seg ctrl;
struct mlx5_wqe_eth_seg eth;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8e8d809..19403d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -957,7 +957,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
sq->max_inline = param->max_inline;
sq->min_inline_mode =
- MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5E_INLINE_MODE_VPORT_CONTEXT ?
+ MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT ?
param->min_inline_mode : 0;
err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu));
@@ -3417,14 +3417,13 @@ static void mlx5e_query_min_inline(struct mlx5_core_dev *mdev,
u8 *min_inline_mode)
{
switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) {
- case MLX5E_INLINE_MODE_L2:
+ case MLX5_CAP_INLINE_MODE_L2:
*min_inline_mode = MLX5_INLINE_MODE_L2;
break;
- case MLX5E_INLINE_MODE_VPORT_CONTEXT:
- mlx5_query_nic_vport_min_inline(mdev,
- min_inline_mode);
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode);
break;
- case MLX5_INLINE_MODE_NOT_REQUIRED:
+ case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
*min_inline_mode = MLX5_INLINE_MODE_NONE;
break;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 525f17a..269e440 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -113,15 +113,17 @@ static int mlx5_modify_nic_vport_context(struct mlx5_core_dev *mdev, void *in,
return mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
}
-void mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
- u8 *min_inline_mode)
+int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
+ u16 vport, u8 *min_inline)
{
u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {0};
+ int err;
- mlx5_query_nic_vport_context(mdev, 0, out, sizeof(out));
-
- *min_inline_mode = MLX5_GET(query_nic_vport_context_out, out,
- nic_vport_context.min_wqe_inline_mode);
+ err = mlx5_query_nic_vport_context(mdev, vport, out, sizeof(out));
+ if (!err)
+ *min_inline = MLX5_GET(query_nic_vport_context_out, out,
+ nic_vport_context.min_wqe_inline_mode);
+ return err;
}
EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_min_inline);
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 451b0bd..ec35157 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -36,6 +36,12 @@
#include <linux/mlx5/driver.h>
#include <linux/mlx5/device.h>
+enum {
+ MLX5_CAP_INLINE_MODE_L2,
+ MLX5_CAP_INLINE_MODE_VPORT_CONTEXT,
+ MLX5_CAP_INLINE_MODE_NOT_REQUIRED,
+};
+
u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport);
u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
u16 vport);
@@ -43,8 +49,8 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
u16 vport, u8 state);
int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
u16 vport, u8 *addr);
-void mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
- u8 *min_inline);
+int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
+ u16 vport, u8 *min_inline);
int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
u16 vport, u8 min_inline);
int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 3/7] net/mlx5e: Support VF vport link state control for SRIOV switchdev mode
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Reflect the administative link changes done on the VF representor to the
VF e-switch vport. This means that doing ip link set down/up commands on
the VF rep will modify the e-switch vport state which in turn will make
proper VF drivers to set their carrier accordingly.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 33 ++++++++++++++++++++++--
1 file changed, 31 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e0d1a56..5e33f6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -236,6 +236,35 @@ void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
mlx5e_tc_init(priv);
}
+static int mlx5e_rep_open(struct net_device *dev)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ int err;
+
+ err = mlx5e_open(dev);
+ if (err)
+ return err;
+
+ err = mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP);
+ if (!err)
+ netif_carrier_on(dev);
+
+ return 0;
+}
+
+static int mlx5e_rep_close(struct net_device *dev)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+ (void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+
+ return mlx5e_close(dev);
+}
+
static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
char *buf, size_t len)
{
@@ -349,8 +378,8 @@ static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
};
static const struct net_device_ops mlx5e_netdev_ops_rep = {
- .ndo_open = mlx5e_open,
- .ndo_stop = mlx5e_close,
+ .ndo_open = mlx5e_rep_open,
+ .ndo_stop = mlx5e_rep_close,
.ndo_start_xmit = mlx5e_xmit,
.ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name,
.ndo_setup_tc = mlx5e_rep_ndo_setup_tc,
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 2/7] net/mlx5e: Support HW (offloaded) and SW counters for SRIOV switchdev mode
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Switchdev driver net-device port statistics should follow the model introduced
in commit a5ea31f57309 'Merge branch net-offloaded-stats'.
For VF reps we return the SRIOV eswitch vport stats as the usual ones and SW stats
if asked. For the PF, if we're in the switchdev mode, we return the uplink stats
and SW stats if asked, otherwise as before. The uplink stats are implemented using
the PPCNT 802_3 counters which are already being read/cached by the driver.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 9 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 31 +++---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 111 +++++++++++++++++++--
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 1 +
4 files changed, 128 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ac09767..ebf5dbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -874,6 +874,7 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+void mlx5e_update_hw_rep_counters(struct mlx5e_priv *priv);
int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
@@ -890,12 +891,16 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv);
int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
-struct rtnl_link_stats64 *
-mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
void mlx5e_add_vxlan_port(struct net_device *netdev,
struct udp_tunnel_info *ti);
void mlx5e_del_vxlan_port(struct net_device *netdev,
struct udp_tunnel_info *ti);
+int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
+ void *sp);
+bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
+
+bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
+bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv);
#endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6957608..8e8d809 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -470,16 +470,6 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
kfree(rq->mpwqe.info);
}
-static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
-{
- struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
-
- if (rep && rep->vport != FDB_UPLINK_VPORT)
- return true;
-
- return false;
-}
-
static int mlx5e_create_rq(struct mlx5e_channel *c,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
@@ -2664,7 +2654,7 @@ static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle,
return mlx5e_setup_tc(dev, tc->tc);
}
-struct rtnl_link_stats64 *
+static struct rtnl_link_stats64 *
mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
struct mlx5e_priv *priv = netdev_priv(dev);
@@ -2672,13 +2662,20 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
struct mlx5e_vport_stats *vstats = &priv->stats.vport;
struct mlx5e_pport_stats *pstats = &priv->stats.pport;
- stats->rx_packets = sstats->rx_packets;
- stats->rx_bytes = sstats->rx_bytes;
- stats->tx_packets = sstats->tx_packets;
- stats->tx_bytes = sstats->tx_bytes;
+ if (mlx5e_is_uplink_rep(priv)) {
+ stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
+ stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok);
+ stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
+ stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+ } else {
+ stats->rx_packets = sstats->rx_packets;
+ stats->rx_bytes = sstats->rx_bytes;
+ stats->tx_packets = sstats->tx_packets;
+ stats->tx_bytes = sstats->tx_bytes;
+ stats->tx_dropped = sstats->tx_queue_dropped;
+ }
stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
- stats->tx_dropped = sstats->tx_queue_dropped;
stats->rx_length_errors =
PPORT_802_3_GET(pstats, a_in_range_length_errors) +
@@ -3290,6 +3287,8 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = mlx5e_netpoll,
#endif
+ .ndo_has_offload_stats = mlx5e_has_offload_stats,
+ .ndo_get_offload_stats = mlx5e_get_offload_stats,
};
static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a84825d..e0d1a56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -72,7 +72,29 @@ static void mlx5e_rep_get_strings(struct net_device *dev,
}
}
-static void mlx5e_update_sw_rep_counters(struct mlx5e_priv *priv)
+static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
+ struct rtnl_link_stats64 *vport_stats;
+ struct ifla_vf_stats vf_stats;
+ int err;
+
+ err = mlx5_eswitch_get_vport_stats(esw, rep->vport, &vf_stats);
+ if (err) {
+ pr_warn("vport %d error %d reading stats\n", rep->vport, err);
+ return;
+ }
+
+ vport_stats = &priv->stats.vf_vport;
+ /* flip tx/rx as we are reporting the counters for the switch vport */
+ vport_stats->rx_packets = vf_stats.tx_packets;
+ vport_stats->rx_bytes = vf_stats.tx_bytes;
+ vport_stats->tx_packets = vf_stats.rx_packets;
+ vport_stats->tx_bytes = vf_stats.rx_bytes;
+}
+
+static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
{
struct mlx5e_sw_stats *s = &priv->stats.sw;
struct mlx5e_rq_stats *rq_stats;
@@ -95,6 +117,12 @@ static void mlx5e_update_sw_rep_counters(struct mlx5e_priv *priv)
}
}
+static void mlx5e_rep_update_stats(struct mlx5e_priv *priv)
+{
+ mlx5e_rep_update_sw_counters(priv);
+ mlx5e_rep_update_hw_counters(priv);
+}
+
static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
@@ -106,7 +134,7 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
mutex_lock(&priv->state_lock);
if (test_bit(MLX5E_STATE_OPENED, &priv->state))
- mlx5e_update_sw_rep_counters(priv);
+ mlx5e_rep_update_sw_counters(priv);
mutex_unlock(&priv->state_lock);
for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++)
@@ -245,6 +273,77 @@ static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle,
}
}
+bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+ if (rep && rep->vport == FDB_UPLINK_VPORT && esw->mode == SRIOV_OFFLOADS)
+ return true;
+
+ return false;
+}
+
+bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+
+ if (rep && rep->vport != FDB_UPLINK_VPORT)
+ return true;
+
+ return false;
+}
+
+bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ switch (attr_id) {
+ case IFLA_OFFLOAD_XSTATS_CPU_HIT:
+ if (mlx5e_is_vf_vport_rep(priv) || mlx5e_is_uplink_rep(priv))
+ return true;
+ }
+
+ return false;
+}
+
+static int
+mlx5e_get_sw_stats64(const struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5e_sw_stats *sstats = &priv->stats.sw;
+
+ stats->rx_packets = sstats->rx_packets;
+ stats->rx_bytes = sstats->rx_bytes;
+ stats->tx_packets = sstats->tx_packets;
+ stats->tx_bytes = sstats->tx_bytes;
+
+ stats->tx_dropped = sstats->tx_queue_dropped;
+
+ return 0;
+}
+
+int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
+ void *sp)
+{
+ switch (attr_id) {
+ case IFLA_OFFLOAD_XSTATS_CPU_HIT:
+ return mlx5e_get_sw_stats64(dev, sp);
+ }
+
+ return -EINVAL;
+}
+
+static struct rtnl_link_stats64 *
+mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
+ return stats;
+}
+
static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
.switchdev_port_attr_get = mlx5e_attr_get,
};
@@ -255,9 +354,9 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
.ndo_start_xmit = mlx5e_xmit,
.ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name,
.ndo_setup_tc = mlx5e_rep_ndo_setup_tc,
- .ndo_get_stats64 = mlx5e_get_stats,
- .ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
- .ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
+ .ndo_get_stats64 = mlx5e_rep_get_stats,
+ .ndo_has_offload_stats = mlx5e_has_offload_stats,
+ .ndo_get_offload_stats = mlx5e_get_offload_stats,
};
static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
@@ -407,7 +506,7 @@ static struct mlx5e_profile mlx5e_rep_profile = {
.cleanup_rx = mlx5e_cleanup_rep_rx,
.init_tx = mlx5e_init_rep_tx,
.cleanup_tx = mlx5e_cleanup_nic_tx,
- .update_stats = mlx5e_update_sw_rep_counters,
+ .update_stats = mlx5e_rep_update_stats,
.max_nch = mlx5e_get_rep_max_num_channels,
.max_tc = 1,
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 5da6a1c..f202f87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -407,6 +407,7 @@ struct mlx5e_stats {
struct mlx5e_vport_stats vport;
struct mlx5e_pport_stats pport;
struct mlx5e_pcie_stats pcie;
+ struct rtnl_link_stats64 vf_vport;
};
static const struct counter_desc mlx5e_pme_status_desc[] = {
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 4/7] devlink: Add E-Switch inline mode control
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
In-Reply-To: <1479849000-14902-1-git-send-email-saeedm@mellanox.com>
From: Roi Dayan <roid@mellanox.com>
Some HWs need the VF driver to put part of the packet headers on the
TX descriptor so the e-switch can do proper matching and steering.
The supported modes: none, link, network, transport.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/net/devlink.h | 2 ++
include/uapi/linux/devlink.h | 8 +++++
net/core/devlink.c | 70 ++++++++++++++++++++++++++++++++------------
3 files changed, 61 insertions(+), 19 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 211bd3c..d29e5fc 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -92,6 +92,8 @@ struct devlink_ops {
int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode);
int (*eswitch_mode_set)(struct devlink *devlink, u16 mode);
+ int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode);
+ int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode);
};
static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 915bfa7..9014c33 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -102,6 +102,13 @@ enum devlink_eswitch_mode {
DEVLINK_ESWITCH_MODE_SWITCHDEV,
};
+enum devlink_eswitch_inline_mode {
+ DEVLINK_ESWITCH_INLINE_MODE_NONE,
+ DEVLINK_ESWITCH_INLINE_MODE_LINK,
+ DEVLINK_ESWITCH_INLINE_MODE_NETWORK,
+ DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT,
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
@@ -133,6 +140,7 @@ enum devlink_attr {
DEVLINK_ATTR_SB_OCC_CUR, /* u32 */
DEVLINK_ATTR_SB_OCC_MAX, /* u32 */
DEVLINK_ATTR_ESWITCH_MODE, /* u16 */
+ DEVLINK_ATTR_ESWITCH_INLINE_MODE, /* u8 */
/* add new attributes above here, update the policy in devlink.c */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index c14f8b6..2b5bf9e 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1394,26 +1394,45 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
static int devlink_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
enum devlink_command cmd, u32 portid,
- u32 seq, int flags, u16 mode)
+ u32 seq, int flags)
{
+ const struct devlink_ops *ops = devlink->ops;
void *hdr;
+ int err = 0;
+ u16 mode;
+ u8 inline_mode;
hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
if (!hdr)
return -EMSGSIZE;
- if (devlink_nl_put_handle(msg, devlink))
- goto nla_put_failure;
+ err = devlink_nl_put_handle(msg, devlink);
+ if (err)
+ goto out;
- if (nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode))
- goto nla_put_failure;
+ err = ops->eswitch_mode_get(devlink, &mode);
+ if (err)
+ goto out;
+ err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode);
+ if (err)
+ goto out;
+
+ if (ops->eswitch_inline_mode_get) {
+ err = ops->eswitch_inline_mode_get(devlink, &inline_mode);
+ if (err)
+ goto out;
+ err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE,
+ inline_mode);
+ if (err)
+ goto out;
+ }
genlmsg_end(msg, hdr);
return 0;
-nla_put_failure:
+out:
genlmsg_cancel(msg, hdr);
- return -EMSGSIZE;
+ return err;
}
static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb,
@@ -1422,22 +1441,17 @@ static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb,
struct devlink *devlink = info->user_ptr[0];
const struct devlink_ops *ops = devlink->ops;
struct sk_buff *msg;
- u16 mode;
int err;
if (!ops || !ops->eswitch_mode_get)
return -EOPNOTSUPP;
- err = ops->eswitch_mode_get(devlink, &mode);
- if (err)
- return err;
-
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
return -ENOMEM;
err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET,
- info->snd_portid, info->snd_seq, 0, mode);
+ info->snd_portid, info->snd_seq, 0);
if (err) {
nlmsg_free(msg);
@@ -1453,15 +1467,32 @@ static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb,
struct devlink *devlink = info->user_ptr[0];
const struct devlink_ops *ops = devlink->ops;
u16 mode;
+ u8 inline_mode;
+ int err = 0;
- if (!info->attrs[DEVLINK_ATTR_ESWITCH_MODE])
- return -EINVAL;
+ if (!ops)
+ return -EOPNOTSUPP;
- mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+ if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) {
+ if (!ops->eswitch_mode_set)
+ return -EOPNOTSUPP;
+ mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
+ err = ops->eswitch_mode_set(devlink, mode);
+ if (err)
+ return err;
+ }
- if (ops && ops->eswitch_mode_set)
- return ops->eswitch_mode_set(devlink, mode);
- return -EOPNOTSUPP;
+ if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) {
+ if (!ops->eswitch_inline_mode_set)
+ return -EOPNOTSUPP;
+ inline_mode = nla_get_u8(
+ info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]);
+ err = ops->eswitch_inline_mode_set(devlink, inline_mode);
+ if (err)
+ return err;
+ }
+
+ return 0;
}
static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
@@ -1478,6 +1509,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
+ [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
};
static const struct genl_ops devlink_nl_ops[] = {
--
2.7.4
^ permalink raw reply related
* [PATCH net-next V2 0/7] Mellanox 100G mlx5 SRIOV switchdev update
From: Saeed Mahameed @ 2016-11-22 21:09 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Or Gerlitz, Roi Dayan, Saeed Mahameed
Hi Dave,
This series from Roi and Or further enhances the new SRIOV switchdev mode.
Roi's patches deal with allowing users to configure though devlink
the level of inline headers that the VF should be setting in order for
the eswitch HW to do proper matching. We also enforce that the matching
required for offloaded TC rules is aligned with that level on the PF driver.
Or's patches deals with allowing the user to control on the VF operational
link state through admin directives on the mlx5 VF rep link. Also in this series
is implementation of HW and SW counters for the mlx5 VF rep which is aligned
with the design set by commit a5ea31f57309 'Merge branch net-offloaded-stats'.
v1 --> v2:
* constified the net-device param of get offloaded stats ndo in mlxsw
(pointed by 0-day screaming on us...)
* added Or's Review-by tags for Roi's patches
This series was generated against commit
e796f49d826a ("net: ieee802154: constify ieee802154_ops structures")
Thanks,
Saeed.
Or Gerlitz (3):
net: Add net-device param to the get offloaded stats ndo
net/mlx5e: Support HW (offloaded) and SW counters for SRIOV switchdev
mode
net/mlx5e: Support VF vport link state control for SRIOV switchdev
mode
Roi Dayan (4):
devlink: Add E-Switch inline mode control
net/mlx5: Enable to query min inline for a specific vport
net/mlx5: E-Switch, Add control for inline mode
net/mlx5e: Enforce min inline mode when offloading flows
drivers/net/ethernet/mellanox/mlx5/core/en.h | 15 +--
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 42 +++---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 144 +++++++++++++++++++--
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 46 ++++++-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 +
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 +
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 141 ++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +
drivers/net/ethernet/mellanox/mlx5/core/vport.c | 14 +-
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
include/linux/mlx5/vport.h | 10 +-
include/linux/netdevice.h | 4 +-
include/net/devlink.h | 2 +
include/uapi/linux/devlink.h | 8 ++
net/core/devlink.c | 70 +++++++---
net/core/rtnetlink.c | 4 +-
17 files changed, 438 insertions(+), 72 deletions(-)
--
2.7.4
^ 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