* [PATCH net-next v2 2/3] mlxsw: core: Add the hottest thermal zone detection
From: Ido Schimmel @ 2019-06-24 10:32 UTC (permalink / raw)
To: netdev; +Cc: davem, jiri, vadimp, andrew, mlxsw, Ido Schimmel
In-Reply-To: <20190624103203.22090-1-idosch@idosch.org>
From: Vadim Pasternak <vadimp@mellanox.com>
When multiple sensors are mapped to the same cooling device, the
cooling device should be set according the worst sensor from the
sensors associated with this cooling device.
Provide the hottest thermal zone detection and enforce cooling device
to follow the temperature trends of the hottest zone only.
Prevent competition for the cooling device control from others zones,
by "stable trend" indication. A cooling device will not perform any
actions associated with a zone with a "stable trend".
When other thermal zone is detected as a hottest, a cooling device is
to be switched to following temperature trends of new hottest zone.
Thermal zone score is represented by 32 bits unsigned integer and
calculated according to the next formula:
For T < TZ<t><i>, where t from {normal trip = 0, high trip = 1, hot
trip = 2, critical = 3}:
TZ<i> score = (T + (TZ<t><i> - T) / 2) / (TZ<t><i> - T) * 256 ** j;
Highest thermal zone score s is set as MAX(TZ<i>score);
Following this formula, if TZ<i> is in trip point higher than TZ<k>,
the higher score is to be always assigned to TZ<i>.
For two thermal zones located at the same kind of trip point, the higher
score will be assigned to the zone which is closer to the next trip
point. Thus, the highest score will always be assigned objectively to
the hottest thermal zone.
All the thermal zones initially are to be configured with mode
"enabled" with the "step_wise" governor.
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
.../ethernet/mellanox/mlxsw/core_thermal.c | 75 +++++++++++++++----
1 file changed, 62 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 88f43ad2cc4f..504a34d240f7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -23,6 +23,7 @@
#define MLXSW_THERMAL_HYSTERESIS_TEMP 5000 /* 5C */
#define MLXSW_THERMAL_MODULE_TEMP_SHIFT (MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
#define MLXSW_THERMAL_ZONE_MAX_NAME 16
+#define MLXSW_THERMAL_TEMP_SCORE_MAX GENMASK(31, 0)
#define MLXSW_THERMAL_MAX_STATE 10
#define MLXSW_THERMAL_MAX_DUTY 255
/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
@@ -113,6 +114,8 @@ struct mlxsw_thermal {
struct mlxsw_thermal_module *tz_module_arr;
struct mlxsw_thermal_module *tz_gearbox_arr;
u8 tz_gearbox_num;
+ unsigned int tz_highest_score;
+ struct thermal_zone_device *tz_highest_dev;
};
static inline u8 mlxsw_state_to_duty(int state)
@@ -197,6 +200,34 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
return 0;
}
+static void mlxsw_thermal_tz_score_update(struct mlxsw_thermal *thermal,
+ struct thermal_zone_device *tzdev,
+ struct mlxsw_thermal_trip *trips,
+ int temp)
+{
+ struct mlxsw_thermal_trip *trip = trips;
+ unsigned int score, delta, i, shift = 1;
+
+ /* Calculate thermal zone score, if temperature is above the critical
+ * threshold score is set to MLXSW_THERMAL_TEMP_SCORE_MAX.
+ */
+ score = MLXSW_THERMAL_TEMP_SCORE_MAX;
+ for (i = MLXSW_THERMAL_TEMP_TRIP_NORM; i < MLXSW_THERMAL_NUM_TRIPS;
+ i++, trip++) {
+ if (temp < trip->temp) {
+ delta = DIV_ROUND_CLOSEST(temp, trip->temp - temp);
+ score = delta * shift;
+ break;
+ }
+ shift *= 256;
+ }
+
+ if (score > thermal->tz_highest_score) {
+ thermal->tz_highest_score = score;
+ thermal->tz_highest_dev = tzdev;
+ }
+}
+
static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
struct thermal_cooling_device *cdev)
{
@@ -292,6 +323,9 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
return err;
}
mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+ if (temp > 0)
+ mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
+ temp);
*p_temp = (int) temp;
return 0;
@@ -353,6 +387,22 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
return 0;
}
+static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
+ int trip, enum thermal_trend *trend)
+{
+ struct mlxsw_thermal_module *tz = tzdev->devdata;
+ struct mlxsw_thermal *thermal = tz->parent;
+
+ if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+ return -EINVAL;
+
+ if (tzdev == thermal->tz_highest_dev)
+ return 1;
+
+ *trend = THERMAL_TREND_STABLE;
+ return 0;
+}
+
static struct thermal_zone_device_ops mlxsw_thermal_ops = {
.bind = mlxsw_thermal_bind,
.unbind = mlxsw_thermal_unbind,
@@ -364,6 +414,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
.set_trip_temp = mlxsw_thermal_set_trip_temp,
.get_trip_hyst = mlxsw_thermal_get_trip_hyst,
.set_trip_hyst = mlxsw_thermal_set_trip_hyst,
+ .get_trend = mlxsw_thermal_trend_get,
};
static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
@@ -474,7 +525,9 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
return 0;
/* Update trip points. */
- mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+ err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+ if (!err)
+ mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
return 0;
}
@@ -539,10 +592,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
return 0;
}
-static struct thermal_zone_params mlxsw_thermal_module_params = {
- .governor_name = "user_space",
-};
-
static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
.bind = mlxsw_thermal_module_bind,
.unbind = mlxsw_thermal_module_unbind,
@@ -554,6 +603,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
.set_trip_temp = mlxsw_thermal_module_trip_temp_set,
.get_trip_hyst = mlxsw_thermal_module_trip_hyst_get,
.set_trip_hyst = mlxsw_thermal_module_trip_hyst_set,
+ .get_trend = mlxsw_thermal_trend_get,
};
static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -574,6 +624,8 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
return err;
mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+ if (temp > 0)
+ mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
*p_temp = (int) temp;
return 0;
@@ -590,10 +642,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
.set_trip_temp = mlxsw_thermal_module_trip_temp_set,
.get_trip_hyst = mlxsw_thermal_module_trip_hyst_get,
.set_trip_hyst = mlxsw_thermal_module_trip_hyst_set,
-};
-
-static struct thermal_zone_params mlxsw_thermal_gearbox_params = {
- .governor_name = "user_space",
+ .get_trend = mlxsw_thermal_trend_get,
};
static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
@@ -709,13 +758,13 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
MLXSW_THERMAL_TRIP_MASK,
module_tz,
&mlxsw_thermal_module_ops,
- &mlxsw_thermal_module_params,
- 0, 0);
+ NULL, 0, 0);
if (IS_ERR(module_tz->tzdev)) {
err = PTR_ERR(module_tz->tzdev);
return err;
}
+ module_tz->mode = THERMAL_DEVICE_ENABLED;
return 0;
}
@@ -833,11 +882,11 @@ mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz)
MLXSW_THERMAL_TRIP_MASK,
gearbox_tz,
&mlxsw_thermal_gearbox_ops,
- &mlxsw_thermal_gearbox_params,
- 0, 0);
+ NULL, 0, 0);
if (IS_ERR(gearbox_tz->tzdev))
return PTR_ERR(gearbox_tz->tzdev);
+ gearbox_tz->mode = THERMAL_DEVICE_ENABLED;
return 0;
}
--
2.20.1
^ permalink raw reply related
* [PATCH net-next v2 3/3] mlxsw: core: Add support for negative temperature readout
From: Ido Schimmel @ 2019-06-24 10:32 UTC (permalink / raw)
To: netdev; +Cc: davem, jiri, vadimp, andrew, mlxsw, Ido Schimmel
In-Reply-To: <20190624103203.22090-1-idosch@idosch.org>
From: Vadim Pasternak <vadimp@mellanox.com>
Extend macros MLXSW_REG_MTMP_TEMP_TO_MC() to allow support of negative
temperature readout, since chip and others thermal components are
capable of operating within the negative temperature.
With no such support negative temperature will be consider as very high
temperature and it will cause wrong readout and thermal shutdown.
For negative values 2`s complement is used.
Tested in chamber.
Example of chip ambient temperature readout with chamber temperature:
-10 Celsius:
temp1: -6.0C (highest = -5.0C)
-5 Celsius:
temp1: -1.0C (highest = -1.0C)
v2 (Andrew Lunn):
* Replace '%u' with '%d' in mlxsw_hwmon_module_temp_show()
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c | 14 ++++++--------
drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 14 +++++++-------
drivers/net/ethernet/mellanox/mlxsw/reg.h | 12 +++++++-----
3 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 056e3f55ae6c..5b00726c4346 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -52,8 +52,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp;
- int index;
+ int temp, index;
int err;
index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
@@ -65,7 +64,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
return err;
}
mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
- return sprintf(buf, "%u\n", temp);
+ return sprintf(buf, "%d\n", temp);
}
static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
@@ -76,8 +75,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp_max;
- int index;
+ int temp_max, index;
int err;
index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
@@ -89,7 +87,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
return err;
}
mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL);
- return sprintf(buf, "%u\n", temp_max);
+ return sprintf(buf, "%d\n", temp_max);
}
static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
@@ -215,8 +213,8 @@ static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp;
u8 module;
+ int temp;
int err;
module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
@@ -227,7 +225,7 @@ static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
return err;
mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
- return sprintf(buf, "%u\n", temp);
+ return sprintf(buf, "%d\n", temp);
}
static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 504a34d240f7..35a1dc89c28a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -312,7 +312,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
struct mlxsw_thermal *thermal = tzdev->devdata;
struct device *dev = thermal->bus_info->dev;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp;
+ int temp;
int err;
mlxsw_reg_mtmp_pack(mtmp_pl, 0, false, false);
@@ -327,7 +327,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
temp);
- *p_temp = (int) temp;
+ *p_temp = temp;
return 0;
}
@@ -503,7 +503,7 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
struct mlxsw_thermal *thermal = tz->parent;
struct device *dev = thermal->bus_info->dev;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp;
+ int temp;
int err;
/* Read module temperature. */
@@ -519,14 +519,14 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
return 0;
}
mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
- *p_temp = (int) temp;
+ *p_temp = temp;
if (!temp)
return 0;
/* Update trip points. */
err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
- if (!err)
+ if (!err && temp > 0)
mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
return 0;
@@ -612,8 +612,8 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
struct mlxsw_thermal_module *tz = tzdev->devdata;
struct mlxsw_thermal *thermal = tz->parent;
char mtmp_pl[MLXSW_REG_MTMP_LEN];
- unsigned int temp;
u16 index;
+ int temp;
int err;
index = MLXSW_REG_MTMP_GBOX_INDEX_MIN + tz->module;
@@ -627,7 +627,7 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
if (temp > 0)
mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
- *p_temp = (int) temp;
+ *p_temp = temp;
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 452f645fa040..e5f6bfd8a35a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -8050,7 +8050,10 @@ MLXSW_REG_DEFINE(mtmp, MLXSW_REG_MTMP_ID, MLXSW_REG_MTMP_LEN);
MLXSW_ITEM32(reg, mtmp, sensor_index, 0x00, 0, 12);
/* Convert to milli degrees Celsius */
-#define MLXSW_REG_MTMP_TEMP_TO_MC(val) (val * 125)
+#define MLXSW_REG_MTMP_TEMP_TO_MC(val) ({ typeof(val) v_ = (val); \
+ ((v_) >= 0) ? ((v_) * 125) : \
+ ((s16)((GENMASK(15, 0) + (v_) + 1) \
+ * 125)); })
/* reg_mtmp_temperature
* Temperature reading from the sensor. Reading is in 0.125 Celsius
@@ -8121,11 +8124,10 @@ static inline void mlxsw_reg_mtmp_pack(char *payload, u16 sensor_index,
MLXSW_REG_MTMP_THRESH_HI);
}
-static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp,
- unsigned int *p_max_temp,
- char *sensor_name)
+static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp,
+ int *p_max_temp, char *sensor_name)
{
- u16 temp;
+ s16 temp;
if (p_temp) {
temp = mlxsw_reg_mtmp_temperature_get(payload);
--
2.20.1
^ permalink raw reply related
* RE: [PATCH v4 2/5] net: macb: add support for sgmii MAC-PHY interface
From: Parshuram Raju Thombare @ 2019-06-24 10:32 UTC (permalink / raw)
To: Russell King - ARM Linux admin
Cc: andrew@lunn.ch, nicolas.ferre@microchip.com, davem@davemloft.net,
f.fainelli@gmail.com, netdev@vger.kernel.org,
hkallweit1@gmail.com, linux-kernel@vger.kernel.org,
Rafal Ciepiela, Anil Joy Varughese, Piotr Sroka
In-Reply-To: <20190624102224.6gudxxdaz43wrlcc@shell.armlinux.org.uk>
>> >Sorry, this reply doesn't answer my question. I'm not asking about
>> >bp->speed and bp->duplex. I'm asking:
>> >1) why you are initialising bp->phy_interface here
>> >2) you to consider the impact that has on the mac_config() implementation
>> > you are proposing
>> > because I think it's buggy.
>> bp->phy_interface is to store phy mode value from device tree. This is used
>later
>> to know what phy interface user has selected for PHY-MAC. Same is used
>> to configure MAC correctly and based on your suggestion code is
>> added to handle PHY dynamically changing phy interface, in which
>> case bp->phy_interface is also updated. Though it may not be what user
>> want,
>> if phy interface is totally decided by PHY and is anyway going to be different
>> from what user has selected in DT, initializing it here doesn't make sense.
>> But in case of PHY not changing phy_interface dynamically bp-
>>phy_interface need to be initialized with value from DT.
>When phylink_start() is called, you will receive a mac_config() call to
>configure the MAC for the initial operating settings, which will include
>the current PHY interface mode. This will initially be whatever
>interface mode was passed in to phylink_create().
Yes, and same bp->phy_interface is passed to phylink_create().
We need this to know what phy interface is selected by user.
Regards,
Parshuram Thombare
^ permalink raw reply
* RE: [EXT] Re: [PATCH v3 rdma-next 0/3] RDMA/qedr: Use the doorbell overflow recovery mechanism for RDMA
From: Michal Kalderon @ 2019-06-24 10:36 UTC (permalink / raw)
To: Jason Gunthorpe, Doug Ledford
Cc: Ariel Elior, linux-rdma@vger.kernel.org, davem@davemloft.net,
netdev@vger.kernel.org
In-Reply-To: <20190621195818.GY19891@ziepe.ca>
> From: Jason Gunthorpe <jgg@ziepe.ca>
> Sent: Friday, June 21, 2019 10:58 PM
>
> External Email
>
> ----------------------------------------------------------------------
> On Fri, Jun 21, 2019 at 07:49:39PM +0000, Michal Kalderon wrote:
> > > From: linux-rdma-owner@vger.kernel.org <linux-rdma-
> > > owner@vger.kernel.org> On Behalf Of Doug Ledford
> > >
> > > On Thu, 2019-06-13 at 11:38 +0300, Michal Kalderon wrote:
> > > > This patch series used the doorbell overflow recovery mechanism
> > > > introduced in commit 36907cd5cd72 ("qed: Add doorbell overflow
> > > > recovery mechanism") for rdma ( RoCE and iWARP )
> > > >
> > > > rdma-core pull request #493
> > > >
> > > > Changes from V2:
> > > > - Don't use long-lived kmap. Instead use user-trigger mmap for the
> > > > doorbell recovery entries.
> > > > - Modify dpi_addr to be denoted with __iomem and avoid redundant
> > > > casts
> > > >
> > > > Changes from V1:
> > > > - call kmap to map virtual address into kernel space
> > > > - modify db_rec_delete to be void
> > > > - remove some cpu_to_le16 that were added to previous patch which
> are
> > > > correct but not related to the overflow recovery mechanism. Will be
> > > > submitted as part of a different patch
> > > >
> > > >
> > > > Michal Kalderon (3):
> > > > qed*: Change dpi_addr to be denoted with __iomem
> > > > RDMA/qedr: Add doorbell overflow recovery support
> > > > RDMA/qedr: Add iWARP doorbell recovery support
> > > >
> > > > drivers/infiniband/hw/qedr/main.c | 2 +-
> > > > drivers/infiniband/hw/qedr/qedr.h | 27 +-
> > > > drivers/infiniband/hw/qedr/verbs.c | 387
> > > > ++++++++++++++++++++++++-----
> > > > drivers/net/ethernet/qlogic/qed/qed_rdma.c | 6 +-
> > > > include/linux/qed/qed_rdma_if.h | 2 +-
> > > > include/uapi/rdma/qedr-abi.h | 25 ++
> > > > 6 files changed, 378 insertions(+), 71 deletions(-)
> > > >
> > >
> > > Hi Michal,
> > >
> > > In patch 2 and 3 both, you still have quite a few casts to (u8 __iomem *).
> > > Why not just define the struct elements as u8 __iomem * instead of
> > > void __iomem * and avoid all the casts?
> > >
> > Hi Doug,
> >
> > Thanks for the review. The remaining casts are due to pointer
> > arithmetic and not variable assignments as before. Removing the cast
> > entirely will require quite a lot of changes in qed and in rdma-core which I
> would be happy to avoid at this time.
>
> In linux pointer math on a void * acts the same as a u8 so you should never
> need to cast a void * to a u8 just to do math?
>
Ok, thanks. Sent v4.
Michal
> Jason
^ permalink raw reply
* Re: WARNING: ODEBUG bug in netdev_freemem (2)
From: Dmitry Vyukov @ 2019-06-24 10:54 UTC (permalink / raw)
To: Thomas Gleixner
Cc: syzbot, Alexander Duyck, amritha.nambiar, Andy Shevchenko,
David Miller, Dmitry Torokhov, Florian Fainelli,
Greg Kroah-Hartman, Ido Schimmel, LKML, netdev, syzkaller-bugs,
tyhicks, wanghai26, yuehaibing
In-Reply-To: <alpine.DEB.2.21.1906241130100.32342@nanos.tec.linutronix.de>
On Mon, Jun 24, 2019 at 11:34 AM Thomas Gleixner <tglx@linutronix.de> wrote:
>
> On Mon, 24 Jun 2019, syzbot wrote:
>
> > Hello,
> >
> > syzbot found the following crash on:
> >
> > HEAD commit: fd6b99fa Merge branch 'akpm' (patches from Andrew)
> > git tree: upstream
> > console output: https://syzkaller.appspot.com/x/log.txt?x=144de256a00000
> > kernel config: https://syzkaller.appspot.com/x/.config?x=fa9f7e1b6a8bb586
> > dashboard link: https://syzkaller.appspot.com/bug?extid=c4521ac872a4ccc3afec
> > compiler: gcc (GCC) 9.0.0 20181231 (experimental)
> >
> > Unfortunately, I don't have any reproducer for this crash yet.
> >
> > IMPORTANT: if you fix the bug, please add the following tag to the commit:
> > Reported-by: syzbot+c4521ac872a4ccc3afec@syzkaller.appspotmail.com
> >
> > device hsr_slave_0 left promiscuous mode
> > team0 (unregistering): Port device team_slave_1 removed
> > team0 (unregistering): Port device team_slave_0 removed
> > bond0 (unregistering): Releasing backup interface bond_slave_1
> > bond0 (unregistering): Releasing backup interface bond_slave_0
> > bond0 (unregistering): Released all slaves
> > ------------[ cut here ]------------
> > ODEBUG: free active (active state 0) object type: timer_list hint:
> > delayed_work_timer_fn+0x0/0x90 arch/x86/include/asm/paravirt.h:767
>
> One of the cleaned up devices has left an active timer which belongs to a
> delayed work. That's all I can decode out of that splat. :(
Hi Thomas,
If ODEBUG would memorize full stack traces for object allocation
(using lib/stackdepot.c), it would make this splat actionable, right?
I've fixed https://bugzilla.kernel.org/show_bug.cgi?id=203969 for this.
^ permalink raw reply
* Re: [PATCH net-next 1/7] net: aquantia: replace internal driver version code with uts
From: Igor Russkikh @ 2019-06-24 11:02 UTC (permalink / raw)
To: Jakub Kicinski, Andrew Lunn
Cc: David S . Miller, netdev@vger.kernel.org, Jiri Pirko
In-Reply-To: <20190623204954.3aa09ded@cakuba>
>
>> Devlink has just gained something similar to ethtool -i. Maybe we
>> should get the devlink core to also report the kernel version?
>
> I don't think we have the driver version at all there, my usual
> inclination being to not duplicate information across APIs. Do we
> have non-hypothetical instances of users reporting ethtool -i without
> uname output? Admittedly I may work with above-average Linux-trained
> engineers :S Would it be okay to just get devlink user space to use
> uname() to get the info?
I work alot with field support engineering people, they have a 'NIC-centric'
view on a system and often assume NIC driver version is all that matters.
Therefore `ethtool -i` is often the only thing we get when debugging user issues.
Regards,
Igor
^ permalink raw reply
* Re: [PATCH 3/3] module: Properly propagate MODULE_STATE_COMING failure
From: Peter Zijlstra @ 2019-06-24 11:07 UTC (permalink / raw)
To: Jessica Yu, linux-kernel, jpoimboe, jikos, mbenes, pmladek, ast,
daniel, akpm
Cc: Martin KaFai Lau, Song Liu, Yonghong Song, netdev, bpf
In-Reply-To: <20190624092109.863781858@infradead.org>
On Mon, Jun 24, 2019 at 11:18:46AM +0200, Peter Zijlstra wrote:
> Now that notifiers got unbroken; use the proper interface to handle
> notifier errors and propagate them.
>
> There were already MODULE_STATE_COMING notifiers that failed; notably:
>
> - jump_label_module_notifier()
> - tracepoint_module_notify()
> - bpf_event_notify()
>
> By propagating this error, we fix those users.
>
> Cc: Jessica Yu <jeyu@kernel.org>
> Cc: Alexei Starovoitov <ast@kernel.org>
> Cc: Daniel Borkmann <daniel@iogearbox.net>
> Cc: Martin KaFai Lau <kafai@fb.com>
> Cc: Song Liu <songliubraving@fb.com>
> Cc: Yonghong Song <yhs@fb.com>
> Cc: linux-kernel@vger.kernel.org
> Cc: netdev@vger.kernel.org
> Cc: bpf@vger.kernel.org
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
> kernel/module.c | 7 ++++---
> 1 file changed, 4 insertions(+), 3 deletions(-)
>
> --- a/kernel/module.c
> +++ b/kernel/module.c
> @@ -3643,9 +3643,10 @@ static int prepare_coming_module(struct
> if (err)
> return err;
>
> - blocking_notifier_call_chain(&module_notify_list,
> - MODULE_STATE_COMING, mod);
> - return 0;
> + err = blocking_notifier_call_chain_error(&module_notify_list,
> + MODULE_STATE_COMING, MODULE_STATE_GOING, mod);
> +
> + return notifier_to_errno(err);
> }
Argh, I messed up that klp thing again :/
^ permalink raw reply
* Re: [PATCH net-next 2/7] net: aquantia: add documentation for the atlantic driver
From: Igor Russkikh @ 2019-06-24 11:17 UTC (permalink / raw)
To: Andrew Lunn; +Cc: David S . Miller, netdev@vger.kernel.org
In-Reply-To: <20190622151657.GC8497@lunn.ch>
>> + increase the MTU size. For example:
>> +
>> + ifconfig <ethX> mtu 16000 up
>
> ifconfig has been deprecated for many years. Please document the
> iproute2 command.
Thanks for review, Andrew, yep, will update that.
>> + supports-priv-flags: no
>
> Shouldn't there be 5.2-rc5 in here somewhere, given the first patch in
> this series?
Good catch )
>> + Disable GRO when routing/bridging
>> + ---------------------------------
>> + Due to a known kernel issue, GRO must be turned off when routing/bridging.
>> + It can be done with command:
>
> Is this a kernel issue, or a driver issue?
Hm, honestly I've just copy pasted that section from our old driver spec.
Checked this, for now I see that networking core by itself takes actions to
disable LRO/GRO on device when its not appropriate, for example when ip4
forwarding is enabled.
May be that was a case with older kernels. Will remove these LRO/GRO notices.
>> + To disable coalescing:
>> +
>> + ethtool -C <ethX> tx-usecs 0 rx-usecs 0 tx-max-frames 1 tx-max-frames 1
>
> Please put these before the module parameters. We should discourage
> the use of module parameters. Using ethtool is the correct way to do
> this.
Ok,
>
> grep SPDX drivers/net/ethernet/aquantia/atlantic/*.c
> drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c:// SPDX-License-Identifier: GPL-2.0-or-later
> drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_filters.c:// SPDX-License-Identifier: GPL-2.0-or-later
> drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_main.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_nic.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_ring.c:// SPDX-License-Identifier: GPL-2.0-only
> drivers/net/ethernet/aquantia/atlantic/aq_vec.c:// SPDX-License-Identifier: GPL-2.0-only
>
> You have a mix of 2 and 2+.
Thanks, will clean this up.
Regards,
Igor
^ permalink raw reply
* [PATCH] samples: bpf: make the use of xdp samples consistent
From: Daniel T. Lee @ 2019-06-24 11:20 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov; +Cc: netdev
Currently, each xdp samples are inconsistent in the use.
Most of the samples fetch the interface with it's name.
(ex. xdp1, xdp2skb, xdp_redirect, xdp_sample_pkts, etc.)
But only xdp_adjst_tail and xdp_tx_iptunnel fetch the interface with
ifindex by command argument.
This commit enables those two samples to fetch interface with it's name
without changing the original index interface fetching.
(<ifname|ifindex> fetching in the same way as xdp_sample_pkts_user.c does.)
Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
---
samples/bpf/xdp_adjust_tail_user.c | 12 ++++++++++--
samples/bpf/xdp_tx_iptunnel_user.c | 12 ++++++++++--
2 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index 586ff751aba9..a3596b617c4c 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -13,6 +13,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <net/if.h>
#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
@@ -69,7 +70,7 @@ static void usage(const char *cmd)
printf("Start a XDP prog which send ICMP \"packet too big\" \n"
"messages if ingress packet is bigger then MAX_SIZE bytes\n");
printf("Usage: %s [...]\n", cmd);
- printf(" -i <ifindex> Interface Index\n");
+ printf(" -i <ifname|ifindex> Interface\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -S use skb-mode\n");
printf(" -N enforce native mode\n");
@@ -102,7 +103,9 @@ int main(int argc, char **argv)
switch (opt) {
case 'i':
- ifindex = atoi(optarg);
+ ifindex = if_nametoindex(optarg);
+ if (!ifindex)
+ ifindex = atoi(optarg);
break;
case 'T':
kill_after_s = atoi(optarg);
@@ -136,6 +139,11 @@ int main(int argc, char **argv)
return 1;
}
+ if (!ifindex) {
+ fprintf(stderr, "Invalid ifname\n");
+ return 1;
+ }
+
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
prog_load_attr.file = filename;
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 394896430712..dfb68582e243 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -9,6 +9,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <net/if.h>
#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
@@ -83,7 +84,7 @@ static void usage(const char *cmd)
"in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n"
"is used to select packets to encapsulate\n\n");
printf("Usage: %s [...]\n", cmd);
- printf(" -i <ifindex> Interface Index\n");
+ printf(" -i <ifname|ifindex> Interface\n");
printf(" -a <vip-service-address> IPv4 or IPv6\n");
printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
printf(" -s <source-ip> Used in the IPTunnel header\n");
@@ -181,7 +182,9 @@ int main(int argc, char **argv)
switch (opt) {
case 'i':
- ifindex = atoi(optarg);
+ ifindex = if_nametoindex(optarg);
+ if (!ifindex)
+ ifindex = atoi(optarg);
break;
case 'a':
vip.family = parse_ipstr(optarg, vip.daddr.v6);
@@ -253,6 +256,11 @@ int main(int argc, char **argv)
return 1;
}
+ if (!ifindex) {
+ fprintf(stderr, "Invalid ifname\n");
+ return 1;
+ }
+
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
prog_load_attr.file = filename;
--
2.17.1
^ permalink raw reply related
* Re: [PATCH net-next v2 1/3] mlxsw: core: Extend thermal core with per inter-connect device thermal zones
From: Jiri Pirko @ 2019-06-24 11:39 UTC (permalink / raw)
To: Ido Schimmel; +Cc: netdev, davem, jiri, vadimp, andrew, mlxsw, Ido Schimmel
In-Reply-To: <20190624103203.22090-2-idosch@idosch.org>
Mon, Jun 24, 2019 at 12:32:01PM CEST, idosch@idosch.org wrote:
>From: Vadim Pasternak <vadimp@mellanox.com>
>
>Add a dedicated thermal zone for each inter-connect device. The
>current temperature is obtained from inter-connect temperature sensor
>and the default trip points are set to the same values as default ASIC
>trip points. These settings could be changed from the user space.
>A cooling device (fan) is bound to all inter-connect devices.
>
>Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
>Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* [PATCH net-next v2] hinic: implement the statistical interface of ethtool
From: Xue Chaojing @ 2019-06-24 3:50 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, luoshaokai, cloud.wangxiaoyun, xuechaojing,
chiqijun, wulike1
This patch implement the statistical interface of ethtool, user can use
ethtool -S to show hinic statistics.
Signed-off-by: Xue Chaojing <xuechaojing@huawei.com>
---
.../net/ethernet/huawei/hinic/hinic_ethtool.c | 341 ++++++++++++++++++
.../net/ethernet/huawei/hinic/hinic_hw_dev.h | 8 +
.../net/ethernet/huawei/hinic/hinic_main.c | 5 +
.../net/ethernet/huawei/hinic/hinic_port.c | 66 ++++
.../net/ethernet/huawei/hinic/hinic_port.h | 174 +++++++++
drivers/net/ethernet/huawei/hinic/hinic_rx.c | 15 +-
drivers/net/ethernet/huawei/hinic/hinic_rx.h | 5 +-
drivers/net/ethernet/huawei/hinic/hinic_tx.c | 8 +
drivers/net/ethernet/huawei/hinic/hinic_tx.h | 1 +
9 files changed, 620 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index be28a9a7f033..8d98f37c88a8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -438,6 +438,344 @@ static u32 hinic_get_rxfh_indir_size(struct net_device *netdev)
return HINIC_RSS_INDIR_SIZE;
}
+#define ARRAY_LEN(arr) ((int)((int)sizeof(arr) / (int)sizeof(arr[0])))
+
+#define HINIC_NETDEV_STAT(_stat_item) { \
+ .name = #_stat_item, \
+ .size = FIELD_SIZEOF(struct rtnl_link_stats64, _stat_item), \
+ .offset = offsetof(struct rtnl_link_stats64, _stat_item) \
+}
+
+static struct hinic_stats hinic_netdev_stats[] = {
+ HINIC_NETDEV_STAT(rx_packets),
+ HINIC_NETDEV_STAT(tx_packets),
+ HINIC_NETDEV_STAT(rx_bytes),
+ HINIC_NETDEV_STAT(tx_bytes),
+ HINIC_NETDEV_STAT(rx_errors),
+ HINIC_NETDEV_STAT(tx_errors),
+ HINIC_NETDEV_STAT(rx_dropped),
+ HINIC_NETDEV_STAT(tx_dropped),
+ HINIC_NETDEV_STAT(multicast),
+ HINIC_NETDEV_STAT(collisions),
+ HINIC_NETDEV_STAT(rx_length_errors),
+ HINIC_NETDEV_STAT(rx_over_errors),
+ HINIC_NETDEV_STAT(rx_crc_errors),
+ HINIC_NETDEV_STAT(rx_frame_errors),
+ HINIC_NETDEV_STAT(rx_fifo_errors),
+ HINIC_NETDEV_STAT(rx_missed_errors),
+ HINIC_NETDEV_STAT(tx_aborted_errors),
+ HINIC_NETDEV_STAT(tx_carrier_errors),
+ HINIC_NETDEV_STAT(tx_fifo_errors),
+ HINIC_NETDEV_STAT(tx_heartbeat_errors),
+};
+
+#define HINIC_FUNC_STAT(_stat_item) { \
+ .name = #_stat_item, \
+ .size = FIELD_SIZEOF(struct hinic_vport_stats, _stat_item), \
+ .offset = offsetof(struct hinic_vport_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_function_stats[] = {
+ HINIC_FUNC_STAT(tx_unicast_pkts_vport),
+ HINIC_FUNC_STAT(tx_unicast_bytes_vport),
+ HINIC_FUNC_STAT(tx_multicast_pkts_vport),
+ HINIC_FUNC_STAT(tx_multicast_bytes_vport),
+ HINIC_FUNC_STAT(tx_broadcast_pkts_vport),
+ HINIC_FUNC_STAT(tx_broadcast_bytes_vport),
+
+ HINIC_FUNC_STAT(rx_unicast_pkts_vport),
+ HINIC_FUNC_STAT(rx_unicast_bytes_vport),
+ HINIC_FUNC_STAT(rx_multicast_pkts_vport),
+ HINIC_FUNC_STAT(rx_multicast_bytes_vport),
+ HINIC_FUNC_STAT(rx_broadcast_pkts_vport),
+ HINIC_FUNC_STAT(rx_broadcast_bytes_vport),
+
+ HINIC_FUNC_STAT(tx_discard_vport),
+ HINIC_FUNC_STAT(rx_discard_vport),
+ HINIC_FUNC_STAT(tx_err_vport),
+ HINIC_FUNC_STAT(rx_err_vport),
+};
+
+#define HINIC_PORT_STAT(_stat_item) { \
+ .name = #_stat_item, \
+ .size = FIELD_SIZEOF(struct hinic_phy_port_stats, _stat_item), \
+ .offset = offsetof(struct hinic_phy_port_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_port_stats[] = {
+ HINIC_PORT_STAT(mac_rx_total_pkt_num),
+ HINIC_PORT_STAT(mac_rx_total_oct_num),
+ HINIC_PORT_STAT(mac_rx_bad_pkt_num),
+ HINIC_PORT_STAT(mac_rx_bad_oct_num),
+ HINIC_PORT_STAT(mac_rx_good_pkt_num),
+ HINIC_PORT_STAT(mac_rx_good_oct_num),
+ HINIC_PORT_STAT(mac_rx_uni_pkt_num),
+ HINIC_PORT_STAT(mac_rx_multi_pkt_num),
+ HINIC_PORT_STAT(mac_rx_broad_pkt_num),
+ HINIC_PORT_STAT(mac_tx_total_pkt_num),
+ HINIC_PORT_STAT(mac_tx_total_oct_num),
+ HINIC_PORT_STAT(mac_tx_bad_pkt_num),
+ HINIC_PORT_STAT(mac_tx_bad_oct_num),
+ HINIC_PORT_STAT(mac_tx_good_pkt_num),
+ HINIC_PORT_STAT(mac_tx_good_oct_num),
+ HINIC_PORT_STAT(mac_tx_uni_pkt_num),
+ HINIC_PORT_STAT(mac_tx_multi_pkt_num),
+ HINIC_PORT_STAT(mac_tx_broad_pkt_num),
+ HINIC_PORT_STAT(mac_rx_fragment_pkt_num),
+ HINIC_PORT_STAT(mac_rx_undersize_pkt_num),
+ HINIC_PORT_STAT(mac_rx_undermin_pkt_num),
+ HINIC_PORT_STAT(mac_rx_64_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_65_127_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_128_255_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_256_511_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_512_1023_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_1024_1518_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_1519_2047_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_2048_4095_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_4096_8191_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_8192_9216_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_9217_12287_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_12288_16383_oct_pkt_num),
+ HINIC_PORT_STAT(mac_rx_1519_max_good_pkt_num),
+ HINIC_PORT_STAT(mac_rx_1519_max_bad_pkt_num),
+ HINIC_PORT_STAT(mac_rx_oversize_pkt_num),
+ HINIC_PORT_STAT(mac_rx_jabber_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pause_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri0_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri1_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri2_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri3_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri4_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri5_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri6_pkt_num),
+ HINIC_PORT_STAT(mac_rx_pfc_pri7_pkt_num),
+ HINIC_PORT_STAT(mac_rx_control_pkt_num),
+ HINIC_PORT_STAT(mac_rx_sym_err_pkt_num),
+ HINIC_PORT_STAT(mac_rx_fcs_err_pkt_num),
+ HINIC_PORT_STAT(mac_rx_send_app_good_pkt_num),
+ HINIC_PORT_STAT(mac_rx_send_app_bad_pkt_num),
+ HINIC_PORT_STAT(mac_tx_fragment_pkt_num),
+ HINIC_PORT_STAT(mac_tx_undersize_pkt_num),
+ HINIC_PORT_STAT(mac_tx_undermin_pkt_num),
+ HINIC_PORT_STAT(mac_tx_64_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_65_127_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_128_255_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_256_511_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_512_1023_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_1024_1518_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_1519_2047_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_2048_4095_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_4096_8191_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_8192_9216_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_9217_12287_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_12288_16383_oct_pkt_num),
+ HINIC_PORT_STAT(mac_tx_1519_max_good_pkt_num),
+ HINIC_PORT_STAT(mac_tx_1519_max_bad_pkt_num),
+ HINIC_PORT_STAT(mac_tx_oversize_pkt_num),
+ HINIC_PORT_STAT(mac_tx_jabber_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pause_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri0_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri1_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri2_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri3_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri4_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri5_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri6_pkt_num),
+ HINIC_PORT_STAT(mac_tx_pfc_pri7_pkt_num),
+ HINIC_PORT_STAT(mac_tx_control_pkt_num),
+ HINIC_PORT_STAT(mac_tx_err_all_pkt_num),
+ HINIC_PORT_STAT(mac_tx_from_app_good_pkt_num),
+ HINIC_PORT_STAT(mac_tx_from_app_bad_pkt_num),
+};
+
+#define HINIC_TXQ_STAT(_stat_item) { \
+ .name = "txq%d_"#_stat_item, \
+ .size = FIELD_SIZEOF(struct hinic_txq_stats, _stat_item), \
+ .offset = offsetof(struct hinic_txq_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_tx_queue_stats[] = {
+ HINIC_TXQ_STAT(pkts),
+ HINIC_TXQ_STAT(bytes),
+ HINIC_TXQ_STAT(tx_busy),
+ HINIC_TXQ_STAT(tx_wake),
+ HINIC_TXQ_STAT(tx_dropped),
+ HINIC_TXQ_STAT(big_frags_pkts),
+};
+
+#define HINIC_RXQ_STAT(_stat_item) { \
+ .name = "rxq%d_"#_stat_item, \
+ .size = FIELD_SIZEOF(struct hinic_rxq_stats, _stat_item), \
+ .offset = offsetof(struct hinic_rxq_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_rx_queue_stats[] = {
+ HINIC_RXQ_STAT(pkts),
+ HINIC_RXQ_STAT(bytes),
+ HINIC_RXQ_STAT(errors),
+ HINIC_RXQ_STAT(csum_errors),
+ HINIC_RXQ_STAT(other_errors),
+};
+
+static void get_drv_queue_stats(struct hinic_dev *nic_dev, u64 *data)
+{
+ struct hinic_txq_stats txq_stats;
+ struct hinic_rxq_stats rxq_stats;
+ u16 i = 0, j = 0, qid = 0;
+ char *p;
+
+ for (qid = 0; qid < nic_dev->num_qps; qid++) {
+ if (!nic_dev->txqs)
+ break;
+
+ hinic_txq_get_stats(&nic_dev->txqs[qid], &txq_stats);
+ for (j = 0; j < ARRAY_LEN(hinic_tx_queue_stats); j++, i++) {
+ p = (char *)&txq_stats +
+ hinic_tx_queue_stats[j].offset;
+ data[i] = (hinic_tx_queue_stats[j].size ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ }
+
+ for (qid = 0; qid < nic_dev->num_qps; qid++) {
+ if (!nic_dev->rxqs)
+ break;
+
+ hinic_rxq_get_stats(&nic_dev->rxqs[qid], &rxq_stats);
+ for (j = 0; j < ARRAY_LEN(hinic_rx_queue_stats); j++, i++) {
+ p = (char *)&rxq_stats +
+ hinic_rx_queue_stats[j].offset;
+ data[i] = (hinic_rx_queue_stats[j].size ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+ }
+}
+
+static void hinic_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ struct hinic_vport_stats vport_stats = {0};
+ const struct rtnl_link_stats64 *net_stats;
+ struct hinic_phy_port_stats *port_stats;
+ struct rtnl_link_stats64 temp;
+ u16 i = 0, j = 0;
+ char *p;
+ int err;
+
+ net_stats = dev_get_stats(netdev, &temp);
+ for (j = 0; j < ARRAY_LEN(hinic_netdev_stats); j++, i++) {
+ p = (char *)net_stats + hinic_netdev_stats[j].offset;
+ data[i] = (hinic_netdev_stats[j].size ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+
+ err = hinic_get_vport_stats(nic_dev, &vport_stats);
+ if (err)
+ netif_err(nic_dev, drv, netdev,
+ "Failed to get vport stats from firmware\n");
+
+ for (j = 0; j < ARRAY_LEN(hinic_function_stats); j++, i++) {
+ p = (char *)&vport_stats + hinic_function_stats[j].offset;
+ data[i] = (hinic_function_stats[j].size ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+
+ port_stats = kzalloc(sizeof(*port_stats), GFP_KERNEL);
+ if (!port_stats) {
+ memset(&data[i], 0,
+ ARRAY_LEN(hinic_port_stats) * sizeof(*data));
+ i += ARRAY_LEN(hinic_port_stats);
+ goto get_drv_stats;
+ }
+
+ err = hinic_get_phy_port_stats(nic_dev, port_stats);
+ if (err)
+ netif_err(nic_dev, drv, netdev,
+ "Failed to get port stats from firmware\n");
+
+ for (j = 0; j < ARRAY_LEN(hinic_port_stats); j++, i++) {
+ p = (char *)port_stats + hinic_port_stats[j].offset;
+ data[i] = (hinic_port_stats[j].size ==
+ sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+ }
+
+ kfree(port_stats);
+
+get_drv_stats:
+ get_drv_queue_stats(nic_dev, data + i);
+}
+
+static int hinic_get_sset_count(struct net_device *netdev, int sset)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ int count, q_num;
+
+ switch (sset) {
+ case ETH_SS_STATS:
+ q_num = nic_dev->num_qps;
+ count = ARRAY_LEN(hinic_netdev_stats) +
+ ARRAY_LEN(hinic_function_stats) +
+ (ARRAY_LEN(hinic_tx_queue_stats) +
+ ARRAY_LEN(hinic_rx_queue_stats)) * q_num;
+
+ count += ARRAY_LEN(hinic_port_stats);
+
+ return count;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void hinic_get_strings(struct net_device *netdev,
+ u32 stringset, u8 *data)
+{
+ struct hinic_dev *nic_dev = netdev_priv(netdev);
+ char *p = (char *)data;
+ u16 i, j;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < ARRAY_LEN(hinic_netdev_stats); i++) {
+ memcpy(p, hinic_netdev_stats[i].name,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+
+ for (i = 0; i < ARRAY_LEN(hinic_function_stats); i++) {
+ memcpy(p, hinic_function_stats[i].name,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+
+ for (i = 0; i < ARRAY_LEN(hinic_port_stats); i++) {
+ memcpy(p, hinic_port_stats[i].name,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+
+ for (i = 0; i < nic_dev->num_qps; i++) {
+ for (j = 0; j < ARRAY_LEN(hinic_tx_queue_stats); j++) {
+ sprintf(p, hinic_tx_queue_stats[j].name, i);
+ p += ETH_GSTRING_LEN;
+ }
+ }
+
+ for (i = 0; i < nic_dev->num_qps; i++) {
+ for (j = 0; j < ARRAY_LEN(hinic_rx_queue_stats); j++) {
+ sprintf(p, hinic_rx_queue_stats[j].name, i);
+ p += ETH_GSTRING_LEN;
+ }
+ }
+
+ return;
+ default:
+ return;
+ }
+}
+
static const struct ethtool_ops hinic_ethtool_ops = {
.get_link_ksettings = hinic_get_link_ksettings,
.get_drvinfo = hinic_get_drvinfo,
@@ -450,6 +788,9 @@ static const struct ethtool_ops hinic_ethtool_ops = {
.get_rxfh_indir_size = hinic_get_rxfh_indir_size,
.get_rxfh = hinic_get_rxfh,
.set_rxfh = hinic_set_rxfh,
+ .get_sset_count = hinic_get_sset_count,
+ .get_ethtool_stats = hinic_get_ethtool_stats,
+ .get_strings = hinic_get_strings,
};
void hinic_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 7a086350fefc..e83e3bf850d5 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -45,6 +45,14 @@ enum hinic_port_cmd {
HINIC_PORT_CMD_SET_RX_CSUM = 26,
+ HINIC_PORT_CMD_GET_PORT_STATISTICS = 28,
+
+ HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 29,
+
+ HINIC_PORT_CMD_GET_VPORT_STAT = 30,
+
+ HINIC_PORT_CMD_CLEAN_VPORT_STAT = 31,
+
HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 37,
HINIC_PORT_CMD_SET_PORT_STATE = 41,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index bfcb675d2299..1b917543feac 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -83,6 +83,9 @@ static void update_rx_stats(struct hinic_dev *nic_dev, struct hinic_rxq *rxq)
u64_stats_update_begin(&nic_rx_stats->syncp);
nic_rx_stats->bytes += rx_stats.bytes;
nic_rx_stats->pkts += rx_stats.pkts;
+ nic_rx_stats->errors += rx_stats.errors;
+ nic_rx_stats->csum_errors += rx_stats.csum_errors;
+ nic_rx_stats->other_errors += rx_stats.other_errors;
u64_stats_update_end(&nic_rx_stats->syncp);
hinic_rxq_clean_stats(rxq);
@@ -103,6 +106,7 @@ static void update_tx_stats(struct hinic_dev *nic_dev, struct hinic_txq *txq)
nic_tx_stats->tx_busy += tx_stats.tx_busy;
nic_tx_stats->tx_wake += tx_stats.tx_wake;
nic_tx_stats->tx_dropped += tx_stats.tx_dropped;
+ nic_tx_stats->big_frags_pkts += tx_stats.big_frags_pkts;
u64_stats_update_end(&nic_tx_stats->syncp);
hinic_txq_clean_stats(txq);
@@ -782,6 +786,7 @@ static void hinic_get_stats64(struct net_device *netdev,
stats->rx_bytes = nic_rx_stats->bytes;
stats->rx_packets = nic_rx_stats->pkts;
+ stats->rx_errors = nic_rx_stats->errors;
stats->tx_bytes = nic_tx_stats->bytes;
stats->tx_packets = nic_tx_stats->pkts;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 1c3b3c0d6298..c07adf793215 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -942,3 +942,69 @@ int hinic_rss_template_free(struct hinic_dev *nic_dev, u8 tmpl_idx)
return 0;
}
+
+int hinic_get_vport_stats(struct hinic_dev *nic_dev,
+ struct hinic_vport_stats *stats)
+{
+ struct hinic_cmd_vport_stats vport_stats = { 0 };
+ struct hinic_port_stats_info stats_info = { 0 };
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ u16 out_size = sizeof(vport_stats);
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ stats_info.stats_version = HINIC_PORT_STATS_VERSION;
+ stats_info.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+ stats_info.stats_size = sizeof(vport_stats);
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_VPORT_STAT,
+ &stats_info, sizeof(stats_info),
+ &vport_stats, &out_size);
+ if (err || !out_size || vport_stats.status) {
+ dev_err(&pdev->dev,
+ "Failed to get function statistics, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, vport_stats.status, out_size);
+ return -EFAULT;
+ }
+
+ memcpy(stats, &vport_stats.stats, sizeof(*stats));
+ return 0;
+}
+
+int hinic_get_phy_port_stats(struct hinic_dev *nic_dev,
+ struct hinic_phy_port_stats *stats)
+{
+ struct hinic_port_stats_info stats_info = { 0 };
+ struct hinic_hwdev *hwdev = nic_dev->hwdev;
+ struct hinic_hwif *hwif = hwdev->hwif;
+ struct hinic_port_stats *port_stats;
+ u16 out_size = sizeof(*port_stats);
+ struct pci_dev *pdev = hwif->pdev;
+ int err;
+
+ port_stats = kzalloc(sizeof(*port_stats), GFP_KERNEL);
+ if (!port_stats)
+ return -ENOMEM;
+
+ stats_info.stats_version = HINIC_PORT_STATS_VERSION;
+ stats_info.stats_size = sizeof(*port_stats);
+
+ err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_PORT_STATISTICS,
+ &stats_info, sizeof(stats_info),
+ port_stats, &out_size);
+ if (err || !out_size || port_stats->status) {
+ dev_err(&pdev->dev,
+ "Failed to get port statistics, err: %d, status: 0x%x, out size: 0x%x\n",
+ err, port_stats->status, out_size);
+ err = -EINVAL;
+ goto out;
+ }
+
+ memcpy(stats, &port_stats->stats, sizeof(*stats));
+
+out:
+ kfree(port_stats);
+
+ return err;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 826f0677be87..16140a13000b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -15,6 +15,7 @@
#define HINIC_RSS_KEY_SIZE 40
#define HINIC_RSS_INDIR_SIZE 256
+#define HINIC_PORT_STATS_VERSION 0
enum hinic_rx_mode {
HINIC_RX_MODE_UC = BIT(0),
@@ -316,6 +317,173 @@ struct hinic_rss_config {
u8 rsvd1[11];
};
+struct hinic_stats {
+ char name[ETH_GSTRING_LEN];
+ u32 size;
+ int offset;
+};
+
+struct hinic_vport_stats {
+ u64 tx_unicast_pkts_vport;
+ u64 tx_unicast_bytes_vport;
+ u64 tx_multicast_pkts_vport;
+ u64 tx_multicast_bytes_vport;
+ u64 tx_broadcast_pkts_vport;
+ u64 tx_broadcast_bytes_vport;
+
+ u64 rx_unicast_pkts_vport;
+ u64 rx_unicast_bytes_vport;
+ u64 rx_multicast_pkts_vport;
+ u64 rx_multicast_bytes_vport;
+ u64 rx_broadcast_pkts_vport;
+ u64 rx_broadcast_bytes_vport;
+
+ u64 tx_discard_vport;
+ u64 rx_discard_vport;
+ u64 tx_err_vport;
+ u64 rx_err_vport;
+};
+
+struct hinic_phy_port_stats {
+ u64 mac_rx_total_pkt_num;
+ u64 mac_rx_total_oct_num;
+ u64 mac_rx_bad_pkt_num;
+ u64 mac_rx_bad_oct_num;
+ u64 mac_rx_good_pkt_num;
+ u64 mac_rx_good_oct_num;
+ u64 mac_rx_uni_pkt_num;
+ u64 mac_rx_multi_pkt_num;
+ u64 mac_rx_broad_pkt_num;
+
+ u64 mac_tx_total_pkt_num;
+ u64 mac_tx_total_oct_num;
+ u64 mac_tx_bad_pkt_num;
+ u64 mac_tx_bad_oct_num;
+ u64 mac_tx_good_pkt_num;
+ u64 mac_tx_good_oct_num;
+ u64 mac_tx_uni_pkt_num;
+ u64 mac_tx_multi_pkt_num;
+ u64 mac_tx_broad_pkt_num;
+
+ u64 mac_rx_fragment_pkt_num;
+ u64 mac_rx_undersize_pkt_num;
+ u64 mac_rx_undermin_pkt_num;
+ u64 mac_rx_64_oct_pkt_num;
+ u64 mac_rx_65_127_oct_pkt_num;
+ u64 mac_rx_128_255_oct_pkt_num;
+ u64 mac_rx_256_511_oct_pkt_num;
+ u64 mac_rx_512_1023_oct_pkt_num;
+ u64 mac_rx_1024_1518_oct_pkt_num;
+ u64 mac_rx_1519_2047_oct_pkt_num;
+ u64 mac_rx_2048_4095_oct_pkt_num;
+ u64 mac_rx_4096_8191_oct_pkt_num;
+ u64 mac_rx_8192_9216_oct_pkt_num;
+ u64 mac_rx_9217_12287_oct_pkt_num;
+ u64 mac_rx_12288_16383_oct_pkt_num;
+ u64 mac_rx_1519_max_bad_pkt_num;
+ u64 mac_rx_1519_max_good_pkt_num;
+ u64 mac_rx_oversize_pkt_num;
+ u64 mac_rx_jabber_pkt_num;
+
+ u64 mac_rx_pause_num;
+ u64 mac_rx_pfc_pkt_num;
+ u64 mac_rx_pfc_pri0_pkt_num;
+ u64 mac_rx_pfc_pri1_pkt_num;
+ u64 mac_rx_pfc_pri2_pkt_num;
+ u64 mac_rx_pfc_pri3_pkt_num;
+ u64 mac_rx_pfc_pri4_pkt_num;
+ u64 mac_rx_pfc_pri5_pkt_num;
+ u64 mac_rx_pfc_pri6_pkt_num;
+ u64 mac_rx_pfc_pri7_pkt_num;
+ u64 mac_rx_control_pkt_num;
+ u64 mac_rx_y1731_pkt_num;
+ u64 mac_rx_sym_err_pkt_num;
+ u64 mac_rx_fcs_err_pkt_num;
+ u64 mac_rx_send_app_good_pkt_num;
+ u64 mac_rx_send_app_bad_pkt_num;
+
+ u64 mac_tx_fragment_pkt_num;
+ u64 mac_tx_undersize_pkt_num;
+ u64 mac_tx_undermin_pkt_num;
+ u64 mac_tx_64_oct_pkt_num;
+ u64 mac_tx_65_127_oct_pkt_num;
+ u64 mac_tx_128_255_oct_pkt_num;
+ u64 mac_tx_256_511_oct_pkt_num;
+ u64 mac_tx_512_1023_oct_pkt_num;
+ u64 mac_tx_1024_1518_oct_pkt_num;
+ u64 mac_tx_1519_2047_oct_pkt_num;
+ u64 mac_tx_2048_4095_oct_pkt_num;
+ u64 mac_tx_4096_8191_oct_pkt_num;
+ u64 mac_tx_8192_9216_oct_pkt_num;
+ u64 mac_tx_9217_12287_oct_pkt_num;
+ u64 mac_tx_12288_16383_oct_pkt_num;
+ u64 mac_tx_1519_max_bad_pkt_num;
+ u64 mac_tx_1519_max_good_pkt_num;
+ u64 mac_tx_oversize_pkt_num;
+ u64 mac_tx_jabber_pkt_num;
+
+ u64 mac_tx_pause_num;
+ u64 mac_tx_pfc_pkt_num;
+ u64 mac_tx_pfc_pri0_pkt_num;
+ u64 mac_tx_pfc_pri1_pkt_num;
+ u64 mac_tx_pfc_pri2_pkt_num;
+ u64 mac_tx_pfc_pri3_pkt_num;
+ u64 mac_tx_pfc_pri4_pkt_num;
+ u64 mac_tx_pfc_pri5_pkt_num;
+ u64 mac_tx_pfc_pri6_pkt_num;
+ u64 mac_tx_pfc_pri7_pkt_num;
+ u64 mac_tx_control_pkt_num;
+ u64 mac_tx_y1731_pkt_num;
+ u64 mac_tx_1588_pkt_num;
+ u64 mac_tx_err_all_pkt_num;
+ u64 mac_tx_from_app_good_pkt_num;
+ u64 mac_tx_from_app_bad_pkt_num;
+
+ u64 mac_rx_higig2_ext_pkt_num;
+ u64 mac_rx_higig2_message_pkt_num;
+ u64 mac_rx_higig2_error_pkt_num;
+ u64 mac_rx_higig2_cpu_ctrl_pkt_num;
+ u64 mac_rx_higig2_unicast_pkt_num;
+ u64 mac_rx_higig2_broadcast_pkt_num;
+ u64 mac_rx_higig2_l2_multicast_pkt_num;
+ u64 mac_rx_higig2_l3_multicast_pkt_num;
+
+ u64 mac_tx_higig2_message_pkt_num;
+ u64 mac_tx_higig2_ext_pkt_num;
+ u64 mac_tx_higig2_cpu_ctrl_pkt_num;
+ u64 mac_tx_higig2_unicast_pkt_num;
+ u64 mac_tx_higig2_broadcast_pkt_num;
+ u64 mac_tx_higig2_l2_multicast_pkt_num;
+ u64 mac_tx_higig2_l3_multicast_pkt_num;
+};
+
+struct hinic_port_stats_info {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ u16 func_id;
+ u16 rsvd1;
+ u32 stats_version;
+ u32 stats_size;
+};
+
+struct hinic_port_stats {
+ u8 status;
+ u8 version;
+ u8 rsvd[6];
+
+ struct hinic_phy_port_stats stats;
+};
+
+struct hinic_cmd_vport_stats {
+ u8 status;
+ u8 version;
+ u8 rsvd0[6];
+
+ struct hinic_vport_stats stats;
+};
+
int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
u16 vlan_id);
@@ -384,4 +552,10 @@ int hinic_rss_get_template_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
int hinic_rss_get_hash_engine(struct hinic_dev *nic_dev, u8 tmpl_idx,
u8 *type);
+
+int hinic_get_phy_port_stats(struct hinic_dev *nic_dev,
+ struct hinic_phy_port_stats *stats);
+
+int hinic_get_vport_stats(struct hinic_dev *nic_dev,
+ struct hinic_vport_stats *stats);
#endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 95b09fd110d3..609ad4333cdd 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -56,6 +56,9 @@ void hinic_rxq_clean_stats(struct hinic_rxq *rxq)
u64_stats_update_begin(&rxq_stats->syncp);
rxq_stats->pkts = 0;
rxq_stats->bytes = 0;
+ rxq_stats->errors = 0;
+ rxq_stats->csum_errors = 0;
+ rxq_stats->other_errors = 0;
u64_stats_update_end(&rxq_stats->syncp);
}
@@ -74,6 +77,10 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats)
start = u64_stats_fetch_begin(&rxq_stats->syncp);
stats->pkts = rxq_stats->pkts;
stats->bytes = rxq_stats->bytes;
+ stats->errors = rxq_stats->csum_errors +
+ rxq_stats->other_errors;
+ stats->csum_errors = rxq_stats->csum_errors;
+ stats->other_errors = rxq_stats->other_errors;
} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
u64_stats_update_end(&stats->syncp);
}
@@ -101,10 +108,14 @@ static void rx_csum(struct hinic_rxq *rxq, u32 status,
if (!(netdev->features & NETIF_F_RXCSUM))
return;
- if (!csum_err)
+ if (!csum_err) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
+ } else {
+ if (!(csum_err & (HINIC_RX_CSUM_HW_CHECK_NONE |
+ HINIC_RX_CSUM_IPSU_OTHER_ERR)))
+ rxq->rxq_stats.csum_errors++;
skb->ip_summed = CHECKSUM_NONE;
+ }
}
/**
* rx_alloc_skb - allocate skb and map it to dma address
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
index 4fa31691d328..507dcbae9085 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -21,7 +21,10 @@
struct hinic_rxq_stats {
u64 pkts;
u64 bytes;
-
+ u64 errors;
+ u64 csum_errors;
+ u64 other_errors;
+ u64 alloc_skb_err;
struct u64_stats_sync syncp;
};
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index b9fd8d720349..f4f76370cd65 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -83,6 +83,7 @@ void hinic_txq_clean_stats(struct hinic_txq *txq)
txq_stats->tx_busy = 0;
txq_stats->tx_wake = 0;
txq_stats->tx_dropped = 0;
+ txq_stats->big_frags_pkts = 0;
u64_stats_update_end(&txq_stats->syncp);
}
@@ -104,6 +105,7 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats)
stats->tx_busy = txq_stats->tx_busy;
stats->tx_wake = txq_stats->tx_wake;
stats->tx_dropped = txq_stats->tx_dropped;
+ stats->big_frags_pkts = txq_stats->big_frags_pkts;
} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
u64_stats_update_end(&stats->syncp);
}
@@ -464,6 +466,12 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
}
nr_sges = skb_shinfo(skb)->nr_frags + 1;
+ if (nr_sges > 17) {
+ u64_stats_update_begin(&txq->txq_stats.syncp);
+ txq->txq_stats.big_frags_pkts++;
+ u64_stats_update_end(&txq->txq_stats.syncp);
+ }
+
if (nr_sges > txq->max_sges) {
netdev_err(netdev, "Too many Tx sges\n");
goto skb_error;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.h b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
index ca5f537fc383..f158b7db7fb8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
@@ -21,6 +21,7 @@ struct hinic_txq_stats {
u64 tx_busy;
u64 tx_wake;
u64 tx_dropped;
+ u64 big_frags_pkts;
struct u64_stats_sync syncp;
};
--
2.17.1
^ permalink raw reply related
* Re: [PATCH net-next v2 3/3] mlxsw: core: Add support for negative temperature readout
From: Jiri Pirko @ 2019-06-24 11:42 UTC (permalink / raw)
To: Ido Schimmel; +Cc: netdev, davem, jiri, vadimp, andrew, mlxsw, Ido Schimmel
In-Reply-To: <20190624103203.22090-4-idosch@idosch.org>
Mon, Jun 24, 2019 at 12:32:03PM CEST, idosch@idosch.org wrote:
>From: Vadim Pasternak <vadimp@mellanox.com>
>
>Extend macros MLXSW_REG_MTMP_TEMP_TO_MC() to allow support of negative
>temperature readout, since chip and others thermal components are
>capable of operating within the negative temperature.
>With no such support negative temperature will be consider as very high
>temperature and it will cause wrong readout and thermal shutdown.
>For negative values 2`s complement is used.
>Tested in chamber.
>Example of chip ambient temperature readout with chamber temperature:
>-10 Celsius:
>temp1: -6.0C (highest = -5.0C)
>-5 Celsius:
>temp1: -1.0C (highest = -1.0C)
>
>v2 (Andrew Lunn):
>* Replace '%u' with '%d' in mlxsw_hwmon_module_temp_show()
>
>Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
>Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* RE: [PATCH net-next 4/6] arm64: dts: fsl: ls1028a: Add Felix switch port DT node
From: Claudiu Manoil @ 2019-06-24 11:45 UTC (permalink / raw)
To: Andrew Lunn
Cc: David S . Miller, devicetree@vger.kernel.org, Alexandre Belloni,
netdev@vger.kernel.org, Alexandru Marginean,
linux-kernel@vger.kernel.org, UNGLinuxDriver@microchip.com,
Allan Nielsen, Rob Herring, linux-arm-kernel@lists.infradead.org
In-Reply-To: <20190621164940.GL31306@lunn.ch>
Hi Andrew,
>-----Original Message-----
>From: Andrew Lunn <andrew@lunn.ch>
>Sent: Friday, June 21, 2019 7:50 PM
>To: Claudiu Manoil <claudiu.manoil@nxp.com>
>Cc: David S . Miller <davem@davemloft.net>; devicetree@vger.kernel.org;
>Alexandre Belloni <alexandre.belloni@bootlin.com>; netdev@vger.kernel.org;
>Alexandru Marginean <alexandru.marginean@nxp.com>; linux-
>kernel@vger.kernel.org; UNGLinuxDriver@microchip.com; Allan Nielsen
><Allan.Nielsen@microsemi.com>; Rob Herring <robh+dt@kernel.org>; linux-
>arm-kernel@lists.infradead.org
>Subject: Re: [PATCH net-next 4/6] arm64: dts: fsl: ls1028a: Add Felix switch port
>DT node
>
>On Fri, Jun 21, 2019 at 06:38:50PM +0300, Claudiu Manoil wrote:
>> The switch device features 6 ports, 4 with external links
>> and 2 internally facing to the ls1028a SoC and connected via
>> fixed links to 2 internal enetc ethernet controller ports.
>
>Hi Claudiu
>
>> + switch@0,5 {
>> + compatible = "mscc,felix-switch";
>> + reg = <0x000500 0 0 0 0>;
>> +
>> + ethernet-ports {
>> + #address-cells = <1>;
>> + #size-cells = <0>;
>> +
>> + /* external ports */
>> + switch_port0: port@0 {
>> + reg = <0>;
>> + };
>> + switch_port1: port@1 {
>> + reg = <1>;
>> + };
>> + switch_port2: port@2 {
>> + reg = <2>;
>> + };
>> + switch_port3: port@3 {
>> + reg = <3>;
>> + };
>> + /* internal to-cpu ports */
>> + port@4 {
>> + reg = <4>;
>> + fixed-link {
>> + speed = <1000>;
>> + full-duplex;
>> + };
>> + };
>> + port@5 {
>> + reg = <5>;
>> + fixed-link {
>> + speed = <1000>;
>> + full-duplex;
>> + };
>> + };
>> + };
>> + };
>
>This sounds like a DSA setup, where you have SoC ports connected to
>the switch. With DSA, the CPU ports of the switch are special. We
>don't create netdev's for them, the binding explicitly list which SoC
>interface they are bound to, etc.
>
>What model are you using here? I'm just trying to understand the setup
>to ensure it is consistent with the swichdev model.
>
Yeah, there are 2 ethernet controller ports (managed by the enetc driver)
connected inside the SoC via SGMII links to 2 of the switch ports, one of
these switch ports can be configured as CPU port (with follow-up patches).
This configuration may look prettier on DSA, but the main restriction here
is that the entire functionality is provided by the ocelot driver which is a
switchdev driver. I don't think it would be a good idea to copy-paste code
from ocelot to a separate dsa driver.
Thanks for the review.
Claudiu
^ permalink raw reply
* Re: [PATCH rdma-next v1 08/12] IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD
From: Jason Gunthorpe @ 2019-06-24 11:51 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
In-Reply-To: <20190618171540.11729-9-leon@kernel.org>
On Tue, Jun 18, 2019 at 08:15:36PM +0300, Leon Romanovsky wrote:
> From: Yishai Hadas <yishaih@mellanox.com>
>
> Introduce MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD and its initial
> implementation.
>
> This object is from type class FD and will be used to read DEVX
> async events.
>
> Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> drivers/infiniband/hw/mlx5/devx.c | 112 ++++++++++++++++++++--
> include/uapi/rdma/mlx5_user_ioctl_cmds.h | 10 ++
> include/uapi/rdma/mlx5_user_ioctl_verbs.h | 4 +
> 3 files changed, 116 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
> index 80b42d069328..1815ce0f8daf 100644
> +++ b/drivers/infiniband/hw/mlx5/devx.c
> @@ -33,6 +33,24 @@ struct devx_async_data {
> struct mlx5_ib_uapi_devx_async_cmd_hdr hdr;
> };
>
> +struct devx_async_event_queue {
It seems to be a mistake to try and re-use the async_event_queue for
both cmd and event, as they use it very differently and don't even
store the same things in the event_list. I think it is bettter to just
inline this into devx_async_event_file (and inline the old struct in
the cmd file
> + spinlock_t lock;
> + wait_queue_head_t poll_wait;
> + struct list_head event_list;
> + atomic_t bytes_in_use;
> + u8 is_destroyed:1;
> + u32 flags;
> +};
All the flags testing is ugly, why not just add another bitfield?
> +
> +struct devx_async_event_file {
> + struct ib_uobject uobj;
> + struct list_head subscribed_events_list; /* Head of events that are
> + * subscribed to this FD
> + */
> + struct devx_async_event_queue ev_queue;
> + struct mlx5_ib_dev *dev;
> +};
> +
Crazy indenting
> diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
> index a8f34c237458..57beea4589e4 100644
> +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
> @@ -63,5 +63,9 @@ enum mlx5_ib_uapi_dm_type {
> MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM,
> };
>
> +enum mlx5_ib_uapi_devx_create_event_channel_flags {
> + MLX5_IB_UAPI_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA = 1
> << 0,
Maybe this name is too long
Jason
^ permalink raw reply
* Re: KASAN: slab-out-of-bounds Read in p54u_load_firmware_cb
From: Andrey Konovalov @ 2019-06-24 11:51 UTC (permalink / raw)
To: Christian Lamparter
Cc: Alan Stern, syzbot, Christian Lamparter, David S. Miller,
Kalle Valo, Kernel development list, USB list, linux-wireless,
netdev, syzkaller-bugs
In-Reply-To: <3232861.cjm3rXpEJU@debian64>
On Thu, Jun 20, 2019 at 9:56 PM Christian Lamparter <chunkeey@gmail.com> wrote:
>
> On Thursday, June 20, 2019 9:46:32 PM CEST Alan Stern wrote:
> > On Wed, 19 Jun 2019, syzbot wrote:
> >
> > > syzbot has found a reproducer for the following crash on:
> > >
> > > HEAD commit: 9939f56e usb-fuzzer: main usb gadget fuzzer driver
> > > git tree: https://github.com/google/kasan.git usb-fuzzer
> > > console output: https://syzkaller.appspot.com/x/log.txt?x=135e29faa00000
> > > kernel config: https://syzkaller.appspot.com/x/.config?x=df134eda130bb43a
> > > dashboard link: https://syzkaller.appspot.com/bug?extid=6d237e74cdc13f036473
> > > compiler: gcc (GCC) 9.0.0 20181231 (experimental)
> > > syz repro: https://syzkaller.appspot.com/x/repro.syz?x=175d946ea00000
> > >
> > > IMPORTANT: if you fix the bug, please add the following tag to the commit:
> > > Reported-by: syzbot+6d237e74cdc13f036473@syzkaller.appspotmail.com
> > >
> > > usb 3-1: Direct firmware load for isl3887usb failed with error -2
> > > usb 3-1: Firmware not found.
> > > ==================================================================
> > > BUG: KASAN: slab-out-of-bounds in p54u_load_firmware_cb.cold+0x97/0x13d
> > > drivers/net/wireless/intersil/p54/p54usb.c:936
> > > Read of size 8 at addr ffff8881c9cf7588 by task kworker/1:5/2759
> > >
> > > CPU: 1 PID: 2759 Comm: kworker/1:5 Not tainted 5.2.0-rc5+ #11
> > > Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> > > Google 01/01/2011
> > > Workqueue: events request_firmware_work_func
> > > Call Trace:
> > > __dump_stack lib/dump_stack.c:77 [inline]
> > > dump_stack+0xca/0x13e lib/dump_stack.c:113
> > > print_address_description+0x67/0x231 mm/kasan/report.c:188
> > > __kasan_report.cold+0x1a/0x32 mm/kasan/report.c:317
> > > kasan_report+0xe/0x20 mm/kasan/common.c:614
> > > p54u_load_firmware_cb.cold+0x97/0x13d
> > > drivers/net/wireless/intersil/p54/p54usb.c:936
> > > request_firmware_work_func+0x126/0x242
> > > drivers/base/firmware_loader/main.c:785
> > > process_one_work+0x905/0x1570 kernel/workqueue.c:2269
> > > worker_thread+0x96/0xe20 kernel/workqueue.c:2415
> > > kthread+0x30b/0x410 kernel/kthread.c:255
> > > ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
> > >
> > > Allocated by task 1612:
> > > save_stack+0x1b/0x80 mm/kasan/common.c:71
> > > set_track mm/kasan/common.c:79 [inline]
> > > __kasan_kmalloc mm/kasan/common.c:489 [inline]
> > > __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:462
> > > kmalloc include/linux/slab.h:547 [inline]
> > > syslog_print kernel/printk/printk.c:1346 [inline]
> > > do_syslog kernel/printk/printk.c:1519 [inline]
> > > do_syslog+0x4f4/0x12e0 kernel/printk/printk.c:1493
> > > kmsg_read+0x8a/0xb0 fs/proc/kmsg.c:40
> > > proc_reg_read+0x1c1/0x280 fs/proc/inode.c:221
> > > __vfs_read+0x76/0x100 fs/read_write.c:425
> > > vfs_read+0x18e/0x3d0 fs/read_write.c:461
> > > ksys_read+0x127/0x250 fs/read_write.c:587
> > > do_syscall_64+0xb7/0x560 arch/x86/entry/common.c:301
> > > entry_SYSCALL_64_after_hwframe+0x49/0xbe
> > >
> > > Freed by task 1612:
> > > save_stack+0x1b/0x80 mm/kasan/common.c:71
> > > set_track mm/kasan/common.c:79 [inline]
> > > __kasan_slab_free+0x130/0x180 mm/kasan/common.c:451
> > > slab_free_hook mm/slub.c:1421 [inline]
> > > slab_free_freelist_hook mm/slub.c:1448 [inline]
> > > slab_free mm/slub.c:2994 [inline]
> > > kfree+0xd7/0x280 mm/slub.c:3949
> > > syslog_print kernel/printk/printk.c:1405 [inline]
> > > do_syslog kernel/printk/printk.c:1519 [inline]
> > > do_syslog+0xff3/0x12e0 kernel/printk/printk.c:1493
> > > kmsg_read+0x8a/0xb0 fs/proc/kmsg.c:40
> > > proc_reg_read+0x1c1/0x280 fs/proc/inode.c:221
> > > __vfs_read+0x76/0x100 fs/read_write.c:425
> > > vfs_read+0x18e/0x3d0 fs/read_write.c:461
> > > ksys_read+0x127/0x250 fs/read_write.c:587
> > > do_syscall_64+0xb7/0x560 arch/x86/entry/common.c:301
> > > entry_SYSCALL_64_after_hwframe+0x49/0xbe
> > >
> > > The buggy address belongs to the object at ffff8881c9cf7180
> > > which belongs to the cache kmalloc-1k of size 1024
> > > The buggy address is located 8 bytes to the right of
> > > 1024-byte region [ffff8881c9cf7180, ffff8881c9cf7580)
> > > The buggy address belongs to the page:
> > > page:ffffea0007273d00 refcount:1 mapcount:0 mapping:ffff8881dac02a00
> > > index:0x0 compound_mapcount: 0
> > > flags: 0x200000000010200(slab|head)
> > > raw: 0200000000010200 dead000000000100 dead000000000200 ffff8881dac02a00
> > > raw: 0000000000000000 00000000000e000e 00000001ffffffff 0000000000000000
> > > page dumped because: kasan: bad access detected
> > >
> > > Memory state around the buggy address:
> > > ffff8881c9cf7480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> > > ffff8881c9cf7500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> > > > ffff8881c9cf7580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
> > > ^
> > > ffff8881c9cf7600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> > > ffff8881c9cf7680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> > > ==================================================================
> >
> > Isn't this the same as syzkaller bug 200d4bb11b23d929335f ? Doesn't
> > the same patch fix it?
> >
> I think Kalle hasn't applied it yet? It's still sitting on the patchwork queue:
> <https://patchwork.kernel.org/patch/10951527/>
Yes, until this patch is in the tree that is being tested (which is
based on the usb-linus branch; I update it every few weeks), syzbot
considers this bug as open.
>
> Regards,
> Christian
>
>
^ permalink raw reply
* Re: [PATCH rdma-next v1 09/12] IB/mlx5: Register DEVX with mlx5_core to get async events
From: Jason Gunthorpe @ 2019-06-24 11:52 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
In-Reply-To: <20190618171540.11729-10-leon@kernel.org>
On Tue, Jun 18, 2019 at 08:15:37PM +0300, Leon Romanovsky wrote:
> void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> index 9cf23ae6324e..556af34b788b 100644
> +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> @@ -944,6 +944,13 @@ struct mlx5_ib_pf_eq {
> mempool_t *pool;
> };
>
> +struct mlx5_devx_event_table {
> + struct mlx5_nb devx_nb;
> + /* serialize updating the event_xa */
> + struct mutex event_xa_lock;
> + struct xarray event_xa;
> +};
> +
> struct mlx5_ib_dev {
> struct ib_device ib_dev;
> struct mlx5_core_dev *mdev;
> @@ -994,6 +1001,7 @@ struct mlx5_ib_dev {
> struct mlx5_srq_table srq_table;
> struct mlx5_async_ctx async_ctx;
> int free_port;
> + struct mlx5_devx_event_table devx_event_table;
I really question if adding all these structs really does anything for
readability..
Jason
^ permalink raw reply
* Re: [PATCH net-next 4/6] arm64: dts: fsl: ls1028a: Add Felix switch port DT node
From: Alexandre Belloni @ 2019-06-24 11:55 UTC (permalink / raw)
To: Claudiu Manoil
Cc: Andrew Lunn, David S . Miller, devicetree@vger.kernel.org,
netdev@vger.kernel.org, Alexandru Marginean,
linux-kernel@vger.kernel.org, UNGLinuxDriver@microchip.com,
Allan Nielsen, Rob Herring, linux-arm-kernel@lists.infradead.org
In-Reply-To: <VI1PR04MB4880D8F90BBCD30BF8A69C9696E00@VI1PR04MB4880.eurprd04.prod.outlook.com>
On 24/06/2019 11:45:37+0000, Claudiu Manoil wrote:
> Hi Andrew,
>
> >-----Original Message-----
> >From: Andrew Lunn <andrew@lunn.ch>
> >Sent: Friday, June 21, 2019 7:50 PM
> >To: Claudiu Manoil <claudiu.manoil@nxp.com>
> >Cc: David S . Miller <davem@davemloft.net>; devicetree@vger.kernel.org;
> >Alexandre Belloni <alexandre.belloni@bootlin.com>; netdev@vger.kernel.org;
> >Alexandru Marginean <alexandru.marginean@nxp.com>; linux-
> >kernel@vger.kernel.org; UNGLinuxDriver@microchip.com; Allan Nielsen
> ><Allan.Nielsen@microsemi.com>; Rob Herring <robh+dt@kernel.org>; linux-
> >arm-kernel@lists.infradead.org
> >Subject: Re: [PATCH net-next 4/6] arm64: dts: fsl: ls1028a: Add Felix switch port
> >DT node
> >
> >On Fri, Jun 21, 2019 at 06:38:50PM +0300, Claudiu Manoil wrote:
> >> The switch device features 6 ports, 4 with external links
> >> and 2 internally facing to the ls1028a SoC and connected via
> >> fixed links to 2 internal enetc ethernet controller ports.
> >
> >Hi Claudiu
> >
> >> + switch@0,5 {
> >> + compatible = "mscc,felix-switch";
> >> + reg = <0x000500 0 0 0 0>;
> >> +
> >> + ethernet-ports {
> >> + #address-cells = <1>;
> >> + #size-cells = <0>;
> >> +
> >> + /* external ports */
> >> + switch_port0: port@0 {
> >> + reg = <0>;
> >> + };
> >> + switch_port1: port@1 {
> >> + reg = <1>;
> >> + };
> >> + switch_port2: port@2 {
> >> + reg = <2>;
> >> + };
> >> + switch_port3: port@3 {
> >> + reg = <3>;
> >> + };
> >> + /* internal to-cpu ports */
> >> + port@4 {
> >> + reg = <4>;
> >> + fixed-link {
> >> + speed = <1000>;
> >> + full-duplex;
> >> + };
> >> + };
> >> + port@5 {
> >> + reg = <5>;
> >> + fixed-link {
> >> + speed = <1000>;
> >> + full-duplex;
> >> + };
> >> + };
> >> + };
> >> + };
> >
> >This sounds like a DSA setup, where you have SoC ports connected to
> >the switch. With DSA, the CPU ports of the switch are special. We
> >don't create netdev's for them, the binding explicitly list which SoC
> >interface they are bound to, etc.
> >
> >What model are you using here? I'm just trying to understand the setup
> >to ensure it is consistent with the swichdev model.
> >
>
> Yeah, there are 2 ethernet controller ports (managed by the enetc driver)
> connected inside the SoC via SGMII links to 2 of the switch ports, one of
> these switch ports can be configured as CPU port (with follow-up patches).
>
> This configuration may look prettier on DSA, but the main restriction here
> is that the entire functionality is provided by the ocelot driver which is a
> switchdev driver. I don't think it would be a good idea to copy-paste code
> from ocelot to a separate dsa driver.
>
We should probably make the ocelot driver a DSA driver then...
--
Alexandre Belloni, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH rdma-next v1 10/12] IB/mlx5: Enable subscription for device events over DEVX
From: Jason Gunthorpe @ 2019-06-24 11:57 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
In-Reply-To: <20190618171540.11729-11-leon@kernel.org>
On Tue, Jun 18, 2019 at 08:15:38PM +0300, Leon Romanovsky wrote:
> From: Yishai Hadas <yishaih@mellanox.com>
>
> Enable subscription for device events over DEVX.
>
> Each subscription is added to the two level XA data structure according
> to its event number and the DEVX object information in case was given
> with the given target fd.
>
> Those events will be reported over the given fd once will occur.
> Downstream patches will mange the dispatching to any subscription.
>
> Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> drivers/infiniband/hw/mlx5/devx.c | 564 ++++++++++++++++++++++-
> include/uapi/rdma/mlx5_user_ioctl_cmds.h | 9 +
> 2 files changed, 566 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
> index e9b9ba5a3e9a..304b13e7a265 100644
> +++ b/drivers/infiniband/hw/mlx5/devx.c
> @@ -14,6 +14,7 @@
> #include <linux/mlx5/driver.h>
> #include <linux/mlx5/fs.h>
> #include "mlx5_ib.h"
> +#include <linux/xarray.h>
>
> #define UVERBS_MODULE_NAME mlx5_ib
> #include <rdma/uverbs_named_ioctl.h>
> @@ -33,6 +34,37 @@ struct devx_async_data {
> struct mlx5_ib_uapi_devx_async_cmd_hdr hdr;
> };
>
> +/* first level XA value data structure */
> +struct devx_event {
> + struct xarray object_ids; /* second XA level, Key = object id */
> + struct list_head unaffiliated_list;
> +};
> +
> +/* second level XA value data structure */
> +struct devx_obj_event {
> + struct rcu_head rcu;
> + struct list_head obj_sub_list;
> +};
> +
> +struct devx_event_subscription {
> + struct list_head file_list; /* headed in private_data->
> + * subscribed_events_list
> + */
> + struct list_head xa_list; /* headed in devx_event->unaffiliated_list or
> + * devx_obj_event->obj_sub_list
> + */
> + struct list_head obj_list; /* headed in devx_object */
> +
> + u32 xa_key_level1;
> + u32 xa_key_level2;
> + struct rcu_head rcu;
> + u64 cookie;
> + bool is_obj_related;
> + struct ib_uobject *fd_uobj;
> + void *object; /* May need direct access upon hot unplug */
This should be a 'struct file *' and have a better name.
And I'm unclear why we need to store both the ib_uobject and the
struct file for the same thing? And why are we storing the uobj here
instead of the struct devx_async_event_file *?
Since uobj->object == flip && filp->private_data == uobj, I have a
hard time to understand why we need both things, it seems to me that
if we get the fget on the filp then we can rely on the
filp->private_data to get back to the devx_async_event_file.
> + struct eventfd_ctx *eventfd;
> +};
> +
> /*
> * As the obj_id in the firmware is not globally unique the object type
> * must be considered upon checking for a valid object id.
> @@ -1143,14 +1275,53 @@ static void devx_cleanup_mkey(struct devx_obj *obj)
> write_unlock_irqrestore(&table->lock, flags);
> }
>
> +static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
> + struct devx_event_subscription *sub)
> +{
> + list_del_rcu(&sub->file_list);
> + list_del_rcu(&sub->xa_list);
> +
> + if (sub->is_obj_related) {
is_obj_related looks like it is just list_empty(obj_list)??
Success oriented flow
> @@ -1523,6 +1700,350 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY)(
> return err;
> }
>
> +static void
> +subscribe_event_xa_dealloc(struct mlx5_devx_event_table *devx_event_table,
> + u32 key_level1,
> + u32 key_level2,
> + struct devx_obj_event *alloc_obj_event)
> +{
> + struct devx_event *event;
> +
> + /* Level 1 is valid for future use - no need to free */
> + if (!alloc_obj_event)
> + return;
> +
> + event = xa_load(&devx_event_table->event_xa, key_level1);
> + WARN_ON(!event);
> +
> + xa_erase(&event->object_ids, key_level2);
Shoulnd't this only erase if the value stored is NULL?
> + kfree(alloc_obj_event);
> +}
> +
> +static int
> +subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
> + u32 key_level1,
> + bool is_level2,
> + u32 key_level2,
> + struct devx_obj_event **alloc_obj_event)
> +{
> + struct devx_obj_event *obj_event;
> + struct devx_event *event;
> + bool new_entry_level1 = false;
> + int err;
> +
> + event = xa_load(&devx_event_table->event_xa, key_level1);
> + if (!event) {
> + event = kzalloc(sizeof(*event), GFP_KERNEL);
> + if (!event)
> + return -ENOMEM;
> +
> + new_entry_level1 = true;
> + INIT_LIST_HEAD(&event->unaffiliated_list);
> + xa_init(&event->object_ids);
> +
> + err = xa_insert(&devx_event_table->event_xa,
> + key_level1,
> + event,
> + GFP_KERNEL);
> + if (err)
> + goto end;
> + }
> +
> + if (!is_level2)
> + return 0;
> +
> + obj_event = xa_load(&event->object_ids, key_level2);
> + if (!obj_event) {
> + err = xa_reserve(&event->object_ids, key_level2, GFP_KERNEL);
> + if (err)
> + goto err_level1;
> +
> + obj_event = kzalloc(sizeof(*obj_event), GFP_KERNEL);
> + if (!obj_event) {
> + err = -ENOMEM;
> + goto err_level2;
> + }
> +
> + INIT_LIST_HEAD(&obj_event->obj_sub_list);
> + *alloc_obj_event = obj_event;
This is goofy, just store the empty obj_event in the xa instead of
using xa_reserve, and when you go to do the error unwind just delete
any level2' devx_obj_event' that has a list_empty(obj_sub_list), get
rid of the wonky alloc_obj_event stuff.
The best configuration would be to use devx_cleanup_subscription to
undo the partially ready subscription.
> + }
> +
> + return 0;
> +
> +err_level2:
> + xa_erase(&event->object_ids, key_level2);
> +
> +err_level1:
> + if (new_entry_level1)
> + xa_erase(&devx_event_table->event_xa, key_level1);
> +end:
> + if (new_entry_level1)
> + kfree(event);
Can't do this, once the level1 is put in the tree it could be referenced by
the irqs. At least it needs a kfree_rcu, most likely it is simpler to
just leave it.
> +#define MAX_NUM_EVENTS 16
> +static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)(
> + struct uverbs_attr_bundle *attrs)
> +{
> + struct ib_uobject *devx_uobj = uverbs_attr_get_uobject(
> + attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_OBJ_HANDLE);
> + struct mlx5_ib_ucontext *c = rdma_udata_to_drv_context(
> + &attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
> + struct mlx5_ib_dev *dev = to_mdev(c->ibucontext.device);
> + struct ib_uobject *fd_uobj;
> + struct devx_obj *obj = NULL;
> + struct devx_async_event_file *ev_file;
> + struct mlx5_devx_event_table *devx_event_table = &dev->devx_event_table;
> + u16 *event_type_num_list;
> + struct devx_event_subscription **event_sub_arr;
> + struct devx_obj_event **event_obj_array_alloc;
> + int redirect_fd;
> + bool use_eventfd = false;
> + int num_events;
> + int num_alloc_xa_entries = 0;
> + u16 obj_type = 0;
> + u64 cookie = 0;
> + u32 obj_id = 0;
> + int err;
> + int i;
> +
> + if (!c->devx_uid)
> + return -EINVAL;
> +
> + if (!IS_ERR(devx_uobj)) {
> + obj = (struct devx_obj *)devx_uobj->object;
> + if (obj)
> + obj_id = get_dec_obj_id(obj->obj_id);
> + }
> +
> + fd_uobj = uverbs_attr_get_uobject(attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_HANDLE);
> + if (IS_ERR(fd_uobj))
> + return PTR_ERR(fd_uobj);
> +
> + ev_file = container_of(fd_uobj, struct devx_async_event_file,
> + uobj);
> +
> + if (uverbs_attr_is_valid(attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM)) {
> + err = uverbs_copy_from(&redirect_fd, attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM);
> + if (err)
> + return err;
> +
> + use_eventfd = true;
> + }
> +
> + if (uverbs_attr_is_valid(attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE)) {
> + if (use_eventfd)
> + return -EINVAL;
> +
> + err = uverbs_copy_from(&cookie, attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE);
> + if (err)
> + return err;
> + }
> +
> + num_events = uverbs_attr_ptr_get_array_size(
> + attrs, MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST,
> + sizeof(u16));
> +
> + if (num_events < 0)
> + return num_events;
> +
> + if (num_events > MAX_NUM_EVENTS)
> + return -EINVAL;
> +
> + event_type_num_list = uverbs_attr_get_alloced_ptr(attrs,
> + MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST);
> +
> + if (!is_valid_events(dev->mdev, num_events, event_type_num_list, obj))
> + return -EINVAL;
> +
> + event_sub_arr = uverbs_zalloc(attrs,
> + MAX_NUM_EVENTS * sizeof(struct devx_event_subscription *));
> + event_obj_array_alloc = uverbs_zalloc(attrs,
> + MAX_NUM_EVENTS * sizeof(struct devx_obj_event *));
There are so many list_heads in the devx_event_subscription, why not
use just one of them to store the allocated events instead of this
temp array? ie event_list looks good for this purpose.
> +
> + if (!event_sub_arr || !event_obj_array_alloc)
> + return -ENOMEM;
> +
> + /* Protect from concurrent subscriptions to same XA entries to allow
> + * both to succeed
> + */
> + mutex_lock(&devx_event_table->event_xa_lock);
> + for (i = 0; i < num_events; i++) {
> + u32 key_level1;
> +
> + if (obj)
> + obj_type = get_dec_obj_type(obj,
> + event_type_num_list[i]);
> + key_level1 = event_type_num_list[i] | obj_type << 16;
> +
> + err = subscribe_event_xa_alloc(devx_event_table,
> + key_level1,
> + obj ? true : false,
> + obj_id,
> + &event_obj_array_alloc[i]);
Usless ?:
> + if (err)
> + goto err;
> +
> + num_alloc_xa_entries++;
> + event_sub_arr[i] = kzalloc(sizeof(*event_sub_arr[i]),
> + GFP_KERNEL);
> + if (!event_sub_arr[i])
> + goto err;
> +
> + if (use_eventfd) {
> + event_sub_arr[i]->eventfd =
> + eventfd_ctx_fdget(redirect_fd);
> +
> + if (IS_ERR(event_sub_arr[i]->eventfd)) {
> + err = PTR_ERR(event_sub_arr[i]->eventfd);
> + event_sub_arr[i]->eventfd = NULL;
> + goto err;
> + }
> + }
> +
> + event_sub_arr[i]->cookie = cookie;
> + event_sub_arr[i]->fd_uobj = fd_uobj;
> + event_sub_arr[i]->object = fd_uobj->object;
> + /* May be needed upon cleanup the devx object/subscription */
> + event_sub_arr[i]->xa_key_level1 = key_level1;
> + event_sub_arr[i]->xa_key_level2 = obj_id;
> + event_sub_arr[i]->is_obj_related = obj ? true : false;
Unneeded ?:
Jason
^ permalink raw reply
* Re: [PATCH rdma-next v1 11/12] IB/mlx5: Implement DEVX dispatching event
From: Jason Gunthorpe @ 2019-06-24 12:03 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
In-Reply-To: <20190618171540.11729-12-leon@kernel.org>
On Tue, Jun 18, 2019 at 08:15:39PM +0300, Leon Romanovsky wrote:
> From: Yishai Hadas <yishaih@mellanox.com>
>
> Implement DEVX dispatching event by looking up for the applicable
> subscriptions for the reported event and using their target fd to
> signal/set the event.
>
> Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> drivers/infiniband/hw/mlx5/devx.c | 362 +++++++++++++++++++++-
> include/uapi/rdma/mlx5_user_ioctl_verbs.h | 5 +
> 2 files changed, 357 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
> index 304b13e7a265..49fdce95d6d9 100644
> +++ b/drivers/infiniband/hw/mlx5/devx.c
> @@ -34,6 +34,11 @@ struct devx_async_data {
> struct mlx5_ib_uapi_devx_async_cmd_hdr hdr;
> };
>
> +struct devx_async_event_data {
> + struct list_head list; /* headed in ev_queue->event_list */
> + struct mlx5_ib_uapi_devx_async_event_hdr hdr;
> +};
> +
> /* first level XA value data structure */
> struct devx_event {
> struct xarray object_ids; /* second XA level, Key = object id */
> @@ -54,7 +59,9 @@ struct devx_event_subscription {
> * devx_obj_event->obj_sub_list
> */
> struct list_head obj_list; /* headed in devx_object */
> + struct list_head event_list; /* headed in ev_queue->event_list */
>
> + u8 is_cleaned:1;
There is a loose bool 'is_obj_related' that should be combined with
this bool bitfield as well.
> static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
> - struct devx_event_subscription *sub)
> + struct devx_event_subscription *sub,
> + bool file_close)
> {
> - list_del_rcu(&sub->file_list);
> + if (sub->is_cleaned)
> + goto end;
> +
> + sub->is_cleaned = 1;
> list_del_rcu(&sub->xa_list);
>
> if (sub->is_obj_related) {
> @@ -1303,10 +1355,15 @@ static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
> }
> }
>
> - if (sub->eventfd)
> - eventfd_ctx_put(sub->eventfd);
> +end:
> + if (file_close) {
> + if (sub->eventfd)
> + eventfd_ctx_put(sub->eventfd);
>
> - kfree_rcu(sub, rcu);
> + list_del_rcu(&sub->file_list);
> + /* subscription may not be used by the read API any more */
> + kfree_rcu(sub, rcu);
> + }
Dis like this confusing file_close stuff, just put this in the single place
that calls this with the true bool
> +static int deliver_event(struct devx_event_subscription *event_sub,
> + const void *data)
> +{
> + struct ib_uobject *fd_uobj = event_sub->fd_uobj;
> + struct devx_async_event_file *ev_file;
> + struct devx_async_event_queue *ev_queue;
> + struct devx_async_event_data *event_data;
> + unsigned long flags;
> + bool omit_data;
> +
> + ev_file = container_of(fd_uobj, struct devx_async_event_file,
> + uobj);
> + ev_queue = &ev_file->ev_queue;
> + omit_data = ev_queue->flags &
> + MLX5_IB_UAPI_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA;
> +
> + if (omit_data) {
> + spin_lock_irqsave(&ev_queue->lock, flags);
> + if (!list_empty(&event_sub->event_list)) {
> + spin_unlock_irqrestore(&ev_queue->lock, flags);
> + return 0;
> + }
> +
> + list_add_tail(&event_sub->event_list, &ev_queue->event_list);
> + spin_unlock_irqrestore(&ev_queue->lock, flags);
> + wake_up_interruptible(&ev_queue->poll_wait);
> + return 0;
> + }
> +
> + event_data = kzalloc(sizeof(*event_data) +
> + (omit_data ? 0 : sizeof(struct mlx5_eqe)),
> + GFP_ATOMIC);
omit_data is always false here
> + if (!event_data) {
> + spin_lock_irqsave(&ev_queue->lock, flags);
> + ev_queue->is_overflow_err = 1;
> + spin_unlock_irqrestore(&ev_queue->lock, flags);
> + return -ENOMEM;
> + }
> +
> + event_data->hdr.cookie = event_sub->cookie;
> + memcpy(event_data->hdr.out_data, data, sizeof(struct mlx5_eqe));
> +
> + spin_lock_irqsave(&ev_queue->lock, flags);
> + list_add_tail(&event_data->list, &ev_queue->event_list);
> + spin_unlock_irqrestore(&ev_queue->lock, flags);
> + wake_up_interruptible(&ev_queue->poll_wait);
> +
> + return 0;
> +}
> +
> +static void dispatch_event_fd(struct list_head *fd_list,
> + const void *data)
> +{
> + struct devx_event_subscription *item;
> +
> + list_for_each_entry_rcu(item, fd_list, xa_list) {
> + if (!get_file_rcu((struct file *)item->object))
> + continue;
> +
> + if (item->eventfd) {
> + eventfd_signal(item->eventfd, 1);
> + fput(item->object);
> + continue;
> + }
> +
> + deliver_event(item, data);
> + fput(item->object);
> + }
> +}
> +
> static int devx_event_notifier(struct notifier_block *nb,
> unsigned long event_type, void *data)
> {
> - return NOTIFY_DONE;
> + struct mlx5_devx_event_table *table;
> + struct mlx5_ib_dev *dev;
> + struct devx_event *event;
> + struct devx_obj_event *obj_event;
> + u16 obj_type = 0;
> + bool is_unaffiliated;
> + u32 obj_id;
> +
> + /* Explicit filtering to kernel events which may occur frequently */
> + if (event_type == MLX5_EVENT_TYPE_CMD ||
> + event_type == MLX5_EVENT_TYPE_PAGE_REQUEST)
> + return NOTIFY_OK;
> +
> + table = container_of(nb, struct mlx5_devx_event_table, devx_nb.nb);
> + dev = container_of(table, struct mlx5_ib_dev, devx_event_table);
> + is_unaffiliated = is_unaffiliated_event(dev->mdev, event_type);
> +
> + if (!is_unaffiliated)
> + obj_type = get_event_obj_type(event_type, data);
> + event = xa_load(&table->event_xa, event_type | (obj_type << 16));
> + if (!event)
> + return NOTIFY_DONE;
event should be in the rcu as well
> + if (is_unaffiliated) {
> + dispatch_event_fd(&event->unaffiliated_list, data);
> + return NOTIFY_OK;
> + }
> +
> + obj_id = devx_get_obj_id_from_event(event_type, data);
> + rcu_read_lock();
> + obj_event = xa_load(&event->object_ids, obj_id);
> + if (!obj_event) {
> + rcu_read_unlock();
> + return NOTIFY_DONE;
> + }
> +
> + dispatch_event_fd(&obj_event->obj_sub_list, data);
> +
> + rcu_read_unlock();
> + return NOTIFY_OK;
> }
>
> void mlx5_ib_devx_init_event_table(struct mlx5_ib_dev *dev)
> @@ -2221,7 +2444,7 @@ void mlx5_ib_devx_cleanup_event_table(struct mlx5_ib_dev *dev)
> event = entry;
> list_for_each_entry_safe(sub, tmp, &event->unaffiliated_list,
> xa_list)
> - devx_cleanup_subscription(dev, sub);
> + devx_cleanup_subscription(dev, sub, false);
> kfree(entry);
> }
> mutex_unlock(&dev->devx_event_table.event_xa_lock);
> @@ -2329,18 +2552,126 @@ static const struct file_operations devx_async_cmd_event_fops = {
> static ssize_t devx_async_event_read(struct file *filp, char __user *buf,
> size_t count, loff_t *pos)
> {
> - return -EINVAL;
> + struct devx_async_event_file *ev_file = filp->private_data;
> + struct devx_async_event_queue *ev_queue = &ev_file->ev_queue;
> + struct devx_event_subscription *event_sub;
> + struct devx_async_event_data *uninitialized_var(event);
> + int ret = 0;
> + size_t eventsz;
> + bool omit_data;
> + void *event_data;
> +
> + omit_data = ev_queue->flags &
> + MLX5_IB_UAPI_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA;
> +
> + spin_lock_irq(&ev_queue->lock);
> +
> + if (ev_queue->is_overflow_err) {
> + ev_queue->is_overflow_err = 0;
> + spin_unlock_irq(&ev_queue->lock);
> + return -EOVERFLOW;
> + }
> +
> + while (list_empty(&ev_queue->event_list)) {
> + spin_unlock_irq(&ev_queue->lock);
> +
> + if (filp->f_flags & O_NONBLOCK)
> + return -EAGAIN;
> +
> + if (wait_event_interruptible(ev_queue->poll_wait,
> + (!list_empty(&ev_queue->event_list) ||
> + ev_queue->is_destroyed))) {
> + return -ERESTARTSYS;
> + }
> +
> + if (list_empty(&ev_queue->event_list) &&
> + ev_queue->is_destroyed)
> + return -EIO;
All these tests should be under the lock.
Why don't we return EIO as soon as is-destroyed happens? What is the
point of flushing out the accumulated events?
> +
> + spin_lock_irq(&ev_queue->lock);
> + }
> +
> + if (omit_data) {
> + event_sub = list_first_entry(&ev_queue->event_list,
> + struct devx_event_subscription,
> + event_list);
> + eventsz = sizeof(event_sub->cookie);
> + event_data = &event_sub->cookie;
> + } else {
> + event = list_first_entry(&ev_queue->event_list,
> + struct devx_async_event_data, list);
> + eventsz = sizeof(struct mlx5_eqe) +
> + sizeof(struct mlx5_ib_uapi_devx_async_event_hdr);
> + event_data = &event->hdr;
> + }
> +
> + if (eventsz > count) {
> + spin_unlock_irq(&ev_queue->lock);
> + return -ENOSPC;
This is probably the wrong errno
> + }
> +
> + if (omit_data)
> + list_del_init(&event_sub->event_list);
> + else
> + list_del(&event->list);
> +
> + spin_unlock_irq(&ev_queue->lock);
> +
> + if (copy_to_user(buf, event_data, eventsz))
> + ret = -EFAULT;
> + else
> + ret = eventsz;
This is really poorly ordered, EFAULT will cause the event to be lost. :(
Maybe the event should be re-added on error? Tricky.
> + if (!omit_data)
> + kfree(event);
> + return ret;
> }
>
> static __poll_t devx_async_event_poll(struct file *filp,
> struct poll_table_struct *wait)
> {
> - return 0;
> + struct devx_async_event_file *ev_file = filp->private_data;
> + struct devx_async_event_queue *ev_queue = &ev_file->ev_queue;
> + __poll_t pollflags = 0;
> +
> + poll_wait(filp, &ev_queue->poll_wait, wait);
> +
> + spin_lock_irq(&ev_queue->lock);
> + if (ev_queue->is_destroyed)
> + pollflags = EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
> + else if (!list_empty(&ev_queue->event_list))
> + pollflags = EPOLLIN | EPOLLRDNORM;
> + spin_unlock_irq(&ev_queue->lock);
> +
> + return pollflags;
> }
>
> static int devx_async_event_close(struct inode *inode, struct file *filp)
> {
> + struct ib_uobject *uobj = filp->private_data;
> + struct devx_async_event_file *ev_file =
> + container_of(uobj, struct devx_async_event_file, uobj);
> + struct devx_event_subscription *event_sub, *event_sub_tmp;
> + struct devx_async_event_data *entry, *tmp;
> +
> + mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock);
> + /* delete the subscriptions which are related to this FD */
> + list_for_each_entry_safe(event_sub, event_sub_tmp,
> + &ev_file->subscribed_events_list, file_list)
> + devx_cleanup_subscription(ev_file->dev, event_sub, true);
> + mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock);
> +
> + /* free the pending events allocation */
> + if (!(ev_file->ev_queue.flags &
> + MLX5_IB_UAPI_DEVX_CREATE_EVENT_CHANNEL_FLAGS_OMIT_EV_DATA)) {
> + spin_lock_irq(&ev_file->ev_queue.lock);
> + list_for_each_entry_safe(entry, tmp,
> + &ev_file->ev_queue.event_list, list)
> + kfree(entry); /* read can't come any nore */
spelling
> + spin_unlock_irq(&ev_file->ev_queue.lock);
> + }
> uverbs_close_fd(filp);
> + put_device(&ev_file->dev->ib_dev.dev);
> return 0;
> }
>
> @@ -2374,6 +2705,17 @@ static int devx_hot_unplug_async_cmd_event_file(struct ib_uobject *uobj,
> static int devx_hot_unplug_async_event_file(struct ib_uobject *uobj,
> enum rdma_remove_reason why)
> {
> + struct devx_async_event_file *ev_file =
> + container_of(uobj, struct devx_async_event_file,
> + uobj);
> + struct devx_async_event_queue *ev_queue = &ev_file->ev_queue;
> +
> + spin_lock_irq(&ev_queue->lock);
> + ev_queue->is_destroyed = 1;
> + spin_unlock_irq(&ev_queue->lock);
> +
> + if (why == RDMA_REMOVE_DRIVER_REMOVE)
> + wake_up_interruptible(&ev_queue->poll_wait);
Why isn't this wakeup always done?
Jason
^ permalink raw reply
* Re: [PATCH rdma-next v1 12/12] IB/mlx5: Add DEVX support for CQ events
From: Jason Gunthorpe @ 2019-06-24 12:04 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
In-Reply-To: <20190618171540.11729-13-leon@kernel.org>
On Tue, Jun 18, 2019 at 08:15:40PM +0300, Leon Romanovsky wrote:
> From: Yishai Hadas <yishaih@mellanox.com>
>
> Add DEVX support for CQ events by creating and destroying the CQ via
> mlx5_core and set an handler to manage its completions.
>
> Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> drivers/infiniband/hw/mlx5/devx.c | 40 +++++++++++++++++++++++++++++++
> 1 file changed, 40 insertions(+)
>
> diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
> index 49fdce95d6d9..91ccd58ebc05 100644
> +++ b/drivers/infiniband/hw/mlx5/devx.c
> @@ -19,9 +19,12 @@
> #define UVERBS_MODULE_NAME mlx5_ib
> #include <rdma/uverbs_named_ioctl.h>
>
> +static void dispatch_event_fd(struct list_head *fd_list, const void *data);
> +
> enum devx_obj_flags {
> DEVX_OBJ_FLAGS_INDIRECT_MKEY = 1 << 0,
> DEVX_OBJ_FLAGS_DCT = 1 << 1,
> + DEVX_OBJ_FLAGS_CQ = 1 << 2,
> };
>
> struct devx_async_data {
> @@ -94,6 +97,7 @@ struct devx_async_event_file {
> #define MLX5_MAX_DESTROY_INBOX_SIZE_DW MLX5_ST_SZ_DW(delete_fte_in)
> struct devx_obj {
> struct mlx5_core_dev *mdev;
> + struct mlx5_ib_dev *ib_dev;
This seems strange, why would we need to store the core_dev and the ib_dev
in a struct when ibdev->mdev == core_dev?
Jason
^ permalink raw reply
* KASAN: global-out-of-bounds Read in qmi_wwan_probe
From: syzbot @ 2019-06-24 12:07 UTC (permalink / raw)
To: andreyknvl, bjorn, davem, linux-kernel, linux-usb, netdev,
syzkaller-bugs
Hello,
syzbot found the following crash on:
HEAD commit: 9939f56e usb-fuzzer: main usb gadget fuzzer driver
git tree: https://github.com/google/kasan.git usb-fuzzer
console output: https://syzkaller.appspot.com/x/log.txt?x=1615a669a00000
kernel config: https://syzkaller.appspot.com/x/.config?x=df134eda130bb43a
dashboard link: https://syzkaller.appspot.com/bug?extid=b68605d7fadd21510de1
compiler: gcc (GCC) 9.0.0 20181231 (experimental)
syz repro: https://syzkaller.appspot.com/x/repro.syz?x=10630af6a00000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=1127da69a00000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+b68605d7fadd21510de1@syzkaller.appspotmail.com
usb 1-1: new high-speed USB device number 2 using dummy_hcd
usb 1-1: Using ep0 maxpacket: 8
usb 1-1: New USB device found, idVendor=12d1, idProduct=14f1,
bcdDevice=d4.d9
usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0
usb 1-1: config 0 descriptor??
==================================================================
BUG: KASAN: global-out-of-bounds in qmi_wwan_probe+0x342/0x360
drivers/net/usb/qmi_wwan.c:1417
Read of size 8 at addr ffffffff8618c140 by task kworker/1:1/22
CPU: 1 PID: 22 Comm: kworker/1:1 Not tainted 5.2.0-rc5+ #11
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Workqueue: usb_hub_wq hub_event
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0xca/0x13e lib/dump_stack.c:113
print_address_description+0x67/0x231 mm/kasan/report.c:188
__kasan_report.cold+0x1a/0x32 mm/kasan/report.c:317
kasan_report+0xe/0x20 mm/kasan/common.c:614
qmi_wwan_probe+0x342/0x360 drivers/net/usb/qmi_wwan.c:1417
usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361
really_probe+0x281/0x660 drivers/base/dd.c:509
driver_probe_device+0x104/0x210 drivers/base/dd.c:670
__device_attach_driver+0x1c2/0x220 drivers/base/dd.c:777
bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches
^ permalink raw reply
* Re: WARNING: ODEBUG bug in netdev_freemem (2)
From: Eric Dumazet @ 2019-06-24 12:08 UTC (permalink / raw)
To: Dmitry Vyukov, Thomas Gleixner
Cc: syzbot, Alexander Duyck, amritha.nambiar, Andy Shevchenko,
David Miller, Dmitry Torokhov, Florian Fainelli,
Greg Kroah-Hartman, Ido Schimmel, LKML, netdev, syzkaller-bugs,
tyhicks, wanghai26, yuehaibing
In-Reply-To: <CACT4Y+Y_TadXGE_CVFa4fKqrbpAD4i5WGem9StgoyP_YAVraXw@mail.gmail.com>
On 6/24/19 3:54 AM, Dmitry Vyukov wrote:
> On Mon, Jun 24, 2019 at 11:34 AM Thomas Gleixner <tglx@linutronix.de> wrote:
>>
>> On Mon, 24 Jun 2019, syzbot wrote:
>>
>>> Hello,
>>>
>>> syzbot found the following crash on:
>>>
>>> HEAD commit: fd6b99fa Merge branch 'akpm' (patches from Andrew)
>>> git tree: upstream
>>> console output: https://syzkaller.appspot.com/x/log.txt?x=144de256a00000
>>> kernel config: https://syzkaller.appspot.com/x/.config?x=fa9f7e1b6a8bb586
>>> dashboard link: https://syzkaller.appspot.com/bug?extid=c4521ac872a4ccc3afec
>>> compiler: gcc (GCC) 9.0.0 20181231 (experimental)
>>>
>>> Unfortunately, I don't have any reproducer for this crash yet.
>>>
>>> IMPORTANT: if you fix the bug, please add the following tag to the commit:
>>> Reported-by: syzbot+c4521ac872a4ccc3afec@syzkaller.appspotmail.com
>>>
>>> device hsr_slave_0 left promiscuous mode
>>> team0 (unregistering): Port device team_slave_1 removed
>>> team0 (unregistering): Port device team_slave_0 removed
>>> bond0 (unregistering): Releasing backup interface bond_slave_1
>>> bond0 (unregistering): Releasing backup interface bond_slave_0
>>> bond0 (unregistering): Released all slaves
>>> ------------[ cut here ]------------
>>> ODEBUG: free active (active state 0) object type: timer_list hint:
>>> delayed_work_timer_fn+0x0/0x90 arch/x86/include/asm/paravirt.h:767
>>
>> One of the cleaned up devices has left an active timer which belongs to a
>> delayed work. That's all I can decode out of that splat. :(
>
> Hi Thomas,
>
> If ODEBUG would memorize full stack traces for object allocation
> (using lib/stackdepot.c), it would make this splat actionable, right?
> I've fixed https://bugzilla.kernel.org/show_bug.cgi?id=203969 for this.
>
Not sure this would help in this case as some netdev are allocated through a generic helper.
The driver specific portion might not show up in the stack trace.
It would be nice here to get the work queue function pointer,
so that it gives us a clue which driver needs a fix.
^ permalink raw reply
* [PATCH v5 0/5] net: macb: cover letter
From: Parshuram Thombare @ 2019-06-24 12:10 UTC (permalink / raw)
To: andrew, nicolas.ferre, davem, f.fainelli
Cc: linux, netdev, hkallweit1, linux-kernel, rafalc, aniljoy, piotrs,
pthombar
Hello !
This is 5th version of patch set containing following patches
for Cadence ethernet controller driver.
1. 0001-net-macb-add-phylink-support.patch
Replace phylib API's with phylink API's.
2. 0002-net-macb-add-support-for-sgmii-MAC-PHY-interface.patch
This patch add support for SGMII mode.
3. 0004-net-macb-add-support-for-c45-PHY.patch
This patch is to support C45 PHY.
4. 0005-net-macb-add-support-for-high-speed-interface
This patch add support for 10G USXGMII PCS in fixed mode.
5. 0006-net-macb-parameter-added-to-cadence-ethernet-controller-DT-binding
New parameter added to Cadence ethernet controller DT binding
for USXGMII interface.
Changes in v2:
1. Dropped patch configuring TI PHY DP83867 from
Cadence PCI wrapper driver.
2. Removed code registering emulated PHY for fixed mode.
3. Code reformatting as per Andrew's and Florian's suggestions.
Changes in v3:
Based on Russell's suggestions
1. Configure MAC in mac_config only for non in-band modes
2. Handle dynamic phy_mode changes in mac_config
3. Move MAC configurations to mac_config
4. Removed seemingly redundant check for phylink handle
5. Removed code from mac_an_restart and mac_link_state
now just return -EOPNOTSUPP
Changes in v4:
1. Removed PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_1000BASEX and
2.5G PHY_INTERFACE_MODE_SGMII phy modes from supported modes
Changes in v5:
1. Code refactoring
Parshuram Thombare (5):
net: macb: add phylink support
net: macb: add support for sgmii MAC-PHY interface
net: macb: add support for c45 PHY
net: macb: add support for high speed interface
net: macb: parameter added to cadence ethernet controller DT binding
.../devicetree/bindings/net/macb.txt | 3 +
drivers/net/ethernet/cadence/Kconfig | 2 +-
drivers/net/ethernet/cadence/macb.h | 113 +++-
drivers/net/ethernet/cadence/macb_main.c | 593 +++++++++++++-----
4 files changed, 528 insertions(+), 183 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH v5 1/5] net: macb: add phylink support
From: Parshuram Thombare @ 2019-06-24 12:10 UTC (permalink / raw)
To: andrew, nicolas.ferre, davem, f.fainelli
Cc: linux, netdev, hkallweit1, linux-kernel, rafalc, aniljoy, piotrs,
pthombar
In-Reply-To: <1561378210-11033-1-git-send-email-pthombar@cadence.com>
This patch replace phylib API's by phylink API's.
Signed-off-by: Parshuram Thombare <pthombar@cadence.com>
---
drivers/net/ethernet/cadence/Kconfig | 2 +-
drivers/net/ethernet/cadence/macb.h | 3 +
drivers/net/ethernet/cadence/macb_main.c | 301 ++++++++++++-----------
3 files changed, 163 insertions(+), 143 deletions(-)
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 1766697c9c5a..d71411a71587 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -22,7 +22,7 @@ if NET_VENDOR_CADENCE
config MACB
tristate "Cadence MACB/GEM support"
depends on HAS_DMA
- select PHYLIB
+ select PHYLINK
---help---
The Cadence MACB ethernet interface is found on many Atmel AT32 and
AT91 parts. This driver also supports the Cadence GEM (Gigabit
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 6ff123da6a14..8629d345af31 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -11,6 +11,7 @@
#include <linux/ptp_clock_kernel.h>
#include <linux/net_tstamp.h>
#include <linux/interrupt.h>
+#include <linux/phylink.h>
#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP)
#define MACB_EXT_DESC
@@ -1224,6 +1225,8 @@ struct macb {
u32 rx_intr_mask;
struct macb_pm_data pm_data;
+ struct phylink *pl;
+ struct phylink_config pl_config;
};
#ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b4fa0111cd7a..ac5b233cd2e5 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -36,6 +36,7 @@
#include <linux/tcp.h>
#include <linux/iopoll.h>
#include <linux/pm_runtime.h>
+#include <linux/phylink.h>
#include "macb.h"
/* This structure is only used for MACB on SiFive FU540 devices */
@@ -435,115 +436,142 @@ static void macb_set_tx_clk(struct clk *clk, int speed, struct net_device *dev)
netdev_err(dev, "adjusting tx_clk failed.\n");
}
-static void macb_handle_link_change(struct net_device *dev)
+static void gem_phylink_validate(struct phylink_config *pl_config,
+ unsigned long *supported,
+ struct phylink_link_state *state)
{
- struct macb *bp = netdev_priv(dev);
- struct phy_device *phydev = dev->phydev;
- unsigned long flags;
- int status_change = 0;
+ struct net_device *netdev = to_net_dev(pl_config->dev);
+ struct macb *bp = netdev_priv(netdev);
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+ switch (state->interface) {
+ case PHY_INTERFACE_MODE_GMII:
+ case PHY_INTERFACE_MODE_RGMII:
+ if (bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE) {
+ phylink_set(mask, 1000baseT_Full);
+ phylink_set(mask, 1000baseX_Full);
+ if (!(bp->caps & MACB_CAPS_NO_GIGABIT_HALF))
+ phylink_set(mask, 1000baseT_Half);
+ }
+ /* fallthrough */
+ case PHY_INTERFACE_MODE_MII:
+ case PHY_INTERFACE_MODE_RMII:
+ phylink_set(mask, 10baseT_Half);
+ phylink_set(mask, 10baseT_Full);
+ phylink_set(mask, 100baseT_Half);
+ phylink_set(mask, 100baseT_Full);
+ break;
+ default:
+ break;
+ }
- spin_lock_irqsave(&bp->lock, flags);
+ linkmode_and(supported, supported, mask);
+ linkmode_and(state->advertising, state->advertising, mask);
+}
- if (phydev->link) {
- if ((bp->speed != phydev->speed) ||
- (bp->duplex != phydev->duplex)) {
- u32 reg;
+static int gem_phylink_mac_link_state(struct phylink_config *pl_config,
+ struct phylink_link_state *state)
+{
+ return -EOPNOTSUPP;
+}
- reg = macb_readl(bp, NCFGR);
- reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
- if (macb_is_gem(bp))
- reg &= ~GEM_BIT(GBE);
+static void gem_mac_config(struct phylink_config *pl_config, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ struct net_device *netdev = to_net_dev(pl_config->dev);
+ struct macb *bp = netdev_priv(netdev);
+ unsigned long flags;
- if (phydev->duplex)
- reg |= MACB_BIT(FD);
- if (phydev->speed == SPEED_100)
- reg |= MACB_BIT(SPD);
- if (phydev->speed == SPEED_1000 &&
- bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE)
- reg |= GEM_BIT(GBE);
+ spin_lock_irqsave(&bp->lock, flags);
- macb_or_gem_writel(bp, NCFGR, reg);
+ if (!phylink_autoneg_inband(mode) &&
+ (bp->speed != state->speed ||
+ bp->duplex != state->duplex)) {
+ u32 reg;
- bp->speed = phydev->speed;
- bp->duplex = phydev->duplex;
- status_change = 1;
- }
- }
+ reg = macb_readl(bp, NCFGR);
+ reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
+ if (macb_is_gem(bp))
+ reg &= ~GEM_BIT(GBE);
+ if (state->duplex)
+ reg |= MACB_BIT(FD);
- if (phydev->link != bp->link) {
- if (!phydev->link) {
- bp->speed = 0;
- bp->duplex = -1;
+ switch (state->speed) {
+ case SPEED_1000:
+ reg |= GEM_BIT(GBE);
+ break;
+ case SPEED_100:
+ reg |= MACB_BIT(SPD);
+ break;
+ default:
+ break;
}
- bp->link = phydev->link;
+ macb_or_gem_writel(bp, NCFGR, reg);
- status_change = 1;
+ bp->speed = state->speed;
+ bp->duplex = state->duplex;
+
+ if (state->link)
+ macb_set_tx_clk(bp->tx_clk, state->speed, netdev);
}
spin_unlock_irqrestore(&bp->lock, flags);
+}
- if (status_change) {
- if (phydev->link) {
- /* Update the TX clock rate if and only if the link is
- * up and there has been a link change.
- */
- macb_set_tx_clk(bp->tx_clk, phydev->speed, dev);
+static void gem_mac_link_up(struct phylink_config *pl_config, unsigned int mode,
+ phy_interface_t interface, struct phy_device *phy)
+{
+ struct net_device *netdev = to_net_dev(pl_config->dev);
+ struct macb *bp = netdev_priv(netdev);
- netif_carrier_on(dev);
- netdev_info(dev, "link up (%d/%s)\n",
- phydev->speed,
- phydev->duplex == DUPLEX_FULL ?
- "Full" : "Half");
- } else {
- netif_carrier_off(dev);
- netdev_info(dev, "link down\n");
- }
- }
+ bp->link = 1;
+ /* Enable TX and RX */
+ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
+}
+
+static void gem_mac_link_down(struct phylink_config *pl_config,
+ unsigned int mode, phy_interface_t interface)
+{
+ struct net_device *netdev = to_net_dev(pl_config->dev);
+ struct macb *bp = netdev_priv(netdev);
+
+ bp->link = 0;
+ /* Disable TX and RX */
+ macb_writel(bp, NCR,
+ macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)));
}
+static const struct phylink_mac_ops gem_phylink_ops = {
+ .validate = gem_phylink_validate,
+ .mac_link_state = gem_phylink_mac_link_state,
+ .mac_config = gem_mac_config,
+ .mac_link_up = gem_mac_link_up,
+ .mac_link_down = gem_mac_link_down,
+};
+
/* based on au1000_eth. c*/
static int macb_mii_probe(struct net_device *dev)
{
struct macb *bp = netdev_priv(dev);
struct phy_device *phydev;
struct device_node *np;
- int ret, i;
+ int ret;
np = bp->pdev->dev.of_node;
ret = 0;
- if (np) {
- if (of_phy_is_fixed_link(np)) {
- bp->phy_node = of_node_get(np);
- } else {
- bp->phy_node = of_parse_phandle(np, "phy-handle", 0);
- /* fallback to standard phy registration if no
- * phy-handle was found nor any phy found during
- * dt phy registration
- */
- if (!bp->phy_node && !phy_find_first(bp->mii_bus)) {
- for (i = 0; i < PHY_MAX_ADDR; i++) {
- phydev = mdiobus_scan(bp->mii_bus, i);
- if (IS_ERR(phydev) &&
- PTR_ERR(phydev) != -ENODEV) {
- ret = PTR_ERR(phydev);
- break;
- }
- }
-
- if (ret)
- return -ENODEV;
- }
- }
+ bp->pl_config.dev = &dev->dev;
+ bp->pl_config.type = PHYLINK_NETDEV;
+ bp->pl = phylink_create(&bp->pl_config, of_fwnode_handle(np),
+ bp->phy_interface, &gem_phylink_ops);
+ if (IS_ERR(bp->pl)) {
+ netdev_err(dev,
+ "error creating PHYLINK: %ld\n", PTR_ERR(bp->pl));
+ return PTR_ERR(bp->pl);
}
- if (bp->phy_node) {
- phydev = of_phy_connect(dev, bp->phy_node,
- &macb_handle_link_change, 0,
- bp->phy_interface);
- if (!phydev)
- return -ENODEV;
- } else {
+ ret = phylink_of_phy_connect(bp->pl, np, 0);
+ if (ret == -ENODEV && bp->mii_bus) {
phydev = phy_find_first(bp->mii_bus);
if (!phydev) {
netdev_err(dev, "no PHY found\n");
@@ -551,29 +579,18 @@ static int macb_mii_probe(struct net_device *dev)
}
/* attach the mac to the phy */
- ret = phy_connect_direct(dev, phydev, &macb_handle_link_change,
- bp->phy_interface);
+ ret = phylink_connect_phy(bp->pl, phydev);
if (ret) {
netdev_err(dev, "Could not attach to PHY\n");
return ret;
}
}
- /* mask with MAC supported features */
- if (macb_is_gem(bp) && bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE)
- phy_set_max_speed(phydev, SPEED_1000);
- else
- phy_set_max_speed(phydev, SPEED_100);
-
- if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF)
- phy_remove_link_mode(phydev,
- ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
bp->link = 0;
bp->speed = 0;
bp->duplex = -1;
- return 0;
+ return ret;
}
static int macb_mii_init(struct macb *bp)
@@ -601,17 +618,7 @@ static int macb_mii_init(struct macb *bp)
dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
np = bp->pdev->dev.of_node;
- if (np && of_phy_is_fixed_link(np)) {
- if (of_phy_register_fixed_link(np) < 0) {
- dev_err(&bp->pdev->dev,
- "broken fixed-link specification %pOF\n", np);
- goto err_out_free_mdiobus;
- }
-
- err = mdiobus_register(bp->mii_bus);
- } else {
- err = of_mdiobus_register(bp->mii_bus, np);
- }
+ err = of_mdiobus_register(bp->mii_bus, np);
if (err)
goto err_out_free_fixed_link;
@@ -627,7 +634,6 @@ static int macb_mii_init(struct macb *bp)
err_out_free_fixed_link:
if (np && of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
-err_out_free_mdiobus:
of_node_put(bp->phy_node);
mdiobus_free(bp->mii_bus);
err_out:
@@ -2418,12 +2424,6 @@ static int macb_open(struct net_device *dev)
/* carrier starts down */
netif_carrier_off(dev);
- /* if the phy is not yet register, retry later*/
- if (!dev->phydev) {
- err = -EAGAIN;
- goto pm_exit;
- }
-
/* RX buffers initialization */
macb_init_rx_buffer_size(bp, bufsz);
@@ -2441,7 +2441,7 @@ static int macb_open(struct net_device *dev)
macb_init_hw(bp);
/* schedule a link state check */
- phy_start(dev->phydev);
+ phylink_start(bp->pl);
netif_tx_start_all_queues(dev);
@@ -2468,8 +2468,7 @@ static int macb_close(struct net_device *dev)
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
napi_disable(&queue->napi);
- if (dev->phydev)
- phy_stop(dev->phydev);
+ phylink_stop(bp->pl);
spin_lock_irqsave(&bp->lock, flags);
macb_reset_hw(bp);
@@ -3158,6 +3157,23 @@ static int gem_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
return ret;
}
+static int gem_ethtool_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct macb *bp = netdev_priv(netdev);
+
+ return phylink_ethtool_ksettings_get(bp->pl, cmd);
+}
+
+static int
+gem_ethtool_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct macb *bp = netdev_priv(netdev);
+
+ return phylink_ethtool_ksettings_set(bp->pl, cmd);
+}
+
static const struct ethtool_ops macb_ethtool_ops = {
.get_regs_len = macb_get_regs_len,
.get_regs = macb_get_regs,
@@ -3165,8 +3181,8 @@ static const struct ethtool_ops macb_ethtool_ops = {
.get_ts_info = ethtool_op_get_ts_info,
.get_wol = macb_get_wol,
.set_wol = macb_set_wol,
- .get_link_ksettings = phy_ethtool_get_link_ksettings,
- .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_link_ksettings = gem_ethtool_get_link_ksettings,
+ .set_link_ksettings = gem_ethtool_set_link_ksettings,
.get_ringparam = macb_get_ringparam,
.set_ringparam = macb_set_ringparam,
};
@@ -3179,8 +3195,8 @@ static const struct ethtool_ops gem_ethtool_ops = {
.get_ethtool_stats = gem_get_ethtool_stats,
.get_strings = gem_get_ethtool_strings,
.get_sset_count = gem_get_sset_count,
- .get_link_ksettings = phy_ethtool_get_link_ksettings,
- .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_link_ksettings = gem_ethtool_get_link_ksettings,
+ .set_link_ksettings = gem_ethtool_set_link_ksettings,
.get_ringparam = macb_get_ringparam,
.set_ringparam = macb_set_ringparam,
.get_rxnfc = gem_get_rxnfc,
@@ -3189,17 +3205,13 @@ static const struct ethtool_ops gem_ethtool_ops = {
static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
- struct phy_device *phydev = dev->phydev;
struct macb *bp = netdev_priv(dev);
if (!netif_running(dev))
return -EINVAL;
- if (!phydev)
- return -ENODEV;
-
if (!bp->ptp_info)
- return phy_mii_ioctl(phydev, rq, cmd);
+ return phylink_mii_ioctl(bp->pl, rq, cmd);
switch (cmd) {
case SIOCSHWTSTAMP:
@@ -3207,7 +3219,7 @@ static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
case SIOCGHWTSTAMP:
return bp->ptp_info->get_hwtst(dev, rq);
default:
- return phy_mii_ioctl(phydev, rq, cmd);
+ return phylink_mii_ioctl(bp->pl, rq, cmd);
}
}
@@ -3707,7 +3719,7 @@ static int at91ether_open(struct net_device *dev)
MACB_BIT(HRESP));
/* schedule a link state check */
- phy_start(dev->phydev);
+ phylink_start(lp->pl);
netif_start_queue(dev);
@@ -4180,13 +4192,12 @@ static int macb_probe(struct platform_device *pdev)
struct clk *tsu_clk = NULL;
unsigned int queue_mask, num_queues;
bool native_io;
- struct phy_device *phydev;
struct net_device *dev;
struct resource *regs;
void __iomem *mem;
const char *mac;
struct macb *bp;
- int err, val;
+ int err, val, phy_mode;
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mem = devm_ioremap_resource(&pdev->dev, regs);
@@ -4307,12 +4318,12 @@ static int macb_probe(struct platform_device *pdev)
macb_get_hwaddr(bp);
}
- err = of_get_phy_mode(np);
- if (err < 0)
+ phy_mode = of_get_phy_mode(np);
+ if (phy_mode < 0)
/* not found in DT, MII by default */
bp->phy_interface = PHY_INTERFACE_MODE_MII;
else
- bp->phy_interface = err;
+ bp->phy_interface = phy_mode;
/* IP specific init */
err = init(pdev);
@@ -4323,8 +4334,6 @@ static int macb_probe(struct platform_device *pdev)
if (err)
goto err_out_free_netdev;
- phydev = dev->phydev;
-
netif_carrier_off(dev);
err = register_netdev(dev);
@@ -4336,8 +4345,6 @@ static int macb_probe(struct platform_device *pdev)
tasklet_init(&bp->hresp_err_tasklet, macb_hresp_error_task,
(unsigned long)bp);
- phy_attached_info(phydev);
-
netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n",
macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
dev->base_addr, dev->irq, dev->dev_addr);
@@ -4348,7 +4355,9 @@ static int macb_probe(struct platform_device *pdev)
return 0;
err_out_unregister_mdio:
- phy_disconnect(dev->phydev);
+ rtnl_lock();
+ phylink_disconnect_phy(bp->pl);
+ rtnl_unlock();
mdiobus_unregister(bp->mii_bus);
of_node_put(bp->phy_node);
if (np && of_phy_is_fixed_link(np))
@@ -4382,13 +4391,18 @@ static int macb_remove(struct platform_device *pdev)
if (dev) {
bp = netdev_priv(dev);
- if (dev->phydev)
- phy_disconnect(dev->phydev);
+ if (bp->pl) {
+ rtnl_lock();
+ phylink_disconnect_phy(bp->pl);
+ rtnl_unlock();
+ }
mdiobus_unregister(bp->mii_bus);
if (np && of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
dev->phydev = NULL;
mdiobus_free(bp->mii_bus);
+ if (bp->pl)
+ phylink_destroy(bp->pl);
unregister_netdev(dev);
pm_runtime_disable(&pdev->dev);
@@ -4431,8 +4445,9 @@ static int __maybe_unused macb_suspend(struct device *dev)
for (q = 0, queue = bp->queues; q < bp->num_queues;
++q, ++queue)
napi_disable(&queue->napi);
- phy_stop(netdev->phydev);
- phy_suspend(netdev->phydev);
+ phylink_stop(bp->pl);
+ if (netdev->phydev)
+ phy_suspend(netdev->phydev);
spin_lock_irqsave(&bp->lock, flags);
macb_reset_hw(bp);
spin_unlock_irqrestore(&bp->lock, flags);
@@ -4480,9 +4495,11 @@ static int __maybe_unused macb_resume(struct device *dev)
for (q = 0, queue = bp->queues; q < bp->num_queues;
++q, ++queue)
napi_enable(&queue->napi);
- phy_resume(netdev->phydev);
- phy_init_hw(netdev->phydev);
- phy_start(netdev->phydev);
+ if (netdev->phydev) {
+ phy_resume(netdev->phydev);
+ phy_init_hw(netdev->phydev);
+ }
+ phylink_start(bp->pl);
}
bp->macbgem_ops.mog_init_rings(bp);
--
2.17.1
^ permalink raw reply related
* [PATCH v5 2/5] net: macb: add support for sgmii MAC-PHY interface
From: Parshuram Thombare @ 2019-06-24 12:11 UTC (permalink / raw)
To: andrew, nicolas.ferre, davem, f.fainelli
Cc: linux, netdev, hkallweit1, linux-kernel, rafalc, aniljoy, piotrs,
pthombar
In-Reply-To: <1561378210-11033-1-git-send-email-pthombar@cadence.com>
This patch add support for SGMII interface) and
2.5Gbps MAC in Cadence ethernet controller driver.
Signed-off-by: Parshuram Thombare <pthombar@cadence.com>
---
drivers/net/ethernet/cadence/macb.h | 54 +++++++++++++-----
drivers/net/ethernet/cadence/macb_main.c | 72 ++++++++++++++++++++++--
2 files changed, 109 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 8629d345af31..6d268283c318 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -77,6 +77,7 @@
#define MACB_RBQPH 0x04D4
/* GEM register offsets. */
+#define GEM_NCR 0x0000 /* Network Control */
#define GEM_NCFGR 0x0004 /* Network Config */
#define GEM_USRIO 0x000c /* User IO */
#define GEM_DMACFG 0x0010 /* DMA Configuration */
@@ -156,6 +157,7 @@
#define GEM_PEFTN 0x01f4 /* PTP Peer Event Frame Tx Ns */
#define GEM_PEFRSL 0x01f8 /* PTP Peer Event Frame Rx Sec Low */
#define GEM_PEFRN 0x01fc /* PTP Peer Event Frame Rx Ns */
+#define GEM_PCS_CTRL 0x0200 /* PCS Control */
#define GEM_DCFG1 0x0280 /* Design Config 1 */
#define GEM_DCFG2 0x0284 /* Design Config 2 */
#define GEM_DCFG3 0x0288 /* Design Config 3 */
@@ -271,6 +273,10 @@
#define MACB_IRXFCS_OFFSET 19
#define MACB_IRXFCS_SIZE 1
+/* GEM specific NCR bitfields. */
+#define GEM_TWO_PT_FIVE_GIG_OFFSET 29
+#define GEM_TWO_PT_FIVE_GIG_SIZE 1
+
/* GEM specific NCFGR bitfields. */
#define GEM_GBE_OFFSET 10 /* Gigabit mode enable */
#define GEM_GBE_SIZE 1
@@ -323,6 +329,9 @@
#define MACB_MDIO_SIZE 1
#define MACB_IDLE_OFFSET 2 /* The PHY management logic is idle */
#define MACB_IDLE_SIZE 1
+#define MACB_DUPLEX_OFFSET 3
+#define MACB_DUPLEX_SIZE 1
+
/* Bitfields in TSR */
#define MACB_UBR_OFFSET 0 /* Used bit read */
@@ -456,11 +465,17 @@
#define MACB_REV_OFFSET 0
#define MACB_REV_SIZE 16
+/* Bitfields in PCS_CONTROL. */
+#define GEM_PCS_CTRL_RST_OFFSET 15
+#define GEM_PCS_CTRL_RST_SIZE 1
+
/* Bitfields in DCFG1. */
#define GEM_IRQCOR_OFFSET 23
#define GEM_IRQCOR_SIZE 1
#define GEM_DBWDEF_OFFSET 25
#define GEM_DBWDEF_SIZE 3
+#define GEM_NO_PCS_OFFSET 0
+#define GEM_NO_PCS_SIZE 1
/* Bitfields in DCFG2. */
#define GEM_RX_PKT_BUFF_OFFSET 20
@@ -633,19 +648,32 @@
#define MACB_MAN_CODE 2
/* Capability mask bits */
-#define MACB_CAPS_ISR_CLEAR_ON_WRITE 0x00000001
-#define MACB_CAPS_USRIO_HAS_CLKEN 0x00000002
-#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII 0x00000004
-#define MACB_CAPS_NO_GIGABIT_HALF 0x00000008
-#define MACB_CAPS_USRIO_DISABLED 0x00000010
-#define MACB_CAPS_JUMBO 0x00000020
-#define MACB_CAPS_GEM_HAS_PTP 0x00000040
-#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
-#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100
-#define MACB_CAPS_FIFO_MODE 0x10000000
-#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
-#define MACB_CAPS_SG_DISABLED 0x40000000
-#define MACB_CAPS_MACB_IS_GEM 0x80000000
+#define MACB_CAPS_ISR_CLEAR_ON_WRITE BIT(0)
+#define MACB_CAPS_USRIO_HAS_CLKEN BIT(1)
+#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII BIT(2)
+#define MACB_CAPS_NO_GIGABIT_HALF BIT(3)
+#define MACB_CAPS_USRIO_DISABLED BIT(4)
+#define MACB_CAPS_JUMBO BIT(5)
+#define MACB_CAPS_GEM_HAS_PTP BIT(6)
+#define MACB_CAPS_BD_RD_PREFETCH BIT(7)
+#define MACB_CAPS_NEEDS_RSTONUBR BIT(8)
+#define MACB_CAPS_FIFO_MODE BIT(28)
+#define MACB_CAPS_GIGABIT_MODE_AVAILABLE BIT(29)
+#define MACB_CAPS_SG_DISABLED BIT(30)
+#define MACB_CAPS_MACB_IS_GEM BIT(31)
+#define MACB_CAPS_PCS BIT(24)
+#define MACB_CAPS_MACB_IS_GEM_GXL BIT(25)
+
+#define MACB_GEM7010_IDNUM 0x009
+#define MACB_GEM7014_IDNU 0x107
+#define MACB_GEM7014A_IDNUM 0x207
+#define MACB_GEM7016_IDNUM 0x10a
+#define MACB_GEM7017_IDNUM 0x00a
+#define MACB_GEM7017A_IDNUM 0x20a
+#define MACB_GEM7020_IDNUM 0x003
+#define MACB_GEM7021_IDNUM 0x00c
+#define MACB_GEM7021A_IDNUM 0x20c
+#define MACB_GEM7022_IDNUM 0x00b
/* LSO settings */
#define MACB_LSO_UFO_ENABLE 0x01
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index ac5b233cd2e5..572691d948e9 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -445,6 +445,8 @@ static void gem_phylink_validate(struct phylink_config *pl_config,
__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
switch (state->interface) {
+ case PHY_INTERFACE_MODE_NA:
+ case PHY_INTERFACE_MODE_SGMII:
case PHY_INTERFACE_MODE_GMII:
case PHY_INTERFACE_MODE_RGMII:
if (bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE) {
@@ -480,10 +482,31 @@ static void gem_mac_config(struct phylink_config *pl_config, unsigned int mode,
{
struct net_device *netdev = to_net_dev(pl_config->dev);
struct macb *bp = netdev_priv(netdev);
+ bool change_interface = bp->phy_interface != state->interface;
unsigned long flags;
spin_lock_irqsave(&bp->lock, flags);
+ if (change_interface) {
+ bp->phy_interface = state->interface;
+ gem_writel(bp, NCR, ~GEM_BIT(TWO_PT_FIVE_GIG) &
+ gem_readl(bp, NCR));
+
+ if (state->interface == PHY_INTERFACE_MODE_SGMII) {
+ gem_writel(bp, NCFGR, GEM_BIT(SGMIIEN) |
+ GEM_BIT(PCSSEL) |
+ gem_readl(bp, NCFGR));
+ } else {
+ /* Disable SGMII mode and PCS */
+ gem_writel(bp, NCFGR, ~(GEM_BIT(SGMIIEN) |
+ GEM_BIT(PCSSEL)) &
+ gem_readl(bp, NCFGR));
+ /* Reset PCS */
+ gem_writel(bp, PCS_CTRL, gem_readl(bp, PCS_CTRL) |
+ GEM_BIT(PCS_CTRL_RST));
+ }
+ }
+
if (!phylink_autoneg_inband(mode) &&
(bp->speed != state->speed ||
bp->duplex != state->duplex)) {
@@ -493,6 +516,7 @@ static void gem_mac_config(struct phylink_config *pl_config, unsigned int mode,
reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
if (macb_is_gem(bp))
reg &= ~GEM_BIT(GBE);
+
if (state->duplex)
reg |= MACB_BIT(FD);
@@ -587,8 +611,8 @@ static int macb_mii_probe(struct net_device *dev)
}
bp->link = 0;
- bp->speed = 0;
- bp->duplex = -1;
+ bp->speed = SPEED_UNKNOWN;
+ bp->duplex = DUPLEX_UNKNOWN;
return ret;
}
@@ -3337,6 +3361,22 @@ static void macb_configure_caps(struct macb *bp,
dcfg = gem_readl(bp, DCFG1);
if (GEM_BFEXT(IRQCOR, dcfg) == 0)
bp->caps |= MACB_CAPS_ISR_CLEAR_ON_WRITE;
+ if (GEM_BFEXT(NO_PCS, dcfg) == 0)
+ bp->caps |= MACB_CAPS_PCS;
+ switch (MACB_BFEXT(IDNUM, macb_readl(bp, MID))) {
+ case MACB_GEM7016_IDNUM:
+ case MACB_GEM7017_IDNUM:
+ case MACB_GEM7017A_IDNUM:
+ case MACB_GEM7020_IDNUM:
+ case MACB_GEM7021_IDNUM:
+ case MACB_GEM7021A_IDNUM:
+ case MACB_GEM7022_IDNUM:
+ bp->caps |= MACB_CAPS_USRIO_DISABLED;
+ bp->caps |= MACB_CAPS_MACB_IS_GEM_GXL;
+ break;
+ default:
+ break;
+ }
dcfg = gem_readl(bp, DCFG2);
if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0)
bp->caps |= MACB_CAPS_FIFO_MODE;
@@ -4319,11 +4359,35 @@ static int macb_probe(struct platform_device *pdev)
}
phy_mode = of_get_phy_mode(np);
- if (phy_mode < 0)
+ if (phy_mode < 0) {
/* not found in DT, MII by default */
bp->phy_interface = PHY_INTERFACE_MODE_MII;
- else
+ } else if (bp->caps & MACB_CAPS_MACB_IS_GEM_GXL) {
+ u32 interface_supported = 1;
+
+ if (phy_mode == PHY_INTERFACE_MODE_SGMII) {
+ if (!(bp->caps & MACB_CAPS_PCS))
+ interface_supported = 0;
+ } else if (phy_mode == PHY_INTERFACE_MODE_GMII ||
+ phy_mode == PHY_INTERFACE_MODE_RGMII) {
+ if (!macb_is_gem(bp))
+ interface_supported = 0;
+ } else if (phy_mode != PHY_INTERFACE_MODE_RMII &&
+ phy_mode != PHY_INTERFACE_MODE_MII) {
+ /* Add new mode before this */
+ interface_supported = 0;
+ }
+
+ if (!interface_supported) {
+ netdev_err(dev, "Phy mode %s not supported",
+ phy_modes(phy_mode));
+ goto err_out_free_netdev;
+ }
+
+ bp->phy_interface = phy_mode;
+ } else {
bp->phy_interface = phy_mode;
+ }
/* IP specific init */
err = init(pdev);
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox