* [net-next 10/15] ethtool: add ethtool_intersect_link_masks
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This function provides a way to intersect two link masks together to
find the common ground between them. For example in i40e, the driver
first generates link masks for what is supported by the PHY type. The
driver then gets the link masks for what the NVM supports. The
resulting intersection between them yields what can truly be supported.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/linux/ethtool.h | 10 ++++++++++
net/core/ethtool.c | 16 ++++++++++++++++
2 files changed, 26 insertions(+)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 4587a4c36923..c77fa3529e15 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -163,6 +163,16 @@ extern int
__ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *link_ksettings);
+/**
+ * ethtool_intersect_link_masks - Given two link masks, AND them together
+ * @dst: first mask and where result is stored
+ * @src: second mask to intersect with
+ *
+ * Given two link mode masks, AND them together and save the result in dst.
+ */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+ struct ethtool_link_ksettings *src);
+
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 3228411ada0f..0c406306792a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data)
return 0;
}
+/* Given two link masks, AND them together and save the result in dst. */
+void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst,
+ struct ethtool_link_ksettings *src)
+{
+ unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS);
+ unsigned int idx = 0;
+
+ for (; idx < size; idx++) {
+ dst->link_modes.supported[idx] &=
+ src->link_modes.supported[idx];
+ dst->link_modes.advertising[idx] &=
+ src->link_modes.advertising[idx];
+ }
+}
+EXPORT_SYMBOL(ethtool_intersect_link_masks);
+
void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
u32 legacy_u32)
{
--
2.14.2
^ permalink raw reply related
* [net-next 07/15] i40e: fix whitespace issues in i40e_ethtool.c
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
There's a number of minor incidental whitespace issues in this file.
This addresses most of the ones I could find.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 44 +++++++++++---------------
1 file changed, 18 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index e40fb559dacb..89ab398a7d30 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -511,7 +511,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
break;
default:
/* if we got here and link is up something bad is afoot */
- netdev_info(netdev, "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
+ netdev_info(netdev,
+ "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
hw_link_info->phy_type);
}
@@ -614,14 +615,12 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
ks->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
AUTONEG_ENABLE : AUTONEG_DISABLE);
+ /* Set media type settings */
switch (hw->phy.media_type) {
case I40E_MEDIA_TYPE_BACKPLANE:
- ethtool_link_ksettings_add_link_mode(ks, supported,
- Autoneg);
- ethtool_link_ksettings_add_link_mode(ks, supported,
- Backplane);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
ethtool_link_ksettings_add_link_mode(ks, advertising,
Backplane);
ks->base.port = PORT_NONE;
@@ -652,16 +651,14 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
switch (hw->fc.requested_mode) {
case I40E_FC_FULL:
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Pause);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
break;
case I40E_FC_TX_PAUSE:
ethtool_link_ksettings_add_link_mode(ks, advertising,
Asym_Pause);
break;
case I40E_FC_RX_PAUSE:
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Pause);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Pause);
ethtool_link_ksettings_add_link_mode(ks, advertising,
Asym_Pause);
break;
@@ -708,17 +705,14 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
i40e_partition_setting_complaint(pf);
return -EOPNOTSUPP;
}
-
if (vsi != pf->vsi[pf->lan_vsi])
return -EOPNOTSUPP;
-
if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET &&
hw->phy.media_type != I40E_MEDIA_TYPE_FIBER &&
hw->phy.media_type != I40E_MEDIA_TYPE_BACKPLANE &&
hw->phy.media_type != I40E_MEDIA_TYPE_DA &&
hw->phy.link_info.link_info & I40E_AQ_LINK_UP)
return -EOPNOTSUPP;
-
if (hw->device_id == I40E_DEV_ID_KX_B ||
hw->device_id == I40E_DEV_ID_KX_C ||
hw->device_id == I40E_DEV_ID_20G_KR2 ||
@@ -844,7 +838,6 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
*/
if (!config.link_speed)
config.link_speed = abilities.link_speed;
-
if (change || (abilities.link_speed != config.link_speed)) {
/* copy over the rest of the abilities */
config.phy_type = abilities.phy_type;
@@ -872,7 +865,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
/* make the aq call */
status = i40e_aq_set_phy_config(hw, &config, NULL);
if (status) {
- netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n",
+ netdev_info(netdev,
+ "Set phy config failed, err %s aq_err %s\n",
i40e_stat_str(hw, status),
i40e_aq_str(hw, hw->aq.asq_last_status));
err = -EAGAIN;
@@ -881,7 +875,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
status = i40e_update_link_info(hw);
if (status)
- netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n",
+ netdev_dbg(netdev,
+ "Updating link info failed with err %s aq_err %s\n",
i40e_stat_str(hw, status),
i40e_aq_str(hw, hw->aq.asq_last_status));
@@ -2072,14 +2067,13 @@ static int __i40e_get_coalesce(struct net_device *netdev,
ec->tx_max_coalesced_frames_irq = vsi->work_limit;
ec->rx_max_coalesced_frames_irq = vsi->work_limit;
- /* rx and tx usecs has per queue value. If user doesn't specify the queue,
- * return queue 0's value to represent.
+ /* rx and tx usecs has per queue value. If user doesn't specify the
+ * queue, return queue 0's value to represent.
*/
- if (queue < 0) {
+ if (queue < 0)
queue = 0;
- } else if (queue >= vsi->num_queue_pairs) {
+ else if (queue >= vsi->num_queue_pairs)
return -EINVAL;
- }
rx_ring = vsi->rx_rings[queue];
tx_ring = vsi->tx_rings[queue];
@@ -2093,7 +2087,6 @@ static int __i40e_get_coalesce(struct net_device *netdev,
ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC;
ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC;
-
/* we use the _usecs_high to store/set the interrupt rate limit
* that the hardware supports, that almost but not quite
* fits the original intent of the ethtool variable,
@@ -2143,7 +2136,6 @@ static int i40e_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
*
* Change the ITR settings for a specific queue.
**/
-
static void i40e_set_itr_per_queue(struct i40e_vsi *vsi,
struct ethtool_coalesce *ec,
int queue)
@@ -2265,8 +2257,8 @@ static int __i40e_set_coalesce(struct net_device *netdev,
vsi->int_rate_limit);
}
- /* rx and tx usecs has per queue value. If user doesn't specify the queue,
- * apply to all queues.
+ /* rx and tx usecs has per queue value. If user doesn't specify the
+ * queue, apply to all queues.
*/
if (queue < 0) {
for (i = 0; i < vsi->num_queue_pairs; i++)
--
2.14.2
^ permalink raw reply related
* [net-next 09/15] i40e: Add new PHY types for 25G AOC and ACC support
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem
Cc: Sudheer Mogilappagari, netdev, nhorman, sassmann, jogreene,
Krzysztof Malek, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
This patch adds support for 25G Active Optical Cables (AOC) and Active
Copper Cables (ACC) PHY types.
Signed-off-by: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Signed-off-by: Krzysztof Malek <krzysztof.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 4 ++++
drivers/net/ethernet/intel/i40e/i40e_common.c | 2 ++
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 ++
drivers/net/ethernet/intel/i40e/i40e_type.h | 4 ++++
drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 4 ++++
5 files changed, 16 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index a8f65aed5421..6a5db1b33fa2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1771,6 +1771,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_25GBASE_AOC = 0x23,
+ I40E_PHY_TYPE_25GBASE_ACC = 0x24,
I40E_PHY_TYPE_MAX,
I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
I40E_PHY_TYPE_EMPTY = 0xFE,
@@ -1831,6 +1833,8 @@ struct i40e_aq_get_phy_abilities_resp {
#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02
#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04
#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08
+#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10
+#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20
u8 fec_cfg_curr_mod_ext_info;
#define I40E_AQ_ENABLE_FEC_KR 0x01
#define I40E_AQ_ENABLE_FEC_RS 0x02
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index aeb497258f20..8d0ee006606b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1180,6 +1180,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
case I40E_PHY_TYPE_40GBASE_AOC:
case I40E_PHY_TYPE_10GBASE_AOC:
case I40E_PHY_TYPE_25GBASE_CR:
+ case I40E_PHY_TYPE_25GBASE_AOC:
+ case I40E_PHY_TYPE_25GBASE_ACC:
media = I40E_MEDIA_TYPE_DA;
break;
case I40E_PHY_TYPE_1000BASE_KX:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 30deae77e745..a4210ccdaa5f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -502,6 +502,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
case I40E_PHY_TYPE_25GBASE_CR:
case I40E_PHY_TYPE_25GBASE_SR:
case I40E_PHY_TYPE_25GBASE_LR:
+ case I40E_PHY_TYPE_25GBASE_AOC:
+ case I40E_PHY_TYPE_25GBASE_ACC:
supported = SUPPORTED_Autoneg;
advertising = ADVERTISED_Autoneg;
/* TODO: add speeds when ethtool is ready to support*/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 0410fcbdbb94..17a99b53acd9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -271,6 +271,10 @@ struct i40e_phy_info {
I40E_PHY_TYPE_OFFSET)
#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \
I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_AOC BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \
+ I40E_PHY_TYPE_OFFSET)
#define I40E_HW_CAP_MAX_GPIO 30
/* Capabilities of a PF or a VF or the whole device */
struct i40e_hw_capabilities {
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index 60c892f559b9..463e331a70a9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1767,6 +1767,8 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_25GBASE_CR = 0x20,
I40E_PHY_TYPE_25GBASE_SR = 0x21,
I40E_PHY_TYPE_25GBASE_LR = 0x22,
+ I40E_PHY_TYPE_25GBASE_AOC = 0x23,
+ I40E_PHY_TYPE_25GBASE_ACC = 0x24,
I40E_PHY_TYPE_MAX,
I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD,
I40E_PHY_TYPE_EMPTY = 0xFE,
@@ -1827,6 +1829,8 @@ struct i40e_aq_get_phy_abilities_resp {
#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02
#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04
#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08
+#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10
+#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20
u8 fec_cfg_curr_mod_ext_info;
#define I40E_AQ_ENABLE_FEC_KR 0x01
#define I40E_AQ_ENABLE_FEC_RS 0x02
--
2.14.2
^ permalink raw reply related
* [net-next 08/15] i40e: group autoneg PHY types together
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This separates the setting of autoneg in i40e_phy_types_to_ethtool into
its own conditional. Doing this adds clarity as what PHYs
support/advertise autoneg and makes it easier to add new PHY types in
the future.
This also fixes an issue on devices with CRT_RETIMER where advertising
autoneg was being set, but supported autoneg was not.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 85 +++++++++++++-------------
1 file changed, 41 insertions(+), 44 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 89ab398a7d30..30deae77e745 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -268,9 +268,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
*advertising = 0x0;
if (phy_types & I40E_CAP_PHY_TYPE_SGMII) {
- *supported |= SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_1000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
*advertising |= ADVERTISED_1000baseT_Full;
if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
@@ -289,9 +287,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) {
- *supported |= SUPPORTED_Autoneg |
- SUPPORTED_10000baseT_Full;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_10000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
*advertising |= ADVERTISED_10000baseT_Full;
}
@@ -301,16 +297,12 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
*supported |= SUPPORTED_40000baseCR4_Full;
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU ||
phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) {
- *supported |= SUPPORTED_Autoneg |
- SUPPORTED_40000baseCR4_Full;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_40000baseCR4_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB)
*advertising |= ADVERTISED_40000baseCR4_Full;
}
if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
- *supported |= SUPPORTED_Autoneg |
- SUPPORTED_100baseT_Full;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_100baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
*advertising |= ADVERTISED_100baseT_Full;
}
@@ -318,9 +310,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) {
- *supported |= SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_1000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
*advertising |= ADVERTISED_1000baseT_Full;
}
@@ -329,47 +319,54 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
*supported |= SUPPORTED_40000baseLR4_Full;
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
- *supported |= SUPPORTED_40000baseKR4_Full |
- SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_40000baseKR4_Full |
- ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_40000baseKR4_Full;
+ *advertising |= ADVERTISED_40000baseKR4_Full;
}
if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) {
- *supported |= SUPPORTED_20000baseKR2_Full |
- SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_20000baseKR2_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB)
*advertising |= ADVERTISED_20000baseKR2_Full;
}
- if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) {
- if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
- *supported |= SUPPORTED_10000baseKR_Full |
- SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_Autoneg;
- if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
- *advertising |= ADVERTISED_10000baseKR_Full;
- }
if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) {
- *supported |= SUPPORTED_10000baseKX4_Full |
- SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_Autoneg;
+ *supported |= SUPPORTED_10000baseKX4_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
*advertising |= ADVERTISED_10000baseKX4_Full;
}
- if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) {
- if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
- *supported |= SUPPORTED_1000baseKX_Full |
- SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_Autoneg;
+ if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR &&
+ !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+ *supported |= SUPPORTED_10000baseKR_Full;
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ *advertising |= ADVERTISED_10000baseKR_Full;
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX &&
+ !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
+ *supported |= SUPPORTED_1000baseKX_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER))
- *advertising |= ADVERTISED_1000baseKX_Full;
+ *advertising |= ADVERTISED_1000baseKX_Full;
}
- if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
- phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+ /* Autoneg PHY types */
+ if (phy_types & I40E_CAP_PHY_TYPE_SGMII ||
+ phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4 ||
+ phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU ||
+ phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4 ||
phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
- phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) {
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+ phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX ||
+ phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
*supported |= SUPPORTED_Autoneg;
*advertising |= ADVERTISED_Autoneg;
}
--
2.14.2
^ permalink raw reply related
* [net-next 12/15] i40e: convert i40e_get_settings_link_up to new API
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This removes references to old ethtool API macros and functions in
i40e_get_settings_link_up as part of the process of converting to the
new API. The new API also allows us to provide more explicit support
for new 25G and 10G PHY types so some of the PHY types have been
adjusted where necessary as well.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 187 +++++++++++++++++--------
1 file changed, 125 insertions(+), 62 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 0cef8aa85c1d..913ba91fac6c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -474,125 +474,192 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
struct i40e_link_status *hw_link_info = &hw->phy.link_info;
struct ethtool_link_ksettings cap_ksettings;
u32 link_speed = hw_link_info->link_speed;
- u32 supported, advertising;
-
- ethtool_convert_link_mode_to_legacy_u32(&supported,
- ks->link_modes.supported);
- ethtool_convert_link_mode_to_legacy_u32(&advertising,
- ks->link_modes.advertising);
/* Initialize supported and advertised settings based on phy settings */
switch (hw_link_info->phy_type) {
case I40E_PHY_TYPE_40GBASE_CR4:
case I40E_PHY_TYPE_40GBASE_CR4_CU:
- supported = SUPPORTED_Autoneg |
- SUPPORTED_40000baseCR4_Full;
- advertising = ADVERTISED_Autoneg |
- ADVERTISED_40000baseCR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseCR4_Full);
break;
case I40E_PHY_TYPE_XLAUI:
case I40E_PHY_TYPE_XLPPI:
case I40E_PHY_TYPE_40GBASE_AOC:
- supported = SUPPORTED_40000baseCR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
break;
case I40E_PHY_TYPE_40GBASE_SR4:
- supported = SUPPORTED_40000baseSR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseSR4_Full);
break;
case I40E_PHY_TYPE_40GBASE_LR4:
- supported = SUPPORTED_40000baseLR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseLR4_Full);
break;
+ case I40E_PHY_TYPE_25GBASE_SR:
+ case I40E_PHY_TYPE_25GBASE_LR:
case I40E_PHY_TYPE_10GBASE_SR:
case I40E_PHY_TYPE_10GBASE_LR:
case I40E_PHY_TYPE_1000BASE_SX:
case I40E_PHY_TYPE_1000BASE_LX:
- supported = SUPPORTED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseSR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseLR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseLR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
if (hw_link_info->module_type[2] &
I40E_MODULE_TYPE_1000BASE_SX ||
hw_link_info->module_type[2] &
I40E_MODULE_TYPE_1000BASE_LX) {
- supported |= SUPPORTED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
if (hw_link_info->requested_speeds &
I40E_LINK_SPEED_1GB)
- advertising |= ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(
+ ks, advertising, 1000baseT_Full);
}
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- advertising |= ADVERTISED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
break;
case I40E_PHY_TYPE_10GBASE_T:
case I40E_PHY_TYPE_1000BASE_T:
case I40E_PHY_TYPE_100BASE_TX:
- supported = SUPPORTED_Autoneg |
- SUPPORTED_10000baseT_Full |
- SUPPORTED_1000baseT_Full |
- SUPPORTED_100baseT_Full;
- advertising = ADVERTISED_Autoneg;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- advertising |= ADVERTISED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- advertising |= ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
- advertising |= ADVERTISED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100baseT_Full);
break;
case I40E_PHY_TYPE_1000BASE_T_OPTICAL:
- supported = SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
- advertising = ADVERTISED_Autoneg |
- ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
break;
case I40E_PHY_TYPE_10GBASE_CR1_CU:
case I40E_PHY_TYPE_10GBASE_CR1:
- supported = SUPPORTED_Autoneg |
- SUPPORTED_10000baseT_Full;
- advertising = ADVERTISED_Autoneg |
- ADVERTISED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
break;
case I40E_PHY_TYPE_XAUI:
case I40E_PHY_TYPE_XFI:
case I40E_PHY_TYPE_SFI:
case I40E_PHY_TYPE_10GBASE_SFPP_CU:
case I40E_PHY_TYPE_10GBASE_AOC:
- supported = SUPPORTED_10000baseT_Full;
- advertising = SUPPORTED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
break;
case I40E_PHY_TYPE_SGMII:
- supported = SUPPORTED_Autoneg |
- SUPPORTED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- advertising |= ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
- supported |= SUPPORTED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
if (hw_link_info->requested_speeds &
I40E_LINK_SPEED_100MB)
- advertising |= ADVERTISED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(
+ ks, advertising, 100baseT_Full);
}
break;
case I40E_PHY_TYPE_40GBASE_KR4:
+ case I40E_PHY_TYPE_25GBASE_KR:
case I40E_PHY_TYPE_20GBASE_KR2:
case I40E_PHY_TYPE_10GBASE_KR:
case I40E_PHY_TYPE_10GBASE_KX4:
case I40E_PHY_TYPE_1000BASE_KX:
- supported |= SUPPORTED_40000baseKR4_Full |
- SUPPORTED_20000baseKR2_Full |
- SUPPORTED_10000baseKR_Full |
- SUPPORTED_10000baseKX4_Full |
- SUPPORTED_1000baseKX_Full |
- SUPPORTED_Autoneg;
- advertising |= ADVERTISED_40000baseKR4_Full |
- ADVERTISED_20000baseKR2_Full |
- ADVERTISED_10000baseKR_Full |
- ADVERTISED_10000baseKX4_Full |
- ADVERTISED_1000baseKX_Full |
- ADVERTISED_Autoneg;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 20000baseKR2_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKX4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseKX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseKR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 20000baseKR2_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKX4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseKX_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
break;
- case I40E_PHY_TYPE_25GBASE_KR:
case I40E_PHY_TYPE_25GBASE_CR:
- case I40E_PHY_TYPE_25GBASE_SR:
- case I40E_PHY_TYPE_25GBASE_LR:
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ break;
case I40E_PHY_TYPE_25GBASE_AOC:
case I40E_PHY_TYPE_25GBASE_ACC:
- supported = SUPPORTED_Autoneg;
- advertising = ADVERTISED_Autoneg;
- /* TODO: add speeds when ethtool is ready to support*/
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseCR_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseCR_Full);
break;
default:
/* if we got here and link is up something bad is afoot */
@@ -605,10 +672,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
* current PHY type, get what is supported by the NVM and intersect
* them to get what is truly supported
*/
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.supported,
- supported);
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.advertising,
- advertising);
memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings));
i40e_phy_type_to_ethtool(pf, &cap_ksettings);
ethtool_intersect_link_masks(ks, &cap_ksettings);
--
2.14.2
^ permalink raw reply related
* [net-next 05/15] i40e: fix i40e_phy_type_to_ethtool function header
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
The function header erroneously listed 'phy_types' as a parameter. The
correct parameter is 'pf'.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index fe0b2327de5b..a137675c1426 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -253,7 +253,7 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf)
/**
* i40e_phy_type_to_ethtool - convert the phy_types to ethtool link modes
- * @phy_types: PHY types to convert
+ * @pf: PF struct with phy_types
* @supported: pointer to the ethtool supported variable to fill in
* @advertising: pointer to the ethtool advertising variable to fill in
*
--
2.14.2
^ permalink raw reply related
* [net-next 04/15] i40e: fix clearing link masks in i40e_get_link_ksettings
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This fixes two issues in i40e_get_link_ksettings. It adds calls to
ethtool_link_ksettings_zero_link_mode to make sure advertising and
supported link masks are cleared before we start setting bits in them.
This also replaces some funky bit manipulations with a much nicer call
to ethtool_link_ksettings_del_link_mode when removing link modes.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index f4a70ef3f2e0..fe0b2327de5b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -600,7 +600,9 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
struct i40e_hw *hw = &pf->hw;
struct i40e_link_status *hw_link_info = &hw->phy.link_info;
bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP;
- u32 advertising;
+
+ ethtool_link_ksettings_zero_link_mode(ks, supported);
+ ethtool_link_ksettings_zero_link_mode(ks, advertising);
if (link_up)
i40e_get_settings_link_up(hw, ks, netdev, pf);
@@ -664,13 +666,9 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
Asym_Pause);
break;
default:
- ethtool_convert_link_mode_to_legacy_u32(
- &advertising, ks->link_modes.advertising);
-
- advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
-
- ethtool_convert_legacy_u32_to_link_mode(
- ks->link_modes.advertising, advertising);
+ ethtool_link_ksettings_del_link_mode(ks, advertising, Pause);
+ ethtool_link_ksettings_del_link_mode(ks, advertising,
+ Asym_Pause);
break;
}
--
2.14.2
^ permalink raw reply related
* [net-next 13/15] i40e: rename 'change' variable to 'autoneg_changed'
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This variable isn't actually very descriptive and makes the code a bit
confusing as to what it is being used for. This patch enhances the
variable with the longer name, 'autoneg_changed', which makes it clear
we are concerned with autoneg changing in this context.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 913ba91fac6c..9c70555bf49c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -822,14 +822,14 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_aq_get_phy_abilities_resp abilities;
+ struct ethtool_link_ksettings safe_ks;
+ struct ethtool_link_ksettings copy_ks;
struct i40e_aq_set_phy_config config;
struct i40e_pf *pf = np->vsi->back;
struct i40e_vsi *vsi = np->vsi;
struct i40e_hw *hw = &pf->hw;
- struct ethtool_link_ksettings safe_ks;
- struct ethtool_link_ksettings copy_ks;
+ bool autoneg_changed = false;
i40e_status status = 0;
- bool change = false;
int timeout = 50;
int err = 0;
u32 autoneg;
@@ -922,7 +922,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
/* Autoneg is allowed to change */
config.abilities = abilities.abilities |
I40E_AQ_PHY_ENABLE_AN;
- change = true;
+ autoneg_changed = true;
}
} else {
/* If autoneg is currently enabled */
@@ -942,7 +942,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
/* Autoneg is allowed to change */
config.abilities = abilities.abilities &
~I40E_AQ_PHY_ENABLE_AN;
- change = true;
+ autoneg_changed = true;
}
}
@@ -976,7 +976,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
*/
if (!config.link_speed)
config.link_speed = abilities.link_speed;
- if (change || (abilities.link_speed != config.link_speed)) {
+ if (autoneg_changed || abilities.link_speed != config.link_speed) {
/* copy over the rest of the abilities */
config.phy_type = abilities.phy_type;
config.phy_type_ext = abilities.phy_type_ext;
--
2.14.2
^ permalink raw reply related
* [net-next 11/15] i40e: convert i40e_phy_type_to_ethtool to new API
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
We are still largely using the old ethtool API macros. This is
problematic because eventually they will be removed and they only
support 32 bits of PHY types.
This overhauls i40e_phy_type_to_ethtool to use only the new API. Doing
this also allows us to provide much better support for newer 25G and 10G
PHY types which is included here as well.
The remaining usages of the old ethtool API will be addressed in other
patches in the series.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 204 +++++++++++++++++--------
1 file changed, 140 insertions(+), 64 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a4210ccdaa5f..0cef8aa85c1d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -254,95 +254,180 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf)
/**
* i40e_phy_type_to_ethtool - convert the phy_types to ethtool link modes
* @pf: PF struct with phy_types
- * @supported: pointer to the ethtool supported variable to fill in
- * @advertising: pointer to the ethtool advertising variable to fill in
+ * @ks: ethtool link ksettings struct to fill out
*
**/
-static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
- u32 *advertising)
+static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
+ struct ethtool_link_ksettings *ks)
{
struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info;
u64 phy_types = pf->hw.phy.phy_types;
- *supported = 0x0;
- *advertising = 0x0;
+ ethtool_link_ksettings_zero_link_mode(ks, supported);
+ ethtool_link_ksettings_zero_link_mode(ks, advertising);
if (phy_types & I40E_CAP_PHY_TYPE_SGMII) {
- *supported |= SUPPORTED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- *advertising |= ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) {
- *supported |= SUPPORTED_100baseT_Full;
- *advertising |= ADVERTISED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100baseT_Full);
}
}
if (phy_types & I40E_CAP_PHY_TYPE_XAUI ||
phy_types & I40E_CAP_PHY_TYPE_XFI ||
phy_types & I40E_CAP_PHY_TYPE_SFI ||
phy_types & I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC)
- *supported |= SUPPORTED_10000baseT_Full;
- if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
- phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) {
- *supported |= SUPPORTED_10000baseT_Full;
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- *advertising |= ADVERTISED_10000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_T) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseT_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseT_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_XLAUI ||
phy_types & I40E_CAP_PHY_TYPE_XLPPI ||
phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC)
- *supported |= SUPPORTED_40000baseCR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU ||
phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) {
- *supported |= SUPPORTED_40000baseCR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseCR4_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB)
- *advertising |= ADVERTISED_40000baseCR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseCR4_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
- *supported |= SUPPORTED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 100baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB)
- *advertising |= ADVERTISED_100baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 100baseT_Full);
}
- if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
- phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
- phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
- phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) {
- *supported |= SUPPORTED_1000baseT_Full;
+ if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseT_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- *advertising |= ADVERTISED_1000baseT_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseT_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4)
- *supported |= SUPPORTED_40000baseSR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseSR4_Full);
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
- *supported |= SUPPORTED_40000baseLR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseLR4_Full);
if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
- *supported |= SUPPORTED_40000baseKR4_Full;
- *advertising |= ADVERTISED_40000baseKR4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 40000baseLR4_Full);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 40000baseLR4_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) {
- *supported |= SUPPORTED_20000baseKR2_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 20000baseKR2_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB)
- *advertising |= ADVERTISED_20000baseKR2_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 20000baseKR2_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) {
- *supported |= SUPPORTED_10000baseKX4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKX4_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- *advertising |= ADVERTISED_10000baseKX4_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKX4_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR &&
!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
- *supported |= SUPPORTED_10000baseKR_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseKR_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
- *advertising |= ADVERTISED_10000baseKR_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseKR_Full);
}
if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX &&
!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) {
- *supported |= SUPPORTED_1000baseKX_Full;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseKX_Full);
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
- *advertising |= ADVERTISED_1000baseKX_Full;
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseKX_Full);
+ }
+ /* need to add 25G PHY types */
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseKR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseKR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseSR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseSR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 25000baseCR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 25000baseCR_Full);
+ }
+ /* need to add new 10G PHY types */
+ if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+ phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseCR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseCR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseSR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseSR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 10000baseLR_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 10000baseLR_Full);
+ }
+ if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
+ phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) {
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ 1000baseX_Full);
+ if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ 1000baseX_Full);
}
/* Autoneg PHY types */
if (phy_types & I40E_CAP_PHY_TYPE_SGMII ||
@@ -367,8 +452,10 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX ||
phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX ||
phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) {
- *supported |= SUPPORTED_Autoneg;
- *advertising |= ADVERTISED_Autoneg;
+ ethtool_link_ksettings_add_link_mode(ks, supported,
+ Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ Autoneg);
}
}
@@ -385,9 +472,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
struct i40e_pf *pf)
{
struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+ struct ethtool_link_ksettings cap_ksettings;
u32 link_speed = hw_link_info->link_speed;
- u32 e_advertising = 0x0;
- u32 e_supported = 0x0;
u32 supported, advertising;
ethtool_convert_link_mode_to_legacy_u32(&supported,
@@ -519,11 +605,13 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
* current PHY type, get what is supported by the NVM and intersect
* them to get what is truly supported
*/
- i40e_phy_type_to_ethtool(pf, &e_supported,
- &e_advertising);
-
- supported = supported & e_supported;
- advertising = advertising & e_advertising;
+ ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.advertising,
+ advertising);
+ memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings));
+ i40e_phy_type_to_ethtool(pf, &cap_ksettings);
+ ethtool_intersect_link_masks(ks, &cap_ksettings);
/* Set speed and duplex */
switch (link_speed) {
@@ -549,11 +637,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
break;
}
ks->base.duplex = DUPLEX_FULL;
-
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.supported,
- supported);
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.advertising,
- advertising);
}
/**
@@ -568,17 +651,10 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw,
struct ethtool_link_ksettings *ks,
struct i40e_pf *pf)
{
- u32 supported, advertising;
-
/* link is down and the driver needs to fall back on
* supported phy types to figure out what info to display
*/
- i40e_phy_type_to_ethtool(pf, &supported, &advertising);
-
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.supported,
- supported);
- ethtool_convert_legacy_u32_to_link_mode(ks->link_modes.advertising,
- advertising);
+ i40e_phy_type_to_ethtool(pf, ks);
/* With no link speed and duplex are unknown */
ks->base.speed = SPEED_UNKNOWN;
--
2.14.2
^ permalink raw reply related
* [net-next 14/15] i40e: convert i40e_set_link_ksettings to new API
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
This finishes off the conversion to the new ethtool API by removing the
old macros being used in i40e_set_link_ksettings and replacing them with
shiny new ones.
This conversion also allows us to provide link speed support for new 25G
and 10G macros which is included here as well.
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 93 ++++++++++++++++----------
1 file changed, 57 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9c70555bf49c..9eb618799a30 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -832,9 +832,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
i40e_status status = 0;
int timeout = 50;
int err = 0;
- u32 autoneg;
- u32 advertise;
- u32 tmp;
+ u8 autoneg;
/* Changing port settings is not supported if this isn't the
* port's controlling PF
@@ -862,28 +860,34 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
/* copy the ksettings to copy_ks to avoid modifying the origin */
memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings));
+ /* save autoneg out of ksettings */
+ autoneg = copy_ks.base.autoneg;
+
+ memset(&safe_ks, 0, sizeof(safe_ks));
+ /* Get link modes supported by hardware and check against modes
+ * requested by the user. Return an error if unsupported mode was set.
+ */
+ i40e_phy_type_to_ethtool(pf, &safe_ks);
+ if (!bitmap_subset(copy_ks.link_modes.advertising,
+ safe_ks.link_modes.supported,
+ __ETHTOOL_LINK_MODE_MASK_NBITS))
+ return -EINVAL;
+
/* get our own copy of the bits to check against */
memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings));
+ safe_ks.base.cmd = copy_ks.base.cmd;
+ safe_ks.base.link_mode_masks_nwords =
+ copy_ks.base.link_mode_masks_nwords;
i40e_get_link_ksettings(netdev, &safe_ks);
- /* save autoneg and speed out of ksettings */
- autoneg = ks->base.autoneg;
- ethtool_convert_link_mode_to_legacy_u32(&advertise,
- ks->link_modes.advertising);
-
- /* set autoneg and speed back to what they currently are */
+ /* set autoneg back to what it currently is */
copy_ks.base.autoneg = safe_ks.base.autoneg;
- ethtool_convert_link_mode_to_legacy_u32(
- &tmp, safe_ks.link_modes.advertising);
- ethtool_convert_legacy_u32_to_link_mode(
- copy_ks.link_modes.advertising, tmp);
- copy_ks.base.cmd = safe_ks.base.cmd;
-
- /* If copy_ks and safe_ks are not the same now, then they are
- * trying to set something that we do not support
+ /* If copy_ks.base and safe_ks.base are not the same now, then they are
+ * trying to set something that we do not support.
*/
- if (memcmp(©_ks, &safe_ks, sizeof(struct ethtool_link_ksettings)))
+ if (memcmp(©_ks.base, &safe_ks.base,
+ sizeof(struct ethtool_link_settings)))
return -EOPNOTSUPP;
while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
@@ -946,28 +950,45 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
}
}
- ethtool_convert_link_mode_to_legacy_u32(&tmp,
- safe_ks.link_modes.supported);
- if (advertise & ~tmp) {
- err = -EINVAL;
- goto done;
- }
-
- if (advertise & ADVERTISED_100baseT_Full)
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 100baseT_Full))
config.link_speed |= I40E_LINK_SPEED_100MB;
- if (advertise & ADVERTISED_1000baseT_Full ||
- advertise & ADVERTISED_1000baseKX_Full)
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseT_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseX_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 1000baseKX_Full))
config.link_speed |= I40E_LINK_SPEED_1GB;
- if (advertise & ADVERTISED_10000baseT_Full ||
- advertise & ADVERTISED_10000baseKX4_Full ||
- advertise & ADVERTISED_10000baseKR_Full)
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseT_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseKX4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseKR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseCR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 10000baseSR_Full))
config.link_speed |= I40E_LINK_SPEED_10GB;
- if (advertise & ADVERTISED_20000baseKR2_Full)
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 20000baseKR2_Full))
config.link_speed |= I40E_LINK_SPEED_20GB;
- if (advertise & ADVERTISED_40000baseKR4_Full ||
- advertise & ADVERTISED_40000baseCR4_Full ||
- advertise & ADVERTISED_40000baseSR4_Full ||
- advertise & ADVERTISED_40000baseLR4_Full)
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseCR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseKR_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 25000baseSR_Full))
+ config.link_speed |= I40E_LINK_SPEED_25GB;
+ if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseKR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseCR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseSR4_Full) ||
+ ethtool_link_ksettings_test_link_mode(ks, advertising,
+ 40000baseLR4_Full))
config.link_speed |= I40E_LINK_SPEED_40GB;
/* If speed didn't get set, set it to what it currently is.
--
2.14.2
^ permalink raw reply related
* [net-next 15/15] i40e: fix u64 division usage
From: Jeff Kirsher @ 2017-10-17 18:21 UTC (permalink / raw)
To: davem; +Cc: Alan Brady, netdev, nhorman, sassmann, jogreene, Jeff Kirsher
In-Reply-To: <20171017182119.71989-1-jeffrey.t.kirsher@intel.com>
From: Alan Brady <alan.brady@intel.com>
Commit 52eb1ff93e98 ("i40e: Add support setting TC max bandwidth rates")
and commit 1ea6f21ae530 ("i40e: Refactor VF BW rate limiting") add some
needed functionality for TC bandwidth rate limiting. Unfortunately they
introduce several usages of unsigned 64-bit division which needs to be
handled special by the kernel to support all architectures.
Fixes: 52eb1ff93e98 ("i40e: Add support setting TC max bandwidth
rates")
Fixes: 1ea6f21ae530 ("i40e: Refactor VF BW rate limiting")
Signed-off-by: Alan Brady <alan.brady@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 3 +-
drivers/net/ethernet/intel/i40e/i40e_main.c | 58 ++++++++++++++++++++---------
2 files changed, 42 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 266e1dc5e786..eb017763646d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -130,7 +130,8 @@
/* BW rate limiting */
#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */
-#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */
+#define I40E_BW_MBPS_DIVISOR 125000 /* rate / (1000000 / 8) Mbps */
+#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */
/* driver state flags */
enum i40e_state_t {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index bb31d53c4923..1252aaf92fd3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5442,6 +5442,7 @@ int i40e_get_link_speed(struct i40e_vsi *vsi)
int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
{
struct i40e_pf *pf = vsi->back;
+ u64 credits = 0;
int speed = 0;
int ret = 0;
@@ -5459,8 +5460,9 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
}
/* Tx rate credits are in values of 50Mbps, 0 is disabled */
- ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid,
- max_tx_rate / I40E_BW_CREDIT_DIVISOR,
+ credits = max_tx_rate;
+ do_div(credits, I40E_BW_CREDIT_DIVISOR);
+ ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid, credits,
I40E_MAX_BW_INACTIVE_ACCUM, NULL);
if (ret)
dev_err(&pf->pdev->dev,
@@ -6063,13 +6065,17 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi,
/* configure VSI for BW limit */
if (ch->max_tx_rate) {
+ u64 credits = ch->max_tx_rate;
+
if (i40e_set_bw_limit(vsi, ch->seid, ch->max_tx_rate))
return -EINVAL;
+ do_div(credits, I40E_BW_CREDIT_DIVISOR);
dev_dbg(&pf->pdev->dev,
"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
ch->max_tx_rate,
- ch->max_tx_rate / I40E_BW_CREDIT_DIVISOR, ch->seid);
+ credits,
+ ch->seid);
}
/* in case of VF, this will be main SRIOV VSI */
@@ -6090,6 +6096,7 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi,
static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
{
struct i40e_channel *ch;
+ u64 max_rate = 0;
int ret = 0, i;
/* Create app vsi with the TCs. Main VSI with TC0 is already set up */
@@ -6110,8 +6117,9 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
/* Bandwidth limit through tc interface is in bytes/s,
* change to Mbit/s
*/
- ch->max_tx_rate =
- vsi->mqprio_qopt.max_rate[i] / (1000000 / 8);
+ max_rate = vsi->mqprio_qopt.max_rate[i];
+ do_div(max_rate, I40E_BW_MBPS_DIVISOR);
+ ch->max_tx_rate = max_rate;
list_add_tail(&ch->list, &vsi->ch_list);
@@ -6540,6 +6548,7 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi,
struct tc_mqprio_qopt_offload *mqprio_qopt)
{
u64 sum_max_rate = 0;
+ u64 max_rate = 0;
int i;
if (mqprio_qopt->qopt.offset[0] != 0 ||
@@ -6554,7 +6563,9 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi,
"Invalid min tx rate (greater than 0) specified\n");
return -EINVAL;
}
- sum_max_rate += (mqprio_qopt->max_rate[i] / (1000000 / 8));
+ max_rate = mqprio_qopt->max_rate[i];
+ do_div(max_rate, I40E_BW_MBPS_DIVISOR);
+ sum_max_rate += max_rate;
if (i >= mqprio_qopt->qopt.num_tc - 1)
break;
@@ -6698,14 +6709,18 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data)
if (pf->flags & I40E_FLAG_TC_MQPRIO) {
if (vsi->mqprio_qopt.max_rate[0]) {
- u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0] /
- (1000000 / 8);
+ u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+
+ do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
if (!ret) {
+ u64 credits = max_tx_rate;
+
+ do_div(credits, I40E_BW_CREDIT_DIVISOR);
dev_dbg(&vsi->back->pdev->dev,
"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
max_tx_rate,
- max_tx_rate / I40E_BW_CREDIT_DIVISOR,
+ credits,
vsi->seid);
} else {
need_reset = true;
@@ -8166,14 +8181,17 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi)
return ret;
}
if (ch->max_tx_rate) {
+ u64 credits = ch->max_tx_rate;
+
if (i40e_set_bw_limit(vsi, ch->seid,
ch->max_tx_rate))
return -EINVAL;
+ do_div(credits, I40E_BW_CREDIT_DIVISOR);
dev_dbg(&vsi->back->pdev->dev,
"Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
ch->max_tx_rate,
- ch->max_tx_rate / I40E_BW_CREDIT_DIVISOR,
+ credits,
ch->seid);
}
}
@@ -8446,17 +8464,21 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
}
if (vsi->mqprio_qopt.max_rate[0]) {
- u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0] / (1000000 / 8);
+ u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+ u64 credits = 0;
+ do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
- if (!ret)
- dev_dbg(&vsi->back->pdev->dev,
- "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
- max_tx_rate,
- max_tx_rate / I40E_BW_CREDIT_DIVISOR,
- vsi->seid);
- else
+ if (ret)
goto end_unlock;
+
+ credits = max_tx_rate;
+ do_div(credits, I40E_BW_CREDIT_DIVISOR);
+ dev_dbg(&vsi->back->pdev->dev,
+ "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n",
+ max_tx_rate,
+ credits,
+ vsi->seid);
}
/* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs
--
2.14.2
^ permalink raw reply related
* Re: [PATCH net-next 1/3] ipv6: fix route cache dump
From: Wei Wang @ 2017-10-17 18:26 UTC (permalink / raw)
To: Paolo Abeni, Eric Dumazet, Martin KaFai Lau
Cc: Linux Kernel Network Developers, David S. Miller,
Hannes Frederic Sowa
In-Reply-To: <e54ccbb0c97570a8c1a9c97a3c7bc8a910f02083.1508261949.git.pabeni@redhat.com>
On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> After the commit 2b760fcf5cfb ("ipv6: hook up exception table to
> store dst cache"), entries in the routing cache are not shown by:
>
> ip route show cache
>
> because the per route exception table containing such routes is not
> traversed by rt6_dump_route().
> Fix it by explicitly dumping all routes present into the
> rt6i_exception_bucket.
>
> Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> net/ipv6/route.c | 30 ++++++++++++++++++++++++++----
> 1 file changed, 26 insertions(+), 4 deletions(-)
>
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index 01a103c23a6c..5bb53dbd4fd3 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -4190,10 +4190,14 @@ static int rt6_fill_node(struct net *net,
> return -EMSGSIZE;
> }
>
> +/* this is called under the RCU lock */
> int rt6_dump_route(struct rt6_info *rt, void *p_arg)
> {
> struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
> + struct rt6_exception_bucket *bucket;
> + struct rt6_exception *rt6_ex;
> struct net *net = arg->net;
> + int err, port_id, seq, i;
>
> if (rt == net->ipv6.ip6_null_entry)
> return 0;
> @@ -4209,10 +4213,28 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
> }
> }
>
> - return rt6_fill_node(net,
> - arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
> - NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
> - NLM_F_MULTI);
> + /* dump execeptions table, if available */
> + port_id = NETLINK_CB(arg->cb->skb).portid;
> + seq = arg->cb->nlh->nlmsg_seq;
> + bucket = rcu_dereference(rt->rt6i_exception_bucket);
> + if (!bucket)
> + goto no_exceptions;
> +
> + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
> + hlist_for_each_entry_rcu(rt6_ex, &bucket->chain, hlist) {
> + err = rt6_fill_node(net, arg->skb, rt6_ex->rt6i, NULL,
> + NULL, 0, RTM_NEWROUTE, port_id, seq,
> + NLM_F_MULTI);
> + if (err)
> + return err;
> + }
> +
> + bucket++;
> + }
> +
> +no_exceptions:
> + return rt6_fill_node(net, arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
> + port_id, seq, NLM_F_MULTI);
> }
>
Hi Paolo,
Thanks for doing this.
But I think your patch does not take care of the case where there are
a lot of cached routes in the exception table and 1 skb is just not
enough to dump the main route + all cached routes in the exception
table.
In this case, your patch will keep dumping the same main route.
I think some logic needs to be incorporated into the fib6_walk() so
that it can also remember the last dumped cached route if necessary in
the exception table and start from there for the next dump.
I do have a patch for that and that patch tries to keep a linked list
of all cached routes from the exception table in the walker struct and
remove any routes that are already dumped.
It is a bit complicated and might not be the best solution. And as
IPv4 already does not support dumping cached routes, I did not send
that out in the previous patch series.
> static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
> --
> 2.13.6
>
^ permalink raw reply
* [PATCH] mac80211: use constant time comparison with keys
From: Jason A. Donenfeld @ 2017-10-17 18:32 UTC (permalink / raw)
To: Johannes Berg, David Miller, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA
Cc: Jason A. Donenfeld
In-Reply-To: <CAHmME9qd_m-FDj1E+eiBYWKvnMBvr0tWVcJ4ph2tr=Y1d_tb1g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
Otherwise we risk leaking information via timing side channel.
Fixes: fdf7cb4185b6 ("mac80211: accept key reinstall without changing anything")
Signed-off-by: Jason A. Donenfeld <Jason-OnJsPKxuuEcAvxtiuMwx3w@public.gmane.org>
---
net/mac80211/key.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index ae995c8480db..035d16fe926e 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -19,6 +19,7 @@
#include <linux/slab.h>
#include <linux/export.h>
#include <net/mac80211.h>
+#include <crypto/algapi.h>
#include <asm/unaligned.h>
#include "ieee80211_i.h"
#include "driver-ops.h"
@@ -635,7 +636,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
* new version of the key to avoid nonce reuse or replay issues.
*/
if (old_key && key->conf.keylen == old_key->conf.keylen &&
- !memcmp(key->conf.key, old_key->conf.key, key->conf.keylen)) {
+ !crypto_memneq(key->conf.key, old_key->conf.key, key->conf.keylen)) {
ieee80211_key_free_unused(key);
ret = 0;
goto out;
--
2.14.2
^ permalink raw reply related
* Re: [PATCH net-next 2/3] ipv6: start fib6 gc on RTF_CACHE dst creation
From: Wei Wang @ 2017-10-17 18:35 UTC (permalink / raw)
To: Paolo Abeni, Martin KaFai Lau, Eric Dumazet
Cc: Linux Kernel Network Developers, David S. Miller,
Hannes Frederic Sowa
In-Reply-To: <013c220c347b63c0458332898709edc0b469361d.1508261949.git.pabeni@redhat.com>
On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> After the commit Fixes: 2b760fcf5cfb ("ipv6: hook up exception
> table to store dst cache"), the fib6 gc is not started after
> the creation of a RTF_CACHE via a redirect or pmtu update, since
> fib6_add() isn't invoked anymore for such dsts.
>
> We need the fib6 gc to run periodically to clean the RTF_CACHE,
> or the dst will stay there forever.
>
> Fix it by explicitly calling fib6_force_start_gc() on successful
> exception creation. gc_args->more accounting will ensure that
> the gc timer will run for whatever time needed to properly
> clean the table.
>
> Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
Acked-by: Wei Wang <weiwan@google.com>
Totally true. Thanks for catching this.
> net/ipv6/route.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index 5bb53dbd4fd3..8b25a31b6b03 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -1340,8 +1340,10 @@ static int rt6_insert_exception(struct rt6_info *nrt,
> spin_unlock_bh(&rt6_exception_lock);
>
> /* Update fn->fn_sernum to invalidate all cached dst */
> - if (!err)
> + if (!err) {
> fib6_update_sernum(ort);
> + fib6_force_start_gc(net);
> + }
>
> return err;
> }
> --
> 2.13.6
>
^ permalink raw reply
* Re: [PATCH net-next 1/3] ipv6: fix route cache dump
From: Eric Dumazet @ 2017-10-17 18:41 UTC (permalink / raw)
To: Wei Wang
Cc: Paolo Abeni, Martin KaFai Lau, Linux Kernel Network Developers,
David S. Miller, Hannes Frederic Sowa
In-Reply-To: <CAEA6p_DRZA4aHW-Rxb7kJnwhPAy9HqDzY1nQgFGjCwNeVmTfJA@mail.gmail.com>
On Tue, Oct 17, 2017 at 11:26 AM, Wei Wang <weiwan@google.com> wrote:
> On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
>> After the commit 2b760fcf5cfb ("ipv6: hook up exception table to
>> store dst cache"), entries in the routing cache are not shown by:
>>
>> ip route show cache
>
> Hi Paolo,
>
> Thanks for doing this.
> But I think your patch does not take care of the case where there are
> a lot of cached routes in the exception table and 1 skb is just not
> enough to dump the main route + all cached routes in the exception
> table.
> In this case, your patch will keep dumping the same main route.
>
> I think some logic needs to be incorporated into the fib6_walk() so
> that it can also remember the last dumped cached route if necessary in
> the exception table and start from there for the next dump.
> I do have a patch for that and that patch tries to keep a linked list
> of all cached routes from the exception table in the walker struct and
> remove any routes that are already dumped.
> It is a bit complicated and might not be the best solution. And as
> IPv4 already does not support dumping cached routes, I did not send
> that out in the previous patch series.
Yes, since we no longer dump IPV4 cached routes, I doubt anyone
depends on IPv6 cached routes, but not on IPv4 ones.
Paolo, do you have a concrete use case for this ?
^ permalink raw reply
* Re: [PATCH net-next 3/3] ipv6: obsolete cached dst when removing them from fib tree
From: Wei Wang @ 2017-10-17 18:58 UTC (permalink / raw)
To: Paolo Abeni
Cc: Linux Kernel Network Developers, David S. Miller,
Hannes Frederic Sowa
In-Reply-To: <59304478d82e52c817c92d183ef2105f35c17266.1508261949.git.pabeni@redhat.com>
On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> The commit 2b760fcf5cfb ("ipv6: hook up exception table to store
> dst cache") partially reverted 1e2ea8ad37be ("ipv6: set
> dst.obsolete when a cached route has expired").
>
> This change brings back the dst obsoleting and push it a step
> farther: cached dst are always obsoleted when removed from the
> fib tree, and removal by time expiration is now performed
> regardless of dst->__refcnt, to be consistent with what we
> already do for RTF_GATEWAY dst.
>
> Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> net/ipv6/route.c | 13 +++++++++++--
> 1 file changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index 8b25a31b6b03..fce740049e3e 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -1147,6 +1147,12 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
> if (!bucket || !rt6_ex)
> return;
>
> + /* sockets, flow cache, etc. can hold a refence to this dst, be sure
> + * they will drop it.
> + */
> + if (rt6_ex->rt6i)
> + rt6_ex->rt6i->dst.obsolete = DST_OBSOLETE_FORCE_CHK;
> +
Hmm... I don't really think it is needed. rt6 is created with
rt6->dst.obsolete set to DST_OBSOLETE_FORCE_CHK. And by the time the
above function is called, it should still be that value.
Furthermore, the later call rt6_release() calls dst_dev_put() which
sets rt6->dst.obsolete to DST_OBSOLETE_DEAD to indicate this route has
been removed from the tree.
> net = dev_net(rt6_ex->rt6i->dst.dev);
> rt6_ex->rt6i->rt6i_node = NULL;
> hlist_del_rcu(&rt6_ex->hlist);
> @@ -1575,8 +1581,11 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
> {
> struct rt6_info *rt = rt6_ex->rt6i;
>
> - if (atomic_read(&rt->dst.__refcnt) == 1 &&
> - time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
> + /* we are pruning and obsoleting the exception route even if others
> + * have still reference to it, so that on next dst_check() such
> + * reference can be dropped
> + */
> + if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
Why do we want to change this behavior? Before my patch series, cached
routes were only deleted from the tree in fib6_age() when
rt->dst.__refcnt == 1, isn't it?
> RT6_TRACE("aging clone %p\n", rt);
> rt6_remove_exception(bucket, rt6_ex);
> return;
> --
> 2.13.6
>
^ permalink raw reply
* [PATCH 1/2] liquidio: remove unnecessary NULL check before kfree in delete_glists
From: Gustavo A. R. Silva @ 2017-10-17 18:59 UTC (permalink / raw)
To: Derek Chickles, Satanand Burla, Felix Manlunas, Raghu Vatsavayi
Cc: netdev, linux-kernel, Gustavo A. R. Silva
NULL check before freeing functions like kfree is not needed.
This issue was detected with the help of Coccinelle.
Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
---
This code was tested by compilation only.
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 2e993ce..e4a112c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -435,8 +435,7 @@ static void delete_glists(struct lio *lio)
do {
g = (struct octnic_gather *)
list_delete_head(&lio->glist[i]);
- if (g)
- kfree(g);
+ kfree(g);
} while (g);
if (lio->glists_virt_base && lio->glists_virt_base[i] &&
--
2.7.4
^ permalink raw reply related
* [PATCH 2/2] liquidio: mark expected switch fall-through in octeon_destroy_resources
From: Gustavo A. R. Silva @ 2017-10-17 19:01 UTC (permalink / raw)
To: Derek Chickles, Satanand Burla, Felix Manlunas, Raghu Vatsavayi
Cc: netdev, linux-kernel, Gustavo A. R. Silva
In-Reply-To: <20171017185920.GA16976@embeddedor.com>
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
---
This code was tested by compilation only (GCC 7.2.0 was used).
Please, verify if the actual intention of the code is to fall through.
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index e4a112c..4c3b568 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -747,7 +747,7 @@ static void octeon_destroy_resources(struct octeon_device *oct)
if (lio_wait_for_oq_pkts(oct))
dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
-
+ /* fall through */
case OCT_DEV_INTR_SET_DONE:
/* Disable interrupts */
oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net-next 1/3] ipv6: fix route cache dump
From: Paolo Abeni @ 2017-10-17 19:35 UTC (permalink / raw)
To: Eric Dumazet, Wei Wang
Cc: Martin KaFai Lau, Linux Kernel Network Developers,
David S. Miller, Hannes Frederic Sowa
In-Reply-To: <CANn89iK867x7NSoLbDC55CnZg2DHhLc-=pvNQAD3W6hRqiu+Fw@mail.gmail.com>
Hi,
On Tue, 2017-10-17 at 11:41 -0700, Eric Dumazet wrote:
> On Tue, Oct 17, 2017 at 11:26 AM, Wei Wang <weiwan@google.com> wrote:
> > On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> > > After the commit 2b760fcf5cfb ("ipv6: hook up exception table to
> > > store dst cache"), entries in the routing cache are not shown by:
> > >
> > > ip route show cache
> >
> > Hi Paolo,
> >
> > Thanks for doing this.
> > But I think your patch does not take care of the case where there are
> > a lot of cached routes in the exception table and 1 skb is just not
> > enough to dump the main route + all cached routes in the exception
> > table.
> > In this case, your patch will keep dumping the same main route.
> >
> > I think some logic needs to be incorporated into the fib6_walk() so
> > that it can also remember the last dumped cached route if necessary in
> > the exception table and start from there for the next dump.
> > I do have a patch for that and that patch tries to keep a linked list
> > of all cached routes from the exception table in the walker struct and
> > remove any routes that are already dumped.
> > It is a bit complicated and might not be the best solution. And as
> > IPv4 already does not support dumping cached routes, I did not send
> > that out in the previous patch series.
Thanks for the feedback.
You are right, I was too hasty with this.
> Yes, since we no longer dump IPV4 cached routes, I doubt anyone
> depends on IPv6 cached routes, but not on IPv4 ones.
>
> Paolo, do you have a concrete use case for this ?
I have a testing script looking for that, but I guess I can adapt it.
I'm fine with dropping cached routes dumping support if there is
agreement on that.
I haven't understood that such change was intentional.
Cheers,
Paolo
^ permalink raw reply
* [PATCH net] dccp/tcp: fix ireq->opt races
From: Eric Dumazet @ 2017-10-17 19:45 UTC (permalink / raw)
To: David Miller; +Cc: netdev, edumazet
From: Eric Dumazet <edumazet@google.com>
syzkaller found another bug in DCCP/TCP stacks [1]
For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.
[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295
CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:16 [inline]
dump_stack+0x194/0x257 lib/dump_stack.c:52
print_address_description+0x73/0x250 mm/kasan/report.c:252
kasan_report_error mm/kasan/report.c:351 [inline]
kasan_report+0x25b/0x340 mm/kasan/report.c:409
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
__tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000
Allocated by task 3295:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
__do_kmalloc mm/slab.c:3725 [inline]
__kmalloc+0x162/0x760 mm/slab.c:3734
kmalloc include/linux/slab.h:498 [inline]
tcp_v4_save_options include/net/tcp.h:1962 [inline]
tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed by task 3306:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
__cache_free mm/slab.c:3503 [inline]
kfree+0xca/0x250 mm/slab.c:3820
inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
__sk_destruct+0xfd/0x910 net/core/sock.c:1560
sk_destruct+0x47/0x80 net/core/sock.c:1595
__sk_free+0x57/0x230 net/core/sock.c:1603
sk_free+0x2a/0x40 net/core/sock.c:1614
sock_put include/net/sock.h:1652 [inline]
inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
The buggy address belongs to the object at ffff8801c9510380
which belongs to the cache kmalloc-64 of size 64
The buggy address is located 28 bytes inside of
64-byte region [ffff8801c9510380, ffff8801c95103c0)
The buggy address belongs to the page:
page:ffffea0007254400 count:1 mapcount:0 mapping:ffff8801c9510000 index:0x0
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801c9510000 0000000000000000 0000000100000020
raw: ffffea0007264f60 ffffea00072e2ae0 ffff8801dac00340 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801c9510280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
ffff8801c9510300: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8801c9510380: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
^
ffff8801c9510400: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
ffff8801c9510480: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc
==================================================================
Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_sock.h | 2 +-
net/dccp/ipv4.c | 13 ++++++++-----
net/ipv4/inet_connection_sock.c | 8 +++-----
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_input.c | 2 +-
net/ipv4/tcp_ipv4.c | 22 +++++++++++++---------
6 files changed, 27 insertions(+), 22 deletions(-)
^ permalink raw reply
* Re: [PATCH 00/58] networking: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 19:47 UTC (permalink / raw)
To: Kalle Valo
Cc: David S. Miller, Network Development, Thomas Gleixner, LKML,
linux-wireless
In-Reply-To: <87mv4pvowa.fsf@purkki.adurom.net>
On Tue, Oct 17, 2017 at 7:18 AM, Kalle Valo <kvalo@codeaurora.org> wrote:
> + linux-wireless
>
> Hi Kees,
>
> Kees Cook <keescook@chromium.org> writes:
>
>> This is the current set of outstanding networking patches to perform
>> conversions to the new timer interface (rebased to -next). This is not
>> all expected conversions, but it contains everything needed in networking
>> to eliminate init_timer(), and all the non-standard setup_*_timer() uses.
>
> So this also includes patches which I had queued for
> wireless-drivers-next:
>
> https://patchwork.kernel.org/patch/9986253/
> https://patchwork.kernel.org/patch/9986245/
>
> And looking at patchwork[1] I have even more timer_setup() related
> patches from you. It would be really helpful if you could clearly
> document to which tree you want the patches to be applied. I don't care
Hi! Sorry about that. It's been a bit tricky to juggle everything.
> if it's net-next or wireless-drivers-next as long as it's not the both
> (meaning that both Dave and me apply the same patch, which would be
> bad). The thing is that I really do not have time to figure out for
> every patch via which tree it's supposed to go.
Which split is preferred? I had been trying to separate wireless from
the rest of net (but missed some cases).
> For now I'll just drop all your timer_setup() related patches from my
> queue and I'll assume Dave will take those. Ok?
>
> [1] https://patchwork.kernel.org/project/linux-wireless/list/
I guess I'll wait to see what Dave says.
Thanks!
-Kees
--
Kees Cook
Pixel Security
^ permalink raw reply
* [PATCH net] dccp/tcp: fix ireq->opt races
From: Eric Dumazet @ 2017-10-17 19:50 UTC (permalink / raw)
To: David Miller; +Cc: netdev, edumazet
In-Reply-To: <1508269526.31614.113.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <edumazet@google.com>
syzkaller found another bug in DCCP/TCP stacks [1]
For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.
[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295
CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:16 [inline]
dump_stack+0x194/0x257 lib/dump_stack.c:52
print_address_description+0x73/0x250 mm/kasan/report.c:252
kasan_report_error mm/kasan/report.c:351 [inline]
kasan_report+0x25b/0x340 mm/kasan/report.c:409
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
__tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000
Allocated by task 3295:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
__do_kmalloc mm/slab.c:3725 [inline]
__kmalloc+0x162/0x760 mm/slab.c:3734
kmalloc include/linux/slab.h:498 [inline]
tcp_v4_save_options include/net/tcp.h:1962 [inline]
tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed by task 3306:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
__cache_free mm/slab.c:3503 [inline]
kfree+0xca/0x250 mm/slab.c:3820
inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
__sk_destruct+0xfd/0x910 net/core/sock.c:1560
sk_destruct+0x47/0x80 net/core/sock.c:1595
__sk_free+0x57/0x230 net/core/sock.c:1603
sk_free+0x2a/0x40 net/core/sock.c:1614
sock_put include/net/sock.h:1652 [inline]
inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
The buggy address belongs to the object at ffff8801c9510380
which belongs to the cache kmalloc-64 of size 64
The buggy address is located 28 bytes inside of
64-byte region [ffff8801c9510380, ffff8801c95103c0)
The buggy address belongs to the page:
page:ffffea0007254400 count:1 mapcount:0 mapping:ffff8801c9510000 index:0x0
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801c9510000 0000000000000000 0000000100000020
raw: ffffea0007264f60 ffffea00072e2ae0 ffff8801dac00340 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801c9510280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
ffff8801c9510300: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8801c9510380: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
^
ffff8801c9510400: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
ffff8801c9510480: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc
==================================================================
Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_sock.h | 2 +-
net/dccp/ipv4.c | 13 ++++++++-----
net/ipv4/inet_connection_sock.c | 8 +++-----
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_input.c | 2 +-
net/ipv4/tcp_ipv4.c | 22 +++++++++++++---------
6 files changed, 27 insertions(+), 22 deletions(-)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa95053dfc78d35d04aef276e2a5dce7343f72a0..425752f768d2f1a0efb13964204e07f27609e9db 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,7 +96,7 @@ struct inet_request_sock {
kmemcheck_bitfield_end(flags);
u32 ir_mark;
union {
- struct ip_options_rcu *opt;
+ struct ip_options_rcu __rcu *ireq_opt;
#if IS_ENABLED(CONFIG_IPV6)
struct {
struct ipv6_txoptions *ipv6_opt;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 001c08696334bba0ceb896c116e595b814af0667..0490916864f93d5466e87f5b97dc524b3ee57a2e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
sk_daddr_set(newsk, ireq->ir_rmt_addr);
sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
newinet->inet_saddr = ireq->ir_loc_addr;
- newinet->inet_opt = ireq->opt;
- ireq->opt = NULL;
+ RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->inet_id = jiffies;
@@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-
+ if (*own_req)
+ ireq->ireq_opt = NULL;
+ else
+ newinet->inet_opt = NULL;
return newsk;
exit_overflow:
@@ -441,6 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
+ newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto exit;
@@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
ireq->ir_rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq->opt);
+ rcu_dereference(ireq->ireq_opt));
err = net_xmit_eval(err);
}
@@ -548,7 +551,7 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
- kfree(inet_rsk(req)->opt);
+ kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
void dccp_syn_ack_timeout(const struct request_sock *req)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 67aec7a106860b26c929fea1624d652c87972f04..5ec9136a7c36933cb36e5cd50058eb6cf189a7c3 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -540,9 +540,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct net *net = read_pnet(&ireq->ireq_net);
- struct ip_options_rcu *opt = ireq->opt;
+ struct ip_options_rcu *opt;
struct rtable *rt;
+ opt = rcu_dereference(ireq->ireq_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -576,10 +577,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct flowi4 *fl4;
struct rtable *rt;
+ opt = rcu_dereference(ireq->ireq_opt);
fl4 = &newinet->cork.fl.u.ip4;
- rcu_read_lock();
- opt = rcu_dereference(newinet->inet_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -592,13 +592,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
- rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
- rcu_read_unlock();
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b1bb1b3a108232d56aa82383422d68b5ff9da3ed..77cf32a80952fcf3ceff4ada946cc2d0df2411d9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
*/
- ireq->opt = tcp_v4_save_options(sock_net(sk), skb);
+ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
if (security_inet_conn_request(sk, skb, req)) {
reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5d7656beeee29b3c92e1c8824dbf00d3fa32d28..7eec3383702bbab497a12095b55d255532ad5f60 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6196,7 +6196,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
struct inet_request_sock *ireq = inet_rsk(req);
kmemcheck_annotate_bitfield(ireq, flags);
- ireq->opt = NULL;
+ ireq->ireq_opt = NULL;
#if IS_ENABLED(CONFIG_IPV6)
ireq->pktopts = NULL;
#endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85164d4d3e537537c87d74c00172592c860d4dfb..4c43365c374c8bf868fc0b862333244ca26d5016 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq->opt);
+ rcu_dereference(ireq->ireq_opt));
err = net_xmit_eval(err);
}
@@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
*/
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
- kfree(inet_rsk(req)->opt);
+ kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
#ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req,
struct sk_buff *skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
+ struct net *net = sock_net(sk_listener);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
- ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
}
static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
sk_daddr_set(newsk, ireq->ir_rmt_addr);
sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
newsk->sk_bound_dev_if = ireq->ir_iif;
- newinet->inet_saddr = ireq->ir_loc_addr;
- inet_opt = ireq->opt;
- rcu_assign_pointer(newinet->inet_opt, inet_opt);
- ireq->opt = NULL;
+ newinet->inet_saddr = ireq->ir_loc_addr;
+ inet_opt = rcu_dereference(ireq->ireq_opt);
+ RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->rcv_tos = ip_hdr(skb)->tos;
@@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
- if (*own_req)
+ if (likely(*own_req)) {
tcp_move_syn(newtp, req);
-
+ ireq->ireq_opt = NULL;
+ } else {
+ newinet->inet_opt = NULL;
+ }
return newsk;
exit_overflow:
@@ -1416,6 +1419,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
tcp_listendrop(sk);
return NULL;
put_and_exit:
+ newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
goto exit;
^ permalink raw reply related
* Re: [PATCH net] dccp/tcp: fix ireq->opt races
From: Eric Dumazet @ 2017-10-17 19:53 UTC (permalink / raw)
To: David Miller; +Cc: netdev, edumazet
In-Reply-To: <1508269854.31614.114.camel@edumazet-glaptop3.roam.corp.google.com>
On Tue, 2017-10-17 at 12:50 -0700, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> syzkaller found another bug in DCCP/TCP stacks [1]
>
> For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
> ireq->pktopts race"), we need to make sure we do not access
> ireq->opt unless we own the request sock.
Arg, I will send a v2 without the silly lines that confuse patchwork.
^ permalink raw reply
* [PATCH v2 net] dccp/tcp: fix ireq->opt races
From: Eric Dumazet @ 2017-10-17 19:55 UTC (permalink / raw)
To: David Miller; +Cc: netdev, edumazet
In-Reply-To: <1508269854.31614.114.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <edumazet@google.com>
syzkaller found another bug in DCCP/TCP stacks [1]
For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.
[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295
CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:16 [inline]
dump_stack+0x194/0x257 lib/dump_stack.c:52
print_address_description+0x73/0x250 mm/kasan/report.c:252
kasan_report_error mm/kasan/report.c:351 [inline]
kasan_report+0x25b/0x340 mm/kasan/report.c:409
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
__tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000
Allocated by task 3295:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
__do_kmalloc mm/slab.c:3725 [inline]
__kmalloc+0x162/0x760 mm/slab.c:3734
kmalloc include/linux/slab.h:498 [inline]
tcp_v4_save_options include/net/tcp.h:1962 [inline]
tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed by task 3306:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
__cache_free mm/slab.c:3503 [inline]
kfree+0xca/0x250 mm/slab.c:3820
inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
__sk_destruct+0xfd/0x910 net/core/sock.c:1560
sk_destruct+0x47/0x80 net/core/sock.c:1595
__sk_free+0x57/0x230 net/core/sock.c:1603
sk_free+0x2a/0x40 net/core/sock.c:1614
sock_put include/net/sock.h:1652 [inline]
inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
v2: removed some lines from KASAN report that confuse patchwork.
include/net/inet_sock.h | 2 +-
net/dccp/ipv4.c | 13 ++++++++-----
net/ipv4/inet_connection_sock.c | 8 +++-----
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_input.c | 2 +-
net/ipv4/tcp_ipv4.c | 22 +++++++++++++---------
6 files changed, 27 insertions(+), 22 deletions(-)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa95053dfc78d35d04aef276e2a5dce7343f72a0..425752f768d2f1a0efb13964204e07f27609e9db 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,7 +96,7 @@ struct inet_request_sock {
kmemcheck_bitfield_end(flags);
u32 ir_mark;
union {
- struct ip_options_rcu *opt;
+ struct ip_options_rcu __rcu *ireq_opt;
#if IS_ENABLED(CONFIG_IPV6)
struct {
struct ipv6_txoptions *ipv6_opt;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 001c08696334bba0ceb896c116e595b814af0667..0490916864f93d5466e87f5b97dc524b3ee57a2e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
sk_daddr_set(newsk, ireq->ir_rmt_addr);
sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
newinet->inet_saddr = ireq->ir_loc_addr;
- newinet->inet_opt = ireq->opt;
- ireq->opt = NULL;
+ RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->inet_id = jiffies;
@@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-
+ if (*own_req)
+ ireq->ireq_opt = NULL;
+ else
+ newinet->inet_opt = NULL;
return newsk;
exit_overflow:
@@ -441,6 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
+ newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto exit;
@@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
ireq->ir_rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq->opt);
+ rcu_dereference(ireq->ireq_opt));
err = net_xmit_eval(err);
}
@@ -548,7 +551,7 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
- kfree(inet_rsk(req)->opt);
+ kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
void dccp_syn_ack_timeout(const struct request_sock *req)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 67aec7a106860b26c929fea1624d652c87972f04..5ec9136a7c36933cb36e5cd50058eb6cf189a7c3 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -540,9 +540,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct net *net = read_pnet(&ireq->ireq_net);
- struct ip_options_rcu *opt = ireq->opt;
+ struct ip_options_rcu *opt;
struct rtable *rt;
+ opt = rcu_dereference(ireq->ireq_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -576,10 +577,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct flowi4 *fl4;
struct rtable *rt;
+ opt = rcu_dereference(ireq->ireq_opt);
fl4 = &newinet->cork.fl.u.ip4;
- rcu_read_lock();
- opt = rcu_dereference(newinet->inet_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -592,13 +592,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
- rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
- rcu_read_unlock();
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b1bb1b3a108232d56aa82383422d68b5ff9da3ed..77cf32a80952fcf3ceff4ada946cc2d0df2411d9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
*/
- ireq->opt = tcp_v4_save_options(sock_net(sk), skb);
+ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
if (security_inet_conn_request(sk, skb, req)) {
reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5d7656beeee29b3c92e1c8824dbf00d3fa32d28..7eec3383702bbab497a12095b55d255532ad5f60 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6196,7 +6196,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
struct inet_request_sock *ireq = inet_rsk(req);
kmemcheck_annotate_bitfield(ireq, flags);
- ireq->opt = NULL;
+ ireq->ireq_opt = NULL;
#if IS_ENABLED(CONFIG_IPV6)
ireq->pktopts = NULL;
#endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85164d4d3e537537c87d74c00172592c860d4dfb..4c43365c374c8bf868fc0b862333244ca26d5016 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq->opt);
+ rcu_dereference(ireq->ireq_opt));
err = net_xmit_eval(err);
}
@@ -889,7 +889,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
*/
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
- kfree(inet_rsk(req)->opt);
+ kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
#ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1265,11 @@ static void tcp_v4_init_req(struct request_sock *req,
struct sk_buff *skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
+ struct net *net = sock_net(sk_listener);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
- ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
}
static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
sk_daddr_set(newsk, ireq->ir_rmt_addr);
sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
newsk->sk_bound_dev_if = ireq->ir_iif;
- newinet->inet_saddr = ireq->ir_loc_addr;
- inet_opt = ireq->opt;
- rcu_assign_pointer(newinet->inet_opt, inet_opt);
- ireq->opt = NULL;
+ newinet->inet_saddr = ireq->ir_loc_addr;
+ inet_opt = rcu_dereference(ireq->ireq_opt);
+ RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->rcv_tos = ip_hdr(skb)->tos;
@@ -1403,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
- if (*own_req)
+ if (likely(*own_req)) {
tcp_move_syn(newtp, req);
-
+ ireq->ireq_opt = NULL;
+ } else {
+ newinet->inet_opt = NULL;
+ }
return newsk;
exit_overflow:
@@ -1416,6 +1419,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
tcp_listendrop(sk);
return NULL;
put_and_exit:
+ newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
goto exit;
^ permalink raw reply related
* Re: [PATCH net-next 3/3] ipv6: obsolete cached dst when removing them from fib tree
From: Paolo Abeni @ 2017-10-17 20:02 UTC (permalink / raw)
To: Wei Wang
Cc: Linux Kernel Network Developers, David S. Miller,
Hannes Frederic Sowa
In-Reply-To: <CAEA6p_CMZu-ooO4sKXD3=wg8_wcAB+oZbTujJ4hEDQnjPZRNwg@mail.gmail.com>
On Tue, 2017-10-17 at 11:58 -0700, Wei Wang wrote:
> On Tue, Oct 17, 2017 at 10:40 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> > The commit 2b760fcf5cfb ("ipv6: hook up exception table to store
> > dst cache") partially reverted 1e2ea8ad37be ("ipv6: set
> > dst.obsolete when a cached route has expired").
> >
> > This change brings back the dst obsoleting and push it a step
> > farther: cached dst are always obsoleted when removed from the
> > fib tree, and removal by time expiration is now performed
> > regardless of dst->__refcnt, to be consistent with what we
> > already do for RTF_GATEWAY dst.
> >
> > Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> > Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> > ---
> > net/ipv6/route.c | 13 +++++++++++--
> > 1 file changed, 11 insertions(+), 2 deletions(-)
> >
> > diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> > index 8b25a31b6b03..fce740049e3e 100644
> > --- a/net/ipv6/route.c
> > +++ b/net/ipv6/route.c
> > @@ -1147,6 +1147,12 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
> > if (!bucket || !rt6_ex)
> > return;
> >
> > + /* sockets, flow cache, etc. can hold a refence to this dst, be sure
> > + * they will drop it.
> > + */
> > + if (rt6_ex->rt6i)
> > + rt6_ex->rt6i->dst.obsolete = DST_OBSOLETE_FORCE_CHK;
> > +
>
> Hmm... I don't really think it is needed. rt6 is created with
> rt6->dst.obsolete set to DST_OBSOLETE_FORCE_CHK. And by the time the
> above function is called, it should still be that value.
> Furthermore, the later call rt6_release() calls dst_dev_put() which
> sets rt6->dst.obsolete to DST_OBSOLETE_DEAD to indicate this route has
> been removed from the tree.
You are right, this looks as not needed, if we keep the chunck below.
> > net = dev_net(rt6_ex->rt6i->dst.dev);
> > rt6_ex->rt6i->rt6i_node = NULL;
> > hlist_del_rcu(&rt6_ex->hlist);
> > @@ -1575,8 +1581,11 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
> > {
> > struct rt6_info *rt = rt6_ex->rt6i;
> >
> > - if (atomic_read(&rt->dst.__refcnt) == 1 &&
> > - time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
> > + /* we are pruning and obsoleting the exception route even if others
> > + * have still reference to it, so that on next dst_check() such
> > + * reference can be dropped
> > + */
> > + if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
>
> Why do we want to change this behavior? Before my patch series, cached
> routes were only deleted from the tree in fib6_age() when
> rt->dst.__refcnt == 1, isn't it?
yes, but that really looks like a relic from ancient past more than
something really needed. We already remove from the dst from fib tree
regardless of the refcnt if the gateway validation fails - a few lines
below in the same function.
Waiting for __refcnt going down will let the kernel keep the exception
entry around for much longer - potentially forever, if e.g. we have a
reference in a socket dst cache and the application stops processing
packets.
Meanwhile others sockets may grab more references to (and use) the same
aged-out dst.
The commit 1e2ea8ad37be ("ipv6: set dst.obsolete when a cached route
has expired") was the solution to the above issue prior to the recent
refactor.
Cheers,
Paolo
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox