* [net-next 08/20] i40e: use unsigned printf format specifier for active_filters count
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
Replace the %d specifier used for printing vsi->active_filters and
vsi->promisc_threshold with an unsigned %u format specifier. While it is
unlikely in practice that these values will ever reach such a large
number they are unsigned values and thus should not be interpreted as
negative numbers.
Change-ID: Iff050fad5a1c8537c4c57fcd527441cd95cfc0d4
Signed-off-by: Jacob Keller <jacob.e.keller@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_debugfs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index b8a03a0..f1f41f1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -172,7 +172,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
f->macaddr, f->vlan,
i40e_filter_state_string[f->state]);
}
- dev_info(&pf->pdev->dev, " active_filters %d, promisc_threshold %d, overflow promisc %s\n",
+ dev_info(&pf->pdev->dev, " active_filters %u, promisc_threshold %u, overflow promisc %s\n",
vsi->active_filters, vsi->promisc_threshold,
(test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) ?
"ON" : "OFF"));
--
2.9.3
^ permalink raw reply related
* [net-next 12/20] i40e: lock service task correctly
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Mitch Williams, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Mitch Williams <mitch.a.williams@intel.com>
The service task lock was being set in the scheduling function, not the
actual service task. This would potentially leave the bit set for a long
time before the task actually ran. Furthermore, if the service task
takes too long, it calls the schedule function to reschedule itself -
which would fail to take the lock and do nothing.
Instead, set and clear the lock bit in the service task itself. In the
process, get rid of the i40e_service_event_complete() function, which is
really just two lines of code that can be put right in the service task
itself.
Change-ID: I83155e682b686121e2897f4429eb7d3f7c669168
Signed-off-by: Mitch Williams <mitch.a.williams@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_main.c | 24 +++++++-----------------
1 file changed, 7 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b0486c9..c47e9c5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -288,8 +288,7 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
void i40e_service_event_schedule(struct i40e_pf *pf)
{
if (!test_bit(__I40E_DOWN, &pf->state) &&
- !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) &&
- !test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
+ !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
queue_work(i40e_wq, &pf->service_task);
}
@@ -5955,19 +5954,6 @@ static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
}
/**
- * i40e_service_event_complete - Finish up the service event
- * @pf: board private structure
- **/
-static void i40e_service_event_complete(struct i40e_pf *pf)
-{
- WARN_ON(!test_bit(__I40E_SERVICE_SCHED, &pf->state));
-
- /* flush memory to make sure state is correct before next watchog */
- smp_mb__before_atomic();
- clear_bit(__I40E_SERVICE_SCHED, &pf->state);
-}
-
-/**
* i40e_get_cur_guaranteed_fd_count - Get the consumed guaranteed FD filters
* @pf: board private structure
**/
@@ -7276,10 +7262,12 @@ static void i40e_service_task(struct work_struct *work)
/* don't bother with service tasks if a reset is in progress */
if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) {
- i40e_service_event_complete(pf);
return;
}
+ if (test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
+ return;
+
i40e_detect_recover_hung(pf);
i40e_sync_filters_subtask(pf);
i40e_reset_subtask(pf);
@@ -7292,7 +7280,9 @@ static void i40e_service_task(struct work_struct *work)
i40e_sync_udp_filters_subtask(pf);
i40e_clean_adminq_subtask(pf);
- i40e_service_event_complete(pf);
+ /* flush memory to make sure state is correct before next watchdog */
+ smp_mb__before_atomic();
+ clear_bit(__I40E_SERVICE_SCHED, &pf->state);
/* If the tasks have taken longer than one timer cycle or there
* is more work to be done, reschedule the service task now
--
2.9.3
^ permalink raw reply related
* [net-next 09/20] i40e: Add support for 25G devices
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Carolyn Wyborny, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Mitch Williams, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
Add support for 25G devices - defines and data structures.
One tricky part here is that the firmware support for these
Devices introduces a mismatch between the PHY type enum and
the bitfields for the phy types.
This change creates a macro and uses it to increment the 25G
PHY values when creating 25G bitfields.
Change-ID: I69b24d837d44cf9220bf5cb8dd46c5be89ce490b
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Signed-off-by: Mitch Williams <mitch.a.williams@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 | 30 +++++++-
drivers/net/ethernet/intel/i40e/i40e_common.c | 11 ++-
drivers/net/ethernet/intel/i40e/i40e_devids.h | 2 +
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 26 ++++++-
drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +-
drivers/net/ethernet/intel/i40e/i40e_type.h | 82 +++++++++++++---------
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 +
.../net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 30 +++++++-
drivers/net/ethernet/intel/i40evf/i40e_common.c | 2 +
drivers/net/ethernet/intel/i40evf/i40e_devids.h | 2 +
drivers/net/ethernet/intel/i40evf/i40e_type.h | 82 +++++++++++++---------
drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c | 8 +++
.../net/ethernet/intel/i40evf/i40evf_virtchnl.c | 3 +
13 files changed, 208 insertions(+), 79 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 67e396b..c9d1f91 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1642,6 +1642,10 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_1000BASE_LX = 0x1C,
I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D,
I40E_PHY_TYPE_20GBASE_KR2 = 0x1E,
+ I40E_PHY_TYPE_25GBASE_KR = 0x1F,
+ I40E_PHY_TYPE_25GBASE_CR = 0x20,
+ I40E_PHY_TYPE_25GBASE_SR = 0x21,
+ I40E_PHY_TYPE_25GBASE_LR = 0x22,
I40E_PHY_TYPE_MAX
};
@@ -1650,6 +1654,7 @@ enum i40e_aq_phy_type {
#define I40E_LINK_SPEED_10GB_SHIFT 0x3
#define I40E_LINK_SPEED_40GB_SHIFT 0x4
#define I40E_LINK_SPEED_20GB_SHIFT 0x5
+#define I40E_LINK_SPEED_25GB_SHIFT 0x6
enum i40e_aq_link_speed {
I40E_LINK_SPEED_UNKNOWN = 0,
@@ -1657,7 +1662,8 @@ enum i40e_aq_link_speed {
I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT),
I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT),
I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT),
- I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT)
+ I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT),
+ I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT),
};
struct i40e_aqc_module_desc {
@@ -1690,7 +1696,13 @@ struct i40e_aq_get_phy_abilities_resp {
__le32 eeer_val;
u8 d3_lpan;
#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01
- u8 reserved[3];
+ u8 phy_type_ext;
+#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
+#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
+ u8 mod_type_ext;
+ u8 ext_comp_code;
u8 phy_id[4];
u8 module_type[3];
u8 qualified_module_count;
@@ -1712,7 +1724,12 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */
__le16 eee_capability;
__le32 eeer;
u8 low_power_ctrl;
- u8 reserved[3];
+ u8 phy_type_ext;
+#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
+#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
+ u8 reserved[2];
};
I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
@@ -1792,6 +1809,13 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_LINK_TX_DRAINED 0x01
#define I40E_AQ_LINK_TX_FLUSHED 0x03
#define I40E_AQ_LINK_FORCED_40G 0x10
+/* 25G Error Codes */
+#define I40E_AQ_25G_NO_ERR 0X00
+#define I40E_AQ_25G_NOT_PRESENT 0X01
+#define I40E_AQ_25G_NVM_CRC_ERR 0X02
+#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03
+#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04
+#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
__le16 max_frame_size;
u8 config;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index eb392d6..1318c7d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -53,6 +53,8 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
case I40E_DEV_ID_10G_BASE_T4:
case I40E_DEV_ID_20G_KR2:
case I40E_DEV_ID_20G_KR2_A:
+ case I40E_DEV_ID_25G_B:
+ case I40E_DEV_ID_25G_SFP28:
hw->mac.type = I40E_MAC_XL710;
break;
case I40E_DEV_ID_KX_X722:
@@ -1183,6 +1185,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
case I40E_PHY_TYPE_1000BASE_LX:
case I40E_PHY_TYPE_40GBASE_SR4:
case I40E_PHY_TYPE_40GBASE_LR4:
+ case I40E_PHY_TYPE_25GBASE_LR:
+ case I40E_PHY_TYPE_25GBASE_SR:
media = I40E_MEDIA_TYPE_FIBER;
break;
case I40E_PHY_TYPE_100BASE_TX:
@@ -1197,6 +1201,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
case I40E_PHY_TYPE_10GBASE_SFPP_CU:
case I40E_PHY_TYPE_40GBASE_AOC:
case I40E_PHY_TYPE_10GBASE_AOC:
+ case I40E_PHY_TYPE_25GBASE_CR:
media = I40E_MEDIA_TYPE_DA;
break;
case I40E_PHY_TYPE_1000BASE_KX:
@@ -1204,6 +1209,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
case I40E_PHY_TYPE_10GBASE_KR:
case I40E_PHY_TYPE_40GBASE_KR4:
case I40E_PHY_TYPE_20GBASE_KR2:
+ case I40E_PHY_TYPE_25GBASE_KR:
media = I40E_MEDIA_TYPE_BACKPLANE;
break;
case I40E_PHY_TYPE_SGMII:
@@ -1608,8 +1614,10 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
if (hw->aq.asq_last_status == I40E_AQ_RC_EIO)
status = I40E_ERR_UNKNOWN_PHY;
- if (report_init)
+ if (report_init) {
hw->phy.phy_types = le32_to_cpu(abilities->phy_type);
+ hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32);
+ }
return status;
}
@@ -1701,6 +1709,7 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK;
/* Copy over all the old settings */
config.phy_type = abilities.phy_type;
+ config.phy_type_ext = abilities.phy_type_ext;
config.link_speed = abilities.link_speed;
config.eee_capability = abilities.eee_capability;
config.eeer = abilities.eeer_val;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h
index dd4457d..8e46098 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h
@@ -39,6 +39,8 @@
#define I40E_DEV_ID_20G_KR2 0x1587
#define I40E_DEV_ID_20G_KR2_A 0x1588
#define I40E_DEV_ID_10G_BASE_T4 0x1589
+#define I40E_DEV_ID_25G_B 0x158A
+#define I40E_DEV_ID_25G_SFP28 0x158B
#define I40E_DEV_ID_KX_X722 0x37CE
#define I40E_DEV_ID_QSFP_X722 0x37CF
#define I40E_DEV_ID_SFP_X722 0x37D0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 6ba0035..935160a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -265,8 +265,9 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf)
static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
u32 *advertising)
{
- enum i40e_aq_capabilities_phy_type phy_types = pf->hw.phy.phy_types;
struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info;
+ u64 phy_types = pf->hw.phy.phy_types;
+
*supported = 0x0;
*advertising = 0x0;
@@ -369,6 +370,13 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported,
if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER))
*advertising |= ADVERTISED_1000baseKX_Full;
}
+ if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+ phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) {
+ *supported |= SUPPORTED_Autoneg;
+ *advertising |= ADVERTISED_Autoneg;
+ }
}
/**
@@ -491,6 +499,14 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
ADVERTISED_1000baseKX_Full |
ADVERTISED_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:
+ ecmd->supported = SUPPORTED_Autoneg;
+ ecmd->advertising = ADVERTISED_Autoneg;
+ /* TODO: add speeds when ethtool is ready to support*/
+ 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",
@@ -512,6 +528,14 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
case I40E_LINK_SPEED_40GB:
ethtool_cmd_speed_set(ecmd, SPEED_40000);
break;
+ case I40E_LINK_SPEED_25GB:
+#ifdef SPEED_25000
+ ethtool_cmd_speed_set(ecmd, SPEED_25000);
+#else
+ netdev_info(netdev,
+ "Speed is 25G, display not supported by this version of ethtool.\n");
+#endif
+ break;
case I40E_LINK_SPEED_20GB:
ethtool_cmd_speed_set(ecmd, SPEED_20000);
break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index aecf63b..b0486c9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -86,6 +86,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0},
/* required last entry */
{0, }
};
@@ -5260,6 +5262,9 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
case I40E_LINK_SPEED_20GB:
speed = "20 G";
break;
+ case I40E_LINK_SPEED_25GB:
+ speed = "25 G";
+ break;
case I40E_LINK_SPEED_10GB:
speed = "10 G";
break;
@@ -11368,7 +11373,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n",
i40e_stat_str(&pf->hw, err),
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
- pf->hw.phy.phy_types = le32_to_cpu(abilities.phy_type);
/* Add a filter to drop all Flow control frames from any VSI from being
* transmitted. By doing so we stop a malicious VF from sending out
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index bd1ffae..edc0abd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -213,47 +213,59 @@ struct i40e_link_status {
#define I40E_MODULE_TYPE_1000BASE_T 0x08
};
-enum i40e_aq_capabilities_phy_type {
- I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII),
- I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX),
- I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4),
- I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR),
- I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4),
- I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI),
- I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI),
- I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI),
- I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI),
- I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI),
- I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU),
- I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU),
- I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC),
- I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC),
- I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX),
- I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T),
- I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T),
- I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR),
- I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR),
- I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU),
- I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1),
- I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4),
- I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4),
- I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4),
- I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX),
- I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX),
- I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL =
- BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL),
- I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2)
-};
-
struct i40e_phy_info {
struct i40e_link_status link_info;
struct i40e_link_status link_info_old;
bool get_link_info;
enum i40e_media_type media_type;
/* all the phy types the NVM is capable of */
- enum i40e_aq_capabilities_phy_type phy_types;
-};
-
+ u64 phy_types;
+};
+
+#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII)
+#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX)
+#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4)
+#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR)
+#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4)
+#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI)
+#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI)
+#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI)
+#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI)
+#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI)
+#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC)
+#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC)
+#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX)
+#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T)
+#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T)
+#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR)
+#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR)
+#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1)
+#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4)
+#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4)
+#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4)
+#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX)
+#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX)
+#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \
+ BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL)
+#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2)
+/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some
+ * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit
+ * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So,
+ * a shift is needed to adjust for this with values larger than 31. The
+ * only affected values are I40E_PHY_TYPE_25GBASE_*.
+ */
+#define I40E_PHY_TYPE_OFFSET 1
+#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \
+ 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/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 05ed49b..d28b684 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2921,6 +2921,9 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
case I40E_LINK_SPEED_40GB:
speed = 40000;
break;
+ case I40E_LINK_SPEED_25GB:
+ speed = 25000;
+ break;
case I40E_LINK_SPEED_20GB:
speed = 20000;
break;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index 40b0eaf..f8d7d95 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1639,6 +1639,10 @@ enum i40e_aq_phy_type {
I40E_PHY_TYPE_1000BASE_LX = 0x1C,
I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D,
I40E_PHY_TYPE_20GBASE_KR2 = 0x1E,
+ I40E_PHY_TYPE_25GBASE_KR = 0x1F,
+ I40E_PHY_TYPE_25GBASE_CR = 0x20,
+ I40E_PHY_TYPE_25GBASE_SR = 0x21,
+ I40E_PHY_TYPE_25GBASE_LR = 0x22,
I40E_PHY_TYPE_MAX
};
@@ -1647,6 +1651,7 @@ enum i40e_aq_phy_type {
#define I40E_LINK_SPEED_10GB_SHIFT 0x3
#define I40E_LINK_SPEED_40GB_SHIFT 0x4
#define I40E_LINK_SPEED_20GB_SHIFT 0x5
+#define I40E_LINK_SPEED_25GB_SHIFT 0x6
enum i40e_aq_link_speed {
I40E_LINK_SPEED_UNKNOWN = 0,
@@ -1654,7 +1659,8 @@ enum i40e_aq_link_speed {
I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT),
I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT),
I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT),
- I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT)
+ I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT),
+ I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT),
};
struct i40e_aqc_module_desc {
@@ -1687,7 +1693,13 @@ struct i40e_aq_get_phy_abilities_resp {
__le32 eeer_val;
u8 d3_lpan;
#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01
- u8 reserved[3];
+ u8 phy_type_ext;
+#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
+#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
+ u8 mod_type_ext;
+ u8 ext_comp_code;
u8 phy_id[4];
u8 module_type[3];
u8 qualified_module_count;
@@ -1709,7 +1721,12 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */
__le16 eee_capability;
__le32 eeer;
u8 low_power_ctrl;
- u8 reserved[3];
+ u8 phy_type_ext;
+#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01
+#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
+ u8 reserved[2];
};
I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
@@ -1789,6 +1806,13 @@ struct i40e_aqc_get_link_status {
#define I40E_AQ_LINK_TX_DRAINED 0x01
#define I40E_AQ_LINK_TX_FLUSHED 0x03
#define I40E_AQ_LINK_FORCED_40G 0x10
+/* 25G Error Codes */
+#define I40E_AQ_25G_NO_ERR 0X00
+#define I40E_AQ_25G_NOT_PRESENT 0X01
+#define I40E_AQ_25G_NVM_CRC_ERR 0X02
+#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03
+#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04
+#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
__le16 max_frame_size;
u8 config;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 7953c13..aa63b7f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -53,6 +53,8 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw)
case I40E_DEV_ID_10G_BASE_T4:
case I40E_DEV_ID_20G_KR2:
case I40E_DEV_ID_20G_KR2_A:
+ case I40E_DEV_ID_25G_B:
+ case I40E_DEV_ID_25G_SFP28:
hw->mac.type = I40E_MAC_XL710;
break;
case I40E_DEV_ID_SFP_X722:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h
index 7023570..21dcaee 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h
@@ -39,6 +39,8 @@
#define I40E_DEV_ID_20G_KR2 0x1587
#define I40E_DEV_ID_20G_KR2_A 0x1588
#define I40E_DEV_ID_10G_BASE_T4 0x1589
+#define I40E_DEV_ID_25G_B 0x158A
+#define I40E_DEV_ID_25G_SFP28 0x158B
#define I40E_DEV_ID_VF 0x154C
#define I40E_DEV_ID_VF_HV 0x1571
#define I40E_DEV_ID_SFP_X722 0x37D0
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 515484c..c85e8a3 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -187,47 +187,59 @@ struct i40e_link_status {
#define I40E_MODULE_TYPE_1000BASE_T 0x08
};
-enum i40e_aq_capabilities_phy_type {
- I40E_CAP_PHY_TYPE_SGMII = BIT(I40E_PHY_TYPE_SGMII),
- I40E_CAP_PHY_TYPE_1000BASE_KX = BIT(I40E_PHY_TYPE_1000BASE_KX),
- I40E_CAP_PHY_TYPE_10GBASE_KX4 = BIT(I40E_PHY_TYPE_10GBASE_KX4),
- I40E_CAP_PHY_TYPE_10GBASE_KR = BIT(I40E_PHY_TYPE_10GBASE_KR),
- I40E_CAP_PHY_TYPE_40GBASE_KR4 = BIT(I40E_PHY_TYPE_40GBASE_KR4),
- I40E_CAP_PHY_TYPE_XAUI = BIT(I40E_PHY_TYPE_XAUI),
- I40E_CAP_PHY_TYPE_XFI = BIT(I40E_PHY_TYPE_XFI),
- I40E_CAP_PHY_TYPE_SFI = BIT(I40E_PHY_TYPE_SFI),
- I40E_CAP_PHY_TYPE_XLAUI = BIT(I40E_PHY_TYPE_XLAUI),
- I40E_CAP_PHY_TYPE_XLPPI = BIT(I40E_PHY_TYPE_XLPPI),
- I40E_CAP_PHY_TYPE_40GBASE_CR4_CU = BIT(I40E_PHY_TYPE_40GBASE_CR4_CU),
- I40E_CAP_PHY_TYPE_10GBASE_CR1_CU = BIT(I40E_PHY_TYPE_10GBASE_CR1_CU),
- I40E_CAP_PHY_TYPE_10GBASE_AOC = BIT(I40E_PHY_TYPE_10GBASE_AOC),
- I40E_CAP_PHY_TYPE_40GBASE_AOC = BIT(I40E_PHY_TYPE_40GBASE_AOC),
- I40E_CAP_PHY_TYPE_100BASE_TX = BIT(I40E_PHY_TYPE_100BASE_TX),
- I40E_CAP_PHY_TYPE_1000BASE_T = BIT(I40E_PHY_TYPE_1000BASE_T),
- I40E_CAP_PHY_TYPE_10GBASE_T = BIT(I40E_PHY_TYPE_10GBASE_T),
- I40E_CAP_PHY_TYPE_10GBASE_SR = BIT(I40E_PHY_TYPE_10GBASE_SR),
- I40E_CAP_PHY_TYPE_10GBASE_LR = BIT(I40E_PHY_TYPE_10GBASE_LR),
- I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU = BIT(I40E_PHY_TYPE_10GBASE_SFPP_CU),
- I40E_CAP_PHY_TYPE_10GBASE_CR1 = BIT(I40E_PHY_TYPE_10GBASE_CR1),
- I40E_CAP_PHY_TYPE_40GBASE_CR4 = BIT(I40E_PHY_TYPE_40GBASE_CR4),
- I40E_CAP_PHY_TYPE_40GBASE_SR4 = BIT(I40E_PHY_TYPE_40GBASE_SR4),
- I40E_CAP_PHY_TYPE_40GBASE_LR4 = BIT(I40E_PHY_TYPE_40GBASE_LR4),
- I40E_CAP_PHY_TYPE_1000BASE_SX = BIT(I40E_PHY_TYPE_1000BASE_SX),
- I40E_CAP_PHY_TYPE_1000BASE_LX = BIT(I40E_PHY_TYPE_1000BASE_LX),
- I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL =
- BIT(I40E_PHY_TYPE_1000BASE_T_OPTICAL),
- I40E_CAP_PHY_TYPE_20GBASE_KR2 = BIT(I40E_PHY_TYPE_20GBASE_KR2)
-};
-
struct i40e_phy_info {
struct i40e_link_status link_info;
struct i40e_link_status link_info_old;
bool get_link_info;
enum i40e_media_type media_type;
/* all the phy types the NVM is capable of */
- enum i40e_aq_capabilities_phy_type phy_types;
-};
-
+ u64 phy_types;
+};
+
+#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII)
+#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX)
+#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4)
+#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR)
+#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4)
+#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI)
+#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI)
+#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI)
+#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI)
+#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI)
+#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC)
+#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC)
+#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX)
+#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T)
+#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T)
+#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR)
+#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR)
+#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU)
+#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1)
+#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4)
+#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4)
+#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4)
+#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX)
+#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX)
+#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \
+ BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL)
+#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2)
+/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some
+ * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit
+ * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So,
+ * a shift is needed to adjust for this with values larger than 31. The
+ * only affected values are I40E_PHY_TYPE_25GBASE_*.
+ */
+#define I40E_PHY_TYPE_OFFSET 1
+#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \
+ I40E_PHY_TYPE_OFFSET)
+#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \
+ 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/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index a994015..272d600 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -85,6 +85,14 @@ static int i40evf_get_settings(struct net_device *netdev,
case I40E_LINK_SPEED_40GB:
ethtool_cmd_speed_set(ecmd, SPEED_40000);
break;
+ case I40E_LINK_SPEED_25GB:
+#ifdef SPEED_25000
+ ethtool_cmd_speed_set(ecmd, SPEED_25000);
+#else
+ netdev_info(netdev,
+ "Speed is 25G, display not supported by this version of ethtool.\n");
+#endif
+ break;
case I40E_LINK_SPEED_20GB:
ethtool_cmd_speed_set(ecmd, SPEED_20000);
break;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index ddf478d..2059a8e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -836,6 +836,9 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter)
case I40E_LINK_SPEED_40GB:
speed = "40 G";
break;
+ case I40E_LINK_SPEED_25GB:
+ speed = "25 G";
+ break;
case I40E_LINK_SPEED_20GB:
speed = "20 G";
break;
--
2.9.3
^ permalink raw reply related
* [net-next 11/20] i40e: Add functions which apply correct PHY access method for read and write operation
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Michal Kosiarz, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Michal Kosiarz <michal.kosiarz@intel.com>
Depending on external PHY type, register access method should be
different. Clause22 or Clause45 can be chosen for different PHYs.
Implemented functions apply correct access method for used device.
Change-ID: If39d5f0da9c0b905a8cbdc1ab89885535e7d0426
Signed-off-by: Michal Kosiarz <michal.kosiarz@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_common.c | 72 ++++++++++++++++++++++
drivers/net/ethernet/intel/i40e/i40e_prototype.h | 4 ++
drivers/net/ethernet/intel/i40evf/i40e_prototype.h | 4 ++
3 files changed, 80 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index f8c4c14..1287359 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -4676,6 +4676,78 @@ i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw,
}
/**
+ * i40e_write_phy_register
+ * @hw: pointer to the HW structure
+ * @page: registers page number
+ * @reg: register address in the page
+ * @phy_adr: PHY address on MDIO interface
+ * @value: PHY register value
+ *
+ * Writes value to specified PHY register
+ **/
+i40e_status i40e_write_phy_register(struct i40e_hw *hw,
+ u8 page, u16 reg, u8 phy_addr, u16 value)
+{
+ i40e_status status;
+
+ switch (hw->device_id) {
+ case I40E_DEV_ID_1G_BASE_T_X722:
+ status = i40e_write_phy_register_clause22(hw, reg, phy_addr,
+ value);
+ break;
+ case I40E_DEV_ID_10G_BASE_T:
+ case I40E_DEV_ID_10G_BASE_T4:
+ case I40E_DEV_ID_10G_BASE_T_X722:
+ case I40E_DEV_ID_25G_B:
+ case I40E_DEV_ID_25G_SFP28:
+ status = i40e_write_phy_register_clause45(hw, page, reg,
+ phy_addr, value);
+ break;
+ default:
+ status = I40E_ERR_UNKNOWN_PHY;
+ break;
+ }
+
+ return status;
+}
+
+/**
+ * i40e_read_phy_register
+ * @hw: pointer to the HW structure
+ * @page: registers page number
+ * @reg: register address in the page
+ * @phy_adr: PHY address on MDIO interface
+ * @value: PHY register value
+ *
+ * Reads specified PHY register value
+ **/
+i40e_status i40e_read_phy_register(struct i40e_hw *hw,
+ u8 page, u16 reg, u8 phy_addr, u16 *value)
+{
+ i40e_status status;
+
+ switch (hw->device_id) {
+ case I40E_DEV_ID_1G_BASE_T_X722:
+ status = i40e_read_phy_register_clause22(hw, reg, phy_addr,
+ value);
+ break;
+ case I40E_DEV_ID_10G_BASE_T:
+ case I40E_DEV_ID_10G_BASE_T4:
+ case I40E_DEV_ID_10G_BASE_T_X722:
+ case I40E_DEV_ID_25G_B:
+ case I40E_DEV_ID_25G_SFP28:
+ status = i40e_read_phy_register_clause45(hw, page, reg,
+ phy_addr, value);
+ break;
+ default:
+ status = I40E_ERR_UNKNOWN_PHY;
+ break;
+ }
+
+ return status;
+}
+
+/**
* i40e_get_phy_address
* @hw: pointer to the HW structure
* @dev_num: PHY port num that address we want
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 37d67e7..2551fc8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -373,6 +373,10 @@ i40e_status i40e_read_phy_register_clause45(struct i40e_hw *hw,
u8 page, u16 reg, u8 phy_addr, u16 *value);
i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw,
u8 page, u16 reg, u8 phy_addr, u16 value);
+i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
+ u8 phy_addr, u16 *value);
+i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
+ u8 phy_addr, u16 value);
u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
u32 time, u32 interval);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index d89d521..ba6c6bd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -115,6 +115,10 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page,
u16 reg, u8 phy_addr, u16 *value);
i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page,
u16 reg, u8 phy_addr, u16 value);
+i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
+ u8 phy_addr, u16 *value);
+i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg,
+ u8 phy_addr, u16 value);
u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num);
i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw,
u32 time, u32 interval);
--
2.9.3
^ permalink raw reply related
* [net-next 10/20] i40e: Add FEC for 25g
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Carolyn Wyborny, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Mitch Williams, Jacek Naczyk, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
This patch adds adminq support for Forward Error
Correction ("FEC")for 25g products.
Change-ID: Iaff4910737c239d2c730e5c22a313ce9c37d3964
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Jacek Naczyk <jacek.naczyk@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 | 25 ++++++++++++++++++++--
drivers/net/ethernet/intel/i40e/i40e_common.c | 2 ++
.../net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 25 ++++++++++++++++++++--
3 files changed, 48 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index c9d1f91..b2101a5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1686,6 +1686,8 @@ struct i40e_aq_get_phy_abilities_resp {
#define I40E_AQ_PHY_LINK_ENABLED 0x08
#define I40E_AQ_PHY_AN_ENABLED 0x10
#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20
+#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40
+#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80
__le16 eee_capability;
#define I40E_AQ_EEE_100BASE_TX 0x0002
#define I40E_AQ_EEE_1000BASE_T 0x0004
@@ -1701,7 +1703,16 @@ 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
- u8 mod_type_ext;
+ u8 fec_cfg_curr_mod_ext_info;
+#define I40E_AQ_ENABLE_FEC_KR 0x01
+#define I40E_AQ_ENABLE_FEC_RS 0x02
+#define I40E_AQ_REQUEST_FEC_KR 0x04
+#define I40E_AQ_REQUEST_FEC_RS 0x08
+#define I40E_AQ_ENABLE_FEC_AUTO 0x10
+#define I40E_AQ_FEC
+#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0
+#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5
+
u8 ext_comp_code;
u8 phy_id[4];
u8 module_type[3];
@@ -1729,7 +1740,15 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */
#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
- u8 reserved[2];
+ u8 fec_config;
+#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0)
+#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1)
+#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2)
+#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3)
+#define I40E_AQ_SET_FEC_AUTO BIT(4)
+#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0
+#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT)
+ u8 reserved;
};
I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
@@ -1819,6 +1838,8 @@ struct i40e_aqc_get_link_status {
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
__le16 max_frame_size;
u8 config;
+#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01
+#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
u8 external_power_ability;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 1318c7d..f8c4c14 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1714,6 +1714,8 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
config.eee_capability = abilities.eee_capability;
config.eeer = abilities.eeer_val;
config.low_power_ctrl = abilities.d3_lpan;
+ config.fec_config = abilities.fec_cfg_curr_mod_ext_info &
+ I40E_AQ_PHY_FEC_CONFIG_MASK;
status = i40e_aq_set_phy_config(hw, &config, NULL);
if (status)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index f8d7d95..eeb9864 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1683,6 +1683,8 @@ struct i40e_aq_get_phy_abilities_resp {
#define I40E_AQ_PHY_LINK_ENABLED 0x08
#define I40E_AQ_PHY_AN_ENABLED 0x10
#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20
+#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40
+#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80
__le16 eee_capability;
#define I40E_AQ_EEE_100BASE_TX 0x0002
#define I40E_AQ_EEE_1000BASE_T 0x0004
@@ -1698,7 +1700,16 @@ 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
- u8 mod_type_ext;
+ u8 fec_cfg_curr_mod_ext_info;
+#define I40E_AQ_ENABLE_FEC_KR 0x01
+#define I40E_AQ_ENABLE_FEC_RS 0x02
+#define I40E_AQ_REQUEST_FEC_KR 0x04
+#define I40E_AQ_REQUEST_FEC_RS 0x08
+#define I40E_AQ_ENABLE_FEC_AUTO 0x10
+#define I40E_AQ_FEC
+#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0
+#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5
+
u8 ext_comp_code;
u8 phy_id[4];
u8 module_type[3];
@@ -1726,7 +1737,15 @@ struct i40e_aq_set_phy_config { /* same bits as above in all */
#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
- u8 reserved[2];
+ u8 fec_config;
+#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0)
+#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1)
+#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2)
+#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3)
+#define I40E_AQ_SET_FEC_AUTO BIT(4)
+#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0
+#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT)
+ u8 reserved;
};
I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
@@ -1816,6 +1835,8 @@ struct i40e_aqc_get_link_status {
u8 loopback; /* use defines from i40e_aqc_set_lb_mode */
__le16 max_frame_size;
u8 config;
+#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01
+#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
u8 external_power_ability;
--
2.9.3
^ permalink raw reply related
* [net-next 06/20] i40e: Blink LED on 1G BaseT boards
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Henry Tieman, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Harshitha Ramamurthy, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Henry Tieman <henry.w.tieman@intel.com>
Before this patch "ethtool -p" was not blinking the LEDs on boards
with 1G BaseT PHYs.
This commit identifies 1G BaseT boards as having the LEDs connected
to the MAC. Also, renamed the flag to be more descriptive of usage.
The flag is now I40E_FLAG_PHY_CONTROLS_LEDS.
Change-ID: I4eb741da9780da7849ddf2dc4c0cb27ffa42a801
Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Harshitha Ramamurthy <harshitha.ramamurthy@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 | 2 +-
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 10 +++++-----
drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++--
3 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 06e3c23..b8f2978 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -356,7 +356,7 @@ struct i40e_pf {
#define I40E_FLAG_NO_DCB_SUPPORT BIT_ULL(45)
#define I40E_FLAG_USE_SET_LLDP_MIB BIT_ULL(46)
#define I40E_FLAG_STOP_FW_LLDP BIT_ULL(47)
-#define I40E_FLAG_HAVE_10GBASET_PHY BIT_ULL(48)
+#define I40E_FLAG_PHY_CONTROLS_LEDS BIT_ULL(48)
#define I40E_FLAG_PF_MAC BIT_ULL(50)
#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51)
#define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 76753e1..6ba0035 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1890,7 +1890,7 @@ static int i40e_set_phys_id(struct net_device *netdev,
switch (state) {
case ETHTOOL_ID_ACTIVE:
- if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) {
+ if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) {
pf->led_status = i40e_led_get(hw);
} else {
i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL);
@@ -1900,20 +1900,20 @@ static int i40e_set_phys_id(struct net_device *netdev,
}
return blink_freq;
case ETHTOOL_ID_ON:
- if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY))
+ if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS))
i40e_led_set(hw, 0xf, false);
else
ret = i40e_led_set_phy(hw, true, pf->led_status, 0);
break;
case ETHTOOL_ID_OFF:
- if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY))
+ if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS))
i40e_led_set(hw, 0x0, false);
else
ret = i40e_led_set_phy(hw, false, pf->led_status, 0);
break;
case ETHTOOL_ID_INACTIVE:
- if (!(pf->flags & I40E_FLAG_HAVE_10GBASET_PHY)) {
- i40e_led_set(hw, false, pf->led_status);
+ if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) {
+ i40e_led_set(hw, pf->led_status, false);
} else {
ret = i40e_led_set_phy(hw, false, pf->led_status,
(pf->phy_led_val |
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ae4a2b2..dbb854b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11380,8 +11380,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pf->main_vsi_seid);
if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) ||
- (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4))
- pf->flags |= I40E_FLAG_HAVE_10GBASET_PHY;
+ (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4))
+ pf->flags |= I40E_FLAG_PHY_CONTROLS_LEDS;
if (pf->hw.device_id == I40E_DEV_ID_SFP_I_X722)
pf->flags |= I40E_FLAG_HAVE_CRT_RETIMER;
/* print a string summarizing features */
--
2.9.3
^ permalink raw reply related
* [net-next 05/20] i40e: remove code to handle dev_addr specially
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
The netdev->dev_addr MAC filter already exists in the
MAC/VLAN hash table, as it is added when we configure
the netdev in i40e_configure_netdev. Because we already
know that this address will be updated in the
hash_for_each loops, we do not need to handle it
specially. This removes duplicate code and simplifies
the i40e_vsi_add_vlan and i40e_vsi_kill_vlan functions.
Because we know these filters must be part of the
MAC/VLAN hash table, this should not have any functional
impact on what filters are included and is merely a code
simplification.
Change-ID: I5e648302dbdd7cc29efc6d203b7019c11f0b5705
Signed-off-by: Jacob Keller <jacob.e.keller@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_main.c | 43 +++++------------------------
1 file changed, 7 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c467cc4..ae4a2b2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2515,17 +2515,6 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
/* Locked once because all functions invoked below iterates list*/
spin_lock_bh(&vsi->mac_filter_hash_lock);
- if (vsi->netdev) {
- add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid);
- if (!add_f) {
- dev_info(&vsi->back->pdev->dev,
- "Could not add vlan filter %d for %pM\n",
- vid, vsi->netdev->dev_addr);
- spin_unlock_bh(&vsi->mac_filter_hash_lock);
- return -ENOMEM;
- }
- }
-
hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (f->state == I40E_FILTER_REMOVE)
continue;
@@ -2539,28 +2528,14 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
}
}
- /* Now if we add a vlan tag, make sure to check if it is the first
- * tag (i.e. a "tag" -1 does exist) and if so replace the -1 "tag"
- * with 0, so we now accept untagged and specified tagged traffic
- * (and not all tags along with untagged)
+ /* When we add a new VLAN filter, we need to make sure that all existing
+ * filters which are marked as vid=-1 (I40E_VLAN_ANY) are converted to
+ * vid=0. The simplest way is just search for all filters marked as
+ * vid=-1 and replace them with vid=0. This converts all filters that
+ * were marked to receive all traffic (tagged or untagged) into
+ * filters to receive only untagged traffic, so that we don't receive
+ * tagged traffic for VLANs which we have not configured.
*/
- if (vid > 0 && vsi->netdev) {
- del_f = i40e_find_filter(vsi, vsi->netdev->dev_addr,
- I40E_VLAN_ANY);
- if (del_f) {
- __i40e_del_filter(vsi, del_f);
- add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, 0);
- if (!add_f) {
- dev_info(&vsi->back->pdev->dev,
- "Could not add filter 0 for %pM\n",
- vsi->netdev->dev_addr);
- spin_unlock_bh(&vsi->mac_filter_hash_lock);
- return -ENOMEM;
- }
- }
- }
-
- /* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */
if (vid > 0 && !vsi->info.pvid) {
hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (f->state == I40E_FILTER_REMOVE)
@@ -2597,7 +2572,6 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
**/
void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
{
- struct net_device *netdev = vsi->netdev;
struct i40e_mac_filter *f;
struct hlist_node *h;
int bkt;
@@ -2605,9 +2579,6 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
/* Locked once because all functions invoked below iterates list */
spin_lock_bh(&vsi->mac_filter_hash_lock);
- if (vsi->netdev)
- i40e_del_filter(vsi, netdev->dev_addr, vid);
-
hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (f->vlan == vid)
__i40e_del_filter(vsi, f);
--
2.9.3
^ permalink raw reply related
* [net-next 07/20] Changed version from 1.6.21 to 1.6.25
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Bimmy Pujari, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Bimmy Pujari <bimmy.pujari@intel.com>
Signed-off-by: Bimmy Pujari <bimmy.pujari@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_main.c | 2 +-
drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dbb854b..aecf63b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -41,7 +41,7 @@ static const char i40e_driver_string[] =
#define DRV_VERSION_MAJOR 1
#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 21
+#define DRV_VERSION_BUILD 25
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index ca85021..c0fc533 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -38,7 +38,7 @@ static const char i40evf_driver_string[] =
#define DRV_VERSION_MAJOR 1
#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 21
+#define DRV_VERSION_BUILD 25
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) \
--
2.9.3
^ permalink raw reply related
* [net-next 04/20] i40e/i40evf: napi_poll must return the work done
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Alexander Duyck, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
Currently the function i40e_napi-poll() returns 0 when it clean completely
the Rx rings, but this foul budget accounting in core code.
Fix this by returning the actual work done, capped to budget - 1, since
the core doesn't allow to return the full budget when the driver modifies
the NAPI status
This is based on a similar change that was made for the ixgbe driver by
Paolo Abeni.
Change-ID: Ic3d93ad2fa2fc8ce3164bc461e69367da0f9173b
Signed-off-by: Alexander Duyck <alexander.h.duyck@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_txrx.c | 2 +-
drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 5544b50..352cf7c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2027,7 +2027,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
else
i40e_update_enable_itr(vsi, q_vector);
- return 0;
+ return min(work_done, budget - 1);
}
/**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c4b174a..df67ef3 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1490,7 +1490,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
else
i40e_update_enable_itr(vsi, q_vector);
- return 0;
+ return min(work_done, budget - 1);
}
/**
--
2.9.3
^ permalink raw reply related
* [net-next 03/20] i40e: restore workaround for removing default MAC filter
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Jacob Keller, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
A previous commit 53cb6e9e8949 ("i40e: Removal of workaround for simple
MAC address filter deletion") removed a workaround for some
firmware versions which was reported to not be necessary in production
NICs. Unfortunately this workaround is necessary in some configurations,
specifically the Ethernet Controller XL710 for 40GbE QSFP+ (8086:1583).
Without this patch, the mentioned NICs with current firmware exhibit
issues when adding VLANs, as outlined by the following reproduction:
$modprobe i40e
$ip link set <device> up
$ip link add link <device> vlan100 type vlan id 100
$dmesg | tail
<snip>
kernel: i40e 0000:82:00.0: Error I40E_AQ_RC_EINVAL adding RX
filters on PF, promiscuous mode forced on
This results in filters being marked as FAILED and setting the device in
promiscuous mode.
The root cause of receiving the -EINVAL error response appears to be due
to a conflict with the default MAC filter which still exists on the
default firmware for this device. Attempting to add a new VLAN filter on
the default MAC address conflicts with the IGNORE_VLAN setting on the
default rule.
Change-ID: I4d8f6d48ac5f60cfe981b3baad30eb4d7c170d61
Signed-off-by: Jacob Keller <jacob.e.keller@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_main.c | 41 +++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4534d41..c467cc4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1226,6 +1226,39 @@ bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi)
}
/**
+ * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM
+ * @vsi: the PF Main VSI - inappropriate for any other VSI
+ * @macaddr: the MAC address
+ *
+ * Remove whatever filter the firmware set up so the driver can manage
+ * its own filtering intelligently.
+ **/
+static void i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr)
+{
+ struct i40e_aqc_remove_macvlan_element_data element;
+ struct i40e_pf *pf = vsi->back;
+
+ /* Only appropriate for the PF main VSI */
+ if (vsi->type != I40E_VSI_MAIN)
+ return;
+
+ memset(&element, 0, sizeof(element));
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ /* Ignore error returns, some firmware does it this way... */
+ element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+ i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
+
+ memset(&element, 0, sizeof(element));
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ /* ...and some firmware does it this way. */
+ element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH |
+ I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
+ i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
+}
+
+/**
* i40e_add_filter - Add a mac/vlan filter to the VSI
* @vsi: the VSI to be searched
* @macaddr: the MAC address
@@ -9295,6 +9328,12 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
if (vsi->type == I40E_VSI_MAIN) {
SET_NETDEV_DEV(netdev, &pf->pdev->dev);
ether_addr_copy(mac_addr, hw->mac.perm_addr);
+ /* The following steps are necessary to prevent reception
+ * of tagged packets - some older NVM configurations load a
+ * default a MAC-VLAN filter that accepts any tagged packet
+ * which must be replaced by a normal filter.
+ */
+ i40e_rm_default_mac_filter(vsi, mac_addr);
spin_lock_bh(&vsi->mac_filter_hash_lock);
i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY);
spin_unlock_bh(&vsi->mac_filter_hash_lock);
@@ -9828,6 +9867,8 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
+ if (vsi->type == I40E_VSI_MAIN)
+ i40e_rm_default_mac_filter(vsi, pf->hw.mac.perm_addr);
/* assign it some queues */
ret = i40e_alloc_rings(vsi);
--
2.9.3
^ permalink raw reply related
* [net-next 02/20] i40e: simplify txd use count calculation
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Mitch Williams, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Alexander Duyck, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Mitch Williams <mitch.a.williams@intel.com>
The i40e_txd_use_count function was fast but confusing. In the comments,
it even admits that it's ugly. So replace it with a new function that is
(very) slightly faster and has extensive commenting to help the thicker
among us (including the author, who will forget in a week) understand
how it works.
Change-ID: Ifb533f13786a0bf39cb29f77969a5be2c83d9a87
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@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_txrx.h | 45 +++++++++++++++++----------
drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 45 +++++++++++++++++----------
2 files changed, 56 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index de8550f..e065321 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -173,26 +173,37 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
#define I40E_MAX_DATA_PER_TXD_ALIGNED \
(I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1))
-/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is
- * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact
- * that 12K is not a power of 2 and division is expensive. It is used to
- * approximate the number of descriptors used per linear buffer. Note
- * that this will overestimate in some cases as it doesn't account for the
- * fact that we will add up to 4K - 1 in aligning the 12K buffer, however
- * the error should not impact things much as large buffers usually mean
- * we will use fewer descriptors then there are frags in an skb.
+/**
+ * i40e_txd_use_count - estimate the number of descriptors needed for Tx
+ * @size: transmit request size in bytes
+ *
+ * Due to hardware alignment restrictions (4K alignment), we need to
+ * assume that we can have no more than 12K of data per descriptor, even
+ * though each descriptor can take up to 16K - 1 bytes of aligned memory.
+ * Thus, we need to divide by 12K. But division is slow! Instead,
+ * we decompose the operation into shifts and one relatively cheap
+ * multiply operation.
+ *
+ * To divide by 12K, we first divide by 4K, then divide by 3:
+ * To divide by 4K, shift right by 12 bits
+ * To divide by 3, multiply by 85, then divide by 256
+ * (Divide by 256 is done by shifting right by 8 bits)
+ * Finally, we add one to round up. Because 256 isn't an exact multiple of
+ * 3, we'll underestimate near each multiple of 12K. This is actually more
+ * accurate as we have 4K - 1 of wiggle room that we can fit into the last
+ * segment. For our purposes this is accurate out to 1M which is orders of
+ * magnitude greater than our largest possible GSO size.
+ *
+ * This would then be implemented as:
+ * return (((size >> 12) * 85) >> 8) + 1;
+ *
+ * Since multiplication and division are commutative, we can reorder
+ * operations into:
+ * return ((size * 85) >> 20) + 1;
*/
static inline unsigned int i40e_txd_use_count(unsigned int size)
{
- const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED;
- const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max;
- unsigned int adjust = ~(u32)0;
-
- /* if we rounded up on the reciprocal pull down the adjustment */
- if ((max * reciprocal) > adjust)
- adjust = ~(u32)(reciprocal - 1);
-
- return (u32)((((u64)size * reciprocal) + adjust) >> 32);
+ return ((size * 85) >> 20) + 1;
}
/* Tx Descriptors needed, worst case */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index a586e19..a5fc789 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -173,26 +173,37 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc,
#define I40E_MAX_DATA_PER_TXD_ALIGNED \
(I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1))
-/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is
- * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact
- * that 12K is not a power of 2 and division is expensive. It is used to
- * approximate the number of descriptors used per linear buffer. Note
- * that this will overestimate in some cases as it doesn't account for the
- * fact that we will add up to 4K - 1 in aligning the 12K buffer, however
- * the error should not impact things much as large buffers usually mean
- * we will use fewer descriptors then there are frags in an skb.
+/**
+ * i40e_txd_use_count - estimate the number of descriptors needed for Tx
+ * @size: transmit request size in bytes
+ *
+ * Due to hardware alignment restrictions (4K alignment), we need to
+ * assume that we can have no more than 12K of data per descriptor, even
+ * though each descriptor can take up to 16K - 1 bytes of aligned memory.
+ * Thus, we need to divide by 12K. But division is slow! Instead,
+ * we decompose the operation into shifts and one relatively cheap
+ * multiply operation.
+ *
+ * To divide by 12K, we first divide by 4K, then divide by 3:
+ * To divide by 4K, shift right by 12 bits
+ * To divide by 3, multiply by 85, then divide by 256
+ * (Divide by 256 is done by shifting right by 8 bits)
+ * Finally, we add one to round up. Because 256 isn't an exact multiple of
+ * 3, we'll underestimate near each multiple of 12K. This is actually more
+ * accurate as we have 4K - 1 of wiggle room that we can fit into the last
+ * segment. For our purposes this is accurate out to 1M which is orders of
+ * magnitude greater than our largest possible GSO size.
+ *
+ * This would then be implemented as:
+ * return (((size >> 12) * 85) >> 8) + 1;
+ *
+ * Since multiplication and division are commutative, we can reorder
+ * operations into:
+ * return ((size * 85) >> 20) + 1;
*/
static inline unsigned int i40e_txd_use_count(unsigned int size)
{
- const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED;
- const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max;
- unsigned int adjust = ~(u32)0;
-
- /* if we rounded up on the reciprocal pull down the adjustment */
- if ((max * reciprocal) > adjust)
- adjust = ~(u32)(reciprocal - 1);
-
- return (u32)((((u64)size * reciprocal) + adjust) >> 32);
+ return ((size * 85) >> 20) + 1;
}
/* Tx Descriptors needed, worst case */
--
2.9.3
^ permalink raw reply related
* [net-next 01/20] i40e: Driver prints log message on link speed change
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem
Cc: Filip Sadowski, netdev, nhorman, sassmann, jogreene,
guru.anbalagane, Jeff Kirsher
In-Reply-To: <20161207073354.88568-1-jeffrey.t.kirsher@intel.com>
From: Filip Sadowski <filip.sadowski@intel.com>
This patch makes the driver log link speed change. Before applying the
patch link messages were printed only on state change. Now message is
printed when link is brought up or down and when speed changes.
Change-ID: Ifbee14b4b16c24967450b3cecac6e8351dcc8f74
Signed-off-by: Filip Sadowski <filip.sadowski@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 | 1 +
drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +++++-
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 4cb8fb3..06e3c23 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -596,6 +596,7 @@ struct i40e_vsi {
u16 veb_idx; /* index of VEB parent */
struct kobject *kobj; /* sysfs object */
bool current_isup; /* Sync 'link up' logging */
+ enum i40e_aq_link_speed current_speed; /* Sync link speed logging */
void *priv; /* client driver data reference. */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5777e49..4534d41 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5225,12 +5225,16 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
*/
void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
{
+ enum i40e_aq_link_speed new_speed;
char *speed = "Unknown";
char *fc = "Unknown";
- if (vsi->current_isup == isup)
+ new_speed = vsi->back->hw.phy.link_info.link_speed;
+
+ if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed))
return;
vsi->current_isup = isup;
+ vsi->current_speed = new_speed;
if (!isup) {
netdev_info(vsi->netdev, "NIC Link is Down\n");
return;
--
2.9.3
^ permalink raw reply related
* [net-next 00/20][pull request] 40GbE Intel Wired LAN Driver Updates 2016-12-06
From: Jeff Kirsher @ 2016-12-07 7:33 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, nhorman, sassmann, jogreene,
guru.anbalagane
This series contains updates to i40e and i40evf only.
Filip modifies the i40e to log link speed change and when the link is
brought up and down.
Mitch replaces i40e_txd_use_count() with a new function which is slightly
faster and better documented so the dim witted can better follow the
code. Fixes the locking of the service task so that it is actually
done in the service task and not in the scheduling function which calls
the service task.
Jacob, being the busy little beaver he is, provides most of the changes
starting restores a workaround that is still needed in some configurations,
specifically the Ethernet Controller XL710 for 40GbE QSFP+. Removes
duplicate code and simplifies the i40e_vsi_add_vlan() and
i40e_vsi_kill_vlan() functions. Removes detection of PTP frames over L4
(UDP) on the XL710 MAC, since there was a product decision to defeature
it. Fixed a previous refactor of active filters which caused issues in
the accounting of active_filters. Remaining work was done in the VLAN
filters to improve readability and simplify code as much as possible
to reduce inconsistencies.
Alex fixes foul budget accounting in core code by returning actual
work done, capped to budget-1.
Henry fixes the "ethtool -p" function for 1G BaseT PHYs.
Carolyn adds support for 25G devices for i40e and i40evf.
Michal adds functions to apply the correct access method for external PHYs
which could use Clause22 or Clause45 depending on the PHY.
The following are changes since commit d4aea20d889e05575bb331a3dadf176176f7d631:
tun: Use netif_receive_skb instead of netif_rx
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue 40GbE
Alexander Duyck (1):
i40e/i40evf: napi_poll must return the work done
Bimmy Pujari (1):
Changed version from 1.6.21 to 1.6.25
Carolyn Wyborny (2):
i40e: Add support for 25G devices
i40e: Add FEC for 25g
Filip Sadowski (1):
i40e: Driver prints log message on link speed change
Henry Tieman (1):
i40e: Blink LED on 1G BaseT boards
Jacob Keller (11):
i40e: restore workaround for removing default MAC filter
i40e: remove code to handle dev_addr specially
i40e: use unsigned printf format specifier for active_filters count
i40e: defeature support for PTP L4 frame detection on XL710
i40e: recalculate vsi->active_filters from hash contents
i40e: refactor i40e_update_filter_state to avoid passing aq_err
i40e: delete filter after adding its replacement when converting
i40e: factor out addition/deletion of VLAN per each MAC address
i40e: use (add|rm)_vlan_all_mac helper functions when changing PVID
i40e: move all updates for VLAN mode into i40e_sync_vsi_filters
i40e: don't allow i40e_vsi_(add|kill)_vlan to operate when VID<1
Michal Kosiarz (1):
i40e: Add functions which apply correct PHY access method for read and
write operation
Mitch Williams (2):
i40e: simplify txd use count calculation
i40e: lock service task correctly
drivers/net/ethernet/intel/i40e/i40e.h | 10 +-
drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 51 ++-
drivers/net/ethernet/intel/i40e/i40e_common.c | 85 +++-
drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 2 +-
drivers/net/ethernet/intel/i40e/i40e_devids.h | 2 +
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 51 ++-
drivers/net/ethernet/intel/i40e/i40e_main.c | 491 ++++++++++++---------
drivers/net/ethernet/intel/i40e/i40e_prototype.h | 4 +
drivers/net/ethernet/intel/i40e/i40e_ptp.c | 21 +-
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +-
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 45 +-
drivers/net/ethernet/intel/i40e/i40e_type.h | 82 ++--
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 46 +-
.../net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 51 ++-
drivers/net/ethernet/intel/i40evf/i40e_common.c | 2 +
drivers/net/ethernet/intel/i40evf/i40e_devids.h | 2 +
drivers/net/ethernet/intel/i40evf/i40e_prototype.h | 4 +
drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 2 +-
drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 45 +-
drivers/net/ethernet/intel/i40evf/i40e_type.h | 82 ++--
drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c | 8 +
drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
.../net/ethernet/intel/i40evf/i40evf_virtchnl.c | 3 +
23 files changed, 731 insertions(+), 362 deletions(-)
--
2.9.3
^ permalink raw reply
* Re: [PATCH 10/10] virtio: enable endian checks for sparse builds
From: Christoph Hellwig @ 2016-12-07 7:30 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: linux-kernel, Jason Wang, linux-kbuild, Michal Marek,
Arnd Bergmann, Greg Kroah-Hartman, Matt Mackall, Herbert Xu,
David Airlie, Gerd Hoffmann, Ohad Ben-Cohen,
Christian Borntraeger, Cornelia Huck, James E.J. Bottomley,
David S. Miller, Jens Axboe, Neil Armstrong, Stefan Hajnoczi,
Asias He, linux-crypto, dri-devel
In-Reply-To: <1481038106-24899-11-git-send-email-mst@redhat.com>
On Tue, Dec 06, 2016 at 05:41:05PM +0200, Michael S. Tsirkin wrote:
> __CHECK_ENDIAN__ isn't on by default presumably because
> it triggers too many sparse warnings for correct code.
> But virtio is now clean of these warnings, and
> we want to keep it this way - enable this for
> sparse builds.
>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Nah. Please just enable it globally when using sparse. I actually
had a chat with Linus about that a while ago and he seemed generally
fine with it, I just didn't manage to actually do it..
^ permalink raw reply
* Re: [PATCH net-next v2 0/7] bnxt_en: Add interface to support RDMA driver.
From: Christoph Hellwig @ 2016-12-07 7:29 UTC (permalink / raw)
To: Michael Chan
Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q, netdev-u79uwXL29TY76Z2rM5mHXA,
selvin.xavier-dY08KVG/lbpWk0Htik3J/w,
somnath.kotur-dY08KVG/lbpWk0Htik3J/w,
dledford-H+wXaHxf7aLQT0dZR+AlfA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1481088381-30411-1-git-send-email-michael.chan-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
On Wed, Dec 07, 2016 at 12:26:14AM -0500, Michael Chan wrote:
> This series adds an interface to support a brand new RDMA driver bnxt_re.
> The first step is to re-arrange some code so that pci_enable_msix() can
> be called during pci probe. The purpose is to allow the RDMA driver to
> initialize and stay initialized whether the netdev is up or down.
Please switch form pci_enable_msix to pci_alloc_irq_vectors for any
changes to MSI-X code, thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: linux-next: manual merge of the staging tree with the net-next tree
From: Greg KH @ 2016-12-07 7:02 UTC (permalink / raw)
To: Stephen Rothwell
Cc: David Miller, Networking, linux-next, linux-kernel, Jarod Wilson
In-Reply-To: <20161207150447.160b7735@canb.auug.org.au>
On Wed, Dec 07, 2016 at 03:04:47PM +1100, Stephen Rothwell wrote:
> Hi Greg,
>
> Today's linux-next merge of the staging tree got a conflict in:
>
> drivers/staging/slicoss/slicoss.c
>
> between commit:
>
> a52ad514fdf3 ("net: deprecate eth_change_mtu, remove usage")
>
> from the net-next tree and commit:
>
> 0af72df267f2 ("staging: slicoss: remove the staging driver")
>
> from the staging tree.
>
> I fixed it up (I just removed the file) and can carry the fix as
> necessary. This is now fixed as far as linux-next is concerned, but any
> non trivial conflicts should be mentioned to your upstream maintainer
> when your tree is submitted for merging. You may also want to consider
> cooperating with the maintainer of the conflicting tree to minimise any
> particularly complex conflicts.
Thanks, we did coordinate this :)
greg k-h
^ permalink raw reply
* [net-next] icmp: correct return value of icmp_rcv()
From: Zhang Shengju @ 2016-12-07 6:52 UTC (permalink / raw)
To: netdev
Currently, icmp_rcv() always return zero on a packet delivery upcall.
To make its behavior more compliant with the way this API should be
used, this patch changes this to let it return NET_RX_SUCCESS when the
packet is proper handled, and NET_RX_DROP otherwise.
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
---
net/ipv4/icmp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 691146a..f79d7a8 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1047,12 +1047,12 @@ int icmp_rcv(struct sk_buff *skb)
if (success) {
consume_skb(skb);
- return 0;
+ return NET_RX_SUCCESS;
}
drop:
kfree_skb(skb);
- return 0;
+ return NET_RX_DROP;
csum_error:
__ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS);
error:
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH] net: return value of skb_linearize should be handled in Linux kernel
From: Eric Dumazet @ 2016-12-07 6:51 UTC (permalink / raw)
To: Zhouyi Zhou
Cc: faisal.latif, dledford, sean.hefty, hal.rosenstock,
jeffrey.t.kirsher, QLogic-Storage-Upstream, jejb, martin.petersen,
jth, jon.maloy, ying.xue, davem, linux-rdma, linux-kernel,
intel-wired-lan, netdev, linux-scsi, fcoe-devel, tipc-discussion
In-Reply-To: <1481008233-16777-1-git-send-email-zhouzhouyi@gmail.com>
On Tue, 2016-12-06 at 15:10 +0800, Zhouyi Zhou wrote:
> kmalloc_reserve may fail to allocate memory inside skb_linearize,
> which means skb_linearize's return value should not be ignored.
> Following patch correct the uses of skb_linearize.
>
> Compiled in x86_64
>
> Signed-off-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
> ---
> drivers/infiniband/hw/nes/nes_nic.c | 5 +++--
> drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c | 6 +++++-
> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +--
> drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 7 +++++--
> drivers/scsi/fcoe/fcoe.c | 5 ++++-
> net/tipc/link.c | 3 ++-
> net/tipc/name_distr.c | 5 ++++-
> 7 files changed, 24 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
> index 2b27d13..69372ea 100644
> --- a/drivers/infiniband/hw/nes/nes_nic.c
> +++ b/drivers/infiniband/hw/nes/nes_nic.c
> @@ -662,10 +662,11 @@ static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
> nesnic->sq_head &= nesnic->sq_size-1;
> }
> } else {
> - nesvnic->linearized_skbs++;
> hoffset = skb_transport_header(skb) - skb->data;
> nhoffset = skb_network_header(skb) - skb->data;
> - skb_linearize(skb);
> + if (skb_linearize(skb))
> + return NETDEV_TX_BUSY;
This would live lock.
Please drop the packet.
You probably should send one patch per driver, to ease code review and
acceptance.
^ permalink raw reply
* Re: [PATCH net-next] net: sock_rps_record_flow() is for connected sockets
From: Eric Dumazet @ 2016-12-07 6:47 UTC (permalink / raw)
To: Paolo Abeni; +Cc: David Miller, netdev, Willem de Bruijn, Tom Herbert
In-Reply-To: <1481081570.18162.626.camel@edumazet-glaptop3.roam.corp.google.com>
On Tue, 2016-12-06 at 19:32 -0800, Eric Dumazet wrote:
> A follow up patch will provide a static_key (Jump Label) since most
> hosts do not even use RFS.
Speaking of static_key, it appears we now have GRO on UDP, and this
consumes a considerable amount of cpu cycles.
Turning off GRO allows me to get +20 % more packets on my single UDP
socket. (1.2 Mpps instead of 1.0 Mpps)
Surely udp_gro_receive() should be bypassed if no UDP socket has
registered a udp_sk(sk)->gro_receive handler
And/or delay the inet_add_offload(&udpv{4|6}_offload, IPPROTO_UDP); to
the first UDP sockets setting udp_sk(sk)->gro_receive handler,
ie udp_encap_enable() and udpv6_encap_enable()
:(
^ permalink raw reply
* Re: [PATCH] net: return value of skb_linearize should be handled in Linux kernel
From: Zhouyi Zhou @ 2016-12-07 6:27 UTC (permalink / raw)
To: Cong Wang
Cc: faisal.latif, dledford, sean.hefty, Hal Rosenstock, Jeff Kirsher,
QLogic-Storage-Upstream, jejb, Martin K. Petersen,
Johannes Thumshirn, jon.maloy, ying.xue, David Miller, linux-rdma,
LKML, intel-wired-lan, Linux Kernel Network Developers,
linux-scsi, fcoe-devel, tipc-discussion
In-Reply-To: <CAM_iQpX0nA10tCzfZr_q5i6V2hWqfMUkvXdfo+Ro1TWHOEVi_A@mail.gmail.com>
On Wed, Dec 7, 2016 at 1:02 PM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> On Mon, Dec 5, 2016 at 11:10 PM, Zhouyi Zhou <zhouzhouyi@gmail.com> wrote:
>> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
>> index 2a653ec..ab787cb 100644
>> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
>> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
>> @@ -490,7 +490,11 @@ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter,
>> */
>> if ((fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA) &&
>> (fctl & FC_FC_END_SEQ)) {
>> - skb_linearize(skb);
>> + int err = 0;
>> +
>> + err = skb_linearize(skb);
>> + if (err)
>> + return err;
>
>
> You can reuse 'rc' instead of adding 'err'.
rc here is meaningful for the length of data being ddped. If using rc
here, a successful
skb_linearize will assign rc to 0.
>
>
>
>> crc = (struct fcoe_crc_eof *)skb_put(skb, sizeof(*crc));
>> crc->fcoe_eof = FC_EOF_T;
>> }
>> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> index fee1f29..4926d48 100644
>> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>> @@ -2173,8 +2173,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
>> total_rx_bytes += ddp_bytes;
>> total_rx_packets += DIV_ROUND_UP(ddp_bytes,
>> mss);
>> - }
>> - if (!ddp_bytes) {
>> + } else {
>> dev_kfree_skb_any(skb);
>> continue;
>> }
>
>
> This piece doesn't seem to be related.
if ddp_bytes is negative there will be some error, I think the skb
should not pass to upper layer.
^ permalink raw reply
* Re: [PATCH 10/10] virtio: enable endian checks for sparse builds
From: Johannes Berg @ 2016-12-07 6:25 UTC (permalink / raw)
To: Michael S. Tsirkin, linux-kernel
Cc: kvm, Neil Armstrong, David Airlie, linux-remoteproc, dri-devel,
virtualization, linux-s390, James E.J. Bottomley, Herbert Xu,
linux-scsi, v9fs-developer, Asias He, Arnd Bergmann, linux-kbuild,
Jens Axboe, Michal Marek, Stefan Hajnoczi, Matt Mackall,
Greg Kroah-Hartman, linux-crypto, netdev, David S. Miller
In-Reply-To: <1481038106-24899-11-git-send-email-mst@redhat.com>
On Tue, 2016-12-06 at 17:41 +0200, Michael S. Tsirkin wrote:
> It seems that there should be a better way to do it,
> but this works too.
In some cases there might be:
> --- a/drivers/s390/virtio/Makefile
> +++ b/drivers/s390/virtio/Makefile
> @@ -6,6 +6,8 @@
> # it under the terms of the GNU General Public License (version 2
> only)
> # as published by the Free Software Foundation.
>
> +CFLAGS_virtio_ccw.o += -D__CHECK_ENDIAN__
> +CFLAGS_kvm_virtio.o += -D__CHECK_ENDIAN__
> s390-virtio-objs := virtio_ccw.o
> ifdef CONFIG_S390_GUEST_OLD_TRANSPORT
> s390-virtio-objs += kvm_virtio.o
Here you could use
ccflags-y += -D__CHECK_ENDIAN__
for example, or even
subdir-ccflags-y += -D__CHECK_ENDIAN__
(in case any subdirs ever get added here)
> --- a/drivers/vhost/Makefile
> +++ b/drivers/vhost/Makefile
> @@ -1,3 +1,4 @@
> +ccflags-y := -D__CHECK_ENDIAN__
Looks like you did that here and in some other places though - so
perhaps the s390 one was intentionally different?
> --- a/net/packet/Makefile
> +++ b/net/packet/Makefile
> @@ -2,6 +2,7 @@
> # Makefile for the packet AF.
> #
>
> +ccflags-y := -D__CHECK_ENDIAN__
Technically this is slightly more than advertised, but I guess that
still makes sense if it's clean now.
johannes
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* Re: Oops with CONFIG_VMAP_STCK and bond device + virtio-net
From: Cong Wang @ 2016-12-07 5:58 UTC (permalink / raw)
To: Laura Abbott
Cc: Michael S. Tsirkin, Linux Kernel Network Developers,
Linux Kernel Mailing List, virtualization,
Zbigniew Jędrzejewski-Szmek
In-Reply-To: <bd4c37d9-9724-4c2a-8f0f-45b86fb5cb7f@redhat.com>
On Mon, Dec 5, 2016 at 3:53 PM, Laura Abbott <labbott@redhat.com> wrote:
> This looks like an issue with CONFIG_VMAP_STACK since bond_enslave uses
> struct sockaddr from the stack and virtnet_set_mac_address calls
> sg_init_one which triggers BUG_ON(!virt_addr_valid(buf));
>
> I know there have been a lot of CONFIG_VMAP_STACK fixes around but I
> didn't find this one reported yet.
Fixed by:
commit e37e2ff350a321ad9c36b588e76f34fbba305be6
Author: Andy Lutomirski <luto@kernel.org>
Date: Mon Dec 5 18:10:58 2016 -0800
virtio-net: Fix DMA-from-the-stack in virtnet_set_mac_address()
^ permalink raw reply
* [PATCH v3 net-next 3/4] mlx4: xdp: Reserve headroom for receiving packet when XDP prog is active
From: Martin KaFai Lau @ 2016-12-07 5:31 UTC (permalink / raw)
To: netdev
Cc: Alexei Starovoitov, Brenden Blanco, Daniel Borkmann, David Miller,
Jakub Kicinski, Jesper Dangaard Brouer, John Fastabend,
Saeed Mahameed, Tariq Toukan, Kernel Team
In-Reply-To: <1481088714-54512-1-git-send-email-kafai@fb.com>
Reserve XDP_PACKET_HEADROOM for packet and enable bpf_xdp_adjust_head()
support. This patch only affects the code path when XDP is active.
After testing, the tx_dropped counter is incremented if the xdp_prog sends
more than wire MTU.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 5 +++--
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 24 ++++++++++++++++++------
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 9 +++++----
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++-
4 files changed, 28 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5482591688f8..36b9bb042778 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -51,7 +51,8 @@
#include "mlx4_en.h"
#include "en_port.h"
-#define MLX4_EN_MAX_XDP_MTU ((int)(PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN)))
+#define MLX4_EN_MAX_XDP_MTU ((int)(PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) - \
+ XDP_PACKET_HEADROOM))
int mlx4_en_setup_tc(struct net_device *dev, u8 up)
{
@@ -2807,7 +2808,7 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
xdp->prog_attached = mlx4_xdp_attached(dev);
return 0;
case XDP_QUERY_FEATURES:
- xdp->features = 0;
+ xdp->features = XDP_F_ADJUST_HEAD;
return 0;
default:
return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 23e9d04d1ef4..3c37e216bbf3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -96,7 +96,6 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
const struct mlx4_en_frag_info *frag_info;
struct page *page;
- dma_addr_t dma;
int i;
for (i = 0; i < priv->num_frags; i++) {
@@ -115,9 +114,10 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
for (i = 0; i < priv->num_frags; i++) {
frags[i] = ring_alloc[i];
- dma = ring_alloc[i].dma + ring_alloc[i].page_offset;
+ frags[i].page_offset += priv->frag_info[i].rx_headroom;
+ rx_desc->data[i].addr = cpu_to_be64(frags[i].dma +
+ frags[i].page_offset);
ring_alloc[i] = page_alloc[i];
- rx_desc->data[i].addr = cpu_to_be64(dma);
}
return 0;
@@ -250,7 +250,8 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
if (ring->page_cache.index > 0) {
frags[0] = ring->page_cache.buf[--ring->page_cache.index];
- rx_desc->data[0].addr = cpu_to_be64(frags[0].dma);
+ rx_desc->data[0].addr = cpu_to_be64(frags[0].dma +
+ frags[0].page_offset);
return 0;
}
@@ -889,6 +890,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
if (xdp_prog) {
struct xdp_buff xdp;
dma_addr_t dma;
+ void *orig_data;
u32 act;
dma = be64_to_cpu(rx_desc->data[0].addr);
@@ -896,11 +898,19 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
priv->frag_info[0].frag_size,
DMA_FROM_DEVICE);
- xdp.data = page_address(frags[0].page) +
- frags[0].page_offset;
+ xdp.data_hard_start = page_address(frags[0].page);
+ xdp.data = xdp.data_hard_start + frags[0].page_offset;
xdp.data_end = xdp.data + length;
+ orig_data = xdp.data;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+ if (xdp.data != orig_data) {
+ length = xdp.data_end - xdp.data;
+ frags[0].page_offset = xdp.data -
+ xdp.data_hard_start;
+ }
+
switch (act) {
case XDP_PASS:
break;
@@ -1180,6 +1190,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
*/
priv->frag_info[0].frag_stride = PAGE_SIZE;
priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL;
+ priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM;
i = 1;
} else {
int buf_size = 0;
@@ -1194,6 +1205,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
ALIGN(priv->frag_info[i].frag_size,
SMP_CACHE_BYTES);
priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE;
+ priv->frag_info[i].rx_headroom = 0;
buf_size += priv->frag_info[i].frag_size;
i++;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4b597dca5c52..5886ad78058f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -354,7 +354,7 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_alloc frame = {
.page = tx_info->page,
.dma = tx_info->map0_dma,
- .page_offset = 0,
+ .page_offset = XDP_PACKET_HEADROOM,
.page_size = PAGE_SIZE,
};
@@ -1132,7 +1132,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
tx_info->page = frame->page;
frame->page = NULL;
tx_info->map0_dma = dma;
- tx_info->map0_byte_count = length;
+ tx_info->map0_byte_count = PAGE_SIZE;
tx_info->nr_txbb = nr_txbb;
tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
tx_info->data_offset = (void *)data - (void *)tx_desc;
@@ -1141,9 +1141,10 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
tx_info->linear = 1;
tx_info->inl = 0;
- dma_sync_single_for_device(priv->ddev, dma, length, PCI_DMA_TODEVICE);
+ dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset,
+ length, PCI_DMA_TODEVICE);
- data->addr = cpu_to_be64(dma);
+ data->addr = cpu_to_be64(dma + frame->page_offset);
data->lkey = ring->mr_key;
dma_wmb();
data->byte_count = cpu_to_be32(length);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 20a936428f4a..ba1c6cd0cc79 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -475,7 +475,8 @@ struct mlx4_en_frag_info {
u16 frag_prefix_size;
u32 frag_stride;
enum dma_data_direction dma_dir;
- int order;
+ u16 order;
+ u16 rx_headroom;
};
#ifdef CONFIG_MLX4_EN_DCB
--
2.5.1
^ permalink raw reply related
* [PATCH v3 net-next 1/4] bpf: xdp: Allow head adjustment in XDP prog
From: Martin KaFai Lau @ 2016-12-07 5:31 UTC (permalink / raw)
To: netdev
Cc: Alexei Starovoitov, Brenden Blanco, Daniel Borkmann, David Miller,
Jakub Kicinski, Jesper Dangaard Brouer, John Fastabend,
Saeed Mahameed, Tariq Toukan, Kernel Team
In-Reply-To: <1481088714-54512-1-git-send-email-kafai@fb.com>
This patch allows XDP prog to extend/remove the packet
data at the head (like adding or removing header). It is
done by adding a new XDP helper bpf_xdp_adjust_head().
It also renames bpf_helper_changes_skb_data() to
bpf_helper_changes_pkt_data() to better reflect
that XDP prog does not work on skb.
To avoid breaking unsupported drivers, this patch
also does the needed checking before setting
the xdp_prog fd to the device. It is done by
1) Adding a XDP_QUERY_FEATURES command
2) Adding one "xdp_adjust_head" bit to bpf_prog
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
arch/powerpc/net/bpf_jit_comp64.c | 4 ++--
arch/s390/net/bpf_jit_comp.c | 2 +-
arch/x86/net/bpf_jit_comp.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 3 +++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +++
.../net/ethernet/netronome/nfp/nfp_net_common.c | 3 +++
drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +++
include/linux/filter.h | 6 +++--
include/linux/netdevice.h | 12 ++++++++++
include/uapi/linux/bpf.h | 11 ++++++++-
kernel/bpf/core.c | 2 +-
kernel/bpf/syscall.c | 2 ++
kernel/bpf/verifier.c | 2 +-
net/core/dev.c | 9 +++++++
net/core/filter.c | 28 ++++++++++++++++++++--
15 files changed, 81 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0fe98a567125..73a5cf18fd84 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -766,7 +766,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
func = (u8 *) __bpf_call_base + imm;
/* Save skb pointer if we need to re-cache skb data */
- if (bpf_helper_changes_skb_data(func))
+ if (bpf_helper_changes_pkt_data(func))
PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -775,7 +775,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
PPC_MR(b2p[BPF_REG_0], 3);
/* refresh skb cache */
- if (bpf_helper_changes_skb_data(func)) {
+ if (bpf_helper_changes_pkt_data(func)) {
/* reload skb pointer to r3 */
PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
bpf_jit_emit_skb_loads(image, ctx);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index bee281f3163d..167b31b186c1 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -981,7 +981,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
EMIT2(0x0d00, REG_14, REG_W1);
/* lgr %b0,%r2: load return value into %b0 */
EMIT4(0xb9040000, BPF_REG_0, REG_2);
- if (bpf_helper_changes_skb_data((void *)func)) {
+ if (bpf_helper_changes_pkt_data((void *)func)) {
jit->seen |= SEEN_SKB_CHANGE;
/* lg %b1,ST_OFF_SKBP(%r15) */
EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index fe04a04dab8e..e76d1af60f7a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -853,7 +853,7 @@ xadd: if (is_imm8(insn->off))
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
if (seen_ld_abs) {
- reload_skb_data = bpf_helper_changes_skb_data(func);
+ reload_skb_data = bpf_helper_changes_pkt_data(func);
if (reload_skb_data) {
EMIT1(0x57); /* push %rdi */
jmp_offset += 22; /* pop, mov, sub, mov */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 49a81f1fc1d6..6261157f444e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2794,6 +2794,9 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
case XDP_QUERY_PROG:
xdp->prog_attached = mlx4_xdp_attached(dev);
return 0;
+ case XDP_QUERY_FEATURES:
+ xdp->features = 0;
+ return 0;
default:
return -EINVAL;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9def5cc378a3..f7a6b6b56d30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3262,6 +3262,9 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_xdp *xdp)
case XDP_QUERY_PROG:
xdp->prog_attached = mlx5e_xdp_attached(dev);
return 0;
+ case XDP_QUERY_FEATURES:
+ xdp->features = 0;
+ return 0;
default:
return -EINVAL;
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 00d9a03be31d..89c95bb91503 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2981,6 +2981,9 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
case XDP_QUERY_PROG:
xdp->prog_attached = !!nn->xdp_prog;
return 0;
+ case XDP_QUERY_FEATURES:
+ xdp->features = 0;
+ return 0;
default:
return -EINVAL;
}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index cf1dd1436d93..d52dd83ae8a1 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2525,6 +2525,9 @@ static int qede_xdp(struct net_device *dev, struct netdev_xdp *xdp)
case XDP_QUERY_PROG:
xdp->prog_attached = !!edev->xdp_prog;
return 0;
+ case XDP_QUERY_FEATURES:
+ xdp->features = 0;
+ return 0;
default:
return -EINVAL;
}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f078d2b1cff6..6a1658308612 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -406,7 +406,8 @@ struct bpf_prog {
u16 jited:1, /* Is our filter JIT'ed? */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
- dst_needed:1; /* Do we need dst entry? */
+ dst_needed:1, /* Do we need dst entry? */
+ xdp_adjust_head:1; /* Adjusting pkt head? */
kmemcheck_bitfield_end(meta);
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
@@ -440,6 +441,7 @@ struct bpf_skb_data_end {
struct xdp_buff {
void *data;
void *data_end;
+ void *data_hard_start;
};
/* compute the linear packet data range [data, data_end) which
@@ -595,7 +597,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
-bool bpf_helper_changes_skb_data(void *func);
+bool bpf_helper_changes_pkt_data(void *func);
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1ff5ea6e1221..786ad7c67215 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -30,6 +30,7 @@
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/prefetch.h>
+#include <linux/bitops.h>
#include <asm/cache.h>
#include <asm/byteorder.h>
@@ -805,6 +806,13 @@ struct tc_to_netdev {
bool egress_dev;
};
+/* Driver must allow a XDP prog to extend header by
+ * up to XDP_PACKET_HEADROOM. It must also fill out
+ * the data_hard_start value in struct xdp_buff
+ * before calling out the xdp_prog.
+ */
+#define XDP_F_ADJUST_HEAD BIT(0)
+
/* These structures hold the attributes of xdp state that are being passed
* to the netdevice through the xdp op.
*/
@@ -821,6 +829,8 @@ enum xdp_netdev_command {
* return true if a program is currently attached and running.
*/
XDP_QUERY_PROG,
+ /* Check what XDP features are supported by a device */
+ XDP_QUERY_FEATURES,
};
struct netdev_xdp {
@@ -830,6 +840,8 @@ struct netdev_xdp {
struct bpf_prog *prog;
/* XDP_QUERY_PROG */
bool prog_attached;
+ /* XDP_QUERY_FEATURES */
+ u32 features;
};
};
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6123d9b8e828..0eb0e87dbe9f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -424,6 +424,12 @@ union bpf_attr {
* @len: length of header to be pushed in front
* @flags: Flags (unused for now)
* Return: 0 on success or negative error
+ *
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ * Adjust the xdp_md.data by delta
+ * @xdp_md: pointer to xdp_md
+ * @delta: An positive/negative integer to be added to xdp_md.data
+ * Return: 0 on success or negative on error
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -469,7 +475,8 @@ union bpf_attr {
FN(csum_update), \
FN(set_hash_invalid), \
FN(get_numa_node_id), \
- FN(skb_change_head),
+ FN(skb_change_head), \
+ FN(xdp_adjust_head),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -576,6 +583,8 @@ struct bpf_sock {
__u32 protocol;
};
+#define XDP_PACKET_HEADROOM 256
+
/* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other
* return codes are reserved for future use. Unknown return codes will result
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index bdcc9f4ba767..83e0d153b0b4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1143,7 +1143,7 @@ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
return prog;
}
-bool __weak bpf_helper_changes_skb_data(void *func)
+bool __weak bpf_helper_changes_pkt_data(void *func)
{
return false;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c0d2b423ce93..add93ecd7e69 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -579,6 +579,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
prog->dst_needed = 1;
if (insn->imm == BPF_FUNC_get_prandom_u32)
bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_xdp_adjust_head)
+ prog->xdp_adjust_head = 1;
if (insn->imm == BPF_FUNC_tail_call) {
/* mark bpf_tail_call as different opcode
* to avoid conditional branch in
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cb37339ca0da..f5fa326518c9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1216,7 +1216,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
return -EINVAL;
}
- changes_data = bpf_helper_changes_skb_data(fn->func);
+ changes_data = bpf_helper_changes_pkt_data(fn->func);
memset(&meta, 0, sizeof(meta));
meta.pkt_access = fn->pkt_access;
diff --git a/net/core/dev.c b/net/core/dev.c
index bffb5253e778..90696f7e6b59 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6722,6 +6722,15 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags)
prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
if (IS_ERR(prog))
return PTR_ERR(prog);
+
+ xdp.command = XDP_QUERY_FEATURES;
+ err = ops->ndo_xdp(dev, &xdp);
+ if (err)
+ return err;
+
+ if (prog->xdp_adjust_head &&
+ !(xdp.features & XDP_F_ADJUST_HEAD))
+ return -ENOTSUPP;
}
memset(&xdp, 0, sizeof(xdp));
diff --git a/net/core/filter.c b/net/core/filter.c
index b751202e12f8..b1461708a977 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2234,7 +2234,28 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
.arg3_type = ARG_ANYTHING,
};
-bool bpf_helper_changes_skb_data(void *func)
+BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
+{
+ void *data = xdp->data + offset;
+
+ if (unlikely(data < xdp->data_hard_start ||
+ data > xdp->data_end - ETH_HLEN))
+ return -EINVAL;
+
+ xdp->data = data;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
+ .func = bpf_xdp_adjust_head,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
+bool bpf_helper_changes_pkt_data(void *func)
{
if (func == bpf_skb_vlan_push ||
func == bpf_skb_vlan_pop ||
@@ -2244,7 +2265,8 @@ bool bpf_helper_changes_skb_data(void *func)
func == bpf_skb_change_tail ||
func == bpf_skb_pull_data ||
func == bpf_l3_csum_replace ||
- func == bpf_l4_csum_replace)
+ func == bpf_l4_csum_replace ||
+ func == bpf_xdp_adjust_head)
return true;
return false;
@@ -2670,6 +2692,8 @@ xdp_func_proto(enum bpf_func_id func_id)
return &bpf_xdp_event_output_proto;
case BPF_FUNC_get_smp_processor_id:
return &bpf_get_smp_processor_id_proto;
+ case BPF_FUNC_xdp_adjust_head:
+ return &bpf_xdp_adjust_head_proto;
default:
return sk_filter_func_proto(func_id);
}
--
2.5.1
^ permalink raw reply related
* [PATCH v3 net-next 4/4] bpf: xdp: Add XDP example for head adjustment
From: Martin KaFai Lau @ 2016-12-07 5:31 UTC (permalink / raw)
To: netdev
Cc: Alexei Starovoitov, Brenden Blanco, Daniel Borkmann, David Miller,
Jakub Kicinski, Jesper Dangaard Brouer, John Fastabend,
Saeed Mahameed, Tariq Toukan, Kernel Team
In-Reply-To: <1481088714-54512-1-git-send-email-kafai@fb.com>
The XDP prog checks if the incoming packet matches any VIP:PORT
combination in the BPF hashmap. If it is, it will encapsulate
the packet with a IPv4/v6 header as instructed by the value of
the BPF hashmap and then XDP_TX it out.
The VIP:PORT -> IP-Encap-Info can be specified by the cmd args
of the user prog.
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
samples/bpf/Makefile | 4 +
samples/bpf/bpf_helpers.h | 2 +
samples/bpf/bpf_load.c | 94 ++++++++++++++
samples/bpf/bpf_load.h | 1 +
samples/bpf/xdp1_user.c | 93 --------------
samples/bpf/xdp_tx_iptnl_common.h | 37 ++++++
samples/bpf/xdp_tx_iptnl_kern.c | 232 ++++++++++++++++++++++++++++++++++
samples/bpf/xdp_tx_iptnl_user.c | 253 ++++++++++++++++++++++++++++++++++++++
8 files changed, 623 insertions(+), 93 deletions(-)
create mode 100644 samples/bpf/xdp_tx_iptnl_common.h
create mode 100644 samples/bpf/xdp_tx_iptnl_kern.c
create mode 100644 samples/bpf/xdp_tx_iptnl_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 00cd3081c038..f78e0ef6ff10 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -33,6 +33,7 @@ hostprogs-y += trace_event
hostprogs-y += sampleip
hostprogs-y += tc_l2_redirect
hostprogs-y += lwt_len_hist
+hostprogs-y += xdp_tx_iptnl
test_lru_dist-objs := test_lru_dist.o libbpf.o
sock_example-objs := sock_example.o libbpf.o
@@ -67,6 +68,7 @@ trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
+xdp_tx_iptnl-objs := bpf_load.o libbpf.o xdp_tx_iptnl_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -99,6 +101,7 @@ always += test_current_task_under_cgroup_kern.o
always += trace_event_kern.o
always += sampleip_kern.o
always += lwt_len_hist_kern.o
+always += xdp_tx_iptnl_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
@@ -129,6 +132,7 @@ HOSTLOADLIBES_trace_event += -lelf
HOSTLOADLIBES_sampleip += -lelf
HOSTLOADLIBES_tc_l2_redirect += -l elf
HOSTLOADLIBES_lwt_len_hist += -l elf
+HOSTLOADLIBES_xdp_tx_iptnl += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 8370a6e3839d..faaffe2e139a 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -57,6 +57,8 @@ static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
(void *) BPF_FUNC_skb_set_tunnel_opt;
static unsigned long long (*bpf_get_prandom_u32)(void) =
(void *) BPF_FUNC_get_prandom_u32;
+static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
+ (void *) BPF_FUNC_xdp_adjust_head;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 49b45ccbe153..e30b6de94f2e 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -12,6 +12,10 @@
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/perf_event.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/types.h>
+#include <sys/socket.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
@@ -450,3 +454,93 @@ struct ksym *ksym_search(long key)
/* out of range. return _stext */
return &syms[0];
}
+
+int set_link_xdp_fd(int ifindex, int fd)
+{
+ struct sockaddr_nl sa;
+ int sock, seq = 0, len, ret = -1;
+ char buf[4096];
+ struct nlattr *nla, *nla_xdp;
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg ifinfo;
+ char attrbuf[64];
+ } req;
+ struct nlmsghdr *nh;
+ struct nlmsgerr *err;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.nl_family = AF_NETLINK;
+
+ sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (sock < 0) {
+ printf("open netlink socket: %s\n", strerror(errno));
+ return -1;
+ }
+
+ if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+ printf("bind to netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_type = RTM_SETLINK;
+ req.nh.nlmsg_pid = 0;
+ req.nh.nlmsg_seq = ++seq;
+ req.ifinfo.ifi_family = AF_UNSPEC;
+ req.ifinfo.ifi_index = ifindex;
+ nla = (struct nlattr *)(((char *)&req)
+ + NLMSG_ALIGN(req.nh.nlmsg_len));
+ nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+
+ nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
+ nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
+ nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+ memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+ nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
+
+ req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+ if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ printf("send to netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ len = recv(sock, buf, sizeof(buf), 0);
+ if (len < 0) {
+ printf("recv from netlink: %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+ nh = NLMSG_NEXT(nh, len)) {
+ if (nh->nlmsg_pid != getpid()) {
+ printf("Wrong pid %d, expected %d\n",
+ nh->nlmsg_pid, getpid());
+ goto cleanup;
+ }
+ if (nh->nlmsg_seq != seq) {
+ printf("Wrong seq %d, expected %d\n",
+ nh->nlmsg_seq, seq);
+ goto cleanup;
+ }
+ switch (nh->nlmsg_type) {
+ case NLMSG_ERROR:
+ err = (struct nlmsgerr *)NLMSG_DATA(nh);
+ if (!err->error)
+ continue;
+ printf("nlmsg error %s\n", strerror(-err->error));
+ goto cleanup;
+ case NLMSG_DONE:
+ break;
+ }
+ }
+
+ ret = 0;
+
+cleanup:
+ close(sock);
+ return ret;
+}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 4adeeef53ad6..fb46a421ab41 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -31,4 +31,5 @@ struct ksym {
int load_kallsyms(void);
struct ksym *ksym_search(long key);
+int set_link_xdp_fd(int ifindex, int fd);
#endif
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 2b2150d6d6f7..5f040a0d7712 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -5,111 +5,18 @@
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
-#include <linux/netlink.h>
-#include <linux/rtnetlink.h>
#include <assert.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <sys/socket.h>
#include <unistd.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include "libbpf.h"
-static int set_link_xdp_fd(int ifindex, int fd)
-{
- struct sockaddr_nl sa;
- int sock, seq = 0, len, ret = -1;
- char buf[4096];
- struct nlattr *nla, *nla_xdp;
- struct {
- struct nlmsghdr nh;
- struct ifinfomsg ifinfo;
- char attrbuf[64];
- } req;
- struct nlmsghdr *nh;
- struct nlmsgerr *err;
-
- memset(&sa, 0, sizeof(sa));
- sa.nl_family = AF_NETLINK;
-
- sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
- if (sock < 0) {
- printf("open netlink socket: %s\n", strerror(errno));
- return -1;
- }
-
- if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
- printf("bind to netlink: %s\n", strerror(errno));
- goto cleanup;
- }
-
- memset(&req, 0, sizeof(req));
- req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
- req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
- req.nh.nlmsg_type = RTM_SETLINK;
- req.nh.nlmsg_pid = 0;
- req.nh.nlmsg_seq = ++seq;
- req.ifinfo.ifi_family = AF_UNSPEC;
- req.ifinfo.ifi_index = ifindex;
- nla = (struct nlattr *)(((char *)&req)
- + NLMSG_ALIGN(req.nh.nlmsg_len));
- nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
-
- nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
- nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
- nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
- memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
- nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
-
- req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
- if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
- printf("send to netlink: %s\n", strerror(errno));
- goto cleanup;
- }
-
- len = recv(sock, buf, sizeof(buf), 0);
- if (len < 0) {
- printf("recv from netlink: %s\n", strerror(errno));
- goto cleanup;
- }
-
- for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
- nh = NLMSG_NEXT(nh, len)) {
- if (nh->nlmsg_pid != getpid()) {
- printf("Wrong pid %d, expected %d\n",
- nh->nlmsg_pid, getpid());
- goto cleanup;
- }
- if (nh->nlmsg_seq != seq) {
- printf("Wrong seq %d, expected %d\n",
- nh->nlmsg_seq, seq);
- goto cleanup;
- }
- switch (nh->nlmsg_type) {
- case NLMSG_ERROR:
- err = (struct nlmsgerr *)NLMSG_DATA(nh);
- if (!err->error)
- continue;
- printf("nlmsg error %s\n", strerror(-err->error));
- goto cleanup;
- case NLMSG_DONE:
- break;
- }
- }
-
- ret = 0;
-
-cleanup:
- close(sock);
- return ret;
-}
-
static int ifindex;
static void int_exit(int sig)
diff --git a/samples/bpf/xdp_tx_iptnl_common.h b/samples/bpf/xdp_tx_iptnl_common.h
new file mode 100644
index 000000000000..dd12cc35110f
--- /dev/null
+++ b/samples/bpf/xdp_tx_iptnl_common.h
@@ -0,0 +1,37 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
+#define _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_IPTNL_ENTRIES 256U
+
+struct vip {
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } daddr;
+ __u16 dport;
+ __u16 family;
+ __u8 protocol;
+};
+
+struct iptnl_info {
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } saddr;
+ union {
+ __u32 v6[4];
+ __u32 v4;
+ } daddr;
+ __u16 family;
+ __u8 dmac[6];
+};
+
+#endif
diff --git a/samples/bpf/xdp_tx_iptnl_kern.c b/samples/bpf/xdp_tx_iptnl_kern.c
new file mode 100644
index 000000000000..d88c064175aa
--- /dev/null
+++ b/samples/bpf/xdp_tx_iptnl_kern.c
@@ -0,0 +1,232 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "bpf_helpers.h"
+#include "xdp_tx_iptnl_common.h"
+
+struct bpf_map_def SEC("maps") rxcnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(struct vip),
+ .value_size = sizeof(struct iptnl_info),
+ .max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(u32 protocol)
+{
+ u64 *rxcnt_count;
+
+ rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+ if (rxcnt_count)
+ *rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+ u8 protocol)
+{
+ struct tcphdr *th;
+ struct udphdr *uh;
+
+ switch (protocol) {
+ case IPPROTO_TCP:
+ th = (struct tcphdr *)trans_data;
+ if (th + 1 > data_end)
+ return -1;
+ return th->dest;
+ case IPPROTO_UDP:
+ uh = (struct udphdr *)trans_data;
+ if (uh + 1 > data_end)
+ return -1;
+ return uh->dest;
+ default:
+ return 0;
+ }
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+ const struct ethhdr *old_eth,
+ const struct iptnl_info *tnl,
+ __be16 h_proto)
+{
+ memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+ memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+ new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct iptnl_info *tnl;
+ struct ethhdr *new_eth;
+ struct ethhdr *old_eth;
+ struct iphdr *iph = data + sizeof(struct ethhdr);
+ u16 *next_iph_u16;
+ u16 payload_len;
+ struct vip vip = {};
+ int dport;
+ u32 csum = 0;
+ int i;
+
+ if (iph + 1 > data_end)
+ return XDP_DROP;
+
+ dport = get_dport(iph + 1, data_end, iph->protocol);
+ if (dport == -1)
+ return XDP_DROP;
+
+ vip.protocol = iph->protocol;
+ vip.family = AF_INET;
+ vip.daddr.v4 = iph->daddr;
+ vip.dport = dport;
+ payload_len = ntohs(iph->tot_len);
+
+ tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+ /* It only does v4-in-v4 */
+ if (!tnl || tnl->family != AF_INET)
+ return XDP_PASS;
+
+ /* The vip key is found. Add an IP header and send it out */
+
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+ return XDP_DROP;
+
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+
+ new_eth = data;
+ iph = data + sizeof(*new_eth);
+ old_eth = data + sizeof(*iph);
+
+ if (new_eth + 1 > data_end ||
+ old_eth + 1 > data_end ||
+ iph + 1 > data_end)
+ return XDP_DROP;
+
+ set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IP));
+
+ iph->version = 4;
+ iph->ihl = sizeof(*iph) >> 2;
+ iph->frag_off = 0;
+ iph->protocol = IPPROTO_IPIP;
+ iph->check = 0;
+ iph->tos = 0;
+ iph->tot_len = htons(payload_len + sizeof(*iph));
+ iph->daddr = tnl->daddr.v4;
+ iph->saddr = tnl->saddr.v4;
+ iph->ttl = 8;
+
+ next_iph_u16 = (u16 *)iph;
+#pragma clang loop unroll(full)
+ for (i = 0; i < sizeof(*iph) >> 1; i++)
+ csum += *next_iph_u16++;
+
+ iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+ count_tx(vip.protocol);
+
+ return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct iptnl_info *tnl;
+ struct ethhdr *new_eth;
+ struct ethhdr *old_eth;
+ struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+ __u16 payload_len;
+ struct vip vip = {};
+ int dport;
+
+ if (ip6h + 1 > data_end)
+ return XDP_DROP;
+
+ dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+ if (dport == -1)
+ return XDP_DROP;
+
+ vip.protocol = ip6h->nexthdr;
+ vip.family = AF_INET6;
+ memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+ vip.dport = dport;
+ payload_len = ip6h->payload_len;
+
+ tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+ /* It only does v6-in-v6 */
+ if (!tnl || tnl->family != AF_INET6)
+ return XDP_PASS;
+
+ /* The vip key is found. Add an IP header and send it out */
+
+ if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+ return XDP_DROP;
+
+ data = (void *)(long)xdp->data;
+ data_end = (void *)(long)xdp->data_end;
+
+ new_eth = data;
+ ip6h = data + sizeof(*new_eth);
+ old_eth = data + sizeof(*ip6h);
+
+ if (new_eth + 1 > data_end ||
+ old_eth + 1 > data_end ||
+ ip6h + 1 > data_end)
+ return XDP_DROP;
+
+ set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IPV6));
+
+ ip6h->version = 6;
+ ip6h->priority = 0;
+ memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+ ip6h->payload_len = htons(ntohs(payload_len) + sizeof(*ip6h));
+ ip6h->nexthdr = IPPROTO_IPV6;
+ ip6h->hop_limit = 8;
+ memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+ memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+ count_tx(vip.protocol);
+
+ return XDP_TX;
+}
+
+SEC("xdp_tx_iptnl")
+int _xdp_tx_iptnl(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eth = data;
+ __u16 h_proto;
+
+ if (eth + 1 > data_end)
+ return XDP_DROP;
+
+ h_proto = eth->h_proto;
+
+ if (h_proto == htons(ETH_P_IP))
+ return handle_ipv4(xdp);
+ else if (h_proto == htons(ETH_P_IPV6))
+
+ return handle_ipv6(xdp);
+ else
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_tx_iptnl_user.c b/samples/bpf/xdp_tx_iptnl_user.c
new file mode 100644
index 000000000000..9aeef7579af4
--- /dev/null
+++ b/samples/bpf/xdp_tx_iptnl_user.c
@@ -0,0 +1,253 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <arpa/inet.h>
+#include <netinet/ether.h>
+#include <unistd.h>
+#include <time.h>
+#include "bpf_load.h"
+#include "libbpf.h"
+#include "bpf_util.h"
+#include "xdp_tx_iptnl_common.h"
+
+#define STATS_INTERVAL_S 2U
+
+static int ifindex = -1;
+
+static void int_exit(int sig)
+{
+ if (ifindex > -1)
+ set_link_xdp_fd(ifindex, -1);
+ exit(0);
+}
+
+/* simple per-protocol drop counter
+ */
+static void poll_stats(unsigned int kill_after_s)
+{
+ const unsigned int nr_protos = 256;
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ time_t started_at = time(NULL);
+ __u64 values[nr_cpus], prev[nr_protos][nr_cpus];
+ __u32 proto;
+ int i;
+
+ memset(prev, 0, sizeof(prev));
+
+ while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
+ sleep(STATS_INTERVAL_S);
+
+ for (proto = 0; proto < nr_protos; proto++) {
+ __u64 sum = 0;
+
+ assert(bpf_lookup_elem(map_fd[0], &proto, values) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ sum += (values[i] - prev[proto][i]);
+
+ if (sum)
+ printf("proto %u: sum:%10llu pkts, rate:%10llu pkts/s\n",
+ proto, sum, sum / STATS_INTERVAL_S);
+ memcpy(prev[proto], values, sizeof(values));
+ }
+ }
+}
+
+static void usage(const char *cmd)
+{
+ printf("Usage: %s [...]\n", cmd);
+ printf(" -i <ifindex> Interface Index\n");
+ printf(" -a <vip-service-address> IPv4 or IPv6\n");
+ printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
+ printf(" -s <source-ip> Used in the IPTunnel Header\n");
+ printf(" -d <dest-ip> Used in the IPTunnel header>\n");
+ printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt>\n");
+ printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
+ printf(" -P <IP-Protocol> Default is TCP\n");
+ printf(" -h Display this help\n");
+}
+
+static int parse_ipstr(const char *ipstr, unsigned int *addr)
+{
+ if (inet_pton(AF_INET6, ipstr, addr) == 1) {
+ return AF_INET6;
+ } else if (inet_pton(AF_INET, ipstr, addr) == 1) {
+ addr[1] = addr[2] = addr[3] = 0;
+ return AF_INET;
+ }
+
+ fprintf(stderr, "%s is an invalid IP\n", ipstr);
+ return AF_UNSPEC;
+}
+
+static int parse_ports(const char *port_str, int *min_port, int *max_port)
+{
+ char *end;
+ long tmp_min_port;
+ long tmp_max_port;
+
+ tmp_min_port = strtol(optarg, &end, 10);
+ if (tmp_min_port < 1 || tmp_min_port > 65535) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+
+ if (*end == '-') {
+ end++;
+ tmp_max_port = strtol(end, NULL, 10);
+ if (tmp_max_port < 1 || tmp_max_port > 65535) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+ } else {
+ tmp_max_port = tmp_min_port;
+ }
+
+ if (tmp_min_port > tmp_max_port) {
+ fprintf(stderr, "Invalid port(s):%s\n", optarg);
+ return 1;
+ }
+
+ if (tmp_max_port - tmp_min_port + 1 > MAX_IPTNL_ENTRIES) {
+ fprintf(stderr, "Port range (%s) is larger than %u\n",
+ port_str, MAX_IPTNL_ENTRIES);
+ return 1;
+ }
+ *min_port = tmp_min_port;
+ *max_port = tmp_max_port;
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ unsigned char opt_flags[256] = {};
+ unsigned int kill_after_s = 0;
+ const char *optstr = "i:a:p:s:d:m:T:P:";
+ int min_port = 0, max_port = 0;
+ struct iptnl_info tnl = {};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ struct vip vip = {};
+ char filename[256];
+ int opt;
+ int i;
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)");
+ return 1;
+ }
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ if (!prog_fd[0]) {
+ printf("load_bpf_file: %s\n", strerror(errno));
+ return 1;
+ }
+
+ tnl.family = AF_UNSPEC;
+ vip.protocol = IPPROTO_TCP;
+
+ for (i = 0; i < strlen(optstr); i++)
+ if ('a' <= optstr[i] && optstr[i] <= 'z')
+ opt_flags[(unsigned char)optstr[i]] = 1;
+
+ while ((opt = getopt(argc, argv, optstr)) != -1) {
+ unsigned short family;
+ unsigned int *v6;
+
+ switch (opt) {
+ case 'i':
+ ifindex = atoi(optarg);
+ break;
+ case 'a':
+ vip.family = parse_ipstr(optarg, vip.daddr.v6);
+ if (vip.family == AF_UNSPEC)
+ return 1;
+ break;
+ case 'p':
+ if (parse_ports(optarg, &min_port, &max_port))
+ return 1;
+ break;
+ case 'P':
+ vip.protocol = atoi(optarg);
+ break;
+ case 's':
+ case 'd':
+ if (opt == 's')
+ v6 = tnl.saddr.v6;
+ else
+ v6 = tnl.daddr.v6;
+
+ family = parse_ipstr(optarg, v6);
+ if (family == AF_UNSPEC)
+ return 1;
+ if (tnl.family == AF_UNSPEC) {
+ tnl.family = family;
+ } else if (tnl.family != family) {
+ fprintf(stderr,
+ "The IP version of the src and dst addresses used in the IP encapsulation does not match\n");
+ return 1;
+ }
+ break;
+ case 'm':
+ if (!ether_aton_r(optarg,
+ (struct ether_addr *)tnl.dmac)) {
+ fprintf(stderr, "Invalid mac address:%s\n",
+ optarg);
+ return 1;
+ }
+ break;
+ case 'T':
+ kill_after_s = atoi(optarg);
+ break;
+ default:
+ usage(argv[0]);
+ return 1;
+ }
+ opt_flags[opt] = 0;
+ }
+
+ for (i = 0; i < strlen(optstr); i++) {
+ if (opt_flags[(unsigned int)optstr[i]]) {
+ fprintf(stderr, "Missing argument -%c\n", optstr[i]);
+ usage(argv[0]);
+ return 1;
+ }
+ }
+
+ signal(SIGINT, int_exit);
+
+ while (min_port <= max_port) {
+ vip.dport = htons(min_port++);
+ if (bpf_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
+ perror("bpf_update_elem(&vip2tnl)");
+ return 1;
+ }
+ }
+
+ if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+ printf("link set xdp fd failed\n");
+ return 1;
+ }
+
+ poll_stats(kill_after_s);
+
+ set_link_xdp_fd(ifindex, -1);
+
+ return 0;
+}
--
2.5.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox