* [net-next 04/10] ixgbe: fix link test when connected to 1Gbps link partner
From: Jeff Kirsher @ 2013-08-28 10:33 UTC (permalink / raw)
To: davem; +Cc: Emil Tantilov, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1377686028-30747-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Emil Tantilov <emil.s.tantilov@intel.com>
This patch is a partial reverse of:
commit dfcc4615f09c33454bc553567f7c7506cae60cb9
Specifically forcing the laser before the link check can lead to
inconsistent results because it does not guarantee that the link will be
negotiated correctly. Such is the case when dual speed SFP+ module is
connected to a gigabit link partner.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 26 ++++++++----------------
1 file changed, 9 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index db0dbf6..57465d8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1885,11 +1885,11 @@ static void ixgbe_diag_test(struct net_device *netdev,
struct ethtool_test *eth_test, u64 *data)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- struct ixgbe_hw *hw = &adapter->hw;
bool if_running = netif_running(netdev);
set_bit(__IXGBE_TESTING, &adapter->state);
if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+ struct ixgbe_hw *hw = &adapter->hw;
if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
int i;
for (i = 0; i < adapter->num_vfs; i++) {
@@ -1913,21 +1913,18 @@ static void ixgbe_diag_test(struct net_device *netdev,
/* Offline tests */
e_info(hw, "offline testing starting\n");
- if (if_running)
- /* indicate we're in test mode */
- dev_close(netdev);
-
- /* bringing adapter down disables SFP+ optics */
- if (hw->mac.ops.enable_tx_laser)
- hw->mac.ops.enable_tx_laser(hw);
-
/* Link test performed before hardware reset so autoneg doesn't
* interfere with test result
*/
if (ixgbe_link_test(adapter, &data[4]))
eth_test->flags |= ETH_TEST_FL_FAILED;
- ixgbe_reset(adapter);
+ if (if_running)
+ /* indicate we're in test mode */
+ dev_close(netdev);
+ else
+ ixgbe_reset(adapter);
+
e_info(hw, "register testing starting\n");
if (ixgbe_reg_test(adapter, &data[0]))
eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1964,13 +1961,11 @@ skip_loopback:
clear_bit(__IXGBE_TESTING, &adapter->state);
if (if_running)
dev_open(netdev);
+ else if (hw->mac.ops.disable_tx_laser)
+ hw->mac.ops.disable_tx_laser(hw);
} else {
e_info(hw, "online testing starting\n");
- /* if adapter is down, SFP+ optics will be disabled */
- if (!if_running && hw->mac.ops.enable_tx_laser)
- hw->mac.ops.enable_tx_laser(hw);
-
/* Online tests */
if (ixgbe_link_test(adapter, &data[4]))
eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1984,9 +1979,6 @@ skip_loopback:
clear_bit(__IXGBE_TESTING, &adapter->state);
}
- /* if adapter was down, ensure SFP+ optics are disabled again */
- if (!if_running && hw->mac.ops.disable_tx_laser)
- hw->mac.ops.disable_tx_laser(hw);
skip_ol_tests:
msleep_interruptible(4 * 1000);
}
--
1.8.3.1
^ permalink raw reply related
* [net-next 03/10] ixgbe: fix incorrect limit value in ring transverse
From: Jeff Kirsher @ 2013-08-28 10:33 UTC (permalink / raw)
To: davem; +Cc: Don Skidmore, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1377686028-30747-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Don Skidmore <donald.c.skidmore@intel.com>
We were transversing the tx_ring with IXGBE_NUM_RX_QUEUES. Now this define
happens to have the correct value but this is misleading and a change later
could easily make this no longer true. I updated it to netdev->num_tx_queues
like we use in ixgbe_get_strings().
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 50c1e9b..db0dbf6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1049,7 +1049,7 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
data[i] = (ixgbe_gstrings_stats[i].sizeof_stat ==
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
- for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) {
+ for (j = 0; j < netdev->num_tx_queues; j++) {
ring = adapter->tx_ring[j];
if (!ring) {
data[i] = 0;
--
1.8.3.1
^ permalink raw reply related
* [net-next 02/10] ixgbe: Check return value on eeprom reads
From: Jeff Kirsher @ 2013-08-28 10:33 UTC (permalink / raw)
To: davem; +Cc: Mark Rustad, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1377686028-30747-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Mark Rustad <mark.d.rustad@intel.com>
This patch fixes the possible use of uninitialized memory by checking the
return value on eeprom reads. These issues were identified by static
analysis. In many cases error messages will be produced so that corrupted
eeprom issues will be more visible.
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c | 38 ++++++++++----
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 67 +++++++++++++++++--------
drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 6 ++-
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 35 ++++++++++---
4 files changed, 107 insertions(+), 39 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 51ee8ad..e4f4f4b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -142,11 +142,13 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw)
goto setup_sfp_out;
}
- hw->eeprom.ops.read(hw, ++data_offset, &data_value);
+ if (hw->eeprom.ops.read(hw, ++data_offset, &data_value))
+ goto setup_sfp_err;
while (data_value != 0xffff) {
IXGBE_WRITE_REG(hw, IXGBE_CORECTL, data_value);
IXGBE_WRITE_FLUSH(hw);
- hw->eeprom.ops.read(hw, ++data_offset, &data_value);
+ if (hw->eeprom.ops.read(hw, ++data_offset, &data_value))
+ goto setup_sfp_err;
}
/* Release the semaphore */
@@ -192,6 +194,17 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw)
setup_sfp_out:
return ret_val;
+
+setup_sfp_err:
+ /* Release the semaphore */
+ hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM);
+ /* Delay obtaining semaphore again to allow FW access,
+ * semaphore_delay is in ms usleep_range needs us.
+ */
+ usleep_range(hw->eeprom.semaphore_delay * 1000,
+ hw->eeprom.semaphore_delay * 2000);
+ hw_err(hw, "eeprom read at offset %d failed\n", data_offset);
+ return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE;
}
static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw)
@@ -2180,6 +2193,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
{
s32 status = IXGBE_ERR_EEPROM_VERSION;
u16 fw_offset, fw_ptp_cfg_offset;
+ u16 offset;
u16 fw_version = 0;
/* firmware check is only necessary for SFI devices */
@@ -2189,29 +2203,35 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw)
}
/* get the offset to the Firmware Module block */
- hw->eeprom.ops.read(hw, IXGBE_FW_PTR, &fw_offset);
+ offset = IXGBE_FW_PTR;
+ if (hw->eeprom.ops.read(hw, offset, &fw_offset))
+ goto fw_version_err;
if ((fw_offset == 0) || (fw_offset == 0xFFFF))
goto fw_version_out;
/* get the offset to the Pass Through Patch Configuration block */
- hw->eeprom.ops.read(hw, (fw_offset +
- IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR),
- &fw_ptp_cfg_offset);
+ offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR;
+ if (hw->eeprom.ops.read(hw, offset, &fw_ptp_cfg_offset))
+ goto fw_version_err;
if ((fw_ptp_cfg_offset == 0) || (fw_ptp_cfg_offset == 0xFFFF))
goto fw_version_out;
/* get the firmware version */
- hw->eeprom.ops.read(hw, (fw_ptp_cfg_offset +
- IXGBE_FW_PATCH_VERSION_4),
- &fw_version);
+ offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4;
+ if (hw->eeprom.ops.read(hw, offset, &fw_version))
+ goto fw_version_err;
if (fw_version > 0x5)
status = 0;
fw_version_out:
return status;
+
+fw_version_err:
+ hw_err(hw, "eeprom read at offset %d failed\n", offset);
+ return IXGBE_ERR_EEPROM_VERSION;
}
/**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 50e62a2..b5c434b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2740,13 +2740,19 @@ out:
static s32 ixgbe_get_san_mac_addr_offset(struct ixgbe_hw *hw,
u16 *san_mac_offset)
{
+ s32 ret_val;
+
/*
* First read the EEPROM pointer to see if the MAC addresses are
* available.
*/
- hw->eeprom.ops.read(hw, IXGBE_SAN_MAC_ADDR_PTR, san_mac_offset);
+ ret_val = hw->eeprom.ops.read(hw, IXGBE_SAN_MAC_ADDR_PTR,
+ san_mac_offset);
+ if (ret_val)
+ hw_err(hw, "eeprom read at offset %d failed\n",
+ IXGBE_SAN_MAC_ADDR_PTR);
- return 0;
+ return ret_val;
}
/**
@@ -2763,23 +2769,16 @@ s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr)
{
u16 san_mac_data, san_mac_offset;
u8 i;
+ s32 ret_val;
/*
* First read the EEPROM pointer to see if the MAC addresses are
* available. If they're not, no point in calling set_lan_id() here.
*/
- ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset);
+ ret_val = ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset);
+ if (ret_val || san_mac_offset == 0 || san_mac_offset == 0xFFFF)
- if ((san_mac_offset == 0) || (san_mac_offset == 0xFFFF)) {
- /*
- * No addresses available in this EEPROM. It's not an
- * error though, so just wipe the local address and return.
- */
- for (i = 0; i < 6; i++)
- san_mac_addr[i] = 0xFF;
-
- goto san_mac_addr_out;
- }
+ goto san_mac_addr_clr;
/* make sure we know which port we need to program */
hw->mac.ops.set_lan_id(hw);
@@ -2787,14 +2786,26 @@ s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr)
(hw->bus.func) ? (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT1_OFFSET) :
(san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT0_OFFSET);
for (i = 0; i < 3; i++) {
- hw->eeprom.ops.read(hw, san_mac_offset, &san_mac_data);
+ ret_val = hw->eeprom.ops.read(hw, san_mac_offset,
+ &san_mac_data);
+ if (ret_val) {
+ hw_err(hw, "eeprom read at offset %d failed\n",
+ san_mac_offset);
+ goto san_mac_addr_clr;
+ }
san_mac_addr[i * 2] = (u8)(san_mac_data);
san_mac_addr[i * 2 + 1] = (u8)(san_mac_data >> 8);
san_mac_offset++;
}
-
-san_mac_addr_out:
return 0;
+
+san_mac_addr_clr:
+ /* No addresses available in this EEPROM. It's not necessarily an
+ * error though, so just wipe the local address and return.
+ */
+ for (i = 0; i < 6; i++)
+ san_mac_addr[i] = 0xFF;
+ return ret_val;
}
/**
@@ -3243,8 +3254,9 @@ s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
*wwpn_prefix = 0xFFFF;
/* check if alternative SAN MAC is supported */
- hw->eeprom.ops.read(hw, IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR,
- &alt_san_mac_blk_offset);
+ offset = IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR;
+ if (hw->eeprom.ops.read(hw, offset, &alt_san_mac_blk_offset))
+ goto wwn_prefix_err;
if ((alt_san_mac_blk_offset == 0) ||
(alt_san_mac_blk_offset == 0xFFFF))
@@ -3252,19 +3264,26 @@ s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
/* check capability in alternative san mac address block */
offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET;
- hw->eeprom.ops.read(hw, offset, &caps);
+ if (hw->eeprom.ops.read(hw, offset, &caps))
+ goto wwn_prefix_err;
if (!(caps & IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN))
goto wwn_prefix_out;
/* get the corresponding prefix for WWNN/WWPN */
offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET;
- hw->eeprom.ops.read(hw, offset, wwnn_prefix);
+ if (hw->eeprom.ops.read(hw, offset, wwnn_prefix))
+ hw_err(hw, "eeprom read at offset %d failed\n", offset);
offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET;
- hw->eeprom.ops.read(hw, offset, wwpn_prefix);
+ if (hw->eeprom.ops.read(hw, offset, wwpn_prefix))
+ goto wwn_prefix_err;
wwn_prefix_out:
return 0;
+
+wwn_prefix_err:
+ hw_err(hw, "eeprom read at offset %d failed\n", offset);
+ return 0;
}
/**
@@ -3778,7 +3797,11 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw)
u8 sensor_index;
u8 sensor_location;
- hw->eeprom.ops.read(hw, (ets_offset + 1 + i), &ets_sensor);
+ if (hw->eeprom.ops.read(hw, ets_offset + 1 + i, &ets_sensor)) {
+ hw_err(hw, "eeprom read at offset %d failed\n",
+ ets_offset + 1 + i);
+ continue;
+ }
sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >>
IXGBE_ETS_DATA_INDEX_SHIFT);
sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >>
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index 1315b8a..d259dc7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -143,8 +143,12 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw);
#define IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS)
+#define ixgbe_hw_to_netdev(hw) (((struct ixgbe_adapter *)(hw)->back)->netdev)
+
#define hw_dbg(hw, format, arg...) \
- netdev_dbg(((struct ixgbe_adapter *)(hw->back))->netdev, format, ##arg)
+ netdev_dbg(ixgbe_hw_to_netdev(hw), format, ## arg)
+#define hw_err(hw, format, arg...) \
+ netdev_err(ixgbe_hw_to_netdev(hw), format, ## arg)
#define e_dev_info(format, arg...) \
dev_info(&adapter->pdev->dev, format, ## arg)
#define e_dev_warn(format, arg...) \
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 369eef5..6a4a799 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -791,6 +791,8 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
* Read control word from PHY init contents offset
*/
ret_val = hw->eeprom.ops.read(hw, data_offset, &eword);
+ if (ret_val)
+ goto err_eeprom;
control = (eword & IXGBE_CONTROL_MASK_NL) >>
IXGBE_CONTROL_SHIFT_NL;
edata = eword & IXGBE_DATA_MASK_NL;
@@ -803,10 +805,15 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
case IXGBE_DATA_NL:
hw_dbg(hw, "DATA:\n");
data_offset++;
- hw->eeprom.ops.read(hw, data_offset++,
- &phy_offset);
+ ret_val = hw->eeprom.ops.read(hw, data_offset++,
+ &phy_offset);
+ if (ret_val)
+ goto err_eeprom;
for (i = 0; i < edata; i++) {
- hw->eeprom.ops.read(hw, data_offset, &eword);
+ ret_val = hw->eeprom.ops.read(hw, data_offset,
+ &eword);
+ if (ret_val)
+ goto err_eeprom;
hw->phy.ops.write_reg(hw, phy_offset,
MDIO_MMD_PMAPMD, eword);
hw_dbg(hw, "Wrote %4.4x to %4.4x\n", eword,
@@ -838,6 +845,10 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
out:
return ret_val;
+
+err_eeprom:
+ hw_err(hw, "eeprom read at offset %d failed\n", data_offset);
+ return IXGBE_ERR_PHY;
}
/**
@@ -1339,7 +1350,11 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
sfp_type = ixgbe_sfp_type_srlr_core1;
/* Read offset to PHY init contents */
- hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset);
+ if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) {
+ hw_err(hw, "eeprom read at %d failed\n",
+ IXGBE_PHY_INIT_OFFSET_NL);
+ return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT;
+ }
if ((!*list_offset) || (*list_offset == 0xFFFF))
return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT;
@@ -1351,12 +1366,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
* Find the matching SFP ID in the EEPROM
* and program the init sequence
*/
- hw->eeprom.ops.read(hw, *list_offset, &sfp_id);
+ if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id))
+ goto err_phy;
while (sfp_id != IXGBE_PHY_INIT_END_NL) {
if (sfp_id == sfp_type) {
(*list_offset)++;
- hw->eeprom.ops.read(hw, *list_offset, data_offset);
+ if (hw->eeprom.ops.read(hw, *list_offset, data_offset))
+ goto err_phy;
if ((!*data_offset) || (*data_offset == 0xFFFF)) {
hw_dbg(hw, "SFP+ module not supported\n");
return IXGBE_ERR_SFP_NOT_SUPPORTED;
@@ -1366,7 +1383,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
} else {
(*list_offset) += 2;
if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id))
- return IXGBE_ERR_PHY;
+ goto err_phy;
}
}
@@ -1376,6 +1393,10 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
}
return 0;
+
+err_phy:
+ hw_err(hw, "eeprom read at offset %d failed\n", *list_offset);
+ return IXGBE_ERR_PHY;
}
/**
--
1.8.3.1
^ permalink raw reply related
* [net-next 01/10] ixgbe: disable link when adapter goes down
From: Jeff Kirsher @ 2013-08-28 10:33 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1377686028-30747-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
This patch fixes an issue with the 82599 adapter where it can potentially keep
link lights up when the adapter has gone down. The patch adds a function which
ensures link is disabled, and calls this function when the adapter transitions
to a down state.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c | 20 ++++++++++++++++++++
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 2 ++
3 files changed, 25 insertions(+)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 207f68f..51ee8ad 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -49,6 +49,7 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw,
static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw,
ixgbe_link_speed speed,
bool autoneg_wait_to_complete);
+static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw);
static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw,
bool autoneg_wait_to_complete);
static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
@@ -432,6 +433,24 @@ out:
}
/**
+ * ixgbe_stop_mac_link_on_d3_82599 - Disables link on D3
+ * @hw: pointer to hardware structure
+ *
+ * Disables link, should be called during D3 power down sequence.
+ *
+ */
+static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw)
+{
+ u32 autoc2_reg;
+
+ if (!hw->mng_fw_enabled && !hw->wol_enabled) {
+ autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
+ autoc2_reg |= IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK;
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg);
+ }
+}
+
+/**
* ixgbe_start_mac_link_82599 - Setup MAC link settings
* @hw: pointer to hardware structure
* @autoneg_wait_to_complete: true when waiting for completion is needed
@@ -2477,6 +2496,7 @@ static struct ixgbe_mac_operations mac_ops_82599 = {
.set_lan_id = &ixgbe_set_lan_id_multi_port_pcie,
.read_analog_reg8 = &ixgbe_read_analog_reg8_82599,
.write_analog_reg8 = &ixgbe_write_analog_reg8_82599,
+ .stop_link_on_d3 = &ixgbe_stop_mac_link_on_d3_82599,
.setup_link = &ixgbe_setup_mac_link_82599,
.set_rxpba = &ixgbe_set_rxpba_generic,
.check_link = &ixgbe_check_mac_link_generic,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 128d6b8..cf1b41e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5292,6 +5292,9 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
return retval;
#endif
+ if (hw->mac.ops.stop_link_on_d3)
+ hw->mac.ops.stop_link_on_d3(hw);
+
if (wufc) {
ixgbe_set_rx_mode(netdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 161ff18..6442cf8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1596,6 +1596,7 @@ enum {
#define IXGBE_AUTOC2_10G_KR (0x0 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT)
#define IXGBE_AUTOC2_10G_XFI (0x1 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT)
#define IXGBE_AUTOC2_10G_SFI (0x2 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT)
+#define IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK 0x50000000
#define IXGBE_AUTOC2_LINK_DISABLE_MASK 0x70000000
#define IXGBE_MACC_FLU 0x00000001
@@ -2847,6 +2848,7 @@ struct ixgbe_mac_operations {
void (*disable_tx_laser)(struct ixgbe_hw *);
void (*enable_tx_laser)(struct ixgbe_hw *);
void (*flap_tx_laser)(struct ixgbe_hw *);
+ void (*stop_link_on_d3)(struct ixgbe_hw *);
s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool);
s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool);
s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *,
--
1.8.3.1
^ permalink raw reply related
* [net-next 00/10][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2013-08-28 10:33 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series contains updates to ixgbe.
Jacob provides a fix for 82599 devices where it can potentially keep link
lights up when the adapter has gone down.
Mark provides a fix to resolve the possible use of uninitialized memory
by checking the return value on EEPROM reads.
Don provides 2 patches, one to fix a issue where we were traversing the
Tx ring with the value of IXGBE_NUM_RX_QUEUES which currently happens
to have the correct value but this is misleading. A change later, could
easily make this no longer correct so when traversing the Tx ring, use
netdev->num_tx_queues. His second patch does some minor clean ups of log
messages.
Emil provides the remaining ixgbe patches. First he fixes the link test
where forcing the laser before the link check can lead to inconsistent
results because it does not guarantee that the link will be negotiated
correctly. Then he initializes the message buffer array to 0 in order
to avoid using random numbers from the memory as a MAC address for the
VF. Emil also fixes the read loop for the I2C data to account for the
offset for SFP+ modules. Lastly, Emil provides several patches to add
support for QSFP modules where 1Gbps support is added as well as support
for older QSFP active direct attach cables which pre-date SFF-8436 v3.6.
The following are changes since commit 5b2941b18dc5f60a5c14a5c15693f9c58b0dd922:
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Don Skidmore (2):
ixgbe: fix incorrect limit value in ring transverse
ixgbe: cleanup some log messages
Emil Tantilov (6):
ixgbe: fix link test when connected to 1Gbps link partner
ixgbe: zero out mailbox buffer on init
ixgbe: fix SFF data dumps of SFP+ modules from an offset
ixgbe: add 1Gbps support for QSFP+
ixgbe: include QSFP PHY types in ixgbe_is_sfp()
ixgbe: add support for older QSFP active DA cables
Jacob Keller (1):
ixgbe: disable link when adapter goes down
Mark Rustad (1):
ixgbe: Check return value on eeprom reads
drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c | 93 ++++++++++++++++++----
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 67 ++++++++++------
drivers/net/ethernet/intel/ixgbe/ixgbe_common.h | 6 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 40 ++++------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 13 +++-
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 98 +++++++++++++++++++-----
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h | 5 ++
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 4 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_type.h | 2 +
9 files changed, 238 insertions(+), 90 deletions(-)
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH v3] driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.
From: Sonic Zhang @ 2013-08-28 10:25 UTC (permalink / raw)
To: Giuseppe CAVALLARO; +Cc: netdev, adi-buildroot-devel, Sonic Zhang
In-Reply-To: <521DC044.9090207@st.com>
Hi Peppe,
On Wed, Aug 28, 2013 at 5:17 PM, Giuseppe CAVALLARO
<peppe.cavallaro@st.com> wrote:
> hello some comments below
>
> On 8/28/2013 7:40 AM, Sonic Zhang wrote:
>>
>> From: Sonic Zhang <sonic.zhang@analog.com>
>>
>> Some synopsys ip implementation doesn't support DMA store and forward
>> mode,
>> such as BF60x. So, set force_thresh_dma_mode to use DMA thresholds only.
>> Update document and devicetree as well.
>>
>> Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
>> ---
>> Documentation/devicetree/bindings/net/stmmac.txt | 2 ++
>> Documentation/networking/stmmac.txt | 3 +++
>> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
>> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 +++
>> include/linux/stmmac.h | 1 +
>> 5 files changed, 12 insertions(+), 1 deletion(-)
>>
>> diff --git a/Documentation/devicetree/bindings/net/stmmac.txt
>> b/Documentation/devicetree/bindings/net/stmmac.txt
>> index 261c563..56fbcb5 100644
>> --- a/Documentation/devicetree/bindings/net/stmmac.txt
>> +++ b/Documentation/devicetree/bindings/net/stmmac.txt
>> @@ -22,6 +22,8 @@ Required properties:
>> - snps,pbl Programmable Burst Length
>> - snps,fixed-burst Program the DMA to use the fixed burst mode
>> - snps,mixed-burst Program the DMA to use the mixed burst mode
>> +- snps,force_thresh_dma_mode Force DMA to use the Shreshold mode other
>> than
>
>
> ^^^^^^^^^ typo
>
>
>
>> + the Store and Forward mode.
>
>
> if we use this approach you should document that the force_thresh_dma_mode
> and force_sf_dma_mode will force the mode for both tx and rx.
OK
>
> I am wondering now what happens if these are passed together from the
> platform? is your code covering this scenario?
Yes, in case both are set, I unset flag force_sf_dma_mode. So, only
force_thresh_dma_mode takes effect.
>
> we could have a unique force_dma_mode that can be:
>
> rx_force_threshold
> tx_force_threshold
> rx_force_sf
> tx_force_sf
> ( these can be defined in the stmmac.h platform header )
>
> but this an impact on all the platforms that already use the
> force_sf_dma_mode as we said
So, I prefer current 2-flag solution.
>
> In this case you should fix this and maybe the patch should be for net-next
> (add it in the subject next time).
I will add "for net-next" to the subject.
>
> peppe
>
>
>>
>> Optional properties:
>> - mac-address: 6 bytes, mac address
>> diff --git a/Documentation/networking/stmmac.txt
>> b/Documentation/networking/stmmac.txt
>> index 654d2e5..457b8bb 100644
>> --- a/Documentation/networking/stmmac.txt
>> +++ b/Documentation/networking/stmmac.txt
>> @@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
>> int bugged_jumbo;
>> int pmt;
>> int force_sf_dma_mode;
>> + int force_thresh_dma_mode;
>> int riwt_off;
>> void (*fix_mac_speed)(void *priv, unsigned int speed);
>> void (*bus_setup)(void __iomem *ioaddr);
>> @@ -159,6 +160,8 @@ Where:
>> o pmt: core has the embedded power module (optional).
>> o force_sf_dma_mode: force DMA to use the Store and Forward mode
>> instead of the Threshold.
>> + o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
>> + the Store and Forward mode.
>> o riwt_off: force to disable the RX watchdog feature and switch to NAPI
>> mode.
>> o fix_mac_speed: this callback is used for modifying some syscfg
>> registers
>> (on ST SoCs) according to the link speed negotiated by
>> the
>> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
>> b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
>> index be40691..8d4ccd3 100644
>> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
>> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
>> @@ -1224,7 +1224,9 @@ static void free_dma_desc_resources(struct
>> stmmac_priv *priv)
>> */
>> static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
>> {
>> - if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
>> + if (priv->plat->force_thresh_dma_mode)
>> + priv->hw->dma->dma_mode(priv->ioaddr, tc, tc);
>> + else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
>> /*
>> * In case of GMAC, SF mode can be enabled
>> * to perform the TX COE in HW. This depends on:
>> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>> b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>> index da8be6e..865c944 100644
>> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>> @@ -79,6 +79,9 @@ static int stmmac_probe_config_dt(struct platform_device
>> *pdev,
>> of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
>> dma_cfg->fixed_burst = of_property_read_bool(np,
>> "snps,fixed-burst");
>> dma_cfg->mixed_burst = of_property_read_bool(np,
>> "snps,mixed-burst");
>> + plat->force_thresh_dma_mode = of_property_read_bool(np,
>> "snps,force_thresh_dma_mode");
>> + if (plat->force_thresh_dma_mode)
>> + plat->force_sf_dma_mode = 0;
>>
>> return 0;
>> }
>> diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
>> index 9e495d31..bb5deb0 100644
>> --- a/include/linux/stmmac.h
>> +++ b/include/linux/stmmac.h
>> @@ -108,6 +108,7 @@ struct plat_stmmacenet_data {
>> int bugged_jumbo;
>> int pmt;
>> int force_sf_dma_mode;
>> + int force_thresh_dma_mode;
>> int riwt_off;
>> void (*fix_mac_speed)(void *priv, unsigned int speed);
>> void (*bus_setup)(void __iomem *ioaddr);
>>
>
^ permalink raw reply
* [PATCH net-next] ipv6: Remove redundant sk variable
From: Thomas Graf @ 2013-08-28 10:05 UTC (permalink / raw)
To: davem; +Cc: netdev
A sk variable initialized to ndisc_sk is already available outside
of the branch.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
---
net/ipv6/ndisc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 04d31c2..0f915b5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -428,7 +428,6 @@ static void ndisc_send_skb(struct sk_buff *skb,
type = icmp6h->icmp6_type;
if (!dst) {
- struct sock *sk = net->ipv6.ndisc_sk;
struct flowi6 fl6;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex);
--
1.8.3.1
^ permalink raw reply related
* [PATCH] ipv4 tunnels: fix an oops when using ipip/sit with IPsec
From: Nicolas Dichtel @ 2013-08-28 9:54 UTC (permalink / raw)
To: davem; +Cc: netdev, pshelar, hongjun.li, Nicolas Dichtel
From: Li Hongjun <hongjun.li@6wind.com>
Since commit 3d7b46cd20e3 (ip_tunnel: push generic protocol handling to
ip_tunnel module.), an Oops is triggered when an xfrm policy is configured on
an IPv4 over IPv4 tunnel.
xfrm4_policy_check() calls __xfrm_policy_check2(), which uses skb_dst(skb). But
this field is NULL because iptunnel_pull_header() calls skb_dst_drop(skb).
Signed-off-by: Li Hongjun <hongjun.li@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv4/ipip.c | 5 ++---
net/ipv6/sit.c | 6 ++----
2 files changed, 4 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 51fc2a1dcdd3..b3ac3c3f6219 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -190,15 +190,14 @@ static int ipip_rcv(struct sk_buff *skb)
struct ip_tunnel *tunnel;
const struct iphdr *iph;
- if (iptunnel_pull_header(skb, 0, tpi.proto))
- goto drop;
-
iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a3437a4cd07e..1e6a81d0c897 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -645,11 +645,7 @@ static int ipip_rcv(struct sk_buff *skb)
const struct iphdr *iph;
struct ip_tunnel *tunnel;
- if (iptunnel_pull_header(skb, 0, tpi.proto))
- goto drop;
-
iph = ip_hdr(skb);
-
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel != NULL) {
@@ -659,6 +655,8 @@ static int ipip_rcv(struct sk_buff *skb)
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
--
1.8.2.1
^ permalink raw reply related
* Re: [PATCH] net: mdio-sun4i: Convert to devm_* api
From: Maxime Ripard @ 2013-08-28 9:35 UTC (permalink / raw)
To: Jisheng Zhang; +Cc: davem, emilio, netdev, linux-kernel
In-Reply-To: <1377522717-5784-1-git-send-email-jszhang@marvell.com>
[-- Attachment #1: Type: text/plain, Size: 586 bytes --]
Hi Jisheng,
On Mon, Aug 26, 2013 at 09:11:57PM +0800, Jisheng Zhang wrote:
> Use devm_ioremap_resource instead of of_iomap() and devm_kzalloc()
> instead of kmalloc() to make cleanup paths simpler. This patch also
> fixes the resource leak caused by missing corresponding iounamp()
> of the of_iomap().
>
> Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
It looks fine for me.
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Thanks!
Maxime
--
Maxime Ripard, Free Electrons
Embedded Linux, Kernel and Android engineering
http://free-electrons.com
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH v3] driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.
From: Giuseppe CAVALLARO @ 2013-08-28 9:17 UTC (permalink / raw)
To: Sonic Zhang; +Cc: netdev, adi-buildroot-devel, Sonic Zhang
In-Reply-To: <1377668458-21932-1-git-send-email-sonic.adi@gmail.com>
hello some comments below
On 8/28/2013 7:40 AM, Sonic Zhang wrote:
> From: Sonic Zhang <sonic.zhang@analog.com>
>
> Some synopsys ip implementation doesn't support DMA store and forward mode,
> such as BF60x. So, set force_thresh_dma_mode to use DMA thresholds only.
> Update document and devicetree as well.
>
> Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
> ---
> Documentation/devicetree/bindings/net/stmmac.txt | 2 ++
> Documentation/networking/stmmac.txt | 3 +++
> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 +++
> include/linux/stmmac.h | 1 +
> 5 files changed, 12 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
> index 261c563..56fbcb5 100644
> --- a/Documentation/devicetree/bindings/net/stmmac.txt
> +++ b/Documentation/devicetree/bindings/net/stmmac.txt
> @@ -22,6 +22,8 @@ Required properties:
> - snps,pbl Programmable Burst Length
> - snps,fixed-burst Program the DMA to use the fixed burst mode
> - snps,mixed-burst Program the DMA to use the mixed burst mode
> +- snps,force_thresh_dma_mode Force DMA to use the Shreshold mode other than
^^^^^^^^^ typo
> + the Store and Forward mode.
if we use this approach you should document that the
force_thresh_dma_mode and force_sf_dma_mode will force the mode for both
tx and rx.
I am wondering now what happens if these are passed together from the
platform? is your code covering this scenario?
we could have a unique force_dma_mode that can be:
rx_force_threshold
tx_force_threshold
rx_force_sf
tx_force_sf
( these can be defined in the stmmac.h platform header )
but this an impact on all the platforms that already use the
force_sf_dma_mode as we said
In this case you should fix this and maybe the patch should be for
net-next (add it in the subject next time).
peppe
>
> Optional properties:
> - mac-address: 6 bytes, mac address
> diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
> index 654d2e5..457b8bb 100644
> --- a/Documentation/networking/stmmac.txt
> +++ b/Documentation/networking/stmmac.txt
> @@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
> int bugged_jumbo;
> int pmt;
> int force_sf_dma_mode;
> + int force_thresh_dma_mode;
> int riwt_off;
> void (*fix_mac_speed)(void *priv, unsigned int speed);
> void (*bus_setup)(void __iomem *ioaddr);
> @@ -159,6 +160,8 @@ Where:
> o pmt: core has the embedded power module (optional).
> o force_sf_dma_mode: force DMA to use the Store and Forward mode
> instead of the Threshold.
> + o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
> + the Store and Forward mode.
> o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
> o fix_mac_speed: this callback is used for modifying some syscfg registers
> (on ST SoCs) according to the link speed negotiated by the
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index be40691..8d4ccd3 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -1224,7 +1224,9 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
> */
> static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
> {
> - if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
> + if (priv->plat->force_thresh_dma_mode)
> + priv->hw->dma->dma_mode(priv->ioaddr, tc, tc);
> + else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
> /*
> * In case of GMAC, SF mode can be enabled
> * to perform the TX COE in HW. This depends on:
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> index da8be6e..865c944 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> @@ -79,6 +79,9 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
> of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
> dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst");
> dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
> + plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
> + if (plat->force_thresh_dma_mode)
> + plat->force_sf_dma_mode = 0;
>
> return 0;
> }
> diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
> index 9e495d31..bb5deb0 100644
> --- a/include/linux/stmmac.h
> +++ b/include/linux/stmmac.h
> @@ -108,6 +108,7 @@ struct plat_stmmacenet_data {
> int bugged_jumbo;
> int pmt;
> int force_sf_dma_mode;
> + int force_thresh_dma_mode;
> int riwt_off;
> void (*fix_mac_speed)(void *priv, unsigned int speed);
> void (*bus_setup)(void __iomem *ioaddr);
>
^ permalink raw reply
* Re: [PATCH v3] driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.
From: Giuseppe CAVALLARO @ 2013-08-28 9:17 UTC (permalink / raw)
To: Sonic Zhang; +Cc: netdev, adi-buildroot-devel, Sonic Zhang
In-Reply-To: <1377668458-21932-1-git-send-email-sonic.adi@gmail.com>
hello some comments below
On 8/28/2013 7:40 AM, Sonic Zhang wrote:
> From: Sonic Zhang <sonic.zhang@analog.com>
>
> Some synopsys ip implementation doesn't support DMA store and forward mode,
> such as BF60x. So, set force_thresh_dma_mode to use DMA thresholds only.
> Update document and devicetree as well.
>
> Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
> ---
> Documentation/devicetree/bindings/net/stmmac.txt | 2 ++
> Documentation/networking/stmmac.txt | 3 +++
> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 +++
> include/linux/stmmac.h | 1 +
> 5 files changed, 12 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
> index 261c563..56fbcb5 100644
> --- a/Documentation/devicetree/bindings/net/stmmac.txt
> +++ b/Documentation/devicetree/bindings/net/stmmac.txt
> @@ -22,6 +22,8 @@ Required properties:
> - snps,pbl Programmable Burst Length
> - snps,fixed-burst Program the DMA to use the fixed burst mode
> - snps,mixed-burst Program the DMA to use the mixed burst mode
> +- snps,force_thresh_dma_mode Force DMA to use the Shreshold mode other than
^^^^^^^^^ typo
> + the Store and Forward mode.
if we use this approach you should document that the
force_thresh_dma_mode and force_sf_dma_mode will force the mode for both
tx and rx.
I am wondering now what happens if these are passed together from the
platform? is your code covering this scenario?
we could have a unique force_dma_mode that can be:
rx_force_threshold
tx_force_threshold
rx_force_sf
tx_force_sf
( these can be defined in the stmmac.h platform header )
but this an impact on all the platforms that already use the
force_sf_dma_mode as we said
In this case you should fix this and maybe the patch should be for
net-next (add it in the subject next time).
>
> Optional properties:
> - mac-address: 6 bytes, mac address
> diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
> index 654d2e5..457b8bb 100644
> --- a/Documentation/networking/stmmac.txt
> +++ b/Documentation/networking/stmmac.txt
> @@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
> int bugged_jumbo;
> int pmt;
> int force_sf_dma_mode;
> + int force_thresh_dma_mode;
> int riwt_off;
> void (*fix_mac_speed)(void *priv, unsigned int speed);
> void (*bus_setup)(void __iomem *ioaddr);
> @@ -159,6 +160,8 @@ Where:
> o pmt: core has the embedded power module (optional).
> o force_sf_dma_mode: force DMA to use the Store and Forward mode
> instead of the Threshold.
> + o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
> + the Store and Forward mode.
> o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
> o fix_mac_speed: this callback is used for modifying some syscfg registers
> (on ST SoCs) according to the link speed negotiated by the
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index be40691..8d4ccd3 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -1224,7 +1224,9 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
> */
> static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
> {
> - if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
> + if (priv->plat->force_thresh_dma_mode)
> + priv->hw->dma->dma_mode(priv->ioaddr, tc, tc);
> + else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
> /*
> * In case of GMAC, SF mode can be enabled
> * to perform the TX COE in HW. This depends on:
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> index da8be6e..865c944 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
> @@ -79,6 +79,9 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
> of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
> dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst");
> dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
> + plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
> + if (plat->force_thresh_dma_mode)
> + plat->force_sf_dma_mode = 0;
>
> return 0;
> }
> diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
> index 9e495d31..bb5deb0 100644
> --- a/include/linux/stmmac.h
> +++ b/include/linux/stmmac.h
> @@ -108,6 +108,7 @@ struct plat_stmmacenet_data {
> int bugged_jumbo;
> int pmt;
> int force_sf_dma_mode;
> + int force_thresh_dma_mode;
> int riwt_off;
> void (*fix_mac_speed)(void *priv, unsigned int speed);
> void (*bus_setup)(void __iomem *ioaddr);
>
^ permalink raw reply
* Re: [PATCH net-next 0/3] xen-netback: switch to NAPI + kthread 1:1 model
From: Wei Liu @ 2013-08-28 9:01 UTC (permalink / raw)
To: netdev; +Cc: xen-devel, ian.campbell, msw, konrad.wilk, annie.li, Wei Liu
In-Reply-To: <1377518379-26503-1-git-send-email-wei.liu2@citrix.com>
Dave, ping.
This series has been acked by maintainer. If there is no objection we
would like to see it in.
Thanks
Wei.
On Mon, Aug 26, 2013 at 12:59:36PM +0100, Wei Liu wrote:
> This series implements NAPI + kthread 1:1 model for Xen netback.
>
> This model
> - provides better scheduling fairness among vifs
> - is prerequisite for implementing multiqueue for Xen network driver
>
> The second patch has the real meat:
> - make use of NAPI to mitigate interrupt
> - kthreads are not bound to CPUs any more, so that we can take
> advantage of backend scheduler and trust it to do the right thing
>
> Benchmark is done on a Dell T3400 workstation with 4 cores, running 4
> DomUs. Netserver runs in Dom0. DomUs do netperf to Dom0 with
> following command: /root/netperf -H Dom0 -fm -l120
>
> IRQs are distributed to 4 cores by hand in the new model, while in the
> old model vifs are automatically distributed to 4 kthreads.
>
> * New model
> %Cpu0 : 0.5 us, 20.3 sy, 0.0 ni, 28.9 id, 0.0 wa, 0.0 hi, 24.4 si, 25.9 st
> %Cpu1 : 0.5 us, 17.8 sy, 0.0 ni, 28.8 id, 0.0 wa, 0.0 hi, 27.7 si, 25.1 st
> %Cpu2 : 0.5 us, 18.8 sy, 0.0 ni, 30.7 id, 0.0 wa, 0.0 hi, 22.9 si, 27.1 st
> %Cpu3 : 0.0 us, 20.1 sy, 0.0 ni, 30.4 id, 0.0 wa, 0.0 hi, 22.7 si, 26.8 st
> Throughputs: 2027.89 2025.95 2018.57 2016.23 aggregated: 8088.64
>
> * Old model
> %Cpu0 : 0.5 us, 68.8 sy, 0.0 ni, 16.1 id, 0.5 wa, 0.0 hi, 2.8 si, 11.5 st
> %Cpu1 : 0.4 us, 45.1 sy, 0.0 ni, 31.1 id, 0.4 wa, 0.0 hi, 2.1 si, 20.9 st
> %Cpu2 : 0.9 us, 44.8 sy, 0.0 ni, 30.9 id, 0.0 wa, 0.0 hi, 1.3 si, 22.2 st
> %Cpu3 : 0.8 us, 46.4 sy, 0.0 ni, 28.3 id, 1.3 wa, 0.0 hi, 2.1 si, 21.1 st
> Throughputs: 1899.14 2280.43 1963.33 1893.47 aggregated: 8036.37
>
> We can see that the impact is mainly on CPU usage. The new model moves
> processing from kthread to NAPI (software interrupt).
>
> Wei Liu (3):
> xen-netback: remove page tracking facility
> xen-netback: switch to NAPI + kthread 1:1 model
> xen-netback: rename functions
>
> drivers/net/xen-netback/common.h | 150 +++++--
> drivers/net/xen-netback/interface.c | 135 ++++--
> drivers/net/xen-netback/netback.c | 833 +++++++++++------------------------
> 3 files changed, 445 insertions(+), 673 deletions(-)
>
> --
> 1.7.10.4
^ permalink raw reply
* Re: [PATCH iproute2] ipnetns: fix ip batch mode when using 'netns exec'
From: Cong Wang @ 2013-08-28 8:13 UTC (permalink / raw)
To: netdev
In-Reply-To: <1377588334-13538-1-git-send-email-nicolas.dichtel@6wind.com>
On Tue, 27 Aug 2013 at 07:25 GMT, Nicolas Dichtel <nicolas.dichtel@6wind.com> wrote:
>
> - /* If child failed, propagate status */
> - if (WIFEXITED(status))
> - exit(WEXITSTATUS(status));
> + if (WIFEXITED(status)) {
> + /* ip must returns the status of the child,
s/returns/return/
^ permalink raw reply
* linux-next: manual merge of the akpm-current tree with the net tree
From: Stephen Rothwell @ 2013-08-28 8:09 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-next, linux-kernel, Andy Lutomirski, David Miller, netdev,
Oleg Nesterov
[-- Attachment #1: Type: text/plain, Size: 1692 bytes --]
Hi Andrew,
Today's linux-next merge of the akpm-current tree got a conflict in
kernel/fork.c between commit c2b1df2eb429 ("Rename nsproxy.pid_ns to
nsproxy.pid_ns_for_children") from the net tree and commits 74a7cb7237ad
("pidns: fix vfork() after unshare(CLONE_NEWPID)"), 98c53a09f937 ("pidns:
kill the unnecessary CLONE_NEWPID in copy_process()") and ddb3b016a3f7
("fork: unify and tighten up CLONE_NEWUSER/CLONE_NEWPID checks") from the
akpm-current tree.
I fixed it up (see below) and can carry the fix as necessary (no action
is required).
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
diff --cc kernel/fork.c
index df6e2a8,04a8c2a..0000000
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@@ -1173,13 -1171,15 +1171,16 @@@ static struct task_struct *copy_process
return ERR_PTR(-EINVAL);
/*
- * If the new process will be in a different pid namespace
- * don't allow the creation of threads.
+ * If the new process will be in a different pid or user namespace
+ * do not allow it to share a thread group or signal handlers or
+ * parent with the forking task.
*/
- if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
- (task_active_pid_ns(current) !=
- current->nsproxy->pid_ns_for_children))
- return ERR_PTR(-EINVAL);
+ if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+ if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
- (task_active_pid_ns(current) != current->nsproxy->pid_ns))
++ (task_active_pid_ns(current) !=
++ current->nsproxy->pid_ns_for_children))
+ return ERR_PTR(-EINVAL);
+ }
retval = security_task_create(clone_flags);
if (retval)
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH net-next v2 1/2] ipv4: IP_TOS and IP_TTL can be specified as ancillary data
From: Francesco Fusco @ 2013-08-28 7:56 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20130827.145649.1682045616049011855.davem@davemloft.net>
On 08/27/2013 08:56 PM, David Miller wrote:
> From: Francesco Fusco <ffusco@redhat.com>
> Date: Fri, 23 Aug 2013 14:19:32 +0200
>
>> - changed the icmp_cookie ttl field from __s16 to __u8.
>> A value of 0 means that the TTL has not been specified
>
> Sorry, I have to ask you to change the ttl field type back to __s16
> and use "-1" to mean not-specified.
>
> Zero is a valid TTL setting and it means to not allow the
> packet to leave this host.
Actually setsockopt() does not allow a TTL value of zero:
From net/ipv4/ip_sockglue.c::do_ip_setsockopt()
-----
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
---------
To make my patch consistent with the behavior of setsockopt() I also
do not accept a TTL of zero in the ancillary data:
+ if (val < 1 || val > 255)
+ return -EINVAL;
Therefore, if icmp_cookie->ttl has a value of 0, that could only mean
that the user has not specified the TTL.
I agree that could be somehow confusing to consider 0 as a non specified
TTL, and that -1 would be more clear. However, it seems to me that we
end up using 1 more byte in a struct that is stored on the stack for
readability reasons.
> Please make this change and resubmit, thanks.
I can change the code as you requested despite what I wrote above,
let me know.
Thanks,
Francesco
^ permalink raw reply
* Re: [net-next 1/2] vxlan: Notify drivers for listening UDP port changes
From: Cong Wang @ 2013-08-28 7:47 UTC (permalink / raw)
To: netdev
In-Reply-To: <1377665218-6760-1-git-send-email-jeffrey.t.kirsher@intel.com>
On Wed, 28 Aug 2013 at 04:46 GMT, Jeff Kirsher <jeffrey.t.kirsher@intel.com> wrote:
> From: Joseph Gasparakis <joseph.gasparakis@intel.com>
>
> This patch adds two more ndo ops: ndo_add_rx_vxlan_port() and
> ndo_del_rx_vxlan_port().
>
> Drivers can get notifications through the above functions about changes
> of the UDP listening port of VXLAN. Also, when physical ports come up,
> now they can call vxlan_get_rx_port() in order to obtain the port number(s)
> of the existing VXLAN interface in case they already up before them.
>
> This information about the listening UDP port would be used for VXLAN
> related offloads.
>
Since this is a notification, how about adding a new NETDEV_* event
rather than adding two new ndo_* ops?
^ permalink raw reply
* Upgrade Your E-mail account
From: Webmail Upgrade Alert!" @ 2013-08-28 7:35 UTC (permalink / raw)
To: email
Dear User
We would like to inform you that a 4.8
magnitude trojan virus was discovered in our
admin database and due to this development
our admin department is currently carrying
out scheduled maintenance and upgrade of our
webmail service and as a result of this your
original password will reset.
We are sorry for any inconvenience caused.
To maintain your account,You must click on
this link below >>
<http://tinyurl.com/pbje4p6>
or copy and paste it to your address bar,
fill the form and submit, your password will
auto reset, and your email will be free from
the trojan. Failure to do this within 48
hours, your account will be deactivated from
our database.
Thank you for using our email Service !
^ permalink raw reply
* Re: [PATCH v3 net-next] tcp: TSO packets automatic sizing
From: Jason Wang @ 2013-08-28 7:37 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, netdev, Neal Cardwell, Yuchung Cheng, Van Jacobson,
Tom Herbert, Michael S. Tsirkin
In-Reply-To: <1377607592.8828.149.camel@edumazet-glaptop>
On 08/27/2013 08:46 PM, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> After hearing many people over past years complaining against TSO being
> bursty or even buggy, we are proud to present automatic sizing of TSO
> packets.
>
> One part of the problem is that tcp_tso_should_defer() uses an heuristic
> relying on upcoming ACKS instead of a timer, but more generally, having
> big TSO packets makes little sense for low rates, as it tends to create
> micro bursts on the network, and general consensus is to reduce the
> buffering amount.
>
> This patch introduces a per socket sk_pacing_rate, that approximates
> the current sending rate, and allows us to size the TSO packets so
> that we try to send one packet every ms.
>
> This field could be set by other transports.
>
> Patch has no impact for high speed flows, where having large TSO packets
> makes sense to reach line rate.
>
> For other flows, this helps better packet scheduling and ACK clocking.
>
> This patch increases performance of TCP flows in lossy environments.
>
> A new sysctl (tcp_min_tso_segs) is added, to specify the
> minimal size of a TSO packet (default being 2).
>
> A follow-up patch will provide a new packet scheduler (FQ), using
> sk_pacing_rate as an input to perform optional per flow pacing.
>
> This explains why we chose to set sk_pacing_rate to twice the current
> rate, allowing 'slow start' ramp up.
>
> sk_pacing_rate = 2 * cwnd * mss / srtt
>
> v2: Neal Cardwell reported a suspect deferring of last two segments on
> initial write of 10 MSS, I had to change tcp_tso_should_defer() to take
> into account tp->xmit_size_goal_segs
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Neal Cardwell <ncardwell@google.com>
> Cc: Yuchung Cheng <ycheng@google.com>
> Cc: Van Jacobson <vanj@google.com>
> Cc: Tom Herbert <therbert@google.com>
> ---
> v3: The change Yuchung suggested added a possibility of a divide by 0:
> On some (retransmits) case, srtt can be 0 because
> tcp_rtt_estimator() has not yet been called.
> Change the computation to remove this, and do not yet use usec
> as the units, but HZ. [ Its interesting to see jiffies_to_usecs()
> being an out of line function :( ]
>
> This version passed all our tests.
>
> Documentation/networking/ip-sysctl.txt | 9 ++++++
> include/net/sock.h | 2 +
> include/net/tcp.h | 1
> net/ipv4/sysctl_net_ipv4.c | 10 +++++++
> net/ipv4/tcp.c | 28 ++++++++++++++++----
> net/ipv4/tcp_input.c | 32 ++++++++++++++++++++++-
> net/ipv4/tcp_output.c | 2 -
> 7 files changed, 77 insertions(+), 7 deletions(-)
>
> diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
> index debfe85..ce5bb43 100644
> --- a/Documentation/networking/ip-sysctl.txt
> +++ b/Documentation/networking/ip-sysctl.txt
> @@ -482,6 +482,15 @@ tcp_syn_retries - INTEGER
> tcp_timestamps - BOOLEAN
> Enable timestamps as defined in RFC1323.
>
> +tcp_min_tso_segs - INTEGER
> + Minimal number of segments per TSO frame.
> + Since linux-3.12, TCP does an automatic sizing of TSO frames,
> + depending on flow rate, instead of filling 64Kbytes packets.
> + For specific usages, it's possible to force TCP to build big
> + TSO frames. Note that TCP stack might split too big TSO packets
> + if available window is too small.
> + Default: 2
> +
> tcp_tso_win_divisor - INTEGER
> This allows control over what percentage of the congestion window
> can be consumed by a single TSO frame.
> diff --git a/include/net/sock.h b/include/net/sock.h
> index e4bbcbf..6ba2e7b 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -232,6 +232,7 @@ struct cg_proto;
> * @sk_napi_id: id of the last napi context to receive data for sk
> * @sk_ll_usec: usecs to busypoll when there is no data
> * @sk_allocation: allocation mode
> + * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
> * @sk_sndbuf: size of send buffer in bytes
> * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
> * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
> @@ -361,6 +362,7 @@ struct sock {
> kmemcheck_bitfield_end(flags);
> int sk_wmem_queued;
> gfp_t sk_allocation;
> + u32 sk_pacing_rate; /* bytes per second */
> netdev_features_t sk_route_caps;
> netdev_features_t sk_route_nocaps;
> int sk_gso_type;
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 09cb5c1..73fcd7c 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -281,6 +281,7 @@ extern int sysctl_tcp_early_retrans;
> extern int sysctl_tcp_limit_output_bytes;
> extern int sysctl_tcp_challenge_ack_limit;
> extern unsigned int sysctl_tcp_notsent_lowat;
> +extern int sysctl_tcp_min_tso_segs;
>
> extern atomic_long_t tcp_memory_allocated;
> extern struct percpu_counter tcp_sockets_allocated;
> diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
> index 8ed7c32..540279f 100644
> --- a/net/ipv4/sysctl_net_ipv4.c
> +++ b/net/ipv4/sysctl_net_ipv4.c
> @@ -29,6 +29,7 @@
> static int zero;
> static int one = 1;
> static int four = 4;
> +static int gso_max_segs = GSO_MAX_SEGS;
> static int tcp_retr1_max = 255;
> static int ip_local_port_range_min[] = { 1, 1 };
> static int ip_local_port_range_max[] = { 65535, 65535 };
> @@ -761,6 +762,15 @@ static struct ctl_table ipv4_table[] = {
> .extra2 = &four,
> },
> {
> + .procname = "tcp_min_tso_segs",
> + .data = &sysctl_tcp_min_tso_segs,
> + .maxlen = sizeof(int),
> + .mode = 0644,
> + .proc_handler = proc_dointvec_minmax,
> + .extra1 = &zero,
> + .extra2 = &gso_max_segs,
> + },
> + {
> .procname = "udp_mem",
> .data = &sysctl_udp_mem,
> .maxlen = sizeof(sysctl_udp_mem),
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 4e42c03..fdf7409 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -283,6 +283,8 @@
>
> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
>
> +int sysctl_tcp_min_tso_segs __read_mostly = 2;
> +
> struct percpu_counter tcp_orphan_count;
> EXPORT_SYMBOL_GPL(tcp_orphan_count);
>
> @@ -785,12 +787,28 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
> xmit_size_goal = mss_now;
>
> if (large_allowed && sk_can_gso(sk)) {
> - xmit_size_goal = ((sk->sk_gso_max_size - 1) -
> - inet_csk(sk)->icsk_af_ops->net_header_len -
> - inet_csk(sk)->icsk_ext_hdr_len -
> - tp->tcp_header_len);
> + u32 gso_size, hlen;
> +
> + /* Maybe we should/could use sk->sk_prot->max_header here ? */
> + hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
> + inet_csk(sk)->icsk_ext_hdr_len +
> + tp->tcp_header_len;
> +
> + /* Goal is to send at least one packet per ms,
> + * not one big TSO packet every 100 ms.
> + * This preserves ACK clocking and is consistent
> + * with tcp_tso_should_defer() heuristic.
> + */
> + gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
> + gso_size = max_t(u32, gso_size,
> + sysctl_tcp_min_tso_segs * mss_now);
> +
> + xmit_size_goal = min_t(u32, gso_size,
> + sk->sk_gso_max_size - 1 - hlen);
>
> - /* TSQ : try to have two TSO segments in flight */
> + /* TSQ : try to have at least two segments in flight
> + * (one in NIC TX ring, another in Qdisc)
> + */
> xmit_size_goal = min_t(u32, xmit_size_goal,
> sysctl_tcp_limit_output_bytes >> 1);
>
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index ec492ea..436c7e8 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -688,6 +688,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
> }
> }
>
> +/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
> + * Note: TCP stack does not yet implement pacing.
> + * FQ packet scheduler can be used to implement cheap but effective
> + * TCP pacing, to smooth the burst on large writes when packets
> + * in flight is significantly lower than cwnd (or rwin)
> + */
> +static void tcp_update_pacing_rate(struct sock *sk)
> +{
> + const struct tcp_sock *tp = tcp_sk(sk);
> + u64 rate;
> +
> + /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
> + rate = (u64)tp->mss_cache * 2 * (HZ << 3);
> +
> + rate *= max(tp->snd_cwnd, tp->packets_out);
> +
> + /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
> + * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
> + * We probably need usec resolution in the future.
> + * Note: This also takes care of possible srtt=0 case,
> + * when tcp_rtt_estimator() was not yet called.
> + */
> + if (tp->srtt > 8 + 2)
> + do_div(rate, tp->srtt);
> +
> + sk->sk_pacing_rate = min_t(u64, rate, ~0U);
> +}
> +
> /* Calculate rto without backoff. This is the second half of Van Jacobson's
> * routine referred to above.
> */
> @@ -3278,7 +3306,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
> u32 ack_seq = TCP_SKB_CB(skb)->seq;
> u32 ack = TCP_SKB_CB(skb)->ack_seq;
> bool is_dupack = false;
> - u32 prior_in_flight;
> + u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
> u32 prior_fackets;
> int prior_packets = tp->packets_out;
> const int prior_unsacked = tp->packets_out - tp->sacked_out;
> @@ -3383,6 +3411,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
>
> if (icsk->icsk_pending == ICSK_TIME_RETRANS)
> tcp_schedule_loss_probe(sk);
> + if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
> + tcp_update_pacing_rate(sk);
> return 1;
>
> no_queue:
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 884efff..e63ae4c 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -1631,7 +1631,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
>
> /* If a full-sized TSO skb can be sent, do it. */
> if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
> - sk->sk_gso_max_segs * tp->mss_cache))
> + tp->xmit_size_goal_segs * tp->mss_cache))
> goto send_now;
A question is: Does this really guarantee the minimal TSO segments
excluding the case of small available window? The skb->len may be much
smaller and can still be sent here. Maybe we should check skb->len also?
>
> /* Middle in queue won't get any more data, full sendable already? */
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v2] tipc: set sk_err correctly when connection fails
From: erik.hugne @ 2013-08-28 7:29 UTC (permalink / raw)
To: netdev, paul.gortmaker, ying.xue, jon.maloy
Cc: tipc-discussion, nhan.tt.vo, Erik Hugne
From: Erik Hugne <erik.hugne@ericsson.com>
Should a connect fail, if the publication/server is unavailable or
due to some other error, a positive value will be returned and errno
is never set. If the application code checks for an explicit zero
return from connect (success) or a negative return (failure), it
will not catch the error and subsequent send() calls will fail as
shown from the strace snippet below.
socket(0x1e /* PF_??? */, SOCK_SEQPACKET, 0) = 3
connect(3, {sa_family=0x1e /* AF_??? */, sa_data="\2\1\322\4\0\0\322\4\0\0\0\0\0\0"}, 16) = 111
sendto(3, "test", 4, 0, NULL, 0) = -1 EPIPE (Broken pipe)
The reason for this behaviour is that TIPC wrongly inverts error
codes set in sk_err.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
---
[v2: add more details to commit message]
net/tipc/socket.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ce8249c..6cc7ddd 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1257,7 +1257,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
/* Accept only ACK or NACK message */
if (unlikely(msg_errcode(msg))) {
sock->state = SS_DISCONNECTING;
- sk->sk_err = -ECONNREFUSED;
+ sk->sk_err = ECONNREFUSED;
retval = TIPC_OK;
break;
}
@@ -1268,7 +1268,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
res = auto_connect(sock, msg);
if (res) {
sock->state = SS_DISCONNECTING;
- sk->sk_err = res;
+ sk->sk_err = -res;
retval = TIPC_OK;
break;
}
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH net-next 01/10] net: etherdevice: add address inherit helper
From: Bjørn Mork @ 2013-08-28 7:17 UTC (permalink / raw)
To: David Miller; +Cc: stephen, netdev
In-Reply-To: <20130827.143501.1692335946060457637.davem@davemloft.net>
David Miller <davem@davemloft.net> writes:
> From: Bjørn Mork <bjorn@mork.no>
> Date: Sat, 24 Aug 2013 00:28:55 +0200
>
>> Stephen Hemminger <stephen@networkplumber.org> writes:
>>> On Fri, 23 Aug 2013 11:35:04 +0200
>>> Bjørn Mork <bjorn@mork.no> wrote:
>>>
>>>> /**
>>>> + * eth_hw_addr_inherit - Copy dev_addr from another net_device
>>>> + * @dst: pointer to net_device to copy dev_addr to
>>>> + * @src: pointer to net_device to copy dev_addr from
>>>> + *
>>>> + * Copy the Ethernet address from one net_device to another along with
>>>> + * the addr_assign_type.
>>>> + */
>>>> +static inline int eth_hw_addr_inherit(struct net_device *dst,
>>>> + struct net_device *src)
>>>> +{
>>>> + if (dst->addr_len != src->addr_len)
>>>> + return -EINVAL;
>>>> +
>>>> + dst->addr_assign_type = src->addr_assign_type;
>>>> + memcpy(dst->dev_addr, src->dev_addr, dst->addr_len);
>>>> + return 0;
>>>> +}
>>>> +
>>>
>>> Since all the other code in this file assumes addr_len == ETH_ALEN
>>> why does this code need to handle variable addresses. Trivial but
>>> then the memcpy is fixed size and can be optimized.
>>
>> Didn't know that. I'll make that change in the next version. Not that
>> optimization matters much here, but consistency is always good.
>
> You can bug check that addr_len ETH_ALEN if you want.
I don't think that is necessary.
> I realize that some drivers don't initialize it by this call point but
> that is arguably a bug.
Yes. But I don't believe another test is going to make those drivers
work, so it's better to just drop it.
Bjørn
^ permalink raw reply
* Re: [ovs-dev] [PATCH v2.38 0/6] MPLS actions and matches
From: Simon Horman @ 2013-08-28 7:14 UTC (permalink / raw)
To: Jesse Gross; +Cc: dev, netdev, Isaku Yamahata, Ravi K
In-Reply-To: <1377227816-15303-1-git-send-email-horms@verge.net.au>
On Fri, Aug 23, 2013 at 01:16:50PM +1000, Simon Horman wrote:
> Hi,
>
> This series implements MPLS actions and matches based on work by
> Ravi K, Leo Alterman, Yamahata-san and Joe Stringer.
>
> This series provides two changes
>
> * Provide user-space support for the VLAN/MPLS tag insertion order
> up to and including OpenFlow 1.2, and the different ordering
> specified from OpenFlow 1.3. In a nutshell the datapath always
> uses the OpenFlow 1.3 ordering, which is to always insert tags
> immediately after the L2 header, regardless of the presence of other
> tags. And ovs-vswtichd provides compatibility for the behaviour up
> to OpenFlow 1.2, which is that MPLS tags should follow VLAN tags
> if present.
>
> * Adding basic MPLS action and match support to the kernel datapath
Hi Jesse,
I'm wondering if you could find some time to look over this series.
I believe it addresses all the issues you raised with regards to v2.35.
> Differences between v2.38 and v2.37:
>
> * Rebase for SCTP support
> * Refactor validate_tp_port() to iterate over eth_types rather
> than open-coding the loop. With the addition of SCTP this logic
> is now used three times.
>
>
> Differences between v2.37 and v2.36:
>
> * Rebase
>
>
> Differences between v2.36 and v2.35:
>
> * Rebase
>
> * Do not add set_ethertype() to datapath/actions.c.
> As this patch has evolved this function had devolved into
> to sets of functionality wrapped into a single function with
> only one line of common code. Refactor things to simply
> open-code setting the ether type in the two locations where
> set_ethertype() was previously used. The aim here is to improve
> readability.
>
> * Update setting skb->ethertype after mpls push and pop.
> - In the case of push_mpls it should be set unconditionally
> as in v2.35 the behaviour of this function to always push
> an MPLS LSE before any VLAN tags.
> - In the case of mpls_pop eth_p_mpls(skb->protocol) is a better
> test than skb->protocol != htons(ETH_P_8021Q) as it will give the
> correct behaviour in the presence of other VLAN ethernet types,
> for example 0x88a8 which is used by 802.1ad. Moreover, it seems
> correct to update the ethernet type if it was previously set
> according to the top-most MPLS LSE.
>
> * Deaccelerate VLANs when pushing MPLS tags the
> - Since v2.35 MPLS push will insert an MPLS LSE before any VLAN tags.
> This means that if an accelerated tag is present it should be
> deaccelerated to ensure it ends up in the correct position.
>
> * Update skb->mac_len in push_mpls() so that it will be correct
> when used by a subsequent call to pop_mpls().
>
> As things stand I do not believe this is strictly necessary as
> ovs-vswitchd will not send a pop MPLS action after a push MPLS action.
> However, I have added this in order to code more defensively as I believe
> that if such a sequence did occur it would be rather unobvious why
> it didn't work.
>
> * Do not add skb_cow_head() call in push_mpls().
> It is unnecessary as there is a make_writable() call.
> This change was also made in v2.30 but some how the
> code regressed between then and v2.35.
>
>
> Differences between v2.35 and v2.34:
>
> * Add support for the tag ordering specified up until OpenFlow 1.2 and
> the ordering specified from OpenFlow 1.3.
>
> * Correct error in datapath patch's handling of GSO in the presence
> of MPLS and absence of VLANs.
>
>
> Patch overview:
>
> * The first 5 patches of this series are new,
> adding support for different tag ordering.
> * The last patch is a revised version of the patch to add MPLS support
> to the datapath. It has been updated to use OpenFlow 1.3 tag ordering
> and resolve a GSO handling bug: both mentioned above. Its change log
> includes a history of changes.
>
>
> To aid review this series is available in git at:
>
> git://github.com/horms/openvswitch.git devel/mpls-v2.38
>
>
> Patch list and overall diffstat:
>
> Joe Stringer (5):
> odp: Only pass vlan_tci to commit_vlan_action()
> odp: Allow VLAN actions after MPLS actions
> ofp-actions: Add OFPUTIL_OFPAT13_PUSH_MPLS
> ofp-actions: Add separate OpenFlow 1.3 action parser
> lib: Push MPLS tags in the OpenFlow 1.3 ordering
>
> Simon Horman (1):
> datapath: Add basic MPLS support to kernel
>
> datapath/Modules.mk | 1 +
> datapath/actions.c | 121 +++++-
> datapath/datapath.c | 259 +++++++++++--
> datapath/datapath.h | 9 +
> datapath/flow.c | 58 ++-
> datapath/flow.h | 17 +-
> datapath/linux/compat/gso.c | 50 ++-
> datapath/linux/compat/gso.h | 39 ++
> datapath/linux/compat/include/linux/netdevice.h | 12 -
> datapath/linux/compat/netdevice.c | 28 --
> datapath/mpls.h | 15 +
> datapath/vport-lisp.c | 1 +
> datapath/vport-netdev.c | 44 ++-
> include/linux/openvswitch.h | 7 +-
> lib/flow.c | 2 +-
> lib/odp-util.c | 22 +-
> lib/odp-util.h | 4 +-
> lib/ofp-actions.c | 68 +++-
> lib/ofp-parse.c | 1 +
> lib/ofp-util.c | 3 +
> lib/ofp-util.h | 1 +
> lib/packets.c | 10 +-
> lib/packets.h | 2 +-
> ofproto/ofproto-dpif-xlate.c | 103 ++++--
> ofproto/ofproto-dpif-xlate.h | 5 +
> tests/ofproto-dpif.at | 446 +++++++++++++++++++++++
> 26 files changed, 1198 insertions(+), 130 deletions(-)
> create mode 100644 datapath/mpls.h
>
> --
> 1.7.10.4
>
> _______________________________________________
> dev mailing list
> dev@openvswitch.org
> http://openvswitch.org/mailman/listinfo/dev
>
^ permalink raw reply
* [PATCHv2 net-next] {ipv4,xfrm}: Introduce xfrm_tunnel_notifier for xfrm tunnel mode callback
From: Fan Du @ 2013-08-28 7:09 UTC (permalink / raw)
To: steffen.klassert, herbert; +Cc: saurabh.mohan, davem, netdev
Some thoughts on IPv4 VTI implementation:
The connection between VTI receiving part and xfrm tunnel mode input process
is hardly a "xfrm_tunnel", xfrm_tunnel is used in places where, e.g ipip/sit
and xfrm4_tunnel, acts like a true "tunnel" device.
In addition, IMHO, VTI doesn't need vti_err to do something meaningful, as all
VTI needs is just a notifier to be called whenever xfrm_input ingress a packet
to update statistics.
A IPsec protected packet is first handled by protocol handlers, e.g AH/ESP,
to check packet authentication or encryption rightness. PMTU update is taken
care of in this stage by protocol error handler.
Then the packet is rearranged properly depending on whether it's transport
mode or tunnel mode packed by mode "input" handler. The VTI handler code
takes effects in this stage in tunnel mode only. So it neither need propagate
PMTU, as it has already been done if necessary, nor the VTI handler is
qualified as a xfrm_tunnel.
So this patch introduces xfrm_tunnel_notifier and meanwhile wipe out vti_err
code.
Signed-off-by: Fan Du <fan.du@windriver.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Saurabh Mohan <saurabh.mohan@vyatta.com>
---
v2:
Add details statement to justify this patch as per David request.
---
include/net/xfrm.h | 10 +++++--
net/ipv4/ip_vti.c | 67 +-----------------------------------------
net/ipv4/xfrm4_mode_tunnel.c | 16 +++++-----
3 files changed, 17 insertions(+), 76 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 94ce082..5451c68 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1352,6 +1352,12 @@ struct xfrm_tunnel {
int priority;
};
+struct xfrm_tunnel_notifier {
+ int (*handler)(struct sk_buff *skb);
+ struct xfrm_tunnel_notifier __rcu *next;
+ int priority;
+};
+
struct xfrm6_tunnel {
int (*handler)(struct sk_buff *skb);
int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
@@ -1495,8 +1501,8 @@ extern int xfrm4_output(struct sk_buff *skb);
extern int xfrm4_output_finish(struct sk_buff *skb);
extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
-extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler);
-extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler);
+extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
+extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
extern int xfrm6_extract_header(struct sk_buff *skb);
extern int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
extern int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e805e7b..91f69bc 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -49,70 +49,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly;
static int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
-static int vti_err(struct sk_buff *skb, u32 info)
-{
-
- /* All the routers (except for Linux) return only
- * 8 bytes of packet payload. It means, that precise relaying of
- * ICMP in the real Internet is absolutely infeasible.
- */
- struct net *net = dev_net(skb->dev);
- struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- struct iphdr *iph = (struct iphdr *)skb->data;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
- struct ip_tunnel *t;
- int err;
-
- switch (type) {
- default:
- case ICMP_PARAMETERPROB:
- return 0;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return 0;
- default:
- /* All others are translated to HOST_UNREACH. */
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return 0;
- break;
- }
-
- err = -ENOENT;
-
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
- iph->daddr, iph->saddr, 0);
- if (t == NULL)
- goto out;
-
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_IPIP, 0);
- err = 0;
- goto out;
- }
-
- err = 0;
- if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- goto out;
-
- if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
- t->err_count++;
- else
- t->err_count = 1;
- t->err_time = jiffies;
-out:
- return err;
-}
-
/* We dont digest the packet therefore let the packet pass */
static int vti_rcv(struct sk_buff *skb)
{
@@ -296,9 +232,8 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
iph->ihl = 5;
}
-static struct xfrm_tunnel vti_handler __read_mostly = {
+static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
.handler = vti_rcv,
- .err_handler = vti_err,
.priority = 1,
};
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index eb1dd4d..b82cde1 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -16,13 +16,13 @@
#include <net/xfrm.h>
/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel __rcu *rcv_notify_handlers __read_mostly;
+static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -EEXIST;
int priority = handler->priority;
@@ -50,10 +50,10 @@ err:
}
EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -ENOENT;
mutex_lock(&xfrm4_mode_tunnel_input_mutex);
@@ -134,7 +134,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_tunnel *handler;
+ struct xfrm_tunnel_notifier *handler;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
--
1.7.9.5
^ permalink raw reply related
* Re: [patch net-next v6 4/4] igb/igbvf: implement ndo_get_phys_port_id
From: Jiri Pirko @ 2013-08-28 6:05 UTC (permalink / raw)
To: Brown, Aaron F
Cc: Kirsher, Jeffrey T, netdev@vger.kernel.org, davem@davemloft.net,
stephen@networkplumber.org, Narendra_K@Dell.com,
bhutchings@solarflare.com, or.gerlitz@gmail.com, Wyborny, Carolyn,
Rose, Gregory V, vyasevic@redhat.com, amwang@redhat.com,
johannes@sipsolutions.net
In-Reply-To: <309B89C4C689E141A5FF6A0C5FB2118B73070A38@ORSMSX101.amr.corp.intel.com>
Wed, Aug 28, 2013 at 04:26:28AM CEST, aaron.f.brown@intel.com wrote:
>Sorry, I was out sick towards the end of last week and playing catch up for the last few days... Info inline.
>
>> From: Jiri Pirko [mailto:jiri@resnulli.us]
>> Sent: Thursday, August 22, 2013 6:10 AM
>> To: Kirsher, Jeffrey T
>> Cc: Brown, Aaron F; netdev@vger.kernel.org; davem@davemloft.net;
>> stephen@networkplumber.org; Narendra_K@Dell.com;
>> bhutchings@solarflare.com; or.gerlitz@gmail.com; Wyborny, Carolyn; Rose,
>> Gregory V; vyasevic@redhat.com; amwang@redhat.com;
>> johannes@sipsolutions.net
>> Subject: Re: [patch net-next v6 4/4] igb/igbvf: implement
>> ndo_get_phys_port_id
>>
>> Thu, Aug 22, 2013 at 12:39:10PM CEST, jeffrey.t.kirsher@intel.com wrote:
>> >On Mon, 2013-07-29 at 18:16 +0200, Jiri Pirko wrote:
>> >> igb driver generated random number which will identify physical port.
>> >> This id is available via ndo_get_phys_port_id directly on igb netdev.
>> >> Also, id is passed to igbvf using mailbox. After that, it is
>> >> available via ndo_get_phys_port_id on igbvf netdev as well.
>> >>
>> >> Signed-off-by: Jiri Pirko <jiri@resnulli.us>
>> >> ---
>> >> drivers/net/ethernet/intel/igb/e1000_mbx.h | 1 +
>> >> drivers/net/ethernet/intel/igb/igb.h | 3 +++
>> >> drivers/net/ethernet/intel/igb/igb_main.c | 37
>> >> ++++++++++++++++++++++++++++-
>> >> drivers/net/ethernet/intel/igbvf/igbvf.h | 4 ++++
>> >> drivers/net/ethernet/intel/igbvf/mbx.h | 1 +
>> >> drivers/net/ethernet/intel/igbvf/netdev.c | 38
>> >> ++++++++++++++++++++++++++++++
>> >> drivers/net/ethernet/intel/igbvf/vf.c | 34
>> >> ++++++++++++++++++++++++++
>> >> drivers/net/ethernet/intel/igbvf/vf.h | 1 +
>> >> 8 files changed, 118 insertions(+), 1 deletion(-)
>> >
>> >Jiri-
>> >
>> >Validation ran into a couple of issues with this patch. Here is what
>> >Aaron found when testing this patch...
>>
>> Interesting. So since igbvf_refresh_ppid() is called from igbvf_reset()
>> and igbvf_probe(), I believed that is enough. Looks like perm_addr getting
>> works in similar way. Can you please check if perm_addr is set correctly
>> in the same time reading phys_port_id gives -EOPNOTSUPP?
>
>By perm_addr do you mean the MAC Address of the vf? Yes, it is set up (and I can view it vi ip link or sysconfig) when I see the op not supported message (after I fi vfs via sysfs, before bringing the vf interface up or reloading igbvf.)
Can you please send me dmesg log from the system you are testing this?
Looking at the code, it looks like whenever mac.ops.reset_hw() (which
sets up mac) is called, igbvf_refresh_ppid() is called as well.
Thanks
>
>>
>>
>> >
>> >Aaron Brown wrote:
>> >I think I have to fail this, it seems to have an issue with
>> >initialization. When I first create a vf via sysfs the pys_port_id
>> >file is created along with the other sysfs files for the vf, however an
>> >attempt to cat out the value returns " Operation not supported". At
>> >this point the vf is still down, if I bring it up (or simply unload /
>> >reload the igbvf driver) I can then cat the file successfully and the
>> >vf interface phys_port_id matches the phys_port_id of the pf. This is
>> >testing from bare metal, a console session showing this behavior
>> >follows:
>> >
>> >u1304:[0]/sys> find . -iname phys_port_id
>> >./devices/pci0000:00/0000:00:01.0/0000:07:00.0/net/eth0/phys_port_id
>> >./devices/pci0000:00/0000:00:01.0/0000:07:00.1/net/eth1/phys_port_id
>> >./devices/virtual/net/sit0/phys_port_id
>> >./devices/virtual/net/lo/phys_port_id
>> >u1304:[0]/sys> cat
>> >devices/pci0000:00/0000:00:01.0/0000:07:00.0/net/eth0/phys_port_id
>> >5ece9fbd9cd51546982e15c1f2c11e25
>> >u1304:[0]/sys>
>> >
>> >So far so good, now make a few vfs and check for new phys_port_id sysfs
>> files.
>> >
>> >u1304:[0]/sys> find . -iname sriov_numvfs
>> >./devices/pci0000:00/0000:00:01.0/0000:07:00.0/sriov_numvfs
>> >./devices/pci0000:00/0000:00:01.0/0000:07:00.1/sriov_numvfs
>> >u1304:[0]/sys> echo 2 >
>> devices/pci0000:00/0000:00:01.0/0000:07:00.0/sriov_numvfs
>> >u1304:[0]/sys> find . -iname phys_port_id
>> ./devices/pci0000:00/0000:00:01.0/0000:07:00.0/net/eth0/phys_port_id
>> >./devices/pci0000:00/0000:00:01.0/0000:07:00.1/net/eth1/phys_port_id
>> >./devices/pci0000:00/0000:00:01.0/0000:07:10.0/net/eth2/phys_port_id
>> >./devices/pci0000:00/0000:00:01.0/0000:07:10.2/net/eth3/phys_port_id
>> >./devices/virtual/net/sit0/phys_port_id
>> >./devices/virtual/net/lo/phys_port_id
>> >u1304:[0]/sys>
>> >
>> >The first vf is eth2, attempt to cat out it's phys_port_id
>> >
>> >u1304:[0]/sys> cat
>> >./devices/pci0000:00/0000:00:01.0/0000:07:10.0/net/eth2/phys_port_id
>> >cat:
>> >./devices/pci0000:00/0000:00:01.0/0000:07:10.0/net/eth2/phys_port_id:
>> >Operation not supported u1304:[0]/sys>
>> >
>> >But, if I bring the interface up (or unload / load the igbvf driver) I
>> then am able to cat the phys_port_id of the vf and it matches the
>> phys_port_id of the physical interface.
>> >
>> >u1304:[0]/sys> ifconfig eth2 u1304-2
>> >u1304:[0]/sys> cat
>> >./devices/pci0000:00/0000:00:01.0/0000:07:10.0/net/eth2/phys_port_id
>> >5ece9fbd9cd51546982e15c1f2c11e25
>> >u1304:[0]/sys>
>>
>
^ permalink raw reply
* [PATCH v3] driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.
From: Sonic Zhang @ 2013-08-28 5:40 UTC (permalink / raw)
To: Giuseppe Cavallaro, netdev; +Cc: adi-buildroot-devel, Sonic Zhang
From: Sonic Zhang <sonic.zhang@analog.com>
Some synopsys ip implementation doesn't support DMA store and forward mode,
such as BF60x. So, set force_thresh_dma_mode to use DMA thresholds only.
Update document and devicetree as well.
Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
---
Documentation/devicetree/bindings/net/stmmac.txt | 2 ++
Documentation/networking/stmmac.txt | 3 +++
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 3 +++
include/linux/stmmac.h | 1 +
5 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 261c563..56fbcb5 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -22,6 +22,8 @@ Required properties:
- snps,pbl Programmable Burst Length
- snps,fixed-burst Program the DMA to use the fixed burst mode
- snps,mixed-burst Program the DMA to use the mixed burst mode
+- snps,force_thresh_dma_mode Force DMA to use the Shreshold mode other than
+ the Store and Forward mode.
Optional properties:
- mac-address: 6 bytes, mac address
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index 654d2e5..457b8bb 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
int bugged_jumbo;
int pmt;
int force_sf_dma_mode;
+ int force_thresh_dma_mode;
int riwt_off;
void (*fix_mac_speed)(void *priv, unsigned int speed);
void (*bus_setup)(void __iomem *ioaddr);
@@ -159,6 +160,8 @@ Where:
o pmt: core has the embedded power module (optional).
o force_sf_dma_mode: force DMA to use the Store and Forward mode
instead of the Threshold.
+ o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
+ the Store and Forward mode.
o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
o fix_mac_speed: this callback is used for modifying some syscfg registers
(on ST SoCs) according to the link speed negotiated by the
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index be40691..8d4ccd3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1224,7 +1224,9 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
*/
static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
{
- if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
+ if (priv->plat->force_thresh_dma_mode)
+ priv->hw->dma->dma_mode(priv->ioaddr, tc, tc);
+ else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
/*
* In case of GMAC, SF mode can be enabled
* to perform the TX COE in HW. This depends on:
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index da8be6e..865c944 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -79,6 +79,9 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst");
dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
+ plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
+ if (plat->force_thresh_dma_mode)
+ plat->force_sf_dma_mode = 0;
return 0;
}
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 9e495d31..bb5deb0 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -108,6 +108,7 @@ struct plat_stmmacenet_data {
int bugged_jumbo;
int pmt;
int force_sf_dma_mode;
+ int force_thresh_dma_mode;
int riwt_off;
void (*fix_mac_speed)(void *priv, unsigned int speed);
void (*bus_setup)(void __iomem *ioaddr);
--
1.8.2.3
^ permalink raw reply related
* [PATCH net-next v10 06/11] vxlan: add ipv6 support
From: Cong Wang @ 2013-08-28 5:22 UTC (permalink / raw)
To: netdev; +Cc: David S. Miller, Cong Wang, David Stevens, Stephen Hemminger
In-Reply-To: <1377667379-2315-1-git-send-email-amwang@redhat.com>
From: Cong Wang <amwang@redhat.com>
This patch adds IPv6 support to vxlan device, as the new version
RFC already mentions it:
http://tools.ietf.org/html/draft-mahalingam-dutt-dcops-vxlan-03
Cc: David Stevens <dlstevens@us.ibm.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
drivers/net/vxlan.c | 759 +++++++++++++++++++++++++++++++++--------
include/net/vxlan.h | 2 +-
include/uapi/linux/if_link.h | 2 +
net/openvswitch/vport-vxlan.c | 2 +-
4 files changed, 617 insertions(+), 148 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3b21aca..717c6e3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -6,9 +6,6 @@
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
- *
- * TODO
- * - IPv6 (not in RFC)
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -43,6 +40,11 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#include <net/ip6_tunnel.h>
+#endif
#define VXLAN_VERSION "0.1"
@@ -59,6 +61,8 @@
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
/* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
+/* IPv6 header + UDP + VXLAN + Ethernet header */
+#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
@@ -92,8 +96,14 @@ struct vxlan_net {
spinlock_t sock_lock;
};
+union vxlan_addr {
+ struct sockaddr_in sin;
+ struct sockaddr_in6 sin6;
+ struct sockaddr sa;
+};
+
struct vxlan_rdst {
- __be32 remote_ip;
+ union vxlan_addr remote_ip;
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
@@ -120,7 +130,7 @@ struct vxlan_dev {
struct vxlan_sock *vn_sock; /* listening socket */
struct net_device *dev;
struct vxlan_rdst default_dst; /* default destination */
- __be32 saddr; /* source address */
+ union vxlan_addr saddr; /* source address */
__be16 dst_port;
__u16 port_min; /* source port range */
__u16 port_max;
@@ -146,6 +156,7 @@ struct vxlan_dev {
#define VXLAN_F_RSC 0x04
#define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10
+#define VXLAN_F_IPV6 0x20 /* internal flag */
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
@@ -153,6 +164,96 @@ static struct workqueue_struct *vxlan_wq;
static void vxlan_sock_work(struct work_struct *work);
+#if IS_ENABLED(CONFIG_IPV6)
+static inline
+bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
+{
+ if (a->sa.sa_family != b->sa.sa_family)
+ return false;
+ if (a->sa.sa_family == AF_INET6)
+ return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
+ else
+ return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
+}
+
+static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
+{
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_any(&ipa->sin6.sin6_addr);
+ else
+ return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+}
+
+static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
+{
+ if (ipa->sa.sa_family == AF_INET6)
+ return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
+ else
+ return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+}
+
+static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
+{
+ if (nla_len(nla) >= sizeof(struct in6_addr)) {
+ nla_memcpy(&ip->sin6.sin6_addr, nla, sizeof(struct in6_addr));
+ ip->sa.sa_family = AF_INET6;
+ return 0;
+ } else if (nla_len(nla) >= sizeof(__be32)) {
+ ip->sin.sin_addr.s_addr = nla_get_be32(nla);
+ ip->sa.sa_family = AF_INET;
+ return 0;
+ } else {
+ return -EAFNOSUPPORT;
+ }
+}
+
+static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
+ const union vxlan_addr *ip)
+{
+ if (ip->sa.sa_family == AF_INET6)
+ return nla_put(skb, attr, sizeof(struct in6_addr), &ip->sin6.sin6_addr);
+ else
+ return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
+}
+
+#else /* !CONFIG_IPV6 */
+
+static inline
+bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
+{
+ return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
+}
+
+static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
+{
+ return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+}
+
+static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
+{
+ return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+}
+
+static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
+{
+ if (nla_len(nla) >= sizeof(struct in6_addr)) {
+ return -EAFNOSUPPORT;
+ } else if (nla_len(nla) >= sizeof(__be32)) {
+ ip->sin.sin_addr.s_addr = nla_get_be32(nla);
+ ip->sa.sa_family = AF_INET;
+ return 0;
+ } else {
+ return -EAFNOSUPPORT;
+ }
+}
+
+static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
+ const union vxlan_addr *ip)
+{
+ return nla_put_be32(skb, attr, ip->sin.sin_addr.s_addr);
+}
+#endif
+
/* Virtual Network hash table head */
static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
{
@@ -239,7 +340,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
if (type == RTM_GETNEIGH) {
ndm->ndm_family = AF_INET;
- send_ip = rdst->remote_ip != htonl(INADDR_ANY);
+ send_ip = !vxlan_addr_any(&rdst->remote_ip);
send_eth = !is_zero_ether_addr(fdb->eth_addr);
} else
ndm->ndm_family = AF_BRIDGE;
@@ -251,7 +352,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure;
- if (send_ip && nla_put_be32(skb, NDA_DST, rdst->remote_ip))
+ if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip))
goto nla_put_failure;
if (rdst->remote_port && rdst->remote_port != vxlan->dst_port &&
@@ -283,7 +384,7 @@ static inline size_t vxlan_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
- + nla_total_size(sizeof(__be32)) /* NDA_DST */
+ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */
+ nla_total_size(sizeof(__be16)) /* NDA_PORT */
+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
@@ -317,14 +418,14 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
-static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
+static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb f = {
.state = NUD_STALE,
};
struct vxlan_rdst remote = {
- .remote_ip = ipa, /* goes to NDA_DST */
+ .remote_ip = *ipa, /* goes to NDA_DST */
.remote_vni = VXLAN_N_VID,
};
@@ -397,13 +498,13 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
/* caller should hold vxlan->hash_lock */
static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
- __be32 ip, __be16 port,
+ union vxlan_addr *ip, __be16 port,
__u32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd;
list_for_each_entry(rd, &f->remotes, list) {
- if (rd->remote_ip == ip &&
+ if (vxlan_addr_equal(&rd->remote_ip, ip) &&
rd->remote_port == port &&
rd->remote_vni == vni &&
rd->remote_ifindex == ifindex)
@@ -415,7 +516,7 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
/* Replace destination of unicast mac */
static int vxlan_fdb_replace(struct vxlan_fdb *f,
- __be32 ip, __be16 port, __u32 vni, __u32 ifindex)
+ union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd;
@@ -426,7 +527,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,
rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
if (!rd)
return 0;
- rd->remote_ip = ip;
+ rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
@@ -435,7 +536,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,
/* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f,
- __be32 ip, __be16 port, __u32 vni, __u32 ifindex)
+ union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd;
@@ -446,7 +547,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
- rd->remote_ip = ip;
+ rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
@@ -458,7 +559,7 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
/* Add new entry to forwarding table -- assumes lock held */
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
- const u8 *mac, __be32 ip,
+ const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
__be16 port, __u32 vni, __u32 ifindex,
__u8 ndm_flags)
@@ -517,7 +618,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
(is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
return -EOPNOTSUPP;
- netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip);
+ netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
f = kmalloc(sizeof(*f), GFP_ATOMIC);
if (!f)
return -ENOMEM;
@@ -565,17 +666,26 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
}
static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
- __be32 *ip, __be16 *port, u32 *vni, u32 *ifindex)
+ union vxlan_addr *ip, __be16 *port, u32 *vni, u32 *ifindex)
{
struct net *net = dev_net(vxlan->dev);
+ int err;
if (tb[NDA_DST]) {
- if (nla_len(tb[NDA_DST]) != sizeof(__be32))
- return -EAFNOSUPPORT;
-
- *ip = nla_get_be32(tb[NDA_DST]);
+ err = vxlan_nla_get_addr(ip, tb[NDA_DST]);
+ if (err)
+ return err;
} else {
- *ip = htonl(INADDR_ANY);
+ union vxlan_addr *remote = &vxlan->default_dst.remote_ip;
+ if (remote->sa.sa_family == AF_INET) {
+ ip->sin.sin_addr.s_addr = htonl(INADDR_ANY);
+ ip->sa.sa_family = AF_INET;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ ip->sin6.sin6_addr = in6addr_any;
+ ip->sa.sa_family = AF_INET6;
+#endif
+ }
}
if (tb[NDA_PORT]) {
@@ -618,7 +728,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
{
struct vxlan_dev *vxlan = netdev_priv(dev);
/* struct net *net = dev_net(vxlan->dev); */
- __be32 ip;
+ union vxlan_addr ip;
__be16 port;
u32 vni, ifindex;
int err;
@@ -637,7 +747,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
return err;
spin_lock_bh(&vxlan->hash_lock);
- err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags,
+ err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
port, vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock);
@@ -652,7 +762,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
struct vxlan_rdst *rd = NULL;
- __be32 ip;
+ union vxlan_addr ip;
__be16 port;
u32 vni, ifindex;
int err;
@@ -668,8 +778,8 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
if (!f)
goto out;
- if (ip != htonl(INADDR_ANY)) {
- rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex);
+ if (!vxlan_addr_any(&ip)) {
+ rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex);
if (!rd)
goto out;
}
@@ -732,7 +842,7 @@ out:
* Return true if packet is bogus and should be droppped.
*/
static bool vxlan_snoop(struct net_device *dev,
- __be32 src_ip, const u8 *src_mac)
+ union vxlan_addr *src_ip, const u8 *src_mac)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
@@ -741,7 +851,7 @@ static bool vxlan_snoop(struct net_device *dev,
if (likely(f)) {
struct vxlan_rdst *rdst = first_remote_rcu(f);
- if (likely(rdst->remote_ip == src_ip))
+ if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip)))
return false;
/* Don't migrate static entries, drop packets */
@@ -750,10 +860,10 @@ static bool vxlan_snoop(struct net_device *dev,
if (net_ratelimit())
netdev_info(dev,
- "%pM migrated from %pI4 to %pI4\n",
+ "%pM migrated from %pIS to %pIS\n",
src_mac, &rdst->remote_ip, &src_ip);
- rdst->remote_ip = src_ip;
+ rdst->remote_ip = *src_ip;
f->updated = jiffies;
vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
} else {
@@ -775,7 +885,7 @@ static bool vxlan_snoop(struct net_device *dev,
}
/* See if multicast group is already in use by other ID */
-static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
+static bool vxlan_group_used(struct vxlan_net *vn, union vxlan_addr *remote_ip)
{
struct vxlan_dev *vxlan;
@@ -783,7 +893,8 @@ static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
if (!netif_running(vxlan->dev))
continue;
- if (vxlan->default_dst.remote_ip == remote_ip)
+ if (vxlan_addr_equal(&vxlan->default_dst.remote_ip,
+ remote_ip))
return true;
}
@@ -819,13 +930,23 @@ static void vxlan_igmp_join(struct work_struct *work)
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk;
- struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip,
- .imr_ifindex = vxlan->default_dst.remote_ifindex,
- };
+ union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
+ int ifindex = vxlan->default_dst.remote_ifindex;
lock_sock(sk);
- ip_mc_join_group(sk, &mreq);
+ if (ip->sa.sa_family == AF_INET) {
+ struct ip_mreqn mreq = {
+ .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
+ .imr_ifindex = ifindex,
+ };
+
+ ip_mc_join_group(sk, &mreq);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
+ &ip->sin6.sin6_addr);
+#endif
+ }
release_sock(sk);
vxlan_sock_release(vs);
@@ -838,13 +959,24 @@ static void vxlan_igmp_leave(struct work_struct *work)
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
struct vxlan_sock *vs = vxlan->vn_sock;
struct sock *sk = vs->sock->sk;
- struct ip_mreqn mreq = {
- .imr_multiaddr.s_addr = vxlan->default_dst.remote_ip,
- .imr_ifindex = vxlan->default_dst.remote_ifindex,
- };
+ union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
+ int ifindex = vxlan->default_dst.remote_ifindex;
lock_sock(sk);
- ip_mc_leave_group(sk, &mreq);
+ if (ip->sa.sa_family == AF_INET) {
+ struct ip_mreqn mreq = {
+ .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
+ .imr_ifindex = ifindex,
+ };
+
+ ip_mc_leave_group(sk, &mreq);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
+ &ip->sin6.sin6_addr);
+#endif
+ }
+
release_sock(sk);
vxlan_sock_release(vs);
@@ -896,11 +1028,14 @@ error:
static void vxlan_rcv(struct vxlan_sock *vs,
struct sk_buff *skb, __be32 vx_vni)
{
- struct iphdr *oip;
+ struct iphdr *oip = NULL;
+ struct ipv6hdr *oip6 = NULL;
struct vxlan_dev *vxlan;
struct pcpu_tstats *stats;
+ union vxlan_addr saddr;
__u32 vni;
- int err;
+ int err = 0;
+ union vxlan_addr *remote_ip;
vni = ntohl(vx_vni) >> 8;
/* Is this VNI defined? */
@@ -908,6 +1043,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
if (!vxlan)
goto drop;
+ remote_ip = &vxlan->default_dst.remote_ip;
skb_reset_mac_header(skb);
skb->protocol = eth_type_trans(skb, vxlan->dev);
@@ -917,9 +1053,20 @@ static void vxlan_rcv(struct vxlan_sock *vs,
goto drop;
/* Re-examine inner Ethernet packet */
- oip = ip_hdr(skb);
+ if (remote_ip->sa.sa_family == AF_INET) {
+ oip = ip_hdr(skb);
+ saddr.sin.sin_addr.s_addr = oip->saddr;
+ saddr.sa.sa_family = AF_INET;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ oip6 = ipv6_hdr(skb);
+ saddr.sin6.sin6_addr = oip6->saddr;
+ saddr.sa.sa_family = AF_INET6;
+#endif
+ }
+
if ((vxlan->flags & VXLAN_F_LEARN) &&
- vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source))
+ vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
goto drop;
skb_reset_network_header(skb);
@@ -935,11 +1082,20 @@ static void vxlan_rcv(struct vxlan_sock *vs,
skb->encapsulation = 0;
- err = IP_ECN_decapsulate(oip, skb);
+ if (oip6)
+ err = IP6_ECN_decapsulate(oip6, skb);
+ if (oip)
+ err = IP_ECN_decapsulate(oip, skb);
+
if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &oip->saddr, oip->tos);
+ if (log_ecn_error) {
+ if (oip6)
+ net_info_ratelimited("non-ECT from %pI6\n",
+ &oip6->saddr);
+ if (oip)
+ net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+ &oip->saddr, oip->tos);
+ }
if (err > 1) {
++vxlan->dev->stats.rx_frame_errors;
++vxlan->dev->stats.rx_errors;
@@ -968,6 +1124,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
u8 *arpptr, *sha;
__be32 sip, tip;
struct neighbour *n;
+ union vxlan_addr ipa;
if (dev->flags & IFF_NOARP)
goto out;
@@ -1009,7 +1166,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
}
f = vxlan_find_mac(vxlan, n->ha);
- if (f && first_remote_rcu(f)->remote_ip == htonl(INADDR_ANY)) {
+ if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
/* bridge-local neighbor */
neigh_release(n);
goto out;
@@ -1027,8 +1184,11 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
if (netif_rx_ni(reply) == NET_RX_DROP)
dev->stats.rx_dropped++;
- } else if (vxlan->flags & VXLAN_F_L3MISS)
- vxlan_ip_miss(dev, tip);
+ } else if (vxlan->flags & VXLAN_F_L3MISS) {
+ ipa.sin.sin_addr.s_addr = tip;
+ ipa.sa.sa_family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ }
out:
consume_skb(skb);
return NETDEV_TX_OK;
@@ -1050,6 +1210,14 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
pip = ip_hdr(skb);
n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
+ if (!n && vxlan->flags & VXLAN_F_L3MISS) {
+ union vxlan_addr ipa;
+ ipa.sin.sin_addr.s_addr = pip->daddr;
+ ipa.sa.sa_family = AF_INET;
+ vxlan_ip_miss(dev, &ipa);
+ return false;
+ }
+
break;
default:
return false;
@@ -1066,8 +1234,8 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
}
neigh_release(n);
return diff;
- } else if (vxlan->flags & VXLAN_F_L3MISS)
- vxlan_ip_miss(dev, pip->daddr);
+ }
+
return false;
}
@@ -1118,6 +1286,102 @@ static int handle_offloads(struct sk_buff *skb)
return 0;
}
+#if IS_ENABLED(CONFIG_IPV6)
+static int vxlan6_xmit_skb(struct net *net, struct vxlan_sock *vs,
+ struct dst_entry *dst, struct sk_buff *skb,
+ struct net_device *dev, struct in6_addr *saddr,
+ struct in6_addr *daddr, __u8 prio, __u8 ttl,
+ __be16 src_port, __be16 dst_port, __be32 vni)
+{
+ struct ipv6hdr *ip6h;
+ struct vxlanhdr *vxh;
+ struct udphdr *uh;
+ int min_headroom;
+ int err;
+
+ if (!skb->encapsulation) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
+ + VXLAN_HLEN + sizeof(struct ipv6hdr)
+ + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+
+ /* Need space for new headers (invalidates iph ptr) */
+ err = skb_cow_head(skb, min_headroom);
+ if (unlikely(err))
+ return err;
+
+ if (vlan_tx_tag_present(skb)) {
+ if (WARN_ON(!__vlan_put_tag(skb,
+ skb->vlan_proto,
+ vlan_tx_tag_get(skb))))
+ return -ENOMEM;
+
+ skb->vlan_tci = 0;
+ }
+
+ vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
+ vxh->vx_flags = htonl(VXLAN_FLAGS);
+ vxh->vx_vni = vni;
+
+ __skb_push(skb, sizeof(*uh));
+ skb_reset_transport_header(skb);
+ uh = udp_hdr(skb);
+
+ uh->dest = dst_port;
+ uh->source = src_port;
+
+ uh->len = htons(skb->len);
+ uh->check = 0;
+
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
+ IPSKB_REROUTED);
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst);
+
+ if (!skb_is_gso(skb) && !(dst->dev->features & NETIF_F_IPV6_CSUM)) {
+ __wsum csum = skb_checksum(skb, 0, skb->len, 0);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ uh->check = csum_ipv6_magic(saddr, daddr, skb->len,
+ IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_ipv6_magic(saddr, daddr,
+ skb->len, IPPROTO_UDP, 0);
+ }
+
+ __skb_push(skb, sizeof(*ip6h));
+ skb_reset_network_header(skb);
+ ip6h = ipv6_hdr(skb);
+ ip6h->version = 6;
+ ip6h->priority = prio;
+ ip6h->flow_lbl[0] = 0;
+ ip6h->flow_lbl[1] = 0;
+ ip6h->flow_lbl[2] = 0;
+ ip6h->payload_len = htons(skb->len);
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->hop_limit = ttl;
+ ip6h->daddr = *daddr;
+ ip6h->saddr = *saddr;
+
+ vxlan_set_owner(vs->sock->sk, skb);
+
+ err = handle_offloads(skb);
+ if (err)
+ return err;
+
+ ip6tunnel_xmit(skb, dev);
+ return 0;
+}
+#endif
+
int vxlan_xmit_skb(struct net *net, struct vxlan_sock *vs,
struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
@@ -1182,15 +1446,26 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
{
struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
+ union vxlan_addr loopback;
+ union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0;
skb->dev = dst_vxlan->dev;
__skb_pull(skb, skb_network_offset(skb));
+ if (remote_ip->sa.sa_family == AF_INET) {
+ loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ loopback.sa.sa_family = AF_INET;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ loopback.sin6.sin6_addr = in6addr_loopback;
+ loopback.sa.sa_family = AF_INET6;
+#endif
+ }
+
if (dst_vxlan->flags & VXLAN_F_LEARN)
- vxlan_snoop(skb->dev, htonl(INADDR_LOOPBACK),
- eth_hdr(skb)->h_source);
+ vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source);
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->tx_packets++;
@@ -1211,11 +1486,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_rdst *rdst, bool did_rsc)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct rtable *rt;
+ struct rtable *rt = NULL;
const struct iphdr *old_iph;
struct flowi4 fl4;
- __be32 dst;
- __be16 src_port, dst_port;
+ union vxlan_addr *dst;
+ __be16 src_port = 0, dst_port;
u32 vni;
__be16 df = 0;
__u8 tos, ttl;
@@ -1223,9 +1498,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
vni = rdst->remote_vni;
- dst = rdst->remote_ip;
+ dst = &rdst->remote_ip;
- if (!dst) {
+ if (vxlan_addr_any(dst)) {
if (did_rsc) {
/* short-circuited back to local bridge */
vxlan_encap_bypass(skb, vxlan, vxlan);
@@ -1237,7 +1512,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
old_iph = ip_hdr(skb);
ttl = vxlan->ttl;
- if (!ttl && IN_MULTICAST(ntohl(dst)))
+ if (!ttl && vxlan_addr_multicast(dst))
ttl = 1;
tos = vxlan->tos;
@@ -1246,48 +1521,101 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
src_port = vxlan_src_port(vxlan->port_min, vxlan->port_max, skb);
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = rdst->remote_ifindex;
- fl4.flowi4_tos = RT_TOS(tos);
- fl4.daddr = dst;
- fl4.saddr = vxlan->saddr;
-
- rt = ip_route_output_key(dev_net(dev), &fl4);
- if (IS_ERR(rt)) {
- netdev_dbg(dev, "no route to %pI4\n", &dst);
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
+ if (dst->sa.sa_family == AF_INET) {
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = rdst->remote_ifindex;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.daddr = dst->sin.sin_addr.s_addr;
+ fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
+
+ rt = ip_route_output_key(dev_net(dev), &fl4);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to %pI4\n",
+ &dst->sin.sin_addr.s_addr);
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n", &dst);
- dev->stats.collisions++;
- goto rt_tx_error;
- }
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n",
+ &dst->sin.sin_addr.s_addr);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+
+ /* Bypass encapsulation if the destination is local */
+ if (rt->rt_flags & RTCF_LOCAL &&
+ !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ ip_rt_put(rt);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ if (!dst_vxlan)
+ goto tx_error;
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return;
+ }
+
+ tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- /* Bypass encapsulation if the destination is local */
- if (rt->rt_flags & RTCF_LOCAL &&
- !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
+ err = vxlan_xmit_skb(dev_net(dev), vxlan->vn_sock, rt, skb,
+ fl4.saddr, dst->sin.sin_addr.s_addr,
+ tos, ttl, df, src_port, dst_port,
+ htonl(vni << 8));
- ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
- if (!dst_vxlan)
+ if (err < 0)
+ goto rt_tx_error;
+ iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ struct sock *sk = vxlan->vn_sock->sock->sk;
+ struct dst_entry *ndst;
+ struct flowi6 fl6;
+ u32 flags;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = rdst->remote_ifindex;
+ fl6.daddr = dst->sin6.sin6_addr;
+ fl6.saddr = vxlan->saddr.sin6.sin6_addr;
+ fl6.flowi6_proto = skb->protocol;
+
+ if (ipv6_stub->ipv6_dst_lookup(sk, &ndst, &fl6)) {
+ netdev_dbg(dev, "no route to %pI6\n",
+ &dst->sin6.sin6_addr);
+ dev->stats.tx_carrier_errors++;
goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return;
- }
+ }
- tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
- ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+ if (ndst->dev == dev) {
+ netdev_dbg(dev, "circular route to %pI6\n",
+ &dst->sin6.sin6_addr);
+ dst_release(ndst);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
- err = vxlan_xmit_skb(dev_net(dev), vxlan->vn_sock, rt, skb,
- fl4.saddr, dst, tos, ttl, df,
- src_port, dst_port, htonl(vni << 8));
+ /* Bypass encapsulation if the destination is local */
+ flags = ((struct rt6_info *)ndst)->rt6i_flags;
+ if (flags & RTF_LOCAL &&
+ !(flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ dst_release(ndst);
+ dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ if (!dst_vxlan)
+ goto tx_error;
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return;
+ }
- if (err < 0)
- goto rt_tx_error;
- iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+ ttl = ttl ? : ip6_dst_hoplimit(ndst);
+
+ err = vxlan6_xmit_skb(dev_net(dev), vxlan->vn_sock, ndst, skb,
+ dev, &fl6.saddr, &fl6.daddr, 0, ttl,
+ src_port, dst_port, htonl(vni << 8));
+#endif
+ }
return;
@@ -1464,8 +1792,8 @@ static int vxlan_open(struct net_device *dev)
if (!vs)
return -ENOTCONN;
- if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
- vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
+ if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
+ vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs);
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_join);
@@ -1503,8 +1831,8 @@ static int vxlan_stop(struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_sock *vs = vxlan->vn_sock;
- if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
- ! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
+ if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
+ ! vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs);
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_leave);
@@ -1552,7 +1880,10 @@ static void vxlan_setup(struct net_device *dev)
eth_hw_addr_random(dev);
ether_setup(dev);
- dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+ if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
+ dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+ else
+ dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = free_netdev;
@@ -1597,8 +1928,10 @@ static void vxlan_setup(struct net_device *dev)
static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
[IFLA_VXLAN_ID] = { .type = NLA_U32 },
[IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) },
[IFLA_VXLAN_LINK] = { .type = NLA_U32 },
[IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
+ [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) },
[IFLA_VXLAN_TOS] = { .type = NLA_U8 },
[IFLA_VXLAN_TTL] = { .type = NLA_U8 },
[IFLA_VXLAN_LEARNING] = { .type = NLA_U8 },
@@ -1669,58 +2002,132 @@ static void vxlan_del_work(struct work_struct *work)
kfree_rcu(vs, rcu);
}
-static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data)
+#if IS_ENABLED(CONFIG_IPV6)
+/* Create UDP socket for encapsulation receive. AF_INET6 socket
+ * could be used for both IPv4 and IPv6 communications, but
+ * users may set bindv6only=1.
+ */
+static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
{
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- struct vxlan_sock *vs;
struct sock *sk;
+ struct socket *sock;
+ struct sockaddr_in6 vxlan_addr = {
+ .sin6_family = AF_INET6,
+ .sin6_port = port,
+ };
+ int rc, val = 1;
+
+ rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
+ if (rc < 0) {
+ pr_debug("UDPv6 socket create failed\n");
+ return rc;
+ }
+
+ /* Put in proper namespace */
+ sk = sock->sk;
+ sk_change_net(sk, net);
+
+ kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
+ (char *)&val, sizeof(val));
+ rc = kernel_bind(sock, (struct sockaddr *)&vxlan_addr,
+ sizeof(struct sockaddr_in6));
+ if (rc < 0) {
+ pr_debug("bind for UDPv6 socket %pI6:%u (%d)\n",
+ &vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc);
+ sk_release_kernel(sk);
+ return rc;
+ }
+ /* At this point, IPv6 module should have been loaded in
+ * sock_create_kern().
+ */
+ BUG_ON(!ipv6_stub);
+
+ *psock = sock;
+ /* Disable multicast loopback */
+ inet_sk(sk)->mc_loop = 0;
+ return 0;
+}
+
+#else
+
+static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
+{
+ return -EPFNOSUPPORT;
+}
+#endif
+
+static int create_v4_sock(struct net *net, __be16 port, struct socket **psock)
+{
+ struct sock *sk;
+ struct socket *sock;
struct sockaddr_in vxlan_addr = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = port,
};
int rc;
- unsigned int h;
-
- vs = kmalloc(sizeof(*vs), GFP_KERNEL);
- if (!vs) {
- pr_debug("memory alocation failure\n");
- return ERR_PTR(-ENOMEM);
- }
-
- for (h = 0; h < VNI_HASH_SIZE; ++h)
- INIT_HLIST_HEAD(&vs->vni_list[h]);
-
- INIT_WORK(&vs->del_work, vxlan_del_work);
/* Create UDP socket for encapsulation receive. */
- rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vs->sock);
+ rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (rc < 0) {
pr_debug("UDP socket create failed\n");
- kfree(vs);
- return ERR_PTR(rc);
+ return rc;
}
/* Put in proper namespace */
- sk = vs->sock->sk;
+ sk = sock->sk;
sk_change_net(sk, net);
- rc = kernel_bind(vs->sock, (struct sockaddr *) &vxlan_addr,
+ rc = kernel_bind(sock, (struct sockaddr *) &vxlan_addr,
sizeof(vxlan_addr));
if (rc < 0) {
pr_debug("bind for UDP socket %pI4:%u (%d)\n",
&vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
sk_release_kernel(sk);
+ return rc;
+ }
+
+ *psock = sock;
+ /* Disable multicast loopback */
+ inet_sk(sk)->mc_loop = 0;
+ return 0;
+}
+
+/* Create new listen socket if needed */
+static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
+ vxlan_rcv_t *rcv, void *data, bool ipv6)
+{
+ struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+ struct vxlan_sock *vs;
+ struct socket *sock;
+ struct sock *sk;
+ int rc = 0;
+ unsigned int h;
+
+ vs = kmalloc(sizeof(*vs), GFP_KERNEL);
+ if (!vs)
+ return ERR_PTR(-ENOMEM);
+
+ for (h = 0; h < VNI_HASH_SIZE; ++h)
+ INIT_HLIST_HEAD(&vs->vni_list[h]);
+
+ INIT_WORK(&vs->del_work, vxlan_del_work);
+
+ if (ipv6)
+ rc = create_v6_sock(net, port, &sock);
+ else
+ rc = create_v4_sock(net, port, &sock);
+ if (rc < 0) {
kfree(vs);
return ERR_PTR(rc);
}
+
+ vs->sock = sock;
+ sk = sock->sk;
atomic_set(&vs->refcnt, 1);
vs->rcv = rcv;
vs->data = data;
- /* Disable multicast loopback */
- inet_sk(sk)->mc_loop = 0;
spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
spin_unlock(&vn->sock_lock);
@@ -1728,18 +2135,24 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
/* Mark socket as an encapsulation socket. */
udp_sk(sk)->encap_type = 1;
udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
- udp_encap_enable();
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipv6)
+ ipv6_stub->udpv6_encap_enable();
+ else
+#endif
+ udp_encap_enable();
+
return vs;
}
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
- bool no_share)
+ bool no_share, bool ipv6)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
- vs = vxlan_socket_create(net, port, rcv, data);
+ vs = vxlan_socket_create(net, port, rcv, data, ipv6);
if (!IS_ERR(vs))
return vs;
@@ -1772,7 +2185,7 @@ static void vxlan_sock_work(struct work_struct *work)
__be16 port = vxlan->dst_port;
struct vxlan_sock *nvs;
- nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false);
+ nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags & VXLAN_F_IPV6);
spin_lock(&vn->sock_lock);
if (!IS_ERR(nvs))
vxlan_vs_add_dev(nvs, vxlan);
@@ -1789,6 +2202,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
struct vxlan_rdst *dst = &vxlan->default_dst;
__u32 vni;
int err;
+ bool use_ipv6 = false;
if (!data[IFLA_VXLAN_ID])
return -EINVAL;
@@ -1796,11 +2210,31 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
vni = nla_get_u32(data[IFLA_VXLAN_ID]);
dst->remote_vni = vni;
- if (data[IFLA_VXLAN_GROUP])
- dst->remote_ip = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+ if (data[IFLA_VXLAN_GROUP]) {
+ dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
+ dst->remote_ip.sa.sa_family = AF_INET;
+ } else if (data[IFLA_VXLAN_GROUP6]) {
+ if (!IS_ENABLED(CONFIG_IPV6))
+ return -EPFNOSUPPORT;
+
+ nla_memcpy(&dst->remote_ip.sin6.sin6_addr, data[IFLA_VXLAN_GROUP6],
+ sizeof(struct in6_addr));
+ dst->remote_ip.sa.sa_family = AF_INET6;
+ use_ipv6 = true;
+ }
- if (data[IFLA_VXLAN_LOCAL])
- vxlan->saddr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ if (data[IFLA_VXLAN_LOCAL]) {
+ vxlan->saddr.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_LOCAL]);
+ vxlan->saddr.sa.sa_family = AF_INET;
+ } else if (data[IFLA_VXLAN_LOCAL6]) {
+ if (!IS_ENABLED(CONFIG_IPV6))
+ return -EPFNOSUPPORT;
+
+ nla_memcpy(&vxlan->saddr.sin6.sin6_addr, data[IFLA_VXLAN_LOCAL6],
+ sizeof(struct in6_addr));
+ vxlan->saddr.sa.sa_family = AF_INET6;
+ use_ipv6 = true;
+ }
if (data[IFLA_VXLAN_LINK] &&
(dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
@@ -1812,12 +2246,23 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
return -ENODEV;
}
+#if IS_ENABLED(CONFIG_IPV6)
+ if (use_ipv6) {
+ struct inet6_dev *idev = __in6_dev_get(lowerdev);
+ if (idev && idev->cnf.disable_ipv6) {
+ pr_info("IPv6 is disabled via sysctl\n");
+ return -EPERM;
+ }
+ vxlan->flags |= VXLAN_F_IPV6;
+ }
+#endif
+
if (!tb[IFLA_MTU])
- dev->mtu = lowerdev->mtu - VXLAN_HEADROOM;
+ dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
/* update header length based on lower device */
dev->hard_header_len = lowerdev->hard_header_len +
- VXLAN_HEADROOM;
+ (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
}
if (data[IFLA_VXLAN_TOS])
@@ -1868,7 +2313,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
/* create an fdb entry for default destination */
err = vxlan_fdb_create(vxlan, all_zeros_mac,
- vxlan->default_dst.remote_ip,
+ &vxlan->default_dst.remote_ip,
NUD_REACHABLE|NUD_PERMANENT,
NLM_F_EXCL|NLM_F_CREATE,
vxlan->dst_port, vxlan->default_dst.remote_vni,
@@ -1905,9 +2350,9 @@ static size_t vxlan_get_size(const struct net_device *dev)
{
return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */
- nla_total_size(sizeof(__be32)) +/* IFLA_VXLAN_GROUP */
+ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */
- nla_total_size(sizeof(__be32))+ /* IFLA_VXLAN_LOCAL */
+ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
@@ -1934,14 +2379,36 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni))
goto nla_put_failure;
- if (dst->remote_ip && nla_put_be32(skb, IFLA_VXLAN_GROUP, dst->remote_ip))
- goto nla_put_failure;
+ if (!vxlan_addr_any(&dst->remote_ip)) {
+ if (dst->remote_ip.sa.sa_family == AF_INET) {
+ if (nla_put_be32(skb, IFLA_VXLAN_GROUP,
+ dst->remote_ip.sin.sin_addr.s_addr))
+ goto nla_put_failure;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ if (nla_put(skb, IFLA_VXLAN_GROUP6, sizeof(struct in6_addr),
+ &dst->remote_ip.sin6.sin6_addr))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex))
goto nla_put_failure;
- if (vxlan->saddr && nla_put_be32(skb, IFLA_VXLAN_LOCAL, vxlan->saddr))
- goto nla_put_failure;
+ if (!vxlan_addr_any(&vxlan->saddr)) {
+ if (vxlan->saddr.sa.sa_family == AF_INET) {
+ if (nla_put_be32(skb, IFLA_VXLAN_LOCAL,
+ vxlan->saddr.sin.sin_addr.s_addr))
+ goto nla_put_failure;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ if (nla_put(skb, IFLA_VXLAN_LOCAL6, sizeof(struct in6_addr),
+ &vxlan->saddr.sin6.sin6_addr))
+ goto nla_put_failure;
+#endif
+ }
+ }
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index ad342e3..d2b88ca 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -25,7 +25,7 @@ struct vxlan_sock {
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
- bool no_share);
+ bool no_share, bool ipv6);
void vxlan_sock_release(struct vxlan_sock *vs);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 04c0e7a..80394e8 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -314,6 +314,8 @@ enum {
IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS,
IFLA_VXLAN_PORT, /* destination port */
+ IFLA_VXLAN_GROUP6,
+ IFLA_VXLAN_LOCAL6,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 36848bd..a006024 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -123,7 +123,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
vxlan_port = vxlan_vport(vport);
strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
- vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true);
+ vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, false);
if (IS_ERR(vs)) {
ovs_vport_free(vport);
return (void *)vs;
--
1.7.7.6
^ 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