* [PATCH v4 2/5] alx: add constants for the stats fields
From: Sabrina Dubroca @ 2014-01-09 9:09 UTC (permalink / raw)
To: davem; +Cc: bhutchings, johannes, stephen, netdev, Sabrina Dubroca
In-Reply-To: <1389258571-10083-1-git-send-email-sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
---
drivers/net/ethernet/atheros/alx/reg.h | 52 +++++++++++++++++++++++++++++++---
1 file changed, 48 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h
index e4358c9..af006b4 100644
--- a/drivers/net/ethernet/atheros/alx/reg.h
+++ b/drivers/net/ethernet/atheros/alx/reg.h
@@ -404,15 +404,59 @@
/* MIB */
#define ALX_MIB_BASE 0x1700
+
#define ALX_MIB_RX_OK (ALX_MIB_BASE + 0)
+#define ALX_MIB_RX_BCAST (ALX_MIB_BASE + 4)
+#define ALX_MIB_RX_MCAST (ALX_MIB_BASE + 8)
+#define ALX_MIB_RX_PAUSE (ALX_MIB_BASE + 12)
+#define ALX_MIB_RX_CTRL (ALX_MIB_BASE + 16)
+#define ALX_MIB_RX_FCS_ERR (ALX_MIB_BASE + 20)
+#define ALX_MIB_RX_LEN_ERR (ALX_MIB_BASE + 24)
+#define ALX_MIB_RX_BYTE_CNT (ALX_MIB_BASE + 28)
+#define ALX_MIB_RX_RUNT (ALX_MIB_BASE + 32)
+#define ALX_MIB_RX_FRAG (ALX_MIB_BASE + 36)
+#define ALX_MIB_RX_SZ_64B (ALX_MIB_BASE + 40)
+#define ALX_MIB_RX_SZ_127B (ALX_MIB_BASE + 44)
+#define ALX_MIB_RX_SZ_255B (ALX_MIB_BASE + 48)
+#define ALX_MIB_RX_SZ_511B (ALX_MIB_BASE + 52)
+#define ALX_MIB_RX_SZ_1023B (ALX_MIB_BASE + 56)
+#define ALX_MIB_RX_SZ_1518B (ALX_MIB_BASE + 60)
+#define ALX_MIB_RX_SZ_MAX (ALX_MIB_BASE + 64)
+#define ALX_MIB_RX_OV_SZ (ALX_MIB_BASE + 68)
+#define ALX_MIB_RX_OV_RXF (ALX_MIB_BASE + 72)
+#define ALX_MIB_RX_OV_RRD (ALX_MIB_BASE + 76)
+#define ALX_MIB_RX_ALIGN_ERR (ALX_MIB_BASE + 80)
+#define ALX_MIB_RX_BCCNT (ALX_MIB_BASE + 84)
+#define ALX_MIB_RX_MCCNT (ALX_MIB_BASE + 88)
#define ALX_MIB_RX_ERRADDR (ALX_MIB_BASE + 92)
+
#define ALX_MIB_TX_OK (ALX_MIB_BASE + 96)
+#define ALX_MIB_TX_BCAST (ALX_MIB_BASE + 100)
+#define ALX_MIB_TX_MCAST (ALX_MIB_BASE + 104)
+#define ALX_MIB_TX_PAUSE (ALX_MIB_BASE + 108)
+#define ALX_MIB_TX_EXC_DEFER (ALX_MIB_BASE + 112)
+#define ALX_MIB_TX_CTRL (ALX_MIB_BASE + 116)
+#define ALX_MIB_TX_DEFER (ALX_MIB_BASE + 120)
+#define ALX_MIB_TX_BYTE_CNT (ALX_MIB_BASE + 124)
+#define ALX_MIB_TX_SZ_64B (ALX_MIB_BASE + 128)
+#define ALX_MIB_TX_SZ_127B (ALX_MIB_BASE + 132)
+#define ALX_MIB_TX_SZ_255B (ALX_MIB_BASE + 136)
+#define ALX_MIB_TX_SZ_511B (ALX_MIB_BASE + 140)
+#define ALX_MIB_TX_SZ_1023B (ALX_MIB_BASE + 144)
+#define ALX_MIB_TX_SZ_1518B (ALX_MIB_BASE + 148)
+#define ALX_MIB_TX_SZ_MAX (ALX_MIB_BASE + 152)
+#define ALX_MIB_TX_SINGLE_COL (ALX_MIB_BASE + 156)
+#define ALX_MIB_TX_MULTI_COL (ALX_MIB_BASE + 160)
+#define ALX_MIB_TX_LATE_COL (ALX_MIB_BASE + 164)
+#define ALX_MIB_TX_ABORT_COL (ALX_MIB_BASE + 168)
+#define ALX_MIB_TX_UNDERRUN (ALX_MIB_BASE + 172)
+#define ALX_MIB_TX_TRD_EOP (ALX_MIB_BASE + 176)
+#define ALX_MIB_TX_LEN_ERR (ALX_MIB_BASE + 180)
+#define ALX_MIB_TX_TRUNC (ALX_MIB_BASE + 184)
+#define ALX_MIB_TX_BCCNT (ALX_MIB_BASE + 188)
#define ALX_MIB_TX_MCCNT (ALX_MIB_BASE + 192)
+#define ALX_MIB_UPDATE (ALX_MIB_BASE + 196)
-#define ALX_RX_STATS_BIN ALX_MIB_RX_OK
-#define ALX_RX_STATS_END ALX_MIB_RX_ERRADDR
-#define ALX_TX_STATS_BIN ALX_MIB_TX_OK
-#define ALX_TX_STATS_END ALX_MIB_TX_MCCNT
#define ALX_ISR 0x1600
#define ALX_ISR_DIS BIT(31)
--
1.8.5.2
^ permalink raw reply related
* [PATCH v4 3/5] alx: add stats update function
From: Sabrina Dubroca @ 2014-01-09 9:09 UTC (permalink / raw)
To: davem; +Cc: bhutchings, johannes, stephen, netdev, Sabrina Dubroca
In-Reply-To: <1389258571-10083-1-git-send-email-sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
---
drivers/net/ethernet/atheros/alx/hw.c | 58 +++++++++++++++++++++++++++++++++++
drivers/net/ethernet/atheros/alx/hw.h | 4 +++
2 files changed, 62 insertions(+)
diff --git a/drivers/net/ethernet/atheros/alx/hw.c b/drivers/net/ethernet/atheros/alx/hw.c
index 1e8c24a..7712f06 100644
--- a/drivers/net/ethernet/atheros/alx/hw.c
+++ b/drivers/net/ethernet/atheros/alx/hw.c
@@ -1050,3 +1050,61 @@ bool alx_get_phy_info(struct alx_hw *hw)
return true;
}
+
+void alx_update_hw_stats(struct alx_hw *hw)
+{
+ /* RX stats */
+ hw->stats.rx_ok += alx_read_mem32(hw, ALX_MIB_RX_OK);
+ hw->stats.rx_bcast += alx_read_mem32(hw, ALX_MIB_RX_BCAST);
+ hw->stats.rx_mcast += alx_read_mem32(hw, ALX_MIB_RX_MCAST);
+ hw->stats.rx_pause += alx_read_mem32(hw, ALX_MIB_RX_PAUSE);
+ hw->stats.rx_ctrl += alx_read_mem32(hw, ALX_MIB_RX_CTRL);
+ hw->stats.rx_fcs_err += alx_read_mem32(hw, ALX_MIB_RX_FCS_ERR);
+ hw->stats.rx_len_err += alx_read_mem32(hw, ALX_MIB_RX_LEN_ERR);
+ hw->stats.rx_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_BYTE_CNT);
+ hw->stats.rx_runt += alx_read_mem32(hw, ALX_MIB_RX_RUNT);
+ hw->stats.rx_frag += alx_read_mem32(hw, ALX_MIB_RX_FRAG);
+ hw->stats.rx_sz_64B += alx_read_mem32(hw, ALX_MIB_RX_SZ_64B);
+ hw->stats.rx_sz_127B += alx_read_mem32(hw, ALX_MIB_RX_SZ_127B);
+ hw->stats.rx_sz_255B += alx_read_mem32(hw, ALX_MIB_RX_SZ_255B);
+ hw->stats.rx_sz_511B += alx_read_mem32(hw, ALX_MIB_RX_SZ_511B);
+ hw->stats.rx_sz_1023B += alx_read_mem32(hw, ALX_MIB_RX_SZ_1023B);
+ hw->stats.rx_sz_1518B += alx_read_mem32(hw, ALX_MIB_RX_SZ_1518B);
+ hw->stats.rx_sz_max += alx_read_mem32(hw, ALX_MIB_RX_SZ_MAX);
+ hw->stats.rx_ov_sz += alx_read_mem32(hw, ALX_MIB_RX_OV_SZ);
+ hw->stats.rx_ov_rxf += alx_read_mem32(hw, ALX_MIB_RX_OV_RXF);
+ hw->stats.rx_ov_rrd += alx_read_mem32(hw, ALX_MIB_RX_OV_RRD);
+ hw->stats.rx_align_err += alx_read_mem32(hw, ALX_MIB_RX_ALIGN_ERR);
+ hw->stats.rx_bc_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_BCCNT);
+ hw->stats.rx_mc_byte_cnt += alx_read_mem32(hw, ALX_MIB_RX_MCCNT);
+ hw->stats.rx_err_addr += alx_read_mem32(hw, ALX_MIB_RX_ERRADDR);
+
+ /* TX stats */
+ hw->stats.tx_ok += alx_read_mem32(hw, ALX_MIB_TX_OK);
+ hw->stats.tx_bcast += alx_read_mem32(hw, ALX_MIB_TX_BCAST);
+ hw->stats.tx_mcast += alx_read_mem32(hw, ALX_MIB_TX_MCAST);
+ hw->stats.tx_pause += alx_read_mem32(hw, ALX_MIB_TX_PAUSE);
+ hw->stats.tx_exc_defer += alx_read_mem32(hw, ALX_MIB_TX_EXC_DEFER);
+ hw->stats.tx_ctrl += alx_read_mem32(hw, ALX_MIB_TX_CTRL);
+ hw->stats.tx_defer += alx_read_mem32(hw, ALX_MIB_TX_DEFER);
+ hw->stats.tx_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_BYTE_CNT);
+ hw->stats.tx_sz_64B += alx_read_mem32(hw, ALX_MIB_TX_SZ_64B);
+ hw->stats.tx_sz_127B += alx_read_mem32(hw, ALX_MIB_TX_SZ_127B);
+ hw->stats.tx_sz_255B += alx_read_mem32(hw, ALX_MIB_TX_SZ_255B);
+ hw->stats.tx_sz_511B += alx_read_mem32(hw, ALX_MIB_TX_SZ_511B);
+ hw->stats.tx_sz_1023B += alx_read_mem32(hw, ALX_MIB_TX_SZ_1023B);
+ hw->stats.tx_sz_1518B += alx_read_mem32(hw, ALX_MIB_TX_SZ_1518B);
+ hw->stats.tx_sz_max += alx_read_mem32(hw, ALX_MIB_TX_SZ_MAX);
+ hw->stats.tx_single_col += alx_read_mem32(hw, ALX_MIB_TX_SINGLE_COL);
+ hw->stats.tx_multi_col += alx_read_mem32(hw, ALX_MIB_TX_MULTI_COL);
+ hw->stats.tx_late_col += alx_read_mem32(hw, ALX_MIB_TX_LATE_COL);
+ hw->stats.tx_abort_col += alx_read_mem32(hw, ALX_MIB_TX_ABORT_COL);
+ hw->stats.tx_underrun += alx_read_mem32(hw, ALX_MIB_TX_UNDERRUN);
+ hw->stats.tx_trd_eop += alx_read_mem32(hw, ALX_MIB_TX_TRD_EOP);
+ hw->stats.tx_len_err += alx_read_mem32(hw, ALX_MIB_TX_LEN_ERR);
+ hw->stats.tx_trunc += alx_read_mem32(hw, ALX_MIB_TX_TRUNC);
+ hw->stats.tx_bc_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_BCCNT);
+ hw->stats.tx_mc_byte_cnt += alx_read_mem32(hw, ALX_MIB_TX_MCCNT);
+
+ hw->stats.update += alx_read_mem32(hw, ALX_MIB_UPDATE);
+}
diff --git a/drivers/net/ethernet/atheros/alx/hw.h b/drivers/net/ethernet/atheros/alx/hw.h
index 872b362..854d807 100644
--- a/drivers/net/ethernet/atheros/alx/hw.h
+++ b/drivers/net/ethernet/atheros/alx/hw.h
@@ -486,6 +486,9 @@ struct alx_hw {
/* PHY link patch flag */
bool lnk_patch;
+
+ /* cumulated stats from the hardware (registers are cleared on read) */
+ struct alx_hw_stats stats;
};
static inline int alx_hw_revision(struct alx_hw *hw)
@@ -553,6 +556,7 @@ bool alx_phy_configured(struct alx_hw *hw);
void alx_configure_basic(struct alx_hw *hw);
void alx_disable_rss(struct alx_hw *hw);
bool alx_get_phy_info(struct alx_hw *hw);
+void alx_update_hw_stats(struct alx_hw *hw);
static inline u32 alx_speed_to_ethadv(int speed, u8 duplex)
{
--
1.8.5.2
^ permalink raw reply related
* [PATCH v4 5/5] alx: add stats to ethtool
From: Sabrina Dubroca @ 2014-01-09 9:09 UTC (permalink / raw)
To: davem; +Cc: bhutchings, johannes, stephen, netdev, Sabrina Dubroca
In-Reply-To: <1389258571-10083-1-git-send-email-sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
---
drivers/net/ethernet/atheros/alx/ethtool.c | 101 +++++++++++++++++++++++++++++
drivers/net/ethernet/atheros/alx/hw.h | 7 +-
2 files changed, 107 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c
index 45b3650..08e22df 100644
--- a/drivers/net/ethernet/atheros/alx/ethtool.c
+++ b/drivers/net/ethernet/atheros/alx/ethtool.c
@@ -46,6 +46,66 @@
#include "reg.h"
#include "hw.h"
+/* The order of these strings must match the order of the fields in
+ * struct alx_hw_stats
+ * See hw.h
+ */
+static const char alx_gstrings_stats[][ETH_GSTRING_LEN] = {
+ "rx_packets",
+ "rx_bcast_packets",
+ "rx_mcast_packets",
+ "rx_pause_packets",
+ "rx_ctrl_packets",
+ "rx_fcs_errors",
+ "rx_length_errors",
+ "rx_bytes",
+ "rx_runt_packets",
+ "rx_fragments",
+ "rx_64B_or_less_packets",
+ "rx_65B_to_127B_packets",
+ "rx_128B_to_255B_packets",
+ "rx_256B_to_511B_packets",
+ "rx_512B_to_1023B_packets",
+ "rx_1024B_to_1518B_packets",
+ "rx_1519B_to_mtu_packets",
+ "rx_oversize_packets",
+ "rx_rxf_ov_drop_packets",
+ "rx_rrd_ov_drop_packets",
+ "rx_align_errors",
+ "rx_bcast_bytes",
+ "rx_mcast_bytes",
+ "rx_address_errors",
+ "tx_packets",
+ "tx_bcast_packets",
+ "tx_mcast_packets",
+ "tx_pause_packets",
+ "tx_exc_defer_packets",
+ "tx_ctrl_packets",
+ "tx_defer_packets",
+ "tx_bytes",
+ "tx_64B_or_less_packets",
+ "tx_65B_to_127B_packets",
+ "tx_128B_to_255B_packets",
+ "tx_256B_to_511B_packets",
+ "tx_512B_to_1023B_packets",
+ "tx_1024B_to_1518B_packets",
+ "tx_1519B_to_mtu_packets",
+ "tx_single_collision",
+ "tx_multiple_collisions",
+ "tx_late_collision",
+ "tx_abort_collision",
+ "tx_underrun",
+ "tx_trd_eop",
+ "tx_length_errors",
+ "tx_trunc_packets",
+ "tx_bcast_bytes",
+ "tx_mcast_bytes",
+ "tx_update",
+};
+
+#define ALX_NUM_STATS ARRAY_SIZE(alx_gstrings_stats)
+
+
static u32 alx_get_supported_speeds(struct alx_hw *hw)
{
u32 supported = SUPPORTED_10baseT_Half |
@@ -201,6 +261,44 @@ static void alx_set_msglevel(struct net_device *netdev, u32 data)
alx->msg_enable = data;
}
+static void alx_get_ethtool_stats(struct net_device *netdev,
+ struct ethtool_stats *estats, u64 *data)
+{
+ struct alx_priv *alx = netdev_priv(netdev);
+ struct alx_hw *hw = &alx->hw;
+
+ spin_lock(&alx->stats_lock);
+
+ alx_update_hw_stats(hw);
+ BUILD_BUG_ON(sizeof(hw->stats) - offsetof(struct alx_hw_stats, rx_ok) <
+ ALX_NUM_STATS * sizeof(u64));
+ memcpy(data, &hw->stats.rx_ok, ALX_NUM_STATS * sizeof(u64));
+
+ spin_unlock(&alx->stats_lock);
+}
+
+static void alx_get_strings(struct net_device *netdev, u32 stringset, u8 *buf)
+{
+ switch (stringset) {
+ case ETH_SS_STATS:
+ memcpy(buf, &alx_gstrings_stats, sizeof(alx_gstrings_stats));
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+static int alx_get_sset_count(struct net_device *netdev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ALX_NUM_STATS;
+ default:
+ return -EINVAL;
+ }
+}
+
const struct ethtool_ops alx_ethtool_ops = {
.get_settings = alx_get_settings,
.set_settings = alx_set_settings,
@@ -209,4 +307,7 @@ const struct ethtool_ops alx_ethtool_ops = {
.get_msglevel = alx_get_msglevel,
.set_msglevel = alx_set_msglevel,
.get_link = ethtool_op_get_link,
+ .get_strings = alx_get_strings,
+ .get_sset_count = alx_get_sset_count,
+ .get_ethtool_stats = alx_get_ethtool_stats,
};
diff --git a/drivers/net/ethernet/atheros/alx/hw.h b/drivers/net/ethernet/atheros/alx/hw.h
index 854d807..1554880 100644
--- a/drivers/net/ethernet/atheros/alx/hw.h
+++ b/drivers/net/ethernet/atheros/alx/hw.h
@@ -381,7 +381,12 @@ struct alx_rrd {
ALX_ISR_RX_Q6 | \
ALX_ISR_RX_Q7)
-/* Statistics counters collected by the MAC */
+/* Statistics counters collected by the MAC
+ *
+ * The order of the fields must match the strings in alx_gstrings_stats
+ * All stats fields should be u64
+ * See ethtool.c
+ */
struct alx_hw_stats {
/* rx */
u64 rx_ok; /* good RX packets */
--
1.8.5.2
^ permalink raw reply related
* [PATCH v4 4/5] alx: add alx_get_stats64 operation
From: Sabrina Dubroca @ 2014-01-09 9:09 UTC (permalink / raw)
To: davem; +Cc: bhutchings, johannes, stephen, netdev, Sabrina Dubroca
In-Reply-To: <1389258571-10083-1-git-send-email-sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
---
I've modified the assignements of hw stats to netstats here as Ben asked in v3.
The other atheros drivers use the same code as v3. Should I modify
them as well in another patch?
drivers/net/ethernet/atheros/alx/alx.h | 3 ++
drivers/net/ethernet/atheros/alx/main.c | 50 +++++++++++++++++++++++++++++++++
2 files changed, 53 insertions(+)
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index d71103d..8fc93c5 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -106,6 +106,9 @@ struct alx_priv {
u16 msg_enable;
bool msi;
+
+ /* protects hw.stats */
+ spinlock_t stats_lock;
};
extern const struct ethtool_ops alx_ethtool_ops;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c3c4c26..e92ffd6 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1166,10 +1166,60 @@ static void alx_poll_controller(struct net_device *netdev)
}
#endif
+static struct rtnl_link_stats64 *alx_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *net_stats)
+{
+ struct alx_priv *alx = netdev_priv(dev);
+ struct alx_hw_stats *hw_stats = &alx->hw.stats;
+
+ spin_lock(&alx->stats_lock);
+
+ alx_update_hw_stats(&alx->hw);
+
+ net_stats->tx_bytes = hw_stats->tx_byte_cnt;
+ net_stats->rx_bytes = hw_stats->rx_byte_cnt;
+ net_stats->multicast = hw_stats->rx_mcast;
+ net_stats->collisions = hw_stats->tx_single_col +
+ hw_stats->tx_multi_col +
+ hw_stats->tx_late_col +
+ hw_stats->tx_abort_col;
+
+ net_stats->rx_errors = hw_stats->rx_frag +
+ hw_stats->rx_fcs_err +
+ hw_stats->rx_len_err +
+ hw_stats->rx_ov_sz +
+ hw_stats->rx_ov_rrd +
+ hw_stats->rx_align_err +
+ hw_stats->rx_ov_rxf;
+
+ net_stats->rx_fifo_errors = hw_stats->rx_ov_rxf;
+ net_stats->rx_length_errors = hw_stats->rx_len_err;
+ net_stats->rx_crc_errors = hw_stats->rx_fcs_err;
+ net_stats->rx_frame_errors = hw_stats->rx_align_err;
+ net_stats->rx_dropped = hw_stats->rx_ov_rrd;
+
+ net_stats->tx_errors = hw_stats->tx_late_col +
+ hw_stats->tx_abort_col +
+ hw_stats->tx_underrun +
+ hw_stats->tx_trunc;
+
+ net_stats->tx_aborted_errors = hw_stats->tx_abort_col;
+ net_stats->tx_fifo_errors = hw_stats->tx_underrun;
+ net_stats->tx_window_errors = hw_stats->tx_late_col;
+
+ net_stats->tx_packets = hw_stats->tx_ok + net_stats->tx_errors;
+ net_stats->rx_packets = hw_stats->rx_ok + net_stats->rx_errors;
+
+ spin_unlock(&alx->stats_lock);
+
+ return net_stats;
+}
+
static const struct net_device_ops alx_netdev_ops = {
.ndo_open = alx_open,
.ndo_stop = alx_stop,
.ndo_start_xmit = alx_start_xmit,
+ .ndo_get_stats64 = alx_get_stats64,
.ndo_set_rx_mode = alx_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = alx_set_mac_address,
--
1.8.5.2
^ permalink raw reply related
* RE: [PATCH net-next v3 8/9] xen-netback: Timeout packets in RX path
From: Paul Durrant @ 2014-01-09 9:20 UTC (permalink / raw)
To: Zoltan Kiss, Ian Campbell, Wei Liu,
xen-devel@lists.xenproject.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, Jonathan Davies
In-Reply-To: <52CDC45D.3050509@citrix.com>
> -----Original Message-----
> From: Zoltan Kiss
> Sent: 08 January 2014 21:34
> To: Ian Campbell; Wei Liu; xen-devel@lists.xenproject.org;
> netdev@vger.kernel.org; linux-kernel@vger.kernel.org; Jonathan Davies
> Cc: Zoltan Kiss; Paul Durrant
> Subject: Re: [PATCH net-next v3 8/9] xen-netback: Timeout packets in RX
> path
>
> I just realized when answering Ma's mail that this doesn't cause the
> desired effect after Paul's flow control improvement: starting the queue
> doesn't drop the packets which cannot fit the ring. Which in fact might
> be not good.
No, that would not be good.
> We are adding the skb to vif->rx_queue even when
> xenvif_rx_ring_slots_available(vif, min_slots_needed) said there is no
> space for that. Or am I missing something? Paul?
>
That's correct. Part of the flow control improvement was to get rid of needless packet drops. For your purposes, you basically need to avoid using the queuing discipline and take packets into netback's vif->rx_queue regardless of the state of the shared ring so that you can drop them if they get beyond a certain age. So, perhaps you should never stop the netif queue, place an upper limit on vif->rx_queue (either packet or byte count) and drop when that is exceeded (i.e. mimicking pfifo or bfifo internally).
Paul
> Zoli
>
> On 08/01/14 00:10, Zoltan Kiss wrote:
> > A malicious or buggy guest can leave its queue filled indefinitely, in which
> > case qdisc start to queue packets for that VIF. If those packets came from
> an
> > another guest, it can block its slots and prevent shutdown. To avoid that,
> we
> > make sure the queue is drained in every 10 seconds.
> ...
> > diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-
> netback/interface.c
> > index 95fcd63..ce032f9 100644
> > --- a/drivers/net/xen-netback/interface.c
> > +++ b/drivers/net/xen-netback/interface.c
> > @@ -114,6 +114,16 @@ static irqreturn_t xenvif_interrupt(int irq, void
> *dev_id)
> > return IRQ_HANDLED;
> > }
> >
> > +static void xenvif_wake_queue(unsigned long data)
> > +{
> > + struct xenvif *vif = (struct xenvif *)data;
> > +
> > + if (netif_queue_stopped(vif->dev)) {
> > + netdev_err(vif->dev, "draining TX queue\n");
> > + netif_wake_queue(vif->dev);
> > + }
> > +}
> > +
> > static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
> > {
> > struct xenvif *vif = netdev_priv(dev);
> > @@ -143,8 +153,13 @@ static int xenvif_start_xmit(struct sk_buff *skb,
> struct net_device *dev)
> > * then turn off the queue to give the ring a chance to
> > * drain.
> > */
> > - if (!xenvif_rx_ring_slots_available(vif, min_slots_needed))
> > + if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) {
> > + vif->wake_queue.function = xenvif_wake_queue;
> > + vif->wake_queue.data = (unsigned long)vif;
> > xenvif_stop_queue(vif);
> > + mod_timer(&vif->wake_queue,
> > + jiffies + rx_drain_timeout_jiffies);
> > + }
> >
> > skb_queue_tail(&vif->rx_queue, skb);
> > xenvif_kick_thread(vif);
^ permalink raw reply
* RE: [PATCH net-next 1/3] net: add skb_checksum_setup
From: Paul Durrant @ 2014-01-09 9:22 UTC (permalink / raw)
To: Eric Dumazet
Cc: netdev@vger.kernel.org, xen-devel@lists.xen.org, David Miller,
Eric Dumazet, Veaceslav Falico, Alexander Duyck, Nicolas Dichtel
In-Reply-To: <1389220984.31367.22.camel@edumazet-glaptop2.roam.corp.google.com>
> -----Original Message-----
> From: Eric Dumazet [mailto:eric.dumazet@gmail.com]
> Sent: 08 January 2014 22:43
> To: Paul Durrant
> Cc: netdev@vger.kernel.org; xen-devel@lists.xen.org; David Miller; Eric
> Dumazet; Veaceslav Falico; Alexander Duyck; Nicolas Dichtel
> Subject: Re: [PATCH net-next 1/3] net: add skb_checksum_setup
>
> On Wed, 2014-01-08 at 13:58 +0000, Paul Durrant wrote:
> > This patch adds a function to set up the partial checksum offset for IP
> > packets (and optionally re-calculate the pseudo-header checksum) into the
> > core network code.
> > The implementation was previously private and duplicated between xen-
> netback
> > and xen-netfront, however it is not xen-specific and is potentially useful
> > to any network driver.
> >
> > Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
> > Cc: David Miller <davem@davemloft.net>
> > Cc: Eric Dumazet <edumazet@google.com>
> > Cc: Veaceslav Falico <vfalico@redhat.com>
> > Cc: Alexander Duyck <alexander.h.duyck@intel.com>
> > Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
> > ---
> > include/linux/netdevice.h | 1 +
> > net/core/dev.c | 271
> +++++++++++++++++++++++++++++++++++++++++++++
> > 2 files changed, 272 insertions(+)
>
> Is there any reason to put this in net/core/dev.c instead of
> net/core/skbuff.c ?
>
No, no reason. I just wasn't sure which was the better place. I'll put it in skbuff.c if that is more appropriate.
>
> Also, no inline should be used in a .c file
>
> ( skb_maybe_pull_tail )
>
Ok. I'll fix that.
Thanks,
Paul
^ permalink raw reply
* [PATCH net V2 1/2] macvlan: forbid L2 fowarding offload for macvtap
From: Jason Wang @ 2014-01-09 9:37 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: mst, Jason Wang, John Fastabend, Neil Horman
L2 fowarding offload will bypass the rx handler of real device. This will make
the packet could not be forwarded to macvtap device. Another problem is the
dev_hard_start_xmit() called for macvtap does not have any synchronization.
Fix this by forbidding L2 forwarding for macvtap.
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/macvlan.c | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 60406b0..5360f73 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -338,6 +338,8 @@ static const struct header_ops macvlan_hard_header_ops = {
.cache_update = eth_header_cache_update,
};
+static struct rtnl_link_ops macvlan_link_ops;
+
static int macvlan_open(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
@@ -353,7 +355,8 @@ static int macvlan_open(struct net_device *dev)
goto hash_add;
}
- if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
+ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
+ dev->rtnl_link_ops == &macvlan_link_ops) {
vlan->fwd_priv =
lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
--
1.7.1
^ permalink raw reply related
* [PATCH net V2 2/2] net: core: explicitly select a txq before doing l2 forwarding
From: Jason Wang @ 2014-01-09 9:37 UTC (permalink / raw)
To: davem, netdev, linux-kernel
Cc: John Fastabend, e1000-devel, Jason Wang, Neil Horman, mst
In-Reply-To: <1389260252-48591-1-git-send-email-jasowang@redhat.com>
Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:
- NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan
instead of lower device which misses the necessary txq synchronization for
lower device such as txq stopping or frozen required by dev watchdog or
control path.
- dev_hard_start_xmit() was called with NULL txq which bypasses the net device
watchdog.
- dev_hard_start_xmit() does not check txq everywhere which will lead a crash
when tso is disabled for lower device.
Fix this by explicitly introducing a new param for .ndo_select_queue() for just
selecting queues in the case of l2 forwarding offload. And also introducing
dfwd_direct_xmit() to do the queue selecting, txq holding and transmitting for
l2 forwarding.
With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need
to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep
a dedicated ndo_dfwd_start_xmit().
In the future, it was also required for macvtap l2 forwarding support since it
provides a necessary synchronization method.
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: e1000-devel@lists.sourceforge.net
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
Changes from V1:
- Adding a new parameter to ndo_select_queue instead of a new method to select
queue for l2 forwarding.
- Remove the unnecessary ndo_dfwd_start_xmit() since txq was selected
explicitly.
- Keep NETIF_F_LLTX when netdev feature is changed.
- Shape the commit log
---
drivers/net/bonding/bond_main.c | 3 +-
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +-
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 33 +++++++------------
drivers/net/ethernet/lantiq_etop.c | 3 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 3 +-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +-
drivers/net/ethernet/tile/tilegx.c | 3 +-
drivers/net/macvlan.c | 6 +--
drivers/net/team/team.c | 3 +-
drivers/net/tun.c | 3 +-
drivers/net/wireless/mwifiex/main.c | 3 +-
drivers/staging/bcm/Bcmnet.c | 3 +-
drivers/staging/netlogic/xlr_net.c | 3 +-
drivers/staging/rtl8188eu/os_dep/os_intfs.c | 3 +-
include/linux/netdevice.h | 10 ++++--
net/core/dev.c | 39 +++++++++++++++++------
net/core/flow_dissector.c | 2 +-
net/mac80211/iface.c | 6 ++-
net/sched/sch_generic.c | 2 +-
20 files changed, 83 insertions(+), 54 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 398e299..4b8c58b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3732,7 +3732,8 @@ static inline int bond_slave_override(struct bonding *bond,
}
-static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/*
* This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ec96130..513fa85 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1832,7 +1832,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
bnx2x_napi_disable_cnic(bp);
}
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct bnx2x *bp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index da8fcaa..41f3ca5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -524,7 +524,8 @@ int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac);
int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos);
/* select_queue callback */
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv);
static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cc06854..5bcc870 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6827,12 +6827,20 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
return __ixgbe_maybe_stop_tx(tx_ring, size);
}
-#ifdef IXGBE_FCOE
-static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
+ struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
+#ifdef IXGBE_FCOE
struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
int txq;
+#endif
+
+ if (fwd_adapter)
+ return skb->queue_mapping + fwd_adapter->tx_base_queue;
+
+#ifdef IXGBE_FCOE
/*
* only execute the code below if protocol is FCoE
@@ -6858,9 +6866,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
txq -= f->indices;
return txq + f->offset;
+#else
+ return __netdev_pick_tx(dev, skb);
+#endif
}
-#endif
netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
@@ -7629,27 +7639,11 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
kfree(fwd_adapter);
}
-static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
- struct net_device *dev,
- void *priv)
-{
- struct ixgbe_fwd_adapter *fwd_adapter = priv;
- unsigned int queue;
- struct ixgbe_ring *tx_ring;
-
- queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
- tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
-
- return __ixgbe_xmit_frame(skb, dev, tx_ring);
-}
-
static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
.ndo_start_xmit = ixgbe_xmit_frame,
-#ifdef IXGBE_FCOE
.ndo_select_queue = ixgbe_select_queue,
-#endif
.ndo_set_rx_mode = ixgbe_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = ixgbe_set_mac,
@@ -7689,7 +7683,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_bridge_getlink = ixgbe_ndo_bridge_getlink,
.ndo_dfwd_add_station = ixgbe_fwd_add,
.ndo_dfwd_del_station = ixgbe_fwd_del,
- .ndo_dfwd_start_xmit = ixgbe_fwd_xmit,
};
/**
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6a6c1f7..ec94a20 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,8 @@ ltq_etop_set_multicast_list(struct net_device *dev)
}
static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/* we are currently only using the first queue */
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5..a7fcd59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,7 +592,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
}
}
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de..d5758ad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -714,7 +714,8 @@ int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
void mlx4_en_tx_irq(struct mlx4_cq *mcq);
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 628b736..0e9fb33 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2080,7 +2080,8 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
}
/* Return subqueue id on this core (one per core). */
-static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
return smp_processor_id();
}
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 5360f73..7eb4c82 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -299,7 +299,7 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
if (vlan->fwd_priv) {
skb->dev = vlan->lowerdev;
- ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+ ret = dfwd_direct_xmit(skb, skb->dev, vlan->fwd_priv);
} else {
ret = macvlan_queue_xmit(skb, dev);
}
@@ -366,7 +366,6 @@ static int macvlan_open(struct net_device *dev)
if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
vlan->fwd_priv = NULL;
} else {
- dev->features &= ~NETIF_F_LLTX;
return 0;
}
}
@@ -702,8 +701,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
features = netdev_increment_features(vlan->lowerdev->features,
features,
mask);
- if (!vlan->fwd_priv)
- features |= NETIF_F_LLTX;
+ features |= NETIF_F_LLTX;
return features;
}
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 736050d..b75ae5b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,7 +1647,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/*
* This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c8343a..ecec802 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -348,7 +348,8 @@ unlock:
* different rxq no. here. If we could not get rxhash, then we would
* hope the rxq no. may help here.
*/
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct tun_struct *tun = netdev_priv(dev);
struct tun_flow_entry *e;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 78e8a66..8bb8988 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -746,7 +746,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
}
static u16
-mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
+mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
skb->priority = cfg80211_classify8021d(skb);
return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 53fee2f..8dfdd27 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -39,7 +39,8 @@ static INT bcm_close(struct net_device *dev)
return 0;
}
-static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
return ClassifyPacket(netdev_priv(dev), skb);
}
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 235d2b1..eedffed 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -306,7 +306,8 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb)
+static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
+ void *accel_priv)
{
return (u16)smp_processor_id();
}
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 17659bb..dd69e34 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -652,7 +652,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
return dscp >> 5;
}
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct adapter *padapter = rtw_netdev_priv(dev);
struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5faaadb..262b04f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@ struct netdev_phys_port_id {
* (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
* Required can not be NULL.
*
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ * void *accel_priv);
* Called to decide which queue to when device supports multiple
* transmit queues.
*
@@ -990,7 +991,8 @@ struct net_device_ops {
netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb,
struct net_device *dev);
u16 (*ndo_select_queue)(struct net_device *dev,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ void *accel_priv);
void (*ndo_change_rx_flags)(struct net_device *dev,
int flags);
void (*ndo_set_rx_mode)(struct net_device *dev);
@@ -2425,8 +2427,10 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *);
int dev_change_carrier(struct net_device *, bool new_carrier);
int dev_get_phys_port_id(struct net_device *dev,
struct netdev_phys_port_id *ppid);
+int dfwd_direct_xmit(struct sk_buff *skb, struct net_device *dev,
+ void *accel_priv);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq, void *accel_priv);
+ struct netdev_queue *txq);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
extern int netdev_budget;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4fc1722..8d276fe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2538,8 +2538,33 @@ static inline int skb_needs_linearize(struct sk_buff *skb,
!(features & NETIF_F_SG)));
}
+int dfwd_direct_xmit(struct sk_buff *skb, struct net_device *dev,
+ void *accel_priv)
+{
+ struct netdev_queue *txq;
+ int ret = NETDEV_TX_BUSY;
+ int index;
+
+ BUG_ON(!dev->netdev_ops->ndo_select_queue);
+ index = dev->netdev_ops->ndo_select_queue(dev, skb, accel_priv);
+
+ local_bh_disable();
+
+ skb_set_queue_mapping(skb, index);
+ txq = netdev_get_tx_queue(dev, index);
+
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_xmit_frozen_or_stopped(txq))
+ ret = dev_hard_start_xmit(skb, dev, txq);
+ HARD_TX_UNLOCK(dev, txq);
+
+ local_bh_enable();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dfwd_direct_xmit);
+
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq, void *accel_priv)
+ struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc = NETDEV_TX_OK;
@@ -2605,13 +2630,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
- else
rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
- if (rc == NETDEV_TX_OK && txq)
+ if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
@@ -2627,10 +2649,7 @@ gso:
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
- else
- rc = ops->ndo_start_xmit(nskb, dev);
+ rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
@@ -2863,7 +2882,7 @@ int dev_queue_xmit(struct sk_buff *skb)
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
- rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+ rc = dev_hard_start_xmit(skb, dev, txq);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef173..553946d 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -402,7 +402,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = ops->ndo_select_queue(dev, skb, NULL);
else
queue_index = __netdev_pick_tx(dev, skb);
queue_index = dev_cap_txqueue(dev, queue_index);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 36c3a4c..a075791 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1061,7 +1061,8 @@ static void ieee80211_uninit(struct net_device *dev)
}
static u16 ieee80211_netdev_select_queue(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
}
@@ -1078,7 +1079,8 @@ static const struct net_device_ops ieee80211_dataif_ops = {
};
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 922a094..7fc899a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
- ret = dev_hard_start_xmit(skb, dev, txq, NULL);
+ ret = dev_hard_start_xmit(skb, dev, txq);
HARD_TX_UNLOCK(dev, txq);
--
1.7.1
------------------------------------------------------------------------------
CenturyLink Cloud: The Leader in Enterprise Cloud Services.
Learn Why More Businesses Are Choosing CenturyLink Cloud For
Critical Workloads, Development Environments & Everything In Between.
Get a Quote or Start a Free Trial Today.
http://pubads.g.doubleclick.net/gampad/clk?id=119420431&iu=/4140/ostg.clktrk
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
^ permalink raw reply related
* RE: [PATCH net] xen-netback: fix vif tx queue race in xenvif_rx_interrupt
From: Paul Durrant @ 2014-01-09 9:35 UTC (permalink / raw)
To: David Miller, majieyue@gmail.com
Cc: netdev@vger.kernel.org, xen-devel@lists.xen.org,
jieyue.majy@alibaba-inc.com, yingbin.wangyb@alibaba-inc.com,
tienan.ftn@alibaba-inc.com, Wei Liu, Ian Campbell, David Vrabel
In-Reply-To: <20140108.151139.4522881609697040.davem@davemloft.net>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of David Miller
> Sent: 08 January 2014 20:12
> To: majieyue@gmail.com
> Cc: netdev@vger.kernel.org; xen-devel@lists.xen.org; jieyue.majy@alibaba-
> inc.com; yingbin.wangyb@alibaba-inc.com; tienan.ftn@alibaba-inc.com; Wei
> Liu; Ian Campbell; David Vrabel
> Subject: Re: [PATCH net] xen-netback: fix vif tx queue race in
> xenvif_rx_interrupt
>
> From: Ma JieYue <majieyue@gmail.com>
> Date: Thu, 9 Jan 2014 03:24:21 +0800
>
> > - if (xenvif_rx_schedulable(vif))
> > + if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
>
> I do not see anything which prevents a netif_stop_queue() call from
> happening
> between these two tests in another thread of control.
>
> This therefore looks like a bandaid and not a real fix.
My fix "xen-netback: improve guest-receive-side flow control" in net-next will make this change irrelevant as it completely removes all this somewhat fragile code.
Paul
> --
> 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 net-next v2 0/3] make skb_checksum_setup generally available
From: Paul Durrant @ 2014-01-09 10:02 UTC (permalink / raw)
To: netdev, xen-devel
Both xen-netfront and xen-netback need to be able to set up the partial
checksum offset of an skb and may also need to recalculate the pseudo-
header checksum in the process. This functionality is currently private
and duplicated between the two drivers.
Patch #1 of this series moves the implementation into the core network code
as there is nothing xen-specific about it and it is potentially useful to
any network driver.
Patch #2 removes the private implementation from netback.
Patch #3 removes the private implementation from netfront.
v2:
- Put skb_checksum_setup in skbuff.c rather than dev.c
- remove inline
^ permalink raw reply
* [PATCH net-next v2 3/3] xen-netfront: use new skb_checksum_setup function
From: Paul Durrant @ 2014-01-09 10:02 UTC (permalink / raw)
To: netdev, xen-devel
Cc: Paul Durrant, Konrad Rzeszutek Wilk, Boris Ostrovsky,
David Vrabel
In-Reply-To: <1389261768-30606-1-git-send-email-paul.durrant@citrix.com>
Use skb_checksum_setup to set up partial checksum offsets rather
then a private implementation.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
---
drivers/net/xen-netfront.c | 48 +++-----------------------------------------
1 file changed, 3 insertions(+), 45 deletions(-)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e59acb1..c41537b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -859,9 +859,7 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np,
static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
{
- struct iphdr *iph;
- int err = -EPROTO;
- int recalculate_partial_csum = 0;
+ bool recalculate_partial_csum = false;
/*
* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
@@ -873,54 +871,14 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
struct netfront_info *np = netdev_priv(dev);
np->rx_gso_checksum_fixup++;
skb->ip_summed = CHECKSUM_PARTIAL;
- recalculate_partial_csum = 1;
+ recalculate_partial_csum = true;
}
/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
- if (skb->protocol != htons(ETH_P_IP))
- goto out;
-
- iph = (void *)skb->data;
-
- switch (iph->protocol) {
- case IPPROTO_TCP:
- if (!skb_partial_csum_set(skb, 4 * iph->ihl,
- offsetof(struct tcphdr, check)))
- goto out;
-
- if (recalculate_partial_csum) {
- struct tcphdr *tcph = tcp_hdr(skb);
- tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - iph->ihl*4,
- IPPROTO_TCP, 0);
- }
- break;
- case IPPROTO_UDP:
- if (!skb_partial_csum_set(skb, 4 * iph->ihl,
- offsetof(struct udphdr, check)))
- goto out;
-
- if (recalculate_partial_csum) {
- struct udphdr *udph = udp_hdr(skb);
- udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
- skb->len - iph->ihl*4,
- IPPROTO_UDP, 0);
- }
- break;
- default:
- if (net_ratelimit())
- pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
- iph->protocol);
- goto out;
- }
-
- err = 0;
-
-out:
- return err;
+ return skb_checksum_setup(skb, recalculate_partial_csum);
}
static int handle_incoming_queue(struct net_device *dev,
--
1.7.10.4
^ permalink raw reply related
* [PATCH net-next v2 1/3] net: add skb_checksum_setup
From: Paul Durrant @ 2014-01-09 10:02 UTC (permalink / raw)
To: netdev, xen-devel
Cc: Paul Durrant, David Miller, Eric Dumazet, Veaceslav Falico,
Alexander Duyck, Nicolas Dichtel
In-Reply-To: <1389261768-30606-1-git-send-email-paul.durrant@citrix.com>
This patch adds a function to set up the partial checksum offset for IP
packets (and optionally re-calculate the pseudo-header checksum) into the
core network code.
The implementation was previously private and duplicated between xen-netback
and xen-netfront, however it is not xen-specific and is potentially useful
to any network driver.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/linux/skbuff.h | 2 +
net/core/skbuff.c | 273 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 275 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d97f2d0..48b7605 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2893,6 +2893,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb)
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
+
u32 __skb_get_poff(const struct sk_buff *skb);
/**
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1d641e7..15057d2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -65,6 +65,7 @@
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
+#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <asm/uaccess.h>
@@ -3549,6 +3550,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
+static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+ unsigned int max)
+{
+ if (skb_headlen(skb) >= len)
+ return 0;
+
+ /* If we need to pullup then pullup to the max, so we
+ * won't need to do it again.
+ */
+ if (max > skb->len)
+ max = skb->len;
+
+ if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
+ return -ENOMEM;
+
+ if (skb_headlen(skb) < len)
+ return -EPROTO;
+
+ return 0;
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * maximally sized IP and TCP or UDP headers.
+ */
+#define MAX_IP_HDR_LEN 128
+
+static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+{
+ unsigned int off;
+ bool fragment;
+ int err;
+
+ fragment = false;
+
+ err = skb_maybe_pull_tail(skb,
+ sizeof(struct iphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+ fragment = true;
+
+ off = ip_hdrlen(skb);
+
+ err = -EPROTO;
+
+ if (fragment)
+ goto out;
+
+ switch (ip_hdr(skb)->protocol) {
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ tcp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
+ break;
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IP_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ udp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
+ break;
+ default:
+ goto out;
+ }
+
+ err = 0;
+
+out:
+ return err;
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * an IPv6 header, all options, and a maximal TCP or UDP header.
+ */
+#define MAX_IPV6_HDR_LEN 256
+
+#define OPT_HDR(type, skb, off) \
+ (type *)(skb_network_header(skb) + (off))
+
+static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
+{
+ int err;
+ u8 nexthdr;
+ unsigned int off;
+ unsigned int len;
+ bool fragment;
+ bool done;
+
+ fragment = false;
+ done = false;
+
+ off = sizeof(struct ipv6hdr);
+
+ err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ nexthdr = ipv6_hdr(skb)->nexthdr;
+
+ len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+ while (off <= len && !done) {
+ switch (nexthdr) {
+ case IPPROTO_DSTOPTS:
+ case IPPROTO_HOPOPTS:
+ case IPPROTO_ROUTING: {
+ struct ipv6_opt_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct ipv6_opt_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
+ nexthdr = hp->nexthdr;
+ off += ipv6_optlen(hp);
+ break;
+ }
+ case IPPROTO_AH: {
+ struct ip_auth_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct ip_auth_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct ip_auth_hdr, skb, off);
+ nexthdr = hp->nexthdr;
+ off += ipv6_authlen(hp);
+ break;
+ }
+ case IPPROTO_FRAGMENT: {
+ struct frag_hdr *hp;
+
+ err = skb_maybe_pull_tail(skb,
+ off +
+ sizeof(struct frag_hdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ hp = OPT_HDR(struct frag_hdr, skb, off);
+
+ if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+ fragment = true;
+
+ nexthdr = hp->nexthdr;
+ off += sizeof(struct frag_hdr);
+ break;
+ }
+ default:
+ done = true;
+ break;
+ }
+ }
+
+ err = -EPROTO;
+
+ if (!done || fragment)
+ goto out;
+
+ switch (nexthdr) {
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct tcphdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ tcp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_TCP, 0);
+ break;
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb,
+ off + sizeof(struct udphdr),
+ MAX_IPV6_HDR_LEN);
+ if (err < 0)
+ goto out;
+
+ if (!skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
+ goto out;
+ }
+
+ if (recalculate)
+ udp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off,
+ IPPROTO_UDP, 0);
+ break;
+ default:
+ goto out;
+ }
+
+ err = 0;
+
+out:
+ return err;
+}
+
+/**
+ * skb_checksum_setup - set up partial checksum offset
+ * @skb: the skb to set up
+ * @recalculate: if true the pseudo-header checksum will be recalculated
+ */
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
+{
+ int err;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ err = skb_checksum_setup_ip(skb, recalculate);
+ break;
+
+ case htons(ETH_P_IPV6):
+ err = skb_checksum_setup_ipv6(skb, recalculate);
+ break;
+
+ default:
+ err = -EPROTO;
+ break;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(skb_checksum_setup);
+
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
--
1.7.10.4
^ permalink raw reply related
* [PATCH net-next v2 2/3] xen-netback: use new skb_checksum_setup function
From: Paul Durrant @ 2014-01-09 10:02 UTC (permalink / raw)
To: netdev, xen-devel; +Cc: Paul Durrant, Ian Campbell, Wei Liu
In-Reply-To: <1389261768-30606-1-git-send-email-paul.durrant@citrix.com>
Use skb_checksum_setup to set up partial checksum offsets rather
then a private implementation.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
---
drivers/net/xen-netback/netback.c | 260 +------------------------------------
1 file changed, 3 insertions(+), 257 deletions(-)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 4f81ac0..2605405 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -39,7 +39,6 @@
#include <linux/udp.h>
#include <net/tcp.h>
-#include <net/ip6_checksum.h>
#include <xen/xen.h>
#include <xen/events.h>
@@ -1048,257 +1047,9 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
return 0;
}
-static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len,
- unsigned int max)
-{
- if (skb_headlen(skb) >= len)
- return 0;
-
- /* If we need to pullup then pullup to the max, so we
- * won't need to do it again.
- */
- if (max > skb->len)
- max = skb->len;
-
- if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
- return -ENOMEM;
-
- if (skb_headlen(skb) < len)
- return -EPROTO;
-
- return 0;
-}
-
-/* This value should be large enough to cover a tagged ethernet header plus
- * maximally sized IP and TCP or UDP headers.
- */
-#define MAX_IP_HDR_LEN 128
-
-static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
- int recalculate_partial_csum)
-{
- unsigned int off;
- bool fragment;
- int err;
-
- fragment = false;
-
- err = maybe_pull_tail(skb,
- sizeof(struct iphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
- fragment = true;
-
- off = ip_hdrlen(skb);
-
- err = -EPROTO;
-
- if (fragment)
- goto out;
-
- switch (ip_hdr(skb)->protocol) {
- case IPPROTO_TCP:
- err = maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate_partial_csum)
- tcp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate_partial_csum)
- udp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
-
- err = 0;
-
-out:
- return err;
-}
-
-/* This value should be large enough to cover a tagged ethernet header plus
- * an IPv6 header, all options, and a maximal TCP or UDP header.
- */
-#define MAX_IPV6_HDR_LEN 256
-
-#define OPT_HDR(type, skb, off) \
- (type *)(skb_network_header(skb) + (off))
-
-static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
- int recalculate_partial_csum)
-{
- int err;
- u8 nexthdr;
- unsigned int off;
- unsigned int len;
- bool fragment;
- bool done;
-
- fragment = false;
- done = false;
-
- off = sizeof(struct ipv6hdr);
-
- err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- nexthdr = ipv6_hdr(skb)->nexthdr;
-
- len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
- while (off <= len && !done) {
- switch (nexthdr) {
- case IPPROTO_DSTOPTS:
- case IPPROTO_HOPOPTS:
- case IPPROTO_ROUTING: {
- struct ipv6_opt_hdr *hp;
-
- err = maybe_pull_tail(skb,
- off +
- sizeof(struct ipv6_opt_hdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
- nexthdr = hp->nexthdr;
- off += ipv6_optlen(hp);
- break;
- }
- case IPPROTO_AH: {
- struct ip_auth_hdr *hp;
-
- err = maybe_pull_tail(skb,
- off +
- sizeof(struct ip_auth_hdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- hp = OPT_HDR(struct ip_auth_hdr, skb, off);
- nexthdr = hp->nexthdr;
- off += ipv6_authlen(hp);
- break;
- }
- case IPPROTO_FRAGMENT: {
- struct frag_hdr *hp;
-
- err = maybe_pull_tail(skb,
- off +
- sizeof(struct frag_hdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- hp = OPT_HDR(struct frag_hdr, skb, off);
-
- if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
- fragment = true;
-
- nexthdr = hp->nexthdr;
- off += sizeof(struct frag_hdr);
- break;
- }
- default:
- done = true;
- break;
- }
- }
-
- err = -EPROTO;
-
- if (!done || fragment)
- goto out;
-
- switch (nexthdr) {
- case IPPROTO_TCP:
- err = maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate_partial_csum)
- tcp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate_partial_csum)
- udp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
-
- err = 0;
-
-out:
- return err;
-}
-
static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
{
- int err = -EPROTO;
- int recalculate_partial_csum = 0;
+ bool recalculate_partial_csum = false;
/* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
* peers can fail to set NETRXF_csum_blank when sending a GSO
@@ -1308,19 +1059,14 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
vif->rx_gso_checksum_fixup++;
skb->ip_summed = CHECKSUM_PARTIAL;
- recalculate_partial_csum = 1;
+ recalculate_partial_csum = true;
}
/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
- if (skb->protocol == htons(ETH_P_IP))
- err = checksum_setup_ip(vif, skb, recalculate_partial_csum);
- else if (skb->protocol == htons(ETH_P_IPV6))
- err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum);
-
- return err;
+ return skb_checksum_setup(skb, recalculate_partial_csum);
}
static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH net-next] ipv6: move IPV6_TCLASS_SHIFT into ipv6.h
From: RongQing Li @ 2014-01-09 10:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <1389173868-14387-1-git-send-email-roy.qing.li@gmail.com>
On Wed, Jan 8, 2014 at 5:37 PM, <roy.qing.li@gmail.com> wrote:
> From: Li RongQing <roy.qing.li@gmail.com>
>
> Two places defined IPV6_TCLASS_SHIFT, so we should move it into ipv6.h,
> and use this macro as possible.
>
> Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
> ---
> include/net/ipv6.h | 1 +
> net/ipv6/fib6_rules.c | 4 +++-
> net/ipv6/ip6_gre.c | 2 --
> net/ipv6/ip6_tunnel.c | 2 --
> net/ipv6/ipv6_sockglue.c | 4 +++-
> 5 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/include/net/ipv6.h b/include/net/ipv6.h
> index 12079c6..d819f7a 100644
> --- a/include/net/ipv6.h
> +++ b/include/net/ipv6.h
> @@ -239,6 +239,7 @@ struct ip6_flowlabel {
> #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
> #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF)
> #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
> +#define IPV6_TCLASS_SHIFT 20
>
> struct ipv6_fl_socklist {
> struct ipv6_fl_socklist __rcu *next;
> diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
> index 3fd0a57..d50c5ca 100644
> --- a/net/ipv6/fib6_rules.c
> +++ b/net/ipv6/fib6_rules.c
> @@ -150,6 +150,8 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
> {
> struct fib6_rule *r = (struct fib6_rule *) rule;
> struct flowi6 *fl6 = &fl->u.ip6;
> + u8 tclass = (ntohl(fl6->flowlabel) & IPV6_TCLASS_MASK) >>
> + IPV6_TCLASS_SHIFT;
Please drop this patch, it has bug.
The correct should be:
u8 tclass =ntohl(fl6->flowlabe & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT
Thanks
-Roy
^ permalink raw reply
* Re: [PATCH net-next 3/3] xfrm: Don't prohibit AH from using ESN feature
From: Steffen Klassert @ 2014-01-09 10:50 UTC (permalink / raw)
To: Fan Du; +Cc: davem, netdev
In-Reply-To: <1389171192-28091-4-git-send-email-fan.du@windriver.com>
On Wed, Jan 08, 2014 at 04:53:12PM +0800, Fan Du wrote:
> Clear checking when user try to use ESN through netlink keymgr for AH.
>
> Signed-off-by: Fan Du <fan.du@windriver.com>
> ---
> net/xfrm/xfrm_user.c | 4 ----
> 1 file changed, 4 deletions(-)
>
> diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
> index 97681a3..f362a78 100644
> --- a/net/xfrm/xfrm_user.c
> +++ b/net/xfrm/xfrm_user.c
> @@ -141,10 +141,6 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
>
> if (!rt)
> return 0;
> -
> - if (p->id.proto != IPPROTO_ESP)
> - return -EINVAL;
> -
You can not change this as long as AH for ipv6 does not
support ESN. Please provide the ipv6 side too.
Also, simply removing this check is wrong in any case.
You have to make sure that we catch if someone tries
to insert an ESN state for other unsupported protocols,
like ipcomp.
^ permalink raw reply
* [PATCH net-next 0/3] bonding: fix bond_3ad RCU usage
From: Veaceslav Falico @ 2014-01-09 10:48 UTC (permalink / raw)
To: netdev; +Cc: Jay Vosburgh, Andy Gospodarek, Veaceslav Falico
While digging through bond_3ad.c I've found that the RCU usage there is
just wrong - it's used as a kind of mutex/spinlock instead of RCU.
This patchset is on top of bond_3ad.c cleanup:
http://www.spinics.net/lists/netdev/msg265447.html
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: netdev@vger.kernel.org
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
^ permalink raw reply
* [PATCH net-next 2/3] bonding: fix __get_first_agg RCU usage
From: Veaceslav Falico @ 2014-01-09 10:48 UTC (permalink / raw)
To: netdev; +Cc: Veaceslav Falico, dingtianhong, Jay Vosburgh, Andy Gospodarek
In-Reply-To: <1389264510-22141-1-git-send-email-vfalico@redhat.com>
Currently, the RCU read lock usage is just wrong - it gets the slave struct
under RCU and continues to use it when RCU lock is released.
However, it's still safe to do this cause we didn't need the
rcu_read_lock() initially - all of the __get_first_agg() callers are either
holding RCU read lock or the RTNL lock, so that we can't sync while in it.
So, remove the useless rcu locking and add a comment.
Fixes: be79bd048 ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
---
drivers/net/bonding/bond_3ad.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 6330beb..70e72d7 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -143,6 +143,7 @@ static inline struct bonding *__get_bond_by_port(struct port *port)
*
* Return the aggregator of the first slave in @bond, or %NULL if it can't be
* found.
+ * The caller must either hold RCU or RTNL lock.
*/
static inline struct aggregator *__get_first_agg(struct port *port)
{
@@ -153,9 +154,7 @@ static inline struct aggregator *__get_first_agg(struct port *port)
if (bond == NULL)
return NULL;
- rcu_read_lock();
first_slave = bond_first_slave_rcu(bond);
- rcu_read_unlock();
return first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL;
}
--
1.8.4
^ permalink raw reply related
* [PATCH net-next 1/3] bonding: fix bond_3ad_set_carrier() RCU usage
From: Veaceslav Falico @ 2014-01-09 10:48 UTC (permalink / raw)
To: netdev; +Cc: Veaceslav Falico, dingtianhong, Jay Vosburgh, Andy Gospodarek
In-Reply-To: <1389264510-22141-1-git-send-email-vfalico@redhat.com>
Currently, its usage is just plainly wrong. It first gets a slave under
RCU, and, after releasing the RCU lock, continues to use it - whilst it can
be freed.
Fix this by ensuring that bond_3ad_set_carrier() is either under RCU read
lock or under the RTNL lock (bond_set_carrier() always holds it).
Fixes: be79bd048ab ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
---
drivers/net/bonding/bond_3ad.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 29db1ca..6330beb 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1597,9 +1597,9 @@ static void ad_agg_selection_logic(struct aggregator *agg)
}
}
- rcu_read_unlock();
-
bond_3ad_set_carrier(bond);
+
+ rcu_read_unlock();
}
/**
@@ -2322,15 +2322,14 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
*
* Called by bond_set_carrier(). Return zero if carrier state does not
* change, nonzero if it does.
+ * The caller must hold RCU read lock.
*/
int bond_3ad_set_carrier(struct bonding *bond)
{
struct aggregator *active;
struct slave *first_slave;
- rcu_read_lock();
first_slave = bond_first_slave_rcu(bond);
- rcu_read_unlock();
if (!first_slave)
return 0;
active = __get_active_agg(&(SLAVE_AD_INFO(first_slave).aggregator));
--
1.8.4
^ permalink raw reply related
* [PATCH net-next 3/3] bonding: fix __get_active_agg() RCU logic
From: Veaceslav Falico @ 2014-01-09 10:48 UTC (permalink / raw)
To: netdev; +Cc: Veaceslav Falico, dingtianhong, Jay Vosburgh, Andy Gospodarek
In-Reply-To: <1389264510-22141-1-git-send-email-vfalico@redhat.com>
Currently, the implementation is meaningless - once again, we take the
slave structure and use it after we've exited RCU critical section.
Fix this by removing the rcu_read_lock() from __get_active_agg(), and
ensuring that all its callers are holding either RCU or RTNL lock.
Fixes: be79bd048 ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
---
drivers/net/bonding/bond_3ad.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 70e72d7..587fd7e 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -674,6 +674,8 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
/**
* __get_active_agg - get the current active aggregator
* @aggregator: the aggregator we're looking at
+ *
+ * Caller must hold either RCU or RTNL lock.
*/
static struct aggregator *__get_active_agg(struct aggregator *aggregator)
{
@@ -681,13 +683,9 @@ static struct aggregator *__get_active_agg(struct aggregator *aggregator)
struct list_head *iter;
struct slave *slave;
- rcu_read_lock();
bond_for_each_slave_rcu(bond, slave, iter)
- if (SLAVE_AD_INFO(slave).aggregator.is_active) {
- rcu_read_unlock();
+ if (SLAVE_AD_INFO(slave).aggregator.is_active)
return &(SLAVE_AD_INFO(slave).aggregator);
- }
- rcu_read_unlock();
return NULL;
}
@@ -1495,11 +1493,11 @@ static void ad_agg_selection_logic(struct aggregator *agg)
struct slave *slave;
struct port *port;
+ rcu_read_lock();
origin = agg;
active = __get_active_agg(agg);
best = (active && agg_device_up(active)) ? active : NULL;
- rcu_read_lock();
bond_for_each_slave_rcu(bond, slave, iter) {
agg = &(SLAVE_AD_INFO(slave).aggregator);
--
1.8.4
^ permalink raw reply related
* Re: [PATCH net-next 0/3] bonding: fix bond_3ad RCU usage
From: Veaceslav Falico @ 2014-01-09 10:56 UTC (permalink / raw)
To: netdev; +Cc: Jay Vosburgh, Andy Gospodarek
In-Reply-To: <1389264510-22141-1-git-send-email-vfalico@redhat.com>
On Thu, Jan 09, 2014 at 11:48:27AM +0100, Veaceslav Falico wrote:
>While digging through bond_3ad.c I've found that the RCU usage there is
>just wrong - it's used as a kind of mutex/spinlock instead of RCU.
>
>This patchset is on top of bond_3ad.c cleanup:
>http://www.spinics.net/lists/netdev/msg265447.html
Self-NAK, seems like I've missed some locks. Sorry for the noise/early
posting, will post v2 soon.
>
>CC: Jay Vosburgh <fubar@us.ibm.com>
>CC: Andy Gospodarek <andy@greyhouse.net>
>CC: netdev@vger.kernel.org
>Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
^ permalink raw reply
* Re: [PATCH net-next 3/3] xfrm: Don't prohibit AH from using ESN feature
From: Fan Du @ 2014-01-09 11:09 UTC (permalink / raw)
To: Steffen Klassert; +Cc: davem, netdev
In-Reply-To: <20140109105021.GY31491@secunet.com>
On 2014年01月09日 18:50, Steffen Klassert wrote:
> On Wed, Jan 08, 2014 at 04:53:12PM +0800, Fan Du wrote:
>> Clear checking when user try to use ESN through netlink keymgr for AH.
>>
>> Signed-off-by: Fan Du<fan.du@windriver.com>
>> ---
>> net/xfrm/xfrm_user.c | 4 ----
>> 1 file changed, 4 deletions(-)
>>
>> diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
>> index 97681a3..f362a78 100644
>> --- a/net/xfrm/xfrm_user.c
>> +++ b/net/xfrm/xfrm_user.c
>> @@ -141,10 +141,6 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
>>
>> if (!rt)
>> return 0;
>> -
>> - if (p->id.proto != IPPROTO_ESP)
>> - return -EINVAL;
>> -
>
> You can not change this as long as AH for ipv6 does not
> support ESN. Please provide the ipv6 side too.
>
> Also, simply removing this check is wrong in any case.
> You have to make sure that we catch if someone tries
> to insert an ESN state for other unsupported protocols,
> like ipcomp.
>
Sure, will add IPv6 support soon :)
--
浮沉随浪只记今朝笑
--fan
^ permalink raw reply
* [PATCH net-next 1/4] bonding: update the primary when slave name changed
From: Ding Tianhong @ 2014-01-09 11:20 UTC (permalink / raw)
To: Jay Vosburgh, Veaceslav Falico, David S. Miller, Netdev
If the primary_slave's name changed, but the bond->prams.primay was
still using the old name, it is conflict with the meaning of the
primary, so update the primary when the slave change its name.
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
drivers/net/bonding/bond_main.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e06c445..de646e2 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2860,9 +2860,19 @@ static int bond_slave_netdev_event(unsigned long event,
*/
break;
case NETDEV_CHANGENAME:
- /*
- * TODO: handle changing the primary's name
+ /* if the primary's name changed,
+ * save the new name for primary.
*/
+ if (USES_PRIMARY(bond->params.mode) &&
+ bond->params.primary[0]) {
+ if (bond->primary_slave &&
+ strcmp(bond->params.primary,
+ bond->primary_slave->dev->name)) {
+ strncpy(bond->params.primary,
+ bond->primary_slave->dev->name,
+ IFNAMSIZ);
+ }
+ }
break;
case NETDEV_FEAT_CHANGE:
bond_compute_features(bond);
--
1.8.0
^ permalink raw reply related
* [PATCH net-next 3/4] bonding: do not save non-existent device to bond primary in sysfs
From: Ding Tianhong @ 2014-01-09 11:20 UTC (permalink / raw)
To: Jay Vosburgh, Veaceslav Falico, David S. Miller, Netdev
Do not save non-existent device to bond primary in sysfs.
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
drivers/net/bonding/bond_options.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 945a666..9b4518f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -501,6 +501,12 @@ int bond_option_primary_set(struct bonding *bond, const char *primary)
goto out;
}
+ if (!__dev_get_by_name(dev_net(bond->dev), primary)) {
+ pr_err("%s: unable to set non-existent device %s to primary.\n",
+ bond->dev->name, primary);
+ goto out;
+ }
+
bond_for_each_slave(bond, slave, iter) {
if (strncmp(slave->dev->name, primary, IFNAMSIZ) == 0) {
pr_info("%s: Setting %s as primary slave.\n",
--
1.8.0
^ permalink raw reply related
* [PATCH net-next 2/4] bonding: do not save non-existent device to bond primary in check params
From: Ding Tianhong @ 2014-01-09 11:20 UTC (permalink / raw)
To: Jay Vosburgh, Veaceslav Falico, David S. Miller, Netdev
When install the bonding, the primay will be use to distinguish
the primary slave for ab, alb and tlb mode, but it is meanless
to save a no existed device, so add check for it.
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
drivers/net/bonding/bond_main.c | 20 +++++++++++++-------
1 file changed, 13 insertions(+), 7 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index de646e2..651c5fd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4246,13 +4246,19 @@ static int bond_check_params(struct bond_params *params)
pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n");
}
- if (primary && !USES_PRIMARY(bond_mode)) {
- /* currently, using a primary only makes sense
- * in active backup, TLB or ALB modes
- */
- pr_warning("Warning: %s primary device specified but has no effect in %s mode\n",
- primary, bond_mode_name(bond_mode));
- primary = NULL;
+ if (primary) {
+ if (!__dev_get_by_name(&init_net, primary)) {
+ pr_warn("Warning: %s primary device is not exist\n",
+ primary);
+ primary = NULL;
+ } else if (!USES_PRIMARY(bond_mode)) {
+ /* currently, using a primary only makes sense
+ * in active backup, TLB or ALB modes
+ */
+ pr_warn("Warning: %s primary device specified but has no effect in %s mode\n",
+ primary, bond_mode_name(bond_mode));
+ primary = NULL;
+ }
}
if (primary && primary_reselect) {
--
1.8.0
^ permalink raw reply related
* [PATCH net-next 4/4] bonding: update bonding.txt for primary description
From: Ding Tianhong @ 2014-01-09 11:20 UTC (permalink / raw)
To: Jay Vosburgh, Veaceslav Falico, David S. Miller, Netdev
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
---
Documentation/networking/bonding.txt | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index a4d925e..5cdb229 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -657,7 +657,8 @@ primary
one slave is preferred over another, e.g., when one slave has
higher throughput than another.
- The primary option is only valid for active-backup mode.
+ The primary option is only valid for active-backup(1),
+ balance-tlb (5) and balance-alb (6) mode.
primary_reselect
--
1.8.0
^ 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