* [net-next 1/8] ixgbevf: Drop all dead or unnecessary code
From: Jeff Kirsher @ 2012-07-17 10:09 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, sassmann, Greg Rose, Jeff Kirsher
In-Reply-To: <1342519759-25137-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
There is a large amount of code present in this driver to support features
that either do no exist or are not supported such ask packet split, DCA, or
RSC. This patch strips out almost all of that code and in the case of
conditionals based on unused flags I am flatting the code out to just the
path that would have been selected.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ethtool.c | 11 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 40 +----
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 199 ++-------------------
3 files changed, 22 insertions(+), 228 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index e8dddf5..af9c657 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -43,7 +43,6 @@
#define IXGBE_ALL_RAR_ENTRIES 16
-#ifdef ETHTOOL_GSTATS
struct ixgbe_stats {
char stat_string[ETH_GSTRING_LEN];
int sizeof_stat;
@@ -75,21 +74,17 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = {
zero_base)},
{"tx_csum_offload_ctxt", IXGBEVF_STAT(hw_csum_tx_good, zero_base,
zero_base)},
- {"rx_header_split", IXGBEVF_STAT(rx_hdr_split, zero_base, zero_base)},
};
#define IXGBE_QUEUE_STATS_LEN 0
#define IXGBE_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbe_gstrings_stats)
#define IXGBEVF_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + IXGBE_QUEUE_STATS_LEN)
-#endif /* ETHTOOL_GSTATS */
-#ifdef ETHTOOL_TEST
static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
"Register test (offline)",
"Link test (on/offline)"
};
#define IXGBE_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN)
-#endif /* ETHTOOL_TEST */
static int ixgbevf_get_settings(struct net_device *netdev,
struct ethtool_cmd *ecmd)
@@ -674,10 +669,8 @@ static int ixgbevf_nway_reset(struct net_device *netdev)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
- if (netif_running(netdev)) {
- if (!adapter->dev_closed)
- ixgbevf_reinit_locked(adapter);
- }
+ if (netif_running(netdev))
+ ixgbevf_reinit_locked(adapter);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 0a1b992..0cbce49 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -52,9 +52,6 @@ struct ixgbevf_tx_buffer {
struct ixgbevf_rx_buffer {
struct sk_buff *skb;
dma_addr_t dma;
- struct page *page;
- dma_addr_t page_dma;
- unsigned int page_offset;
};
struct ixgbevf_ring {
@@ -83,11 +80,6 @@ struct ixgbevf_ring {
* offset associated with this ring, which is different
* for DCB and RSS modes */
-#if defined(CONFIG_DCA) || defined(CONFIG_DCA_MODULE)
- /* cpu for tx queue */
- int cpu;
-#endif
-
u64 v_idx; /* maps directly to the index for this ring in the hardware
* vector array, can also be used for finding the bit in EICR
* and friends that represents the vector for this ring */
@@ -96,16 +88,6 @@ struct ixgbevf_ring {
u16 rx_buf_len;
};
-enum ixgbevf_ring_f_enum {
- RING_F_NONE = 0,
- RING_F_ARRAY_SIZE /* must be last in enum set */
-};
-
-struct ixgbevf_ring_feature {
- int indices;
- int mask;
-};
-
/* How many Rx Buffers do we bundle into one write to the hardware ? */
#define IXGBEVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */
@@ -120,8 +102,6 @@ struct ixgbevf_ring_feature {
#define IXGBEVF_MIN_RXD 64
/* Supported Rx Buffer Sizes */
-#define IXGBEVF_RXBUFFER_64 64 /* Used for packet split */
-#define IXGBEVF_RXBUFFER_128 128 /* Used for packet split */
#define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */
#define IXGBEVF_RXBUFFER_2048 2048
#define IXGBEVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */
@@ -213,18 +193,13 @@ struct ixgbevf_adapter {
/* RX */
struct ixgbevf_ring *rx_ring; /* One per active queue */
int num_rx_queues;
- int num_rx_pools; /* == num_rx_queues in 82598 */
- int num_rx_queues_per_pool; /* 1 if 82598, can be many if 82599 */
u64 hw_csum_rx_error;
u64 hw_rx_no_dma_resources;
u64 hw_csum_rx_good;
u64 non_eop_descs;
int num_msix_vectors;
- int max_msix_q_vectors; /* true count of q_vectors for device */
- struct ixgbevf_ring_feature ring_feature[RING_F_ARRAY_SIZE];
struct msix_entry *msix_entries;
- u64 rx_hdr_split;
u32 alloc_rx_page_failed;
u32 alloc_rx_buff_failed;
@@ -233,14 +208,8 @@ struct ixgbevf_adapter {
*/
u32 flags;
#define IXGBE_FLAG_RX_CSUM_ENABLED (u32)(1)
-#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 1)
-#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 2)
-#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 3)
-#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 4)
-#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 5)
-#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 6)
-#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 7)
-#define IXGBE_FLAG_IN_WATCHDOG_TASK (u32)(1 << 8)
+#define IXGBE_FLAG_IN_WATCHDOG_TASK (u32)(1 << 1)
+
/* OS defined structs */
struct net_device *netdev;
struct pci_dev *pdev;
@@ -254,18 +223,15 @@ struct ixgbevf_adapter {
u32 eitr_param;
unsigned long state;
- u32 *config_space;
u64 tx_busy;
unsigned int tx_ring_count;
unsigned int rx_ring_count;
u32 link_speed;
bool link_up;
- unsigned long link_check_timeout;
struct work_struct watchdog_task;
bool netdev_registered;
- bool dev_closed;
};
enum ixbgevf_state_t {
@@ -302,10 +268,8 @@ extern void ixgbevf_free_tx_resources(struct ixgbevf_adapter *,
struct ixgbevf_ring *);
extern void ixgbevf_update_stats(struct ixgbevf_adapter *adapter);
-#ifdef ETHTOOL_OPS_COMPAT
extern int ethtool_ioctl(struct ifreq *ifr);
-#endif
extern void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter);
extern void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 0368160..3132771 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -177,12 +177,8 @@ static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter,
/* Tx Descriptors needed, worst case */
#define TXD_USE_COUNT(S) (((S) >> IXGBE_MAX_TXD_PWR) + \
(((S) & (IXGBE_MAX_DATA_PER_TXD - 1)) ? 1 : 0))
-#ifdef MAX_SKB_FRAGS
#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \
MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1) /* for context */
-#else
-#define DESC_NEEDED TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD)
-#endif
static void ixgbevf_tx_timeout(struct net_device *netdev);
@@ -255,19 +251,11 @@ cont_loop:
* sees the new next_to_clean.
*/
smp_mb();
-#ifdef HAVE_TX_MQ
if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
!test_bit(__IXGBEVF_DOWN, &adapter->state)) {
netif_wake_subqueue(netdev, tx_ring->queue_index);
++adapter->restart_queue;
}
-#else
- if (netif_queue_stopped(netdev) &&
- !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
- netif_wake_queue(netdev);
- ++adapter->restart_queue;
- }
-#endif
}
/* re-arm the interrupt */
@@ -304,10 +292,7 @@ static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
if (is_vlan && test_bit(tag, adapter->active_vlans))
__vlan_hwaccel_put_tag(skb, tag);
- if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
- napi_gro_receive(&q_vector->napi, skb);
- else
- netif_rx(skb);
+ napi_gro_receive(&q_vector->napi, skb);
}
/**
@@ -365,27 +350,6 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
while (cleaned_count--) {
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
-
- if (!bi->page_dma &&
- (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
- if (!bi->page) {
- bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
- if (!bi->page) {
- adapter->alloc_rx_page_failed++;
- goto no_buffers;
- }
- bi->page_offset = 0;
- } else {
- /* use a half page if we're re-using */
- bi->page_offset ^= (PAGE_SIZE / 2);
- }
-
- bi->page_dma = dma_map_page(&pdev->dev, bi->page,
- bi->page_offset,
- (PAGE_SIZE / 2),
- DMA_FROM_DEVICE);
- }
-
skb = bi->skb;
if (!skb) {
skb = netdev_alloc_skb(adapter->netdev,
@@ -410,14 +374,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
- /* Refresh the desc even if buffer_addrs didn't change because
- * each write-back erases this info. */
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
- rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
- } else {
- rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
- }
+ rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
i++;
if (i == rx_ring->count)
@@ -445,16 +402,6 @@ static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask);
}
-static inline u16 ixgbevf_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc)
-{
- return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info;
-}
-
-static inline u16 ixgbevf_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc)
-{
- return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
-}
-
static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
struct ixgbevf_ring *rx_ring,
int *work_done, int work_to_do)
@@ -466,7 +413,6 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
struct sk_buff *skb;
unsigned int i;
u32 len, staterr;
- u16 hdr_info;
bool cleaned = false;
int cleaned_count = 0;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
@@ -477,24 +423,12 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
rx_buffer_info = &rx_ring->rx_buffer_info[i];
while (staterr & IXGBE_RXD_STAT_DD) {
- u32 upper_len = 0;
if (*work_done >= work_to_do)
break;
(*work_done)++;
rmb(); /* read descriptor and rx_buffer_info after status DD */
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- hdr_info = le16_to_cpu(ixgbevf_get_hdr_info(rx_desc));
- len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
- IXGBE_RXDADV_HDRBUFLEN_SHIFT;
- if (hdr_info & IXGBE_RXDADV_SPH)
- adapter->rx_hdr_split++;
- if (len > IXGBEVF_RX_HDR_SIZE)
- len = IXGBEVF_RX_HDR_SIZE;
- upper_len = le16_to_cpu(rx_desc->wb.upper.length);
- } else {
- len = le16_to_cpu(rx_desc->wb.upper.length);
- }
+ len = le16_to_cpu(rx_desc->wb.upper.length);
cleaned = true;
skb = rx_buffer_info->skb;
prefetch(skb->data - NET_IP_ALIGN);
@@ -508,26 +442,6 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
skb_put(skb, len);
}
- if (upper_len) {
- dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma,
- PAGE_SIZE / 2, DMA_FROM_DEVICE);
- rx_buffer_info->page_dma = 0;
- skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
- rx_buffer_info->page,
- rx_buffer_info->page_offset,
- upper_len);
-
- if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) ||
- (page_count(rx_buffer_info->page) != 1))
- rx_buffer_info->page = NULL;
- else
- get_page(rx_buffer_info->page);
-
- skb->len += upper_len;
- skb->data_len += upper_len;
- skb->truesize += upper_len;
- }
-
i++;
if (i == rx_ring->count)
i = 0;
@@ -539,15 +453,8 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
next_buffer = &rx_ring->rx_buffer_info[i];
if (!(staterr & IXGBE_RXD_STAT_EOP)) {
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- rx_buffer_info->skb = next_buffer->skb;
- rx_buffer_info->dma = next_buffer->dma;
- next_buffer->skb = skb;
- next_buffer->dma = 0;
- } else {
- skb->next = next_buffer->skb;
- skb->next->prev = skb;
- }
+ skb->next = next_buffer->skb;
+ skb->next->prev = skb;
adapter->non_eop_descs++;
goto next_desc;
}
@@ -673,11 +580,6 @@ static int ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget)
r_idx + 1);
}
-#ifndef HAVE_NETDEV_NAPI_LIST
- if (!netif_running(adapter->netdev))
- work_done = 0;
-
-#endif
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
rx_ring = &(adapter->rx_ring[r_idx]);
@@ -1320,29 +1222,14 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
srrctl = IXGBE_SRRCTL_DROP_EN;
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- u16 bufsz = IXGBEVF_RXBUFFER_2048;
- /* grow the amount we can receive on large page machines */
- if (bufsz < (PAGE_SIZE / 2))
- bufsz = (PAGE_SIZE / 2);
- /* cap the bufsz at our largest descriptor size */
- bufsz = min((u16)IXGBEVF_MAX_RXBUFFER, bufsz);
-
- srrctl |= bufsz >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
- srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
- srrctl |= ((IXGBEVF_RX_HDR_SIZE <<
- IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) &
- IXGBE_SRRCTL_BSIZEHDR_MASK);
- } else {
- srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
+ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
- if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE)
- srrctl |= IXGBEVF_RXBUFFER_2048 >>
- IXGBE_SRRCTL_BSIZEPKT_SHIFT;
- else
- srrctl |= rx_ring->rx_buf_len >>
- IXGBE_SRRCTL_BSIZEPKT_SHIFT;
- }
+ if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE)
+ srrctl |= IXGBEVF_RXBUFFER_2048 >>
+ IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+ else
+ srrctl |= rx_ring->rx_buf_len >>
+ IXGBE_SRRCTL_BSIZEPKT_SHIFT;
IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
}
@@ -1362,36 +1249,12 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
u32 rdlen;
int rx_buf_len;
- /* Decide whether to use packet split mode or not */
- if (netdev->mtu > ETH_DATA_LEN) {
- if (adapter->flags & IXGBE_FLAG_RX_PS_CAPABLE)
- adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
- else
- adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
- } else {
- if (adapter->flags & IXGBE_FLAG_RX_1BUF_CAPABLE)
- adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
- else
- adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
- }
-
- /* Set the RX buffer length according to the mode */
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- /* PSRTYPE must be initialized in 82599 */
- u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
- IXGBE_PSRTYPE_UDPHDR |
- IXGBE_PSRTYPE_IPV4HDR |
- IXGBE_PSRTYPE_IPV6HDR |
- IXGBE_PSRTYPE_L2HDR;
- IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype);
- rx_buf_len = IXGBEVF_RX_HDR_SIZE;
- } else {
- IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
- if (netdev->mtu <= ETH_DATA_LEN)
- rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
- else
- rx_buf_len = ALIGN(max_frame, 1024);
- }
+ /* PSRTYPE must be initialized in 82599 */
+ IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
+ if (netdev->mtu <= ETH_DATA_LEN)
+ rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
+ else
+ rx_buf_len = ALIGN(max_frame, 1024);
rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc);
/* Setup the HW Rx Head and Tail Descriptor Pointers and
@@ -1667,10 +1530,6 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
ixgbevf_save_reset_stats(adapter);
ixgbevf_init_last_counter_stats(adapter);
- /* bring the link up in the watchdog, this could race with our first
- * link up interrupt but shouldn't be a problem */
- adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
- adapter->link_check_timeout = jiffies;
mod_timer(&adapter->watchdog_timer, jiffies);
}
@@ -1723,14 +1582,6 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
dev_kfree_skb(this);
} while (skb);
}
- if (!rx_buffer_info->page)
- continue;
- dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma,
- PAGE_SIZE / 2, DMA_FROM_DEVICE);
- rx_buffer_info->page_dma = 0;
- put_page(rx_buffer_info->page);
- rx_buffer_info->page = NULL;
- rx_buffer_info->page_offset = 0;
}
size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
@@ -1958,8 +1809,6 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
/* Start with base case */
adapter->num_rx_queues = 1;
adapter->num_tx_queues = 1;
- adapter->num_rx_pools = adapter->num_rx_queues;
- adapter->num_rx_queues_per_pool = 1;
}
/**
@@ -3220,9 +3069,7 @@ static void ixgbevf_shutdown(struct pci_dev *pdev)
ixgbevf_free_all_rx_resources(adapter);
}
-#ifdef CONFIG_PM
pci_save_state(pdev);
-#endif
pci_disable_device(pdev);
}
@@ -3350,12 +3197,8 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
pci_set_master(pdev);
-#ifdef HAVE_TX_MQ
netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter),
MAX_TX_QUEUES);
-#else
- netdev = alloc_etherdev(sizeof(struct ixgbevf_adapter));
-#endif
if (!netdev) {
err = -ENOMEM;
goto err_alloc_etherdev;
@@ -3396,10 +3239,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
sizeof(struct ixgbe_mbx_operations));
- adapter->flags &= ~IXGBE_FLAG_RX_PS_CAPABLE;
- adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
- adapter->flags |= IXGBE_FLAG_RX_1BUF_CAPABLE;
-
/* setup the private structure */
err = ixgbevf_sw_init(adapter);
if (err)
@@ -3469,8 +3308,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
hw_dbg(hw, "MAC: %d\n", hw->mac.type);
- hw_dbg(hw, "LRO is disabled\n");
-
hw_dbg(hw, "Intel(R) 82599 Virtual Function\n");
cards_found++;
return 0;
--
1.7.10.4
^ permalink raw reply related
* [net-next 2/8] ixgbevf: Drop netdev_registered value since that is already stored in netdev
From: Jeff Kirsher @ 2012-07-17 10:09 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1342519759-25137-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
There is no need to keep a separate netdev_registered value since that is
already stored in the netdev itself.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 1 -
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 6 +-----
2 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 0cbce49..ed19f7e 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -231,7 +231,6 @@ struct ixgbevf_adapter {
bool link_up;
struct work_struct watchdog_task;
- bool netdev_registered;
};
enum ixbgevf_state_t {
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 3132771..3cd8651 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3297,8 +3297,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
if (err)
goto err_register;
- adapter->netdev_registered = true;
-
netif_carrier_off(netdev);
ixgbevf_init_last_counter_stats(adapter);
@@ -3347,10 +3345,8 @@ static void __devexit ixgbevf_remove(struct pci_dev *pdev)
cancel_work_sync(&adapter->reset_task);
cancel_work_sync(&adapter->watchdog_task);
- if (adapter->netdev_registered) {
+ if (netdev->reg_state == NETREG_REGISTERED)
unregister_netdev(netdev);
- adapter->netdev_registered = false;
- }
ixgbevf_reset_interrupt_capability(adapter);
--
1.7.10.4
^ permalink raw reply related
* [net-next 0/8][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2012-07-17 10:09 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series contains updates to ixgbevf.
The following are changes since commit 282f23c6ee343126156dd41218b22ece96d747e3:
tcp: implement RFC 5961 3.2
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Alexander Duyck (8):
ixgbevf: Drop all dead or unnecessary code
ixgbevf: Drop netdev_registered value since that is already stored in
netdev
ixgbevf: Make use of NETIF_F_RXCSUM instead of keeping our own flag
ixgbevf: Drop use of eitr_low and eitr_high for hard coded values
ixgbevf: Cleanup accounting for space needed at start of xmit_frame
ixgbevf: Update q_vector to contain ring pointers instead of bitmaps
ixgbevf: Move Tx clean-up into NAPI context
ixgbevf: Use igb style interrupt masks instead of ixgbe style
drivers/net/ethernet/intel/ixgbevf/defines.h | 27 +-
drivers/net/ethernet/intel/ixgbevf/ethtool.c | 13 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 99 +--
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 820 ++++++---------------
4 files changed, 276 insertions(+), 683 deletions(-)
--
1.7.10.4
^ permalink raw reply
* Re: [PATCH 3/3] ipvs: fix oops in ip_vs_dst_event on rmmod
From: Pablo Neira Ayuso @ 2012-07-17 10:08 UTC (permalink / raw)
To: Simon Horman
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer
In-Reply-To: <1341965963-7275-4-git-send-email-horms@verge.net.au>
On Wed, Jul 11, 2012 at 09:19:23AM +0900, Simon Horman wrote:
> From: Julian Anastasov <ja@ssi.bg>
>
> After commit 39f618b4fd95ae243d940ec64c961009c74e3333 (3.4)
> "ipvs: reset ipvs pointer in netns" we can oops in
> ip_vs_dst_event on rmmod ip_vs because ip_vs_control_cleanup
> is called after the ipvs_core_ops subsys is unregistered and
> net->ipvs is NULL. Fix it by exiting early from ip_vs_dst_event
> if ipvs is NULL. It is safe because all services and dests
> for the net are already freed.
Applied, thanks.
^ permalink raw reply
* Re: [PATCH 1/3] ipvs: fix oops on NAT reply in br_nf context
From: Pablo Neira Ayuso @ 2012-07-17 10:08 UTC (permalink / raw)
To: Simon Horman
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Lin Ming
In-Reply-To: <1341965963-7275-2-git-send-email-horms@verge.net.au>
On Wed, Jul 11, 2012 at 09:19:21AM +0900, Simon Horman wrote:
> From: Lin Ming <mlin@ss.pku.edu.cn>
>
> IPVS should not reset skb->nf_bridge in FORWARD hook
> by calling nf_reset for NAT replies. It triggers oops in
> br_nf_forward_finish.
Applied, thanks.
^ permalink raw reply
* [PATCH 2/2] ipvs: fix oops in ip_vs_dst_event on rmmod
From: pablo @ 2012-07-17 10:06 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1342519589-3348-1-git-send-email-pablo@netfilter.org>
From: Julian Anastasov <ja@ssi.bg>
After commit 39f618b4fd95ae243d940ec64c961009c74e3333 (3.4)
"ipvs: reset ipvs pointer in netns" we can oops in
ip_vs_dst_event on rmmod ip_vs because ip_vs_control_cleanup
is called after the ipvs_core_ops subsys is unregistered and
net->ipvs is NULL. Fix it by exiting early from ip_vs_dst_event
if ipvs is NULL. It is safe because all services and dests
for the net are already freed.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/ipvs/ip_vs_ctl.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d43e3c1..84444dd 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1521,11 +1521,12 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
{
struct net_device *dev = ptr;
struct net *net = dev_net(dev);
+ struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_service *svc;
struct ip_vs_dest *dest;
unsigned int idx;
- if (event != NETDEV_UNREGISTER)
+ if (event != NETDEV_UNREGISTER || !ipvs)
return NOTIFY_DONE;
IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
EnterFunction(2);
@@ -1551,7 +1552,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
}
}
- list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) {
+ list_for_each_entry(dest, &ipvs->dest_trash, n_list) {
__ip_vs_dev_reset(dest, dev);
}
mutex_unlock(&__ip_vs_mutex);
--
1.7.10
^ permalink raw reply related
* [PATCH 1/2] ipvs: fix oops on NAT reply in br_nf context
From: pablo @ 2012-07-17 10:06 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1342519589-3348-1-git-send-email-pablo@netfilter.org>
From: Lin Ming <mlin@ss.pku.edu.cn>
IPVS should not reset skb->nf_bridge in FORWARD hook
by calling nf_reset for NAT replies. It triggers oops in
br_nf_forward_finish.
[ 579.781508] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[ 579.781669] IP: [<ffffffff817b1ca5>] br_nf_forward_finish+0x58/0x112
[ 579.781792] PGD 218f9067 PUD 0
[ 579.781865] Oops: 0000 [#1] SMP
[ 579.781945] CPU 0
[ 579.781983] Modules linked in:
[ 579.782047]
[ 579.782080]
[ 579.782114] Pid: 4644, comm: qemu Tainted: G W 3.5.0-rc5-00006-g95e69f9 #282 Hewlett-Packard /30E8
[ 579.782300] RIP: 0010:[<ffffffff817b1ca5>] [<ffffffff817b1ca5>] br_nf_forward_finish+0x58/0x112
[ 579.782455] RSP: 0018:ffff88007b003a98 EFLAGS: 00010287
[ 579.782541] RAX: 0000000000000008 RBX: ffff8800762ead00 RCX: 000000000001670a
[ 579.782653] RDX: 0000000000000000 RSI: 000000000000000a RDI: ffff8800762ead00
[ 579.782845] RBP: ffff88007b003ac8 R08: 0000000000016630 R09: ffff88007b003a90
[ 579.782957] R10: ffff88007b0038e8 R11: ffff88002da37540 R12: ffff88002da01a02
[ 579.783066] R13: ffff88002da01a80 R14: ffff88002d83c000 R15: ffff88002d82a000
[ 579.783177] FS: 0000000000000000(0000) GS:ffff88007b000000(0063) knlGS:00000000f62d1b70
[ 579.783306] CS: 0010 DS: 002b ES: 002b CR0: 000000008005003b
[ 579.783395] CR2: 0000000000000004 CR3: 00000000218fe000 CR4: 00000000000027f0
[ 579.783505] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 579.783684] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 579.783795] Process qemu (pid: 4644, threadinfo ffff880021b20000, task ffff880021aba760)
[ 579.783919] Stack:
[ 579.783959] ffff88007693cedc ffff8800762ead00 ffff88002da01a02 ffff8800762ead00
[ 579.784110] ffff88002da01a02 ffff88002da01a80 ffff88007b003b18 ffffffff817b26c7
[ 579.784260] ffff880080000000 ffffffff81ef59f0 ffff8800762ead00 ffffffff81ef58b0
[ 579.784477] Call Trace:
[ 579.784523] <IRQ>
[ 579.784562]
[ 579.784603] [<ffffffff817b26c7>] br_nf_forward_ip+0x275/0x2c8
[ 579.784707] [<ffffffff81704b58>] nf_iterate+0x47/0x7d
[ 579.784797] [<ffffffff817ac32e>] ? br_dev_queue_push_xmit+0xae/0xae
[ 579.784906] [<ffffffff81704bfb>] nf_hook_slow+0x6d/0x102
[ 579.784995] [<ffffffff817ac32e>] ? br_dev_queue_push_xmit+0xae/0xae
[ 579.785175] [<ffffffff8187fa95>] ? _raw_write_unlock_bh+0x19/0x1b
[ 579.785179] [<ffffffff817ac417>] __br_forward+0x97/0xa2
[ 579.785179] [<ffffffff817ad366>] br_handle_frame_finish+0x1a6/0x257
[ 579.785179] [<ffffffff817b2386>] br_nf_pre_routing_finish+0x26d/0x2cb
[ 579.785179] [<ffffffff817b2cf0>] br_nf_pre_routing+0x55d/0x5c1
[ 579.785179] [<ffffffff81704b58>] nf_iterate+0x47/0x7d
[ 579.785179] [<ffffffff817ad1c0>] ? br_handle_local_finish+0x44/0x44
[ 579.785179] [<ffffffff81704bfb>] nf_hook_slow+0x6d/0x102
[ 579.785179] [<ffffffff817ad1c0>] ? br_handle_local_finish+0x44/0x44
[ 579.785179] [<ffffffff81551525>] ? sky2_poll+0xb35/0xb54
[ 579.785179] [<ffffffff817ad62a>] br_handle_frame+0x213/0x229
[ 579.785179] [<ffffffff817ad417>] ? br_handle_frame_finish+0x257/0x257
[ 579.785179] [<ffffffff816e3b47>] __netif_receive_skb+0x2b4/0x3f1
[ 579.785179] [<ffffffff816e69fc>] process_backlog+0x99/0x1e2
[ 579.785179] [<ffffffff816e6800>] net_rx_action+0xdf/0x242
[ 579.785179] [<ffffffff8107e8a8>] __do_softirq+0xc1/0x1e0
[ 579.785179] [<ffffffff8135a5ba>] ? trace_hardirqs_off_thunk+0x3a/0x6c
[ 579.785179] [<ffffffff8188812c>] call_softirq+0x1c/0x30
The steps to reproduce as follow,
1. On Host1, setup brige br0(192.168.1.106)
2. Boot a kvm guest(192.168.1.105) on Host1 and start httpd
3. Start IPVS service on Host1
ipvsadm -A -t 192.168.1.106:80 -s rr
ipvsadm -a -t 192.168.1.106:80 -r 192.168.1.105:80 -m
4. Run apache benchmark on Host2(192.168.1.101)
ab -n 1000 http://192.168.1.106/
ip_vs_reply4
ip_vs_out
handle_response
ip_vs_notrack
nf_reset()
{
skb->nf_bridge = NULL;
}
Actually, IPVS wants in this case just to replace nfct
with untracked version. So replace the nf_reset(skb) call
in ip_vs_notrack() with a nf_conntrack_put(skb->nfct) call.
Signed-off-by: Lin Ming <mlin@ss.pku.edu.cn>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/ip_vs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d6146b4..95374d1 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1425,7 +1425,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (!ct || !nf_ct_is_untracked(ct)) {
- nf_reset(skb);
+ nf_conntrack_put(skb->nfct);
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
--
1.7.10
^ permalink raw reply related
* [PATCH 0/2] ipvs fixes for 3.5
From: pablo @ 2012-07-17 10:06 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
From: Pablo Neira Ayuso <pablo@netfilter.org>
Hi David,
I know that we're in fairly late stage to request pulls, but the IPVS people
pinged me with little patches with oops fixes last week.
One of them was recently introduced (during the 3.4 development cycle) while
cleaning up the IPVS netns support. They are:
* Fix one regression introduced in 3.4 while cleaning up the
netns support for IPVS, from Julian Anastasov.
* Fix one oops triggered due to resetting the conntrack attached to the skb
instead of just putting it in the forward hook, from Lin Ming. This problem
seems to be there since 2.6.37 according to Simon Horman.
You can pull these changes from:
git://1984.lsi.us.es/nf master
Thanks!
Julian Anastasov (1):
ipvs: fix oops in ip_vs_dst_event on rmmod
Lin Ming (1):
ipvs: fix oops on NAT reply in br_nf context
include/net/ip_vs.h | 2 +-
net/netfilter/ipvs/ip_vs_ctl.c | 5 +++--
2 files changed, 4 insertions(+), 3 deletions(-)
--
1.7.10
^ permalink raw reply
* Re: [net] ixgbevf: Fix panic when loading driver
From: David Miller @ 2012-07-17 9:57 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: alexander.h.duyck, netdev, gospo, sassmann
In-Reply-To: <1342518288-13522-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Tue, 17 Jul 2012 02:44:48 -0700
> From: Alexander Duyck <alexander.h.duyck@intel.com>
>
> This patch addresses a kernel panic seen when setting up the interface.
> Specifically we see a NULL pointer dereference on the Tx descriptor cleanup
> path when enabling interrupts. This change corrects that so it cannot
> occur.
>
> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
> Acked-by: Greg Rose <gregory.v.rose@intel.com>
> Tested-by: Sibai Li <sibai.li@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied, thanks Jeff.
^ permalink raw reply
* Re: [PATCH 2/3] ipvs: add missing lock in ip_vs_ftp_init_conn()
From: Pablo Neira Ayuso @ 2012-07-17 9:46 UTC (permalink / raw)
To: Xiaotian Feng
Cc: Simon Horman, lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer,
Xiaotian Feng, Patrick McHardy, David S. Miller
In-Reply-To: <CAJn8CcEChmrFvASChJfj7qK8F-my79fn+-G8ttst02Sts15y6Q@mail.gmail.com>
Hi,
On Tue, Jul 17, 2012 at 09:44:01AM +0800, Xiaotian Feng wrote:
> On Tue, Jul 17, 2012 at 5:07 AM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> > Hi Simon,
> >
> > On Wed, Jul 11, 2012 at 09:19:22AM +0900, Simon Horman wrote:
> >> From: Xiaotian Feng <xtfeng@gmail.com>
> >>
> >> We met a kernel panic in 2.6.32.43 kernel:
> > [...]
> >> net/netfilter/ipvs/ip_vs_ftp.c | 2 ++
> >> 1 file changed, 2 insertions(+)
> >>
> >> diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
> >> index b20b29c..c2bc264 100644
> >> --- a/net/netfilter/ipvs/ip_vs_ftp.c
> >> +++ b/net/netfilter/ipvs/ip_vs_ftp.c
> >> @@ -65,8 +65,10 @@ static int ip_vs_ftp_pasv;
> >> static int
> >> ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp)
> >> {
> >> + spin_lock(&cp->lock);
> >> /* We use connection tracking for the command connection */
> >> cp->flags |= IP_VS_CONN_F_NFCT;
> >> + spin_unlock(&cp->lock);
> >> return 0;
> >
> > The conntrack support for FTP IPVS helper seems to be there since
> > 2.6.37.
> >
> > However, the patch description mentions 2.6.32.43.
> >
> > Something doesn't match here, could you clarify this?
> >
>
> Sorry for the misleading description in the patch. We found the panic
> in 2.6.32.43 is caused by changing cp->flags without protection. In
> 2.6.32.43, ip_vs_process_message changes cp->flags without protection
> while update active/inactive flags for the connection.
>
> After code inspiration, we found in 3.x kernel, it is accidentally
> fixed by commit f73181c. But with ip_vs_app changes,
> ip_vs_ftp_init_conn() will have chance to change cp->flags without
> protection. So it is a potential bug in 3.x kernel.
Please, then fix the patch description and resend the patch to me.
I have to justify why this is pushed forward to David, and using
misleading description for the patch is not the way to go.
Regarding this bitset operation, I think it's way better if you use
bitwise operations for those cp->flags. Getting the spin_lock just to
set the flag is way too much.
^ permalink raw reply
* [net] ixgbevf: Fix panic when loading driver
From: Jeff Kirsher @ 2012-07-17 9:44 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, sassmann, Jeff Kirsher
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch addresses a kernel panic seen when setting up the interface.
Specifically we see a NULL pointer dereference on the Tx descriptor cleanup
path when enabling interrupts. This change corrects that so it cannot
occur.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 8b304a4..41e3225 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -201,6 +201,9 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter,
unsigned int i, eop, count = 0;
unsigned int total_bytes = 0, total_packets = 0;
+ if (test_bit(__IXGBEVF_DOWN, &adapter->state))
+ return true;
+
i = tx_ring->next_to_clean;
eop = tx_ring->tx_buffer_info[i].next_to_watch;
eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
From: Eric Dumazet @ 2012-07-17 8:48 UTC (permalink / raw)
To: Zhong Hongbo; +Cc: Andy Cress, netdev
In-Reply-To: <50051C83.7020504@windriver.com>
On Tue, 2012-07-17 at 16:04 +0800, Zhong Hongbo wrote:
> Hi Eric,
>
> When forwarding network packages at the network layer, the variable
> value of skb->transport_header is unknown. In my test, the variable
> value of skb->transport_header is equal to skb->network_header. So
> When you count the checksum as following:
>
> offset = skb_transport_offset(skb);
>
> skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
> We should only count the TCP checksum, But it maybe include IP part.
>
> tcp_hdr(skb)->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
> skb->len - offset, IPPROTO_TCP, skb->csum);
> We should fill the checksum in TCP package, But maybe fill it in other
> location and cover the useful information, such as source ip.
>
> So We should count the TCP checksum and fill it in the correct
> location. Or else the forwarding network package will be drop for the
> error checksum.
>
So maybe you should instead test
if (skb->ip_summed == CHECKSUM_PARTIAL) {
...
skb_checksum_start_offset(skb); /* is valid */
}
^ permalink raw reply
* Claim requirements
From: Donna Ashworth @ 2012-07-17 2:06 UTC (permalink / raw)
You are receiving this message because you are a Winner of 300,000 Pounds from Nokia Online Lottery game 2012.
Claim requirements are as follows:
(1) Your full names
(2) Contact Address
(3) Age
(4) Occupation
(5) Telephone
(6) Sex
(7) Nationality
Contact Mr. Thomas Hillary on (nokiadp77@yahoo.cn) Tel: +447024081232
Copyright ©2012 Nokia. All rights reserved.
^ permalink raw reply
* Re: [PATCH net-next v2] tcp: implement RFC 5961 3.2
From: David Miller @ 2012-07-17 8:36 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev, kkiran
In-Reply-To: <1342512785.2626.230.camel@edumazet-glaptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 17 Jul 2012 10:13:05 +0200
> From: Eric Dumazet <edumazet@google.com>
>
> Implement the RFC 5691 mitigation against Blind
> Reset attack using RST bit.
>
> Idea is to validate incoming RST sequence,
> to match RCV.NXT value, instead of previouly accepted
> window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND)
>
> If sequence is in window but not an exact match, send
> a "challenge ACK", so that the other part can resend an
> RST with the appropriate sequence.
>
> Add a new sysctl, tcp_challenge_ack_limit, to limit
> number of challenge ACK sent per second.
>
> Add a new SNMP counter to count number of challenge acks sent.
> (netstat -s | grep TCPChallengeACK)
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Looks good, applied, thanks Eric.
^ permalink raw reply
* Re: [PATCH] ipv6: fix unappropriate errno returned for non-multicast address
From: David Miller @ 2012-07-17 8:35 UTC (permalink / raw)
To: lw; +Cc: netdev
In-Reply-To: <5005143B.9000301@cn.fujitsu.com>
From: Li Wei <lw@cn.fujitsu.com>
Date: Tue, 17 Jul 2012 15:28:59 +0800
> We need to check the passed in multicast address and return
> appropriate errno(EINVAL) if it is not valid. And it's no need
> to walk through the ipv6_mc_list in this situation.
>
> Signed-off-by: Li Wei <lw@cn.fujitsu.com>
Applied to net-next, thanks.
^ permalink raw reply
* Re: pull request: linux-can-next 2012-07-17
From: David Miller @ 2012-07-17 8:34 UTC (permalink / raw)
To: mkl; +Cc: netdev, linux-can, kernel
In-Reply-To: <5005194A.4090900@pengutronix.de>
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 17 Jul 2012 09:50:34 +0200
> the fifth pull request for upcoming v3.6 net-next. The first two
> patches (created by me) add const qualifiers to the flexcan and
> mpc5xxx_can driver. The next patch by Julia Lawall fixes a return value
> problem in the error path of the softing driver.
Pulled, thanks.
^ permalink raw reply
* Re: bnx2x: organize BDs calculation for stop/resumelogin
From: David Miller @ 2012-07-17 8:32 UTC (permalink / raw)
To: dmitry; +Cc: netdev
In-Reply-To: <1342512490.16812.4.camel@lb-tlvb-dmitry>
From: "Dmitry Kravkov" <dmitry@broadcom.com>
Date: Tue, 17 Jul 2012 11:08:10 +0300
> Hi Dave,
>
> I see this patch has been marked as "accepted" in patchwork
> http://patchwork.ozlabs.org/patch/167337/
>
> But i can't see it applied to the git-tree.
>
> Was it missed somehow? Or delayed for some reason?
Thanks for catching that, I've fixed this up, it's applied for
sure now :-)
^ permalink raw reply
* [PATCH net-next v2] tcp: implement RFC 5961 3.2
From: Eric Dumazet @ 2012-07-17 8:13 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Kiran Kumar Kella
From: Eric Dumazet <edumazet@google.com>
Implement the RFC 5691 mitigation against Blind
Reset attack using RST bit.
Idea is to validate incoming RST sequence,
to match RCV.NXT value, instead of previouly accepted
window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND)
If sequence is in window but not an exact match, send
a "challenge ACK", so that the other part can resend an
RST with the appropriate sequence.
Add a new sysctl, tcp_challenge_ack_limit, to limit
number of challenge ACK sent per second.
Add a new SNMP counter to count number of challenge acks sent.
(netstat -s | grep TCPChallengeACK)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kiran Kumar Kella <kkiran@broadcom.com>
---
v2: respin to net-next, better changelog
tcp_challengeack_limit -> tcp_challenge_ack_limit
tcp_time_stamp -> jiffies
Documentation/networking/ip-sysctl.txt | 5 +++
include/linux/snmp.h | 1
include/net/tcp.h | 1
net/ipv4/proc.c | 1
net/ipv4/sysctl_net_ipv4.c | 7 +++++
net/ipv4/tcp_input.c | 31 ++++++++++++++++++++++-
6 files changed, 45 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e20c17a..e1e0215 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -565,6 +565,11 @@ tcp_limit_output_bytes - INTEGER
reduce the size of individual GSO packet (64KB being the max)
Default: 131072
+tcp_challenge_ack_limit - INTEGER
+ Limits number of Challenge ACK sent per second, as recommended
+ in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
+ Default: 100
+
UDP variables:
udp_mem - vector of 3 INTEGERs: min, pressure, max
diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 6e4c511..673e0e9 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -237,6 +237,7 @@ enum
LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */
LINUX_MIB_TCPOFODROP, /* TCPOFODrop */
LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */
+ LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */
__LINUX_MIB_MAX
};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 439984b..85c5090 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -254,6 +254,7 @@ extern int sysctl_tcp_thin_linear_timeouts;
extern int sysctl_tcp_thin_dupack;
extern int sysctl_tcp_early_retrans;
extern int sysctl_tcp_limit_output_bytes;
+extern int sysctl_tcp_challenge_ack_limit;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index dae25e76..3e8e78f 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -261,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE),
SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
+ SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 70730f7..3f6a1e7 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -605,6 +605,13 @@ static struct ctl_table ipv4_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "tcp_challenge_ack_limit",
+ .data = &sysctl_tcp_challenge_ack_limit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
#ifdef CONFIG_NET_DMA
{
.procname = "tcp_dma_copybreak",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc4e12f..c841a89 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -88,6 +88,9 @@ int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 1;
EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
+/* rfc5961 challenge ack rate limiting */
+int sysctl_tcp_challenge_ack_limit = 100;
+
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -5247,6 +5250,23 @@ out:
}
#endif /* CONFIG_NET_DMA */
+static void tcp_send_challenge_ack(struct sock *sk)
+{
+ /* unprotected vars, we dont care of overwrites */
+ static u32 challenge_timestamp;
+ static unsigned int challenge_count;
+ u32 now = jiffies / HZ;
+
+ if (now != challenge_timestamp) {
+ challenge_timestamp = now;
+ challenge_count = 0;
+ }
+ if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+ tcp_send_ack(sk);
+ }
+}
+
/* Does PAWS and seqno based validation of an incoming segment, flags will
* play significant role here.
*/
@@ -5283,7 +5303,16 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
/* Step 2: check RST bit */
if (th->rst) {
- tcp_reset(sk);
+ /* RFC 5961 3.2 :
+ * If sequence number exactly matches RCV.NXT, then
+ * RESET the connection
+ * else
+ * Send a challenge ACK
+ */
+ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
+ tcp_reset(sk);
+ else
+ tcp_send_challenge_ack(sk);
goto discard;
}
^ permalink raw reply related
* bnx2x: organize BDs calculation for stop/resumelogin
From: Dmitry Kravkov @ 2012-07-17 8:08 UTC (permalink / raw)
To: davem; +Cc: netdev
Hi Dave,
I see this patch has been marked as "accepted" in patchwork
http://patchwork.ozlabs.org/patch/167337/
But i can't see it applied to the git-tree.
Was it missed somehow? Or delayed for some reason?
Thanks,
Dmitry
^ permalink raw reply
* Re: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
From: Zhong Hongbo @ 2012-07-17 8:04 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Andy Cress, netdev
In-Reply-To: <1342508968.2626.148.camel@edumazet-glaptop>
On 07/17/2012 03:09 PM, Eric Dumazet wrote:
> On Mon, 2012-07-16 at 13:03 -0700, Andy Cress wrote:
>> Author: Zhong Hongbo <hongbo.zhong@windriver.com>
>>
>> Due to some unknown hardware limitations the pch_gbe hardware cannot
>> calculate checksums when the length of network package is less
>> than 64 bytes, where we will surprisingly encounter a problem of
>> the destination IP incorrectly changed.
>>
>> When forwarding network packages at the network layer the IP packages
>> won't be relayed to the upper transport layer and analyzed there,
>> consequently, skb->transport_header pointer will be mistakenly remained
>> the same as that of skb->network_header, resulting in TCP checksum
>> wrongly
>> filled into the field of destination IP in IP header.
>>
>> We can fix this issue by manually calculate the offset of the TCP
>> checksum
>> and update it accordingly.
>>
>> We would normally use the skb_checksum_start_offset(skb) here, but in
>> this
>> case it is sometimes -2 (csum_start=0 - skb_headroom=2 => -2), hence the
>> manual calculation.
>>
>> Signed-off-by: Zhong Hongbo <hongbo.zhong@windriver.com>
>> Merged-by: Andy Cress <andy.cress@us.kontron.com>
>
> Hmm... I fail to understand why you care about NIC doing checksums,
Hi Eric,
When forwarding network packages at the network layer, the variable value of skb->transport_header is unknown. In my test, the variable value of skb->transport_header is equal to skb->network_header. So When you count the checksum as following:
offset = skb_transport_offset(skb);
skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
We should only count the TCP checksum, But it maybe include IP part.
tcp_hdr(skb)->check = csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len - offset, IPPROTO_TCP, skb->csum);
We should fill the checksum in TCP package, But maybe fill it in other location and cover the useful information, such as source ip.
So We should count the TCP checksum and fill it in the correct location. Or else the forwarding network package will be drop for the error checksum.
> while pch_gbe_tx_queue() make a _copy_ of each outgoing
> packets.
>
> There _must_ be a way to avoid most of these copies (ie not touching
> payload), only mess with the header to insert these 2 nul bytes ?
This is other fix, my patch just fix checksum error issue.
Thanks,
hongbo
>
> /* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
>
> So at device setup : dev->needed_headroom = 2;
>
> and in xmit,
>
> if (skb_headroom(skb) < 2) {
> struct sk_buff *skb_new;
>
> skb_new = skb_realloc_headroom(skb, 2);
> if (!skb_new) { handle error }
> consume_skb(skb);
> skb = skb_new;
> }
> ptr = skb_push(skb, 2);
> memmove(ptr, ptr + 2, ETH_HLEN);
> ptr[ETH_HLEN] = 0;
> ptr[ETH_HLEN + 1] = 0;
>
>
>
>
>
^ permalink raw reply
* pull request: linux-can-next 2012-07-17
From: Marc Kleine-Budde @ 2012-07-17 7:50 UTC (permalink / raw)
To: davem; +Cc: Linux Netdev List, linux-can@vger.kernel.org,
kernel@pengutronix.de
[-- Attachment #1: Type: text/plain, Size: 1570 bytes --]
Hello David,
the fifth pull request for upcoming v3.6 net-next. The first two
patches (created by me) add const qualifiers to the flexcan and
mpc5xxx_can driver. The next patch by Julia Lawall fixes a return value
problem in the error path of the softing driver.
regards, Marc
--
The following changes since commit 6ba6047bf99cf4ade4f63b6b3d97cc3ad763b678:
gigaset: silence GCC warning for unused 'format_ie' (2012-07-16 23:23:53 -0700)
are available in the git repository at:
git://gitorious.org/linux-can/linux-can-next.git for-davem
for you to fetch changes up to da78b7998e365b3f90b2a1a55d3b6ba6cc0c5905:
can: softing: softing_main: ensure a consistent return value in error case (2012-07-17 09:35:59 +0200)
----------------------------------------------------------------
Julia Lawall (1):
can: softing: softing_main: ensure a consistent return value in error case
Marc Kleine-Budde (2):
can: flexcan: make flexcan_priv.devtype_data member point to const data
can: mpc5xxx_can: make data in mpc5xxx_can_probe const
drivers/net/can/flexcan.c | 4 ++--
drivers/net/can/mscan/mpc5xxx_can.c | 2 +-
drivers/net/can/softing/softing_main.c | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
--
Pengutronix e.K. | Marc Kleine-Budde |
Industrial Linux Solutions | Phone: +49-231-2826-924 |
Vertretung West/Dortmund | Fax: +49-5121-206917-5555 |
Amtsgericht Hildesheim, HRA 2686 | http://www.pengutronix.de |
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 262 bytes --]
^ permalink raw reply
* Re: [PATCH] drivers: connector: fixed coding style issues
From: Evgeniy Polyakov @ 2012-07-17 7:26 UTC (permalink / raw)
To: David Miller; +Cc: joe, valentin.ilie, netdev
In-Reply-To: <20120716.232441.1586213661098921458.davem@davemloft.net>
On Mon, Jul 16, 2012 at 11:24:41PM -0700, David Miller (davem@davemloft.net) wrote:
>
> I applied v2 of this patch, thanks.
Thanks, everyone!
--
Evgeniy Polyakov
^ permalink raw reply
* Re: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
From: Eric Dumazet @ 2012-07-17 7:33 UTC (permalink / raw)
To: Andy Cress; +Cc: netdev, Zhong Hongbo
In-Reply-To: <1342508968.2626.148.camel@edumazet-glaptop>
On Tue, 2012-07-17 at 09:09 +0200, Eric Dumazet wrote:
> Hmm... I fail to understand why you care about NIC doing checksums,
> while pch_gbe_tx_queue() make a _copy_ of each outgoing
> packets.
>
> There _must_ be a way to avoid most of these copies (ie not touching
> payload), only mess with the header to insert these 2 nul bytes ?
>
> /* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
>
> So at device setup : dev->needed_headroom = 2;
>
> and in xmit,
>
> if (skb_headroom(skb) < 2) {
> struct sk_buff *skb_new;
>
> skb_new = skb_realloc_headroom(skb, 2);
> if (!skb_new) { handle error }
> consume_skb(skb);
> skb = skb_new;
> }
> ptr = skb_push(skb, 2);
> memmove(ptr, ptr + 2, ETH_HLEN);
> ptr[ETH_HLEN] = 0;
> ptr[ETH_HLEN + 1] = 0;
>
>
Something like the following (untested) patch
drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 55 +++++-----
1 file changed, 29 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index b100656..2d3d982 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -1163,7 +1163,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
struct pch_gbe_hw *hw = &adapter->hw;
struct pch_gbe_tx_desc *tx_desc;
struct pch_gbe_buffer *buffer_info;
- struct sk_buff *tmp_skb;
+ char *ptr;
unsigned int frame_ctrl;
unsigned int ring_num;
@@ -1221,18 +1221,27 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
buffer_info = &tx_ring->buffer_info[ring_num];
- tmp_skb = buffer_info->skb;
+ if (skb_headroom(skb) < 2) {
+ struct sk_buff *skb_new;
+
+ skb_new = skb_realloc_headroom(skb, 2);
+ if (!skb_new) {
+ tx_ring->next_to_use = ring_num;
+ dev_kfree_skb_any(skb);
+ return;
+ }
+ consume_skb(skb);
+ skb = skb_new;
+ }
/* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
- memcpy(tmp_skb->data, skb->data, ETH_HLEN);
- tmp_skb->data[ETH_HLEN] = 0x00;
- tmp_skb->data[ETH_HLEN + 1] = 0x00;
- tmp_skb->len = skb->len;
- memcpy(&tmp_skb->data[ETH_HLEN + 2], &skb->data[ETH_HLEN],
- (skb->len - ETH_HLEN));
+ ptr = skb_push(skb, 2);
+ memmove(ptr, ptr + 2, ETH_HLEN);
+ ptr[ETH_HLEN] = 0x00;
+ ptr[ETH_HLEN + 1] = 0x00;
/*-- Set Buffer information --*/
- buffer_info->length = tmp_skb->len;
- buffer_info->dma = dma_map_single(&adapter->pdev->dev, tmp_skb->data,
+ buffer_info->length = skb->len;
+ buffer_info->dma = dma_map_single(&adapter->pdev->dev, skb->data,
buffer_info->length,
DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma)) {
@@ -1240,18 +1249,20 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
buffer_info->dma = 0;
buffer_info->time_stamp = 0;
tx_ring->next_to_use = ring_num;
+ dev_kfree_skb_any(skb);
return;
}
buffer_info->mapped = true;
buffer_info->time_stamp = jiffies;
+ buffer_info->skb = skb;
/*-- Set Tx descriptor --*/
tx_desc = PCH_GBE_TX_DESC(*tx_ring, ring_num);
- tx_desc->buffer_addr = (buffer_info->dma);
- tx_desc->length = (tmp_skb->len);
- tx_desc->tx_words_eob = ((tmp_skb->len + 3));
+ tx_desc->buffer_addr = buffer_info->dma;
+ tx_desc->length = skb->len;
+ tx_desc->tx_words_eob = skb->len + 3;
tx_desc->tx_frame_ctrl = (frame_ctrl);
- tx_desc->gbec_status = (DSC_INIT16);
+ tx_desc->gbec_status = DSC_INIT16;
if (unlikely(++ring_num == tx_ring->count))
ring_num = 0;
@@ -1265,7 +1276,6 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter,
pch_tx_timestamp(adapter, skb);
#endif
- dev_kfree_skb_any(skb);
}
/**
@@ -1543,19 +1553,12 @@ static void pch_gbe_alloc_tx_buffers(struct pch_gbe_adapter *adapter,
struct pch_gbe_tx_ring *tx_ring)
{
struct pch_gbe_buffer *buffer_info;
- struct sk_buff *skb;
unsigned int i;
- unsigned int bufsz;
struct pch_gbe_tx_desc *tx_desc;
- bufsz =
- adapter->hw.mac.max_frame_size + PCH_GBE_DMA_ALIGN + NET_IP_ALIGN;
-
for (i = 0; i < tx_ring->count; i++) {
buffer_info = &tx_ring->buffer_info[i];
- skb = netdev_alloc_skb(adapter->netdev, bufsz);
- skb_reserve(skb, PCH_GBE_DMA_ALIGN);
- buffer_info->skb = skb;
+ buffer_info->skb = NULL;
tx_desc = PCH_GBE_TX_DESC(*tx_ring, i);
tx_desc->gbec_status = (DSC_INIT16);
}
@@ -1622,9 +1625,9 @@ pch_gbe_clean_tx(struct pch_gbe_adapter *adapter,
buffer_info->length, DMA_TO_DEVICE);
buffer_info->mapped = false;
}
- if (buffer_info->skb) {
- pr_debug("trim buffer_info->skb : %d\n", i);
- skb_trim(buffer_info->skb, 0);
+ if (skb) {
+ dev_kfree_skb_any(skb);
+ buffer_info->skb = NULL;
}
tx_desc->gbec_status = DSC_INIT16;
if (unlikely(++i == tx_ring->count))
^ permalink raw reply related
* [PATCH] ipv6: fix unappropriate errno returned for non-multicast address
From: Li Wei @ 2012-07-17 7:28 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev
We need to check the passed in multicast address and return
appropriate errno(EINVAL) if it is not valid. And it's no need
to walk through the ipv6_mc_list in this situation.
Signed-off-by: Li Wei <lw@cn.fujitsu.com>
---
net/ipv6/mcast.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 6d0f5dc..92f8e48 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -211,6 +211,9 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
struct ipv6_mc_socklist __rcu **lnk;
struct net *net = sock_net(sk);
+ if (!ipv6_addr_is_multicast(addr))
+ return -EINVAL;
+
spin_lock(&ipv6_sk_mc_lock);
for (lnk = &np->ipv6_mc_list;
(mc_lst = rcu_dereference_protected(*lnk,
--
1.7.1
^ permalink raw reply related
* Re: [PATCH 1/4] pch_gbe: Fix the checksum fill to the error location
From: Eric Dumazet @ 2012-07-17 7:09 UTC (permalink / raw)
To: Andy Cress; +Cc: netdev, Zhong Hongbo
In-Reply-To: <40680C535D6FE6498883F1640FACD44D011432D4@ka-exchange-1.kontronamerica.local>
On Mon, 2012-07-16 at 13:03 -0700, Andy Cress wrote:
> Author: Zhong Hongbo <hongbo.zhong@windriver.com>
>
> Due to some unknown hardware limitations the pch_gbe hardware cannot
> calculate checksums when the length of network package is less
> than 64 bytes, where we will surprisingly encounter a problem of
> the destination IP incorrectly changed.
>
> When forwarding network packages at the network layer the IP packages
> won't be relayed to the upper transport layer and analyzed there,
> consequently, skb->transport_header pointer will be mistakenly remained
> the same as that of skb->network_header, resulting in TCP checksum
> wrongly
> filled into the field of destination IP in IP header.
>
> We can fix this issue by manually calculate the offset of the TCP
> checksum
> and update it accordingly.
>
> We would normally use the skb_checksum_start_offset(skb) here, but in
> this
> case it is sometimes -2 (csum_start=0 - skb_headroom=2 => -2), hence the
> manual calculation.
>
> Signed-off-by: Zhong Hongbo <hongbo.zhong@windriver.com>
> Merged-by: Andy Cress <andy.cress@us.kontron.com>
Hmm... I fail to understand why you care about NIC doing checksums,
while pch_gbe_tx_queue() make a _copy_ of each outgoing
packets.
There _must_ be a way to avoid most of these copies (ie not touching
payload), only mess with the header to insert these 2 nul bytes ?
/* [Header:14][payload] ---> [Header:14][paddong:2][payload] */
So at device setup : dev->needed_headroom = 2;
and in xmit,
if (skb_headroom(skb) < 2) {
struct sk_buff *skb_new;
skb_new = skb_realloc_headroom(skb, 2);
if (!skb_new) { handle error }
consume_skb(skb);
skb = skb_new;
}
ptr = skb_push(skb, 2);
memmove(ptr, ptr + 2, ETH_HLEN);
ptr[ETH_HLEN] = 0;
ptr[ETH_HLEN + 1] = 0;
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox