commits August 2012

commits@lists.open-mesh.org

1 participants
355 discussions

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 381294331ed2858f8e75223310f873d580921366 Author: Ying Xue <ying.xue(a)windriver.com> Date: Thu Aug 16 12:09:09 2012 +0000 tipc: manually inline single use media_name_valid routine After eliminating the mechanism which checks whether all letters in media name string are within a given character set, the media_name_valid routine becomes trivial. It is also only used once, so it is unnecessary to keep it as a separate function. Signed-off-by: Ying Xue <ying.xue(a)windriver.com> Signed-off-by: Jon Maloy <jon.maloy(a)ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker(a)windriver.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 6b2faa5..4ec5c80 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -49,21 +49,6 @@ struct tipc_bearer tipc_bearers[MAX_BEARERS]; static void bearer_disable(struct tipc_bearer *b_ptr); /** - * media_name_valid - validate media name - * - * Returns 1 if media name is valid, otherwise 0. - */ -static int media_name_valid(const char *name) -{ - u32 len; - - len = strlen(name); - if ((len + 1) > TIPC_MAX_MEDIA_NAME) - return 0; - return 1; -} - -/** * tipc_media_find - locates specified media object by name */ struct tipc_media *tipc_media_find(const char *name) @@ -102,7 +87,7 @@ int tipc_register_media(struct tipc_media *m_ptr) write_lock_bh(&tipc_net_lock); - if (!media_name_valid(m_ptr->name)) + if ((strlen(m_ptr->name) + 1) > TIPC_MAX_MEDIA_NAME) goto exit; if ((m_ptr->bcast_addr.media_id != m_ptr->type_id) || !m_ptr->bcast_addr.broadcast) -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 379c0456afc170d56ceb712a5689ede91d293e88 Author: Ying Xue <ying.xue(a)windriver.com> Date: Thu Aug 16 12:09:10 2012 +0000 tipc: change tipc_net_start routine return value type Since now tipc_net_start() always returns a success code - 0, its return value type should be changed from integer to void, which can avoid unnecessary check for its return value. Signed-off-by: Ying Xue <ying.xue(a)windriver.com> Signed-off-by: Jon Maloy <jon.maloy(a)ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker(a)windriver.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/tipc/core.c b/net/tipc/core.c index c261a5d..daae7f7 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -98,9 +98,8 @@ int tipc_core_start_net(unsigned long addr) { int res; - res = tipc_net_start(addr); - if (!res) - res = tipc_eth_media_start(); + tipc_net_start(addr); + res = tipc_eth_media_start(); if (res) tipc_core_stop_net(); return res; diff --git a/net/tipc/net.c b/net/tipc/net.c index 5b5cea2..7d305ec 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -171,7 +171,7 @@ void tipc_net_route_msg(struct sk_buff *buf) tipc_link_send(buf, dnode, msg_link_selector(msg)); } -int tipc_net_start(u32 addr) +void tipc_net_start(u32 addr) { char addr_string[16]; @@ -187,7 +187,6 @@ int tipc_net_start(u32 addr) pr_info("Started in network mode\n"); pr_info("Own node address %s, network identity %u\n", tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); - return 0; } void tipc_net_stop(void) diff --git a/net/tipc/net.h b/net/tipc/net.h index 9eb4b9e..079daad 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -41,7 +41,7 @@ extern rwlock_t tipc_net_lock; void tipc_net_route_msg(struct sk_buff *buf); -int tipc_net_start(u32 addr); +void tipc_net_start(u32 addr); void tipc_net_stop(void); #endif -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 5ef5d6c569f80cf716d75fa88e9b5ee72f0986b2 Author: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Thu Aug 16 03:14:04 2012 +0000 gre: information leak in ip6_tnl_ioctl() There is a one byte hole between p->hop_limit and p->flowinfo where stack memory is leaked to the user. This was introduced in c12b395a46 "gre: Support GRE over IPv6". Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 33d2a0e..cb7e2de 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1312,6 +1312,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); + } else { + memset(&p, 0, sizeof(p)); } if (t == NULL) t = netdev_priv(dev); -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 16f01365fa01150bf3606fe702a80a03ec87953a Author: Pavel Emelyanov <xemul(a)parallels.com> Date: Thu Aug 16 05:34:22 2012 +0000 packet: Report rings cfg via diag engine One extension bit may result in two nlattrs -- one per ring type. If some ring type is not configured, then the respective nlatts will be empty. The structure reported contains the data, that is given to the corresponding ring setup socket option. Signed-off-by: Pavel Emelyanov <xemul(a)parallels.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index ea2e8923..34ade82 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -14,6 +14,7 @@ struct packet_diag_req { #define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ #define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ +#define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ struct packet_diag_msg { __u8 pdiag_family; @@ -27,6 +28,8 @@ struct packet_diag_msg { enum { PACKET_DIAG_INFO, PACKET_DIAG_MCLIST, + PACKET_DIAG_RX_RING, + PACKET_DIAG_TX_RING, PACKET_DIAG_MAX, }; @@ -54,4 +57,14 @@ struct packet_diag_mclist { __u8 pdmc_addr[MAX_ADDR_LEN]; }; +struct packet_diag_ring { + __u32 pdr_block_size; + __u32 pdr_block_nr; + __u32 pdr_frame_size; + __u32 pdr_frame_nr; + __u32 pdr_retire_tmo; + __u32 pdr_sizeof_priv; + __u32 pdr_features; +}; + #endif diff --git a/net/packet/diag.c b/net/packet/diag.c index 3dda4ec..e3975e4 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -67,12 +67,54 @@ static int pdiag_put_mclist(const struct packet_sock *po, struct sk_buff *nlskb) return 0; } +static int pdiag_put_ring(struct packet_ring_buffer *ring, int ver, int nl_type, + struct sk_buff *nlskb) +{ + struct packet_diag_ring pdr; + + if (!ring->pg_vec || ((ver > TPACKET_V2) && + (nl_type == PACKET_DIAG_TX_RING))) + return 0; + + pdr.pdr_block_size = ring->pg_vec_pages << PAGE_SHIFT; + pdr.pdr_block_nr = ring->pg_vec_len; + pdr.pdr_frame_size = ring->frame_size; + pdr.pdr_frame_nr = ring->frame_max + 1; + + if (ver > TPACKET_V2) { + pdr.pdr_retire_tmo = ring->prb_bdqc.retire_blk_tov; + pdr.pdr_sizeof_priv = ring->prb_bdqc.blk_sizeof_priv; + pdr.pdr_features = ring->prb_bdqc.feature_req_word; + } else { + pdr.pdr_retire_tmo = 0; + pdr.pdr_sizeof_priv = 0; + pdr.pdr_features = 0; + } + + return nla_put(nlskb, nl_type, sizeof(pdr), &pdr); +} + +static int pdiag_put_rings_cfg(struct packet_sock *po, struct sk_buff *skb) +{ + int ret; + + mutex_lock(&po->pg_vec_lock); + ret = pdiag_put_ring(&po->rx_ring, po->tp_version, + PACKET_DIAG_RX_RING, skb); + if (!ret) + ret = pdiag_put_ring(&po->tx_ring, po->tp_version, + PACKET_DIAG_TX_RING, skb); + mutex_unlock(&po->pg_vec_lock); + + return ret; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { struct nlmsghdr *nlh; struct packet_diag_msg *rp; - const struct packet_sock *po = pkt_sk(sk); + struct packet_sock *po = pkt_sk(sk); nlh = nlmsg_put(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rp), flags); if (!nlh) @@ -93,6 +135,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag pdiag_put_mclist(po, skb)) goto out_nlmsg_trim; + if ((req->pdiag_show & PACKET_SHOW_RING_CFG) && + pdiag_put_rings_cfg(po, skb)) + goto out_nlmsg_trim; + return nlmsg_end(skb, nlh); out_nlmsg_trim: -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit fff3321d75b1a18231876a1aceb36eacbbf6221e Author: Pavel Emelyanov <xemul(a)parallels.com> Date: Thu Aug 16 05:36:48 2012 +0000 packet: Report fanout status via diag engine Reported value is the same reported by the FANOUT getsockoption, but unlike it, the absent fanout setup results in absent nlattr, rather than in nlattr with zero value. This is done so, since zero fanout report may mean both -- no fanout, and fanout with both id and type zero. Signed-off-by: Pavel Emelyanov <xemul(a)parallels.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/include/linux/packet_diag.h b/include/linux/packet_diag.h index 34ade82..93f5fa9 100644 --- a/include/linux/packet_diag.h +++ b/include/linux/packet_diag.h @@ -15,6 +15,7 @@ struct packet_diag_req { #define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */ #define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */ #define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */ +#define PACKET_SHOW_FANOUT 0x00000008 struct packet_diag_msg { __u8 pdiag_family; @@ -30,6 +31,7 @@ enum { PACKET_DIAG_MCLIST, PACKET_DIAG_RX_RING, PACKET_DIAG_TX_RING, + PACKET_DIAG_FANOUT, PACKET_DIAG_MAX, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8a1605a..226b2cd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -207,24 +207,6 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); -#define PACKET_FANOUT_MAX 256 - -struct packet_fanout { -#ifdef CONFIG_NET_NS - struct net *net; -#endif - unsigned int num_members; - u16 id; - u8 type; - u8 defrag; - atomic_t rr_cur; - struct list_head list; - struct sock *arr[PACKET_FANOUT_MAX]; - spinlock_t lock; - atomic_t sk_ref; - struct packet_type prot_hook ____cacheline_aligned_in_smp; -}; - struct packet_skb_cb { unsigned int origlen; union { @@ -1148,7 +1130,8 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } -static DEFINE_MUTEX(fanout_mutex); +DEFINE_MUTEX(fanout_mutex); +EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static void __fanout_link(struct sock *sk, struct packet_sock *po) @@ -1260,9 +1243,9 @@ static void fanout_release(struct sock *sk) if (!f) return; + mutex_lock(&fanout_mutex); po->fanout = NULL; - mutex_lock(&fanout_mutex); if (atomic_dec_and_test(&f->sk_ref)) { list_del(&f->list); dev_remove_pack(&f->prot_hook); diff --git a/net/packet/diag.c b/net/packet/diag.c index e3975e4..bc33fbe 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -109,6 +109,22 @@ static int pdiag_put_rings_cfg(struct packet_sock *po, struct sk_buff *skb) return ret; } +static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) +{ + int ret = 0; + + mutex_lock(&fanout_mutex); + if (po->fanout) { + u32 val; + + val = (u32)po->fanout->id | ((u32)po->fanout->type << 16); + ret = nla_put_u32(nlskb, PACKET_DIAG_FANOUT, val); + } + mutex_unlock(&fanout_mutex); + + return ret; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -139,6 +155,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag pdiag_put_rings_cfg(po, skb)) goto out_nlmsg_trim; + if ((req->pdiag_show & PACKET_SHOW_FANOUT) && + pdiag_put_fanout(po, skb)) + goto out_nlmsg_trim; + return nlmsg_end(skb, nlh); out_nlmsg_trim: diff --git a/net/packet/internal.h b/net/packet/internal.h index 2c5fca2..44945f6 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -67,7 +67,25 @@ struct packet_ring_buffer { atomic_t pending; }; -struct packet_fanout; +extern struct mutex fanout_mutex; +#define PACKET_FANOUT_MAX 256 + +struct packet_fanout { +#ifdef CONFIG_NET_NS + struct net *net; +#endif + unsigned int num_members; + u16 id; + u8 type; + u8 defrag; + atomic_t rr_cur; + struct list_head list; + struct sock *arr[PACKET_FANOUT_MAX]; + spinlock_t lock; + atomic_t sk_ref; + struct packet_type prot_hook ____cacheline_aligned_in_smp; +}; + struct packet_sock { /* struct sock has to be the first member of packet_sock */ struct sock sk; -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 62748b7bde84618f06b5c7a8733ae87776ec36c5 Author: Alexander Duyck <alexander.h.duyck(a)intel.com> Date: Fri Jul 20 08:09:01 2012 +0000 ixgbe: Rewrite code related to configuring IFCS bit in Tx descriptor This change updates the code related to configuring the transmit frame checksum. Specifically I have updated the code so that we can only skip inserting the checksum in the case that we are not performing some other offload that will modify the frame data. Signed-off-by: Alexander Duyck <alexander.h.duyck(a)intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt(a)intel.com> Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr(a)intel.com> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index fd2bc69..bffcf1f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -107,6 +107,7 @@ #define IXGBE_TX_FLAGS_FSO (u32)(1 << 6) #define IXGBE_TX_FLAGS_TXSW (u32)(1 << 7) #define IXGBE_TX_FLAGS_TSTAMP (u32)(1 << 8) +#define IXGBE_TX_FLAGS_NO_IFCS (u32)(1 << 9) #define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT 29 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index aa37b84..fa0d6e1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5903,9 +5903,12 @@ static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, u32 type_tucmd = 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN) && - !(first->tx_flags & IXGBE_TX_FLAGS_TXSW)) - return; + if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN)) { + if (unlikely(skb->no_fcs)) + first->tx_flags |= IXGBE_TX_FLAGS_NO_IFCS; + if (!(first->tx_flags & IXGBE_TX_FLAGS_TXSW)) + return; + } } else { u8 l4_hdr = 0; switch (first->protocol) { @@ -5967,7 +5970,6 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ __le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA | - IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT); /* set HW vlan bit if vlan is present */ @@ -5987,6 +5989,10 @@ static __le32 ixgbe_tx_cmd_type(u32 tx_flags) #endif cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); + /* insert frame checksum */ + if (!(tx_flags & IXGBE_TX_FLAGS_NO_IFCS)) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS); + return cmd_type; } @@ -6092,8 +6098,6 @@ static void ixgbe_tx_map(struct ixgbe_ring *tx_ring, if (likely(!data_len)) break; - if (unlikely(skb->no_fcs)) - cmd_type &= ~(cpu_to_le32(IXGBE_ADVTXD_DCMD_IFCS)); tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); i++; -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 56892261ed1a854db5363df8bb3fbdb2c6c28d4c Author: Fan Du <fan.du(a)windriver.com> Date: Thu Aug 16 17:51:25 2012 +0800 xfrm: Use rcu_dereference_bh to deference pointer protected by rcu_read_lock_bh Signed-off-by: Fan Du <fan.du(a)windriver.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5ad4d2c..6405764 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2501,11 +2501,11 @@ static void __net_init xfrm_dst_ops_init(struct net *net) struct xfrm_policy_afinfo *afinfo; rcu_read_lock_bh(); - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]); + afinfo = rcu_dereference_bh(xfrm_policy_afinfo[AF_INET]); if (afinfo) net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; #if IS_ENABLED(CONFIG_IPV6) - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]); + afinfo = rcu_dereference_bh(xfrm_policy_afinfo[AF_INET6]); if (afinfo) net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; #endif -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 19861ce24f2ea9d9db7b96814de9ca8d522cbe40 Author: Alexander Duyck <alexander.h.duyck(a)intel.com> Date: Fri Jul 20 08:08:33 2012 +0000 ixgbe: Make pull tail function separate from rest of cleanup_headers This change creates a separate function for functionality similar to pskb_pull_tail. The main motivation for moving it to a separate function is so that later I can just skip this function in the case where we have already copied the buffer into skb->head. Signed-off-by: Alexander Duyck <alexander.h.duyck(a)intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt(a)intel.com> Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr(a)intel.com> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b0020fc..d926973 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1458,6 +1458,61 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, } /** + * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being adjusted + * + * This function is an ixgbe specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. + */ +static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned char *va; + unsigned int pull_len; + + /* + * it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); + + /* + * we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = skb_frag_size(frag); + if (pull_len > IXGBE_RX_HDR_SIZE) + pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + frag->page_offset += pull_len; + skb->data_len -= pull_len; + skb->tail += pull_len; + + /* + * if we sucked the frag empty then we should free it, + * if there are other frags here something is screwed up in hardware + */ + if (skb_frag_size(frag) == 0) { + BUG_ON(skb_shinfo(skb)->nr_frags != 1); + skb_shinfo(skb)->nr_frags = 0; + __skb_frag_unref(frag); + skb->truesize -= ixgbe_rx_bufsz(rx_ring); + } +} + +/** * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB * @rx_ring: rx descriptor ring packet is being transacted on * @skb: pointer to current skb being updated @@ -1509,10 +1564,7 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; struct net_device *netdev = rx_ring->netdev; - unsigned char *va; - unsigned int pull_len; /* verify that the packet does not have any known errors */ if (unlikely(ixgbe_test_staterr(rx_desc, @@ -1522,40 +1574,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, return true; } - /* - * it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - /* - * we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = skb_frag_size(frag); - if (pull_len > IXGBE_RX_HDR_SIZE) - pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; - - /* - * if we sucked the frag empty then we should free it, - * if there are other frags here something is screwed up in hardware - */ - if (skb_frag_size(frag) == 0) { - BUG_ON(skb_shinfo(skb)->nr_frags != 1); - skb_shinfo(skb)->nr_frags = 0; - __skb_frag_unref(frag); - skb->truesize -= ixgbe_rx_bufsz(rx_ring); - } + /* place header in linear portion of buffer */ + ixgbe_pull_tail(rx_ring, skb); #ifdef IXGBE_FCOE /* do not attempt to pad FCoE Frames as this will disrupt DDP */ -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit cf3fe7aca03e14db107d649c5699a48bec054583 Author: Alexander Duyck <alexander.h.duyck(a)intel.com> Date: Fri Jul 20 08:08:39 2012 +0000 ixgbe: Copybreak sooner to avoid get_page/put_page and offset change overhead This change makes it so that if only the first 256 bytes of a buffer are used we just copy the data out and leave the offset and page count unchanged. There are multiple advantages to this. First it allows us to reuse the page much more in the case of pages larger than 4K. It also allows us to avoid some expensive atomic operations in the form of get_page/put_page. In perf I have seen CPU utilization for put_page drop from 3.5% to 1.8% as a result of this patch when doing small packet routing, and packet rates increased by about 3%. Signed-off-by: Alexander Duyck <alexander.h.duyck(a)intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt(a)intel.com> Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr(a)intel.com> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d926973..d11fac5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1487,9 +1487,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, * we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len = skb_frag_size(frag); - if (pull_len > IXGBE_RX_HDR_SIZE) - pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); + pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); @@ -1499,17 +1497,6 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, frag->page_offset += pull_len; skb->data_len -= pull_len; skb->tail += pull_len; - - /* - * if we sucked the frag empty then we should free it, - * if there are other frags here something is screwed up in hardware - */ - if (skb_frag_size(frag) == 0) { - BUG_ON(skb_shinfo(skb)->nr_frags != 1); - skb_shinfo(skb)->nr_frags = 0; - __skb_frag_unref(frag); - skb->truesize -= ixgbe_rx_bufsz(rx_ring); - } } /** @@ -1575,7 +1562,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, } /* place header in linear portion of buffer */ - ixgbe_pull_tail(rx_ring, skb); + if (skb_is_nonlinear(skb)) + ixgbe_pull_tail(rx_ring, skb); #ifdef IXGBE_FCOE /* do not attempt to pad FCoE Frames as this will disrupt DDP */ @@ -1656,6 +1644,20 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, ixgbe_rx_bufsz(rx_ring); #endif + if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { + unsigned char *va = page_address(page) + rx_buffer->page_offset; + + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* we can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(page) == numa_node_id())) + return true; + + /* this page cannot be reused so discard it */ + put_page(page); + return false; + } + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, rx_buffer->page_offset, size, truesize); -- linux integration

1 0

[linux-merge]linux integration; branch, batman-adv/next, updated. batman-adv-for-davem-8944-g185d3da
by postmaster＠open-mesh.org 21 Aug '12

21 Aug '12

The following commit has been merged in the batman-adv/next branch: commit 18806c9ea28320d5368fd43318506a7d33cc952c Author: Alexander Duyck <alexander.h.duyck(a)intel.com> Date: Fri Jul 20 08:08:44 2012 +0000 ixgbe: Make allocating skb and placing data in it a separate function This patch creates a function named ixgbe_fetch_rx_buffer. The sole purpose of this function is to retrieve a single buffer off of the ring and to place it in an skb. The advantage to doing this is that it helps improve the readability since I can decrease the indentation and for the code in this section. Signed-off-by: Alexander Duyck <alexander.h.duyck(a)intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt(a)intel.com> Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr(a)intel.com> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d11fac5..9e72ae6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1693,6 +1693,89 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, return true; } +static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + struct ixgbe_rx_buffer *rx_buffer; + struct sk_buff *skb; + struct page *page; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + page = rx_buffer->page; + prefetchw(page); + + skb = rx_buffer->skb; + + if (likely(!skb)) { + void *page_addr = page_address(page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IXGBE_RX_HDR_SIZE); + if (unlikely(!skb)) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + return NULL; + } + + /* + * we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + + /* + * Delay unmapping of the first packet. It carries the + * header information, HW may still access the header + * after the writeback. Only unmap it when EOP is + * reached + */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + goto dma_sync; + + IXGBE_CB(skb)->dma = rx_buffer->dma; + } else { + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + ixgbe_dma_sync_frag(rx_ring, skb); + +dma_sync: + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + } + + /* pull page into skb */ + if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + /* hand second half of page back to the ring */ + ixgbe_reuse_rx_page(rx_ring, rx_buffer); + } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + /* the page has been released from the ring */ + IXGBE_CB(skb)->page_released = true; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + } + + /* clear contents of buffer_info */ + rx_buffer->skb = NULL; + rx_buffer->dma = 0; + rx_buffer->page = NULL; + + return skb; +} + /** * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @q_vector: structure containing interrupt and ring information @@ -1718,11 +1801,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, u16 cleaned_count = ixgbe_desc_unused(rx_ring); do { - struct ixgbe_rx_buffer *rx_buffer; union ixgbe_adv_rx_desc *rx_desc; struct sk_buff *skb; - struct page *page; - u16 ntc; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { @@ -1730,9 +1810,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, cleaned_count = 0; } - ntc = rx_ring->next_to_clean; - rx_desc = IXGBE_RX_DESC(rx_ring, ntc); - rx_buffer = &rx_ring->rx_buffer_info[ntc]; + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) break; @@ -1744,78 +1822,12 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ rmb(); - page = rx_buffer->page; - prefetchw(page); - - skb = rx_buffer->skb; - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; - - /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif - - /* allocate a skb to store the frags */ - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - IXGBE_RX_HDR_SIZE); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_rx_buff_failed++; - break; - } - - /* - * we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - - /* - * Delay unmapping of the first packet. It carries the - * header information, HW may still access the header - * after the writeback. Only unmap it when EOP is - * reached - */ - if (likely(ixgbe_test_staterr(rx_desc, - IXGBE_RXD_STAT_EOP))) - goto dma_sync; + /* retrieve a buffer from the ring */ + skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc); - IXGBE_CB(skb)->dma = rx_buffer->dma; - } else { - if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) - ixgbe_dma_sync_frag(rx_ring, skb); - -dma_sync: - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - ixgbe_rx_bufsz(rx_ring), - DMA_FROM_DEVICE); - } - - /* pull page into skb */ - if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { - /* hand second half of page back to the ring */ - ixgbe_reuse_rx_page(rx_ring, rx_buffer); - } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { - /* the page has been released from the ring */ - IXGBE_CB(skb)->page_released = true; - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE); - } - - /* clear contents of buffer_info */ - rx_buffer->skb = NULL; - rx_buffer->dma = 0; - rx_buffer->page = NULL; + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; ixgbe_get_rsc_cnt(rx_ring, rx_desc, skb); -- linux integration

1 0

← Newer
1
...
5
6
7
8
9
10
11
...
36
Older →

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

commits August 2012