diff options
43 files changed, 1059 insertions, 264 deletions
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c index 54720baa7363..a95790452a68 100644 --- a/drivers/atm/horizon.c +++ b/drivers/atm/horizon.c @@ -1645,10 +1645,8 @@ static int hrz_send (struct atm_vcc * atm_vcc, struct sk_buff * skb) { unsigned short d = 0; char * s = skb->data; if (*s++ == 'D') { - for (i = 0; i < 4; ++i) { - d = (d<<4) | ((*s <= '9') ? (*s - '0') : (*s - 'a' + 10)); - ++s; - } + for (i = 0; i < 4; ++i) + d = (d << 4) | hex_to_bin(*s++); PRINTK (KERN_INFO, "debug bitmap is now %hx", debug = d); } } diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index c07de359dc07..d72fb0519a2a 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -1124,7 +1124,7 @@ static const struct proto_ops pppoe_ops = { .ioctl = pppox_ioctl, }; -static struct pppox_proto pppoe_proto = { +static const struct pppox_proto pppoe_proto = { .create = pppoe_create, .ioctl = pppoe_ioctl, .owner = THIS_MODULE, diff --git a/drivers/net/pppox.c b/drivers/net/pppox.c index d4191ef9cad1..8c0d170dabcd 100644 --- a/drivers/net/pppox.c +++ b/drivers/net/pppox.c @@ -36,9 +36,9 @@ #include <asm/uaccess.h> -static struct pppox_proto *pppox_protos[PX_MAX_PROTO + 1]; +static const struct pppox_proto *pppox_protos[PX_MAX_PROTO + 1]; -int register_pppox_proto(int proto_num, struct pppox_proto *pp) +int register_pppox_proto(int proto_num, const struct pppox_proto *pp) { if (proto_num < 0 || proto_num > PX_MAX_PROTO) return -EINVAL; diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c index 761f0eced724..ccbc91326bfa 100644 --- a/drivers/net/pptp.c +++ b/drivers/net/pptp.c @@ -53,7 +53,7 @@ static struct pppox_sock **callid_sock; static DEFINE_SPINLOCK(chan_lock); static struct proto pptp_sk_proto __read_mostly; -static struct ppp_channel_ops pptp_chan_ops; +static const struct ppp_channel_ops pptp_chan_ops; static const struct proto_ops pptp_ops; #define PPP_LCP_ECHOREQ 0x09 @@ -628,7 +628,7 @@ static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd, return err; } -static struct ppp_channel_ops pptp_chan_ops = { +static const struct ppp_channel_ops pptp_chan_ops = { .start_xmit = pptp_xmit, .ioctl = pptp_ppp_ioctl, }; @@ -659,12 +659,12 @@ static const struct proto_ops pptp_ops = { .ioctl = pppox_ioctl, }; -static struct pppox_proto pppox_pptp_proto = { +static const struct pppox_proto pppox_pptp_proto = { .create = pptp_create, .owner = THIS_MODULE, }; -static struct gre_protocol gre_pptp_protocol = { +static const struct gre_protocol gre_pptp_protocol = { .handler = pptp_rcv, }; diff --git a/drivers/net/qlcnic/qlcnic_init.c b/drivers/net/qlcnic/qlcnic_init.c index e26fa9593311..16dd9ebd36c9 100644 --- a/drivers/net/qlcnic/qlcnic_init.c +++ b/drivers/net/qlcnic/qlcnic_init.c @@ -1418,8 +1418,6 @@ qlcnic_process_rcv(struct qlcnic_adapter *adapter, if (pkt_offset) skb_pull(skb, pkt_offset); - skb->truesize = skb->len + sizeof(struct sk_buff); - if (unlikely(qlcnic_check_rx_tagging(adapter, skb, &vid))) { adapter->stats.rxdropped++; dev_kfree_skb(skb); @@ -1491,8 +1489,6 @@ qlcnic_process_lro(struct qlcnic_adapter *adapter, skb_put(skb, lro_length + data_offset); - skb->truesize = skb->len + sizeof(struct sk_buff) + skb_headroom(skb); - skb_pull(skb, l2_hdr_offset); if (unlikely(qlcnic_check_rx_tagging(adapter, skb, &vid))) { @@ -1732,8 +1728,6 @@ qlcnic_process_rcv_diag(struct qlcnic_adapter *adapter, if (pkt_offset) skb_pull(skb, pkt_offset); - skb->truesize = skb->len + sizeof(struct sk_buff); - if (!qlcnic_check_loopback_buff(skb->data)) adapter->diag_cnt++; diff --git a/drivers/net/sfc/Makefile b/drivers/net/sfc/Makefile index 1047b19c60a5..fd9272b5873a 100644 --- a/drivers/net/sfc/Makefile +++ b/drivers/net/sfc/Makefile @@ -1,4 +1,4 @@ -sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o \ +sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \ falcon_gmac.o falcon_xmac.o mcdi_mac.o \ selftest.o ethtool.o qt202x_phy.o mdio_10g.o \ tenxpress.o falcon_boards.o mcdi.o mcdi_phy.o diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index f702f1fb63b6..5be71f49a205 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -124,8 +124,9 @@ MODULE_PARM_DESC(separate_tx_channels, static int napi_weight = 64; /* This is the time (in jiffies) between invocations of the hardware - * monitor, which checks for known hardware bugs and resets the - * hardware and driver as necessary. + * monitor. On Falcon-based NICs, this will: + * - Check the on-board hardware monitor; + * - Poll the link state and reconfigure the hardware as necessary. */ unsigned int efx_monitor_interval = 1 * HZ; @@ -1357,8 +1358,17 @@ static int efx_probe_all(struct efx_nic *efx) if (rc) goto fail3; + rc = efx_probe_filters(efx); + if (rc) { + netif_err(efx, probe, efx->net_dev, + "failed to create filter tables\n"); + goto fail4; + } + return 0; + fail4: + efx_remove_channels(efx); fail3: efx_remove_port(efx); fail2: @@ -1489,6 +1499,7 @@ static void efx_stop_all(struct efx_nic *efx) static void efx_remove_all(struct efx_nic *efx) { + efx_remove_filters(efx); efx_remove_channels(efx); efx_remove_port(efx); efx_remove_nic(efx); @@ -1535,8 +1546,7 @@ void efx_init_irq_moderation(struct efx_nic *efx, int tx_usecs, int rx_usecs, * **************************************************************************/ -/* Run periodically off the general workqueue. Serialised against - * efx_reconfigure_port via the mac_lock */ +/* Run periodically off the general workqueue */ static void efx_monitor(struct work_struct *data) { struct efx_nic *efx = container_of(data, struct efx_nic, @@ -1549,16 +1559,13 @@ static void efx_monitor(struct work_struct *data) /* If the mac_lock is already held then it is likely a port * reconfiguration is already in place, which will likely do - * most of the work of check_hw() anyway. */ - if (!mutex_trylock(&efx->mac_lock)) - goto out_requeue; - if (!efx->port_enabled) - goto out_unlock; - efx->type->monitor(efx); + * most of the work of monitor() anyway. */ + if (mutex_trylock(&efx->mac_lock)) { + if (efx->port_enabled) + efx->type->monitor(efx); + mutex_unlock(&efx->mac_lock); + } -out_unlock: - mutex_unlock(&efx->mac_lock); -out_requeue: queue_delayed_work(efx->workqueue, &efx->monitor_work, efx_monitor_interval); } @@ -2002,6 +2009,7 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) efx->mac_op->reconfigure(efx); efx_init_channels(efx); + efx_restore_filters(efx); mutex_unlock(&efx->spi_lock); mutex_unlock(&efx->mac_lock); diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h index e783c0fedfd8..f502b14eb22c 100644 --- a/drivers/net/sfc/efx.h +++ b/drivers/net/sfc/efx.h @@ -12,6 +12,7 @@ #define EFX_EFX_H #include "net_driver.h" +#include "filter.h" /* PCI IDs */ #define EFX_VENDID_SFC 0x1924 @@ -64,6 +65,19 @@ extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); * skb. Falcon/A1 may require up to three descriptors per skb_frag. */ #define EFX_MIN_RING_SIZE (roundup_pow_of_two(2 * 3 * MAX_SKB_FRAGS)) +/* Filters */ +extern int efx_probe_filters(struct efx_nic *efx); +extern void efx_restore_filters(struct efx_nic *efx); +extern void efx_remove_filters(struct efx_nic *efx); +extern int efx_filter_insert_filter(struct efx_nic *efx, + struct efx_filter_spec *spec, + bool replace); +extern int efx_filter_remove_filter(struct efx_nic *efx, + struct efx_filter_spec *spec); +extern void efx_filter_table_clear(struct efx_nic *efx, + enum efx_filter_table_id table_id, + enum efx_filter_priority priority); + /* Channels */ extern void efx_process_channel_now(struct efx_channel *channel); extern int diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index 7f735d804801..c95328fa3ee8 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -15,6 +15,7 @@ #include "workarounds.h" #include "selftest.h" #include "efx.h" +#include "filter.h" #include "nic.h" #include "spi.h" #include "mdio_10g.h" @@ -551,9 +552,22 @@ static u32 efx_ethtool_get_rx_csum(struct net_device *net_dev) static int efx_ethtool_set_flags(struct net_device *net_dev, u32 data) { struct efx_nic *efx = netdev_priv(net_dev); - u32 supported = efx->type->offload_features & ETH_FLAG_RXHASH; + u32 supported = (efx->type->offload_features & + (ETH_FLAG_RXHASH | ETH_FLAG_NTUPLE)); + int rc; + + rc = ethtool_op_set_flags(net_dev, data, supported); + if (rc) + return rc; + + if (!(data & ETH_FLAG_NTUPLE)) { + efx_filter_table_clear(efx, EFX_FILTER_TABLE_RX_IP, + EFX_FILTER_PRI_MANUAL); + efx_filter_table_clear(efx, EFX_FILTER_TABLE_RX_MAC, + EFX_FILTER_PRI_MANUAL); + } - return ethtool_op_set_flags(net_dev, data, supported); + return 0; } static void efx_ethtool_self_test(struct net_device *net_dev, @@ -955,6 +969,105 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev, } } +static int efx_ethtool_set_rx_ntuple(struct net_device *net_dev, + struct ethtool_rx_ntuple *ntuple) +{ + struct efx_nic *efx = netdev_priv(net_dev); + struct ethtool_tcpip4_spec *ip_entry = &ntuple->fs.h_u.tcp_ip4_spec; + struct ethtool_tcpip4_spec *ip_mask = &ntuple->fs.m_u.tcp_ip4_spec; + struct ethhdr *mac_entry = &ntuple->fs.h_u.ether_spec; + struct ethhdr *mac_mask = &ntuple->fs.m_u.ether_spec; + struct efx_filter_spec filter; + + /* Range-check action */ + if (ntuple->fs.action < ETHTOOL_RXNTUPLE_ACTION_CLEAR || + ntuple->fs.action >= (s32)efx->n_rx_channels) + return -EINVAL; + + if (~ntuple->fs.data_mask) + return -EINVAL; + + switch (ntuple->fs.flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + /* Must match all of destination, */ + if (ip_mask->ip4dst | ip_mask->pdst) + return -EINVAL; + /* all or none of source, */ + if ((ip_mask->ip4src | ip_mask->psrc) && + ((__force u32)~ip_mask->ip4src | + (__force u16)~ip_mask->psrc)) + return -EINVAL; + /* and nothing else */ + if ((u8)~ip_mask->tos | (u16)~ntuple->fs.vlan_tag_mask) + return -EINVAL; + break; + case ETHER_FLOW: + /* Must match all of destination, */ + if (!is_zero_ether_addr(mac_mask->h_dest)) + return -EINVAL; + /* all or none of VID, */ + if (ntuple->fs.vlan_tag_mask != 0xf000 && + ntuple->fs.vlan_tag_mask != 0xffff) + return -EINVAL; + /* and nothing else */ + if (!is_broadcast_ether_addr(mac_mask->h_source) || + mac_mask->h_proto != htons(0xffff)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + filter.priority = EFX_FILTER_PRI_MANUAL; + filter.flags = 0; + + switch (ntuple->fs.flow_type) { + case TCP_V4_FLOW: + if (!ip_mask->ip4src) + efx_filter_set_rx_tcp_full(&filter, + htonl(ip_entry->ip4src), + htons(ip_entry->psrc), + htonl(ip_entry->ip4dst), + htons(ip_entry->pdst)); + else + efx_filter_set_rx_tcp_wild(&filter, + htonl(ip_entry->ip4dst), + htons(ip_entry->pdst)); + break; + case UDP_V4_FLOW: + if (!ip_mask->ip4src) + efx_filter_set_rx_udp_full(&filter, + htonl(ip_entry->ip4src), + htons(ip_entry->psrc), + htonl(ip_entry->ip4dst), + htons(ip_entry->pdst)); + else + efx_filter_set_rx_udp_wild(&filter, + htonl(ip_entry->ip4dst), + htons(ip_entry->pdst)); + break; + case ETHER_FLOW: + if (ntuple->fs.vlan_tag_mask == 0xf000) + efx_filter_set_rx_mac_full(&filter, + ntuple->fs.vlan_tag & 0xfff, + mac_entry->h_dest); + else + efx_filter_set_rx_mac_wild(&filter, mac_entry->h_dest); + break; + } + + if (ntuple->fs.action == ETHTOOL_RXNTUPLE_ACTION_CLEAR) { + return efx_filter_remove_filter(efx, &filter); + } else { + if (ntuple->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) + filter.dmaq_id = 0xfff; + else + filter.dmaq_id = ntuple->fs.action; + return efx_filter_insert_filter(efx, &filter, true); + } +} + static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, struct ethtool_rxfh_indir *indir) { @@ -1033,6 +1146,7 @@ const struct ethtool_ops efx_ethtool_ops = { .set_wol = efx_ethtool_set_wol, .reset = efx_ethtool_reset, .get_rxnfc = efx_ethtool_get_rxnfc, + .set_rx_ntuple = efx_ethtool_set_rx_ntuple, .get_rxfh_indir = efx_ethtool_get_rxfh_indir, .set_rxfh_indir = efx_ethtool_set_rxfh_indir, }; diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c index b4d8efe67772..b398a4198042 100644 --- a/drivers/net/sfc/falcon.c +++ b/drivers/net/sfc/falcon.c @@ -1874,7 +1874,7 @@ struct efx_nic_type falcon_b0_nic_type = { * channels */ .tx_dc_base = 0x130000, .rx_dc_base = 0x100000, - .offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH, + .offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE, .reset_world_flags = ETH_RESET_IRQ, }; diff --git a/drivers/net/sfc/filter.c b/drivers/net/sfc/filter.c new file mode 100644 index 000000000000..abc884d09d57 --- /dev/null +++ b/drivers/net/sfc/filter.c @@ -0,0 +1,445 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2010 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include "efx.h" +#include "filter.h" +#include "io.h" +#include "nic.h" +#include "regs.h" + +/* "Fudge factors" - difference between programmed value and actual depth. + * Due to pipelined implementation we need to program H/W with a value that + * is larger than the hop limit we want. + */ +#define FILTER_CTL_SRCH_FUDGE_WILD 3 +#define FILTER_CTL_SRCH_FUDGE_FULL 1 + +struct efx_filter_table { + u32 offset; /* address of table relative to BAR */ + unsigned size; /* number of entries */ + unsigned step; /* step between entries */ + unsigned used; /* number currently used */ + unsigned long *used_bitmap; + struct efx_filter_spec *spec; +}; + +struct efx_filter_state { + spinlock_t lock; + struct efx_filter_table table[EFX_FILTER_TABLE_COUNT]; + unsigned search_depth[EFX_FILTER_TYPE_COUNT]; +}; + +/* The filter hash function is LFSR polynomial x^16 + x^3 + 1 of a 32-bit + * key derived from the n-tuple. The initial LFSR state is 0xffff. */ +static u16 efx_filter_hash(u32 key) +{ + u16 tmp; + + /* First 16 rounds */ + tmp = 0x1fff ^ key >> 16; + tmp = tmp ^ tmp >> 3 ^ tmp >> 6; + tmp = tmp ^ tmp >> 9; + /* Last 16 rounds */ + tmp = tmp ^ tmp << 13 ^ key; + tmp = tmp ^ tmp >> 3 ^ tmp >> 6; + return tmp ^ tmp >> 9; +} + +/* To allow for hash collisions, filter search continues at these + * increments from the first possible entry selected by the hash. */ +static u16 efx_filter_increment(u32 key) +{ + return key * 2 - 1; +} + +static enum efx_filter_table_id +efx_filter_type_table_id(enum efx_filter_type type) +{ + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_RX_TCP_FULL >> 2)); + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_RX_TCP_WILD >> 2)); + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_RX_UDP_FULL >> 2)); + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_RX_UDP_WILD >> 2)); + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_MAC != (EFX_FILTER_RX_MAC_FULL >> 2)); + BUILD_BUG_ON(EFX_FILTER_TABLE_RX_MAC != (EFX_FILTER_RX_MAC_WILD >> 2)); + return type >> 2; +} + +static void +efx_filter_table_reset_search_depth(struct efx_filter_state *state, + enum efx_filter_table_id table_id) +{ + memset(state->search_depth + (table_id << 2), 0, + sizeof(state->search_depth[0]) << 2); +} + +static void efx_filter_push_rx_limits(struct efx_nic *efx) +{ + struct efx_filter_state *state = efx->filter_state; + efx_oword_t filter_ctl; + + efx_reado(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL); + + EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_FULL_SRCH_LIMIT, + state->search_depth[EFX_FILTER_RX_TCP_FULL] + + FILTER_CTL_SRCH_FUDGE_FULL); + EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_WILD_SRCH_LIMIT, + state->search_depth[EFX_FILTER_RX_TCP_WILD] + + FILTER_CTL_SRCH_FUDGE_WILD); + EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_FULL_SRCH_LIMIT, + state->search_depth[EFX_FILTER_RX_UDP_FULL] + + FILTER_CTL_SRCH_FUDGE_FULL); + EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_WILD_SRCH_LIMIT, + state->search_depth[EFX_FILTER_RX_UDP_WILD] + + FILTER_CTL_SRCH_FUDGE_WILD); + + if (state->table[EFX_FILTER_TABLE_RX_MAC].size) { + EFX_SET_OWORD_FIELD( + filter_ctl, FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT, + state->search_depth[EFX_FILTER_RX_MAC_FULL] + + FILTER_CTL_SRCH_FUDGE_FULL); + EFX_SET_OWORD_FIELD( + filter_ctl, FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT, + state->search_depth[EFX_FILTER_RX_MAC_WILD] + + FILTER_CTL_SRCH_FUDGE_WILD); + } + + efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL); +} + +/* Build a filter entry and return its n-tuple key. */ +static u32 efx_filter_build(efx_oword_t *filter, struct efx_filter_spec *spec) +{ + u32 data3; + + switch (efx_filter_type_table_id(spec->type)) { + case EFX_FILTER_TABLE_RX_IP: { + bool is_udp = (spec->type == EFX_FILTER_RX_UDP_FULL || + spec->type == EFX_FILTER_RX_UDP_WILD); + EFX_POPULATE_OWORD_7( + *filter, + FRF_BZ_RSS_EN, + !!(spec->flags & EFX_FILTER_FLAG_RX_RSS), + FRF_BZ_SCATTER_EN, + !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER), + FRF_BZ_TCP_UDP, is_udp, + FRF_BZ_RXQ_ID, spec->dmaq_id, + EFX_DWORD_2, spec->data[2], + EFX_DWORD_1, spec->data[1], + EFX_DWORD_0, spec->data[0]); + data3 = is_udp; + break; + } + + case EFX_FILTER_TABLE_RX_MAC: { + bool is_wild = spec->type == EFX_FILTER_RX_MAC_WILD; + EFX_POPULATE_OWORD_8( + *filter, + FRF_CZ_RMFT_RSS_EN, + !!(spec->flags & EFX_FILTER_FLAG_RX_RSS), + FRF_CZ_RMFT_SCATTER_EN, + !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER), + FRF_CZ_RMFT_IP_OVERRIDE, + !!(spec->flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP), + FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id, + FRF_CZ_RMFT_WILDCARD_MATCH, is_wild, + FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2], + FRF_CZ_RMFT_DEST_MAC_LO, spec->data[1], + FRF_CZ_RMFT_VLAN_ID, spec->data[0]); + data3 = is_wild; + break; + } + + default: + BUG(); + } + + return spec->data[0] ^ spec->data[1] ^ spec->data[2] ^ data3; +} + +static bool efx_filter_equal(const struct efx_filter_spec *left, + const struct efx_filter_spec *right) +{ + if (left->type != right->type || + memcmp(left->data, right->data, sizeof(left->data))) + return false; + + return true; +} + +static int efx_filter_search(struct efx_filter_table *table, + struct efx_filter_spec *spec, u32 key, + bool for_insert, int *depth_required) +{ + unsigned hash, incr, filter_idx, depth; + struct efx_filter_spec *cmp; + + hash = efx_filter_hash(key); + incr = efx_filter_increment(key); + + for (depth = 1, filter_idx = hash & (table->size - 1); + test_bit(filter_idx, table->used_bitmap); + ++depth) { + cmp = &table->spec[filter_idx]; + if (efx_filter_equal(spec, cmp)) + goto found; + filter_idx = (filter_idx + incr) & (table->size - 1); + } + if (!for_insert) + return -ENOENT; +found: + *depth_required = depth; + return filter_idx; +} + +/** + * efx_filter_insert_filter - add or replace a filter + * @efx: NIC in which to insert the filter + * @spec: Specification for the filter + * @replace: Flag for whether the specified filter may replace a filter + * with an identical match expression and equal or lower priority + * + * On success, return the filter index within its table. + * On failure, return a negative error code. + */ +int efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec, + bool replace) +{ + struct efx_filter_state *state = efx->filter_state; + enum efx_filter_table_id table_id = + efx_filter_type_table_id(spec->type); + struct efx_filter_table *table = &state->table[table_id]; + struct efx_filter_spec *saved_spec; + efx_oword_t filter; + int filter_idx, depth; + u32 key; + int rc; + + if (table->size == 0) + return -EINVAL; + + key = efx_filter_build(&filter, spec); + + netif_vdbg(efx, hw, efx->net_dev, + "%s: type %d search_depth=%d", __func__, spec->type, + state->search_depth[spec->type]); + + spin_lock_bh(&state->lock); + + rc = efx_filter_search(table, spec, key, true, &depth); + if (rc < 0) + goto out; + filter_idx = rc; + BUG_ON(filter_idx >= table->size); + saved_spec = &table->spec[filter_idx]; + + if (test_bit(filter_idx, table->used_bitmap)) { + /* Should we replace the existing filter? */ + if (!replace) { + rc = -EEXIST; + goto out; + } + if (spec->priority < saved_spec->priority) { + rc = -EPERM; + goto out; + } + } else { + __set_bit(filter_idx, table->used_bitmap); + ++table->used; + } + *saved_spec = *spec; + + if (state->search_depth[spec->type] < depth) { + state->search_depth[spec->type] = depth; + efx_filter_push_rx_limits(efx); + } + + efx_writeo(efx, &filter, table->offset + table->step * filter_idx); + + netif_vdbg(efx, hw, efx->net_dev, + "%s: filter type %d index %d rxq %u set", + __func__, spec->type, filter_idx, spec->dmaq_id); + +out: + spin_unlock_bh(&state->lock); + return rc; +} + +static void efx_filter_table_clear_entry(struct efx_nic *efx, + struct efx_filter_table *table, + int filter_idx) +{ + static efx_oword_t filter; + + if (test_bit(filter_idx, table->used_bitmap)) { + __clear_bit(filter_idx, table->used_bitmap); + --table->used; + memset(&table->spec[filter_idx], 0, sizeof(table->spec[0])); + + efx_writeo(efx, &filter, + table->offset + table->step * filter_idx); + } +} + +/** + * efx_filter_remove_filter - remove a filter by specification + * @efx: NIC from which to remove the filter + * @spec: Specification for the filter + * + * On success, return zero. + * On failure, return a negative error code. + */ +int efx_filter_remove_filter(struct efx_nic *efx, struct efx_filter_spec *spec) +{ + struct efx_filter_state *state = efx->filter_state; + enum efx_filter_table_id table_id = + efx_filter_type_table_id(spec->type); + struct efx_filter_table *table = &state->table[table_id]; + struct efx_filter_spec *saved_spec; + efx_oword_t filter; + int filter_idx, depth; + u32 key; + int rc; + + key = efx_filter_build(&filter, spec); + + spin_lock_bh(&state->lock); + + rc = efx_filter_search(table, spec, key, false, &depth); + if (rc < 0) + goto out; + filter_idx = rc; + saved_spec = &table->spec[filter_idx]; + + if (spec->priority < saved_spec->priority) { + rc = -EPERM; + goto out; + } + + efx_filter_table_clear_entry(efx, table, filter_idx); + if (table->used == 0) + efx_filter_table_reset_search_depth(state, table_id); + rc = 0; + +out: + spin_unlock_bh(&state->lock); + return rc; +} + +/** + * efx_filter_table_clear - remove filters from a table by priority + * @efx: NIC from which to remove the filters + * @table_id: Table from which to remove the filters + * @priority: Maximum priority to remove + */ +void efx_filter_table_clear(struct efx_nic *efx, + enum efx_filter_table_id table_id, + enum efx_filter_priority priority) +{ + struct efx_filter_state *state = efx->filter_state; + struct efx_filter_table *table = &state->table[table_id]; + int filter_idx; + + spin_lock_bh(&state->lock); + + for (filter_idx = 0; filter_idx < table->size; ++filter_idx) + if (table->spec[filter_idx].priority <= priority) + efx_filter_table_clear_entry(efx, table, filter_idx); + if (table->used == 0) + efx_filter_table_reset_search_depth(state, table_id); + + spin_unlock_bh(&state->lock); +} + +/* Restore filter stater after reset */ +void efx_restore_filters(struct efx_nic *efx) +{ + struct efx_filter_state *state = efx->filter_state; + enum efx_filter_table_id table_id; + struct efx_filter_table *table; + efx_oword_t filter; + int filter_idx; + + spin_lock_bh(&state->lock); + + for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) { + table = &state->table[table_id]; + for (filter_idx = 0; filter_idx < table->size; filter_idx++) { + if (!test_bit(filter_idx, table->used_bitmap)) + continue; + efx_filter_build(&filter, &table->spec[filter_idx]); + efx_writeo(efx, &filter, + table->offset + table->step * filter_idx); + } + } + + efx_filter_push_rx_limits(efx); + + spin_unlock_bh(&state->lock); +} + +int efx_probe_filters(struct efx_nic *efx) +{ + struct efx_filter_state *state; + struct efx_filter_table *table; + unsigned table_id; + + state = kzalloc(sizeof(*efx->filter_state), GFP_KERNEL); + if (!state) + return -ENOMEM; + efx->filter_state = state; + + spin_lock_init(&state->lock); + + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { + table = &state->table[EFX_FILTER_TABLE_RX_IP]; + table->offset = FR_BZ_RX_FILTER_TBL0; + table->size = FR_BZ_RX_FILTER_TBL0_ROWS; + table->step = FR_BZ_RX_FILTER_TBL0_STEP; + } + + if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) { + table = &state->table[EFX_FILTER_TABLE_RX_MAC]; + table->offset = FR_CZ_RX_MAC_FILTER_TBL0; + table->size = FR_CZ_RX_MAC_FILTER_TBL0_ROWS; + table->step = FR_CZ_RX_MAC_FILTER_TBL0_STEP; + } + + for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) { + table = &state->table[table_id]; + if (table->size == 0) + continue; + table->used_bitmap = kcalloc(BITS_TO_LONGS(table->size), + sizeof(unsigned long), + GFP_KERNEL); + if (!table->used_bitmap) + goto fail; + table->spec = vmalloc(table->size * sizeof(*table->spec)); + if (!table->spec) + goto fail; + memset(table->spec, 0, table->size * sizeof(*table->spec)); + } + + return 0; + +fail: + efx_remove_filters(efx); + return -ENOMEM; +} + +void efx_remove_filters(struct efx_nic *efx) +{ + struct efx_filter_state *state = efx->filter_state; + enum efx_filter_table_id table_id; + + for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) { + kfree(state->table[table_id].used_bitmap); + vfree(state->table[table_id].spec); + } + kfree(state); +} diff --git a/drivers/net/sfc/filter.h b/drivers/net/sfc/filter.h new file mode 100644 index 000000000000..a53319ded79c --- /dev/null +++ b/drivers/net/sfc/filter.h @@ -0,0 +1,189 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2010 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#ifndef EFX_FILTER_H +#define EFX_FILTER_H + +#include <linux/types.h> + +enum efx_filter_table_id { + EFX_FILTER_TABLE_RX_IP = 0, + EFX_FILTER_TABLE_RX_MAC, + EFX_FILTER_TABLE_COUNT, +}; + +/** + * enum efx_filter_type - type of hardware filter + * @EFX_FILTER_RX_TCP_FULL: RX, matching TCP/IPv4 4-tuple + * @EFX_FILTER_RX_TCP_WILD: RX, matching TCP/IPv4 destination (host, port) + * @EFX_FILTER_RX_UDP_FULL: RX, matching UDP/IPv4 4-tuple + * @EFX_FILTER_RX_UDP_WILD: RX, matching UDP/IPv4 destination (host, port) + * @EFX_FILTER_RX_MAC_FULL: RX, matching Ethernet destination MAC address, VID + * @EFX_FILTER_RX_MAC_WILD: RX, matching Ethernet destination MAC address + * + * Falcon NICs only support the RX TCP/IPv4 and UDP/IPv4 filter types. + */ +enum efx_filter_type { + EFX_FILTER_RX_TCP_FULL = 0, + EFX_FILTER_RX_TCP_WILD, + EFX_FILTER_RX_UDP_FULL, + EFX_FILTER_RX_UDP_WILD, + EFX_FILTER_RX_MAC_FULL = 4, + EFX_FILTER_RX_MAC_WILD, + EFX_FILTER_TYPE_COUNT, +}; + +/** + * enum efx_filter_priority - priority of a hardware filter specification + * @EFX_FILTER_PRI_HINT: Performance hint + * @EFX_FILTER_PRI_MANUAL: Manually configured filter + * @EFX_FILTER_PRI_REQUIRED: Required for correct behaviour + */ +enum efx_filter_priority { + EFX_FILTER_PRI_HINT = 0, + EFX_FILTER_PRI_MANUAL, + EFX_FILTER_PRI_REQUIRED, +}; + +/** + * enum efx_filter_flags - flags for hardware filter specifications + * @EFX_FILTER_FLAG_RX_RSS: Use RSS to spread across multiple queues. + * By default, matching packets will be delivered only to the + * specified queue. If this flag is set, they will be delivered + * to a range of queues offset from the specified queue number + * according to the indirection table. + * @EFX_FILTER_FLAG_RX_SCATTER: Enable DMA scatter on the receiving + * queue. + * @EFX_FILTER_FLAG_RX_OVERRIDE_IP: Enables a MAC filter to override + * any IP filter that matches the same packet. By default, IP + * filters take precedence. + * + * Currently, no flags are defined for TX filters. + */ +enum efx_filter_flags { + EFX_FILTER_FLAG_RX_RSS = 0x01, + EFX_FILTER_FLAG_RX_SCATTER = 0x02, + EFX_FILTER_FLAG_RX_OVERRIDE_IP = 0x04, +}; + +/** + * struct efx_filter_spec - specification for a hardware filter + * @type: Type of match to be performed, from &enum efx_filter_type + * @priority: Priority of the filter, from &enum efx_filter_priority + * @flags: Miscellaneous flags, from &enum efx_filter_flags + * @dmaq_id: Source/target queue index + * @data: Match data (type-dependent) + * + * Use the efx_filter_set_*() functions to initialise the @type and + * @data fields. + */ +struct efx_filter_spec { + u8 type:4; + u8 priority:4; + u8 flags; + u16 dmaq_id; + u32 data[3]; +}; + +/** + * efx_filter_set_rx_tcp_full - specify RX filter with TCP/IPv4 full match + * @spec: Specification to initialise + * @shost: Source host address (host byte order) + * @sport: Source port (host byte order) + * @dhost: Destination host address (host byte order) + * @dport: Destination port (host byte order) + */ +static inline void +efx_filter_set_rx_tcp_full(struct efx_filter_spec *spec, + u32 shost, u16 sport, u32 dhost, u16 dport) +{ + spec->type = EFX_FILTER_RX_TCP_FULL; + spec->data[0] = sport | shost << 16; + spec->data[1] = dport << 16 | shost >> 16; + spec->data[2] = dhost; +} + +/** + * efx_filter_set_rx_tcp_wild - specify RX filter with TCP/IPv4 wildcard match + * @spec: Specification to initialise + * @dhost: Destination host address (host byte order) + * @dport: Destination port (host byte order) + */ +static inline void +efx_filter_set_rx_tcp_wild(struct efx_filter_spec *spec, u32 dhost, u16 dport) +{ + spec->type = EFX_FILTER_RX_TCP_WILD; + spec->data[0] = 0; + spec->data[1] = dport << 16; + spec->data[2] = dhost; +} + +/** + * efx_filter_set_rx_udp_full - specify RX filter with UDP/IPv4 full match + * @spec: Specification to initialise + * @shost: Source host address (host byte order) + * @sport: Source port (host byte order) + * @dhost: Destination host address (host byte order) + * @dport: Destination port (host byte order) + */ +static inline void +efx_filter_set_rx_udp_full(struct efx_filter_spec *spec, + u32 shost, u16 sport, u32 dhost, u16 dport) +{ + spec->type = EFX_FILTER_RX_UDP_FULL; + spec->data[0] = sport | shost << 16; + spec->data[1] = dport << 16 | shost >> 16; + spec->data[2] = dhost; +} + +/** + * efx_filter_set_rx_udp_wild - specify RX filter with UDP/IPv4 wildcard match + * @spec: Specification to initialise + * @dhost: Destination host address (host byte order) + * @dport: Destination port (host byte order) + */ +static inline void +efx_filter_set_rx_udp_wild(struct efx_filter_spec *spec, u32 dhost, u16 dport) +{ + spec->type = EFX_FILTER_RX_UDP_WILD; + spec->data[0] = dport; + spec->data[1] = 0; + spec->data[2] = dhost; +} + +/** + * efx_filter_set_rx_mac_full - specify RX filter with MAC full match + * @spec: Specification to initialise + * @vid: VLAN ID + * @addr: Destination MAC address + */ +static inline void efx_filter_set_rx_mac_full(struct efx_filter_spec *spec, + u16 vid, const u8 *addr) +{ + spec->type = EFX_FILTER_RX_MAC_FULL; + spec->data[0] = vid; + spec->data[1] = addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5]; + spec->data[2] = addr[0] << 8 | addr[1]; +} + +/** + * efx_filter_set_rx_mac_full - specify RX filter with MAC wildcard match + * @spec: Specification to initialise + * @addr: Destination MAC address + */ +static inline void efx_filter_set_rx_mac_wild(struct efx_filter_spec *spec, + const u8 *addr) +{ + spec->type = EFX_FILTER_RX_MAC_WILD; + spec->data[0] = 0; + spec->data[1] = addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5]; + spec->data[2] = addr[0] << 8 | addr[1]; +} + +#endif /* EFX_FILTER_H */ diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index 152342dbff29..b3f2bf436735 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -29,6 +29,7 @@ #include <linux/device.h> #include <linux/highmem.h> #include <linux/workqueue.h> +#include <linux/vmalloc.h> #include <linux/i2c.h> #include "enum.h" @@ -619,6 +620,8 @@ union efx_multicast_hash { efx_oword_t oword[EFX_MCAST_HASH_ENTRIES / sizeof(efx_oword_t) / 8]; }; +struct efx_filter_state; + /** * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) @@ -799,6 +802,8 @@ struct efx_nic { u64 loopback_modes; void *loopback_selftest; + + struct efx_filter_state *filter_state; }; static inline int efx_dev_registered(struct efx_nic *efx) diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c index 6c5c0cefa9d8..c4de0014441c 100644 --- a/drivers/net/sfc/nic.c +++ b/drivers/net/sfc/nic.c @@ -1849,8 +1849,7 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = { REGISTER_TABLE_BB_CZ(TX_DESC_PTR_TBL), REGISTER_TABLE_AA(EVQ_PTR_TBL_KER), REGISTER_TABLE_BB_CZ(EVQ_PTR_TBL), - /* The register buffer is allocated with slab, so we can't - * reasonably read all of the buffer table (up to 8MB!). + /* We can't reasonably read all of the buffer table (up to 8MB!). * However this driver will only use a few entries. Reading * 1K entries allows for some expansion of queue count and * size before we need to change the version. */ @@ -1858,7 +1857,6 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = { A, A, 8, 1024), REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL, FR_BZ_BUF_FULL_TBL, B, Z, 8, 1024), - /* RX_FILTER_TBL{0,1} is huge and not used by this driver */ REGISTER_TABLE_CZ(RX_MAC_FILTER_TBL0), REGISTER_TABLE_BB_CZ(TIMER_TBL), REGISTER_TABLE_BB_CZ(TX_PACE_TBL), @@ -1868,6 +1866,7 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = { REGISTER_TABLE_CZ(MC_TREG_SMEM), /* MSIX_PBA_TABLE is not mapped */ /* SRM_DBG is not mapped (and is redundant with BUF_FLL_TBL) */ + REGISTER_TABLE_BZ(RX_FILTER_TBL0), }; size_t efx_nic_get_regs_len(struct efx_nic *efx) diff --git a/drivers/net/sfc/regs.h b/drivers/net/sfc/regs.h index 18a3be428348..96430ed81c36 100644 --- a/drivers/net/sfc/regs.h +++ b/drivers/net/sfc/regs.h @@ -2893,6 +2893,20 @@ #define FRF_AB_XX_FORCE_SIG_WIDTH 8 #define FFE_AB_XX_FORCE_SIG_ALL_LANES 0xff +/* RX_MAC_FILTER_TBL0 */ +/* RMFT_DEST_MAC is wider than 32 bits */ +#define FRF_CZ_RMFT_DEST_MAC_LO_LBN 12 +#define FRF_CZ_RMFT_DEST_MAC_LO_WIDTH 32 +#define FRF_CZ_RMFT_DEST_MAC_HI_LBN 44 +#define FRF_CZ_RMFT_DEST_MAC_HI_WIDTH 16 + +/* TX_MAC_FILTER_TBL0 */ +/* TMFT_SRC_MAC is wider than 32 bits */ +#define FRF_CZ_TMFT_SRC_MAC_LO_LBN 12 +#define FRF_CZ_TMFT_SRC_MAC_LO_WIDTH 32 +#define FRF_CZ_TMFT_SRC_MAC_HI_LBN 44 +#define FRF_CZ_TMFT_SRC_MAC_HI_WIDTH 16 + /* DRIVER_EV */ /* Sub-fields of an RX flush completion event */ #define FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL_LBN 12 diff --git a/drivers/net/sfc/siena.c b/drivers/net/sfc/siena.c index 9f5368049694..2115f95ddc88 100644 --- a/drivers/net/sfc/siena.c +++ b/drivers/net/sfc/siena.c @@ -651,6 +651,6 @@ struct efx_nic_type siena_a0_nic_type = { .tx_dc_base = 0x88000, .rx_dc_base = 0x68000, .offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_RXHASH), + NETIF_F_RXHASH | NETIF_F_NTUPLE), .reset_world_flags = ETH_RESET_MGMT << ETH_RESET_SHARED_SHIFT, }; diff --git a/drivers/net/sundance.c b/drivers/net/sundance.c index 7dfdbee878e8..8b5aeca24d5d 100644 --- a/drivers/net/sundance.c +++ b/drivers/net/sundance.c @@ -96,6 +96,7 @@ static char *media[MAX_UNITS]; #include <asm/io.h> #include <linux/delay.h> #include <linux/spinlock.h> +#include <linux/dma-mapping.h> #ifndef _COMPAT_WITH_OLD_KERNEL #include <linux/crc32.h> #include <linux/ethtool.h> @@ -523,13 +524,15 @@ static int __devinit sundance_probe1 (struct pci_dev *pdev, tasklet_init(&np->rx_tasklet, rx_poll, (unsigned long)dev); tasklet_init(&np->tx_tasklet, tx_poll, (unsigned long)dev); - ring_space = pci_alloc_consistent(pdev, TX_TOTAL_SIZE, &ring_dma); + ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, + &ring_dma, GFP_KERNEL); if (!ring_space) goto err_out_cleardev; np->tx_ring = (struct netdev_desc *)ring_space; np->tx_ring_dma = ring_dma; - ring_space = pci_alloc_consistent(pdev, RX_TOTAL_SIZE, &ring_dma); + ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, + &ring_dma, GFP_KERNEL); if (!ring_space) goto err_out_unmap_tx; np->rx_ring = (struct netdev_desc *)ring_space; @@ -663,9 +666,11 @@ static int __devinit sundance_probe1 (struct pci_dev *pdev, err_out_unregister: unregister_netdev(dev); err_out_unmap_rx: - pci_free_consistent(pdev, RX_TOTAL_SIZE, np->rx_ring, np->rx_ring_dma); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, + np->rx_ring, np->rx_ring_dma); err_out_unmap_tx: - pci_free_consistent(pdev, TX_TOTAL_SIZE, np->tx_ring, np->tx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, + np->tx_ring, np->tx_ring_dma); err_out_cleardev: pci_set_drvdata(pdev, NULL); pci_iounmap(pdev, ioaddr); @@ -1011,8 +1016,14 @@ static void init_ring(struct net_device *dev) skb->dev = dev; /* Mark as being used by this device. */ skb_reserve(skb, 2); /* 16 byte align the IP header. */ np->rx_ring[i].frag[0].addr = cpu_to_le32( - pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, - PCI_DMA_FROMDEVICE)); + dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE)); + if (dma_mapping_error(&np->pci_dev->dev, + np->rx_ring[i].frag[0].addr)) { + dev_kfree_skb(skb); + np->rx_skbuff[i] = NULL; + break; + } np->rx_ring[i].frag[0].length = cpu_to_le32(np->rx_buf_sz | LastFrag); } np->dirty_rx = (unsigned int)(i - RX_RING_SIZE); @@ -1063,9 +1074,11 @@ start_tx (struct sk_buff *skb, struct net_device *dev) txdesc->next_desc = 0; txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign); - txdesc->frag[0].addr = cpu_to_le32 (pci_map_single (np->pci_dev, skb->data, - skb->len, - PCI_DMA_TODEVICE)); + txdesc->frag[0].addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev, + skb->data, skb->len, DMA_TO_DEVICE)); + if (dma_mapping_error(&np->pci_dev->dev, + txdesc->frag[0].addr)) + goto drop_frame; txdesc->frag[0].length = cpu_to_le32 (skb->len | LastFrag); /* Increment cur_tx before tasklet_schedule() */ @@ -1087,6 +1100,12 @@ start_tx (struct sk_buff *skb, struct net_device *dev) dev->name, np->cur_tx, entry); } return NETDEV_TX_OK; + +drop_frame: + dev_kfree_skb(skb); + np->tx_skbuff[entry] = NULL; + dev->stats.tx_dropped++; + return NETDEV_TX_OK; } /* Reset hardware tx and free all of tx buffers */ @@ -1097,7 +1116,6 @@ reset_tx (struct net_device *dev) void __iomem *ioaddr = np->base; struct sk_buff *skb; int i; - int irq = in_interrupt(); /* Reset tx logic, TxListPtr will be cleaned */ iowrite16 (TxDisable, ioaddr + MACCtrl1); @@ -1109,13 +1127,10 @@ reset_tx (struct net_device *dev) skb = np->tx_skbuff[i]; if (skb) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[i].frag[0].addr), - skb->len, PCI_DMA_TODEVICE); - if (irq) - dev_kfree_skb_irq (skb); - else - dev_kfree_skb (skb); + skb->len, DMA_TO_DEVICE); + dev_kfree_skb_any(skb); np->tx_skbuff[i] = NULL; dev->stats.tx_dropped++; } @@ -1233,9 +1248,9 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) break; skb = np->tx_skbuff[entry]; /* Free the original skb. */ - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), - skb->len, PCI_DMA_TODEVICE); + skb->len, DMA_TO_DEVICE); dev_kfree_skb_irq (np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; @@ -1252,9 +1267,9 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) break; skb = np->tx_skbuff[entry]; /* Free the original skb. */ - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), - skb->len, PCI_DMA_TODEVICE); + skb->len, DMA_TO_DEVICE); dev_kfree_skb_irq (np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; @@ -1334,22 +1349,18 @@ static void rx_poll(unsigned long data) if (pkt_len < rx_copybreak && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ - pci_dma_sync_single_for_cpu(np->pci_dev, - le32_to_cpu(desc->frag[0].addr), - np->rx_buf_sz, - PCI_DMA_FROMDEVICE); - + dma_sync_single_for_cpu(&np->pci_dev->dev, + le32_to_cpu(desc->frag[0].addr), + np->rx_buf_sz, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len); - pci_dma_sync_single_for_device(np->pci_dev, - le32_to_cpu(desc->frag[0].addr), - np->rx_buf_sz, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&np->pci_dev->dev, + le32_to_cpu(desc->frag[0].addr), + np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb, pkt_len); } else { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(desc->frag[0].addr), - np->rx_buf_sz, - PCI_DMA_FROMDEVICE); + np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb = np->rx_skbuff[entry], pkt_len); np->rx_skbuff[entry] = NULL; } @@ -1396,8 +1407,14 @@ static void refill_rx (struct net_device *dev) skb->dev = dev; /* Mark as being used by this device. */ skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ np->rx_ring[entry].frag[0].addr = cpu_to_le32( - pci_map_single(np->pci_dev, skb->data, - np->rx_buf_sz, PCI_DMA_FROMDEVICE)); + dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE)); + if (dma_mapping_error(&np->pci_dev->dev, + np->rx_ring[entry].frag[0].addr)) { + dev_kfree_skb_irq(skb); + np->rx_skbuff[entry] = NULL; + break; + } } /* Perhaps we need not reset this field. */ np->rx_ring[entry].frag[0].length = @@ -1715,9 +1732,9 @@ static int netdev_close(struct net_device *dev) np->rx_ring[i].status = 0; skb = np->rx_skbuff[i]; if (skb) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->rx_ring[i].frag[0].addr), - np->rx_buf_sz, PCI_DMA_FROMDEVICE); + np->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(skb); np->rx_skbuff[i] = NULL; } @@ -1727,9 +1744,9 @@ static int netdev_close(struct net_device *dev) np->tx_ring[i].next_desc = 0; skb = np->tx_skbuff[i]; if (skb) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[i].frag[0].addr), - skb->len, PCI_DMA_TODEVICE); + skb->len, DMA_TO_DEVICE); dev_kfree_skb(skb); np->tx_skbuff[i] = NULL; } @@ -1743,17 +1760,16 @@ static void __devexit sundance_remove1 (struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); if (dev) { - struct netdev_private *np = netdev_priv(dev); - - unregister_netdev(dev); - pci_free_consistent(pdev, RX_TOTAL_SIZE, np->rx_ring, - np->rx_ring_dma); - pci_free_consistent(pdev, TX_TOTAL_SIZE, np->tx_ring, - np->tx_ring_dma); - pci_iounmap(pdev, np->base); - pci_release_regions(pdev); - free_netdev(dev); - pci_set_drvdata(pdev, NULL); + struct netdev_private *np = netdev_priv(dev); + unregister_netdev(dev); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, + np->rx_ring, np->rx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, + np->tx_ring, np->tx_ring_dma); + pci_iounmap(pdev, np->base); + pci_release_regions(pdev); + free_netdev(dev); + pci_set_drvdata(pdev, NULL); } } diff --git a/drivers/net/tokenring/tmspci.c b/drivers/net/tokenring/tmspci.c index d4c7c0c0a3d6..d3e788a9cd1c 100644 --- a/drivers/net/tokenring/tmspci.c +++ b/drivers/net/tokenring/tmspci.c @@ -125,18 +125,16 @@ static int __devinit tms_pci_attach(struct pci_dev *pdev, const struct pci_devic dev->irq = pci_irq_line; dev->dma = 0; - printk("%s: %s\n", dev->name, cardinfo->name); - printk("%s: IO: %#4lx IRQ: %d\n", - dev->name, dev->base_addr, dev->irq); + dev_info(&pdev->dev, "%s\n", cardinfo->name); + dev_info(&pdev->dev, " IO: %#4lx IRQ: %d\n", dev->base_addr, dev->irq); tms_pci_read_eeprom(dev); - printk("%s: Ring Station Address: %pM\n", - dev->name, dev->dev_addr); + dev_info(&pdev->dev, " Ring Station Address: %pM\n", dev->dev_addr); ret = tmsdev_init(dev, &pdev->dev); if (ret) { - printk("%s: unable to get memory for dev->priv.\n", dev->name); + dev_info(&pdev->dev, "unable to get memory for dev->priv.\n"); goto err_out_region; } diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 7434a8353e23..7187bd8a75f6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -165,8 +165,10 @@ enum { DCCPO_TIMESTAMP_ECHO = 42, DCCPO_ELAPSED_TIME = 43, DCCPO_MAX = 45, - DCCPO_MIN_CCID_SPECIFIC = 128, - DCCPO_MAX_CCID_SPECIFIC = 255, + DCCPO_MIN_RX_CCID_SPECIFIC = 128, /* from sender to receiver */ + DCCPO_MAX_RX_CCID_SPECIFIC = 191, + DCCPO_MIN_TX_CCID_SPECIFIC = 192, /* from receiver to sender */ + DCCPO_MAX_TX_CCID_SPECIFIC = 255, }; /* maximum size of a single TLV-encoded DCCP option (sans type/len bytes) */ #define DCCP_SINGLE_OPT_MAXLEN 253 diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b67af60a8890..8a3338ceb438 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -14,6 +14,7 @@ #define _LINUX_ETHTOOL_H #include <linux/types.h> +#include <linux/if_ether.h> /* This should work for both 32 and 64 bit userland. */ struct ethtool_cmd { @@ -391,6 +392,7 @@ struct ethtool_rx_flow_spec { struct ethtool_ah_espip4_spec ah_ip4_spec; struct ethtool_ah_espip4_spec esp_ip4_spec; struct ethtool_usrip4_spec usr_ip4_spec; + struct ethhdr ether_spec; __u8 hdata[72]; } h_u, m_u; __u64 ring_cookie; @@ -483,6 +485,7 @@ struct ethtool_rx_ntuple_flow_spec { struct ethtool_ah_espip4_spec ah_ip4_spec; struct ethtool_ah_espip4_spec esp_ip4_spec; struct ethtool_usrip4_spec usr_ip4_spec; + struct ethhdr ether_spec; __u8 hdata[72]; } h_u, m_u; @@ -492,11 +495,12 @@ struct ethtool_rx_ntuple_flow_spec { __u64 data_mask; __s32 action; -#define ETHTOOL_RXNTUPLE_ACTION_DROP -1 /* drop packet */ +#define ETHTOOL_RXNTUPLE_ACTION_DROP (-1) /* drop packet */ +#define ETHTOOL_RXNTUPLE_ACTION_CLEAR (-2) /* clear filter */ }; /** - * struct ethtool_rx_ntuple - command to set RX flow filter + * struct ethtool_rx_ntuple - command to set or clear RX flow filter * @cmd: Command number - %ETHTOOL_SRXNTUPLE * @fs: Flow filter specification */ @@ -840,7 +844,7 @@ struct ethtool_ops { #define WAKE_MAGIC (1 << 5) #define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ -/* L3-L4 network traffic flow types */ +/* L2-L4 network traffic flow types */ #define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ #define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ #define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ @@ -856,6 +860,7 @@ struct ethtool_ops { #define IP_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ #define IPV4_FLOW 0x10 /* hash only */ #define IPV6_FLOW 0x11 /* hash only */ +#define ETHER_FLOW 0x12 /* spec only (ether_spec) */ /* L3-L4 network traffic flow hash options */ #define RXH_L2DA (1 << 1) diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 29bcd55851eb..397921b09ef9 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -204,7 +204,7 @@ struct pppox_proto { struct module *owner; }; -extern int register_pppox_proto(int proto_num, struct pppox_proto *pp); +extern int register_pppox_proto(int proto_num, const struct pppox_proto *pp); extern void unregister_pppox_proto(int proto_num); extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */ extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 45375b41a2a0..7d178a758acf 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -174,20 +174,32 @@ extern int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, extern int register_inet6addr_notifier(struct notifier_block *nb); extern int unregister_inet6addr_notifier(struct notifier_block *nb); -static inline struct inet6_dev * -__in6_dev_get(struct net_device *dev) +/** + * __in6_dev_get - get inet6_dev pointer from netdevice + * @dev: network device + * + * Caller must hold rcu_read_lock or RTNL, because this function + * does not take a reference on the inet6_dev. + */ +static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) { - return rcu_dereference_check(dev->ip6_ptr, - rcu_read_lock_held() || - lockdep_rtnl_is_held()); + return rcu_dereference_rtnl(dev->ip6_ptr); } -static inline struct inet6_dev * -in6_dev_get(struct net_device *dev) +/** + * in6_dev_get - get inet6_dev pointer from netdevice + * @dev: network device + * + * This version can be used in any context, and takes a reference + * on the inet6_dev. Callers must use in6_dev_put() later to + * release this reference. + */ +static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) { - struct inet6_dev *idev = NULL; + struct inet6_dev *idev; + rcu_read_lock(); - idev = __in6_dev_get(dev); + idev = rcu_dereference(dev->ip6_ptr); if (idev) atomic_inc(&idev->refcnt); rcu_read_unlock(); @@ -196,16 +208,21 @@ in6_dev_get(struct net_device *dev) extern void in6_dev_finish_destroy(struct inet6_dev *idev); -static inline void -in6_dev_put(struct inet6_dev *idev) +static inline void in6_dev_put(struct inet6_dev *idev) { if (atomic_dec_and_test(&idev->refcnt)) in6_dev_finish_destroy(idev); } -#define __in6_dev_put(idev) atomic_dec(&(idev)->refcnt) -#define in6_dev_hold(idev) atomic_inc(&(idev)->refcnt) +static inline void __in6_dev_put(struct inet6_dev *idev) +{ + atomic_dec(&idev->refcnt); +} +static inline void in6_dev_hold(struct inet6_dev *idev) +{ + atomic_inc(&idev->refcnt); +} extern void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); @@ -215,9 +232,15 @@ static inline void in6_ifa_put(struct inet6_ifaddr *ifp) inet6_ifa_finish_destroy(ifp); } -#define __in6_ifa_put(ifp) atomic_dec(&(ifp)->refcnt) -#define in6_ifa_hold(ifp) atomic_inc(&(ifp)->refcnt) +static inline void __in6_ifa_put(struct inet6_ifaddr *ifp) +{ + atomic_dec(&ifp->refcnt); +} +static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) +{ + atomic_inc(&ifp->refcnt); +} /* @@ -240,23 +263,23 @@ static inline int ipv6_addr_is_multicast(const struct in6_addr *addr) static inline int ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) { - return (((addr->s6_addr32[0] ^ htonl(0xff020000)) | + return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | - (addr->s6_addr32[3] ^ htonl(0x00000001))) == 0); + (addr->s6_addr32[3] ^ htonl(0x00000001))) == 0; } static inline int ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) { - return (((addr->s6_addr32[0] ^ htonl(0xff020000)) | + return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | - (addr->s6_addr32[3] ^ htonl(0x00000002))) == 0); + (addr->s6_addr32[3] ^ htonl(0x00000002))) == 0; } extern int __ipv6_isatap_ifid(u8 *eui, __be32 addr); static inline int ipv6_addr_is_isatap(const struct in6_addr *addr) { - return ((addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE)); + return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); } #ifdef CONFIG_PROC_FS diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 8d9503ad01da..b26ce343072c 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -25,6 +25,7 @@ struct vlan_priority_tci_mapping { * @rx_multicast: number of received multicast packets * @syncp: synchronization point for 64bit counters * @rx_errors: number of errors + * @rx_dropped: number of dropped packets */ struct vlan_rx_stats { u64 rx_packets; @@ -32,6 +33,7 @@ struct vlan_rx_stats { u64 rx_multicast; struct u64_stats_sync syncp; unsigned long rx_errors; + unsigned long rx_dropped; }; /** diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3bccdd12a264..94a1feddeb49 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -225,7 +225,10 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, } } - netif_rx(skb); + if (unlikely(netif_rx(skb) == NET_RX_DROP)) { + if (rx_stats) + rx_stats->rx_dropped++; + } rcu_read_unlock(); return NET_RX_SUCCESS; @@ -843,13 +846,15 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st accum.rx_packets += rxpackets; accum.rx_bytes += rxbytes; accum.rx_multicast += rxmulticast; - /* rx_errors is an ulong, not protected by syncp */ + /* rx_errors, rx_dropped are ulong, not protected by syncp */ accum.rx_errors += p->rx_errors; + accum.rx_dropped += p->rx_dropped; } stats->rx_packets = accum.rx_packets; stats->rx_bytes = accum.rx_bytes; stats->rx_errors = accum.rx_errors; stats->multicast = accum.rx_multicast; + stats->rx_dropped = accum.rx_dropped; } return stats; } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 0fd01dd17c48..b99369a055d1 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -173,7 +173,7 @@ static int receive(struct sk_buff *skb, struct net_device *dev, net = dev_net(dev); pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); caifd = caif_get(dev); - if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) + if (!caifd || !caifd->layer.up || !caifd->layer.up->receive) return NET_RX_DROP; if (caifd->layer.up->receive(caifd->layer.up, pkt)) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index fd1f5df0827c..4d918f8f4e67 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -30,9 +30,6 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(AF_CAIF); -#define CAIF_DEF_SNDBUF (4096*10) -#define CAIF_DEF_RCVBUF (4096*100) - /* * CAIF state is re-using the TCP socket states. * caif_states stored in sk_state reflect the state as reported by @@ -159,9 +156,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) { - trace_printk("CAIF: %s(): " - "sending flow OFF (queue len = %d %d)\n", - __func__, + pr_debug("sending flow OFF (queue len = %d %d)\n", atomic_read(&cf_sk->sk.sk_rmem_alloc), sk_rcvbuf_lowwater(cf_sk)); set_rx_flow_off(cf_sk); @@ -174,9 +169,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return err; if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) { set_rx_flow_off(cf_sk); - trace_printk("CAIF: %s(): " - "sending flow OFF due to rmem_schedule\n", - __func__); + pr_debug("sending flow OFF due to rmem_schedule\n"); dbfs_atomic_inc(&cnt.num_rx_flow_off); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } @@ -1122,10 +1115,6 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, /* Store the protocol */ sk->sk_protocol = (unsigned char) protocol; - /* Sendbuf dictates the amount of outbound packets not yet sent */ - sk->sk_sndbuf = CAIF_DEF_SNDBUF; - sk->sk_rcvbuf = CAIF_DEF_RCVBUF; - /* * Lock in order to try to stop someone from opening the socket * too early. diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index ef93a131310b..41adafd18914 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -197,7 +197,7 @@ int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) caif_assert(adap_layer != NULL); channel_id = adap_layer->id; if (adap_layer->dn == NULL || channel_id == 0) { - pr_err("adap_layer->id is 0\n"); + pr_err("adap_layer->dn == NULL or adap_layer->id is 0\n"); ret = -ENOTCONN; goto end; } diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 86aac24b0225..84a422c98941 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -30,9 +30,6 @@ #define CONNECT_TIMEOUT (5 * HZ) #define CAIF_NET_DEFAULT_QUEUE_LEN 500 -#undef pr_debug -#define pr_debug pr_warn - /*This list is protected by the rtnl lock. */ static LIST_HEAD(chnl_net_list); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 91ffce20c36b..7d7e572cedc7 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -19,6 +19,7 @@ #include <linux/netdevice.h> #include <linux/bitops.h> #include <linux/uaccess.h> +#include <linux/vmalloc.h> #include <linux/slab.h> /* @@ -815,7 +816,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = kmalloc(reglen, GFP_USER); + regbuf = vmalloc(reglen); if (!regbuf) return -ENOMEM; @@ -830,7 +831,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) ret = 0; out: - kfree(regbuf); + vfree(regbuf); return ret; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 386c2283f14e..2c0df0f95b3d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -729,16 +729,14 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, *num = 0; for (; i < maxlen; i++) { + int value; char c; *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; - if ((c >= '0') && (c <= '9')) - *num |= c - '0'; - else if ((c >= 'a') && (c <= 'f')) - *num |= c - 'a' + 10; - else if ((c >= 'A') && (c <= 'F')) - *num |= c - 'A' + 10; + value = hex_to_bin(c); + if (value >= 0) + *num |= value; else break; } diff --git a/net/core/utils.c b/net/core/utils.c index f41854470539..ec6bb322f372 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -92,18 +92,19 @@ EXPORT_SYMBOL(in_aton); static inline int xdigit2bin(char c, int delim) { + int val; + if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; - if (c >= '0' && c <= '9') - return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); - if (c >= 'a' && c <= 'f') - return (IN6PTON_XDIGIT | (c - 'a' + 10)); - if (c >= 'A' && c <= 'F') - return (IN6PTON_XDIGIT | (c - 'A' + 10)); + + val = hex_to_bin(c); + if (val >= 0) + return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); + if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6df6f8ac9636..6d16a9070ff0 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -62,18 +62,14 @@ struct ccid_operations { void (*ccid_hc_tx_exit)(struct sock *sk); void (*ccid_hc_rx_packet_recv)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_rx_parse_options)(struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_rx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_tx_parse_options)(struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_tx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_tx_send_packet)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_sent)(struct sock *sk, @@ -168,27 +164,31 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb); } +/** + * ccid_hc_tx_parse_options - Parse CCID-specific options sent by the receiver + * @pkt: type of packet that @opt appears on (RFC 4340, 5.1) + * @opt: the CCID-specific option type (RFC 4340, 5.8 and 10.3) + * @val: value of @opt + * @len: length of @val in bytes + */ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx, - value); - return rc; + if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } +/** + * ccid_hc_rx_parse_options - Parse CCID-specific options sent by the sender + * Arguments are analogous to ccid_hc_tx_parse_options() + */ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value); - return rc; + if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index ce8059130070..c3f3a25bbd7a 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -54,7 +54,6 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) [TFRC_SSTATE_NO_SENT] = "NO_SENT", [TFRC_SSTATE_NO_FBACK] = "NO_FBACK", [TFRC_SSTATE_FBACK] = "FBACK", - [TFRC_SSTATE_TERM] = "TERM", }; return ccid3_state_names[state]; @@ -208,10 +207,13 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, ccid3_tx_state_name(hc->tx_state)); + /* Ignore and do not restart after leaving the established state */ + if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) + goto out; + + /* Reset feedback state to "no feedback received" */ if (hc->tx_state == TFRC_SSTATE_FBACK) ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - else if (hc->tx_state != TFRC_SSTATE_NO_FBACK) - goto out; /* * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4 @@ -287,8 +289,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) if (unlikely(skb->len == 0)) return -EBADMSG; - switch (hc->tx_state) { - case TFRC_SSTATE_NO_SENT: + if (hc->tx_state == TFRC_SSTATE_NO_SENT) { sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); hc->tx_last_win_count = 0; @@ -323,9 +324,8 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) ccid3_update_send_interval(hc); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - break; - case TFRC_SSTATE_NO_FBACK: - case TFRC_SSTATE_FBACK: + + } else { delay = ktime_us_delta(hc->tx_t_nom, now); ccid3_pr_debug("delay=%ld\n", (long)delay); /* @@ -340,10 +340,6 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) return (u32)delay / USEC_PER_MSEC; ccid3_hc_tx_update_win_count(hc, now); - break; - case TFRC_SSTATE_TERM: - DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk); - return -EINVAL; } /* prepare to send now (add options etc.) */ @@ -369,21 +365,15 @@ static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv = &hc->tx_options_received; struct tfrc_tx_hist_entry *acked; ktime_t now; unsigned long t_nfb; - u32 pinv, r_sample; + u32 r_sample; /* we are only interested in ACKs */ if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK || DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK)) return; - /* ... and only in the established state */ - if (hc->tx_state != TFRC_SSTATE_FBACK && - hc->tx_state != TFRC_SSTATE_NO_FBACK) - return; - /* * Locate the acknowledged packet in the TX history. * @@ -403,17 +393,6 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp)); hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9); - /* Update receive rate in units of 64 * bytes/second */ - hc->tx_x_recv = opt_recv->ccid3or_receive_rate; - hc->tx_x_recv <<= 6; - - /* Update loss event rate (which is scaled by 1e6) */ - pinv = opt_recv->ccid3or_loss_event_rate; - if (pinv == ~0U || pinv == 0) /* see RFC 4342, 8.5 */ - hc->tx_p = 0; - else /* can not exceed 100% */ - hc->tx_p = scaled_div(1, pinv); - /* * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ @@ -481,30 +460,36 @@ done_computing_x: jiffies + usecs_to_jiffies(t_nfb)); } -static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, - unsigned char len, u16 idx, - unsigned char *value) +static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, + u8 option, u8 *optval, u8 optlen) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv = &hc->tx_options_received; __be32 opt_val; switch (option) { case TFRC_OPT_RECEIVE_RATE: case TFRC_OPT_LOSS_EVENT_RATE: - if (unlikely(len != 4)) { + /* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */ + if (packet_type == DCCP_PKT_DATA) + break; + if (unlikely(optlen != 4)) { DCCP_WARN("%s(%p), invalid len %d for %u\n", - dccp_role(sk), sk, len, option); + dccp_role(sk), sk, optlen, option); return -EINVAL; } - opt_val = ntohl(get_unaligned((__be32 *)value)); + opt_val = ntohl(get_unaligned((__be32 *)optval)); if (option == TFRC_OPT_RECEIVE_RATE) { - opt_recv->ccid3or_receive_rate = opt_val; + /* Receive Rate is kept in units of 64 bytes/second */ + hc->tx_x_recv = opt_val; + hc->tx_x_recv <<= 6; + ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n", dccp_role(sk), sk, opt_val); } else { - opt_recv->ccid3or_loss_event_rate = opt_val; + /* Update the fixpoint Loss Event Rate fraction */ + hc->tx_p = tfrc_invert_loss_event_rate(opt_val); + ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", dccp_role(sk), sk, opt_val); } @@ -527,9 +512,7 @@ static void ccid3_hc_tx_exit(struct sock *sk) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM); sk_stop_timer(sk, &hc->tx_no_feedback_timer); - tfrc_tx_hist_purge(&hc->tx_hist); } @@ -588,7 +571,6 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) static const char *const ccid3_rx_state_names[] = { [TFRC_RSTATE_NO_DATA] = "NO_DATA", [TFRC_RSTATE_DATA] = "DATA", - [TFRC_RSTATE_TERM] = "TERM", }; return ccid3_rx_state_names[state]; @@ -614,14 +596,9 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now; + ktime_t now = ktime_get_real(); s64 delta = 0; - if (unlikely(hc->rx_state == TFRC_RSTATE_TERM)) - return; - - now = ktime_get_real(); - switch (fbtype) { case CCID3_FBACK_INITIAL: hc->rx_x_recv = 0; @@ -825,8 +802,6 @@ static void ccid3_hc_rx_exit(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - ccid3_hc_rx_set_state(sk, TFRC_RSTATE_TERM); - tfrc_rx_hist_purge(&hc->rx_hist); tfrc_lh_cleanup(&hc->rx_li_hist); } @@ -851,8 +826,7 @@ static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, return -EINVAL; rx_info.tfrcrx_x_recv = hc->rx_x_recv; rx_info.tfrcrx_rtt = hc->rx_rtt; - rx_info.tfrcrx_p = hc->rx_pinv == 0 ? ~0U : - scaled_div(1, hc->rx_pinv); + rx_info.tfrcrx_p = tfrc_invert_loss_event_rate(hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 9eb90b863abd..1a9933c29672 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -67,17 +67,11 @@ enum ccid3_options { TFRC_OPT_RECEIVE_RATE = 194, }; -struct ccid3_options_received { - u32 ccid3or_loss_event_rate; - u32 ccid3or_receive_rate; -}; - /* TFRC sender states */ enum ccid3_hc_tx_states { TFRC_SSTATE_NO_SENT = 1, TFRC_SSTATE_NO_FBACK, TFRC_SSTATE_FBACK, - TFRC_SSTATE_TERM, }; /** @@ -98,7 +92,6 @@ enum ccid3_hc_tx_states { * @tx_t_ld: Time last doubled during slow start * @tx_t_nom: Nominal send time of next packet * @tx_hist: Packet history - * @tx_options_received: Parsed set of retrieved options */ struct ccid3_hc_tx_sock { u64 tx_x; @@ -116,7 +109,6 @@ struct ccid3_hc_tx_sock { ktime_t tx_t_ld; ktime_t tx_t_nom; struct tfrc_tx_hist_entry *tx_hist; - struct ccid3_options_received tx_options_received; }; static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) @@ -130,7 +122,6 @@ static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) enum ccid3_hc_rx_states { TFRC_RSTATE_NO_DATA = 1, TFRC_RSTATE_DATA, - TFRC_RSTATE_TERM = 127, }; /** diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 01bb48e96c2e..f8ee3f549770 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -57,6 +57,7 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern u32 tfrc_invert_loss_event_rate(u32 loss_event_rate); extern int tfrc_tx_packet_history_init(void); extern void tfrc_tx_packet_history_exit(void); diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index 22ca1cf0eb55..a052a4377e26 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -687,3 +687,17 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) index = tfrc_binsearch(fvalue, 0); return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE; } + +/** + * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * When @loss_event_rate is large, there is a chance that p is truncated to 0. + * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. + */ +u32 tfrc_invert_loss_event_rate(u32 loss_event_rate) +{ + if (loss_event_rate == UINT_MAX) /* see RFC 4342, 8.5 */ + return 0; + if (unlikely(loss_event_rate == 0)) /* map 1/0 into 100% */ + return 1000000; + return max_t(u32, scaled_div(1, loss_event_rate), TFRC_SMALLEST_P); +} diff --git a/net/dccp/options.c b/net/dccp/options.c index bfda087bd90d..92718511eac5 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -96,18 +96,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, } /* - * CCID-Specific Options (from RFC 4340, sec. 10.3): - * - * Option numbers 128 through 191 are for options sent from the - * HC-Sender to the HC-Receiver; option numbers 192 through 255 - * are for options sent from the HC-Receiver to the HC-Sender. - * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). * The same applies to Ack Vectors, as these depend on the CCID. - * */ - if (dreq != NULL && (opt >= 128 || + if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; @@ -226,23 +219,15 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; - case 128 ... 191: { - const u16 idx = value - options; - + case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; - case 192 ... 255: { - const u16 idx = value - options; - + case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index fc20e687e933..714b6a80361d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -647,9 +647,11 @@ static int ipgre_rcv(struct sk_buff *skb) skb_reset_network_header(skb); ipgre_ecn_decapsulate(iph, skb); - netif_rx(skb); + if (netif_rx(skb) == NET_RX_DROP) + stats->rx_dropped++; + rcu_read_unlock(); - return(0); + return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 8de8888dc95a..babd25278106 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -377,7 +377,10 @@ static int ipip_rcv(struct sk_buff *skb) skb_tunnel_rx(skb, tunnel->dev); ipip_ecn_decapsulate(iph, skb); - netif_rx(skb); + + if (netif_rx(skb) == NET_RX_DROP) + tunnel->dev->stats.rx_dropped++; + rcu_read_unlock(); return 0; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9289cecac4de..f6d9f683543e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -725,7 +725,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb_tunnel_rx(skb, t->dev); dscp_ecn_decapsulate(t, ipv6h, skb); - netif_rx(skb); + + if (netif_rx(skb) == NET_RX_DROP) + t->dev->stats.rx_dropped++; + rcu_read_unlock(); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 66078dad7fe8..2640c9be589d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -666,7 +666,9 @@ static int pim6_rcv(struct sk_buff *skb) skb_tunnel_rx(skb, reg_dev); - netif_rx(skb); + if (netif_rx(skb) == NET_RX_DROP) + reg_dev->stats.rx_dropped++; + dev_put(reg_dev); return 0; drop: diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 6822481ff766..8a0399822230 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -564,7 +564,10 @@ static int ipip6_rcv(struct sk_buff *skb) skb_tunnel_rx(skb, tunnel->dev); ipip6_ecn_decapsulate(iph, skb); - netif_rx(skb); + + if (netif_rx(skb) == NET_RX_DROP) + tunnel->dev->stats.rx_dropped++; + rcu_read_unlock(); return 0; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ff954b3e94b6..39a21d0c61c4 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1768,7 +1768,7 @@ static const struct proto_ops pppol2tp_ops = { .ioctl = pppox_ioctl, }; -static struct pppox_proto pppol2tp_proto = { +static const struct pppox_proto pppol2tp_proto = { .create = pppol2tp_create, .ioctl = pppol2tp_ioctl }; |