From d6e640f9766e2fb9aa3853b4ff19e4d7d5d7e373 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 8 May 2012 22:20:33 +0200 Subject: can: update documentation wording error frames -> error messages As Heinz-Juergen Oertel pointed out 'CAN error frames' are a already defined term for the CAN protocol violation indication on the wire. To avoid confusion with the error messages created by CAN drivers available via CAN RAW sockets update the documentation and change the naming from 'error frames' to 'error messages' or 'error message frames'. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can.h | 8 ++++---- include/linux/can/error.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can.h b/include/linux/can.h index 9a19bcb3eeaf..17334c09bd93 100644 --- a/include/linux/can.h +++ b/include/linux/can.h @@ -21,7 +21,7 @@ /* special address description flags for the CAN_ID */ #define CAN_EFF_FLAG 0x80000000U /* EFF/SFF is set in the MSB */ #define CAN_RTR_FLAG 0x40000000U /* remote transmission request */ -#define CAN_ERR_FLAG 0x20000000U /* error frame */ +#define CAN_ERR_FLAG 0x20000000U /* error message frame */ /* valid bits in CAN ID for frame formats */ #define CAN_SFF_MASK 0x000007FFU /* standard frame format (SFF) */ @@ -32,14 +32,14 @@ * Controller Area Network Identifier structure * * bit 0-28 : CAN identifier (11/29 bit) - * bit 29 : error frame flag (0 = data frame, 1 = error frame) + * bit 29 : error message frame flag (0 = data frame, 1 = error message) * bit 30 : remote transmission request flag (1 = rtr frame) * bit 31 : frame format flag (0 = standard 11 bit, 1 = extended 29 bit) */ typedef __u32 canid_t; /* - * Controller Area Network Error Frame Mask structure + * Controller Area Network Error Message Frame Mask structure * * bit 0-28 : error class mask (see include/linux/can/error.h) * bit 29-31 : set to zero @@ -97,7 +97,7 @@ struct sockaddr_can { * & mask == can_id & mask * * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can - * filter for error frames (CAN_ERR_FLAG bit set in mask). + * filter for error message frames (CAN_ERR_FLAG bit set in mask). */ struct can_filter { canid_t can_id; diff --git a/include/linux/can/error.h b/include/linux/can/error.h index 63e855ea6b84..7b7148bded71 100644 --- a/include/linux/can/error.h +++ b/include/linux/can/error.h @@ -1,7 +1,7 @@ /* * linux/can/error.h * - * Definitions of the CAN error frame to be filtered and passed to the user. + * Definitions of the CAN error messages to be filtered and passed to the user. * * Author: Oliver Hartkopp * Copyright (c) 2002-2007 Volkswagen Group Electronic Research @@ -12,7 +12,7 @@ #ifndef CAN_ERROR_H #define CAN_ERROR_H -#define CAN_ERR_DLC 8 /* dlc for error frames */ +#define CAN_ERR_DLC 8 /* dlc for error message frames */ /* error class (mask) in can_id */ #define CAN_ERR_TX_TIMEOUT 0x00000001U /* TX timeout (by netdevice driver) */ -- cgit v1.2.3 From d594e987c6f5417cc63dd7e107a2a03a7eeee03f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Jun 2012 03:50:35 +0000 Subject: sock_diag: add SK_MEMINFO_BACKLOG Adding socket backlog len in INET_DIAG_SKMEMINFO is really useful to diagnose various TCP problems. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 1 + net/core/sock_diag.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index db4bae78bda9..6793fac5eab5 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -18,6 +18,7 @@ enum { SK_MEMINFO_FWD_ALLOC, SK_MEMINFO_WMEM_QUEUED, SK_MEMINFO_OPTMEM, + SK_MEMINFO_BACKLOG, SK_MEMINFO_VARS, }; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 5fd146720f39..0d934ce1075f 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -46,6 +46,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; return 0; -- cgit v1.2.3 From 29a6b6c060445eb46528785d51a2d8b0e6d898c4 Mon Sep 17 00:00:00 2001 From: Raffaele Recalcati Date: Sun, 3 Jun 2012 10:43:43 +0000 Subject: net/ethernet: ks8851_mll mac address configuration support added Signed-off-by: Raffaele Recalcati Signed-off-by: David S. Miller --- drivers/net/ethernet/micrel/ks8851_mll.c | 25 +++++++++++++++++------- include/linux/ks8851_mll.h | 33 ++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 7 deletions(-) create mode 100644 include/linux/ks8851_mll.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 5ffde23ac8fb..70bd329882c6 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -35,7 +35,7 @@ #include #include #include -#include +#include #define DRV_NAME "ks8851_mll" @@ -1515,6 +1515,7 @@ static int __devinit ks8851_probe(struct platform_device *pdev) struct net_device *netdev; struct ks_net *ks; u16 id, data; + struct ks8851_mll_platform_data *pdata; io_d = platform_get_resource(pdev, IORESOURCE_MEM, 0); io_c = platform_get_resource(pdev, IORESOURCE_MEM, 1); @@ -1596,17 +1597,27 @@ static int __devinit ks8851_probe(struct platform_device *pdev) ks_disable_qmu(ks); ks_setup(ks); ks_setup_int(ks); - memcpy(netdev->dev_addr, ks->mac_addr, 6); data = ks_rdreg16(ks, KS_OBCR); ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA); - /** - * If you want to use the default MAC addr, - * comment out the 2 functions below. - */ + /* overwriting the default MAC address */ + pdata = pdev->dev.platform_data; + if (!pdata) { + netdev_err(netdev, "No platform data\n"); + err = -ENODEV; + goto err_register; + } + memcpy(ks->mac_addr, pdata->mac_addr, 6); + if (!is_valid_ether_addr(ks->mac_addr)) { + /* Use random MAC address if none passed */ + random_ether_addr(ks->mac_addr); + netdev_info(netdev, "Using random mac address\n"); + } + netdev_info(netdev, "Mac address is: %pM\n", ks->mac_addr); + + memcpy(netdev->dev_addr, ks->mac_addr, 6); - random_ether_addr(netdev->dev_addr); ks_set_mac(ks, netdev->dev_addr); id = ks_rdreg16(ks, KS_CIDER); diff --git a/include/linux/ks8851_mll.h b/include/linux/ks8851_mll.h new file mode 100644 index 000000000000..e9ccfb59ed30 --- /dev/null +++ b/include/linux/ks8851_mll.h @@ -0,0 +1,33 @@ +/* + * ks8861_mll platform data struct definition + * Copyright (c) 2012 BTicino S.p.A. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _LINUX_KS8851_MLL_H +#define _LINUX_KS8851_MLL_H + +#include + +/** + * struct ks8851_mll_platform_data - Platform data of the KS8851_MLL network driver + * @macaddr: The MAC address of the device, set to all 0:s to use the on in + * the chip. + */ +struct ks8851_mll_platform_data { + u8 mac_addr[ETH_ALEN]; +}; + +#endif -- cgit v1.2.3 From fe7c580073280c15bb4eb4f82bf20dddc1a68383 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Tue, 15 May 2012 15:57:06 +0200 Subject: NFC: Add target mode protocols to the polling loop startup routine Signed-off-by: Samuel Ortiz --- drivers/nfc/pn533.c | 39 +++++++++++++++++++++++++++++---------- drivers/nfc/pn544_hci.c | 10 ++++++---- include/linux/nfc.h | 4 ++++ include/net/nfc/hci.h | 3 ++- include/net/nfc/nfc.h | 3 ++- include/net/nfc/shdlc.h | 3 ++- net/nfc/core.c | 10 +++++----- net/nfc/hci/core.c | 5 +++-- net/nfc/hci/shdlc.c | 6 ++++-- net/nfc/nci/core.c | 7 ++++--- net/nfc/netlink.c | 19 +++++++++++++++---- net/nfc/nfc.h | 2 +- 12 files changed, 77 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c index 19110f0eb15f..38a523c62132 100644 --- a/drivers/nfc/pn533.c +++ b/drivers/nfc/pn533.c @@ -1078,27 +1078,23 @@ stop_poll: return 0; } -static int pn533_start_poll(struct nfc_dev *nfc_dev, u32 protocols) +static int pn533_init_target(struct nfc_dev *nfc_dev, u32 protocols) +{ + return 0; +} + +static int pn533_start_im_poll(struct nfc_dev *nfc_dev, u32 protocols) { struct pn533 *dev = nfc_get_drvdata(nfc_dev); struct pn533_poll_modulations *start_mod; int rc; - nfc_dev_dbg(&dev->interface->dev, "%s - protocols=0x%x", __func__, - protocols); - if (dev->poll_mod_count) { nfc_dev_err(&dev->interface->dev, "Polling operation already" " active"); return -EBUSY; } - if (dev->tgt_active_prot) { - nfc_dev_err(&dev->interface->dev, "Cannot poll with a target" - " already activated"); - return -EBUSY; - } - pn533_poll_create_mod_list(dev, protocols); if (!dev->poll_mod_count) { @@ -1135,6 +1131,29 @@ error: return rc; } +static int pn533_start_poll(struct nfc_dev *nfc_dev, + u32 im_protocols, u32 tm_protocols) +{ + struct pn533 *dev = nfc_get_drvdata(nfc_dev); + + nfc_dev_dbg(&dev->interface->dev, + "%s: im protocols 0x%x tm protocols 0x%x", + __func__, im_protocols, tm_protocols); + + if (dev->tgt_active_prot) { + nfc_dev_err(&dev->interface->dev, + "Cannot poll with a target already activated"); + return -EBUSY; + } + + if (!tm_protocols) + return pn533_start_im_poll(nfc_dev, im_protocols); + else if (!im_protocols) + return pn533_init_target(nfc_dev, tm_protocols); + else + return -EINVAL; +} + static void pn533_stop_poll(struct nfc_dev *nfc_dev) { struct pn533 *dev = nfc_get_drvdata(nfc_dev); diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c index 281f18c2fb82..457eac35dc74 100644 --- a/drivers/nfc/pn544_hci.c +++ b/drivers/nfc/pn544_hci.c @@ -576,7 +576,8 @@ static int pn544_hci_xmit(struct nfc_shdlc *shdlc, struct sk_buff *skb) return pn544_hci_i2c_write(client, skb->data, skb->len); } -static int pn544_hci_start_poll(struct nfc_shdlc *shdlc, u32 protocols) +static int pn544_hci_start_poll(struct nfc_shdlc *shdlc, + u32 im_protocols, u32 tm_protocols) { struct nfc_hci_dev *hdev = nfc_shdlc_get_hci_dev(shdlc); u8 phases = 0; @@ -584,7 +585,8 @@ static int pn544_hci_start_poll(struct nfc_shdlc *shdlc, u32 protocols) u8 duration[2]; u8 activated; - pr_info(DRIVER_DESC ": %s protocols = %d\n", __func__, protocols); + pr_info(DRIVER_DESC ": %s protocols 0x%x 0x%x\n", + __func__, im_protocols, tm_protocols); r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, NFC_HCI_EVT_END_OPERATION, NULL, 0); @@ -604,10 +606,10 @@ static int pn544_hci_start_poll(struct nfc_shdlc *shdlc, u32 protocols) if (r < 0) return r; - if (protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_MIFARE_MASK | + if (im_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_MIFARE_MASK | NFC_PROTO_JEWEL_MASK)) phases |= 1; /* Type A */ - if (protocols & NFC_PROTO_FELICA_MASK) { + if (im_protocols & NFC_PROTO_FELICA_MASK) { phases |= (1 << 2); /* Type F 212 */ phases |= (1 << 3); /* Type F 424 */ } diff --git a/include/linux/nfc.h b/include/linux/nfc.h index 0ae9b5857c83..548715881fb0 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -94,6 +94,8 @@ enum nfc_commands { * @NFC_ATTR_TARGET_SENSF_RES: NFC-F targets extra information, max 18 bytes * @NFC_ATTR_COMM_MODE: Passive or active mode * @NFC_ATTR_RF_MODE: Initiator or target + * @NFC_ATTR_IM_PROTOCOLS: Initiator mode protocols to poll for + * @NFC_ATTR_TM_PROTOCOLS: Target mode protocols to listen for */ enum nfc_attrs { NFC_ATTR_UNSPEC, @@ -109,6 +111,8 @@ enum nfc_attrs { NFC_ATTR_COMM_MODE, NFC_ATTR_RF_MODE, NFC_ATTR_DEVICE_POWERED, + NFC_ATTR_IM_PROTOCOLS, + NFC_ATTR_TM_PROTOCOLS, /* private: internal use only */ __NFC_ATTR_AFTER_LAST }; diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h index 4467c9460857..e30e6a869714 100644 --- a/include/net/nfc/hci.h +++ b/include/net/nfc/hci.h @@ -31,7 +31,8 @@ struct nfc_hci_ops { void (*close) (struct nfc_hci_dev *hdev); int (*hci_ready) (struct nfc_hci_dev *hdev); int (*xmit) (struct nfc_hci_dev *hdev, struct sk_buff *skb); - int (*start_poll) (struct nfc_hci_dev *hdev, u32 protocols); + int (*start_poll) (struct nfc_hci_dev *hdev, + u32 im_protocols, u32 tm_protocols); int (*target_from_gate) (struct nfc_hci_dev *hdev, u8 gate, struct nfc_target *target); int (*complete_target_discovered) (struct nfc_hci_dev *hdev, u8 gate, diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3116f923f607..97aa0e81aa83 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -53,7 +53,8 @@ struct nfc_target; struct nfc_ops { int (*dev_up)(struct nfc_dev *dev); int (*dev_down)(struct nfc_dev *dev); - int (*start_poll)(struct nfc_dev *dev, u32 protocols); + int (*start_poll)(struct nfc_dev *dev, + u32 im_protocols, u32 tm_protocols); void (*stop_poll)(struct nfc_dev *dev); int (*dep_link_up)(struct nfc_dev *dev, struct nfc_target *target, u8 comm_mode, u8 *gb, size_t gb_len); diff --git a/include/net/nfc/shdlc.h b/include/net/nfc/shdlc.h index ab06afd462da..35e930d2f638 100644 --- a/include/net/nfc/shdlc.h +++ b/include/net/nfc/shdlc.h @@ -27,7 +27,8 @@ struct nfc_shdlc_ops { void (*close) (struct nfc_shdlc *shdlc); int (*hci_ready) (struct nfc_shdlc *shdlc); int (*xmit) (struct nfc_shdlc *shdlc, struct sk_buff *skb); - int (*start_poll) (struct nfc_shdlc *shdlc, u32 protocols); + int (*start_poll) (struct nfc_shdlc *shdlc, + u32 im_protocols, u32 tm_protocols); int (*target_from_gate) (struct nfc_shdlc *shdlc, u8 gate, struct nfc_target *target); int (*complete_target_discovered) (struct nfc_shdlc *shdlc, u8 gate, diff --git a/net/nfc/core.c b/net/nfc/core.c index f5a43f701a9e..c83717bfcb8a 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -121,14 +121,14 @@ error: * The device remains polling for targets until a target is found or * the nfc_stop_poll function is called. */ -int nfc_start_poll(struct nfc_dev *dev, u32 protocols) +int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) { int rc; - pr_debug("dev_name=%s protocols=0x%x\n", - dev_name(&dev->dev), protocols); + pr_debug("dev_name %s initiator protocols 0x%x target protocols 0x%x\n", + dev_name(&dev->dev), im_protocols, tm_protocols); - if (!protocols) + if (!im_protocols && !tm_protocols) return -EINVAL; device_lock(&dev->dev); @@ -143,7 +143,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 protocols) goto error; } - rc = dev->ops->start_poll(dev, protocols); + rc = dev->ops->start_poll(dev, im_protocols, tm_protocols); if (!rc) dev->polling = true; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index e1a640d2b588..281f3a3bec00 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -481,12 +481,13 @@ static int hci_dev_down(struct nfc_dev *nfc_dev) return 0; } -static int hci_start_poll(struct nfc_dev *nfc_dev, u32 protocols) +static int hci_start_poll(struct nfc_dev *nfc_dev, + u32 im_protocols, u32 tm_protocols) { struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); if (hdev->ops->start_poll) - return hdev->ops->start_poll(hdev, protocols); + return hdev->ops->start_poll(hdev, im_protocols, tm_protocols); else return nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, NFC_HCI_EVT_READER_REQUESTED, NULL, 0); diff --git a/net/nfc/hci/shdlc.c b/net/nfc/hci/shdlc.c index 5665dc6d893a..6b836e6242b7 100644 --- a/net/nfc/hci/shdlc.c +++ b/net/nfc/hci/shdlc.c @@ -765,14 +765,16 @@ static int nfc_shdlc_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb) return 0; } -static int nfc_shdlc_start_poll(struct nfc_hci_dev *hdev, u32 protocols) +static int nfc_shdlc_start_poll(struct nfc_hci_dev *hdev, + u32 im_protocols, u32 tm_protocols) { struct nfc_shdlc *shdlc = nfc_hci_get_clientdata(hdev); pr_debug("\n"); if (shdlc->ops->start_poll) - return shdlc->ops->start_poll(shdlc, protocols); + return shdlc->ops->start_poll(shdlc, + im_protocols, tm_protocols); return 0; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index d560e6f13072..0f718982f808 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -387,7 +387,8 @@ static int nci_dev_down(struct nfc_dev *nfc_dev) return nci_close_device(ndev); } -static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 protocols) +static int nci_start_poll(struct nfc_dev *nfc_dev, + __u32 im_protocols, __u32 tm_protocols) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; @@ -413,11 +414,11 @@ static int nci_start_poll(struct nfc_dev *nfc_dev, __u32 protocols) return -EBUSY; } - rc = nci_request(ndev, nci_rf_discover_req, protocols, + rc = nci_request(ndev, nci_rf_discover_req, im_protocols, msecs_to_jiffies(NCI_RF_DISC_TIMEOUT)); if (!rc) - ndev->poll_prots = protocols; + ndev->poll_prots = im_protocols; return rc; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 581d419083aa..a18fd56798fc 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -49,6 +49,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, + [NFC_ATTR_IM_PROTOCOLS] = { .type = NLA_U32 }, + [NFC_ATTR_TM_PROTOCOLS] = { .type = NLA_U32 }, }; static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, @@ -519,16 +521,25 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) struct nfc_dev *dev; int rc; u32 idx; - u32 protocols; + u32 im_protocols = 0, tm_protocols = 0; pr_debug("Poll start\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || - !info->attrs[NFC_ATTR_PROTOCOLS]) + ((!info->attrs[NFC_ATTR_IM_PROTOCOLS] && + !info->attrs[NFC_ATTR_PROTOCOLS]) && + !info->attrs[NFC_ATTR_TM_PROTOCOLS])) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); - protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); + + if (info->attrs[NFC_ATTR_TM_PROTOCOLS]) + tm_protocols = nla_get_u32(info->attrs[NFC_ATTR_TM_PROTOCOLS]); + else if (info->attrs[NFC_ATTR_PROTOCOLS]) + tm_protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); + + if (info->attrs[NFC_ATTR_IM_PROTOCOLS]) + im_protocols = nla_get_u32(info->attrs[NFC_ATTR_IM_PROTOCOLS]); dev = nfc_get_device(idx); if (!dev) @@ -536,7 +547,7 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) mutex_lock(&dev->genl_data.genl_data_mutex); - rc = nfc_start_poll(dev, protocols); + rc = nfc_start_poll(dev, im_protocols, tm_protocols); if (!rc) dev->genl_data.poll_req_pid = info->snd_pid; diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 3dd4232ae664..7d9708f2a66c 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -158,7 +158,7 @@ int nfc_dev_up(struct nfc_dev *dev); int nfc_dev_down(struct nfc_dev *dev); -int nfc_start_poll(struct nfc_dev *dev, u32 protocols); +int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); int nfc_stop_poll(struct nfc_dev *dev); -- cgit v1.2.3 From fc40a8c1a06ab7db45da790693dd9802612a055c Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Fri, 1 Jun 2012 13:21:13 +0200 Subject: NFC: Add target mode activation netlink event Userspace gets a netlink event upon target mode activation. The LLCP layer is also signaled when we get an ATR_REQ in order to get the remote general bytes. Signed-off-by: Samuel Ortiz --- drivers/nfc/pn533.c | 27 ++++++++++++++++++++-- include/linux/nfc.h | 7 ++++++ include/net/nfc/nfc.h | 4 ++++ net/nfc/core.c | 35 +++++++++++++++++++++++++++++ net/nfc/netlink.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++ net/nfc/nfc.h | 3 +++ 6 files changed, 136 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c index 605a08a62e45..c6b9bc5ac6e6 100644 --- a/drivers/nfc/pn533.c +++ b/drivers/nfc/pn533.c @@ -260,6 +260,10 @@ struct pn533_cmd_jump_dep_response { #define PN533_INIT_TARGET_PASSIVE 0x1 #define PN533_INIT_TARGET_DEP 0x2 +#define PN533_INIT_TARGET_RESP_FRAME_MASK 0x3 +#define PN533_INIT_TARGET_RESP_ACTIVE 0x1 +#define PN533_INIT_TARGET_RESP_DEP 0x4 + struct pn533_cmd_init_target { u8 mode; u8 mifare[6]; @@ -1128,10 +1132,13 @@ static int pn533_init_target_frame(struct pn533_frame *frame, return 0; } +#define ATR_REQ_GB_OFFSET 17 static int pn533_init_target_complete(struct pn533 *dev, void *arg, u8 *params, int params_len) { struct pn533_cmd_init_target_response *resp; + u8 frame, comm_mode = NFC_COMM_PASSIVE, *gb; + size_t gb_len; nfc_dev_dbg(&dev->interface->dev, "%s", __func__); @@ -1143,11 +1150,27 @@ static int pn533_init_target_complete(struct pn533 *dev, void *arg, return params_len; } + if (params_len < ATR_REQ_GB_OFFSET + 1) + return -EINVAL; + resp = (struct pn533_cmd_init_target_response *) params; - nfc_dev_dbg(&dev->interface->dev, "Target mode 0x%x\n", resp->mode); + nfc_dev_dbg(&dev->interface->dev, "Target mode 0x%x param len %d\n", + resp->mode, params_len); - return 0; + frame = resp->mode & PN533_INIT_TARGET_RESP_FRAME_MASK; + if (frame == PN533_INIT_TARGET_RESP_ACTIVE) + comm_mode = NFC_COMM_ACTIVE; + + /* Again, only DEP */ + if ((resp->mode & PN533_INIT_TARGET_RESP_DEP) == 0) + return -EOPNOTSUPP; + + gb = resp->cmd + ATR_REQ_GB_OFFSET; + gb_len = params_len - (ATR_REQ_GB_OFFSET + 1); + + return nfc_tm_activated(dev->nfc_dev, NFC_PROTO_NFC_DEP_MASK, + comm_mode, gb, gb_len); } static int pn533_init_target(struct nfc_dev *nfc_dev, u32 protocols) diff --git a/include/linux/nfc.h b/include/linux/nfc.h index 548715881fb0..d124e9273fcb 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -56,6 +56,10 @@ * %NFC_ATTR_PROTOCOLS) * @NFC_EVENT_DEVICE_REMOVED: event emitted when a device is removed * (it sends %NFC_ATTR_DEVICE_INDEX) + * @NFC_EVENT_TM_ACTIVATED: event emitted when the adapter is activated in + * target mode. + * @NFC_EVENT_DEVICE_DEACTIVATED: event emitted when the adapter is deactivated + * from target mode. */ enum nfc_commands { NFC_CMD_UNSPEC, @@ -71,6 +75,8 @@ enum nfc_commands { NFC_EVENT_DEVICE_ADDED, NFC_EVENT_DEVICE_REMOVED, NFC_EVENT_TARGET_LOST, + NFC_EVENT_TM_ACTIVATED, + NFC_EVENT_TM_DEACTIVATED, /* private: internal use only */ __NFC_CMD_AFTER_LAST }; @@ -122,6 +128,7 @@ enum nfc_attrs { #define NFC_NFCID1_MAXSIZE 10 #define NFC_SENSB_RES_MAXSIZE 12 #define NFC_SENSF_RES_MAXSIZE 18 +#define NFC_GB_MAXSIZE 48 /* NFC protocols */ #define NFC_PROTO_JEWEL 1 diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 97aa0e81aa83..41573b4bd78a 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -198,4 +198,8 @@ int nfc_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); +int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, + u8 *gb, size_t gb_len); +int nfc_tm_deactivated(struct nfc_dev *dev); + #endif /* __NET_NFC_H */ diff --git a/net/nfc/core.c b/net/nfc/core.c index c83717bfcb8a..17f147430b7c 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -455,6 +455,41 @@ u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len) } EXPORT_SYMBOL(nfc_get_local_general_bytes); +int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, + u8 *gb, size_t gb_len) +{ + int rc; + + device_lock(&dev->dev); + + dev->polling = false; + + if (gb != NULL) { + rc = nfc_set_remote_general_bytes(dev, gb, gb_len); + if (rc < 0) + goto out; + } + + if (protocol == NFC_PROTO_NFC_DEP_MASK) + nfc_dep_link_is_up(dev, 0, comm_mode, NFC_RF_TARGET); + + rc = nfc_genl_tm_activated(dev, protocol); + +out: + device_unlock(&dev->dev); + + return rc; +} +EXPORT_SYMBOL(nfc_tm_activated); + +int nfc_tm_deactivated(struct nfc_dev *dev) +{ + dev->dep_link_up = false; + + return nfc_genl_tm_deactivated(dev); +} +EXPORT_SYMBOL(nfc_tm_deactivated); + /** * nfc_alloc_send_skb - allocate a skb for data exchange responses * diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index a18fd56798fc..21eaa9b5c6bf 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -221,6 +221,68 @@ free_msg: return -EMSGSIZE; } +int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TM_ACTIVATED); + if (!hdr) + goto free_msg; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + if (nla_put_u32(msg, NFC_ATTR_TM_PROTOCOLS, protocol)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int nfc_genl_tm_deactivated(struct nfc_dev *dev) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TM_DEACTIVATED); + if (!hdr) + goto free_msg; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + int nfc_genl_device_added(struct nfc_dev *dev) { struct sk_buff *msg; diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 7d9708f2a66c..cd9fcbe57464 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -128,6 +128,9 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_genl_dep_link_down_event(struct nfc_dev *dev); +int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol); +int nfc_genl_tm_deactivated(struct nfc_dev *dev); + struct nfc_dev *nfc_get_device(unsigned int idx); static inline void nfc_put_device(struct nfc_dev *dev) -- cgit v1.2.3 From f212ad5e993e7efb996fc8ce94a5de8f0bd06d41 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Thu, 31 May 2012 00:02:26 +0200 Subject: NFC: Set the NFC device RF mode appropriately Signed-off-by: Samuel Ortiz --- include/linux/nfc.h | 1 + include/net/nfc/nfc.h | 2 +- net/nfc/core.c | 14 ++++++++++---- 3 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfc.h b/include/linux/nfc.h index d124e9273fcb..f4e6dd915b1c 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -146,6 +146,7 @@ enum nfc_attrs { /* NFC RF modes */ #define NFC_RF_INITIATOR 0 #define NFC_RF_TARGET 1 +#define NFC_RF_NONE 2 /* NFC protocols masks used in bitsets */ #define NFC_PROTO_JEWEL_MASK (1 << NFC_PROTO_JEWEL) diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 41573b4bd78a..a6a7b49a3e2d 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -100,10 +100,10 @@ struct nfc_dev { int targets_generation; struct device dev; bool dev_up; + u8 rf_mode; bool polling; struct nfc_target *active_target; bool dep_link_up; - u32 dep_rf_mode; struct nfc_genl_data genl_data; u32 supported_protocols; diff --git a/net/nfc/core.c b/net/nfc/core.c index 17f147430b7c..722a0c76c669 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -144,8 +144,10 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) } rc = dev->ops->start_poll(dev, im_protocols, tm_protocols); - if (!rc) + if (!rc) { dev->polling = true; + dev->rf_mode = NFC_RF_NONE; + } error: device_unlock(&dev->dev); @@ -235,8 +237,10 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) } rc = dev->ops->dep_link_up(dev, target, comm_mode, gb, gb_len); - if (!rc) + if (!rc) { dev->active_target = target; + dev->rf_mode = NFC_RF_INITIATOR; + } error: device_unlock(&dev->dev); @@ -264,7 +268,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) goto error; } - if (dev->dep_rf_mode == NFC_RF_TARGET) { + if (dev->rf_mode == NFC_RF_TARGET) { rc = -EOPNOTSUPP; goto error; } @@ -286,7 +290,6 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { dev->dep_link_up = true; - dev->dep_rf_mode = rf_mode; nfc_llcp_mac_is_up(dev, target_idx, comm_mode, rf_mode); @@ -330,6 +333,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) rc = dev->ops->activate_target(dev, target, protocol); if (!rc) { dev->active_target = target; + dev->rf_mode = NFC_RF_INITIATOR; if (dev->ops->check_presence) mod_timer(&dev->check_pres_timer, jiffies + @@ -470,6 +474,8 @@ int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, goto out; } + dev->rf_mode = NFC_RF_TARGET; + if (protocol == NFC_PROTO_NFC_DEP_MASK) nfc_dep_link_is_up(dev, 0, comm_mode, NFC_RF_TARGET); -- cgit v1.2.3 From 5dad021dee7c3c601a9e17d86139e586c05c2ee2 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Tue, 15 May 2012 14:50:58 +0300 Subject: nl80211: add new rssi event to indicate beacon loss Tell userspace about beacon loss event. This event doesn't replace the deauth/disassoc that might come if the AP is not available. The driver can send this event in order to hint userspace what might follow (which in turn can use it as roaming trigger). Signed-off-by: Eliad Peller Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index a6959f72745e..6930dddad18a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -2534,10 +2534,14 @@ enum nl80211_attr_cqm { * configured threshold * @NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH: The RSSI is higher than the * configured threshold + * @NL80211_CQM_RSSI_BEACON_LOSS_EVENT: The device experienced beacon loss. + * (Note that deauth/disassoc will still follow if the AP is not + * available. This event might get used as roaming event, etc.) */ enum nl80211_cqm_rssi_threshold_event { NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW, NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH, + NL80211_CQM_RSSI_BEACON_LOSS_EVENT, }; -- cgit v1.2.3 From aa430da41019c1694f6a8e3b8bef1d12ed52b0ad Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 16 May 2012 23:50:18 +0200 Subject: cfg80211: provide channel to start_ap function Instead of setting the channel first and then starting the AP, let cfg80211 store the channel and provide it as one of the AP settings. This means that now you have to set the channel before you can start an AP interface, but since hostapd/wpa_supplicant always do that we're OK with this change. Alternatively, it's now possible to give the channel as an attribute to the start-ap nl80211 command, overriding any preset channel. Cc: Kalle Valo Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 36 ++------------------ drivers/net/wireless/ath/ath6kl/core.h | 3 -- drivers/net/wireless/ath/ath6kl/main.c | 1 - include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 12 ++++++- net/mac80211/cfg.c | 5 +++ net/wireless/nl80211.c | 53 ++++++++++++++++++++++++++++-- 7 files changed, 72 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index b869a358ce43..f27e9732951d 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -2585,35 +2585,6 @@ static int ath6kl_set_ies(struct ath6kl_vif *vif, return 0; } -static int ath6kl_set_channel(struct wiphy *wiphy, struct net_device *dev, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) -{ - struct ath6kl_vif *vif; - - /* - * 'dev' could be NULL if a channel change is required for the hardware - * device itself, instead of a particular VIF. - * - * FIXME: To be handled properly when monitor mode is supported. - */ - if (!dev) - return -EBUSY; - - vif = netdev_priv(dev); - - if (!ath6kl_cfg80211_ready(vif)) - return -EIO; - - ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: center_freq=%u hw_value=%u\n", - __func__, chan->center_freq, chan->hw_value); - vif->next_chan = chan->center_freq; - vif->next_ch_type = channel_type; - vif->next_ch_band = chan->band; - - return 0; -} - static int ath6kl_get_rsn_capab(struct cfg80211_beacon_data *beacon, u8 *rsn_capab) { @@ -2791,7 +2762,7 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev, p.ssid_len = vif->ssid_len; memcpy(p.ssid, vif->ssid, vif->ssid_len); p.dot11_auth_mode = vif->dot11_auth_mode; - p.ch = cpu_to_le16(vif->next_chan); + p.ch = cpu_to_le16(info->channel->center_freq); /* Enable uAPSD support by default */ res = ath6kl_wmi_ap_set_apsd(ar->wmi, vif->fw_vif_idx, true); @@ -2815,8 +2786,8 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev, return res; } - if (ath6kl_set_htcap(vif, vif->next_ch_band, - vif->next_ch_type != NL80211_CHAN_NO_HT)) + if (ath6kl_set_htcap(vif, info->channel->band, + info->channel_type != NL80211_CHAN_NO_HT)) return -EIO; /* @@ -3271,7 +3242,6 @@ static struct cfg80211_ops ath6kl_cfg80211_ops = { .suspend = __ath6kl_cfg80211_suspend, .resume = __ath6kl_cfg80211_resume, #endif - .set_channel = ath6kl_set_channel, .start_ap = ath6kl_start_ap, .change_beacon = ath6kl_change_beacon, .stop_ap = ath6kl_stop_ap, diff --git a/drivers/net/wireless/ath/ath6kl/core.h b/drivers/net/wireless/ath/ath6kl/core.h index 4d9c6f142698..8443b2a4133e 100644 --- a/drivers/net/wireless/ath/ath6kl/core.h +++ b/drivers/net/wireless/ath/ath6kl/core.h @@ -553,9 +553,6 @@ struct ath6kl_vif { u32 last_cancel_roc_id; u32 send_action_id; bool probe_req_report; - u16 next_chan; - enum nl80211_channel_type next_ch_type; - enum ieee80211_band next_ch_band; u16 assoc_bss_beacon_int; u16 listen_intvl_t; u16 bmiss_time_t; diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c index e5524470529c..b836f2795114 100644 --- a/drivers/net/wireless/ath/ath6kl/main.c +++ b/drivers/net/wireless/ath/ath6kl/main.c @@ -598,7 +598,6 @@ static int ath6kl_commit_ch_switch(struct ath6kl_vif *vif, u16 channel) struct ath6kl *ar = vif->ar; - vif->next_chan = channel; vif->profile.ch = cpu_to_le16(channel); switch (vif->nw_type) { diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 6930dddad18a..85e5037a218d 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -170,6 +170,8 @@ * %NL80211_ATTR_CIPHER_GROUP, %NL80211_ATTR_WPA_VERSIONS, * %NL80211_ATTR_AKM_SUITES, %NL80211_ATTR_PRIVACY, * %NL80211_ATTR_AUTH_TYPE and %NL80211_ATTR_INACTIVITY_TIMEOUT. + * The channel to use can be set on the interface or be given using the + * %NL80211_ATTR_WIPHY_FREQ and %NL80211_ATTR_WIPHY_CHANNEL_TYPE attrs. * @NL80211_CMD_NEW_BEACON: old alias for %NL80211_CMD_START_AP * @NL80211_CMD_STOP_AP: Stop AP operation on the given interface * @NL80211_CMD_DEL_BEACON: old alias for %NL80211_CMD_STOP_AP diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a8496f4ff5f1..a54fb895f613 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -404,6 +404,8 @@ struct cfg80211_beacon_data { * * Used to configure an AP interface. * + * @channel: the channel to start the AP on + * @channel_type: the channel type to use * @beacon: beacon data * @beacon_interval: beacon interval * @dtim_period: DTIM period @@ -417,6 +419,9 @@ struct cfg80211_beacon_data { * @inactivity_timeout: time in seconds to determine station's inactivity. */ struct cfg80211_ap_settings { + struct ieee80211_channel *channel; + enum nl80211_channel_type channel_type; + struct cfg80211_beacon_data beacon; int beacon_interval, dtim_period; @@ -2263,7 +2268,10 @@ struct cfg80211_cached_keys; * @netdev: (private) Used to reference back to the netdev * @current_bss: (private) Used by the internal configuration code * @channel: (private) Used by the internal configuration code to track - * user-set AP, monitor and WDS channels for wireless extensions + * the user-set AP, monitor and WDS channel + * @preset_chan: (private) Used by the internal configuration code to + * track the channel to be used for AP later + * @preset_chantype: (private) the corresponding channel type * @bssid: (private) Used by the internal configuration code * @ssid: (private) Used by the internal configuration code * @ssid_len: (private) Used by the internal configuration code @@ -2314,6 +2322,8 @@ struct wireless_dev { struct cfg80211_internal_bss *current_bss; /* associated / joined */ struct ieee80211_channel *channel; + struct ieee80211_channel *preset_chan; + enum nl80211_channel_type preset_chantype; bool ps; int ps_timeout; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 9aab849fd6cf..8e9d525c4653 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -823,6 +823,11 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) return -EALREADY; + err = ieee80211_set_channel(wiphy, dev, params->channel, + params->channel_type); + if (err) + return err; + /* * Apply control port protocol, this allows us to * not encrypt dynamic WEP control frames. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 206465dc0cab..74f4a8f93935 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -921,7 +921,11 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS)) goto nla_put_failure; } - CMD(set_channel, SET_CHANNEL); + if (dev->ops->set_channel || dev->ops->start_ap) { + i++; + if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL)) + goto nla_put_failure; + } CMD(set_wds_peer, SET_WDS_PEER); if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) { CMD(tdls_mgmt, TDLS_MGMT); @@ -1170,6 +1174,9 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) * Monitors are special as they are normally slaved to * whatever else is going on, so they behave as though * you tried setting the wiphy channel itself. + * + * For AP/GO modes, it's only for compatibility, you can + * also give the channel to the start-AP command. */ return !wdev || wdev->iftype == NL80211_IFTYPE_AP || @@ -1204,6 +1211,7 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct genl_info *info) { + struct ieee80211_channel *channel; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; u32 freq; int result; @@ -1221,7 +1229,25 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); mutex_lock(&rdev->devlist_mtx); - if (wdev) { + if (wdev) switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + if (wdev->beacon_interval) { + result = -EBUSY; + break; + } + channel = rdev_freq_to_chan(rdev, freq, channel_type); + if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy, + channel, + channel_type)) { + result = -EINVAL; + break; + } + wdev->preset_chan = channel; + wdev->preset_chantype = channel_type; + result = 0; + break; + default: wdev_lock(wdev); result = cfg80211_set_freq(rdev, wdev, freq, channel_type); wdev_unlock(wdev); @@ -2299,6 +2325,29 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]); } + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && + !nl80211_valid_channel_type(info, &channel_type)) + return -EINVAL; + + params.channel = rdev_freq_to_chan(rdev, + nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), + channel_type); + if (!params.channel) + return -EINVAL; + params.channel_type = channel_type; + } else if (wdev->preset_chan) { + params.channel = wdev->preset_chan; + params.channel_type = wdev->preset_chantype; + } else + return -EINVAL; + + if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, params.channel, + params.channel_type)) + return -EINVAL; + err = rdev->ops->start_ap(&rdev->wiphy, dev, ¶ms); if (!err) wdev->beacon_interval = params.beacon_interval; -- cgit v1.2.3 From ccaf8c32d5ed08bfb4c45492f8f1c145fd45f4e8 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Thu, 31 May 2012 22:38:22 +0200 Subject: ssb: recognize ARM Cortex M3 I found this core on a BCM4322, a PCI card in the Linksys WRT610N V1. This core is not used by the driver, this patch just makes ssb show the correct name. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/ssb/scan.c | 2 ++ include/linux/ssb/ssb.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c index 266c7c5c86dc..ab4627cf1114 100644 --- a/drivers/ssb/scan.c +++ b/drivers/ssb/scan.c @@ -90,6 +90,8 @@ const char *ssb_core_name(u16 coreid) return "ARM 1176"; case SSB_DEV_ARM_7TDMI: return "ARM 7TDMI"; + case SSB_DEV_ARM_CM3: + return "ARM Cortex M3"; } return "UNKNOWN"; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index bc14bd738ade..bb674c02f306 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -243,6 +243,7 @@ struct ssb_bus_ops { #define SSB_DEV_MINI_MACPHY 0x823 #define SSB_DEV_ARM_1176 0x824 #define SSB_DEV_ARM_7TDMI 0x825 +#define SSB_DEV_ARM_CM3 0x82A /* Vendor-ID values */ #define SSB_VENDOR_BROADCOM 0x4243 -- cgit v1.2.3 From ebf348fcd088e3ffc6e76f6f349e27d30604865b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Jun 2012 12:50:54 +0200 Subject: cfg80211: validate remain-on-channel time better The remain-on-channel time validation shouldn't depend on the value of HZ, as it does now with the check against jiffies, since then you might use a value that works on one system but not on another. Fix it by checking against a minimum that's fixed. Also add validation of the wait duration for a management frame TX since this also translates into remain-on-channel internally. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ net/wireless/nl80211.c | 23 ++++++++++++++++------- 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 85e5037a218d..970afdf5a605 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1522,6 +1522,8 @@ enum nl80211_attrs { #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 +#define NL80211_MIN_REMAIN_ON_CHANNEL_TIME 10 + /** * enum nl80211_iftype - (virtual) interface types * diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5e29bd38e7df..7ae54b82291f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5545,18 +5545,18 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, duration = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + if (!rdev->ops->remain_on_channel || + !(rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)) + return -EOPNOTSUPP; + /* - * We should be on that channel for at least one jiffie, - * and more than 5 seconds seems excessive. + * We should be on that channel for at least a minimum amount of + * time (10ms) but no longer than the driver supports. */ - if (!duration || !msecs_to_jiffies(duration) || + if (duration < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || duration > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; - if (!rdev->ops->remain_on_channel || - !(rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)) - return -EOPNOTSUPP; - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && !nl80211_valid_channel_type(info, &channel_type)) return -EINVAL; @@ -5827,6 +5827,15 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (!(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) return -EINVAL; wait = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + + /* + * We should wait on the channel for at least a minimum amount + * of time (10ms) but no longer than the driver supports. + */ + if (wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || + wait > rdev->wiphy.max_remain_on_channel_duration) + return -EINVAL; + } if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { -- cgit v1.2.3 From 7a74c1a18d1f03462f9f766ee8213535ce131b0f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 19 May 2012 04:39:00 +0000 Subject: netfilter: remove include/linux/netfilter_ipv4/ipt_addrtype.h It was scheduled to be removed. Acked-by: Florian Westphal Signed-off-by: Cong Wang Signed-off-by: Pablo Neira Ayuso --- Documentation/feature-removal-schedule.txt | 8 -------- include/linux/netfilter_ipv4/Kbuild | 1 - include/linux/netfilter_ipv4/ipt_addrtype.h | 27 --------------------------- 3 files changed, 36 deletions(-) delete mode 100644 include/linux/netfilter_ipv4/ipt_addrtype.h (limited to 'include/linux') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 56000b33340b..08e7e71b266c 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -421,14 +421,6 @@ Files: net/netfilter/xt_connlimit.c ---------------------------- -What: ipt_addrtype match include file -When: 2012 -Why: superseded by xt_addrtype -Who: Florian Westphal -Files: include/linux/netfilter_ipv4/ipt_addrtype.h - ----------------------------- - What: i2c_driver.attach_adapter i2c_driver.detach_adapter When: September 2011 diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild index c61b8fb1a9ef..8ba0c5b72ea9 100644 --- a/include/linux/netfilter_ipv4/Kbuild +++ b/include/linux/netfilter_ipv4/Kbuild @@ -5,7 +5,6 @@ header-y += ipt_LOG.h header-y += ipt_REJECT.h header-y += ipt_TTL.h header-y += ipt_ULOG.h -header-y += ipt_addrtype.h header-y += ipt_ah.h header-y += ipt_ecn.h header-y += ipt_ttl.h diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h deleted file mode 100644 index 0da42237c8da..000000000000 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef _IPT_ADDRTYPE_H -#define _IPT_ADDRTYPE_H - -#include - -enum { - IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, - IPT_ADDRTYPE_INVERT_DEST = 0x0002, - IPT_ADDRTYPE_LIMIT_IFACE_IN = 0x0004, - IPT_ADDRTYPE_LIMIT_IFACE_OUT = 0x0008, -}; - -struct ipt_addrtype_info_v1 { - __u16 source; /* source-type mask */ - __u16 dest; /* dest-type mask */ - __u32 flags; -}; - -/* revision 0 */ -struct ipt_addrtype_info { - __u16 source; /* source-type mask */ - __u16 dest; /* dest-type mask */ - __u32 invert_source; - __u32 invert_dest; -}; - -#endif -- cgit v1.2.3 From 68c07cb6d8aa05daf38ab47d5bb674d81a2066fb Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 19 May 2012 04:39:01 +0000 Subject: netfilter: xt_connlimit: remove revision 0 It was scheduled to be removed. Cc: Jan Engelhardt Signed-off-by: Cong Wang Signed-off-by: Pablo Neira Ayuso --- Documentation/feature-removal-schedule.txt | 7 ------ include/linux/netfilter/xt_connlimit.h | 9 ++------ net/netfilter/xt_connlimit.c | 35 ++++++++++-------------------- 3 files changed, 13 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 08e7e71b266c..24ac00f4ae4b 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -414,13 +414,6 @@ Who: Jean Delvare ---------------------------- -What: xt_connlimit rev 0 -When: 2012 -Who: Jan Engelhardt -Files: net/netfilter/xt_connlimit.c - ----------------------------- - What: i2c_driver.attach_adapter i2c_driver.detach_adapter When: September 2011 diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index d1366f05d1b2..f1656096121e 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -22,13 +22,8 @@ struct xt_connlimit_info { #endif }; unsigned int limit; - union { - /* revision 0 */ - unsigned int inverse; - - /* revision 1 */ - __u32 flags; - }; + /* revision 1 */ + __u32 flags; /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index c6d5a83450c9..70b5591a2586 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -274,38 +274,25 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) kfree(info->data); } -static struct xt_match connlimit_mt_reg[] __read_mostly = { - { - .name = "connlimit", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, - }, - { - .name = "connlimit", - .revision = 1, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, - }, +static struct xt_match connlimit_mt_reg __read_mostly = { + .name = "connlimit", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, }; static int __init connlimit_mt_init(void) { - return xt_register_matches(connlimit_mt_reg, - ARRAY_SIZE(connlimit_mt_reg)); + return xt_register_match(&connlimit_mt_reg); } static void __exit connlimit_mt_exit(void) { - xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg)); + xt_unregister_match(&connlimit_mt_reg); } module_init(connlimit_mt_init); -- cgit v1.2.3 From fdb694a01f1fcd30fd16d8aa290c34699fe98a17 Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Thu, 24 May 2012 03:56:44 +0000 Subject: netfilter: Add fail-open support Implement a new "fail-open" mode where packets are not dropped upon queue-full condition. This mode can be enabled/disabled per queue using netlink NFQA_CFG_FLAGS & NFQA_CFG_MASK attributes. Signed-off-by: Krishna Kumar Signed-off-by: Vivek Kashyap Signed-off-by: Sridhar Samudrala --- include/linux/netfilter/nfnetlink_queue.h | 5 ++++ net/netfilter/nfnetlink_queue.c | 40 ++++++++++++++++++++++++++++--- 2 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 24b32e6c009e..a6c1ddac05cc 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -84,8 +84,13 @@ enum nfqnl_attr_config { NFQA_CFG_CMD, /* nfqnl_msg_config_cmd */ NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ NFQA_CFG_QUEUE_MAXLEN, /* __u32 */ + NFQA_CFG_MASK, /* identify which flags to change */ + NFQA_CFG_FLAGS, /* value of these flags (__u32) */ __NFQA_CFG_MAX }; #define NFQA_CFG_MAX (__NFQA_CFG_MAX-1) +/* Flags for NFQA_CFG_FLAGS */ +#define NFQA_CFG_F_FAIL_OPEN (1 << 0) + #endif /* _NFNETLINK_QUEUE_H */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4162437b8361..630da3d2c62a 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -52,6 +52,7 @@ struct nfqnl_instance { u_int16_t queue_num; /* number of this queue */ u_int8_t copy_mode; + u_int32_t flags; /* Set using NFQA_CFG_FLAGS */ /* * Following fields are dirtied for each queued packet, * keep them in same cache line if possible. @@ -406,6 +407,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct nfqnl_instance *queue; int err = -ENOBUFS; __be32 *packet_id_ptr; + int failopen = 0; /* rcu_read_lock()ed by nf_hook_slow() */ queue = instance_lookup(queuenum); @@ -431,9 +433,14 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto err_out_free_nskb; } if (queue->queue_total >= queue->queue_maxlen) { - queue->queue_dropped++; - net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", - queue->queue_total); + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { + failopen = 1; + err = 0; + } else { + queue->queue_dropped++; + net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", + queue->queue_total); + } goto err_out_free_nskb; } entry->id = ++queue->id_sequence; @@ -455,6 +462,8 @@ err_out_free_nskb: kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); + if (failopen) + nf_reinject(entry, NF_ACCEPT); err_out: return err; } @@ -858,6 +867,31 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, spin_unlock_bh(&queue->lock); } + if (nfqa[NFQA_CFG_FLAGS]) { + __u32 flags, mask; + + if (!queue) { + ret = -ENODEV; + goto err_out_unlock; + } + + if (!nfqa[NFQA_CFG_MASK]) { + /* A mask is needed to specify which flags are being + * changed. + */ + ret = -EINVAL; + goto err_out_unlock; + } + + flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); + mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); + + spin_lock_bh(&queue->lock); + queue->flags &= ~mask; + queue->flags |= flags & mask; + spin_unlock_bh(&queue->lock); + } + err_out_unlock: rcu_read_unlock(); return ret; -- cgit v1.2.3 From efdedd5426a94b00d23483a1bcb4af3a91c894db Mon Sep 17 00:00:00 2001 From: Denys Fedoryshchenko Date: Thu, 17 May 2012 23:08:57 +0300 Subject: netfilter: xt_recent: add address masking option The mask option allows you put all address belonging that mask into the same recent slot. This can be useful in case that recent is used to detect attacks from the same network segment. Tested for backward compatibility. Signed-off-by: Denys Fedoryshchenko Signed-off-by: Pablo Neira Ayuso --- Documentation/feature-removal-schedule.txt | 7 ++++ include/linux/netfilter.h | 10 +++++ include/linux/netfilter/xt_recent.h | 10 +++++ net/netfilter/xt_recent.c | 62 +++++++++++++++++++++++++----- 4 files changed, 80 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 24ac00f4ae4b..bc4b9c6eb80e 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -574,6 +574,13 @@ Why: Remount currently allows changing bound subsystems and ---------------------------- +What: xt_recent rev 0 +When: 2013 +Who: Pablo Neira Ayuso +Files: net/netfilter/xt_recent.c + +---------------------------- + What: KVM debugfs statistics When: 2013 Why: KVM tracepoints provide mostly equivalent information in a much more diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ff9c84c29b28..4541f33dbfc3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -94,6 +94,16 @@ static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, a1->all[3] == a2->all[3]; } +static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, + union nf_inet_addr *result, + const union nf_inet_addr *mask) +{ + result->all[0] = a1->all[0] & mask->all[0]; + result->all[1] = a1->all[1] & mask->all[1]; + result->all[2] = a1->all[2] & mask->all[2]; + result->all[3] = a1->all[3] & mask->all[3]; +} + extern void netfilter_init(void); /* Largest hook number + 1 */ diff --git a/include/linux/netfilter/xt_recent.h b/include/linux/netfilter/xt_recent.h index 83318e01425e..6ef36c113e89 100644 --- a/include/linux/netfilter/xt_recent.h +++ b/include/linux/netfilter/xt_recent.h @@ -32,4 +32,14 @@ struct xt_recent_mtinfo { __u8 side; }; +struct xt_recent_mtinfo_v1 { + __u32 seconds; + __u32 hit_count; + __u8 check_set; + __u8 invert; + char name[XT_RECENT_NAME_LEN]; + __u8 side; + union nf_inet_addr mask; +}; + #endif /* _LINUX_NETFILTER_XT_RECENT_H */ diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index fc0d6dbe5d17..ae2ad1eec8d0 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -75,6 +75,7 @@ struct recent_entry { struct recent_table { struct list_head list; char name[XT_RECENT_NAME_LEN]; + union nf_inet_addr mask; unsigned int refcnt; unsigned int entries; struct list_head lru_list; @@ -228,10 +229,10 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct net *net = dev_net(par->in ? par->in : par->out); struct recent_net *recent_net = recent_pernet(net); - const struct xt_recent_mtinfo *info = par->matchinfo; + const struct xt_recent_mtinfo_v1 *info = par->matchinfo; struct recent_table *t; struct recent_entry *e; - union nf_inet_addr addr = {}; + union nf_inet_addr addr = {}, addr_mask; u_int8_t ttl; bool ret = info->invert; @@ -261,12 +262,15 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) spin_lock_bh(&recent_lock); t = recent_table_lookup(recent_net, info->name); - e = recent_entry_lookup(t, &addr, par->family, + + nf_inet_addr_mask(&addr, &addr_mask, &t->mask); + + e = recent_entry_lookup(t, &addr_mask, par->family, (info->check_set & XT_RECENT_TTL) ? ttl : 0); if (e == NULL) { if (!(info->check_set & XT_RECENT_SET)) goto out; - e = recent_entry_init(t, &addr, par->family, ttl); + e = recent_entry_init(t, &addr_mask, par->family, ttl); if (e == NULL) par->hotdrop = true; ret = !ret; @@ -306,10 +310,10 @@ out: return ret; } -static int recent_mt_check(const struct xt_mtchk_param *par) +static int recent_mt_check(const struct xt_mtchk_param *par, + const struct xt_recent_mtinfo_v1 *info) { struct recent_net *recent_net = recent_pernet(par->net); - const struct xt_recent_mtinfo *info = par->matchinfo; struct recent_table *t; #ifdef CONFIG_PROC_FS struct proc_dir_entry *pde; @@ -361,6 +365,8 @@ static int recent_mt_check(const struct xt_mtchk_param *par) goto out; } t->refcnt = 1; + + memcpy(&t->mask, &info->mask, sizeof(t->mask)); strcpy(t->name, info->name); INIT_LIST_HEAD(&t->lru_list); for (i = 0; i < ip_list_hash_size; i++) @@ -385,10 +391,28 @@ out: return ret; } +static int recent_mt_check_v0(const struct xt_mtchk_param *par) +{ + const struct xt_recent_mtinfo_v0 *info_v0 = par->matchinfo; + struct xt_recent_mtinfo_v1 info_v1; + + /* Copy revision 0 structure to revision 1 */ + memcpy(&info_v1, info_v0, sizeof(struct xt_recent_mtinfo)); + /* Set default mask to ensure backward compatible behaviour */ + memset(info_v1.mask.all, 0xFF, sizeof(info_v1.mask.all)); + + return recent_mt_check(par, &info_v1); +} + +static int recent_mt_check_v1(const struct xt_mtchk_param *par) +{ + return recent_mt_check(par, par->matchinfo); +} + static void recent_mt_destroy(const struct xt_mtdtor_param *par) { struct recent_net *recent_net = recent_pernet(par->net); - const struct xt_recent_mtinfo *info = par->matchinfo; + const struct xt_recent_mtinfo_v1 *info = par->matchinfo; struct recent_table *t; mutex_lock(&recent_mutex); @@ -625,7 +649,7 @@ static struct xt_match recent_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = recent_mt, .matchsize = sizeof(struct xt_recent_mtinfo), - .checkentry = recent_mt_check, + .checkentry = recent_mt_check_v0, .destroy = recent_mt_destroy, .me = THIS_MODULE, }, @@ -635,10 +659,30 @@ static struct xt_match recent_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = recent_mt, .matchsize = sizeof(struct xt_recent_mtinfo), - .checkentry = recent_mt_check, + .checkentry = recent_mt_check_v0, + .destroy = recent_mt_destroy, + .me = THIS_MODULE, + }, + { + .name = "recent", + .revision = 1, + .family = NFPROTO_IPV4, + .match = recent_mt, + .matchsize = sizeof(struct xt_recent_mtinfo_v1), + .checkentry = recent_mt_check_v1, .destroy = recent_mt_destroy, .me = THIS_MODULE, }, + { + .name = "recent", + .revision = 1, + .family = NFPROTO_IPV6, + .match = recent_mt, + .matchsize = sizeof(struct xt_recent_mtinfo_v1), + .checkentry = recent_mt_check_v1, + .destroy = recent_mt_destroy, + .me = THIS_MODULE, + } }; static int __init recent_mt_init(void) -- cgit v1.2.3 From 80f12eccce775dc6bb93dba9b52529740f929237 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Wed, 6 Jun 2012 17:13:06 +0000 Subject: Added kernel support in EEE Ethtool commands This patch extends the kernel's ethtool interface by adding support for 2 new EEE commands - get_eee and set_eee. Thanks goes to Giuseppe Cavallaro for his original patch adding this support. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 35 +++++++++++++++++++++++++++++++++++ net/core/ethtool.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e17fa7140588..297370a6cb18 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -136,6 +136,35 @@ struct ethtool_eeprom { __u8 data[0]; }; +/** + * struct ethtool_eee - Energy Efficient Ethernet information + * @cmd: ETHTOOL_{G,S}EEE + * @supported: Mask of %SUPPORTED_* flags for the speed/duplex combinations + * for which there is EEE support. + * @advertised: Mask of %ADVERTISED_* flags for the speed/duplex combinations + * advertised as eee capable. + * @lp_advertised: Mask of %ADVERTISED_* flags for the speed/duplex + * combinations advertised by the link partner as eee capable. + * @eee_active: Result of the eee auto negotiation. + * @eee_enabled: EEE configured mode (enabled/disabled). + * @tx_lpi_enabled: Whether the interface should assert its tx lpi, given + * that eee was negotiated. + * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting + * its tx lpi (after reaching 'idle' state). Effective only when eee + * was negotiated and tx_lpi_enabled was set. + */ +struct ethtool_eee { + __u32 cmd; + __u32 supported; + __u32 advertised; + __u32 lp_advertised; + __u32 eee_active; + __u32 eee_enabled; + __u32 tx_lpi_enabled; + __u32 tx_lpi_timer; + __u32 reserved[2]; +}; + /** * struct ethtool_modinfo - plugin module eeprom information * @cmd: %ETHTOOL_GMODULEINFO @@ -945,6 +974,8 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module + * @get_eee: Get Energy-Efficient (EEE) supported and status. + * @set_eee: Set EEE status (enable/disable) as well as LPI timers. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -1011,6 +1042,8 @@ struct ethtool_ops { struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); + int (*get_eee)(struct net_device *, struct ethtool_eee *); + int (*set_eee)(struct net_device *, struct ethtool_eee *); }; @@ -1089,6 +1122,8 @@ struct ethtool_ops { #define ETHTOOL_GET_TS_INFO 0x00000041 /* Get time stamping and PHC info */ #define ETHTOOL_GMODULEINFO 0x00000042 /* Get plug-in module information */ #define ETHTOOL_GMODULEEEPROM 0x00000043 /* Get plug-in module eeprom */ +#define ETHTOOL_GEEE 0x00000044 /* Get EEE settings */ +#define ETHTOOL_SEEE 0x00000045 /* Set EEE settings */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9c2afb480270..c73d0a59212c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -729,6 +729,40 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_wol(dev, &wol); } +static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + int rc; + + if (!dev->ethtool_ops->get_eee) + return -EOPNOTSUPP; + + memset(&edata, 0, sizeof(struct ethtool_eee)); + edata.cmd = ETHTOOL_GEEE; + rc = dev->ethtool_ops->get_eee(dev, &edata); + + if (rc) + return rc; + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + + return 0; +} + +static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + + if (!dev->ethtool_ops->set_eee) + return -EOPNOTSUPP; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + return dev->ethtool_ops->set_eee(dev, &edata); +} + static int ethtool_nway_reset(struct net_device *dev) { if (!dev->ethtool_ops->nway_reset) @@ -1471,6 +1505,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; + case ETHTOOL_GEEE: + rc = ethtool_get_eee(dev, useraddr); + break; + case ETHTOOL_SEEE: + rc = ethtool_set_eee(dev, useraddr); + break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; -- cgit v1.2.3 From 2397849baa7c44c242e5d5142d5d16d1e7ed53d0 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 9 Jun 2012 14:56:12 -0700 Subject: [PATCH] tcp: Cache inetpeer in timewait socket, and only when necessary. Since it's guarenteed that we will access the inetpeer if we're trying to do timewait recycling and TCP options were enabled on the connection, just cache the peer in the timewait socket. In the future, inetpeer lookups will be context dependent (per routing realm), and this helps facilitate that as well. Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- include/net/tcp.h | 1 - include/net/timewait_sock.h | 8 -------- net/ipv4/tcp_ipv4.c | 10 ---------- net/ipv4/tcp_minisocks.c | 27 ++++++++++++++++++++------- net/ipv6/tcp_ipv6.c | 13 ------------- 6 files changed, 22 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4c5b63283377..23e8234f75a5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -506,8 +506,9 @@ struct tcp_timewait_sock { u32 tw_rcv_wnd; u32 tw_ts_recent; long tw_ts_recent_stamp; + struct inet_peer *tw_peer; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *tw_md5_key; + struct tcp_md5sig_key *tw_md5_key; #endif /* Few sockets in timewait have cookies; in that case, then this * object holds a reference to them (tw_cookie_values->kref). diff --git a/include/net/tcp.h b/include/net/tcp.h index 424591866037..9332f342259a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -328,7 +328,6 @@ extern void tcp_shutdown (struct sock *sk, int how); extern int tcp_v4_rcv(struct sk_buff *skb); extern struct inet_peer *tcp_v4_get_peer(struct sock *sk); -extern void *tcp_v4_tw_get_peer(struct sock *sk); extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 8d6689cb2c66..68f0ecad6c6e 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -22,7 +22,6 @@ struct timewait_sock_ops { int (*twsk_unique)(struct sock *sk, struct sock *sktw, void *twp); void (*twsk_destructor)(struct sock *sk); - void *(*twsk_getpeer)(struct sock *sk); }; static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -41,11 +40,4 @@ static inline void twsk_destructor(struct sock *sk) sk->sk_prot->twsk_prot->twsk_destructor(sk); } -static inline void *twsk_getpeer(struct sock *sk) -{ - if (sk->sk_prot->twsk_prot->twsk_getpeer) - return sk->sk_prot->twsk_prot->twsk_getpeer(sk); - return NULL; -} - #endif /* _TIMEWAIT_SOCK_H */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 77f049d00dbb..fda2ca17135e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1835,20 +1835,10 @@ struct inet_peer *tcp_v4_get_peer(struct sock *sk) } EXPORT_SYMBOL(tcp_v4_get_peer); -void *tcp_v4_tw_get_peer(struct sock *sk) -{ - const struct inet_timewait_sock *tw = inet_twsk(sk); - struct net *net = sock_net(sk); - - return inet_getpeer_v4(net, tw->tw_daddr, 1); -} -EXPORT_SYMBOL(tcp_v4_tw_get_peer); - static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v4_tw_get_peer, }; const struct inet_connection_sock_af_ops ipv4_specific = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index fef9dbf3af00..cb015317c9f7 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -77,20 +77,19 @@ static bool tcp_remember_stamp(struct sock *sk) static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) { + const struct tcp_timewait_sock *tcptw; struct sock *sk = (struct sock *) tw; struct inet_peer *peer; - peer = twsk_getpeer(sk); + tcptw = tcp_twsk(sk); + peer = tcptw->tw_peer; if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; peer->tcp_ts = tcptw->tw_ts_recent; } - inet_putpeer(peer); return true; } return false; @@ -314,9 +313,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); bool recycle_ok = false; + bool recycle_on = false; - if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) + if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) { recycle_ok = tcp_remember_stamp(sk); + recycle_on = true; + } if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) tw = inet_twsk_alloc(sk, state); @@ -324,8 +326,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tw != NULL) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + struct inet_sock *inet = inet_sk(sk); + struct inet_peer *peer = NULL; - tw->tw_transparent = inet_sk(sk)->transparent; + tw->tw_transparent = inet->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -347,6 +351,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } #endif + if (recycle_on) + peer = icsk->icsk_af_ops->get_peer(sk); + tcptw->tw_peer = peer; + if (peer) + atomic_inc(&peer->refcnt); + #ifdef CONFIG_TCP_MD5SIG /* * The timewait bucket does not have the key DB from the @@ -398,8 +408,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) void tcp_twsk_destructor(struct sock *sk) { -#ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); + + if (twsk->tw_peer) + inet_putpeer(twsk->tw_peer); +#ifdef CONFIG_TCP_MD5SIG if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); kfree_rcu(twsk->tw_md5_key, rcu); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b5ecf37b61a6..f91b0bfd12d5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1746,23 +1746,10 @@ static struct inet_peer *tcp_v6_get_peer(struct sock *sk) return rt6_get_peer_create(rt); } -static void *tcp_v6_tw_get_peer(struct sock *sk) -{ - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - const struct inet_timewait_sock *tw = inet_twsk(sk); - struct net *net = sock_net(sk); - - if (tw->tw_family == AF_INET) - return tcp_v4_tw_get_peer(sk); - - return inet_getpeer_v6(net, &tw6->tw_v6_daddr, 1); -} - static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v6_tw_get_peer, }; static const struct inet_connection_sock_af_ops ipv6_specific = { -- cgit v1.2.3 From a4f606ea73d56d15f28653d2242e54d58bb612e5 Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Mon, 11 Jun 2012 11:59:36 +0800 Subject: {nl,cfg,mac}80211: fix the coding style related to mesh parameters fix the coding style related to mesh parameters, especially the indentation, as pointed out by Johannes Berg. Signed-off-by: Chun-Yeow Yeoh Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 +-- include/linux/nl80211.h | 98 ++++++++++++++++++++++--------------------- include/net/cfg80211.h | 12 +++--- net/mac80211/cfg.c | 3 +- net/mac80211/debugfs_netdev.c | 34 +++++++-------- net/wireless/nl80211.c | 97 ++++++++++++++++++++++-------------------- 6 files changed, 130 insertions(+), 120 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ce9af8918514..f831078182de 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1443,7 +1443,7 @@ enum ieee80211_tdls_actioncode { * * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method - * that will be specified in a vendor specific information element + * that will be specified in a vendor specific information element */ enum { IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, @@ -1455,7 +1455,7 @@ enum { * * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will - * be specified in a vendor specific information element + * be specified in a vendor specific information element */ enum { IEEE80211_PATH_PROTOCOL_HWMP = 1, @@ -1467,7 +1467,7 @@ enum { * * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be - * specified in a vendor specific information element + * specified in a vendor specific information element */ enum { IEEE80211_PATH_METRIC_AIRTIME = 1, diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 970afdf5a605..c61e1621822c 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -2090,78 +2090,80 @@ enum nl80211_mntr_flags { * @__NL80211_MESHCONF_INVALID: internal use * * @NL80211_MESHCONF_RETRY_TIMEOUT: specifies the initial retry timeout in - * millisecond units, used by the Peer Link Open message + * millisecond units, used by the Peer Link Open message * * @NL80211_MESHCONF_CONFIRM_TIMEOUT: specifies the initial confirm timeout, in - * millisecond units, used by the peer link management to close a peer link + * millisecond units, used by the peer link management to close a peer link * * @NL80211_MESHCONF_HOLDING_TIMEOUT: specifies the holding timeout, in - * millisecond units + * millisecond units * * @NL80211_MESHCONF_MAX_PEER_LINKS: maximum number of peer links allowed - * on this mesh interface + * on this mesh interface * * @NL80211_MESHCONF_MAX_RETRIES: specifies the maximum number of peer link - * open retries that can be sent to establish a new peer link instance in a - * mesh + * open retries that can be sent to establish a new peer link instance in a + * mesh * * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh - * point. + * point. * * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically - * open peer links when we detect compatible mesh peers. + * open peer links when we detect compatible mesh peers. * * @NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES: the number of action frames - * containing a PREQ that an MP can send to a particular destination (path - * target) + * containing a PREQ that an MP can send to a particular destination (path + * target) * * @NL80211_MESHCONF_PATH_REFRESH_TIME: how frequently to refresh mesh paths - * (in milliseconds) + * (in milliseconds) * * @NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT: minimum length of time to wait - * until giving up on a path discovery (in milliseconds) + * until giving up on a path discovery (in milliseconds) * * @NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT: The time (in TUs) for which mesh - * points receiving a PREQ shall consider the forwarding information from the - * root to be valid. (TU = time unit) + * points receiving a PREQ shall consider the forwarding information from + * the root to be valid. (TU = time unit) * * @NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL: The minimum interval of time (in - * TUs) during which an MP can send only one action frame containing a PREQ - * reference element + * TUs) during which an MP can send only one action frame containing a PREQ + * reference element * * @NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME: The interval of time (in TUs) - * that it takes for an HWMP information element to propagate across the mesh + * that it takes for an HWMP information element to propagate across the + * mesh * * @NL80211_MESHCONF_HWMP_ROOTMODE: whether root mode is enabled or not * * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a - * source mesh point for path selection elements. + * source mesh point for path selection elements. * * @NL80211_MESHCONF_HWMP_RANN_INTERVAL: The interval of time (in TUs) between - * root announcements are transmitted. + * root announcements are transmitted. * * @NL80211_MESHCONF_GATE_ANNOUNCEMENTS: Advertise that this mesh station has - * access to a broader network beyond the MBSS. This is done via Root - * Announcement frames. + * access to a broader network beyond the MBSS. This is done via Root + * Announcement frames. * * @NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL: The minimum interval of time (in - * TUs) during which a mesh STA can send only one Action frame containing a - * PERR element. + * TUs) during which a mesh STA can send only one Action frame containing a + * PERR element. * * @NL80211_MESHCONF_FORWARDING: set Mesh STA as forwarding or non-forwarding - * or forwarding entity (default is TRUE - forwarding entity) + * or forwarding entity (default is TRUE - forwarding entity) * * @NL80211_MESHCONF_RSSI_THRESHOLD: RSSI threshold in dBm. This specifies the - * threshold for average signal strength of candidate station to establish - * a peer link. - * - * @NL80211_MESHCONF_ATTR_MAX: highest possible mesh configuration attribute + * threshold for average signal strength of candidate station to establish + * a peer link. * * @NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR: maximum number of neighbors - * to synchronize to for 11s default synchronization method (see 11C.12.2.2) + * to synchronize to for 11s default synchronization method + * (see 11C.12.2.2) * * @NL80211_MESHCONF_HT_OPMODE: set mesh HT protection mode. * + * @NL80211_MESHCONF_ATTR_MAX: highest possible mesh configuration attribute + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -2203,34 +2205,36 @@ enum nl80211_meshconf_params { * @__NL80211_MESH_SETUP_INVALID: Internal use * * @NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL: Enable this option to use a - * vendor specific path selection algorithm or disable it to use the default - * HWMP. + * vendor specific path selection algorithm or disable it to use the + * default HWMP. * * @NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC: Enable this option to use a - * vendor specific path metric or disable it to use the default Airtime - * metric. + * vendor specific path metric or disable it to use the default Airtime + * metric. * * @NL80211_MESH_SETUP_IE: Information elements for this mesh, for instance, a - * robust security network ie, or a vendor specific information element that - * vendors will use to identify the path selection methods and metrics in use. + * robust security network ie, or a vendor specific information element + * that vendors will use to identify the path selection methods and + * metrics in use. * * @NL80211_MESH_SETUP_USERSPACE_AUTH: Enable this option if an authentication - * daemon will be authenticating mesh candidates. + * daemon will be authenticating mesh candidates. * * @NL80211_MESH_SETUP_USERSPACE_AMPE: Enable this option if an authentication - * daemon will be securing peer link frames. AMPE is a secured version of Mesh - * Peering Management (MPM) and is implemented with the assistance of a - * userspace daemon. When this flag is set, the kernel will send peer - * management frames to a userspace daemon that will implement AMPE - * functionality (security capabilities selection, key confirmation, and key - * management). When the flag is unset (default), the kernel can autonomously - * complete (unsecured) mesh peering without the need of a userspace daemon. - * - * @NL80211_MESH_SETUP_ATTR_MAX: highest possible mesh setup attribute number + * daemon will be securing peer link frames. AMPE is a secured version of + * Mesh Peering Management (MPM) and is implemented with the assistance of + * a userspace daemon. When this flag is set, the kernel will send peer + * management frames to a userspace daemon that will implement AMPE + * functionality (security capabilities selection, key confirmation, and + * key management). When the flag is unset (default), the kernel can + * autonomously complete (unsecured) mesh peering without the need of a + * userspace daemon. * * @NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC: Enable this option to use a - * vendor specific synchronization method or disable it to use the default - * neighbor offset synchronization + * vendor specific synchronization method or disable it to use the default + * neighbor offset synchronization + * + * @NL80211_MESH_SETUP_ATTR_MAX: highest possible mesh setup attribute number * * @__NL80211_MESH_SETUP_ATTR_AFTER_LAST: Internal use */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a129ee2f5483..778e533a9734 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -848,21 +848,21 @@ struct mesh_config { u16 dot11MeshConfirmTimeout; u16 dot11MeshHoldingTimeout; u16 dot11MeshMaxPeerLinks; - u8 dot11MeshMaxRetries; - u8 dot11MeshTTL; - u8 element_ttl; + u8 dot11MeshMaxRetries; + u8 dot11MeshTTL; + u8 element_ttl; bool auto_open_plinks; u32 dot11MeshNbrOffsetMaxNeighbor; - u8 dot11MeshHWMPmaxPREQretries; + u8 dot11MeshHWMPmaxPREQretries; u32 path_refresh_time; u16 min_discovery_timeout; u32 dot11MeshHWMPactivePathTimeout; u16 dot11MeshHWMPpreqMinInterval; u16 dot11MeshHWMPperrMinInterval; u16 dot11MeshHWMPnetDiameterTraversalTime; - u8 dot11MeshHWMPRootMode; + u8 dot11MeshHWMPRootMode; u16 dot11MeshHWMPRannInterval; - bool dot11MeshGateAnnouncementProtocol; + bool dot11MeshGateAnnouncementProtocol; bool dot11MeshForwarding; s32 rssi_threshold; u16 ht_opmode; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 498c94e34427..f41f9bea242a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1571,10 +1571,9 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, conf->dot11MeshGateAnnouncementProtocol = nconf->dot11MeshGateAnnouncementProtocol; } - if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) { + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) conf->dot11MeshHWMPRannInterval = nconf->dot11MeshHWMPRannInterval; - } if (_chg_mesh_attr(NL80211_MESHCONF_FORWARDING, mask)) conf->dot11MeshForwarding = nconf->dot11MeshForwarding; if (_chg_mesh_attr(NL80211_MESHCONF_RSSI_THRESHOLD, mask)) { diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index d4272ff43f71..c429417e1322 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -468,45 +468,45 @@ IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); IEEE80211_IF_FILE(dropped_frames_congestion, - u.mesh.mshstats.dropped_frames_congestion, DEC); + u.mesh.mshstats.dropped_frames_congestion, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, - u.mesh.mshstats.dropped_frames_no_route, DEC); + u.mesh.mshstats.dropped_frames_no_route, DEC); IEEE80211_IF_FILE(estab_plinks, u.mesh.mshstats.estab_plinks, ATOMIC); /* Mesh parameters */ IEEE80211_IF_FILE(dot11MeshMaxRetries, - u.mesh.mshcfg.dot11MeshMaxRetries, DEC); + u.mesh.mshcfg.dot11MeshMaxRetries, DEC); IEEE80211_IF_FILE(dot11MeshRetryTimeout, - u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); + u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); IEEE80211_IF_FILE(dot11MeshConfirmTimeout, - u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); + u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHoldingTimeout, - u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); + u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); IEEE80211_IF_FILE(dot11MeshTTL, u.mesh.mshcfg.dot11MeshTTL, DEC); IEEE80211_IF_FILE(element_ttl, u.mesh.mshcfg.element_ttl, DEC); IEEE80211_IF_FILE(auto_open_plinks, u.mesh.mshcfg.auto_open_plinks, DEC); IEEE80211_IF_FILE(dot11MeshMaxPeerLinks, - u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); + u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathTimeout, - u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); + u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPpreqMinInterval, - u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPperrMinInterval, - u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPnetDiameterTraversalTime, - u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); + u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); IEEE80211_IF_FILE(dot11MeshHWMPmaxPREQretries, - u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); + u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); IEEE80211_IF_FILE(path_refresh_time, - u.mesh.mshcfg.path_refresh_time, DEC); + u.mesh.mshcfg.path_refresh_time, DEC); IEEE80211_IF_FILE(min_discovery_timeout, - u.mesh.mshcfg.min_discovery_timeout, DEC); + u.mesh.mshcfg.min_discovery_timeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRootMode, - u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); + u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); IEEE80211_IF_FILE(dot11MeshGateAnnouncementProtocol, - u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); + u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, - u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); + u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); IEEE80211_IF_FILE(ht_opmode, u.mesh.mshcfg.ht_opmode, DEC); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7ae54b82291f..dd94ee5fb40a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -115,7 +115,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_STA_VLAN] = { .type = NLA_U32 }, [NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ }, [NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_MESH_ID_LEN }, + .len = IEEE80211_MAX_MESH_ID_LEN }, [NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 }, [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, @@ -3492,7 +3492,6 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_ELEMENT_TTL] = { .type = NLA_U8 }, [NL80211_MESHCONF_AUTO_OPEN_PLINKS] = { .type = NLA_U8 }, [NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR] = { .type = NLA_U32 }, - [NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES] = { .type = NLA_U8 }, [NL80211_MESHCONF_PATH_REFRESH_TIME] = { .type = NLA_U32 }, [NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT] = { .type = NLA_U16 }, @@ -3504,8 +3503,8 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_RANN_INTERVAL] = { .type = NLA_U16 }, [NL80211_MESHCONF_GATE_ANNOUNCEMENTS] = { .type = NLA_U8 }, [NL80211_MESHCONF_FORWARDING] = { .type = NLA_U8 }, - [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32}, - [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16}, + [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32 }, + [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16 }, }; static const struct nla_policy @@ -3515,7 +3514,7 @@ static const struct nla_policy [NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC] = { .type = NLA_U8 }, [NL80211_MESH_SETUP_USERSPACE_AUTH] = { .type = NLA_FLAG }, [NL80211_MESH_SETUP_IE] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_DATA_LEN }, + .len = IEEE80211_MAX_DATA_LEN }, [NL80211_MESH_SETUP_USERSPACE_AMPE] = { .type = NLA_FLAG }, }; @@ -3548,63 +3547,71 @@ do {\ /* Fill in the params struct */ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshRetryTimeout, - mask, NL80211_MESHCONF_RETRY_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_RETRY_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConfirmTimeout, - mask, NL80211_MESHCONF_CONFIRM_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_CONFIRM_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHoldingTimeout, - mask, NL80211_MESHCONF_HOLDING_TIMEOUT, nla_get_u16); + mask, NL80211_MESHCONF_HOLDING_TIMEOUT, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxPeerLinks, - mask, NL80211_MESHCONF_MAX_PEER_LINKS, nla_get_u16); + mask, NL80211_MESHCONF_MAX_PEER_LINKS, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxRetries, - mask, NL80211_MESHCONF_MAX_RETRIES, nla_get_u8); + mask, NL80211_MESHCONF_MAX_RETRIES, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshTTL, - mask, NL80211_MESHCONF_TTL, nla_get_u8); + mask, NL80211_MESHCONF_TTL, nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, element_ttl, - mask, NL80211_MESHCONF_ELEMENT_TTL, nla_get_u8); + mask, NL80211_MESHCONF_ELEMENT_TTL, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, - mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, - mask, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, - nla_get_u32); + mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, + nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, mask, + NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, - mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, - nla_get_u8); + mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, path_refresh_time, - mask, NL80211_MESHCONF_PATH_REFRESH_TIME, nla_get_u32); + mask, NL80211_MESHCONF_PATH_REFRESH_TIME, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, min_discovery_timeout, - mask, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, - nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, - mask, NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, - nla_get_u32); + mask, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, mask, + NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPpreqMinInterval, - mask, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, - nla_get_u16); + mask, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPperrMinInterval, - mask, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, - nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPnetDiameterTraversalTime, - mask, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, - nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPRootMode, mask, - NL80211_MESHCONF_HWMP_ROOTMODE, - nla_get_u8); + mask, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPRannInterval, mask, - NL80211_MESHCONF_HWMP_RANN_INTERVAL, - nla_get_u16); + dot11MeshHWMPnetDiameterTraversalTime, mask, + NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, + nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRootMode, mask, + NL80211_MESHCONF_HWMP_ROOTMODE, nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRannInterval, mask, + NL80211_MESHCONF_HWMP_RANN_INTERVAL, + nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshGateAnnouncementProtocol, mask, - NL80211_MESHCONF_GATE_ANNOUNCEMENTS, - nla_get_u8); + dot11MeshGateAnnouncementProtocol, mask, + NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshForwarding, - mask, NL80211_MESHCONF_FORWARDING, nla_get_u8); + mask, NL80211_MESHCONF_FORWARDING, + nla_get_u8); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, - mask, NL80211_MESHCONF_RSSI_THRESHOLD, nla_get_u32); + mask, NL80211_MESHCONF_RSSI_THRESHOLD, + nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, - mask, NL80211_MESHCONF_HT_OPMODE, nla_get_u16); + mask, NL80211_MESHCONF_HT_OPMODE, + nla_get_u16); if (mask_out) *mask_out = mask; -- cgit v1.2.3 From 9136461ab921fd5066ba6a0de08399e2172f4d71 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Jun 2012 06:36:13 +0000 Subject: net: keep name_hlist close to name __dev_get_by_name() is slow because pm_qos_req has been inserted between name[] and name_hlist, adding cache misses. pm_qos_req has nothing to do at the beginning of struct net_device Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d94cb1431519..a0b84e3b087c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1046,10 +1046,9 @@ struct net_device { */ char name[IFNAMSIZ]; - struct pm_qos_request pm_qos_req; - - /* device name hash chain */ + /* device name hash chain, please keep it close to name[] */ struct hlist_node name_hlist; + /* snmp alias */ char *ifalias; @@ -1322,6 +1321,8 @@ struct net_device { /* group the device belongs to */ int group; + + struct pm_qos_request pm_qos_req; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 535588e61a007416f46cf08b4ccb6cc73b3f6fb0 Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Mon, 11 Jun 2012 18:14:16 -0700 Subject: ieee80211: definitions for Microsoft Vendor OUI and WPA OUI type Reference: http://standards.ieee.org/develop/regauth/oui/oui.txt Signed-off-by: Avinash Patil Signed-off-by: Bing Zhao Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f831078182de..98c86ff657bb 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1589,6 +1589,8 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 +#define WLAN_OUI_MICROSOFT 0x0050f2 +#define WLAN_OUI_TYPE_MICROSOFT_WPA 1 /* * WMM/802.11e Tspec Element -- cgit v1.2.3 From d0daebc3d622f95db181601cb0c4a0781f74f758 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 12 Jun 2012 00:44:01 +0000 Subject: ipv4: Add interface option to enable routing of 127.0.0.0/8 Routing of 127/8 is tradtionally forbidden, we consider packets from that address block martian when routing and do not process corresponding ARP requests. This is a sane default but renders a huge address space practically unuseable. The RFC states that no address within the 127/8 block should ever appear on any network anywhere but it does not forbid the use of such addresses outside of the loopback device in particular. For example to address a pool of virtual guests behind a load balancer. This patch adds a new interface option 'route_localnet' enabling routing of the 127/8 address block and processing of ARP requests on a specific interface. Note that for the feature to work, the default local route covering 127/8 dev lo needs to be removed. Example: $ sysctl -w net.ipv4.conf.eth0.route_localnet=1 $ ip route del 127.0.0.0/8 dev lo table local $ ip addr add 127.1.0.1/16 dev eth0 $ ip route flush cache V2: Fix invalid check to auto flush cache (thanks davem) Signed-off-by: Thomas Graf Acked-by: Neil Horman Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 +++++ include/linux/inetdevice.h | 2 ++ net/ipv4/arp.c | 3 ++- net/ipv4/devinet.c | 5 ++++- net/ipv4/route.c | 30 +++++++++++++++++++++--------- 5 files changed, 34 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 6f896b94abdc..99d0e0504d6e 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -862,6 +862,11 @@ accept_local - BOOLEAN local interfaces over the wire and have them accepted properly. default FALSE +route_localnet - BOOLEAN + Do not consider loopback addresses as martian source or destination + while routing. This enables the use of 127/8 for local routing purposes. + default FALSE + rp_filter - INTEGER 0 - No source validation. 1 - Strict mode as defined in RFC3704 Strict Reverse Path diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 597f4a9f3240..67f9ddacb70c 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -38,6 +38,7 @@ enum IPV4_DEVCONF_ACCEPT_LOCAL, IPV4_DEVCONF_SRC_VMARK, IPV4_DEVCONF_PROXY_ARP_PVLAN, + IPV4_DEVCONF_ROUTE_LOCALNET, __IPV4_DEVCONF_MAX }; @@ -131,6 +132,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) +#define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index cda37be02f8d..2e560f0c757d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -790,7 +790,8 @@ static int arp_process(struct sk_buff *skb) * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + if (ipv4_is_multicast(tip) || + (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) goto out; /* diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 10e15a144e95..44bf82e3aef7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1500,7 +1500,8 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); - if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || + i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net, 0); } @@ -1617,6 +1618,8 @@ static struct devinet_sysctl_table { "force_igmp_version"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), + DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, + "route_localnet"), }, }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 842510d50453..655506af47ca 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1960,9 +1960,13 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP)) + skb->protocol != htons(ETH_P_IP)) goto e_inval; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(saddr)) + goto e_inval; + if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) goto e_inval; @@ -2203,8 +2207,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr)) + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) @@ -2216,9 +2219,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(saddr)) goto martian_source; - if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr)) + if (ipv4_is_zeronet(daddr)) goto martian_destination; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) { + if (ipv4_is_loopback(daddr)) + goto martian_destination; + + if (ipv4_is_loopback(saddr)) + goto martian_source; + } + /* * Now we are ready to route packet. */ @@ -2457,9 +2468,14 @@ static struct rtable *__mkroute_output(const struct fib_result *res, u16 type = res->type; struct rtable *rth; - if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + in_dev = __in_dev_get_rcu(dev_out); + if (!in_dev) return ERR_PTR(-EINVAL); + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + return ERR_PTR(-EINVAL); + if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) @@ -2470,10 +2486,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - in_dev = __in_dev_get_rcu(dev_out); - if (!in_dev) - return ERR_PTR(-EINVAL); - if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; -- cgit v1.2.3 From 4a5a14d39e8164b5c77f1bf42851a58a69a6c7b2 Mon Sep 17 00:00:00 2001 From: "tom.leiming@gmail.com" Date: Mon, 11 Jun 2012 15:19:43 +0000 Subject: usbnet: remove flag of EVENT_DEV_WAKING The flag of EVENT_DEV_WAKING is not used any more, so just remove it. Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 76f439647c4b..f87cf622317f 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -66,9 +66,8 @@ struct usbnet { # define EVENT_STS_SPLIT 3 # define EVENT_LINK_RESET 4 # define EVENT_RX_PAUSED 5 -# define EVENT_DEV_WAKING 6 -# define EVENT_DEV_ASLEEP 7 -# define EVENT_DEV_OPEN 8 +# define EVENT_DEV_ASLEEP 6 +# define EVENT_DEV_OPEN 7 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) -- cgit v1.2.3 From 95603e2293de556de7e82221649bfd7fd98b64a3 Mon Sep 17 00:00:00 2001 From: Michel Machado Date: Tue, 12 Jun 2012 10:16:35 +0000 Subject: net-next: add dev_loopback_xmit() to avoid duplicate code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add dev_loopback_xmit() in order to deduplicate functions ip_dev_loopback_xmit() (in net/ipv4/ip_output.c) and ip6_dev_loopback_xmit() (in net/ipv6/ip6_output.c). I was about to reinvent the wheel when I noticed that ip_dev_loopback_xmit() and ip6_dev_loopback_xmit() do exactly what I need and are not IP-only functions, but they were not available to reuse elsewhere. ip6_dev_loopback_xmit() does not have line "skb_dst_force(skb);", but I understand that this is harmless, and should be in dev_loopback_xmit(). Signed-off-by: Michel Machado CC: "David S. Miller" CC: Alexey Kuznetsov CC: James Morris CC: Hideaki YOSHIFUJI CC: Patrick McHardy CC: Eric Dumazet CC: Jiri Pirko CC: "Michał Mirosław" CC: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 17 +++++++++++++++++ net/ipv4/ip_output.c | 17 ++--------------- net/ipv6/ip6_output.c | 15 +-------------- 4 files changed, 21 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a0b84e3b087c..2c2ecea28a1b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1627,6 +1627,7 @@ extern int dev_alloc_name(struct net_device *dev, const char *name); extern int dev_open(struct net_device *dev); extern int dev_close(struct net_device *dev); extern void dev_disable_lro(struct net_device *dev); +extern int dev_loopback_xmit(struct sk_buff *newskb); extern int dev_queue_xmit(struct sk_buff *skb); extern int register_netdevice(struct net_device *dev); extern void unregister_netdevice_queue(struct net_device *dev, diff --git a/net/core/dev.c b/net/core/dev.c index cd0981977f5c..c6e29ea65bd9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2475,6 +2475,23 @@ static void skb_update_prio(struct sk_buff *skb) static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 +/** + * dev_loopback_xmit - loop back @skb + * @skb: buffer to transmit + */ +int dev_loopback_xmit(struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->pkt_type = PACKET_LOOPBACK; + skb->ip_summed = CHECKSUM_UNNECESSARY; + WARN_ON(!skb_dst(skb)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b99ca4e154b9..0f3185a662c3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -113,19 +113,6 @@ int ip_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip_local_out); -/* dev_loopback_xmit for use with netfilter. */ -static int ip_dev_loopback_xmit(struct sk_buff *newskb) -{ - skb_reset_mac_header(newskb); - __skb_pull(newskb, skb_network_offset(newskb)); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(newskb)); - skb_dst_force(newskb); - netif_rx_ni(newskb); - return 0; -} - static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; @@ -281,7 +268,7 @@ int ip_mc_output(struct sk_buff *skb) if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, - ip_dev_loopback_xmit); + dev_loopback_xmit); } /* Multicasts with ttl 0 must not go beyond the host */ @@ -296,7 +283,7 @@ int ip_mc_output(struct sk_buff *skb) struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, - NULL, newskb->dev, ip_dev_loopback_xmit); + NULL, newskb->dev, dev_loopback_xmit); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 62fcf3e48aca..ee1bb450bfe4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -83,19 +83,6 @@ int ip6_local_out(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip6_local_out); -/* dev_loopback_xmit for use with netfilter. */ -static int ip6_dev_loopback_xmit(struct sk_buff *newskb) -{ - skb_reset_mac_header(newskb); - __skb_pull(newskb, skb_network_offset(newskb)); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(newskb)); - - netif_rx_ni(newskb); - return 0; -} - static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -121,7 +108,7 @@ static int ip6_finish_output2(struct sk_buff *skb) if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, - ip6_dev_loopback_xmit); + dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { IP6_INC_STATS(dev_net(dev), idev, -- cgit v1.2.3 From 4a4ab0d7c9abe4e403bcea6ae2fc5d3f28a64a29 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Jun 2012 11:17:11 +0200 Subject: nl80211: fix sched scan match attribute name It should be NL80211_SCHED_SCAN_MATCH_ATTR_SSID as documented, not NL80211_ATTR_SCHED_SCAN_MATCH_SSID. Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 5 ++++- net/wireless/nl80211.c | 4 ++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c61e1621822c..e7b1fc1fe26b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1963,7 +1963,7 @@ enum nl80211_reg_rule_attr { enum nl80211_sched_scan_match_attr { __NL80211_SCHED_SCAN_MATCH_ATTR_INVALID, - NL80211_ATTR_SCHED_SCAN_MATCH_SSID, + NL80211_SCHED_SCAN_MATCH_ATTR_SSID, /* keep last */ __NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST, @@ -1971,6 +1971,9 @@ enum nl80211_sched_scan_match_attr { __NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST - 1 }; +/* only for backward compatibility */ +#define NL80211_ATTR_SCHED_SCAN_MATCH_SSID NL80211_SCHED_SCAN_MATCH_ATTR_SSID + /** * enum nl80211_reg_rule_flags - regulatory rule flags * diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dd94ee5fb40a..7db0aee8cd5b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -250,7 +250,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { static const struct nla_policy nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { - [NL80211_ATTR_SCHED_SCAN_MATCH_SSID] = { .type = NLA_BINARY, + [NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_SSID_LEN }, }; @@ -4253,7 +4253,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, nla_data(attr), nla_len(attr), nl80211_match_policy); - ssid = tb[NL80211_ATTR_SCHED_SCAN_MATCH_SSID]; + ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]; if (ssid) { if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; -- cgit v1.2.3 From 73c3df3ba3f2d7fe3ea47f944282f3cda31c5505 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Jun 2012 11:17:14 +0200 Subject: cfg80211/nl80211: fix kernel-doc Add missing entries to nl80211.h and fix the kernel-doc notation in cfg80211.h. Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 33 ++++++++++++++++++++++++++++----- include/net/cfg80211.h | 8 ++++---- 2 files changed, 32 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index e7b1fc1fe26b..e4f41bdebc07 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -277,6 +277,12 @@ * @NL80211_CMD_NEW_SURVEY_RESULTS: survey data notification (as a reply to * NL80211_CMD_GET_SURVEY and on the "scan" multicast group) * + * @NL80211_CMD_SET_PMKSA: Add a PMKSA cache entry, using %NL80211_ATTR_MAC + * (for the BSSID) and %NL80211_ATTR_PMKID. + * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC + * (for the BSSID) and %NL80211_ATTR_PMKID. + * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries. + * * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain * has been changed and provides details of the request information * that caused the change such as who initiated the regulatory request @@ -456,6 +462,10 @@ * the frame. * @NL80211_CMD_ACTION_TX_STATUS: Alias for @NL80211_CMD_FRAME_TX_STATUS for * backward compatibility. + * + * @NL80211_CMD_SET_POWER_SAVE: Set powersave, using %NL80211_ATTR_PS_STATE + * @NL80211_CMD_GET_POWER_SAVE: Get powersave status in %NL80211_ATTR_PS_STATE + * * @NL80211_CMD_SET_CQM: Connection quality monitor configuration. This command * is used to configure connection quality monitoring notification trigger * levels. @@ -771,6 +781,13 @@ enum nl80211_commands { * section 7.3.2.25.1, e.g. 0x000FAC04) * @NL80211_ATTR_KEY_SEQ: transmit key sequence number (IV/PN) for TKIP and * CCMP keys, each six bytes in little endian + * @NL80211_ATTR_KEY_DEFAULT: Flag attribute indicating the key is default key + * @NL80211_ATTR_KEY_DEFAULT_MGMT: Flag attribute indicating the key is the + * default management key + * @NL80211_ATTR_CIPHER_SUITES_PAIRWISE: For crypto settings for connect or + * other commands, indicates which pairwise cipher suites are used + * @NL80211_ATTR_CIPHER_SUITE_GROUP: For crypto settings for connect or + * other commands, indicates which group cipher suite is used * * @NL80211_ATTR_BEACON_INTERVAL: beacon interval in TU * @NL80211_ATTR_DTIM_PERIOD: DTIM period for beaconing @@ -1006,6 +1023,8 @@ enum nl80211_commands { * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was * acknowledged by the recipient. * + * @NL80211_ATTR_PS_STATE: powersave state, using &enum nl80211_ps_state values. + * * @NL80211_ATTR_CQM: connection quality monitor configuration in a * nested attribute with %NL80211_ATTR_CQM_* sub-attributes. * @@ -1063,7 +1082,7 @@ enum nl80211_commands { * flag isn't set, the frame will be rejected. This is also used as an * nl80211 capability flag. * - * @NL80211_ATTR_BSS_HTOPMODE: HT operation mode (u16) + * @NL80211_ATTR_BSS_HT_OPMODE: HT operation mode (u16) * * @NL80211_ATTR_KEY_DEFAULT_TYPES: A nested attribute containing flags * attributes, specifying what a key should be set as default as. @@ -1087,10 +1106,10 @@ enum nl80211_commands { * indicate which WoW triggers should be enabled. This is also * used by %NL80211_CMD_GET_WOWLAN to get the currently enabled WoWLAN * triggers. - + * * @NL80211_ATTR_SCHED_SCAN_INTERVAL: Interval between scheduled scan * cycles, in msecs. - + * * @NL80211_ATTR_SCHED_SCAN_MATCH: Nested attribute with one or more * sets of attributes to match during scheduled scans. Only BSSs * that match any of the sets will be reported. These are @@ -1117,7 +1136,7 @@ enum nl80211_commands { * are managed in software: interfaces of these types aren't subject to * any restrictions in their number or combinations. * - * @%NL80211_ATTR_REKEY_DATA: nested attribute containing the information + * @NL80211_ATTR_REKEY_DATA: nested attribute containing the information * necessary for GTK rekeying in the device, see &enum nl80211_rekey_data. * * @NL80211_ATTR_SCAN_SUPP_RATES: rates per to be advertised as supported in scan, @@ -1184,7 +1203,6 @@ enum nl80211_commands { * @NL80211_ATTR_FEATURE_FLAGS: This u32 attribute contains flags from * &enum nl80211_feature_flags and is advertised in wiphy information. * @NL80211_ATTR_PROBE_RESP_OFFLOAD: Indicates that the HW responds to probe - * * requests while operating in AP-mode. * This attribute holds a bitmap of the supported protocols for * offloading (see &enum nl80211_probe_resp_offload_support_attr). @@ -2507,6 +2525,11 @@ enum nl80211_band { NL80211_BAND_5GHZ, }; +/** + * enum nl80211_ps_state - powersave state + * @NL80211_PS_DISABLED: powersave is disabled + * @NL80211_PS_ENABLED: powersave is enabled + */ enum nl80211_ps_state { NL80211_PS_DISABLED, NL80211_PS_ENABLED, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 778e533a9734..76d54725ea31 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -627,10 +627,10 @@ struct sta_bss_parameters { * @llid: mesh local link id * @plid: mesh peer link id * @plink_state: mesh peer link state - * @signal: the signal strength, type depends on the wiphy's signal_type - NOTE: For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. - * @signal_avg: avg signal strength, type depends on the wiphy's signal_type - NOTE: For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. + * @signal: The signal strength, type depends on the wiphy's signal_type. + * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. + * @signal_avg: Average signal strength, type depends on the wiphy's signal_type. + * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. * @txrate: current unicast bitrate from this station * @rxrate: current unicast bitrate to this station * @rx_packets: packets received from this station -- cgit v1.2.3 From ac1073a61d73b6277794d2efc872eb7e1b706b5c Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Thu, 14 Jun 2012 02:06:06 +0800 Subject: {nl,cfg,mac}80211: implement dot11MeshHWMProotInterval and dot11MeshHWMPactivePathToRootTimeout Add the mesh configuration parameters dot11MeshHWMProotInterval and dot11MeshHWMPactivePathToRootTimeout to be used by proactive PREQ mechanism. Signed-off-by: Chun-Yeow Yeoh [line-break commit log] Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 9 +++++++++ include/net/cfg80211.h | 9 +++++++++ net/mac80211/cfg.c | 6 ++++++ net/mac80211/debugfs_netdev.c | 6 ++++++ net/wireless/mesh.c | 4 ++++ net/wireless/nl80211.c | 15 ++++++++++++++- 6 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index e4f41bdebc07..6936fabe8797 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -2185,6 +2185,13 @@ enum nl80211_mntr_flags { * * @NL80211_MESHCONF_ATTR_MAX: highest possible mesh configuration attribute * + * @NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT: The time (in TUs) for + * which mesh STAs receiving a proactive PREQ shall consider the forwarding + * information to the root mesh STA to be valid. + * + * @NL80211_MESHCONF_HWMP_ROOT_INTERVAL: The interval of time (in TUs) between + * proactive PREQs are transmitted. + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -2211,6 +2218,8 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_RSSI_THRESHOLD, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, NL80211_MESHCONF_HT_OPMODE, + NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, + NL80211_MESHCONF_HWMP_ROOT_INTERVAL, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 76d54725ea31..e52b38d7b1b6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -842,6 +842,13 @@ struct bss_parameters { * @rssi_threshold: the threshold for average signal strength of candidate * station to establish a peer link * @ht_opmode: mesh HT protection mode + * + * @dot11MeshHWMPactivePathToRootTimeout: The time (in TUs) for which mesh STAs + * receiving a proactive PREQ shall consider the forwarding information to + * the root mesh STA to be valid. + * + * @dot11MeshHWMProotInterval: The interval of time (in TUs) between proactive + * PREQs are transmitted. */ struct mesh_config { u16 dot11MeshRetryTimeout; @@ -866,6 +873,8 @@ struct mesh_config { bool dot11MeshForwarding; s32 rssi_threshold; u16 ht_opmode; + u32 dot11MeshHWMPactivePathToRootTimeout; + u16 dot11MeshHWMProotInterval; }; /** diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index cd8b1fb05d42..d93cda1c4215 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1590,6 +1590,12 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); } + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, mask)) + conf->dot11MeshHWMPactivePathToRootTimeout = + nconf->dot11MeshHWMPactivePathToRootTimeout; + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) + conf->dot11MeshHWMProotInterval = + nconf->dot11MeshHWMProotInterval; return 0; } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index c429417e1322..a8cea70902e4 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -510,6 +510,10 @@ IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); IEEE80211_IF_FILE(ht_opmode, u.mesh.mshcfg.ht_opmode, DEC); +IEEE80211_IF_FILE(dot11MeshHWMPactivePathToRootTimeout, + u.mesh.mshcfg.dot11MeshHWMPactivePathToRootTimeout, DEC); +IEEE80211_IF_FILE(dot11MeshHWMProotInterval, + u.mesh.mshcfg.dot11MeshHWMProotInterval, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ @@ -611,6 +615,8 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(dot11MeshGateAnnouncementProtocol); MESHPARAMS_ADD(rssi_threshold); MESHPARAMS_ADD(ht_opmode); + MESHPARAMS_ADD(dot11MeshHWMPactivePathToRootTimeout); + MESHPARAMS_ADD(dot11MeshHWMProotInterval); #undef MESHPARAMS_ADD } #endif diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index b44c736bf9cf..2f141cfd581e 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -14,6 +14,8 @@ #define MESH_PATH_TIMEOUT 5000 #define MESH_RANN_INTERVAL 5000 +#define MESH_PATH_TO_ROOT_TIMEOUT 6000 +#define MESH_ROOT_INTERVAL 5000 /* * Minimum interval between two consecutive PREQs originated by the same @@ -62,6 +64,8 @@ const struct mesh_config default_mesh_config = { .dot11MeshForwarding = true, .rssi_threshold = MESH_RSSI_THRESHOLD, .ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED, + .dot11MeshHWMPactivePathToRootTimeout = MESH_PATH_TO_ROOT_TIMEOUT, + .dot11MeshHWMProotInterval = MESH_ROOT_INTERVAL, }; const struct mesh_setup default_mesh_setup = { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7db0aee8cd5b..f8930db613df 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3469,7 +3469,11 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_u32(msg, NL80211_MESHCONF_RSSI_THRESHOLD, cur_params.rssi_threshold) || nla_put_u32(msg, NL80211_MESHCONF_HT_OPMODE, - cur_params.ht_opmode)) + cur_params.ht_opmode) || + nla_put_u32(msg, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, + cur_params.dot11MeshHWMPactivePathToRootTimeout) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, + cur_params.dot11MeshHWMProotInterval)) goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); @@ -3505,6 +3509,8 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_FORWARDING] = { .type = NLA_U8 }, [NL80211_MESHCONF_RSSI_THRESHOLD] = { .type = NLA_U32 }, [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16 }, + [NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT] = { .type = NLA_U32 }, + [NL80211_MESHCONF_HWMP_ROOT_INTERVAL] = { .type = NLA_U16 }, }; static const struct nla_policy @@ -3612,6 +3618,13 @@ do {\ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, mask, NL80211_MESHCONF_HT_OPMODE, nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, + mask, + NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, + nla_get_u32); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMProotInterval, + mask, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, + nla_get_u16); if (mask_out) *mask_out = mask; -- cgit v1.2.3 From a69cc44fe9ebb806c5f3f8bd83fb4a50ca63647b Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Thu, 14 Jun 2012 02:06:07 +0800 Subject: mac80211: implement the proactive PREQ generation Generate the proactive PREQ element as defined in Sec. 13.10.9.3 (Case C) of IEEE Std. 802.11-2012 based on the selection of dot11MeshHWMPRootMode as follow: dot11MeshHWMPRootMode (2) is proactivePREQnoPREP dot11MeshHWMPRootMode (3) is proactivePREQwithPREP The proactive PREQ is generated based on the interval defined by dot11MeshHWMProotInterval. With this change, proactive RANN element is now generated if the dot11MeshHWMPRootMode is set to (4) instead of (1). Signed-off-by: Chun-Yeow Yeoh [line-break commit log] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 42 ++++++++++++++++++++++++++++++++++++++++++ net/mac80211/mesh.c | 10 ++++++++-- net/mac80211/mesh_hwmp.c | 27 ++++++++++++++++++++++++--- 3 files changed, 74 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 98c86ff657bb..6e0601189db9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -567,6 +567,26 @@ struct ieee80211s_hdr { #define MESH_FLAGS_AE 0x3 #define MESH_FLAGS_PS_DEEP 0x4 +/** + * enum ieee80211_preq_flags - mesh PREQ element flags + * + * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield + */ +enum ieee80211_preq_flags { + IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, +}; + +/** + * enum ieee80211_preq_target_flags - mesh PREQ element per target flags + * + * @IEEE80211_PREQ_TO_FLAG: target only subfield + * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield + */ +enum ieee80211_preq_target_flags { + IEEE80211_PREQ_TO_FLAG = 1<<0, + IEEE80211_PREQ_USN_FLAG = 1<<2, +}; + /** * struct ieee80211_quiet_ie * @@ -1474,6 +1494,28 @@ enum { IEEE80211_PATH_METRIC_VENDOR = 255, }; +/** + * enum ieee80211_root_mode_identifier - root mesh STA mode identifier + * + * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode + * + * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) + * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than + * this value + * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports + * the proactive PREQ with proactive PREP subfield set to 0 + * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA + * supports the proactive PREQ with proactive PREP subfield set to 1 + * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports + * the proactive RANN + */ +enum ieee80211_root_mode_identifier { + IEEE80211_ROOTMODE_NO_ROOT = 0, + IEEE80211_ROOTMODE_ROOT = 1, + IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, + IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, + IEEE80211_PROACTIVE_RANN = 4, +}; /* * IEEE 802.11-2007 7.3.2.9 Country information element diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 7cf19509fb68..6bff3c4d17dd 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -541,11 +541,17 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata, static void ieee80211_mesh_rootpath(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u32 interval; mesh_path_tx_root_frame(sdata); + + if (ifmsh->mshcfg.dot11MeshHWMPRootMode == IEEE80211_PROACTIVE_RANN) + interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; + else + interval = ifmsh->mshcfg.dot11MeshHWMProotInterval; + mod_timer(&ifmsh->mesh_path_root_timer, - round_jiffies(TU_TO_EXP_TIME( - ifmsh->mshcfg.dot11MeshHWMPRannInterval))); + round_jiffies(TU_TO_EXP_TIME(interval))); } #ifdef CONFIG_PM diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 9b6da2de660d..a6b08f5c4612 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1154,13 +1154,34 @@ mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u32 interval = ifmsh->mshcfg.dot11MeshHWMPRannInterval; - u8 flags; + u8 flags, target_flags = 0; flags = (ifmsh->mshcfg.dot11MeshGateAnnouncementProtocol) ? RANN_FLAG_IS_GATE : 0; - mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, + + switch (ifmsh->mshcfg.dot11MeshHWMPRootMode) { + case IEEE80211_PROACTIVE_RANN: + mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, cpu_to_le32(++ifmsh->sn), 0, NULL, 0, broadcast_addr, - 0, sdata->u.mesh.mshcfg.element_ttl, + 0, ifmsh->mshcfg.element_ttl, cpu_to_le32(interval), 0, 0, sdata); + break; + case IEEE80211_PROACTIVE_PREQ_WITH_PREP: + flags |= IEEE80211_PREQ_PROACTIVE_PREP_FLAG; + case IEEE80211_PROACTIVE_PREQ_NO_PREP: + interval = ifmsh->mshcfg.dot11MeshHWMPactivePathToRootTimeout; + target_flags |= IEEE80211_PREQ_TO_FLAG | + IEEE80211_PREQ_USN_FLAG; + mesh_path_sel_frame_tx(MPATH_PREQ, flags, sdata->vif.addr, + cpu_to_le32(++ifmsh->sn), target_flags, + (u8 *) broadcast_addr, 0, broadcast_addr, + 0, ifmsh->mshcfg.element_ttl, + cpu_to_le32(interval), + 0, cpu_to_le32(ifmsh->preq_id++), sdata); + break; + default: + mhwmp_dbg("Proactive mechanism not supported"); + return; + } } -- cgit v1.2.3 From 1afc56794e03229fa53cfa3c5012704d226e1dec Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Jun 2012 12:11:50 +0200 Subject: netfilter: nf_ct_helper: implement variable length helper private data This patch uses the new variable length conntrack extensions. Instead of using union nf_conntrack_help that contain all the helper private data information, we allocate variable length area to store the private helper data. This patch includes the modification of all existing helpers. It also includes a couple of include header to avoid compilation warnings. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_sip.h | 2 ++ include/net/netfilter/nf_conntrack.h | 35 ++--------------------- include/net/netfilter/nf_conntrack_helper.h | 15 +++++++++- net/ipv4/netfilter/nf_nat_amanda.c | 4 +-- net/ipv4/netfilter/nf_nat_h323.c | 8 +++--- net/ipv4/netfilter/nf_nat_pptp.c | 6 ++-- net/ipv4/netfilter/nf_nat_tftp.c | 4 +-- net/netfilter/nf_conntrack_core.c | 3 +- net/netfilter/nf_conntrack_ftp.c | 3 +- net/netfilter/nf_conntrack_h323_main.c | 16 +++++++---- net/netfilter/nf_conntrack_helper.c | 11 +++++--- net/netfilter/nf_conntrack_netlink.c | 4 +-- net/netfilter/nf_conntrack_pptp.c | 17 +++++------ net/netfilter/nf_conntrack_proto_gre.c | 16 +++++------ net/netfilter/nf_conntrack_sane.c | 4 +-- net/netfilter/nf_conntrack_sip.c | 25 ++++++++-------- net/netfilter/xt_CT.c | 44 +++++++++++++++++------------ 17 files changed, 111 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 0ce91d56a5f2..0dfc8b7210a3 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -2,6 +2,8 @@ #define __NF_CONNTRACK_SIP_H__ #ifdef __KERNEL__ +#include + #define SIP_PORT 5060 #define SIP_TIMEOUT 3600 diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cce7f6a798bf..f1494feba79f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -39,36 +39,6 @@ union nf_conntrack_expect_proto { /* insert expect proto private data here */ }; -/* Add protocol helper include file here */ -#include -#include -#include -#include -#include - -/* per conntrack: application helper private data */ -union nf_conntrack_help { - /* insert conntrack helper private data (master) here */ -#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) - struct nf_ct_ftp_master ct_ftp_info; -#endif -#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ - defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) - struct nf_ct_pptp_master ct_pptp_info; -#endif -#if defined(CONFIG_NF_CONNTRACK_H323) || \ - defined(CONFIG_NF_CONNTRACK_H323_MODULE) - struct nf_ct_h323_master ct_h323_info; -#endif -#if defined(CONFIG_NF_CONNTRACK_SANE) || \ - defined(CONFIG_NF_CONNTRACK_SANE_MODULE) - struct nf_ct_sane_master ct_sane_info; -#endif -#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) - struct nf_ct_sip_master ct_sip_info; -#endif -}; - #include #include #include @@ -89,12 +59,13 @@ struct nf_conn_help { /* Helper. if any */ struct nf_conntrack_helper __rcu *helper; - union nf_conntrack_help help; - struct hlist_head expectations; /* Current number of expected connections */ u8 expecting[NF_CT_MAX_EXPECT_CLASSES]; + + /* private helper information. */ + char data[]; }; #include diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 5f5a4d9d4df5..061352f71a84 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -11,6 +11,7 @@ #define _NF_CONNTRACK_HELPER_H #include #include +#include struct module; @@ -23,6 +24,9 @@ struct nf_conntrack_helper { struct module *me; /* pointer to self */ const struct nf_conntrack_expect_policy *expect_policy; + /* length of internal data, ie. sizeof(struct nf_ct_*_master) */ + size_t data_len; + /* Tuple of things we will help (compared against server response) */ struct nf_conntrack_tuple tuple; @@ -48,7 +52,7 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum); extern int nf_conntrack_helper_register(struct nf_conntrack_helper *); extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); -extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); +extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp); extern int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags); @@ -60,6 +64,15 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) return nf_ct_ext_find(ct, NF_CT_EXT_HELPER); } +static inline void *nfct_help_data(const struct nf_conn *ct) +{ + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + + return (void *)help->data; +} + extern int nf_conntrack_helper_init(struct net *net); extern void nf_conntrack_helper_fini(struct net *net); diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 7b22382ff0e9..3c04d24e2976 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -13,10 +13,10 @@ #include #include -#include -#include #include #include +#include +#include #include MODULE_AUTHOR("Brian J. Murrell "); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index cad29c121318..c6784a18c1c4 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -95,7 +95,7 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int count) { - const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + const struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int i; __be16 port; @@ -178,7 +178,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int i; u_int16_t nated_port; @@ -330,7 +330,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); u_int16_t nated_port = ntohs(port); @@ -419,7 +419,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); u_int16_t nated_port = ntohs(port); union nf_inet_addr addr; diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index c273d58980ae..388140881ebe 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -49,7 +49,7 @@ static void pptp_nat_expected(struct nf_conn *ct, const struct nf_nat_pptp *nat_pptp_info; struct nf_nat_ipv4_range range; - ct_pptp_info = &nfct_help(master)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(master); nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info; /* And here goes the grand finale of corrosion... */ @@ -123,7 +123,7 @@ pptp_outbound_pkt(struct sk_buff *skb, __be16 new_callid; unsigned int cid_off; - ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(ct); nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info; new_callid = ct_pptp_info->pns_call_id; @@ -192,7 +192,7 @@ pptp_exp_gre(struct nf_conntrack_expect *expect_orig, struct nf_ct_pptp_master *ct_pptp_info; struct nf_nat_pptp *nat_pptp_info; - ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info; + ct_pptp_info = nfct_help_data(ct); nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info; /* save original PAC call ID in nat_info */ diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index a2901bf829c0..9dbb8d284f99 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -8,10 +8,10 @@ #include #include -#include -#include #include #include +#include +#include #include MODULE_AUTHOR("Magnus Boden "); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 1ee2082b81b5..cf4875565d67 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -819,7 +819,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = exp->master; if (exp->helper) { - help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, exp->helper, + GFP_ATOMIC); if (help) rcu_assign_pointer(help->helper, exp->helper); } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 44e47c9e14fb..4bb771d1f57a 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -358,7 +358,7 @@ static int help(struct sk_buff *skb, u32 seq; int dir = CTINFO2DIR(ctinfo); unsigned int uninitialized_var(matchlen), uninitialized_var(matchoff); - struct nf_ct_ftp_master *ct_ftp_info = &nfct_help(ct)->help.ct_ftp_info; + struct nf_ct_ftp_master *ct_ftp_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; union nf_inet_addr *daddr; struct nf_conntrack_man cmd = {}; @@ -554,6 +554,7 @@ static int __init nf_conntrack_ftp_init(void) ftp[i][0].tuple.src.l3num = PF_INET; ftp[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { + ftp[i][j].data_len = sizeof(struct nf_ct_ftp_master); ftp[i][j].tuple.src.u.tcp.port = htons(ports[i]); ftp[i][j].tuple.dst.protonum = IPPROTO_TCP; ftp[i][j].expect_policy = &ftp_exp_policy; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 46d69d7f1bb4..ed2199280527 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -114,7 +114,7 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, int *datalen, int *dataoff) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); const struct tcphdr *th; struct tcphdr _tcph; @@ -618,6 +618,7 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = { static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = { .name = "H.245", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_UNSPEC, .tuple.dst.protonum = IPPROTO_UDP, .help = h245_help, @@ -1170,6 +1171,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_q931[] __read_mostly = { { .name = "Q.931", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET, .tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT), .tuple.dst.protonum = IPPROTO_TCP, @@ -1245,7 +1247,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, unsigned char **data, TransportAddress *taddr, int count) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret = 0; int i; @@ -1360,7 +1362,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, RegistrationRequest *rrq) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int ret; typeof(set_ras_addr_hook) set_ras_addr; @@ -1395,7 +1397,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, RegistrationConfirm *rcf) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret; struct nf_conntrack_expect *exp; @@ -1444,7 +1446,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, UnregistrationRequest *urq) { - struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); int ret; typeof(set_sig_addr_hook) set_sig_addr; @@ -1476,7 +1478,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned char **data, AdmissionRequest *arq) { - const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info; + const struct nf_ct_h323_master *info = nfct_help_data(ct); int dir = CTINFO2DIR(ctinfo); __be16 port; union nf_inet_addr addr; @@ -1743,6 +1745,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { { .name = "RAS", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET, .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT), .tuple.dst.protonum = IPPROTO_UDP, @@ -1752,6 +1755,7 @@ static struct nf_conntrack_helper nf_conntrack_helper_ras[] __read_mostly = { { .name = "RAS", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_h323_master), .tuple.src.l3num = AF_INET6, .tuple.src.u.udp.port = cpu_to_be16(RAS_PORT), .tuple.dst.protonum = IPPROTO_UDP, diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 4fa2ff961f5a..9c18ecb0ab81 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -161,11 +161,14 @@ nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); -struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) +struct nf_conn_help * +nf_ct_helper_ext_add(struct nf_conn *ct, + struct nf_conntrack_helper *helper, gfp_t gfp) { struct nf_conn_help *help; - help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp); + help = nf_ct_ext_add_length(ct, NF_CT_EXT_HELPER, + helper->data_len, gfp); if (help) INIT_HLIST_HEAD(&help->expectations); else @@ -218,13 +221,13 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } if (help == NULL) { - help = nf_ct_helper_ext_add(ct, flags); + help = nf_ct_helper_ext_add(ct, helper, flags); if (help == NULL) { ret = -ENOMEM; goto out; } } else { - memset(&help->help, 0, sizeof(help->help)); + memset(help->data, 0, helper->data_len); } rcu_assign_pointer(help->helper, helper); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6f4b00a8fc73..a08892048b46 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1218,7 +1218,7 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) if (help->helper) return -EBUSY; /* need to zero data of old helper */ - memset(&help->help, 0, sizeof(help->help)); + memset(help->data, 0, help->helper->data_len); } else { /* we cannot set a helper for an existing conntrack */ return -EOPNOTSUPP; @@ -1440,7 +1440,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } else { struct nf_conn_help *help; - help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + help = nf_ct_helper_ext_add(ct, helper, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 31d56b23b9e9..6fed9ec35248 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -174,7 +174,7 @@ static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct, static void pptp_destroy_siblings(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - const struct nf_conn_help *help = nfct_help(ct); + const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_conntrack_tuple t; nf_ct_gre_keymap_destroy(ct); @@ -182,16 +182,16 @@ static void pptp_destroy_siblings(struct nf_conn *ct) /* try original (pns->pac) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = help->help.ct_pptp_info.pns_call_id; - t.dst.u.gre.key = help->help.ct_pptp_info.pac_call_id; + t.src.u.gre.key = ct_pptp_info->pns_call_id; + t.dst.u.gre.key = ct_pptp_info->pac_call_id; if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout original pns->pac ct/exp\n"); /* try reply (pac->pns) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = help->help.ct_pptp_info.pac_call_id; - t.dst.u.gre.key = help->help.ct_pptp_info.pns_call_id; + t.src.u.gre.key = ct_pptp_info->pac_call_id; + t.dst.u.gre.key = ct_pptp_info->pns_call_id; if (!destroy_sibling_or_exp(net, ct, &t)) pr_debug("failed to timeout reply pac->pns ct/exp\n"); } @@ -269,7 +269,7 @@ pptp_inbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + struct nf_ct_pptp_master *info = nfct_help_data(ct); u_int16_t msg; __be16 cid = 0, pcid = 0; typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound; @@ -396,7 +396,7 @@ pptp_outbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + struct nf_ct_pptp_master *info = nfct_help_data(ct); u_int16_t msg; __be16 cid = 0, pcid = 0; typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound; @@ -506,7 +506,7 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, { int dir = CTINFO2DIR(ctinfo); - const struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info; + const struct nf_ct_pptp_master *info = nfct_help_data(ct); const struct tcphdr *tcph; struct tcphdr _tcph; const struct pptp_pkt_hdr *pptph; @@ -592,6 +592,7 @@ static const struct nf_conntrack_expect_policy pptp_exp_policy = { static struct nf_conntrack_helper pptp __read_mostly = { .name = "pptp", .me = THIS_MODULE, + .data_len = sizeof(struct nf_ct_pptp_master), .tuple.src.l3num = AF_INET, .tuple.src.u.tcp.port = cpu_to_be16(PPTP_CONTROL_PORT), .tuple.dst.protonum = IPPROTO_TCP, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 25ba5a2f5edc..5cac41c2fa09 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -117,10 +117,10 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, { struct net *net = nf_ct_net(ct); struct netns_proto_gre *net_gre = gre_pernet(net); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_ct_gre_keymap **kmp, *km; - kmp = &help->help.ct_pptp_info.keymap[dir]; + kmp = &ct_pptp_info->keymap[dir]; if (*kmp) { /* check whether it's a retransmission */ read_lock_bh(&net_gre->keymap_lock); @@ -158,19 +158,19 @@ void nf_ct_gre_keymap_destroy(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); struct netns_proto_gre *net_gre = gre_pernet(net); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); enum ip_conntrack_dir dir; pr_debug("entering for ct %p\n", ct); write_lock_bh(&net_gre->keymap_lock); for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) { - if (help->help.ct_pptp_info.keymap[dir]) { + if (ct_pptp_info->keymap[dir]) { pr_debug("removing %p from list\n", - help->help.ct_pptp_info.keymap[dir]); - list_del(&help->help.ct_pptp_info.keymap[dir]->list); - kfree(help->help.ct_pptp_info.keymap[dir]); - help->help.ct_pptp_info.keymap[dir] = NULL; + ct_pptp_info->keymap[dir]); + list_del(&ct_pptp_info->keymap[dir]->list); + kfree(ct_pptp_info->keymap[dir]); + ct_pptp_info->keymap[dir] = NULL; } } write_unlock_bh(&net_gre->keymap_lock); diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index ec3fc18c4ef6..295429f39088 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -69,13 +69,12 @@ static int help(struct sk_buff *skb, void *sb_ptr; int ret = NF_ACCEPT; int dir = CTINFO2DIR(ctinfo); - struct nf_ct_sane_master *ct_sane_info; + struct nf_ct_sane_master *ct_sane_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; struct nf_conntrack_tuple *tuple; struct sane_request *req; struct sane_reply_net_start *reply; - ct_sane_info = &nfct_help(ct)->help.ct_sane_info; /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) @@ -203,6 +202,7 @@ static int __init nf_conntrack_sane_init(void) sane[i][0].tuple.src.l3num = PF_INET; sane[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { + sane[i][j].data_len = sizeof(struct nf_ct_sane_master); sane[i][j].tuple.src.u.tcp.port = htons(ports[i]); sane[i][j].tuple.dst.protonum = IPPROTO_TCP; sane[i][j].expect_policy = &sane_exp_policy; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index dfd3ff382243..758a1bacc126 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1075,12 +1075,12 @@ static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1091,12 +1091,12 @@ static int process_update_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1107,12 +1107,12 @@ static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) return process_sdp(skb, dataoff, dptr, datalen, cseq); - else if (help->help.ct_sip_info.invite_cseq == cseq) + else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } @@ -1123,13 +1123,13 @@ static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); unsigned int ret; flush_expectations(ct, true); ret = process_sdp(skb, dataoff, dptr, datalen, cseq); if (ret == NF_ACCEPT) - help->help.ct_sip_info.invite_cseq = cseq; + ct_sip_info->invite_cseq = cseq; return ret; } @@ -1154,7 +1154,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int matchoff, matchlen; struct nf_conntrack_expect *exp; @@ -1235,7 +1235,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, store_cseq: if (ret == NF_ACCEPT) - help->help.ct_sip_info.register_cseq = cseq; + ct_sip_info->register_cseq = cseq; return ret; } @@ -1245,7 +1245,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct nf_conn_help *help = nfct_help(ct); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); union nf_inet_addr addr; __be16 port; @@ -1262,7 +1262,7 @@ static int process_register_response(struct sk_buff *skb, unsigned int dataoff, * responses, so we store the sequence number of the last valid * request and compare it here. */ - if (help->help.ct_sip_info.register_cseq != cseq) + if (ct_sip_info->register_cseq != cseq) return NF_ACCEPT; if (code >= 100 && code <= 199) @@ -1578,6 +1578,7 @@ static int __init nf_conntrack_sip_init(void) sip[i][3].help = sip_help_tcp; for (j = 0; j < ARRAY_SIZE(sip[i]); j++) { + sip[i][j].data_len = sizeof(struct nf_ct_sip_master); sip[i][j].tuple.src.u.udp.port = htons(ports[i]); sip[i][j].expect_policy = sip_exp_policy; sip[i][j].expect_class_max = SIP_EXPECT_MAX; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index a51de9b052be..116018560c60 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -112,6 +112,8 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { + struct nf_conntrack_helper *helper; + ret = -ENOENT; proto = xt_ct_find_proto(par); if (!proto) { @@ -120,19 +122,21 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) goto err3; } - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) - goto err3; - ret = -ENOENT; - help->helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (help->helper == NULL) { + helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (helper == NULL) { pr_info("No such helper \"%s\"\n", info->helper); goto err3; } + + ret = -ENOMEM; + help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + if (help == NULL) + goto err3; + + help->helper = helper; } __set_bit(IPS_TEMPLATE_BIT, &ct->status); @@ -202,6 +206,8 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err3; if (info->helper[0]) { + struct nf_conntrack_helper *helper; + ret = -ENOENT; proto = xt_ct_find_proto(par); if (!proto) { @@ -210,19 +216,21 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) goto err3; } - ret = -ENOMEM; - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) - goto err3; - ret = -ENOENT; - help->helper = nf_conntrack_helper_try_module_get(info->helper, - par->family, - proto); - if (help->helper == NULL) { + helper = nf_conntrack_helper_try_module_get(info->helper, + par->family, + proto); + if (helper == NULL) { pr_info("No such helper \"%s\"\n", info->helper); goto err3; } + + ret = -ENOMEM; + help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL); + if (help == NULL) + goto err3; + + help->helper = helper; } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -- cgit v1.2.3 From 9cb0176654a7dc33a32af8a0bc9e0b2f9f9ebb0f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Jun 2012 12:13:39 +0200 Subject: netfilter: add glue code to integrate nfnetlink_queue and ctnetlink This patch allows you to include the conntrack information together with the packet that is sent to user-space via NFQUEUE. Previously, there was no integration between ctnetlink and nfnetlink_queue. If you wanted to access conntrack information from your libnetfilter_queue program, you required to query ctnetlink from user-space to obtain it. Thus, delaying the packet processing even more. Including the conntrack information is optional, you can set it via NFQA_CFG_F_CONNTRACK flag with the new NFQA_CFG_FLAGS attribute. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 10 +++ include/linux/netfilter/nfnetlink_queue.h | 3 + net/netfilter/core.c | 4 + net/netfilter/nf_conntrack_netlink.c | 144 +++++++++++++++++++++++++++++- net/netfilter/nfnetlink_queue.c | 48 ++++++++++ 5 files changed, 208 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 4541f33dbfc3..ba65bfbd7f74 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -393,6 +393,16 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; + +struct nf_conn; +struct nlattr; + +struct nfq_ct_hook { + size_t (*build_size)(const struct nf_conn *ct); + int (*build)(struct sk_buff *skb, struct nf_conn *ct); + int (*parse)(const struct nlattr *attr, struct nf_conn *ct); +}; +extern struct nfq_ct_hook *nfq_ct_hook; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index a6c1ddac05cc..e0d8fd8d4d24 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -42,6 +42,8 @@ enum nfqnl_attr_type { NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */ NFQA_HWADDR, /* nfqnl_msg_packet_hw */ NFQA_PAYLOAD, /* opaque data payload */ + NFQA_CT, /* nf_conntrack_netlink.h */ + NFQA_CT_INFO, /* enum ip_conntrack_info */ __NFQA_MAX }; @@ -92,5 +94,6 @@ enum nfqnl_attr_config { /* Flags for NFQA_CFG_FLAGS */ #define NFQA_CFG_F_FAIL_OPEN (1 << 0) +#define NFQA_CFG_F_CONNTRACK (1 << 1) #endif /* _NFNETLINK_QUEUE_H */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index e19f3653db23..7eef8453b909 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -264,6 +264,10 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) rcu_read_unlock(); } EXPORT_SYMBOL(nf_conntrack_destroy); + +struct nfq_ct_hook *nfq_ct_hook; +EXPORT_SYMBOL_GPL(nfq_ct_hook); + #endif /* CONFIG_NF_CONNTRACK */ #ifdef CONFIG_PROC_FS diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a08892048b46..d304d5917950 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1620,6 +1620,140 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } +#if defined(CONFIG_NETFILTER_NETLINK_QUEUE) || \ + defined(CONFIG_NETFILTER_NETLINK_QUEUE_MODULE) +static size_t +ctnetlink_nfqueue_build_size(const struct nf_conn *ct) +{ + return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + + nla_total_size(0) /* CTA_PROTOINFO */ + + nla_total_size(0) /* CTA_HELP */ + + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + + ctnetlink_secctx_size(ct) +#ifdef CONFIG_NF_NAT_NEEDED + + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ +#endif +#ifdef CONFIG_NF_CONNTRACK_MARK + + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ +#endif + + ctnetlink_proto_size(ct) + ; +} + +static int +ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) +{ + struct nlattr *nest_parms; + + rcu_read_lock(); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest_parms); + + nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest_parms); + + if (nf_ct_zone(ct)) { + if (nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + goto nla_put_failure; + } + + if (ctnetlink_dump_id(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_status(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_timeout(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_protoinfo(skb, ct) < 0) + goto nla_put_failure; + + if (ctnetlink_dump_helpinfo(skb, ct) < 0) + goto nla_put_failure; + +#ifdef CONFIG_NF_CONNTRACK_SECMARK + if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) + goto nla_put_failure; +#endif + if (ct->master && ctnetlink_dump_master(skb, ct) < 0) + goto nla_put_failure; + + if ((ct->status & IPS_SEQ_ADJUST) && + ctnetlink_dump_nat_seq_adj(skb, ct) < 0) + goto nla_put_failure; + +#ifdef CONFIG_NF_CONNTRACK_MARK + if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + goto nla_put_failure; +#endif + rcu_read_unlock(); + return 0; + +nla_put_failure: + rcu_read_unlock(); + return -ENOSPC; +} + +static int +ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) +{ + int err; + + if (cda[CTA_TIMEOUT]) { + err = ctnetlink_change_timeout(ct, cda); + if (err < 0) + return err; + } + if (cda[CTA_STATUS]) { + err = ctnetlink_change_status(ct, cda); + if (err < 0) + return err; + } + if (cda[CTA_HELP]) { + err = ctnetlink_change_helper(ct, cda); + if (err < 0) + return err; + } +#if defined(CONFIG_NF_CONNTRACK_MARK) + if (cda[CTA_MARK]) + ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); +#endif + return 0; +} + +static int +ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) +{ + struct nlattr *cda[CTA_MAX+1]; + + nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy); + + return ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); +} + +static struct nfq_ct_hook ctnetlink_nfqueue_hook = { + .build_size = ctnetlink_nfqueue_build_size, + .build = ctnetlink_nfqueue_build, + .parse = ctnetlink_nfqueue_parse, +}; +#endif /* CONFIG_NETFILTER_NETLINK_QUEUE */ + /*********************************************************************** * EXPECT ***********************************************************************/ @@ -2424,7 +2558,11 @@ static int __init ctnetlink_init(void) pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } - +#if defined(CONFIG_NETFILTER_NETLINK_QUEUE) || \ + defined(CONFIG_NETFILTER_NETLINK_QUEUE_MODULE) + /* setup interaction between nf_queue and nf_conntrack_netlink. */ + RCU_INIT_POINTER(nfq_ct_hook, &ctnetlink_nfqueue_hook); +#endif return 0; err_unreg_exp_subsys: @@ -2442,6 +2580,10 @@ static void __exit ctnetlink_exit(void) unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); +#if defined(CONFIG_NETFILTER_NETLINK_QUEUE) || \ + defined(CONFIG_NETFILTER_NETLINK_QUEUE_MODULE) + RCU_INIT_POINTER(nfq_ct_hook, NULL); +#endif } module_init(ctnetlink_init); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 630da3d2c62a..647923ae9230 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -30,6 +30,7 @@ #include #include #include +#include #include @@ -233,6 +234,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; + struct nfq_ct_hook *nfq_ct; + struct nf_conn *ct = NULL; + enum ip_conntrack_info uninitialized_var(ctinfo); size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) @@ -266,6 +270,17 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, break; } + /* rcu_read_lock()ed by __nf_queue already. */ + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct != NULL && (queue->flags & NFQA_CFG_F_CONNTRACK)) { + ct = nf_ct_get(entskb, &ctinfo); + if (ct) { + if (!nf_ct_is_untracked(ct)) + size += nfq_ct->build_size(ct); + else + ct = NULL; + } + } skb = alloc_skb(size, GFP_ATOMIC); if (!skb) @@ -389,6 +404,24 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, BUG(); } + if (ct) { + struct nlattr *nest_parms; + u_int32_t tmp; + + nest_parms = nla_nest_start(skb, NFQA_CT | NLA_F_NESTED); + if (!nest_parms) + goto nla_put_failure; + + if (nfq_ct->build(skb, ct) < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + + tmp = ctinfo; + if (nla_put_u32(skb, NFQA_CT_INFO, htonl(ctinfo))) + goto nla_put_failure; + } + nlh->nlmsg_len = skb->tail - old_tail; return skb; @@ -632,6 +665,7 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, + [NFQA_CT] = { .type = NLA_UNSPEC }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { @@ -732,6 +766,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, struct nfqnl_instance *queue; unsigned int verdict; struct nf_queue_entry *entry; + struct nfq_ct_hook *nfq_ct; queue = instance_lookup(queue_num); if (!queue) @@ -750,6 +785,19 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, if (entry == NULL) return -ENOENT; + rcu_read_lock(); + nfq_ct = rcu_dereference(nfq_ct_hook); + if (nfq_ct != NULL && + (queue->flags & NFQA_CFG_F_CONNTRACK) && nfqa[NFQA_CT]) { + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(entry->skb, &ctinfo); + if (ct && !nf_ct_is_untracked(ct)) + nfq_ct->parse(nfqa[NFQA_CT], ct); + } + rcu_read_unlock(); + if (nfqa[NFQA_PAYLOAD]) { if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), nla_len(nfqa[NFQA_PAYLOAD]), entry) < 0) -- cgit v1.2.3 From 8c88f87cb27ad09086940bdd3e6955e5325ec89a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Jun 2012 13:31:25 +0200 Subject: netfilter: nfnetlink_queue: add NAT TCP sequence adjustment if packet mangled User-space programs that receive traffic via NFQUEUE may mangle packets. If NAT is enabled, this usually puzzles sequence tracking, leading to traffic disruptions. With this patch, nfnl_queue will make the corresponding NAT TCP sequence adjustment if: 1) The packet has been mangled, 2) the NFQA_CFG_F_CONNTRACK flag has been set, and 3) NAT is detected. There are some records on the Internet complaning about this issue: http://stackoverflow.com/questions/260757/packet-mangling-utilities-besides-iptables By now, we only support TCP since we have no helpers for DCCP or SCTP. Better to add this if we ever have some helper over those layer 4 protocols. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 ++ include/net/netfilter/nf_nat_helper.h | 4 ++++ net/ipv4/netfilter/nf_nat_helper.c | 13 +++++++++++++ net/netfilter/nf_conntrack_netlink.c | 4 ++++ net/netfilter/nfnetlink_queue.c | 19 +++++++++++-------- 5 files changed, 34 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ba65bfbd7f74..dca19e61b30a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -401,6 +401,8 @@ struct nfq_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); + void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off); }; extern struct nfq_ct_hook *nfq_ct_hook; #else diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 02bb6c29dc3d..7d8fb7b46c44 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -54,4 +54,8 @@ extern void nf_nat_follow_master(struct nf_conn *ct, extern s16 nf_nat_get_offset(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); + +extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 dir, int off); + #endif diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index af65958f6308..2e59ad0b90ca 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -153,6 +153,19 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); +void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); + static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data, int datalen, __sum16 *check, int oldlen) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d304d5917950..8be0ab9b4758 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -46,6 +46,7 @@ #ifdef CONFIG_NF_NAT_NEEDED #include #include +#include #endif #include @@ -1751,6 +1752,9 @@ static struct nfq_ct_hook ctnetlink_nfqueue_hook = { .build_size = ctnetlink_nfqueue_build_size, .build = ctnetlink_nfqueue_build, .parse = ctnetlink_nfqueue_parse, +#ifdef CONFIG_NF_NAT_NEEDED + .seq_adjust = nf_nat_tcp_seq_adjust, +#endif }; #endif /* CONFIG_NETFILTER_NETLINK_QUEUE */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 647923ae9230..ff82c7933dfd 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -502,12 +502,10 @@ err_out: } static int -nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e) +nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; - int diff; - diff = data_len - e->skb->len; if (diff < 0) { if (pskb_trim(e->skb, data_len)) return -ENOMEM; @@ -767,6 +765,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, unsigned int verdict; struct nf_queue_entry *entry; struct nfq_ct_hook *nfq_ct; + enum ip_conntrack_info uninitialized_var(ctinfo); + struct nf_conn *ct = NULL; queue = instance_lookup(queue_num); if (!queue) @@ -789,20 +789,23 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, nfq_ct = rcu_dereference(nfq_ct_hook); if (nfq_ct != NULL && (queue->flags & NFQA_CFG_F_CONNTRACK) && nfqa[NFQA_CT]) { - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - ct = nf_ct_get(entry->skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) nfq_ct->parse(nfqa[NFQA_CT], ct); } - rcu_read_unlock(); if (nfqa[NFQA_PAYLOAD]) { + u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); + int diff = payload_len - entry->skb->len; + if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), - nla_len(nfqa[NFQA_PAYLOAD]), entry) < 0) + payload_len, entry, diff) < 0) verdict = NF_DROP; + + if (ct && (ct->status & IPS_NAT_MASK) && diff) + nfq_ct->seq_adjust(skb, ct, ctinfo, diff); } + rcu_read_unlock(); if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); -- cgit v1.2.3 From ae243bee397102c51fbf9db440eca3b077e0e702 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Jun 2012 14:19:42 +0200 Subject: netfilter: ctnetlink: add CTA_HELP_INFO attribute This attribute can be used to modify and to dump the internal protocol information. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_conntrack.h | 1 + include/net/netfilter/nf_conntrack_helper.h | 1 + net/netfilter/nf_conntrack_netlink.c | 23 ++++++++++++++++++----- 3 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index e58e4b93c108..768883370080 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -191,6 +191,7 @@ enum ctattr_expect_nat { enum ctattr_help { CTA_HELP_UNSPEC, CTA_HELP_NAME, + CTA_HELP_INFO, __CTA_HELP_MAX }; #define CTA_HELP_MAX (__CTA_HELP_MAX - 1) diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 061352f71a84..84b24c3a3834 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -39,6 +39,7 @@ struct nf_conntrack_helper { void (*destroy)(struct nf_conn *ct); + int (*from_nlattr)(struct nlattr *attr, struct nf_conn *ct); int (*to_nlattr)(struct sk_buff *skb, const struct nf_conn *ct); unsigned int expect_class_max; }; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 8be0ab9b4758..ae156dff4887 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -902,7 +902,8 @@ static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { }; static inline int -ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) +ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, + struct nlattr **helpinfo) { struct nlattr *tb[CTA_HELP_MAX+1]; @@ -913,6 +914,9 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name) *helper_name = nla_data(tb[CTA_HELP_NAME]); + if (tb[CTA_HELP_INFO]) + *helpinfo = tb[CTA_HELP_INFO]; + return 0; } @@ -1173,13 +1177,14 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; + struct nlattr *helpinfo = NULL; int err; /* don't change helper of sibling connections */ if (ct->master) return -EBUSY; - err = ctnetlink_parse_help(cda[CTA_HELP], &helpname); + err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; @@ -1214,8 +1219,12 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) } if (help) { - if (help->helper == helper) + if (help->helper == helper) { + /* update private helper data if allowed. */ + if (helper->from_nlattr && helpinfo) + helper->from_nlattr(helpinfo, ct); return 0; + } if (help->helper) return -EBUSY; /* need to zero data of old helper */ @@ -1411,8 +1420,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; - - err = ctnetlink_parse_help(cda[CTA_HELP], &helpname); + struct nlattr *helpinfo = NULL; + + err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; @@ -1446,6 +1456,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, err = -ENOMEM; goto err2; } + /* set private helper data if allowed. */ + if (helper->from_nlattr && helpinfo) + helper->from_nlattr(helpinfo, ct); /* not in hash table yet so not strictly necessary */ RCU_INIT_POINTER(help->helper, helper); -- cgit v1.2.3 From 12f7a505331e6b2754684b509f2ac8f0011ce644 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 13 May 2012 21:44:54 +0200 Subject: netfilter: add user-space connection tracking helper infrastructure There are good reasons to supports helpers in user-space instead: * Rapid connection tracking helper development, as developing code in user-space is usually faster. * Reliability: A buggy helper does not crash the kernel. Moreover, we can monitor the helper process and restart it in case of problems. * Security: Avoid complex string matching and mangling in kernel-space running in privileged mode. Going further, we can even think about running user-space helpers as a non-root process. * Extensibility: It allows the development of very specific helpers (most likely non-standard proprietary protocols) that are very likely not to be accepted for mainline inclusion in the form of kernel-space connection tracking helpers. This patch adds the infrastructure to allow the implementation of user-space conntrack helpers by means of the new nfnetlink subsystem `nfnetlink_cthelper' and the existing queueing infrastructure (nfnetlink_queue). I had to add the new hook NF_IP6_PRI_CONNTRACK_HELPER to register ipv[4|6]_helper which results from splitting ipv[4|6]_confirm into two pieces. This change is required not to break NAT sequence adjustment and conntrack confirmation for traffic that is enqueued to our user-space conntrack helpers. Basic operation, in a few steps: 1) Register user-space helper by means of `nfct': nfct helper add ftp inet tcp [ It must be a valid existing helper supported by conntrack-tools ] 2) Add rules to enable the FTP user-space helper which is used to track traffic going to TCP port 21. For locally generated packets: iptables -I OUTPUT -t raw -p tcp --dport 21 -j CT --helper ftp For non-locally generated packets: iptables -I PREROUTING -t raw -p tcp --dport 21 -j CT --helper ftp 3) Run the test conntrackd in helper mode (see example files under doc/helper/conntrackd.conf conntrackd 4) Generate FTP traffic going, if everything is OK, then conntrackd should create expectations (you can check that with `conntrack': conntrack -E expect [NEW] 301 proto=6 src=192.168.1.136 dst=130.89.148.12 sport=0 dport=54037 mask-src=255.255.255.255 mask-dst=255.255.255.255 sport=0 dport=65535 master-src=192.168.1.136 master-dst=130.89.148.12 sport=57127 dport=21 class=0 helper=ftp [DESTROY] 301 proto=6 src=192.168.1.136 dst=130.89.148.12 sport=0 dport=54037 mask-src=255.255.255.255 mask-dst=255.255.255.255 sport=0 dport=65535 master-src=192.168.1.136 master-dst=130.89.148.12 sport=57127 dport=21 class=0 helper=ftp This confirms that our test helper is receiving packets including the conntrack information, and adding expectations in kernel-space. The user-space helper can also store its private tracking information in the conntrack structure in the kernel via the CTA_HELP_INFO. The kernel will consider this a binary blob whose layout is unknown. This information will be included in the information that is transfered to user-space via glue code that integrates nfnetlink_queue and ctnetlink. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/nfnetlink.h | 3 +- include/linux/netfilter/nfnetlink_cthelper.h | 55 ++ include/linux/netfilter_ipv4.h | 1 + include/linux/netfilter_ipv6.h | 1 + include/net/netfilter/nf_conntrack_helper.h | 11 + net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 48 +- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 43 +- net/netfilter/Kconfig | 8 + net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_helper.c | 21 +- net/netfilter/nfnetlink_cthelper.c | 672 +++++++++++++++++++++++++ 12 files changed, 839 insertions(+), 26 deletions(-) create mode 100644 include/linux/netfilter/nfnetlink_cthelper.h create mode 100644 net/netfilter/nfnetlink_cthelper.c (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 1697036336b6..874ae8f2706b 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -10,6 +10,7 @@ header-y += nfnetlink.h header-y += nfnetlink_acct.h header-y += nfnetlink_compat.h header-y += nfnetlink_conntrack.h +header-y += nfnetlink_cthelper.h header-y += nfnetlink_cttimeout.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index a1048c1587d1..18341cdb2443 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -50,7 +50,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_IPSET 6 #define NFNL_SUBSYS_ACCT 7 #define NFNL_SUBSYS_CTNETLINK_TIMEOUT 8 -#define NFNL_SUBSYS_COUNT 9 +#define NFNL_SUBSYS_CTHELPER 9 +#define NFNL_SUBSYS_COUNT 10 #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink_cthelper.h b/include/linux/netfilter/nfnetlink_cthelper.h new file mode 100644 index 000000000000..33659f6fad3e --- /dev/null +++ b/include/linux/netfilter/nfnetlink_cthelper.h @@ -0,0 +1,55 @@ +#ifndef _NFNL_CTHELPER_H_ +#define _NFNL_CTHELPER_H_ + +#define NFCT_HELPER_STATUS_DISABLED 0 +#define NFCT_HELPER_STATUS_ENABLED 1 + +enum nfnl_acct_msg_types { + NFNL_MSG_CTHELPER_NEW, + NFNL_MSG_CTHELPER_GET, + NFNL_MSG_CTHELPER_DEL, + NFNL_MSG_CTHELPER_MAX +}; + +enum nfnl_cthelper_type { + NFCTH_UNSPEC, + NFCTH_NAME, + NFCTH_TUPLE, + NFCTH_QUEUE_NUM, + NFCTH_POLICY, + NFCTH_PRIV_DATA_LEN, + NFCTH_STATUS, + __NFCTH_MAX +}; +#define NFCTH_MAX (__NFCTH_MAX - 1) + +enum nfnl_cthelper_policy_type { + NFCTH_POLICY_SET_UNSPEC, + NFCTH_POLICY_SET_NUM, + NFCTH_POLICY_SET, + NFCTH_POLICY_SET1 = NFCTH_POLICY_SET, + NFCTH_POLICY_SET2, + NFCTH_POLICY_SET3, + NFCTH_POLICY_SET4, + __NFCTH_POLICY_SET_MAX +}; +#define NFCTH_POLICY_SET_MAX (__NFCTH_POLICY_SET_MAX - 1) + +enum nfnl_cthelper_pol_type { + NFCTH_POLICY_UNSPEC, + NFCTH_POLICY_NAME, + NFCTH_POLICY_EXPECT_MAX, + NFCTH_POLICY_EXPECT_TIMEOUT, + __NFCTH_POLICY_MAX +}; +#define NFCTH_POLICY_MAX (__NFCTH_POLICY_MAX - 1) + +enum nfnl_cthelper_tuple_type { + NFCTH_TUPLE_UNSPEC, + NFCTH_TUPLE_L3PROTONUM, + NFCTH_TUPLE_L4PROTONUM, + __NFCTH_TUPLE_MAX, +}; +#define NFCTH_TUPLE_MAX (__NFCTH_TUPLE_MAX - 1) + +#endif /* _NFNL_CTHELPER_H */ diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index fa0946c549d3..e2b12801378d 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -66,6 +66,7 @@ enum nf_ip_hook_priorities { NF_IP_PRI_SECURITY = 50, NF_IP_PRI_NAT_SRC = 100, NF_IP_PRI_SELINUX_LAST = 225, + NF_IP_PRI_CONNTRACK_HELPER = 300, NF_IP_PRI_CONNTRACK_CONFIRM = INT_MAX, NF_IP_PRI_LAST = INT_MAX, }; diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 57c025127f1d..7c8a513ce7a3 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -71,6 +71,7 @@ enum nf_ip6_hook_priorities { NF_IP6_PRI_SECURITY = 50, NF_IP6_PRI_NAT_SRC = 100, NF_IP6_PRI_SELINUX_LAST = 225, + NF_IP6_PRI_CONNTRACK_HELPER = 300, NF_IP6_PRI_LAST = INT_MAX, }; diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 84b24c3a3834..9aad956d1008 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -15,6 +15,11 @@ struct module; +enum nf_ct_helper_flags { + NF_CT_HELPER_F_USERSPACE = (1 << 0), + NF_CT_HELPER_F_CONFIGURED = (1 << 1), +}; + #define NF_CT_HELPER_NAME_LEN 16 struct nf_conntrack_helper { @@ -42,6 +47,9 @@ struct nf_conntrack_helper { int (*from_nlattr)(struct nlattr *attr, struct nf_conn *ct); int (*to_nlattr)(struct sk_buff *skb, const struct nf_conn *ct); unsigned int expect_class_max; + + unsigned int flags; + unsigned int queue_num; /* For user-space helpers. */ }; extern struct nf_conntrack_helper * @@ -96,4 +104,7 @@ nf_ct_helper_expectfn_find_by_name(const char *name); struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_symbol(const void *symbol); +extern struct hlist_head *nf_ct_helper_hash; +extern unsigned int nf_ct_helper_hsize; + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index d79b961a8009..e7ff2dcab6ce 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -95,11 +95,11 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv4_confirm(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ipv4_helper(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -110,24 +110,38 @@ static unsigned int ipv4_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return NF_ACCEPT; help = nfct_help(ct); if (!help) - goto out; + return NF_ACCEPT; /* rcu_read_lock()ed by nf_hook_slow */ helper = rcu_dereference(help->helper); if (!helper) - goto out; + return NF_ACCEPT; ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), ct, ctinfo); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL, "nf_ct_%s: dropping packet", helper->name); - return ret; } + return ret; +} + +static unsigned int ipv4_confirm(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; /* adjust seqs for loopback traffic only in outgoing direction */ if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && @@ -184,6 +198,13 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK, }, + { + .hook = ipv4_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, { .hook = ipv4_confirm, .owner = THIS_MODULE, @@ -191,6 +212,13 @@ static struct nf_hook_ops ipv4_conntrack_ops[] __read_mostly = { .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, + { + .hook = ipv4_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, { .hook = ipv4_confirm, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index fca10da80ea7..4794f96cf2e0 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -143,11 +143,11 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_confirm(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int ipv6_helper(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; const struct nf_conn_help *help; @@ -161,15 +161,15 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return NF_ACCEPT; help = nfct_help(ct); if (!help) - goto out; + return NF_ACCEPT; /* rcu_read_lock()ed by nf_hook_slow */ helper = rcu_dereference(help->helper); if (!helper) - goto out; + return NF_ACCEPT; protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff); @@ -179,12 +179,19 @@ static unsigned int ipv6_confirm(unsigned int hooknum, } ret = helper->help(skb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) { nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL, "nf_ct_%s: dropping packet", helper->name); - return ret; } -out: + return ret; +} + +static unsigned int ipv6_confirm(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } @@ -253,6 +260,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK, }, + { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, { .hook = ipv6_confirm, .owner = THIS_MODULE, @@ -260,6 +274,13 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, + { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, { .hook = ipv6_confirm, .owner = THIS_MODULE, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 209c1ed43368..aae6c628991d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -12,6 +12,14 @@ tristate "Netfilter NFACCT over NFNETLINK interface" If this option is enabled, the kernel will include support for extended accounting via NFNETLINK. +config NETFILTER_NETLINK_CTHELPER +tristate "Netfilter CTHELPER over NFNETLINK interface" + depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK + help + If this option is enabled, the kernel will include support + for user-space connection tracking helpers via NFNETLINK. + config NETFILTER_NETLINK_QUEUE tristate "Netfilter NFQUEUE over NFNETLINK interface" depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 4e7960cc7b97..2f3bc0f647ba 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_NETFILTER) = netfilter.o obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o +obj-$(CONFIG_NETFILTER_NETLINK_CTHELPER) += nfnetlink_cthelper.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 9c18ecb0ab81..2918ec2e4509 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -30,8 +30,10 @@ #include static DEFINE_MUTEX(nf_ct_helper_mutex); -static struct hlist_head *nf_ct_helper_hash __read_mostly; -static unsigned int nf_ct_helper_hsize __read_mostly; +struct hlist_head *nf_ct_helper_hash __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_helper_hash); +unsigned int nf_ct_helper_hsize __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_helper_hsize); static unsigned int nf_ct_helper_count __read_mostly; static bool nf_ct_auto_assign_helper __read_mostly = true; @@ -322,6 +324,9 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { + int ret = 0; + struct nf_conntrack_helper *cur; + struct hlist_node *n; unsigned int h = helper_hash(&me->tuple); BUG_ON(me->expect_policy == NULL); @@ -329,11 +334,19 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); mutex_lock(&nf_ct_helper_mutex); + hlist_for_each_entry(cur, n, &nf_ct_helper_hash[h], hnode) { + if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 && + cur->tuple.src.l3num == me->tuple.src.l3num && + cur->tuple.dst.protonum == me->tuple.dst.protonum) { + ret = -EEXIST; + goto out; + } + } hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); nf_ct_helper_count++; +out: mutex_unlock(&nf_ct_helper_mutex); - - return 0; + return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c new file mode 100644 index 000000000000..d6836193d479 --- /dev/null +++ b/net/netfilter/nfnetlink_cthelper.c @@ -0,0 +1,672 @@ +/* + * (C) 2012 Pablo Neira Ayuso + * + * 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 (or any later at your option). + * + * This software has been sponsored by Vyatta Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso "); +MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers"); + +static int +nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + const struct nf_conn_help *help; + struct nf_conntrack_helper *helper; + + help = nfct_help(ct); + if (help == NULL) + return NF_DROP; + + /* rcu_read_lock()ed by nf_hook_slow */ + helper = rcu_dereference(help->helper); + if (helper == NULL) + return NF_DROP; + + /* This is an user-space helper not yet configured, skip. */ + if ((helper->flags & + (NF_CT_HELPER_F_USERSPACE | NF_CT_HELPER_F_CONFIGURED)) == + NF_CT_HELPER_F_USERSPACE) + return NF_ACCEPT; + + /* If the user-space helper is not available, don't block traffic. */ + return NF_QUEUE_NR(helper->queue_num) | NF_VERDICT_FLAG_QUEUE_BYPASS; +} + +static const struct nla_policy nfnl_cthelper_tuple_pol[NFCTH_TUPLE_MAX+1] = { + [NFCTH_TUPLE_L3PROTONUM] = { .type = NLA_U16, }, + [NFCTH_TUPLE_L4PROTONUM] = { .type = NLA_U8, }, +}; + +static int +nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_TUPLE_MAX+1]; + + nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol); + + if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM]) + return -EINVAL; + + tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM])); + tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]); + + return 0; +} + +static int +nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) +{ + const struct nf_conn_help *help = nfct_help(ct); + + if (help->helper->data_len == 0) + return -EINVAL; + + memcpy(&help->data, nla_data(attr), help->helper->data_len); + return 0; +} + +static int +nfnl_cthelper_to_nlattr(struct sk_buff *skb, const struct nf_conn *ct) +{ + const struct nf_conn_help *help = nfct_help(ct); + + if (help->helper->data_len && + nla_put(skb, CTA_HELP_INFO, help->helper->data_len, &help->data)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy nfnl_cthelper_expect_pol[NFCTH_POLICY_MAX+1] = { + [NFCTH_POLICY_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN-1 }, + [NFCTH_POLICY_EXPECT_MAX] = { .type = NLA_U32, }, + [NFCTH_POLICY_EXPECT_TIMEOUT] = { .type = NLA_U32, }, +}; + +static int +nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy, + const struct nlattr *attr) +{ + struct nlattr *tb[NFCTH_POLICY_MAX+1]; + + nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol); + + if (!tb[NFCTH_POLICY_NAME] || + !tb[NFCTH_POLICY_EXPECT_MAX] || + !tb[NFCTH_POLICY_EXPECT_TIMEOUT]) + return -EINVAL; + + strncpy(expect_policy->name, + nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN); + expect_policy->max_expected = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); + expect_policy->timeout = + ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT])); + + return 0; +} + +static const struct nla_policy +nfnl_cthelper_expect_policy_set[NFCTH_POLICY_SET_MAX+1] = { + [NFCTH_POLICY_SET_NUM] = { .type = NLA_U32, }, +}; + +static int +nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper, + const struct nlattr *attr) +{ + int i, ret; + struct nf_conntrack_expect_policy *expect_policy; + struct nlattr *tb[NFCTH_POLICY_SET_MAX+1]; + + nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr, + nfnl_cthelper_expect_policy_set); + + if (!tb[NFCTH_POLICY_SET_NUM]) + return -EINVAL; + + helper->expect_class_max = + ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM])); + + if (helper->expect_class_max != 0 && + helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES) + return -EOVERFLOW; + + expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) * + helper->expect_class_max, GFP_KERNEL); + if (expect_policy == NULL) + return -ENOMEM; + + for (i=0; iexpect_class_max; i++) { + if (!tb[NFCTH_POLICY_SET+i]) + goto err; + + ret = nfnl_cthelper_expect_policy(&expect_policy[i], + tb[NFCTH_POLICY_SET+i]); + if (ret < 0) + goto err; + } + helper->expect_policy = expect_policy; + return 0; +err: + kfree(expect_policy); + return -EINVAL; +} + +static int +nfnl_cthelper_create(const struct nlattr * const tb[], + struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_helper *helper; + int ret; + + if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN]) + return -EINVAL; + + helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL); + if (helper == NULL) + return -ENOMEM; + + ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]); + if (ret < 0) + goto err; + + strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); + helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); + helper->flags |= NF_CT_HELPER_F_USERSPACE; + memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple)); + + helper->me = THIS_MODULE; + helper->help = nfnl_userspace_cthelper; + helper->from_nlattr = nfnl_cthelper_from_nlattr; + helper->to_nlattr = nfnl_cthelper_to_nlattr; + + /* Default to queue number zero, this can be updated at any time. */ + if (tb[NFCTH_QUEUE_NUM]) + helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM])); + + if (tb[NFCTH_STATUS]) { + int status = ntohl(nla_get_be32(tb[NFCTH_STATUS])); + + switch(status) { + case NFCT_HELPER_STATUS_ENABLED: + helper->flags |= NF_CT_HELPER_F_CONFIGURED; + break; + case NFCT_HELPER_STATUS_DISABLED: + helper->flags &= ~NF_CT_HELPER_F_CONFIGURED; + break; + } + } + + ret = nf_conntrack_helper_register(helper); + if (ret < 0) + goto err; + + return 0; +err: + kfree(helper); + return ret; +} + +static int +nfnl_cthelper_update(const struct nlattr * const tb[], + struct nf_conntrack_helper *helper) +{ + int ret; + + if (tb[NFCTH_PRIV_DATA_LEN]) + return -EBUSY; + + if (tb[NFCTH_POLICY]) { + ret = nfnl_cthelper_parse_expect_policy(helper, + tb[NFCTH_POLICY]); + if (ret < 0) + return ret; + } + if (tb[NFCTH_QUEUE_NUM]) + helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM])); + + if (tb[NFCTH_STATUS]) { + int status = ntohl(nla_get_be32(tb[NFCTH_STATUS])); + + switch(status) { + case NFCT_HELPER_STATUS_ENABLED: + helper->flags |= NF_CT_HELPER_F_CONFIGURED; + break; + case NFCT_HELPER_STATUS_DISABLED: + helper->flags &= ~NF_CT_HELPER_F_CONFIGURED; + break; + } + } + return 0; +} + +static int +nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + const char *helper_name; + struct nf_conntrack_helper *cur, *helper = NULL; + struct nf_conntrack_tuple tuple; + struct hlist_node *n; + int ret = 0, i; + + if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) + return -EINVAL; + + helper_name = nla_data(tb[NFCTH_NAME]); + + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + rcu_read_lock(); + for (i = 0; i < nf_ct_helper_hsize && !helper; i++) { + hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) + continue; + + if ((tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + if (nlh->nlmsg_flags & NLM_F_EXCL) { + ret = -EEXIST; + goto err; + } + helper = cur; + break; + } + } + rcu_read_unlock(); + + if (helper == NULL) + ret = nfnl_cthelper_create(tb, &tuple); + else + ret = nfnl_cthelper_update(tb, helper); + + return ret; +err: + rcu_read_unlock(); + return ret; +} + +static int +nfnl_cthelper_dump_tuple(struct sk_buff *skb, + struct nf_conntrack_helper *helper) +{ + struct nlattr *nest_parms; + + nest_parms = nla_nest_start(skb, NFCTH_TUPLE | NLA_F_NESTED); + if (nest_parms == NULL) + goto nla_put_failure; + + if (nla_put_be16(skb, NFCTH_TUPLE_L3PROTONUM, + htons(helper->tuple.src.l3num))) + goto nla_put_failure; + + if (nla_put_u8(skb, NFCTH_TUPLE_L4PROTONUM, helper->tuple.dst.protonum)) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms); + return 0; + +nla_put_failure: + return -1; +} + +static int +nfnl_cthelper_dump_policy(struct sk_buff *skb, + struct nf_conntrack_helper *helper) +{ + int i; + struct nlattr *nest_parms1, *nest_parms2; + + nest_parms1 = nla_nest_start(skb, NFCTH_POLICY | NLA_F_NESTED); + if (nest_parms1 == NULL) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM, + htonl(helper->expect_class_max))) + goto nla_put_failure; + + for (i=0; iexpect_class_max; i++) { + nest_parms2 = nla_nest_start(skb, + (NFCTH_POLICY_SET+i) | NLA_F_NESTED); + if (nest_parms2 == NULL) + goto nla_put_failure; + + if (nla_put_string(skb, NFCTH_POLICY_NAME, + helper->expect_policy[i].name)) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_MAX, + htonl(helper->expect_policy[i].max_expected))) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_TIMEOUT, + htonl(helper->expect_policy[i].timeout))) + goto nla_put_failure; + + nla_nest_end(skb, nest_parms2); + } + nla_nest_end(skb, nest_parms1); + return 0; + +nla_put_failure: + return -1; +} + +static int +nfnl_cthelper_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + int event, struct nf_conntrack_helper *helper) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0; + int status; + + event |= NFNL_SUBSYS_CTHELPER << 8; + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_string(skb, NFCTH_NAME, helper->name)) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_QUEUE_NUM, htonl(helper->queue_num))) + goto nla_put_failure; + + if (nfnl_cthelper_dump_tuple(skb, helper) < 0) + goto nla_put_failure; + + if (nfnl_cthelper_dump_policy(skb, helper) < 0) + goto nla_put_failure; + + if (nla_put_be32(skb, NFCTH_PRIV_DATA_LEN, htonl(helper->data_len))) + goto nla_put_failure; + + if (helper->flags & NF_CT_HELPER_F_CONFIGURED) + status = NFCT_HELPER_STATUS_ENABLED; + else + status = NFCT_HELPER_STATUS_DISABLED; + + if (nla_put_be32(skb, NFCTH_STATUS, htonl(status))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nlmsg_failure: +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nf_conntrack_helper *cur, *last; + struct hlist_node *n; + + rcu_read_lock(); + last = (struct nf_conntrack_helper *)cb->args[1]; + for (; cb->args[0] < nf_ct_helper_hsize; cb->args[0]++) { +restart: + hlist_for_each_entry_rcu(cur, n, + &nf_ct_helper_hash[cb->args[0]], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (cb->args[1]) { + if (cur != last) + continue; + cb->args[1] = 0; + } + if (nfnl_cthelper_fill_info(skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + NFNL_MSG_CTHELPER_NEW, cur) < 0) { + cb->args[1] = (unsigned long)cur; + goto out; + } + } + } + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } +out: + rcu_read_unlock(); + return skb->len; +} + +static int +nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + int ret = -ENOENT, i; + struct nf_conntrack_helper *cur; + struct hlist_node *n; + struct sk_buff *skb2; + char *helper_name = NULL; + struct nf_conntrack_tuple tuple; + bool tuple_set = false; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = nfnl_cthelper_dump_table, + }; + return netlink_dump_start(nfnl, skb, nlh, &c); + } + + if (tb[NFCTH_NAME]) + helper_name = nla_data(tb[NFCTH_NAME]); + + if (tb[NFCTH_TUPLE]) { + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + tuple_set = true; + } + + for (i = 0; i < nf_ct_helper_hsize; i++) { + hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + if (helper_name && strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) { + continue; + } + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) { + ret = -ENOMEM; + break; + } + + ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + NFNL_MSG_CTHELPER_NEW, cur); + if (ret <= 0) { + kfree_skb(skb2); + break; + } + + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + MSG_DONTWAIT); + if (ret > 0) + ret = 0; + + /* this avoids a loop in nfnetlink. */ + return ret == -EAGAIN ? -ENOBUFS : ret; + } + } + return ret; +} + +static int +nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, const struct nlattr * const tb[]) +{ + char *helper_name = NULL; + struct nf_conntrack_helper *cur; + struct hlist_node *n, *tmp; + struct nf_conntrack_tuple tuple; + bool tuple_set = false, found = false; + int i, j = 0, ret; + + if (tb[NFCTH_NAME]) + helper_name = nla_data(tb[NFCTH_NAME]); + + if (tb[NFCTH_TUPLE]) { + ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]); + if (ret < 0) + return ret; + + tuple_set = true; + } + + for (i = 0; i < nf_ct_helper_hsize; i++) { + hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hnode) { + /* skip non-userspace conntrack helpers. */ + if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) + continue; + + j++; + + if (helper_name && strncmp(cur->name, helper_name, + NF_CT_HELPER_NAME_LEN) != 0) { + continue; + } + if (tuple_set && + (tuple.src.l3num != cur->tuple.src.l3num || + tuple.dst.protonum != cur->tuple.dst.protonum)) + continue; + + found = true; + nf_conntrack_helper_unregister(cur); + } + } + /* Make sure we return success if we flush and there is no helpers */ + return (found || j == 0) ? 0 : -ENOENT; +} + +static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { + [NFCTH_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN-1 }, + [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, +}; + +static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { + [NFNL_MSG_CTHELPER_NEW] = { .call = nfnl_cthelper_new, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, + [NFNL_MSG_CTHELPER_GET] = { .call = nfnl_cthelper_get, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, + [NFNL_MSG_CTHELPER_DEL] = { .call = nfnl_cthelper_del, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy }, +}; + +static const struct nfnetlink_subsystem nfnl_cthelper_subsys = { + .name = "cthelper", + .subsys_id = NFNL_SUBSYS_CTHELPER, + .cb_count = NFNL_MSG_CTHELPER_MAX, + .cb = nfnl_cthelper_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTHELPER); + +static int __init nfnl_cthelper_init(void) +{ + int ret; + + ret = nfnetlink_subsys_register(&nfnl_cthelper_subsys); + if (ret < 0) { + pr_err("nfnl_cthelper: cannot register with nfnetlink.\n"); + goto err_out; + } + return 0; +err_out: + return ret; +} + +static void __exit nfnl_cthelper_exit(void) +{ + struct nf_conntrack_helper *cur; + struct hlist_node *n, *tmp; + int i; + + nfnetlink_subsys_unregister(&nfnl_cthelper_subsys); + + for (i=0; iflags & NF_CT_HELPER_F_USERSPACE)) + continue; + + nf_conntrack_helper_unregister(cur); + } + } +} + +module_init(nfnl_cthelper_init); +module_exit(nfnl_cthelper_exit); -- cgit v1.2.3 From 728b19e5fb9bbebbd580784a092b786fe379ed8e Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Thu, 14 Jun 2012 02:06:10 +0800 Subject: {nl,cfg,mac}80211: implement dot11MeshHWMPconfirmationInterval As defined in section 13.10.9.3 Case D (802.11-2012), this control variable is used to limit the mesh STA to send only one PREQ to a root mesh STA within this interval of time (in TUs). The default value for this variable is set to 2000 TUs. However, for current implementation, the maximum configurable of dot11MeshHWMPconfirmationInterval is restricted by dot11MeshHWMPactivePathTimeout. Signed-off-by: Chun-Yeow Yeoh [line-break commit log] Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 5 +++++ include/net/cfg80211.h | 4 ++++ net/mac80211/cfg.c | 3 +++ net/mac80211/debugfs_netdev.c | 3 +++ net/mac80211/mesh.h | 2 ++ net/mac80211/mesh_hwmp.c | 7 ++++++- net/wireless/mesh.c | 2 ++ net/wireless/nl80211.c | 9 ++++++++- 8 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 6936fabe8797..b7c3b737ddde 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -2192,6 +2192,10 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_HWMP_ROOT_INTERVAL: The interval of time (in TUs) between * proactive PREQs are transmitted. * + * @NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL: The minimum interval of time + * (in TUs) during which a mesh STA can send only one Action frame + * containing a PREQ element for root path confirmation. + * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ enum nl80211_meshconf_params { @@ -2220,6 +2224,7 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_HT_OPMODE, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, + NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e52b38d7b1b6..f0163a10b8ce 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -849,6 +849,9 @@ struct bss_parameters { * * @dot11MeshHWMProotInterval: The interval of time (in TUs) between proactive * PREQs are transmitted. + * @dot11MeshHWMPconfirmationInterval: The minimum interval of time (in TUs) + * during which a mesh STA can send only one Action frame containing + * a PREQ element for root path confirmation. */ struct mesh_config { u16 dot11MeshRetryTimeout; @@ -875,6 +878,7 @@ struct mesh_config { u16 ht_opmode; u32 dot11MeshHWMPactivePathToRootTimeout; u16 dot11MeshHWMProotInterval; + u16 dot11MeshHWMPconfirmationInterval; }; /** diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 5bd316c0a63d..6e25ac4873c7 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1596,6 +1596,9 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) conf->dot11MeshHWMProotInterval = nconf->dot11MeshHWMProotInterval; + if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, mask)) + conf->dot11MeshHWMPconfirmationInterval = + nconf->dot11MeshHWMPconfirmationInterval; return 0; } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index a8cea70902e4..512c894893d6 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -514,6 +514,8 @@ IEEE80211_IF_FILE(dot11MeshHWMPactivePathToRootTimeout, u.mesh.mshcfg.dot11MeshHWMPactivePathToRootTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMProotInterval, u.mesh.mshcfg.dot11MeshHWMProotInterval, DEC); +IEEE80211_IF_FILE(dot11MeshHWMPconfirmationInterval, + u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ @@ -617,6 +619,7 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata) MESHPARAMS_ADD(ht_opmode); MESHPARAMS_ADD(dot11MeshHWMPactivePathToRootTimeout); MESHPARAMS_ADD(dot11MeshHWMProotInterval); + MESHPARAMS_ADD(dot11MeshHWMPconfirmationInterval); #undef MESHPARAMS_ADD } #endif diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index c7400a23b64b..faaa39bcfd10 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -104,6 +104,7 @@ enum mesh_deferred_task_flags { * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address * @rann_metric: the aggregated path metric towards the root node + * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @@ -131,6 +132,7 @@ struct mesh_path { spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; u32 rann_metric; + unsigned long last_preq_to_root; bool is_root; bool is_gate; }; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 35e3acbe2262..bea52479e3aa 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -98,6 +98,8 @@ static inline u32 u16_field_get(u8 *preq_elem, int offset, bool ae) #define max_preq_retries(s) (s->u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries) #define disc_timeout_jiff(s) \ msecs_to_jiffies(sdata->u.mesh.mshcfg.min_discovery_timeout) +#define root_path_confirmation_jiffies(s) \ + msecs_to_jiffies(sdata->u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval) enum mpath_frame_type { MPATH_PREQ = 0, @@ -811,11 +813,14 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } if ((!(mpath->flags & (MESH_PATH_ACTIVE | MESH_PATH_RESOLVING)) || - time_after(jiffies, mpath->exp_time - 1*HZ)) && + (time_after(jiffies, mpath->last_preq_to_root + + root_path_confirmation_jiffies(sdata)) || + time_before(jiffies, mpath->last_preq_to_root))) && !(mpath->flags & MESH_PATH_FIXED)) { mhwmp_dbg("%s time to refresh root mpath %pM", sdata->name, orig_addr); mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); + mpath->last_preq_to_root = jiffies; } if ((SN_LT(mpath->sn, orig_sn) || (mpath->sn == orig_sn && diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 2f141cfd581e..3b73b07486cf 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -16,6 +16,7 @@ #define MESH_RANN_INTERVAL 5000 #define MESH_PATH_TO_ROOT_TIMEOUT 6000 #define MESH_ROOT_INTERVAL 5000 +#define MESH_ROOT_CONFIRMATION_INTERVAL 2000 /* * Minimum interval between two consecutive PREQs originated by the same @@ -66,6 +67,7 @@ const struct mesh_config default_mesh_config = { .ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED, .dot11MeshHWMPactivePathToRootTimeout = MESH_PATH_TO_ROOT_TIMEOUT, .dot11MeshHWMProotInterval = MESH_ROOT_INTERVAL, + .dot11MeshHWMPconfirmationInterval = MESH_ROOT_CONFIRMATION_INTERVAL, }; const struct mesh_setup default_mesh_setup = { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f8930db613df..a363ca17bfc5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3473,7 +3473,9 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_u32(msg, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, cur_params.dot11MeshHWMPactivePathToRootTimeout) || nla_put_u16(msg, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, - cur_params.dot11MeshHWMProotInterval)) + cur_params.dot11MeshHWMProotInterval) || + nla_put_u16(msg, NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, + cur_params.dot11MeshHWMPconfirmationInterval)) goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); @@ -3511,6 +3513,7 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HT_OPMODE] = { .type = NLA_U16 }, [NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT] = { .type = NLA_U32 }, [NL80211_MESHCONF_HWMP_ROOT_INTERVAL] = { .type = NLA_U16 }, + [NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL] = { .type = NLA_U16 }, }; static const struct nla_policy @@ -3625,6 +3628,10 @@ do {\ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMProotInterval, mask, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, + dot11MeshHWMPconfirmationInterval, mask, + NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, + nla_get_u16); if (mask_out) *mask_out = mask; -- cgit v1.2.3 From 7c9416365c60f150ef8961a2855fafbc7394ad6b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 13 Jun 2012 20:04:33 +0200 Subject: canfd: add new data structures and constants - add new struct canfd_frame - check identical element offsets in struct can_frame and struct canfd_frame - new ETH_P_CANFD definition to tag CAN FD skbs correctly - add CAN_MTU and CANFD_MTU definitions for easy frame and mode detection - add CAN[FD]_MAX_[DLC|DLEN] helper constants to remove hard coded values - update existing struct can_frame with helper constants and comments Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can.h | 59 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/if_ether.h | 3 ++- net/can/af_can.c | 7 ++++++ 3 files changed, 63 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can.h b/include/linux/can.h index 17334c09bd93..1a66cf6112ae 100644 --- a/include/linux/can.h +++ b/include/linux/can.h @@ -46,18 +46,67 @@ typedef __u32 canid_t; */ typedef __u32 can_err_mask_t; +/* CAN payload length and DLC definitions according to ISO 11898-1 */ +#define CAN_MAX_DLC 8 +#define CAN_MAX_DLEN 8 + +/* CAN FD payload length and DLC definitions according to ISO 11898-7 */ +#define CANFD_MAX_DLC 15 +#define CANFD_MAX_DLEN 64 + /** * struct can_frame - basic CAN frame structure - * @can_id: the CAN ID of the frame and CAN_*_FLAG flags, see above. - * @can_dlc: the data length field of the CAN frame - * @data: the CAN frame payload. + * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition + * @can_dlc: frame payload length in byte (0 .. 8) aka data length code + * N.B. the DLC field from ISO 11898-1 Chapter 8.4.2.3 has a 1:1 + * mapping of the 'data length code' to the real payload length + * @data: CAN frame payload (up to 8 byte) */ struct can_frame { canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */ - __u8 can_dlc; /* data length code: 0 .. 8 */ - __u8 data[8] __attribute__((aligned(8))); + __u8 can_dlc; /* frame payload length in byte (0 .. CAN_MAX_DLEN) */ + __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8))); }; +/* + * defined bits for canfd_frame.flags + * + * As the default for CAN FD should be to support the high data rate in the + * payload section of the frame (HDR) and to support up to 64 byte in the + * data section (EDL) the bits are only set in the non-default case. + * Btw. as long as there's no real implementation for CAN FD network driver + * these bits are only preliminary. + * + * RX: NOHDR/NOEDL - info about received CAN FD frame + * ESI - bit from originating CAN controller + * TX: NOHDR/NOEDL - control per-frame settings if supported by CAN controller + * ESI - bit is set by local CAN controller + */ +#define CANFD_NOHDR 0x01 /* frame without high data rate */ +#define CANFD_NOEDL 0x02 /* frame without extended data length */ +#define CANFD_ESI 0x04 /* error state indicator */ + +/** + * struct canfd_frame - CAN flexible data rate frame structure + * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition + * @len: frame payload length in byte (0 .. CANFD_MAX_DLEN) + * @flags: additional flags for CAN FD + * @__res0: reserved / padding + * @__res1: reserved / padding + * @data: CAN FD frame payload (up to CANFD_MAX_DLEN byte) + */ +struct canfd_frame { + canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */ + __u8 len; /* frame payload length in byte */ + __u8 flags; /* additional flags for CAN FD */ + __u8 __res0; /* reserved / padding */ + __u8 __res1; /* reserved / padding */ + __u8 data[CANFD_MAX_DLEN] __attribute__((aligned(8))); +}; + +#define CAN_MTU (sizeof(struct can_frame)) +#define CANFD_MTU (sizeof(struct canfd_frame)) + /* particular protocols of the protocol family PF_CAN */ #define CAN_RAW 1 /* RAW sockets */ #define CAN_BCM 2 /* Broadcast Manager */ diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 56d907a2c804..167ce5b363d2 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -105,7 +105,8 @@ #define ETH_P_WAN_PPP 0x0007 /* Dummy type for WAN PPP frames*/ #define ETH_P_PPP_MP 0x0008 /* Dummy type for PPP MP frames */ #define ETH_P_LOCALTALK 0x0009 /* Localtalk pseudo type */ -#define ETH_P_CAN 0x000C /* Controller Area Network */ +#define ETH_P_CAN 0x000C /* CAN: Controller Area Network */ +#define ETH_P_CANFD 0x000D /* CANFD: CAN flexible data rate*/ #define ETH_P_PPPTALK 0x0010 /* Dummy type for Atalk over PPP*/ #define ETH_P_TR_802_2 0x0011 /* 802.2 frames */ #define ETH_P_MOBITEX 0x0015 /* Mobitex (kaz@cafe.net) */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 6efcd37b4bd0..c96140a1458e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -41,6 +41,7 @@ */ #include +#include #include #include #include @@ -824,6 +825,12 @@ static struct notifier_block can_netdev_notifier __read_mostly = { static __init int can_init(void) { + /* check for correct padding to be able to use the structs similarly */ + BUILD_BUG_ON(offsetof(struct can_frame, can_dlc) != + offsetof(struct canfd_frame, len) || + offsetof(struct can_frame, data) != + offsetof(struct canfd_frame, data)); + printk(banner); memset(&can_rx_alldev_list, 0, sizeof(can_rx_alldev_list)); -- cgit v1.2.3 From 8b01939f358d680cea971151375268cfdb6b9635 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 13 Jun 2012 20:33:02 +0200 Subject: canfd: add support for CAN FD in PF_CAN core - handle ETH_P_CAN and ETH_P_CANFD skbuffs - update sanity checks for CAN and CAN FD - make sure the CAN frame can pass the selected CAN netdevice on send - bump core version and abi version to indicate the new CAN FD support Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 4 +- net/can/af_can.c | 109 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 84 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 0ccc1cd28b95..78c6c52073ad 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -17,10 +17,10 @@ #include #include -#define CAN_VERSION "20090105" +#define CAN_VERSION "20120528" /* increment this number each time you change some user-space interface */ -#define CAN_ABI_VERSION "8" +#define CAN_ABI_VERSION "9" #define CAN_VERSION_STRING "rev " CAN_VERSION " abi " CAN_ABI_VERSION diff --git a/net/can/af_can.c b/net/can/af_can.c index c96140a1458e..821022a7214f 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -221,30 +221,46 @@ static int can_create(struct net *net, struct socket *sock, int protocol, * -ENOBUFS on full driver queue (see net_xmit_errno()) * -ENOMEM when local loopback failed at calling skb_clone() * -EPERM when trying to send on a non-CAN interface + * -EMSGSIZE CAN frame size is bigger than CAN interface MTU * -EINVAL when the skb->data does not contain a valid CAN frame */ int can_send(struct sk_buff *skb, int loop) { struct sk_buff *newskb = NULL; - struct can_frame *cf = (struct can_frame *)skb->data; - int err; + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + int err = -EINVAL; + + if (skb->len == CAN_MTU) { + skb->protocol = htons(ETH_P_CAN); + if (unlikely(cfd->len > CAN_MAX_DLEN)) + goto inval_skb; + } else if (skb->len == CANFD_MTU) { + skb->protocol = htons(ETH_P_CANFD); + if (unlikely(cfd->len > CANFD_MAX_DLEN)) + goto inval_skb; + } else + goto inval_skb; - if (skb->len != sizeof(struct can_frame) || cf->can_dlc > 8) { - kfree_skb(skb); - return -EINVAL; + /* + * Make sure the CAN frame can pass the selected CAN netdevice. + * As structs can_frame and canfd_frame are similar, we can provide + * CAN FD frames to legacy CAN drivers as long as the length is <= 8 + */ + if (unlikely(skb->len > skb->dev->mtu && cfd->len > CAN_MAX_DLEN)) { + err = -EMSGSIZE; + goto inval_skb; } - if (skb->dev->type != ARPHRD_CAN) { - kfree_skb(skb); - return -EPERM; + if (unlikely(skb->dev->type != ARPHRD_CAN)) { + err = -EPERM; + goto inval_skb; } - if (!(skb->dev->flags & IFF_UP)) { - kfree_skb(skb); - return -ENETDOWN; + if (unlikely(!(skb->dev->flags & IFF_UP))) { + err = -ENETDOWN; + goto inval_skb; } - skb->protocol = htons(ETH_P_CAN); skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -301,6 +317,10 @@ int can_send(struct sk_buff *skb, int loop) can_stats.tx_frames_delta++; return 0; + +inval_skb: + kfree_skb(skb); + return err; } EXPORT_SYMBOL(can_send); @@ -633,24 +653,11 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return matches; } -static int can_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static void can_receive(struct sk_buff *skb, struct net_device *dev) { struct dev_rcv_lists *d; - struct can_frame *cf = (struct can_frame *)skb->data; int matches; - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - - if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != sizeof(struct can_frame) || - cf->can_dlc > 8, - "PF_CAN: dropped non conform skbuf: " - "dev type %d, len %d, can_dlc %d\n", - dev->type, skb->len, cf->can_dlc)) - goto drop; - /* update statistics */ can_stats.rx_frames++; can_stats.rx_frames_delta++; @@ -674,7 +681,49 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, can_stats.matches++; can_stats.matches_delta++; } +} + +static int can_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + if (unlikely(!net_eq(dev_net(dev), &init_net))) + goto drop; + + if (WARN_ONCE(dev->type != ARPHRD_CAN || + skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN, + "PF_CAN: dropped non conform CAN skbuf: " + "dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len)) + goto drop; + + can_receive(skb, dev); + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (unlikely(!net_eq(dev_net(dev), &init_net))) + goto drop; + + if (WARN_ONCE(dev->type != ARPHRD_CAN || + skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN, + "PF_CAN: dropped non conform CAN FD skbuf: " + "dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len)) + goto drop; + + can_receive(skb, dev); return NET_RX_SUCCESS; drop: @@ -808,10 +857,14 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, static struct packet_type can_packet __read_mostly = { .type = cpu_to_be16(ETH_P_CAN), - .dev = NULL, .func = can_rcv, }; +static struct packet_type canfd_packet __read_mostly = { + .type = cpu_to_be16(ETH_P_CANFD), + .func = canfd_rcv, +}; + static const struct net_proto_family can_family_ops = { .family = PF_CAN, .create = can_create, @@ -853,6 +906,7 @@ static __init int can_init(void) sock_register(&can_family_ops); register_netdevice_notifier(&can_netdev_notifier); dev_add_pack(&can_packet); + dev_add_pack(&canfd_packet); return 0; } @@ -867,6 +921,7 @@ static __exit void can_exit(void) can_remove_proc(); /* protocol unregister */ + dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); -- cgit v1.2.3 From e2d265d3b587f5f6f8febc0222aace93302ff0be Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 13 Jun 2012 20:41:31 +0200 Subject: canfd: add support for CAN FD in CAN_RAW sockets - introduce a new sockopt CAN_RAW_FD_FRAMES to allow CAN FD frames - handle CAN frames and CAN FD frames simultaneously when enabled Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/raw.h | 3 ++- net/can/raw.c | 50 +++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 48 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/raw.h b/include/linux/can/raw.h index 781f3a3701be..a814062b0719 100644 --- a/include/linux/can/raw.h +++ b/include/linux/can/raw.h @@ -23,7 +23,8 @@ enum { CAN_RAW_FILTER = 1, /* set 0 .. n can_filter(s) */ CAN_RAW_ERR_FILTER, /* set filter for error frames */ CAN_RAW_LOOPBACK, /* local loopback (default:on) */ - CAN_RAW_RECV_OWN_MSGS /* receive my own msgs (default:off) */ + CAN_RAW_RECV_OWN_MSGS, /* receive my own msgs (default:off) */ + CAN_RAW_FD_FRAMES, /* allow CAN FD frames (default:off) */ }; #endif diff --git a/net/can/raw.c b/net/can/raw.c index 46cca3a91d19..3e9c89356a93 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -82,6 +82,7 @@ struct raw_sock { struct notifier_block notifier; int loopback; int recv_own_msgs; + int fd_frames; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ @@ -119,6 +120,14 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->recv_own_msgs && oskb->sk == sk) return; + /* do not pass frames with DLC > 8 to a legacy socket */ + if (!ro->fd_frames) { + struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; + + if (unlikely(cfd->len > CAN_MAX_DLEN)) + return; + } + /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) @@ -291,6 +300,7 @@ static int raw_init(struct sock *sk) /* set default loopback behaviour */ ro->loopback = 1; ro->recv_own_msgs = 0; + ro->fd_frames = 0; /* set notifier */ ro->notifier.notifier_call = raw_notifier; @@ -569,6 +579,15 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; + case CAN_RAW_FD_FRAMES: + if (optlen != sizeof(ro->fd_frames)) + return -EINVAL; + + if (copy_from_user(&ro->fd_frames, optval, optlen)) + return -EFAULT; + + break; + default: return -ENOPROTOOPT; } @@ -627,6 +646,12 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, val = &ro->recv_own_msgs; break; + case CAN_RAW_FD_FRAMES: + if (len > sizeof(int)) + len = sizeof(int); + val = &ro->fd_frames; + break; + default: return -ENOPROTOOPT; } @@ -662,8 +687,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, } else ifindex = ro->ifindex; - if (size != sizeof(struct can_frame)) - return -EINVAL; + if (ro->fd_frames) { + if (unlikely(size != CANFD_MTU && size != CAN_MTU)) + return -EINVAL; + } else { + if (unlikely(size != CAN_MTU)) + return -EINVAL; + } dev = dev_get_by_index(&init_net, ifindex); if (!dev) @@ -705,7 +735,9 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; + struct raw_sock *ro = raw_sk(sk); struct sk_buff *skb; + int rxmtu; int err = 0; int noblock; @@ -716,10 +748,20 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - if (size < skb->len) + /* + * when serving a legacy socket the DLC <= 8 is already checked inside + * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy + * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU + */ + if (!ro->fd_frames) + rxmtu = CAN_MTU; + else + rxmtu = skb->len; + + if (size < rxmtu) msg->msg_flags |= MSG_TRUNC; else - size = skb->len; + size = rxmtu; err = memcpy_toiovec(msg->msg_iov, skb->data, size); if (err < 0) { -- cgit v1.2.3 From 1e0625facab2e871472472b7df87d8fbe6caf75a Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 13 Jun 2012 20:48:21 +0200 Subject: candev: add/update helpers for CAN FD - update sanity checks - add DLC to length conversion helpers - can_dlc2len() - get data length from can_dlc with sanitized can_dlc - can_len2dlc() - map the sanitized data length to an appropriate DLC Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 35 ++++++++++++++++++++++++++++++++++- include/linux/can/dev.h | 33 +++++++++++++++++++++++++-------- 2 files changed, 59 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index f03d7a481a80..239e4dd92ca1 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -33,6 +33,39 @@ MODULE_DESCRIPTION(MOD_DESC); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Wolfgang Grandegger "); +/* CAN DLC to real data length conversion helpers */ + +static const u8 dlc2len[] = {0, 1, 2, 3, 4, 5, 6, 7, + 8, 12, 16, 20, 24, 32, 48, 64}; + +/* get data length from can_dlc with sanitized can_dlc */ +u8 can_dlc2len(u8 can_dlc) +{ + return dlc2len[can_dlc & 0x0F]; +} +EXPORT_SYMBOL_GPL(can_dlc2len); + +static const u8 len2dlc[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, /* 0 - 8 */ + 9, 9, 9, 9, /* 9 - 12 */ + 10, 10, 10, 10, /* 13 - 16 */ + 11, 11, 11, 11, /* 17 - 20 */ + 12, 12, 12, 12, /* 21 - 24 */ + 13, 13, 13, 13, 13, 13, 13, 13, /* 25 - 32 */ + 14, 14, 14, 14, 14, 14, 14, 14, /* 33 - 40 */ + 14, 14, 14, 14, 14, 14, 14, 14, /* 41 - 48 */ + 15, 15, 15, 15, 15, 15, 15, 15, /* 49 - 56 */ + 15, 15, 15, 15, 15, 15, 15, 15}; /* 57 - 64 */ + +/* map the sanitized data length to an appropriate data length code */ +u8 can_len2dlc(u8 len) +{ + if (unlikely(len > 64)) + return 0xF; + + return len2dlc[len]; +} +EXPORT_SYMBOL_GPL(can_len2dlc); + #ifdef CONFIG_CAN_CALC_BITTIMING #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */ @@ -454,7 +487,7 @@ EXPORT_SYMBOL_GPL(can_bus_off); static void can_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; - dev->mtu = sizeof(struct can_frame); + dev->mtu = CAN_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5d2efe7e3f1b..ee5a771fb20d 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -61,23 +61,40 @@ struct can_priv { * To be used in the CAN netdriver receive path to ensure conformance with * ISO 11898-1 Chapter 8.4.2.3 (DLC field) */ -#define get_can_dlc(i) (min_t(__u8, (i), 8)) +#define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC)) +#define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ static inline int can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) { - const struct can_frame *cf = (struct can_frame *)skb->data; - - if (unlikely(skb->len != sizeof(*cf) || cf->can_dlc > 8)) { - kfree_skb(skb); - dev->stats.tx_dropped++; - return 1; - } + const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (skb->protocol == htons(ETH_P_CAN)) { + if (unlikely(skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN)) + goto inval_skb; + } else if (skb->protocol == htons(ETH_P_CANFD)) { + if (unlikely(skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN)) + goto inval_skb; + } else + goto inval_skb; return 0; + +inval_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; + return 1; } +/* get data length from can_dlc with sanitized can_dlc */ +u8 can_dlc2len(u8 can_dlc); + +/* map the sanitized data length to an appropriate data length code */ +u8 can_len2dlc(u8 len); + struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max); void free_candev(struct net_device *dev); -- cgit v1.2.3 From 0402788a6cda4e204a805e83eaaff64fef9e4418 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:03 +0000 Subject: team: make team_mode struct const Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 55 +++++++++++++++++++++---------- drivers/net/team/team_mode_activebackup.c | 2 +- drivers/net/team/team_mode_loadbalance.c | 2 +- drivers/net/team/team_mode_roundrobin.c | 2 +- include/linux/if_team.h | 5 ++- 5 files changed, 43 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index c61ae35a53ce..bdf87a971382 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -371,13 +371,18 @@ static int team_option_set(struct team *team, static LIST_HEAD(mode_list); static DEFINE_SPINLOCK(mode_list_lock); -static struct team_mode *__find_mode(const char *kind) +struct team_mode_item { + struct list_head list; + const struct team_mode *mode; +}; + +static struct team_mode_item *__find_mode(const char *kind) { - struct team_mode *mode; + struct team_mode_item *mitem; - list_for_each_entry(mode, &mode_list, list) { - if (strcmp(mode->kind, kind) == 0) - return mode; + list_for_each_entry(mitem, &mode_list, list) { + if (strcmp(mitem->mode->kind, kind) == 0) + return mitem; } return NULL; } @@ -392,49 +397,65 @@ static bool is_good_mode_name(const char *name) return true; } -int team_mode_register(struct team_mode *mode) +int team_mode_register(const struct team_mode *mode) { int err = 0; + struct team_mode_item *mitem; if (!is_good_mode_name(mode->kind) || mode->priv_size > TEAM_MODE_PRIV_SIZE) return -EINVAL; + + mitem = kmalloc(sizeof(*mitem), GFP_KERNEL); + if (!mitem) + return -ENOMEM; + spin_lock(&mode_list_lock); if (__find_mode(mode->kind)) { err = -EEXIST; + kfree(mitem); goto unlock; } - list_add_tail(&mode->list, &mode_list); + mitem->mode = mode; + list_add_tail(&mitem->list, &mode_list); unlock: spin_unlock(&mode_list_lock); return err; } EXPORT_SYMBOL(team_mode_register); -int team_mode_unregister(struct team_mode *mode) +void team_mode_unregister(const struct team_mode *mode) { + struct team_mode_item *mitem; + spin_lock(&mode_list_lock); - list_del_init(&mode->list); + mitem = __find_mode(mode->kind); + if (mitem) { + list_del_init(&mitem->list); + kfree(mitem); + } spin_unlock(&mode_list_lock); - return 0; } EXPORT_SYMBOL(team_mode_unregister); -static struct team_mode *team_mode_get(const char *kind) +static const struct team_mode *team_mode_get(const char *kind) { - struct team_mode *mode; + struct team_mode_item *mitem; + const struct team_mode *mode = NULL; spin_lock(&mode_list_lock); - mode = __find_mode(kind); - if (!mode) { + mitem = __find_mode(kind); + if (!mitem) { spin_unlock(&mode_list_lock); request_module("team-mode-%s", kind); spin_lock(&mode_list_lock); - mode = __find_mode(kind); + mitem = __find_mode(kind); } - if (mode) + if (mitem) { + mode = mitem->mode; if (!try_module_get(mode->owner)) mode = NULL; + } spin_unlock(&mode_list_lock); return mode; @@ -523,7 +544,7 @@ static int __team_change_mode(struct team *team, static int team_change_mode(struct team *team, const char *kind) { - struct team_mode *new_mode; + const struct team_mode *new_mode; struct net_device *dev = team->dev; int err; diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c index fd6bd03aaa89..acd925f070b5 100644 --- a/drivers/net/team/team_mode_activebackup.c +++ b/drivers/net/team/team_mode_activebackup.c @@ -108,7 +108,7 @@ static const struct team_mode_ops ab_mode_ops = { .port_leave = ab_port_leave, }; -static struct team_mode ab_mode = { +static const struct team_mode ab_mode = { .kind = "activebackup", .owner = THIS_MODULE, .priv_size = sizeof(struct ab_priv), diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 86e8183c8e3d..6452428a1d6c 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -148,7 +148,7 @@ static const struct team_mode_ops lb_mode_ops = { .transmit = lb_transmit, }; -static struct team_mode lb_mode = { +static const struct team_mode lb_mode = { .kind = "loadbalance", .owner = THIS_MODULE, .priv_size = sizeof(struct lb_priv), diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c index 6abfbdc96be5..daafca2b2da4 100644 --- a/drivers/net/team/team_mode_roundrobin.c +++ b/drivers/net/team/team_mode_roundrobin.c @@ -81,7 +81,7 @@ static const struct team_mode_ops rr_mode_ops = { .port_change_mac = rr_port_change_mac, }; -static struct team_mode rr_mode = { +static const struct team_mode rr_mode = { .kind = "roundrobin", .owner = THIS_MODULE, .priv_size = sizeof(struct rr_priv), diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 8185f57a9c7f..d45fcd5a188d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -105,7 +105,6 @@ struct team_option { }; struct team_mode { - struct list_head list; const char *kind; struct module *owner; size_t priv_size; @@ -178,8 +177,8 @@ extern int team_options_register(struct team *team, extern void team_options_unregister(struct team *team, const struct team_option *option, size_t option_count); -extern int team_mode_register(struct team_mode *mode); -extern int team_mode_unregister(struct team_mode *mode); +extern int team_mode_register(const struct team_mode *mode); +extern void team_mode_unregister(const struct team_mode *mode); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 5149ee58385bdfef260fb07a89a8ff0913be6b25 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:05 +0000 Subject: team: add mode priv to port Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 3 ++- include/linux/if_team.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 343f4ffaf8f0..dea2d8afa2f4 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -793,7 +793,8 @@ static int team_port_add(struct team *team, struct net_device *port_dev) return -EBUSY; } - port = kzalloc(sizeof(struct team_port), GFP_KERNEL); + port = kzalloc(sizeof(struct team_port) + team->mode->port_priv_size, + GFP_KERNEL); if (!port) return -ENOMEM; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index d45fcd5a188d..54af95f5d58b 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -61,6 +61,7 @@ struct team_port { } orig; struct rcu_head rcu; + long mode_priv[0]; }; struct team_mode_ops { @@ -108,6 +109,7 @@ struct team_mode { const char *kind; struct module *owner; size_t priv_size; + size_t port_priv_size; const struct team_mode_ops *ops; }; -- cgit v1.2.3 From b13033262d2496e271444d5a09226a2be5ceb989 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:08 +0000 Subject: team: introduce array options Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 75 ++++++++++++++++++++++++++++++++++--------------- include/linux/if_team.h | 3 ++ 2 files changed, 55 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index f50b8ca8dc94..32cb290fb800 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -90,6 +90,7 @@ struct team_option_inst { /* One for each option instance */ struct list_head list; struct team_option *option; struct team_port *port; /* != NULL if per-port */ + u32 array_index; bool changed; bool removed; }; @@ -106,22 +107,6 @@ static struct team_option *__team_find_option(struct team *team, return NULL; } -static int __team_option_inst_add(struct team *team, struct team_option *option, - struct team_port *port) -{ - struct team_option_inst *opt_inst; - - opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); - if (!opt_inst) - return -ENOMEM; - opt_inst->option = option; - opt_inst->port = port; - opt_inst->changed = true; - opt_inst->removed = false; - list_add_tail(&opt_inst->list, &team->option_inst_list); - return 0; -} - static void __team_option_inst_del(struct team_option_inst *opt_inst) { list_del(&opt_inst->list); @@ -139,14 +124,42 @@ static void __team_option_inst_del_option(struct team *team, } } +static int __team_option_inst_add(struct team *team, struct team_option *option, + struct team_port *port) +{ + struct team_option_inst *opt_inst; + unsigned int array_size; + unsigned int i; + + array_size = option->array_size; + if (!array_size) + array_size = 1; /* No array but still need one instance */ + + for (i = 0; i < array_size; i++) { + opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); + if (!opt_inst) + return -ENOMEM; + opt_inst->option = option; + opt_inst->port = port; + opt_inst->array_index = i; + opt_inst->changed = true; + opt_inst->removed = false; + list_add_tail(&opt_inst->list, &team->option_inst_list); + } + return 0; +} + static int __team_option_inst_add_option(struct team *team, struct team_option *option) { struct team_port *port; int err; - if (!option->per_port) - return __team_option_inst_add(team, option, 0); + if (!option->per_port) { + err = __team_option_inst_add(team, option, 0); + if (err) + goto inst_del_option; + } list_for_each_entry(port, &team->port_list, list) { err = __team_option_inst_add(team, option, port); @@ -1567,6 +1580,11 @@ static int team_nl_fill_options_get(struct sk_buff *skb, opt_inst->port->dev->ifindex)) goto nla_put_failure; ctx.port = opt_inst->port; + if (opt_inst->option->array_size && + nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, + opt_inst->array_index)) + goto nla_put_failure; + ctx.array_index = opt_inst->array_index; switch (option->type) { case TEAM_OPTION_TYPE_U32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) @@ -1668,10 +1686,12 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) { struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; - struct nlattr *attr_port_ifindex; + struct nlattr *attr; struct nlattr *attr_data; enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ + u32 opt_array_index = 0; + bool opt_is_array = false; struct team_option_inst *opt_inst; char *opt_name; bool opt_found = false; @@ -1713,9 +1733,15 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) } opt_name = nla_data(opt_attrs[TEAM_ATTR_OPTION_NAME]); - attr_port_ifindex = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; - if (attr_port_ifindex) - opt_port_ifindex = nla_get_u32(attr_port_ifindex); + attr = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; + if (attr) + opt_port_ifindex = nla_get_u32(attr); + + attr = opt_attrs[TEAM_ATTR_OPTION_ARRAY_INDEX]; + if (attr) { + opt_is_array = true; + opt_array_index = nla_get_u32(attr); + } list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; @@ -1726,10 +1752,13 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) opt_inst->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || - tmp_ifindex != opt_port_ifindex) + tmp_ifindex != opt_port_ifindex || + (option->array_size && !opt_is_array) || + opt_inst->array_index != opt_array_index) continue; opt_found = true; ctx.port = opt_inst->port; + ctx.array_index = opt_inst->array_index; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 54af95f5d58b..b1719e239a0b 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -93,6 +93,7 @@ struct team_gsetter_ctx { } bin_val; bool bool_val; } data; + u32 array_index; struct team_port *port; }; @@ -100,6 +101,7 @@ struct team_option { struct list_head list; const char *name; bool per_port; + unsigned int array_size; /* != 0 means the option is array */ enum team_option_type type; int (*getter)(struct team *team, struct team_gsetter_ctx *ctx); int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); @@ -242,6 +244,7 @@ enum { TEAM_ATTR_OPTION_DATA, /* dynamic */ TEAM_ATTR_OPTION_REMOVED, /* flag */ TEAM_ATTR_OPTION_PORT_IFINDEX, /* u32 */ /* for per-port options */ + TEAM_ATTR_OPTION_ARRAY_INDEX, /* u32 */ /* for array options */ __TEAM_ATTR_OPTION_MAX, TEAM_ATTR_OPTION_MAX = __TEAM_ATTR_OPTION_MAX - 1, -- cgit v1.2.3 From 85d59a87248de90e3266e10dce99477b60f524c0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:10 +0000 Subject: team: push array_index and port into separate structure Introduce struct team_option_inst_info and push option instance info there. It can be then easily passed to gsetter context and used for feature async option changes. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 68 +++++++++++++++++++++++++++++++------------------ include/linux/if_team.h | 9 +++++-- 2 files changed, 50 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 7ec53f81c1c4..cff8e253df72 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -89,8 +89,7 @@ static void team_refresh_port_linkup(struct team_port *port) struct team_option_inst { /* One for each option instance */ struct list_head list; struct team_option *option; - struct team_port *port; /* != NULL if per-port */ - u32 array_index; + struct team_option_inst_info info; bool changed; bool removed; }; @@ -130,6 +129,7 @@ static int __team_option_inst_add(struct team *team, struct team_option *option, struct team_option_inst *opt_inst; unsigned int array_size; unsigned int i; + int err; array_size = option->array_size; if (!array_size) @@ -140,11 +140,17 @@ static int __team_option_inst_add(struct team *team, struct team_option *option, if (!opt_inst) return -ENOMEM; opt_inst->option = option; - opt_inst->port = port; - opt_inst->array_index = i; + opt_inst->info.port = port; + opt_inst->info.array_index = i; opt_inst->changed = true; opt_inst->removed = false; list_add_tail(&opt_inst->list, &team->option_inst_list); + if (option->init) { + err = option->init(team, &opt_inst->info); + if (err) + return err; + } + } return 0; } @@ -193,7 +199,7 @@ static void __team_option_inst_del_port(struct team *team, list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option->per_port && - opt_inst->port == port) + opt_inst->info.port == port) __team_option_inst_del(opt_inst); } } @@ -224,7 +230,7 @@ static void __team_option_inst_mark_removed_port(struct team *team, struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { - if (opt_inst->port == port) { + if (opt_inst->info.port == port) { opt_inst->changed = true; opt_inst->removed = true; } @@ -958,39 +964,47 @@ static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) static int team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->data.bool_val = team_port_enabled(ctx->port); + struct team_port *port = ctx->info->port; + + ctx->data.bool_val = team_port_enabled(port); return 0; } static int team_port_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { + struct team_port *port = ctx->info->port; + if (ctx->data.bool_val) - team_port_enable(team, ctx->port); + team_port_enable(team, port); else - team_port_disable(team, ctx->port); + team_port_disable(team, port); return 0; } static int team_user_linkup_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->data.bool_val = ctx->port->user.linkup; + struct team_port *port = ctx->info->port; + + ctx->data.bool_val = port->user.linkup; return 0; } static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { - ctx->port->user.linkup = ctx->data.bool_val; - team_refresh_port_linkup(ctx->port); + struct team_port *port = ctx->info->port; + + port->user.linkup = ctx->data.bool_val; + team_refresh_port_linkup(port); return 0; } static int team_user_linkup_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { - struct team_port *port = ctx->port; + struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; return 0; @@ -999,10 +1013,10 @@ static int team_user_linkup_en_option_get(struct team *team, static int team_user_linkup_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { - struct team_port *port = ctx->port; + struct team_port *port = ctx->info->port; port->user.linkup_enabled = ctx->data.bool_val; - team_refresh_port_linkup(ctx->port); + team_refresh_port_linkup(port); return 0; } @@ -1557,6 +1571,7 @@ static int team_nl_fill_options_get(struct sk_buff *skb, list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct nlattr *option_item; struct team_option *option = opt_inst->option; + struct team_option_inst_info *opt_inst_info; struct team_gsetter_ctx ctx; /* Include only changed options if fill all mode is not on */ @@ -1575,16 +1590,18 @@ static int team_nl_fill_options_get(struct sk_buff *skb, if (opt_inst->removed && nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) goto nla_put_failure; - if (opt_inst->port && + + opt_inst_info = &opt_inst->info; + if (opt_inst_info->port && nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, - opt_inst->port->dev->ifindex)) + opt_inst_info->port->dev->ifindex)) goto nla_put_failure; - ctx.port = opt_inst->port; if (opt_inst->option->array_size && nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, - opt_inst->array_index)) + opt_inst_info->array_index)) goto nla_put_failure; - ctx.array_index = opt_inst->array_index; + ctx.info = opt_inst_info; + switch (option->type) { case TEAM_OPTION_TYPE_U32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) @@ -1746,19 +1763,20 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; struct team_gsetter_ctx ctx; + struct team_option_inst_info *opt_inst_info; int tmp_ifindex; - tmp_ifindex = opt_inst->port ? - opt_inst->port->dev->ifindex : 0; + opt_inst_info = &opt_inst->info; + tmp_ifindex = opt_inst_info->port ? + opt_inst_info->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || tmp_ifindex != opt_port_ifindex || (option->array_size && !opt_is_array) || - opt_inst->array_index != opt_array_index) + opt_inst_info->array_index != opt_array_index) continue; opt_found = true; - ctx.port = opt_inst->port; - ctx.array_index = opt_inst->array_index; + ctx.info = opt_inst_info; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); diff --git a/include/linux/if_team.h b/include/linux/if_team.h index b1719e239a0b..30854cb0c855 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -83,6 +83,11 @@ enum team_option_type { TEAM_OPTION_TYPE_BOOL, }; +struct team_option_inst_info { + u32 array_index; + struct team_port *port; /* != NULL if per-port */ +}; + struct team_gsetter_ctx { union { u32 u32_val; @@ -93,8 +98,7 @@ struct team_gsetter_ctx { } bin_val; bool bool_val; } data; - u32 array_index; - struct team_port *port; + struct team_option_inst_info *info; }; struct team_option { @@ -103,6 +107,7 @@ struct team_option { bool per_port; unsigned int array_size; /* != 0 means the option is array */ enum team_option_type type; + int (*init)(struct team *team, struct team_option_inst_info *info); int (*getter)(struct team *team, struct team_gsetter_ctx *ctx); int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); }; -- cgit v1.2.3 From 0f1aad2b7f01d88782fbf4ab08b13a7d92b9b6b2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:11 +0000 Subject: team: allow async option changes This patch adds two exported functions. One allows to mark option instance as changed and the second processes change check and does transfer of changed options to userspace. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 18 ++++++++++++++++++ include/linux/if_team.h | 3 +++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index cff8e253df72..7988ba099b94 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -82,6 +82,7 @@ static void team_refresh_port_linkup(struct team_port *port) port->state.linkup; } + /******************* * Options handling *******************/ @@ -387,6 +388,22 @@ static int team_option_set(struct team *team, return err; } +void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info) +{ + struct team_option_inst *opt_inst; + + opt_inst = container_of(opt_inst_info, struct team_option_inst, info); + opt_inst->changed = true; +} +EXPORT_SYMBOL(team_option_inst_set_change); + +void team_options_change_check(struct team *team) +{ + __team_options_change_check(team); +} +EXPORT_SYMBOL(team_options_change_check); + + /**************** * Mode handling ****************/ @@ -2051,6 +2068,7 @@ static void team_port_change_check(struct team_port *port, bool linkup) mutex_unlock(&team->lock); } + /************************************ * Net device notifier event handler ************************************/ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 30854cb0c855..2f2972535cc0 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -112,6 +112,9 @@ struct team_option { int (*setter)(struct team *team, struct team_gsetter_ctx *ctx); }; +extern void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info); +extern void team_options_change_check(struct team *team); + struct team_mode { const char *kind; struct module *owner; -- cgit v1.2.3 From 4bccfd17e1f77593e99d5321c48c704a0a43ab68 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 19 Jun 2012 05:54:16 +0000 Subject: team: add port_[enabled/disabled] mode callbacks Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 4 ++++ include/linux/if_team.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index eb18ac93095a..bc76f946e071 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -714,6 +714,8 @@ static void team_port_enable(struct team *team, port->index = team->en_port_count++; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); + if (team->ops.port_enabled) + team->ops.port_enabled(team, port); } static void __reconstruct_port_hlist(struct team *team, int rm_index) @@ -737,6 +739,8 @@ static void team_port_disable(struct team *team, if (!team_port_enabled(port)) return; + if (team->ops.port_disabled) + team->ops.port_disabled(team, port); hlist_del_rcu(&port->hlist); __reconstruct_port_hlist(team, rm_index); team->en_port_count--; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 2f2972535cc0..c1938869191f 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -74,6 +74,8 @@ struct team_mode_ops { int (*port_enter)(struct team *team, struct team_port *port); void (*port_leave)(struct team *team, struct team_port *port); void (*port_change_mac)(struct team *team, struct team_port *port); + void (*port_enabled)(struct team *team, struct team_port *port); + void (*port_disabled)(struct team *team, struct team_port *port); }; enum team_option_type { -- cgit v1.2.3 From 5a05fae5ca7cd5279567747fc34d60413b504cd6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 20 Jun 2012 20:50:31 +0200 Subject: netfilter: nfq_ct_hook needs __rcu and __read_mostly This removes some sparse warnings. Reported-by: Fengguang Wu Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- net/netfilter/core.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index dca19e61b30a..38b96a54f9a5 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -404,7 +404,7 @@ struct nfq_ct_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, u32 ctinfo, int off); }; -extern struct nfq_ct_hook *nfq_ct_hook; +extern struct nfq_ct_hook __rcu *nfq_ct_hook; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 7eef8453b909..4cd10ed2d6e6 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -265,7 +265,7 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy); -struct nfq_ct_hook *nfq_ct_hook; +struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfq_ct_hook); #endif /* CONFIG_NF_CONNTRACK */ -- cgit v1.2.3 From c2ebea2097f84f0973c58b8467c1a2236bbb307a Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Wed, 20 Jun 2012 17:59:01 -0700 Subject: ieee80211: more OUI type definitions for WLAN_OUI_MICROSOFT WMM and WPS Signed-off-by: Avinash Patil Signed-off-by: Bing Zhao Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 6e0601189db9..318fc1f705b1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1633,6 +1633,8 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_TYPE_WFA_P2P 9 #define WLAN_OUI_MICROSOFT 0x0050f2 #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 +#define WLAN_OUI_TYPE_MICROSOFT_WMM 2 +#define WLAN_OUI_TYPE_MICROSOFT_WPS 4 /* * WMM/802.11e Tspec Element -- cgit v1.2.3 From d584a61a931e6cbfef0dd811c4ae0250ec5987f4 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 20 Jun 2012 20:52:31 +0200 Subject: netfilter: nfnetlink_queue: fix compilation with CONFIG_NF_NAT=m and CONFIG_NF_CT_NETLINK=y LD init/built-in.o net/built-in.o:(.data+0x4408): undefined reference to `nf_nat_tcp_seq_adjust' make: *** [vmlinux] Error 1 This patch adds a new pointer hook (nfq_ct_nat_hook) similar to other existing in Netfilter to solve our complicated configuration dependencies. Reported-by: Valdis Kletnieks Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 6 +++++- net/ipv4/netfilter/nf_nat_core.c | 6 ++++++ net/netfilter/core.c | 3 +++ net/netfilter/nf_conntrack_netlink.c | 3 --- net/netfilter/nfnetlink_queue_ct.c | 8 ++++---- 5 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 38b96a54f9a5..c613cf0d7884 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -401,10 +401,14 @@ struct nfq_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); +}; +extern struct nfq_ct_hook __rcu *nfq_ct_hook; + +struct nfq_ct_nat_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, u32 ctinfo, int off); }; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; +extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index abb52adf5acd..44b082fd48ab 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -691,6 +691,10 @@ static struct nf_ct_helper_expectfn follow_master_nat = { .expectfn = nf_nat_follow_master, }; +static struct nfq_ct_nat_hook nfq_ct_nat = { + .seq_adjust = nf_nat_tcp_seq_adjust, +}; + static int __init nf_nat_init(void) { size_t i; @@ -731,6 +735,7 @@ static int __init nf_nat_init(void) nfnetlink_parse_nat_setup); BUG_ON(nf_ct_nat_offset != NULL); RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); return 0; cleanup_extend: @@ -747,6 +752,7 @@ static void __exit nf_nat_cleanup(void) RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); RCU_INIT_POINTER(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); synchronize_net(); } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 4cd10ed2d6e6..0bc6b60db4df 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -268,6 +268,9 @@ EXPORT_SYMBOL(nf_conntrack_destroy); struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfq_ct_hook); +struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook __read_mostly; +EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); + #endif /* CONFIG_NF_CONNTRACK */ #ifdef CONFIG_PROC_FS diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 31d1d8f3a6ce..8bb47339b770 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1757,9 +1757,6 @@ static struct nfq_ct_hook ctnetlink_nfqueue_hook = { .build_size = ctnetlink_nfqueue_build_size, .build = ctnetlink_nfqueue_build, .parse = ctnetlink_nfqueue_parse, -#ifdef CONFIG_NF_NAT_NEEDED - .seq_adjust = nf_nat_tcp_seq_adjust, -#endif }; #endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */ diff --git a/net/netfilter/nfnetlink_queue_ct.c b/net/netfilter/nfnetlink_queue_ct.c index 68ef550066f5..01247b730e66 100644 --- a/net/netfilter/nfnetlink_queue_ct.c +++ b/net/netfilter/nfnetlink_queue_ct.c @@ -86,12 +86,12 @@ nla_put_failure: void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { - struct nfq_ct_hook *nfq_ct; + struct nfq_ct_nat_hook *nfq_nat_ct; - nfq_ct = rcu_dereference(nfq_ct_hook); - if (nfq_ct == NULL) + nfq_nat_ct = rcu_dereference(nfq_ct_nat_hook); + if (nfq_nat_ct == NULL) return; if ((ct->status & IPS_NAT_MASK) && diff) - nfq_ct->seq_adjust(skb, ct, ctinfo, diff); + nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff); } -- cgit v1.2.3 From 6648bd7e0e62c0c8c03b15e00c9e7015e232feff Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 21 Jun 2012 13:58:31 +0000 Subject: ipv4: Add sysctl knob to control early socket demux This change is meant to add a control for disabling early socket demux. The main motivation behind this patch is to provide an option to disable the feature as it adds an additional cost to routing that reduces overall throughput by up to 5%. For example one of my systems went from 12.1Mpps to 11.6 after the early socket demux was added. It looks like the reason for the regression is that we are now having to perform two lookups, first the one for an established socket, and then the one for the routing table. By adding this patch and toggling the value for ip_early_demux to 0 I am able to get back to the 12.1Mpps I was previously seeing. [ Move local variables in ip_rcv_finish() down into the basic block in which they are actually used. -DaveM ] Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 + include/net/ip.h | 3 +++ kernel/sysctl_binary.c | 2 ++ net/ipv4/ip_input.c | 22 +++++++++++++--------- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ 5 files changed, 26 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index c34b4c82b0dc..20825e5f433f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -425,6 +425,7 @@ enum NET_TCP_ALLOWED_CONG_CONTROL=123, NET_TCP_MAX_SSTHRESH=124, NET_TCP_FRTO_RESPONSE=125, + NET_IPV4_EARLY_DEMUX=126, }; enum { diff --git a/include/net/ip.h b/include/net/ip.h index 83e0619f59d0..50841bd6f10e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -210,6 +210,9 @@ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; +/* From ip_input.c */ +extern int sysctl_ip_early_demux; + /* From ip_output.c */ extern int sysctl_ip_dynaddr; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index a650694883a1..6a3cf8253aae 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -415,6 +415,8 @@ static const struct bin_table bin_net_ipv4_table[] = { { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */ + { CTL_INT, NET_IPV4_EARLY_DEMUX, "ip_early_demux" }, + { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, /* NET_TCP_DEFAULT_WIN_SCALE unused */ diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 93b092c9a394..bca25179cdb9 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -313,6 +313,8 @@ drop: return true; } +int sysctl_ip_early_demux __read_mostly = 1; + static int ip_rcv_finish(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -323,16 +325,18 @@ static int ip_rcv_finish(struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (skb_dst(skb) == NULL) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; - int err; + int err = -ENOENT; - rcu_read_lock(); - ipprot = rcu_dereference(inet_protos[protocol]); - err = -ENOENT; - if (ipprot && ipprot->early_demux) - err = ipprot->early_demux(skb); - rcu_read_unlock(); + if (sysctl_ip_early_demux) { + const struct net_protocol *ipprot; + int protocol = iph->protocol; + + rcu_read_lock(); + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot && ipprot->early_demux) + err = ipprot->early_demux(skb); + rcu_read_unlock(); + } if (err) { err = ip_route_input_noref(skb, iph->daddr, iph->saddr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ef32956ed655..12aa0c5867c4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -300,6 +300,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_early_demux", + .data = &sysctl_ip_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "ip_dynaddr", .data = &sysctl_ip_dynaddr, -- cgit v1.2.3 From dfbce08c19cba2ba4faaf8c0dd6d7678f46c78dd Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 22 Jun 2012 23:02:22 -0700 Subject: ipv4: Don't add deprecated new binary sysctl value. Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 - kernel/sysctl_binary.c | 2 -- 2 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 20825e5f433f..c34b4c82b0dc 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -425,7 +425,6 @@ enum NET_TCP_ALLOWED_CONG_CONTROL=123, NET_TCP_MAX_SSTHRESH=124, NET_TCP_FRTO_RESPONSE=125, - NET_IPV4_EARLY_DEMUX=126, }; enum { diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 6a3cf8253aae..a650694883a1 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -415,8 +415,6 @@ static const struct bin_table bin_net_ipv4_table[] = { { CTL_INT, NET_IPV4_IPFRAG_SECRET_INTERVAL, "ipfrag_secret_interval" }, /* NET_IPV4_IPFRAG_MAX_DIST "ipfrag_max_dist" no longer used */ - { CTL_INT, NET_IPV4_EARLY_DEMUX, "ip_early_demux" }, - { CTL_INT, 2088 /* NET_IPQ_QMAX */, "ip_queue_maxlen" }, /* NET_TCP_DEFAULT_WIN_SCALE unused */ -- cgit v1.2.3 From 88e920b4505105b710f8d4a535ec02c4078f8e2e Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 21 Jun 2012 11:09:54 -0700 Subject: nl80211: specify RSSI threshold in scheduled scan Support configuring an RSSI threshold in dBm (s32) when requesting scheduled scan, below which a BSS won't be reported by the cfg80211 driver. Signed-off-by: Thomas Pedersen Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 6 ++++++ include/net/cfg80211.h | 2 ++ net/wireless/nl80211.c | 9 ++++++++- 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index b7c3b737ddde..c0fc5d277338 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1542,6 +1542,9 @@ enum nl80211_attrs { #define NL80211_MIN_REMAIN_ON_CHANNEL_TIME 10 +/* default RSSI threshold for scan results if none specified. */ +#define NL80211_SCAN_RSSI_THOLD_OFF -300 + /** * enum nl80211_iftype - (virtual) interface types * @@ -1974,6 +1977,8 @@ enum nl80211_reg_rule_attr { * @__NL80211_SCHED_SCAN_MATCH_ATTR_INVALID: attribute number 0 is reserved * @NL80211_SCHED_SCAN_MATCH_ATTR_SSID: SSID to be used for matching, * only report BSS with matching SSID. + * @NL80211_SCHED_SCAN_MATCH_ATTR_RSSI: RSSI threshold (in dBm) for reporting a + * BSS in scan results. Filtering is turned off if not specified. * @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter * attribute number currently defined * @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use @@ -1982,6 +1987,7 @@ enum nl80211_sched_scan_match_attr { __NL80211_SCHED_SCAN_MATCH_ATTR_INVALID, NL80211_SCHED_SCAN_MATCH_ATTR_SSID, + NL80211_SCHED_SCAN_MATCH_ATTR_RSSI, /* keep last */ __NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f0163a10b8ce..061c01957e54 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1027,6 +1027,7 @@ struct cfg80211_match_set { * @wiphy: the wiphy this was for * @dev: the interface * @channels: channels to scan + * @rssi_thold: don't report scan results below this threshold (in s32 dBm) */ struct cfg80211_sched_scan_request { struct cfg80211_ssid *ssids; @@ -1037,6 +1038,7 @@ struct cfg80211_sched_scan_request { size_t ie_len; struct cfg80211_match_set *match_sets; int n_match_sets; + s32 rssi_thold; /* internal */ struct wiphy *wiphy; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 888fadc4d63e..234ff3bbd104 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -340,6 +340,7 @@ static const struct nla_policy nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { [NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_SSID_LEN }, + [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, }; /* ifidx get helper */ @@ -4387,7 +4388,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH], tmp) { - struct nlattr *ssid; + struct nlattr *ssid, *rssi; nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, nla_data(attr), nla_len(attr), @@ -4403,6 +4404,12 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request->match_sets[i].ssid.ssid_len = nla_len(ssid); } + rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI]; + if (rssi) + request->rssi_thold = nla_get_u32(rssi); + else + request->rssi_thold = + NL80211_SCAN_RSSI_THOLD_OFF; i++; } } -- cgit v1.2.3 From 32bad7e30f113a8a5cebe4704bf6519ab4383e1b Mon Sep 17 00:00:00 2001 From: "alex.bluesman.smirnov@gmail.com" Date: Mon, 25 Jun 2012 23:24:48 +0000 Subject: mac802154: add wpan device-class support Every real 802.15.4 transceiver, which works with software MAC layer, can be classified as a wpan device in this stack. So the wpan device implementation provides missing link in datapath between the device drivers and the Linux network queue. According to the IEEE 802.15.4 standard each packet can be one of the following types: - beacon - MAC layer command - ACK - data This patch adds support for the data packet-type only, but this is enough to perform data transmission and receiving over radio. Signed-off-by: Alexander Smirnov Signed-off-by: David S. Miller --- include/linux/nl802154.h | 14 +- include/net/mac802154.h | 8 + net/mac802154/Makefile | 2 +- net/mac802154/ieee802154_dev.c | 4 + net/mac802154/mac802154.h | 4 + net/mac802154/mac_cmd.c | 4 + net/mac802154/rx.c | 1 + net/mac802154/wpan.c | 559 +++++++++++++++++++++++++++++++++++++++++ 8 files changed, 583 insertions(+), 13 deletions(-) create mode 100644 net/mac802154/wpan.c (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index 5a3db3aa5f17..fd4f2d1cdf6c 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -130,18 +130,8 @@ enum { enum { __IEEE802154_DEV_INVALID = -1, - /* TODO: - * Nowadays three device types supported by this stack at linux-zigbee - * project: WPAN = 0, MONITOR = 1 and SMAC = 2. - * - * Since this stack implementation exists many years, it's definitely - * bad idea to change the assigned values due to they are already used - * by third-party userspace software like: iz-tools, wireshark... - * - * Currently only monitor device is added and initialized by '1' for - * compatibility. - */ - IEEE802154_DEV_MONITOR = 1, + IEEE802154_DEV_WPAN, + IEEE802154_DEV_MONITOR, __IEEE802154_DEV_MAX, }; diff --git a/include/net/mac802154.h b/include/net/mac802154.h index c9f8ab5cc687..d0d11df9cba1 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -21,6 +21,14 @@ #include +/* General MAC frame format: + * 2 bytes: Frame Control + * 1 byte: Sequence Number + * 20 bytes: Addressing fields + * 14 bytes: Auxiliary Security Header + */ +#define MAC802154_FRAME_HARD_HEADER_LEN (2 + 1 + 20 + 14) + /* The following flags are used to indicate changed address settings from * the stack to the hardware. */ diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile index ec1bd3fc1273..57cf5d1a2e4a 100644 --- a/net/mac802154/Makefile +++ b/net/mac802154/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_MAC802154) += mac802154.o -mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o +mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index e3edfb0661b0..e748aed290aa 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -140,6 +140,10 @@ mac802154_add_iface(struct wpan_phy *phy, const char *name, int type) dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), name, mac802154_monitor_setup); break; + case IEEE802154_DEV_WPAN: + dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), + name, mac802154_wpan_setup); + break; default: dev = NULL; err = -EINVAL; diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h index 789d9c948aec..c0efcf19a171 100644 --- a/net/mac802154/mac802154.h +++ b/net/mac802154/mac802154.h @@ -93,6 +93,7 @@ struct mac802154_sub_if_data { #define MAC802154_CHAN_NONE (~(u8)0) /* No channel is assigned */ extern struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced; +extern struct ieee802154_mlme_ops mac802154_mlme_wpan; int mac802154_slave_open(struct net_device *dev); int mac802154_slave_close(struct net_device *dev); @@ -100,6 +101,9 @@ int mac802154_slave_close(struct net_device *dev); void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb); void mac802154_monitor_setup(struct net_device *dev); +void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb); +void mac802154_wpan_setup(struct net_device *dev); + netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, u8 page, u8 chan); diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index 7a5d0e052cd7..db8341957bd2 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -43,3 +43,7 @@ struct wpan_phy *mac802154_get_phy(const struct net_device *dev) struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = { .get_phy = mac802154_get_phy, }; + +struct ieee802154_mlme_ops mac802154_mlme_wpan = { + .get_phy = mac802154_get_phy, +}; diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 4a7d76d4f8bc..38548ec2098f 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -77,6 +77,7 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) } mac802154_monitors_rx(priv, skb); + mac802154_wpans_rx(priv, skb); out: dev_kfree_skb(skb); return; diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c new file mode 100644 index 000000000000..f30f6d4beea1 --- /dev/null +++ b/net/mac802154/wpan.c @@ -0,0 +1,559 @@ +/* + * Copyright 2007-2012 Siemens AG + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov + * Sergey Lapin + * Maxim Gorbachyov + * Alexander Smirnov + */ + +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "mac802154.h" + +static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val) +{ + if (unlikely(!pskb_may_pull(skb, 1))) + return -EINVAL; + + *val = skb->data[0]; + skb_pull(skb, 1); + + return 0; +} + +static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val) +{ + if (unlikely(!pskb_may_pull(skb, 2))) + return -EINVAL; + + *val = skb->data[0] | (skb->data[1] << 8); + skb_pull(skb, 2); + + return 0; +} + +static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src) +{ + int i; + for (i = 0; i < IEEE802154_ADDR_LEN; i++) + dest[IEEE802154_ADDR_LEN - i - 1] = src[i]; +} + +static int +mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct sockaddr_ieee802154 *sa = + (struct sockaddr_ieee802154 *)&ifr->ifr_addr; + int err = -ENOIOCTLCMD; + + spin_lock_bh(&priv->mib_lock); + + switch (cmd) { + case SIOCGIFADDR: + if (priv->pan_id == IEEE802154_PANID_BROADCAST || + priv->short_addr == IEEE802154_ADDR_BROADCAST) { + err = -EADDRNOTAVAIL; + break; + } + + sa->family = AF_IEEE802154; + sa->addr.addr_type = IEEE802154_ADDR_SHORT; + sa->addr.pan_id = priv->pan_id; + sa->addr.short_addr = priv->short_addr; + + err = 0; + break; + case SIOCSIFADDR: + dev_warn(&dev->dev, + "Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n"); + if (sa->family != AF_IEEE802154 || + sa->addr.addr_type != IEEE802154_ADDR_SHORT || + sa->addr.pan_id == IEEE802154_PANID_BROADCAST || + sa->addr.short_addr == IEEE802154_ADDR_BROADCAST || + sa->addr.short_addr == IEEE802154_ADDR_UNDEF) { + err = -EINVAL; + break; + } + + priv->pan_id = sa->addr.pan_id; + priv->short_addr = sa->addr.short_addr; + + err = 0; + break; + } + + spin_unlock_bh(&priv->mib_lock); + return err; +} + +static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (netif_running(dev)) + return -EBUSY; + + /* FIXME: validate addr */ + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + mac802154_dev_set_ieee_addr(dev); + return 0; +} + +static int mac802154_header_create(struct sk_buff *skb, + struct net_device *dev, + unsigned short type, + const void *_daddr, + const void *_saddr, + unsigned len) +{ + const struct ieee802154_addr *saddr = _saddr; + const struct ieee802154_addr *daddr = _daddr; + struct ieee802154_addr dev_addr; + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int pos = 2; + u8 *head; + u16 fc; + + if (!daddr) + return -EINVAL; + + head = kzalloc(MAC802154_FRAME_HARD_HEADER_LEN, GFP_KERNEL); + if (head == NULL) + return -ENOMEM; + + head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */ + fc = mac_cb_type(skb); + + if (!saddr) { + spin_lock_bh(&priv->mib_lock); + + if (priv->short_addr == IEEE802154_ADDR_BROADCAST || + priv->short_addr == IEEE802154_ADDR_UNDEF || + priv->pan_id == IEEE802154_PANID_BROADCAST) { + dev_addr.addr_type = IEEE802154_ADDR_LONG; + memcpy(dev_addr.hwaddr, dev->dev_addr, + IEEE802154_ADDR_LEN); + } else { + dev_addr.addr_type = IEEE802154_ADDR_SHORT; + dev_addr.short_addr = priv->short_addr; + } + + dev_addr.pan_id = priv->pan_id; + saddr = &dev_addr; + + spin_unlock_bh(&priv->mib_lock); + } + + if (daddr->addr_type != IEEE802154_ADDR_NONE) { + fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT); + + head[pos++] = daddr->pan_id & 0xff; + head[pos++] = daddr->pan_id >> 8; + + if (daddr->addr_type == IEEE802154_ADDR_SHORT) { + head[pos++] = daddr->short_addr & 0xff; + head[pos++] = daddr->short_addr >> 8; + } else { + mac802154_haddr_copy_swap(head + pos, daddr->hwaddr); + pos += IEEE802154_ADDR_LEN; + } + } + + if (saddr->addr_type != IEEE802154_ADDR_NONE) { + fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT); + + if ((saddr->pan_id == daddr->pan_id) && + (saddr->pan_id != IEEE802154_PANID_BROADCAST)) { + /* PANID compression/intra PAN */ + fc |= IEEE802154_FC_INTRA_PAN; + } else { + head[pos++] = saddr->pan_id & 0xff; + head[pos++] = saddr->pan_id >> 8; + } + + if (saddr->addr_type == IEEE802154_ADDR_SHORT) { + head[pos++] = saddr->short_addr & 0xff; + head[pos++] = saddr->short_addr >> 8; + } else { + mac802154_haddr_copy_swap(head + pos, saddr->hwaddr); + pos += IEEE802154_ADDR_LEN; + } + } + + head[0] = fc; + head[1] = fc >> 8; + + memcpy(skb_push(skb, pos), head, pos); + kfree(head); + + return pos; +} + +static int +mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) +{ + const u8 *hdr = skb_mac_header(skb); + const u8 *tail = skb_tail_pointer(skb); + struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; + u16 fc; + int da_type; + + if (hdr + 3 > tail) + goto malformed; + + fc = hdr[0] | (hdr[1] << 8); + + hdr += 3; + + da_type = IEEE802154_FC_DAMODE(fc); + addr->addr_type = IEEE802154_FC_SAMODE(fc); + + switch (da_type) { + case IEEE802154_ADDR_NONE: + if (fc & IEEE802154_FC_INTRA_PAN) + goto malformed; + break; + case IEEE802154_ADDR_LONG: + if (fc & IEEE802154_FC_INTRA_PAN) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + IEEE802154_ADDR_LEN > tail) + goto malformed; + + hdr += IEEE802154_ADDR_LEN; + break; + case IEEE802154_ADDR_SHORT: + if (fc & IEEE802154_FC_INTRA_PAN) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + 2 > tail) + goto malformed; + + hdr += 2; + break; + default: + goto malformed; + + } + + switch (addr->addr_type) { + case IEEE802154_ADDR_NONE: + break; + case IEEE802154_ADDR_LONG: + if (!(fc & IEEE802154_FC_INTRA_PAN)) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + IEEE802154_ADDR_LEN > tail) + goto malformed; + + mac802154_haddr_copy_swap(addr->hwaddr, hdr); + hdr += IEEE802154_ADDR_LEN; + break; + case IEEE802154_ADDR_SHORT: + if (!(fc & IEEE802154_FC_INTRA_PAN)) { + if (hdr + 2 > tail) + goto malformed; + addr->pan_id = hdr[0] | (hdr[1] << 8); + hdr += 2; + } + + if (hdr + 2 > tail) + goto malformed; + + addr->short_addr = hdr[0] | (hdr[1] << 8); + hdr += 2; + break; + default: + goto malformed; + } + + return sizeof(struct ieee802154_addr); + +malformed: + pr_debug("malformed packet\n"); + return 0; +} + +static netdev_tx_t +mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + u8 chan, page; + + priv = netdev_priv(dev); + + spin_lock_bh(&priv->mib_lock); + chan = priv->chan; + page = priv->page; + spin_unlock_bh(&priv->mib_lock); + + if (chan == MAC802154_CHAN_NONE || + page >= WPAN_NUM_PAGES || + chan >= WPAN_NUM_CHANNELS) + return NETDEV_TX_OK; + + skb->skb_iif = dev->ifindex; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + return mac802154_tx(priv->hw, skb, page, chan); +} + +static struct header_ops mac802154_header_ops = { + .create = mac802154_header_create, + .parse = mac802154_header_parse, +}; + +static const struct net_device_ops mac802154_wpan_ops = { + .ndo_open = mac802154_slave_open, + .ndo_stop = mac802154_slave_close, + .ndo_start_xmit = mac802154_wpan_xmit, + .ndo_do_ioctl = mac802154_wpan_ioctl, + .ndo_set_mac_address = mac802154_wpan_mac_addr, +}; + +void mac802154_wpan_setup(struct net_device *dev) +{ + struct mac802154_sub_if_data *priv; + + dev->addr_len = IEEE802154_ADDR_LEN; + memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); + + dev->hard_header_len = MAC802154_FRAME_HARD_HEADER_LEN; + dev->header_ops = &mac802154_header_ops; + dev->needed_tailroom = 2; /* FCS */ + dev->mtu = IEEE802154_MTU; + dev->tx_queue_len = 10; + dev->type = ARPHRD_IEEE802154; + dev->flags = IFF_NOARP | IFF_BROADCAST; + dev->watchdog_timeo = 0; + + dev->destructor = free_netdev; + dev->netdev_ops = &mac802154_wpan_ops; + dev->ml_priv = &mac802154_mlme_wpan; + + priv = netdev_priv(dev); + priv->type = IEEE802154_DEV_WPAN; + + priv->chan = MAC802154_CHAN_NONE; + priv->page = 0; + + spin_lock_init(&priv->mib_lock); + + get_random_bytes(&priv->bsn, 1); + get_random_bytes(&priv->dsn, 1); + + priv->pan_id = IEEE802154_PANID_BROADCAST; + priv->short_addr = IEEE802154_ADDR_BROADCAST; +} + +static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) +{ + return netif_rx(skb); +} + +static int +mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) +{ + pr_debug("getting packet via slave interface %s\n", sdata->dev->name); + + spin_lock_bh(&sdata->mib_lock); + + switch (mac_cb(skb)->da.addr_type) { + case IEEE802154_ADDR_NONE: + if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) + /* FIXME: check if we are PAN coordinator */ + skb->pkt_type = PACKET_OTHERHOST; + else + /* ACK comes with both addresses empty */ + skb->pkt_type = PACKET_HOST; + break; + case IEEE802154_ADDR_LONG: + if (mac_cb(skb)->da.pan_id != sdata->pan_id && + mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + skb->pkt_type = PACKET_OTHERHOST; + else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr, + IEEE802154_ADDR_LEN)) + skb->pkt_type = PACKET_HOST; + else + skb->pkt_type = PACKET_OTHERHOST; + break; + case IEEE802154_ADDR_SHORT: + if (mac_cb(skb)->da.pan_id != sdata->pan_id && + mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + skb->pkt_type = PACKET_OTHERHOST; + else if (mac_cb(skb)->da.short_addr == sdata->short_addr) + skb->pkt_type = PACKET_HOST; + else if (mac_cb(skb)->da.short_addr == + IEEE802154_ADDR_BROADCAST) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_OTHERHOST; + break; + default: + break; + } + + spin_unlock_bh(&sdata->mib_lock); + + skb->dev = sdata->dev; + + sdata->dev->stats.rx_packets++; + sdata->dev->stats.rx_bytes += skb->len; + + switch (mac_cb_type(skb)) { + case IEEE802154_FC_TYPE_DATA: + return mac802154_process_data(sdata->dev, skb); + default: + pr_warning("ieee802154: bad frame received (type = %d)\n", + mac_cb_type(skb)); + kfree_skb(skb); + return NET_RX_DROP; + } +} + +static int mac802154_parse_frame_start(struct sk_buff *skb) +{ + u8 *head = skb->data; + u16 fc; + + if (mac802154_fetch_skb_u16(skb, &fc) || + mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq))) + goto err; + + pr_debug("fc: %04x dsn: %02x\n", fc, head[2]); + + mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc); + mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc); + mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc); + + if (fc & IEEE802154_FC_INTRA_PAN) + mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN; + + if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) { + if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id))) + goto err; + + /* source PAN id compression */ + if (mac_cb_is_intrapan(skb)) + mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id; + + pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + + if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) { + u16 *da = &(mac_cb(skb)->da.short_addr); + + if (mac802154_fetch_skb_u16(skb, da)) + goto err; + + pr_debug("destination address is short: %04x\n", + mac_cb(skb)->da.short_addr); + } else { + if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) + goto err; + + mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr, + skb->data); + skb_pull(skb, IEEE802154_ADDR_LEN); + + pr_debug("destination address is hardware\n"); + } + } + + if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) { + /* non PAN-compression, fetch source address id */ + if (!(mac_cb_is_intrapan(skb))) { + u16 *sa_pan = &(mac_cb(skb)->sa.pan_id); + + if (mac802154_fetch_skb_u16(skb, sa_pan)) + goto err; + } + + pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + + if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) { + u16 *sa = &(mac_cb(skb)->sa.short_addr); + + if (mac802154_fetch_skb_u16(skb, sa)) + goto err; + + pr_debug("source address is short: %04x\n", + mac_cb(skb)->sa.short_addr); + } else { + if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) + goto err; + + mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr, + skb->data); + skb_pull(skb, IEEE802154_ADDR_LEN); + + pr_debug("source address is hardware\n"); + } + } + + return 0; +err: + return -EINVAL; +} + +void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) +{ + int ret; + struct sk_buff *sskb; + struct mac802154_sub_if_data *sdata; + + ret = mac802154_parse_frame_start(skb); + if (ret) { + pr_debug("got invalid frame\n"); + return; + } + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &priv->slaves, list) { + if (sdata->type != IEEE802154_DEV_WPAN) + continue; + + sskb = skb_clone(skb, GFP_ATOMIC); + if (sskb) + mac802154_subif_frame(sdata, sskb); + } + rcu_read_unlock(); +} -- cgit v1.2.3 From 7b8e19b67c1b171a04f6bd2f973d0b38cb496bf6 Mon Sep 17 00:00:00 2001 From: "alex.bluesman.smirnov@gmail.com" Date: Mon, 25 Jun 2012 23:24:53 +0000 Subject: drivers/ieee802154: add support for the at86rf230/231 transceivers The AT86RF231 is a feature rich, low-power 2.4 GHz radio transceiver designed for industrial and consumer ZigBee/IEEE 802.15.4, 6LoWPAN, RF4CE and high data rate 2.4 GHz ISM band applications. This patch adds support for the Atmel RF230/231 radio transceivers. Signed-off-by: Alexander Smirnov Signed-off-by: David S. Miller --- drivers/ieee802154/Kconfig | 6 + drivers/ieee802154/Makefile | 1 + drivers/ieee802154/at86rf230.c | 965 +++++++++++++++++++++++++++++++++++++++++ include/linux/spi/at86rf230.h | 31 ++ 4 files changed, 1003 insertions(+) create mode 100644 drivers/ieee802154/at86rf230.c create mode 100644 include/linux/spi/at86rf230.h (limited to 'include/linux') diff --git a/drivers/ieee802154/Kconfig b/drivers/ieee802154/Kconfig index 15c064073701..1fc4eefc20ed 100644 --- a/drivers/ieee802154/Kconfig +++ b/drivers/ieee802154/Kconfig @@ -19,6 +19,7 @@ config IEEE802154_FAKEHARD This driver can also be built as a module. To do so say M here. The module will be called 'fakehard'. + config IEEE802154_FAKELB depends on IEEE802154_DRIVERS && MAC802154 tristate "IEEE 802.15.4 loopback driver" @@ -28,3 +29,8 @@ config IEEE802154_FAKELB This driver can also be built as a module. To do so say M here. The module will be called 'fakelb'. + +config IEEE802154_AT86RF230 + depends on IEEE802154_DRIVERS && MAC802154 + tristate "AT86RF230/231 transceiver driver" + depends on SPI diff --git a/drivers/ieee802154/Makefile b/drivers/ieee802154/Makefile index ea784ea6f0f8..4f4371d3aa7d 100644 --- a/drivers/ieee802154/Makefile +++ b/drivers/ieee802154/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_IEEE802154_FAKEHARD) += fakehard.o obj-$(CONFIG_IEEE802154_FAKELB) += fakelb.o +obj-$(CONFIG_IEEE802154_AT86RF230) += at86rf230.o diff --git a/drivers/ieee802154/at86rf230.c b/drivers/ieee802154/at86rf230.c new file mode 100644 index 000000000000..4d033d4c4ddc --- /dev/null +++ b/drivers/ieee802154/at86rf230.c @@ -0,0 +1,965 @@ +/* + * AT86RF230/RF231 driver + * + * Copyright (C) 2009-2012 Siemens AG + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov + * Alexander Smirnov + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +struct at86rf230_local { + struct spi_device *spi; + int rstn, slp_tr, dig2; + + u8 part; + u8 vers; + + u8 buf[2]; + struct mutex bmux; + + struct work_struct irqwork; + struct completion tx_complete; + + struct ieee802154_dev *dev; + + spinlock_t lock; + bool irq_disabled; + bool is_tx; +}; + +#define RG_TRX_STATUS (0x01) +#define SR_TRX_STATUS 0x01, 0x1f, 0 +#define SR_RESERVED_01_3 0x01, 0x20, 5 +#define SR_CCA_STATUS 0x01, 0x40, 6 +#define SR_CCA_DONE 0x01, 0x80, 7 +#define RG_TRX_STATE (0x02) +#define SR_TRX_CMD 0x02, 0x1f, 0 +#define SR_TRAC_STATUS 0x02, 0xe0, 5 +#define RG_TRX_CTRL_0 (0x03) +#define SR_CLKM_CTRL 0x03, 0x07, 0 +#define SR_CLKM_SHA_SEL 0x03, 0x08, 3 +#define SR_PAD_IO_CLKM 0x03, 0x30, 4 +#define SR_PAD_IO 0x03, 0xc0, 6 +#define RG_TRX_CTRL_1 (0x04) +#define SR_IRQ_POLARITY 0x04, 0x01, 0 +#define SR_IRQ_MASK_MODE 0x04, 0x02, 1 +#define SR_SPI_CMD_MODE 0x04, 0x0c, 2 +#define SR_RX_BL_CTRL 0x04, 0x10, 4 +#define SR_TX_AUTO_CRC_ON 0x04, 0x20, 5 +#define SR_IRQ_2_EXT_EN 0x04, 0x40, 6 +#define SR_PA_EXT_EN 0x04, 0x80, 7 +#define RG_PHY_TX_PWR (0x05) +#define SR_TX_PWR 0x05, 0x0f, 0 +#define SR_PA_LT 0x05, 0x30, 4 +#define SR_PA_BUF_LT 0x05, 0xc0, 6 +#define RG_PHY_RSSI (0x06) +#define SR_RSSI 0x06, 0x1f, 0 +#define SR_RND_VALUE 0x06, 0x60, 5 +#define SR_RX_CRC_VALID 0x06, 0x80, 7 +#define RG_PHY_ED_LEVEL (0x07) +#define SR_ED_LEVEL 0x07, 0xff, 0 +#define RG_PHY_CC_CCA (0x08) +#define SR_CHANNEL 0x08, 0x1f, 0 +#define SR_CCA_MODE 0x08, 0x60, 5 +#define SR_CCA_REQUEST 0x08, 0x80, 7 +#define RG_CCA_THRES (0x09) +#define SR_CCA_ED_THRES 0x09, 0x0f, 0 +#define SR_RESERVED_09_1 0x09, 0xf0, 4 +#define RG_RX_CTRL (0x0a) +#define SR_PDT_THRES 0x0a, 0x0f, 0 +#define SR_RESERVED_0a_1 0x0a, 0xf0, 4 +#define RG_SFD_VALUE (0x0b) +#define SR_SFD_VALUE 0x0b, 0xff, 0 +#define RG_TRX_CTRL_2 (0x0c) +#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0 +#define SR_RESERVED_0c_2 0x0c, 0x7c, 2 +#define SR_RX_SAFE_MODE 0x0c, 0x80, 7 +#define RG_ANT_DIV (0x0d) +#define SR_ANT_CTRL 0x0d, 0x03, 0 +#define SR_ANT_EXT_SW_EN 0x0d, 0x04, 2 +#define SR_ANT_DIV_EN 0x0d, 0x08, 3 +#define SR_RESERVED_0d_2 0x0d, 0x70, 4 +#define SR_ANT_SEL 0x0d, 0x80, 7 +#define RG_IRQ_MASK (0x0e) +#define SR_IRQ_MASK 0x0e, 0xff, 0 +#define RG_IRQ_STATUS (0x0f) +#define SR_IRQ_0_PLL_LOCK 0x0f, 0x01, 0 +#define SR_IRQ_1_PLL_UNLOCK 0x0f, 0x02, 1 +#define SR_IRQ_2_RX_START 0x0f, 0x04, 2 +#define SR_IRQ_3_TRX_END 0x0f, 0x08, 3 +#define SR_IRQ_4_CCA_ED_DONE 0x0f, 0x10, 4 +#define SR_IRQ_5_AMI 0x0f, 0x20, 5 +#define SR_IRQ_6_TRX_UR 0x0f, 0x40, 6 +#define SR_IRQ_7_BAT_LOW 0x0f, 0x80, 7 +#define RG_VREG_CTRL (0x10) +#define SR_RESERVED_10_6 0x10, 0x03, 0 +#define SR_DVDD_OK 0x10, 0x04, 2 +#define SR_DVREG_EXT 0x10, 0x08, 3 +#define SR_RESERVED_10_3 0x10, 0x30, 4 +#define SR_AVDD_OK 0x10, 0x40, 6 +#define SR_AVREG_EXT 0x10, 0x80, 7 +#define RG_BATMON (0x11) +#define SR_BATMON_VTH 0x11, 0x0f, 0 +#define SR_BATMON_HR 0x11, 0x10, 4 +#define SR_BATMON_OK 0x11, 0x20, 5 +#define SR_RESERVED_11_1 0x11, 0xc0, 6 +#define RG_XOSC_CTRL (0x12) +#define SR_XTAL_TRIM 0x12, 0x0f, 0 +#define SR_XTAL_MODE 0x12, 0xf0, 4 +#define RG_RX_SYN (0x15) +#define SR_RX_PDT_LEVEL 0x15, 0x0f, 0 +#define SR_RESERVED_15_2 0x15, 0x70, 4 +#define SR_RX_PDT_DIS 0x15, 0x80, 7 +#define RG_XAH_CTRL_1 (0x17) +#define SR_RESERVED_17_8 0x17, 0x01, 0 +#define SR_AACK_PROM_MODE 0x17, 0x02, 1 +#define SR_AACK_ACK_TIME 0x17, 0x04, 2 +#define SR_RESERVED_17_5 0x17, 0x08, 3 +#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4 +#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5 +#define SR_RESERVED_17_2 0x17, 0x40, 6 +#define SR_RESERVED_17_1 0x17, 0x80, 7 +#define RG_FTN_CTRL (0x18) +#define SR_RESERVED_18_2 0x18, 0x7f, 0 +#define SR_FTN_START 0x18, 0x80, 7 +#define RG_PLL_CF (0x1a) +#define SR_RESERVED_1a_2 0x1a, 0x7f, 0 +#define SR_PLL_CF_START 0x1a, 0x80, 7 +#define RG_PLL_DCU (0x1b) +#define SR_RESERVED_1b_3 0x1b, 0x3f, 0 +#define SR_RESERVED_1b_2 0x1b, 0x40, 6 +#define SR_PLL_DCU_START 0x1b, 0x80, 7 +#define RG_PART_NUM (0x1c) +#define SR_PART_NUM 0x1c, 0xff, 0 +#define RG_VERSION_NUM (0x1d) +#define SR_VERSION_NUM 0x1d, 0xff, 0 +#define RG_MAN_ID_0 (0x1e) +#define SR_MAN_ID_0 0x1e, 0xff, 0 +#define RG_MAN_ID_1 (0x1f) +#define SR_MAN_ID_1 0x1f, 0xff, 0 +#define RG_SHORT_ADDR_0 (0x20) +#define SR_SHORT_ADDR_0 0x20, 0xff, 0 +#define RG_SHORT_ADDR_1 (0x21) +#define SR_SHORT_ADDR_1 0x21, 0xff, 0 +#define RG_PAN_ID_0 (0x22) +#define SR_PAN_ID_0 0x22, 0xff, 0 +#define RG_PAN_ID_1 (0x23) +#define SR_PAN_ID_1 0x23, 0xff, 0 +#define RG_IEEE_ADDR_0 (0x24) +#define SR_IEEE_ADDR_0 0x24, 0xff, 0 +#define RG_IEEE_ADDR_1 (0x25) +#define SR_IEEE_ADDR_1 0x25, 0xff, 0 +#define RG_IEEE_ADDR_2 (0x26) +#define SR_IEEE_ADDR_2 0x26, 0xff, 0 +#define RG_IEEE_ADDR_3 (0x27) +#define SR_IEEE_ADDR_3 0x27, 0xff, 0 +#define RG_IEEE_ADDR_4 (0x28) +#define SR_IEEE_ADDR_4 0x28, 0xff, 0 +#define RG_IEEE_ADDR_5 (0x29) +#define SR_IEEE_ADDR_5 0x29, 0xff, 0 +#define RG_IEEE_ADDR_6 (0x2a) +#define SR_IEEE_ADDR_6 0x2a, 0xff, 0 +#define RG_IEEE_ADDR_7 (0x2b) +#define SR_IEEE_ADDR_7 0x2b, 0xff, 0 +#define RG_XAH_CTRL_0 (0x2c) +#define SR_SLOTTED_OPERATION 0x2c, 0x01, 0 +#define SR_MAX_CSMA_RETRIES 0x2c, 0x0e, 1 +#define SR_MAX_FRAME_RETRIES 0x2c, 0xf0, 4 +#define RG_CSMA_SEED_0 (0x2d) +#define SR_CSMA_SEED_0 0x2d, 0xff, 0 +#define RG_CSMA_SEED_1 (0x2e) +#define SR_CSMA_SEED_1 0x2e, 0x07, 0 +#define SR_AACK_I_AM_COORD 0x2e, 0x08, 3 +#define SR_AACK_DIS_ACK 0x2e, 0x10, 4 +#define SR_AACK_SET_PD 0x2e, 0x20, 5 +#define SR_AACK_FVN_MODE 0x2e, 0xc0, 6 +#define RG_CSMA_BE (0x2f) +#define SR_MIN_BE 0x2f, 0x0f, 0 +#define SR_MAX_BE 0x2f, 0xf0, 4 + +#define CMD_REG 0x80 +#define CMD_REG_MASK 0x3f +#define CMD_WRITE 0x40 +#define CMD_FB 0x20 + +#define IRQ_BAT_LOW (1 << 7) +#define IRQ_TRX_UR (1 << 6) +#define IRQ_AMI (1 << 5) +#define IRQ_CCA_ED (1 << 4) +#define IRQ_TRX_END (1 << 3) +#define IRQ_RX_START (1 << 2) +#define IRQ_PLL_UNL (1 << 1) +#define IRQ_PLL_LOCK (1 << 0) + +#define STATE_P_ON 0x00 /* BUSY */ +#define STATE_BUSY_RX 0x01 +#define STATE_BUSY_TX 0x02 +#define STATE_FORCE_TRX_OFF 0x03 +#define STATE_FORCE_TX_ON 0x04 /* IDLE */ +/* 0x05 */ /* INVALID_PARAMETER */ +#define STATE_RX_ON 0x06 +/* 0x07 */ /* SUCCESS */ +#define STATE_TRX_OFF 0x08 +#define STATE_TX_ON 0x09 +/* 0x0a - 0x0e */ /* 0x0a - UNSUPPORTED_ATTRIBUTE */ +#define STATE_SLEEP 0x0F +#define STATE_BUSY_RX_AACK 0x11 +#define STATE_BUSY_TX_ARET 0x12 +#define STATE_BUSY_RX_AACK_ON 0x16 +#define STATE_BUSY_TX_ARET_ON 0x19 +#define STATE_RX_ON_NOCLK 0x1C +#define STATE_RX_AACK_ON_NOCLK 0x1D +#define STATE_BUSY_RX_AACK_NOCLK 0x1E +#define STATE_TRANSITION_IN_PROGRESS 0x1F + +static int +__at86rf230_write(struct at86rf230_local *lp, u8 addr, u8 data) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer = { + .len = 2, + .tx_buf = buf, + }; + + buf[0] = (addr & CMD_REG_MASK) | CMD_REG | CMD_WRITE; + buf[1] = data; + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + status = spi_sync(lp->spi, &msg); + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + if (msg.status) + status = msg.status; + + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + + return status; +} + +static int +__at86rf230_read_subreg(struct at86rf230_local *lp, + u8 addr, u8 mask, int shift, u8 *data) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer = { + .len = 2, + .tx_buf = buf, + .rx_buf = buf, + }; + + buf[0] = (addr & CMD_REG_MASK) | CMD_REG; + buf[1] = 0xff; + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + status = spi_sync(lp->spi, &msg); + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + if (msg.status) + status = msg.status; + + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + + if (status == 0) + *data = buf[1]; + + return status; +} + +static int +at86rf230_read_subreg(struct at86rf230_local *lp, + u8 addr, u8 mask, int shift, u8 *data) +{ + int status; + + mutex_lock(&lp->bmux); + status = __at86rf230_read_subreg(lp, addr, mask, shift, data); + mutex_unlock(&lp->bmux); + + return status; +} + +static int +at86rf230_write_subreg(struct at86rf230_local *lp, + u8 addr, u8 mask, int shift, u8 data) +{ + int status; + u8 val; + + mutex_lock(&lp->bmux); + status = __at86rf230_read_subreg(lp, addr, 0xff, 0, &val); + if (status) + goto out; + + val &= ~mask; + val |= (data << shift) & mask; + + status = __at86rf230_write(lp, addr, val); +out: + mutex_unlock(&lp->bmux); + + return status; +} + +static int +at86rf230_write_fbuf(struct at86rf230_local *lp, u8 *data, u8 len) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer_head = { + .len = 2, + .tx_buf = buf, + + }; + struct spi_transfer xfer_buf = { + .len = len, + .tx_buf = data, + }; + + mutex_lock(&lp->bmux); + buf[0] = CMD_WRITE | CMD_FB; + buf[1] = len + 2; /* 2 bytes for CRC that isn't written */ + + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head, &msg); + spi_message_add_tail(&xfer_buf, &msg); + + status = spi_sync(lp->spi, &msg); + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + if (msg.status) + status = msg.status; + + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + + mutex_unlock(&lp->bmux); + return status; +} + +static int +at86rf230_read_fbuf(struct at86rf230_local *lp, u8 *data, u8 *len, u8 *lqi) +{ + u8 *buf = lp->buf; + int status; + struct spi_message msg; + struct spi_transfer xfer_head = { + .len = 2, + .tx_buf = buf, + .rx_buf = buf, + }; + struct spi_transfer xfer_head1 = { + .len = 2, + .tx_buf = buf, + .rx_buf = buf, + }; + struct spi_transfer xfer_buf = { + .len = 0, + .rx_buf = data, + }; + + mutex_lock(&lp->bmux); + + buf[0] = CMD_FB; + buf[1] = 0x00; + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head, &msg); + + status = spi_sync(lp->spi, &msg); + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + + xfer_buf.len = *(buf + 1) + 1; + *len = buf[1]; + + buf[0] = CMD_FB; + buf[1] = 0x00; + + spi_message_init(&msg); + spi_message_add_tail(&xfer_head1, &msg); + spi_message_add_tail(&xfer_buf, &msg); + + status = spi_sync(lp->spi, &msg); + + if (msg.status) + status = msg.status; + + dev_vdbg(&lp->spi->dev, "status = %d\n", status); + dev_vdbg(&lp->spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&lp->spi->dev, "buf[1] = %02x\n", buf[1]); + + if (status) { + if (lqi && (*len > lp->buf[1])) + *lqi = data[lp->buf[1]]; + } + mutex_unlock(&lp->bmux); + + return status; +} + +static int +at86rf230_ed(struct ieee802154_dev *dev, u8 *level) +{ + might_sleep(); + BUG_ON(!level); + *level = 0xbe; + return 0; +} + +static int +at86rf230_state(struct ieee802154_dev *dev, int state) +{ + struct at86rf230_local *lp = dev->priv; + int rc; + u8 val; + u8 desired_status; + + might_sleep(); + + if (state == STATE_FORCE_TX_ON) + desired_status = STATE_TX_ON; + else if (state == STATE_FORCE_TRX_OFF) + desired_status = STATE_TRX_OFF; + else + desired_status = state; + + do { + rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &val); + if (rc) + goto err; + } while (val == STATE_TRANSITION_IN_PROGRESS); + + if (val == desired_status) + return 0; + + /* state is equal to phy states */ + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, state); + if (rc) + goto err; + + do { + rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &val); + if (rc) + goto err; + } while (val == STATE_TRANSITION_IN_PROGRESS); + + + if (val == desired_status) + return 0; + + pr_err("unexpected state change: %d, asked for %d\n", val, state); + return -EBUSY; + +err: + pr_err("error: %d\n", rc); + return rc; +} + +static int +at86rf230_start(struct ieee802154_dev *dev) +{ + struct at86rf230_local *lp = dev->priv; + u8 rc; + + rc = at86rf230_write_subreg(lp, SR_RX_SAFE_MODE, 1); + if (rc) + return rc; + + return at86rf230_state(dev, STATE_RX_ON); +} + +static void +at86rf230_stop(struct ieee802154_dev *dev) +{ + at86rf230_state(dev, STATE_FORCE_TRX_OFF); +} + +static int +at86rf230_channel(struct ieee802154_dev *dev, int page, int channel) +{ + struct at86rf230_local *lp = dev->priv; + int rc; + + might_sleep(); + + if (page != 0 || channel < 11 || channel > 26) { + WARN_ON(1); + return -EINVAL; + } + + rc = at86rf230_write_subreg(lp, SR_CHANNEL, channel); + msleep(1); /* Wait for PLL */ + dev->phy->current_channel = channel; + + return 0; +} + +static int +at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb) +{ + struct at86rf230_local *lp = dev->priv; + int rc; + unsigned long flags; + + might_sleep(); + + rc = at86rf230_state(dev, STATE_FORCE_TX_ON); + if (rc) + goto err; + + spin_lock_irqsave(&lp->lock, flags); + lp->is_tx = 1; + INIT_COMPLETION(lp->tx_complete); + spin_unlock_irqrestore(&lp->lock, flags); + + rc = at86rf230_write_fbuf(lp, skb->data, skb->len); + if (rc) + goto err_rx; + + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_BUSY_TX); + if (rc) + goto err_rx; + + rc = wait_for_completion_interruptible(&lp->tx_complete); + if (rc < 0) + goto err_rx; + + rc = at86rf230_start(dev); + + return rc; + +err_rx: + at86rf230_start(dev); +err: + pr_err("error: %d\n", rc); + + spin_lock_irqsave(&lp->lock, flags); + lp->is_tx = 0; + spin_unlock_irqrestore(&lp->lock, flags); + + return rc; +} + +static int at86rf230_rx(struct at86rf230_local *lp) +{ + u8 len = 128, lqi = 0; + int rc; + struct sk_buff *skb; + + skb = alloc_skb(len, GFP_KERNEL); + + if (!skb) + return -ENOMEM; + + if (at86rf230_write_subreg(lp, SR_RX_PDT_DIS, 1) || + at86rf230_read_fbuf(lp, skb_put(skb, len), &len, &lqi) || + at86rf230_write_subreg(lp, SR_RX_SAFE_MODE, 1) || + at86rf230_write_subreg(lp, SR_RX_PDT_DIS, 0)) { + goto err; + } + + if (len < 2) + goto err; + + skb_trim(skb, len - 2); /* We do not put CRC into the frame */ + + ieee802154_rx_irqsafe(lp->dev, skb, lqi); + + dev_dbg(&lp->spi->dev, "READ_FBUF: %d %d %x\n", rc, len, lqi); + + return 0; +err: + pr_debug("received frame is too small\n"); + + kfree_skb(skb); + return -EINVAL; +} + +static struct ieee802154_ops at86rf230_ops = { + .owner = THIS_MODULE, + .xmit = at86rf230_xmit, + .ed = at86rf230_ed, + .set_channel = at86rf230_channel, + .start = at86rf230_start, + .stop = at86rf230_stop, +}; + +static void at86rf230_irqwork(struct work_struct *work) +{ + struct at86rf230_local *lp = + container_of(work, struct at86rf230_local, irqwork); + u8 status = 0, val; + int rc; + unsigned long flags; + + spin_lock_irqsave(&lp->lock, flags); + rc = at86rf230_read_subreg(lp, RG_IRQ_STATUS, 0xff, 0, &val); + status |= val; + + status &= ~IRQ_PLL_LOCK; /* ignore */ + status &= ~IRQ_RX_START; /* ignore */ + status &= ~IRQ_AMI; /* ignore */ + status &= ~IRQ_TRX_UR; /* FIXME: possibly handle ???*/ + + if (status & IRQ_TRX_END) { + status &= ~IRQ_TRX_END; + if (lp->is_tx) { + lp->is_tx = 0; + complete(&lp->tx_complete); + } else { + at86rf230_rx(lp); + } + } + + if (lp->irq_disabled) { + lp->irq_disabled = 0; + enable_irq(lp->spi->irq); + } + spin_unlock_irqrestore(&lp->lock, flags); +} + +static irqreturn_t at86rf230_isr(int irq, void *data) +{ + struct at86rf230_local *lp = data; + + spin_lock(&lp->lock); + if (!lp->irq_disabled) { + disable_irq_nosync(irq); + lp->irq_disabled = 1; + } + spin_unlock(&lp->lock); + + schedule_work(&lp->irqwork); + + return IRQ_HANDLED; +} + + +static int at86rf230_hw_init(struct at86rf230_local *lp) +{ + u8 status; + int rc; + + rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); + if (rc) + return rc; + + dev_info(&lp->spi->dev, "Status: %02x\n", status); + if (status == STATE_P_ON) { + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TRX_OFF); + if (rc) + return rc; + msleep(1); + rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); + if (rc) + return rc; + dev_info(&lp->spi->dev, "Status: %02x\n", status); + } + + rc = at86rf230_write_subreg(lp, SR_IRQ_MASK, 0xff); /* IRQ_TRX_UR | + * IRQ_CCA_ED | + * IRQ_TRX_END | + * IRQ_PLL_UNL | + * IRQ_PLL_LOCK + */ + if (rc) + return rc; + + /* CLKM changes are applied immediately */ + rc = at86rf230_write_subreg(lp, SR_CLKM_SHA_SEL, 0x00); + if (rc) + return rc; + + /* Turn CLKM Off */ + rc = at86rf230_write_subreg(lp, SR_CLKM_CTRL, 0x00); + if (rc) + return rc; + /* Wait the next SLEEP cycle */ + msleep(100); + + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TX_ON); + if (rc) + return rc; + msleep(1); + + rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); + if (rc) + return rc; + dev_info(&lp->spi->dev, "Status: %02x\n", status); + + rc = at86rf230_read_subreg(lp, SR_DVDD_OK, &status); + if (rc) + return rc; + if (!status) { + dev_err(&lp->spi->dev, "DVDD error\n"); + return -EINVAL; + } + + rc = at86rf230_read_subreg(lp, SR_AVDD_OK, &status); + if (rc) + return rc; + if (!status) { + dev_err(&lp->spi->dev, "AVDD error\n"); + return -EINVAL; + } + + return 0; +} + +static int at86rf230_suspend(struct spi_device *spi, pm_message_t message) +{ + return 0; +} + +static int at86rf230_resume(struct spi_device *spi) +{ + return 0; +} + +static int at86rf230_fill_data(struct spi_device *spi) +{ + struct at86rf230_local *lp = spi_get_drvdata(spi); + struct at86rf230_platform_data *pdata = spi->dev.platform_data; + + if (!pdata) { + dev_err(&spi->dev, "no platform_data\n"); + return -EINVAL; + } + + lp->rstn = pdata->rstn; + lp->slp_tr = pdata->slp_tr; + lp->dig2 = pdata->dig2; + + return 0; +} + +static int __devinit at86rf230_probe(struct spi_device *spi) +{ + struct ieee802154_dev *dev; + struct at86rf230_local *lp; + u8 man_id_0, man_id_1; + int rc; + const char *chip; + int supported = 0; + + if (!spi->irq) { + dev_err(&spi->dev, "no IRQ specified\n"); + return -EINVAL; + } + + dev = ieee802154_alloc_device(sizeof(*lp), &at86rf230_ops); + if (!dev) + return -ENOMEM; + + lp = dev->priv; + lp->dev = dev; + + lp->spi = spi; + + dev->priv = lp; + dev->parent = &spi->dev; + dev->extra_tx_headroom = 0; + /* We do support only 2.4 Ghz */ + dev->phy->channels_supported[0] = 0x7FFF800; + dev->flags = IEEE802154_HW_OMIT_CKSUM; + + mutex_init(&lp->bmux); + INIT_WORK(&lp->irqwork, at86rf230_irqwork); + spin_lock_init(&lp->lock); + init_completion(&lp->tx_complete); + + spi_set_drvdata(spi, lp); + + rc = at86rf230_fill_data(spi); + if (rc) + goto err_fill; + + rc = gpio_request(lp->rstn, "rstn"); + if (rc) + goto err_rstn; + + if (gpio_is_valid(lp->slp_tr)) { + rc = gpio_request(lp->slp_tr, "slp_tr"); + if (rc) + goto err_slp_tr; + } + + rc = gpio_direction_output(lp->rstn, 1); + if (rc) + goto err_gpio_dir; + + if (gpio_is_valid(lp->slp_tr)) { + rc = gpio_direction_output(lp->slp_tr, 0); + if (rc) + goto err_gpio_dir; + } + + /* Reset */ + msleep(1); + gpio_set_value(lp->rstn, 0); + msleep(1); + gpio_set_value(lp->rstn, 1); + msleep(1); + + rc = at86rf230_read_subreg(lp, SR_MAN_ID_0, &man_id_0); + if (rc) + goto err_gpio_dir; + rc = at86rf230_read_subreg(lp, SR_MAN_ID_1, &man_id_1); + if (rc) + goto err_gpio_dir; + + if (man_id_1 != 0x00 || man_id_0 != 0x1f) { + dev_err(&spi->dev, "Non-Atmel dev found (MAN_ID %02x %02x)\n", + man_id_1, man_id_0); + rc = -EINVAL; + goto err_gpio_dir; + } + + rc = at86rf230_read_subreg(lp, SR_PART_NUM, &lp->part); + if (rc) + goto err_gpio_dir; + + rc = at86rf230_read_subreg(lp, SR_VERSION_NUM, &lp->vers); + if (rc) + goto err_gpio_dir; + + switch (lp->part) { + case 2: + chip = "at86rf230"; + /* supported = 1; FIXME: should be easy to support; */ + break; + case 3: + chip = "at86rf231"; + supported = 1; + break; + default: + chip = "UNKNOWN"; + break; + } + + dev_info(&spi->dev, "Detected %s chip version %d\n", chip, lp->vers); + if (!supported) { + rc = -ENOTSUPP; + goto err_gpio_dir; + } + + rc = at86rf230_hw_init(lp); + if (rc) + goto err_gpio_dir; + + rc = request_irq(spi->irq, at86rf230_isr, IRQF_SHARED, + dev_name(&spi->dev), lp); + if (rc) + goto err_gpio_dir; + + rc = ieee802154_register_device(lp->dev); + if (rc) + goto err_irq; + + return rc; + + ieee802154_unregister_device(lp->dev); +err_irq: + free_irq(spi->irq, lp); + flush_work(&lp->irqwork); +err_gpio_dir: + if (gpio_is_valid(lp->slp_tr)) + gpio_free(lp->slp_tr); +err_slp_tr: + gpio_free(lp->rstn); +err_rstn: +err_fill: + spi_set_drvdata(spi, NULL); + mutex_destroy(&lp->bmux); + ieee802154_free_device(lp->dev); + return rc; +} + +static int __devexit at86rf230_remove(struct spi_device *spi) +{ + struct at86rf230_local *lp = spi_get_drvdata(spi); + + ieee802154_unregister_device(lp->dev); + + free_irq(spi->irq, lp); + flush_work(&lp->irqwork); + + if (gpio_is_valid(lp->slp_tr)) + gpio_free(lp->slp_tr); + gpio_free(lp->rstn); + + spi_set_drvdata(spi, NULL); + mutex_destroy(&lp->bmux); + ieee802154_free_device(lp->dev); + + dev_dbg(&spi->dev, "unregistered at86rf230\n"); + return 0; +} + +static struct spi_driver at86rf230_driver = { + .driver = { + .name = "at86rf230", + .owner = THIS_MODULE, + }, + .probe = at86rf230_probe, + .remove = __devexit_p(at86rf230_remove), + .suspend = at86rf230_suspend, + .resume = at86rf230_resume, +}; + +static int __init at86rf230_init(void) +{ + return spi_register_driver(&at86rf230_driver); +} +module_init(at86rf230_init); + +static void __exit at86rf230_exit(void) +{ + spi_unregister_driver(&at86rf230_driver); +} +module_exit(at86rf230_exit); + +MODULE_DESCRIPTION("AT86RF230 Transceiver Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h new file mode 100644 index 000000000000..b2b1afbb3202 --- /dev/null +++ b/include/linux/spi/at86rf230.h @@ -0,0 +1,31 @@ +/* + * AT86RF230/RF231 driver + * + * Copyright (C) 2009-2012 Siemens AG + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Written by: + * Dmitry Eremin-Solenikov + */ +#ifndef AT86RF230_H +#define AT86RF230_H + +struct at86rf230_platform_data { + int rstn; + int slp_tr; + int dig2; +}; + +#endif -- cgit v1.2.3 From 52a4fd77808662a16cd17ad3b0e1ad75e0162d8b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 26 Jun 2012 06:52:46 +0000 Subject: team: do not allow to map disabled ports Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 5 ++--- drivers/net/team/team_mode_loadbalance.c | 3 ++- include/linux/if_team.h | 2 ++ 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6b4cf6eca238..5350eeaa22ce 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -614,8 +614,6 @@ static int team_change_mode(struct team *team, const char *kind) * Rx path frame handler ************************/ -static bool team_port_enabled(struct team_port *port); - /* note: already called with rcu_read_lock */ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) { @@ -673,10 +671,11 @@ static bool team_port_find(const struct team *team, return false; } -static bool team_port_enabled(struct team_port *port) +bool team_port_enabled(struct team_port *port) { return port->index != -1; } +EXPORT_SYMBOL(team_port_enabled); /* * Enable/disable port by adding to enabled port hashlist and setting diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index c92fa02d6a63..51a4b199c75c 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -359,7 +359,8 @@ static int lb_tx_hash_to_port_mapping_set(struct team *team, unsigned char hash = ctx->info->array_index; list_for_each_entry(port, &team->port_list, list) { - if (ctx->data.u32_val == port->dev->ifindex) { + if (ctx->data.u32_val == port->dev->ifindex && + team_port_enabled(port)) { rcu_assign_pointer(LB_HTPM_PORT_BY_HASH(lb_priv, hash), port); return 0; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index c1938869191f..e636a54e7a71 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -64,6 +64,8 @@ struct team_port { long mode_priv[0]; }; +extern bool team_port_enabled(struct team_port *port); + struct team_mode_ops { int (*init)(struct team *team); void (*exit)(struct team *team); -- cgit v1.2.3 From 4a9fbcc6d606ae7f6a4e65b8a2759f46be8d45c6 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 26 Jun 2012 06:52:47 +0000 Subject: team: remove unused rcu_head field from team_port struct Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index e636a54e7a71..99efd60fa8c9 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -60,7 +60,6 @@ struct team_port { unsigned int mtu; } orig; - struct rcu_head rcu; long mode_priv[0]; }; -- cgit v1.2.3 From c3deafc5261a9421b315ee0d0e8e36ba7857128c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 26 Jun 2012 21:51:35 -0700 Subject: netlink: Delete NLMSG_PUT and NLMSG_NEW. No longer used and a poor interface as they were macros with embedded gotos. Signed-off-by: David S. Miller --- include/linux/netlink.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 0f628ffa420c..ed33f0901bc2 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -241,14 +241,6 @@ struct netlink_notify { struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags); -#define NLMSG_NEW(skb, pid, seq, type, len, flags) \ -({ if (unlikely(skb_tailroom(skb) < (int)NLMSG_SPACE(len))) \ - goto nlmsg_failure; \ - __nlmsg_put(skb, pid, seq, type, len, flags); }) - -#define NLMSG_PUT(skb, pid, seq, type, len) \ - NLMSG_NEW(skb, pid, seq, type, len, 0) - struct netlink_dump_control { int (*dump)(struct sk_buff *skb, struct netlink_callback *); int (*done)(struct netlink_callback*); -- cgit v1.2.3 From 392025f87a5105c640cf1b4b317c21c14c05a6f9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 26 Jun 2012 20:27:09 +0200 Subject: netfilter: ctnetlink: add new messages to obtain statistics This patch adds the following messages to ctnetlink: IPCTNL_MSG_CT_GET_STATS_CPU IPCTNL_MSG_CT_GET_STATS IPCTNL_MSG_EXP_GET_STATS_CPU To display connection tracking system per-cpu and global statistics. This provides a replacement for the following /proc interfaces: /proc/net/stat/nf_conntrack /proc/sys/net/netfilter/nf_conntrack_count Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_conntrack.h | 38 +++++ net/netfilter/nf_conntrack_netlink.c | 227 +++++++++++++++++++++++++- 2 files changed, 264 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 768883370080..f649f7423ca2 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -7,6 +7,8 @@ enum cntl_msg_types { IPCTNL_MSG_CT_GET, IPCTNL_MSG_CT_DELETE, IPCTNL_MSG_CT_GET_CTRZERO, + IPCTNL_MSG_CT_GET_STATS_CPU, + IPCTNL_MSG_CT_GET_STATS, IPCTNL_MSG_MAX }; @@ -15,6 +17,7 @@ enum ctnl_exp_msg_types { IPCTNL_MSG_EXP_NEW, IPCTNL_MSG_EXP_GET, IPCTNL_MSG_EXP_DELETE, + IPCTNL_MSG_EXP_GET_STATS_CPU, IPCTNL_MSG_EXP_MAX }; @@ -203,4 +206,39 @@ enum ctattr_secctx { }; #define CTA_SECCTX_MAX (__CTA_SECCTX_MAX - 1) +enum ctattr_stats_cpu { + CTA_STATS_UNSPEC, + CTA_STATS_SEARCHED, + CTA_STATS_FOUND, + CTA_STATS_NEW, + CTA_STATS_INVALID, + CTA_STATS_IGNORE, + CTA_STATS_DELETE, + CTA_STATS_DELETE_LIST, + CTA_STATS_INSERT, + CTA_STATS_INSERT_FAILED, + CTA_STATS_DROP, + CTA_STATS_EARLY_DROP, + CTA_STATS_ERROR, + CTA_STATS_SEARCH_RESTART, + __CTA_STATS_MAX, +}; +#define CTA_STATS_MAX (__CTA_STATS_MAX - 1) + +enum ctattr_stats_global { + CTA_STATS_GLOBAL_UNSPEC, + CTA_STATS_GLOBAL_ENTRIES, + __CTA_STATS_GLOBAL_MAX, +}; +#define CTA_STATS_GLOBAL_MAX (__CTA_STATS_GLOBAL_MAX - 1) + +enum ctattr_expect_stats { + CTA_STATS_EXP_UNSPEC, + CTA_STATS_EXP_NEW, + CTA_STATS_EXP_CREATE, + CTA_STATS_EXP_DELETE, + __CTA_STATS_EXP_MAX, +}; +#define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1) + #endif /* _IPCONNTRACK_NETLINK_H */ diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index b9b8f4ac7a36..14f67a2cbcb5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist * (C) 2002-2006 by Harald Welte * (C) 2003 by Patrick Mchardy - * (C) 2005-2011 by Pablo Neira Ayuso + * (C) 2005-2012 by Pablo Neira Ayuso * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -1627,6 +1627,155 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } +static int +ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 pid, u32 seq, + __u16 cpu, const struct ip_conntrack_stat *st) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS_CPU); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = htons(cpu); + + if (nla_put_be32(skb, CTA_STATS_SEARCHED, htonl(st->searched)) || + nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || + nla_put_be32(skb, CTA_STATS_NEW, htonl(st->new)) || + nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || + nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || + nla_put_be32(skb, CTA_STATS_DELETE, htonl(st->delete)) || + nla_put_be32(skb, CTA_STATS_DELETE_LIST, htonl(st->delete_list)) || + nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || + nla_put_be32(skb, CTA_STATS_INSERT_FAILED, + htonl(st->insert_failed)) || + nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || + nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || + nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || + nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, + htonl(st->search_restart))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int cpu; + struct net *net = sock_net(skb->sk); + + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + const struct ip_conntrack_stat *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(net->ct.stat, cpu); + if (ctnetlink_ct_stat_cpu_fill_info(skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + cpu, st) < 0) + break; + } + cb->args[0] = cpu; + + return skb->len; +} + +static int +ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_ct_stat_cpu_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return 0; +} + +static int +ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, + struct net *net) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int nr_conntracks = atomic_read(&net->ct.count); + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_stat_ct(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + struct sk_buff *skb2; + int err; + + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb2 == NULL) + return -ENOMEM; + + err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, + NFNL_MSG_TYPE(nlh->nlmsg_type), + sock_net(skb->sk)); + if (err <= 0) + goto free; + + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto out; + + return 0; + +free: + kfree_skb(skb2); +out: + /* this avoids a loop in nfnetlink. */ + return err == -EAGAIN ? -ENOBUFS : err; +} + #ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT static size_t ctnetlink_nfqueue_build_size(const struct nf_conn *ct) @@ -2440,6 +2589,79 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, return err; } +static int +ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int cpu, + const struct ip_conntrack_stat *st) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned int flags = pid ? NLM_F_MULTI : 0, event; + + event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_EXP_GET_STATS_CPU); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + if (nlh == NULL) + goto nlmsg_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = AF_UNSPEC; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = htons(cpu); + + if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || + nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || + nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return skb->len; + +nla_put_failure: +nlmsg_failure: + nlmsg_cancel(skb, nlh); + return -1; +} + +static int +ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int cpu; + struct net *net = sock_net(skb->sk); + + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + const struct ip_conntrack_stat *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(net->ct.stat, cpu); + if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + cpu, st) < 0) + break; + } + cb->args[0] = cpu; + + return skb->len; +} + +static int +ctnetlink_stat_exp_cpu(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_exp_stat_cpu_dump, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return 0; +} + #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .fcn = ctnetlink_conntrack_event, @@ -2463,6 +2685,8 @@ static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, + [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu }, + [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { @@ -2475,6 +2699,7 @@ static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, + [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu }, }; static const struct nfnetlink_subsystem ctnl_subsys = { -- cgit v1.2.3 From d2bb2b9e9161d221badafae063d0c62b41bf3078 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Mon, 25 Jun 2012 22:12:20 +0200 Subject: bcma: define some additional cores IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some of them are BCM4706 specific AFAWK. Most of them was confirmed on Netgear WNDR450. Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- drivers/bcma/scan.c | 6 ++++++ include/linux/bcma/bcma.h | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c index 5ed0718fc660..a3420585d942 100644 --- a/drivers/bcma/scan.c +++ b/drivers/bcma/scan.c @@ -28,6 +28,12 @@ static const struct bcma_device_id_name bcma_arm_device_names[] = { static const struct bcma_device_id_name bcma_bcm_device_names[] = { { BCMA_CORE_OOB_ROUTER, "OOB Router" }, + { BCMA_CORE_4706_CHIPCOMMON, "BCM4706 ChipCommon" }, + { BCMA_CORE_4706_SOC_RAM, "BCM4706 SOC RAM" }, + { BCMA_CORE_4706_MAC_GBIT, "BCM4706 GBit MAC" }, + { BCMA_CORE_AMEMC, "AMEMC (DDR)" }, + { BCMA_CORE_ALTA, "ALTA (I2S)" }, + { BCMA_CORE_4706_MAC_GBIT_COMMON, "BCM4706 GBit MAC Common" }, { BCMA_CORE_INVALID, "Invalid" }, { BCMA_CORE_CHIPCOMMON, "ChipCommon" }, { BCMA_CORE_ILINE20, "ILine 20" }, diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 8deaf6d050c3..12334f9190cb 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -70,6 +70,13 @@ struct bcma_host_ops { /* Core-ID values. */ #define BCMA_CORE_OOB_ROUTER 0x367 /* Out of band */ +#define BCMA_CORE_4706_CHIPCOMMON 0x500 +#define BCMA_CORE_4706_SOC_RAM 0x50E +#define BCMA_CORE_4706_MAC_GBIT 0x52D +#define BCMA_CORE_AMEMC 0x52E /* DDR1/2 memory controller core */ +#define BCMA_CORE_ALTA 0x534 /* I2S core */ +#define BCMA_CORE_4706_MAC_GBIT_COMMON 0x5DC +#define BCMA_CORE_DDR23_PHY 0x5DD #define BCMA_CORE_INVALID 0x700 #define BCMA_CORE_CHIPCOMMON 0x800 #define BCMA_CORE_ILINE20 0x801 -- cgit v1.2.3 From 4c3af034fafeb7269176bf1310c9bcff0b9fd9bb Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 26 Jun 2012 23:36:16 +0000 Subject: netlink: Get rid of obsolete rtnetlink macros Removes all RTA_GET*() and RTA_PUT*() variations, as well as the the unused rtattr_strcmp(). Get rid of rtm_get_table() by moving it to its only user decnet. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 129 ---------------------------------------------- net/core/rtnetlink.c | 13 ----- net/decnet/dn_fib.c | 8 +++ 3 files changed, 8 insertions(+), 142 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 2c1de8982c85..ea60b0854109 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -612,12 +612,6 @@ struct tcamsg { #include #include -static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) -{ - int len = strlen(str) + 1; - return len > rta->rta_len || memcmp(RTA_DATA(rta), str, len); -} - extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, @@ -628,122 +622,6 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, u32 ts, u32 tsage, long expires, u32 error); -extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data); - -#define RTA_PUT(skb, attrtype, attrlen, data) \ -({ if (unlikely(skb_tailroom(skb) < (int)RTA_SPACE(attrlen))) \ - goto rtattr_failure; \ - __rta_fill(skb, attrtype, attrlen, data); }) - -#define RTA_APPEND(skb, attrlen, data) \ -({ if (unlikely(skb_tailroom(skb) < (int)(attrlen))) \ - goto rtattr_failure; \ - memcpy(skb_put(skb, attrlen), data, attrlen); }) - -#define RTA_PUT_NOHDR(skb, attrlen, data) \ -({ RTA_APPEND(skb, RTA_ALIGN(attrlen), data); \ - memset(skb_tail_pointer(skb) - (RTA_ALIGN(attrlen) - attrlen), 0, \ - RTA_ALIGN(attrlen) - attrlen); }) - -#define RTA_PUT_U8(skb, attrtype, value) \ -({ u8 _tmp = (value); \ - RTA_PUT(skb, attrtype, sizeof(u8), &_tmp); }) - -#define RTA_PUT_U16(skb, attrtype, value) \ -({ u16 _tmp = (value); \ - RTA_PUT(skb, attrtype, sizeof(u16), &_tmp); }) - -#define RTA_PUT_U32(skb, attrtype, value) \ -({ u32 _tmp = (value); \ - RTA_PUT(skb, attrtype, sizeof(u32), &_tmp); }) - -#define RTA_PUT_U64(skb, attrtype, value) \ -({ u64 _tmp = (value); \ - RTA_PUT(skb, attrtype, sizeof(u64), &_tmp); }) - -#define RTA_PUT_SECS(skb, attrtype, value) \ - RTA_PUT_U64(skb, attrtype, (value) / HZ) - -#define RTA_PUT_MSECS(skb, attrtype, value) \ - RTA_PUT_U64(skb, attrtype, jiffies_to_msecs(value)) - -#define RTA_PUT_STRING(skb, attrtype, value) \ - RTA_PUT(skb, attrtype, strlen(value) + 1, value) - -#define RTA_PUT_FLAG(skb, attrtype) \ - RTA_PUT(skb, attrtype, 0, NULL); - -#define RTA_NEST(skb, type) \ -({ struct rtattr *__start = (struct rtattr *)skb_tail_pointer(skb); \ - RTA_PUT(skb, type, 0, NULL); \ - __start; }) - -#define RTA_NEST_END(skb, start) \ -({ (start)->rta_len = skb_tail_pointer(skb) - (unsigned char *)(start); \ - (skb)->len; }) - -#define RTA_NEST_COMPAT(skb, type, attrlen, data) \ -({ struct rtattr *__start = (struct rtattr *)skb_tail_pointer(skb); \ - RTA_PUT(skb, type, attrlen, data); \ - RTA_NEST(skb, type); \ - __start; }) - -#define RTA_NEST_COMPAT_END(skb, start) \ -({ struct rtattr *__nest = (void *)(start) + NLMSG_ALIGN((start)->rta_len); \ - (start)->rta_len = skb_tail_pointer(skb) - (unsigned char *)(start); \ - RTA_NEST_END(skb, __nest); \ - (skb)->len; }) - -#define RTA_NEST_CANCEL(skb, start) \ -({ if (start) \ - skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ - -1; }) - -#define RTA_GET_U8(rta) \ -({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u8)) \ - goto rtattr_failure; \ - *(u8 *) RTA_DATA(rta); }) - -#define RTA_GET_U16(rta) \ -({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u16)) \ - goto rtattr_failure; \ - *(u16 *) RTA_DATA(rta); }) - -#define RTA_GET_U32(rta) \ -({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u32)) \ - goto rtattr_failure; \ - *(u32 *) RTA_DATA(rta); }) - -#define RTA_GET_U64(rta) \ -({ u64 _tmp; \ - if (!rta || RTA_PAYLOAD(rta) < sizeof(u64)) \ - goto rtattr_failure; \ - memcpy(&_tmp, RTA_DATA(rta), sizeof(_tmp)); \ - _tmp; }) - -#define RTA_GET_FLAG(rta) (!!(rta)) - -#define RTA_GET_SECS(rta) ((unsigned long) RTA_GET_U64(rta) * HZ) -#define RTA_GET_MSECS(rta) (msecs_to_jiffies((unsigned long) RTA_GET_U64(rta))) - -static inline struct rtattr * -__rta_reserve(struct sk_buff *skb, int attrtype, int attrlen) -{ - struct rtattr *rta; - int size = RTA_LENGTH(attrlen); - - rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size)); - rta->rta_type = attrtype; - rta->rta_len = size; - memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); - return rta; -} - -#define __RTA_PUT(skb, attrtype, attrlen) \ -({ if (unlikely(skb_tailroom(skb) < (int)RTA_SPACE(attrlen))) \ - goto rtattr_failure; \ - __rta_reserve(skb, attrtype, attrlen); }) - extern void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change); /* RTNL is used as a global lock for all changes to network configuration */ @@ -794,13 +672,6 @@ extern void __rtnl_unlock(void); } \ } while(0) -static inline u32 rtm_get_table(struct rtattr **rta, u8 table) -{ - return RTA_GET_U32(rta[RTA_TABLE-1]); -rtattr_failure: - return table; -} - extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 21318d15bbc3..bc8a1cdaac98 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -541,19 +541,6 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, }; -void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) -{ - struct rtattr *rta; - int size = RTA_LENGTH(attrlen); - - rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size)); - rta->rta_type = attrtype; - rta->rta_len = size; - memcpy(RTA_DATA(rta), data, attrlen); - memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); -} -EXPORT_SYMBOL(__rta_fill); - int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 7eaf98799729..102d6106a942 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,6 +505,14 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) return 0; } +static inline u32 rtm_get_table(struct rtattr **rta, u8 table) +{ + if (rta[RTA_TABLE - 1]) + table = nla_get_u32((struct nlattr *) rta[RTA_TABLE - 1]); + + return table; +} + static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); -- cgit v1.2.3 From e440cf2ca0a1b075c64016240d46c3aa9d877bbf Mon Sep 17 00:00:00 2001 From: "parav.pandit@emulex.com" Date: Wed, 27 Jun 2012 03:56:12 +0000 Subject: net: added support for 40GbE link. 1. removed code replication for tov calculation for 1G, 10G and made is common for speed > 1G (1G, 10G, 40G, 100G). 2. defines values for #4 different 40G Phys (KR4, LF4, SR4, CR4) Signed-off-by: Parav Pandit Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 8 ++++++++ net/packet/af_packet.c | 18 ++++++------------ 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 297370a6cb18..21eff418091b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1153,6 +1153,10 @@ struct ethtool_ops { #define SUPPORTED_10000baseR_FEC (1 << 20) #define SUPPORTED_20000baseMLD2_Full (1 << 21) #define SUPPORTED_20000baseKR2_Full (1 << 22) +#define SUPPORTED_40000baseKR4_Full (1 << 23) +#define SUPPORTED_40000baseCR4_Full (1 << 24) +#define SUPPORTED_40000baseSR4_Full (1 << 25) +#define SUPPORTED_40000baseLR4_Full (1 << 26) /* Indicates what features are advertised by the interface. */ #define ADVERTISED_10baseT_Half (1 << 0) @@ -1178,6 +1182,10 @@ struct ethtool_ops { #define ADVERTISED_10000baseR_FEC (1 << 20) #define ADVERTISED_20000baseMLD2_Full (1 << 21) #define ADVERTISED_20000baseKR2_Full (1 << 22) +#define ADVERTISED_40000baseKR4_Full (1 << 23) +#define ADVERTISED_40000baseCR4_Full (1 << 24) +#define ADVERTISED_40000baseSR4_Full (1 << 25) +#define ADVERTISED_40000baseLR4_Full (1 << 26) /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8a10d5b3c832..ceaca7c134a0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -531,6 +531,7 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, unsigned int mbits = 0, msec = 0, div = 0, tmo = 0; struct ethtool_cmd ecmd; int err; + u32 speed; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); @@ -539,25 +540,18 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_settings(dev, &ecmd); + speed = ethtool_cmd_speed(&ecmd); rtnl_unlock(); if (!err) { - switch (ecmd.speed) { - case SPEED_10000: - msec = 1; - div = 10000/1000; - break; - case SPEED_1000: - msec = 1; - div = 1000/1000; - break; /* * If the link speed is so slow you don't really * need to worry about perf anyways */ - case SPEED_100: - case SPEED_10: - default: + if (speed < SPEED_1000 || speed == SPEED_UNKNOWN) { return DEFAULT_PRB_RETIRE_TOV; + } else { + msec = 1; + div = speed / 1000; } } -- cgit v1.2.3 From ac28b9f8cd66d6bc54f8063df59e99abd62173a4 Mon Sep 17 00:00:00 2001 From: David Daney Date: Wed, 27 Jun 2012 07:33:35 +0000 Subject: netdev/phy: Handle IEEE802.3 clause 45 Ethernet PHYs The IEEE802.3 clause 45 MDIO bus protocol allows for directly addressing PHY registers using a 21 bit address, and is used by many 10G Ethernet PHYS. Already existing is the ability of MDIO bus drivers to use clause 45, with the MII_ADDR_C45 flag. Here we add struct phy_c45_device_ids to hold the device identifier registers present in clause 45. struct phy_device gets a couple of new fields: c45_ids to hold the identifiers and is_c45 to signal that it is clause 45. get_phy_device() gets a new parameter is_c45 to indicate that the PHY device should use the clause 45 protocol, and its callers are adjusted to pass false. The follow-on patch to of_mdio.c will pass true where appropriate. EXPORT phy_device_create() so that the follow-on patch to of_mdio.c can use it to create phy devices for PHYs, that have non-standard device identifier registers, based on the device tree bindings. Signed-off-by: David Daney Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 2 +- drivers/net/phy/phy_device.c | 105 +++++++++++++++++++++++++++++++++++++++---- drivers/of/of_mdio.c | 2 +- include/linux/phy.h | 18 +++++++- 4 files changed, 116 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 31470b0d0c32..2cee6d218d21 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -232,7 +232,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr) struct phy_device *phydev; int err; - phydev = get_phy_device(bus, addr); + phydev = get_phy_device(bus, addr, false); if (IS_ERR(phydev) || phydev == NULL) return phydev; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 18ab0daf4490..ef4cdeebedd6 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -152,8 +152,8 @@ int phy_scan_fixups(struct phy_device *phydev) } EXPORT_SYMBOL(phy_scan_fixups); -static struct phy_device* phy_device_create(struct mii_bus *bus, - int addr, int phy_id) +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, + bool is_c45, struct phy_c45_device_ids *c45_ids) { struct phy_device *dev; @@ -174,8 +174,11 @@ static struct phy_device* phy_device_create(struct mii_bus *bus, dev->autoneg = AUTONEG_ENABLE; + dev->is_c45 = is_c45; dev->addr = addr; dev->phy_id = phy_id; + if (c45_ids) + dev->c45_ids = *c45_ids; dev->bus = bus; dev->dev.parent = bus->parent; dev->dev.bus = &mdio_bus_type; @@ -200,20 +203,99 @@ static struct phy_device* phy_device_create(struct mii_bus *bus, return dev; } +EXPORT_SYMBOL(phy_device_create); + +/** + * get_phy_c45_ids - reads the specified addr for its 802.3-c45 IDs. + * @bus: the target MII bus + * @addr: PHY address on the MII bus + * @phy_id: where to store the ID retrieved. + * @c45_ids: where to store the c45 ID information. + * + * If the PHY devices-in-package appears to be valid, it and the + * corresponding identifiers are stored in @c45_ids, zero is stored + * in @phy_id. Otherwise 0xffffffff is stored in @phy_id. Returns + * zero on success. + * + */ +static int get_phy_c45_ids(struct mii_bus *bus, int addr, u32 *phy_id, + struct phy_c45_device_ids *c45_ids) { + int phy_reg; + int i, reg_addr; + const int num_ids = ARRAY_SIZE(c45_ids->device_ids); + + /* Find first non-zero Devices In package. Device + * zero is reserved, so don't probe it. + */ + for (i = 1; + i < num_ids && c45_ids->devices_in_package == 0; + i++) { + reg_addr = MII_ADDR_C45 | i << 16 | 6; + phy_reg = mdiobus_read(bus, addr, reg_addr); + if (phy_reg < 0) + return -EIO; + c45_ids->devices_in_package = (phy_reg & 0xffff) << 16; + + reg_addr = MII_ADDR_C45 | i << 16 | 5; + phy_reg = mdiobus_read(bus, addr, reg_addr); + if (phy_reg < 0) + return -EIO; + c45_ids->devices_in_package |= (phy_reg & 0xffff); + + /* If mostly Fs, there is no device there, + * let's get out of here. + */ + if ((c45_ids->devices_in_package & 0x1fffffff) == 0x1fffffff) { + *phy_id = 0xffffffff; + return 0; + } + } + + /* Now probe Device Identifiers for each device present. */ + for (i = 1; i < num_ids; i++) { + if (!(c45_ids->devices_in_package & (1 << i))) + continue; + + reg_addr = MII_ADDR_C45 | i << 16 | MII_PHYSID1; + phy_reg = mdiobus_read(bus, addr, reg_addr); + if (phy_reg < 0) + return -EIO; + c45_ids->device_ids[i] = (phy_reg & 0xffff) << 16; + + reg_addr = MII_ADDR_C45 | i << 16 | MII_PHYSID2; + phy_reg = mdiobus_read(bus, addr, reg_addr); + if (phy_reg < 0) + return -EIO; + c45_ids->device_ids[i] |= (phy_reg & 0xffff); + } + *phy_id = 0; + return 0; +} /** * get_phy_id - reads the specified addr for its ID. * @bus: the target MII bus * @addr: PHY address on the MII bus * @phy_id: where to store the ID retrieved. + * @is_c45: If true the PHY uses the 802.3 clause 45 protocol + * @c45_ids: where to store the c45 ID information. + * + * Description: In the case of a 802.3-c22 PHY, reads the ID registers + * of the PHY at @addr on the @bus, stores it in @phy_id and returns + * zero on success. + * + * In the case of a 802.3-c45 PHY, get_phy_c45_ids() is invoked, and + * its return value is in turn returned. * - * Description: Reads the ID registers of the PHY at @addr on the - * @bus, stores it in @phy_id and returns zero on success. */ -static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id) +static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id, + bool is_c45, struct phy_c45_device_ids *c45_ids) { int phy_reg; + if (is_c45) + return get_phy_c45_ids(bus, addr, phy_id, c45_ids); + /* Grab the bits from PHYIR1, and put them * in the upper half */ phy_reg = mdiobus_read(bus, addr, MII_PHYSID1); @@ -238,17 +320,19 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id) * get_phy_device - reads the specified PHY device and returns its @phy_device struct * @bus: the target MII bus * @addr: PHY address on the MII bus + * @is_c45: If true the PHY uses the 802.3 clause 45 protocol * * Description: Reads the ID registers of the PHY at @addr on the * @bus, then allocates and returns the phy_device to represent it. */ -struct phy_device * get_phy_device(struct mii_bus *bus, int addr) +struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { struct phy_device *dev = NULL; u32 phy_id; + struct phy_c45_device_ids c45_ids = {0}; int r; - r = get_phy_id(bus, addr, &phy_id); + r = get_phy_id(bus, addr, &phy_id, is_c45, &c45_ids); if (r) return ERR_PTR(r); @@ -256,7 +340,7 @@ struct phy_device * get_phy_device(struct mii_bus *bus, int addr) if ((phy_id & 0x1fffffff) == 0x1fffffff) return NULL; - dev = phy_device_create(bus, addr, phy_id); + dev = phy_device_create(bus, addr, phy_id, is_c45, &c45_ids); return dev; } @@ -449,6 +533,11 @@ static int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, /* Assume that if there is no driver, that it doesn't * exist, and we should use the genphy driver. */ if (NULL == d->driver) { + if (phydev->is_c45) { + pr_err("No driver for phy %x\n", phydev->phy_id); + return -ENODEV; + } + d->driver = &genphy_driver.driver; err = d->driver->probe(d); diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 2574abde8d99..6c24cad322df 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -79,7 +79,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) mdio->irq[addr] = PHY_POLL; } - phy = get_phy_device(mdio, addr); + phy = get_phy_device(mdio, addr, false); if (!phy || IS_ERR(phy)) { dev_err(&mdio->dev, "error probing PHY at address %i\n", addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index c291cae8ce32..597d05dd0fb4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -243,6 +243,15 @@ enum phy_state { PHY_RESUMING }; +/** + * struct phy_c45_device_ids - 802.3-c45 Device Identifiers + * @devices_in_package: Bit vector of devices present. + * @device_ids: The device identifer for each present device. + */ +struct phy_c45_device_ids { + u32 devices_in_package; + u32 device_ids[8]; +}; /* phy_device: An instance of a PHY * @@ -250,6 +259,8 @@ enum phy_state { * bus: Pointer to the bus this PHY is on * dev: driver model device structure for this PHY * phy_id: UID for this device found during discovery + * c45_ids: 802.3-c45 Device Identifers if is_c45. + * is_c45: Set to true if this phy uses clause 45 addressing. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * addr: Bus address of PHY @@ -285,6 +296,9 @@ struct phy_device { u32 phy_id; + struct phy_c45_device_ids c45_ids; + bool is_c45; + enum phy_state state; u32 dev_flags; @@ -480,7 +494,9 @@ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) return mdiobus_write(phydev->bus, phydev->addr, regnum, val); } -struct phy_device* get_phy_device(struct mii_bus *bus, int addr); +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, + bool is_c45, struct phy_c45_device_ids *c45_ids); +struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); int phy_init_hw(struct phy_device *phydev); struct phy_device * phy_attach(struct net_device *dev, -- cgit v1.2.3 From a30e2c1891296b5ee8de48430a07fdf8b818c661 Mon Sep 17 00:00:00 2001 From: David Daney Date: Wed, 27 Jun 2012 07:33:37 +0000 Subject: netdev/phy/of: Add more methods for binding PHY devices to drivers. Allow PHY drivers to supply their own device matching function (match_phy_device()), or to be matched OF compatible properties. PHYs following IEEE802.3 clause 45 have more than one device identifier constants, which breaks the default device matching code. Other 10G PHYs don't follow the standard manufacturer/device identifier register layout standards, but they do use the standard MDIO bus protocols for register access. Both of these require adjustments to the PHY driver to device matching code. If the there is an of_node associated with such a PHY, we can match it to its driver using the "compatible" properties, just as we do with certain platform devices. If the "compatible" property match fails, first check if there is a driver supplied matching function, and if not fall back to the existing identifier matching rules. Signed-off-by: David Daney Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 7 +++++++ include/linux/phy.h | 6 ++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 2cee6d218d21..170eb411ab5d 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -308,6 +309,12 @@ static int mdio_bus_match(struct device *dev, struct device_driver *drv) struct phy_device *phydev = to_phy_device(dev); struct phy_driver *phydrv = to_phy_driver(drv); + if (of_driver_match_device(dev, drv)) + return 1; + + if (phydrv->match_phy_device) + return phydrv->match_phy_device(phydev); + return ((phydrv->phy_id & phydrv->phy_id_mask) == (phydev->phy_id & phydrv->phy_id_mask)); } diff --git a/include/linux/phy.h b/include/linux/phy.h index 597d05dd0fb4..7eac80a2557b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -426,6 +426,12 @@ struct phy_driver { /* Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); + /* Returns true if this is a suitable driver for the given + * phydev. If NULL, matching is based on phy_id and + * phy_id_mask. + */ + int (*match_phy_device)(struct phy_device *phydev); + /* Handles ethtool queries for hardware time stamping. */ int (*ts_info)(struct phy_device *phydev, struct ethtool_ts_info *ti); -- cgit v1.2.3 From ce0e169529a2db1cd910d2d45a5713fcdc29f6e1 Mon Sep 17 00:00:00 2001 From: Mahesh Palivela Date: Fri, 22 Jun 2012 07:27:46 +0000 Subject: wireless: add VHT (802.11ac) definitions Add the VHT definitions to be used by drivers supporting it. Signed-off-by: Mahesh Palivela Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 318fc1f705b1..abf0e5fe6d24 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1092,6 +1092,73 @@ struct ieee80211_ht_operation { #define WLAN_HT_SMPS_CONTROL_STATIC 1 #define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 +#define VHT_MCS_SUPPORTED_SET_SIZE 8 + +struct ieee80211_vht_capabilities { + __le32 vht_capabilities_info; + u8 vht_supported_mcs_set[VHT_MCS_SUPPORTED_SET_SIZE]; +} __packed; + +struct ieee80211_vht_operation { + u8 vht_op_info_chwidth; + u8 vht_op_info_chan_center_freq_seg1_idx; + u8 vht_op_info_chan_center_freq_seg2_idx; + __le16 vht_basic_mcs_set; +} __packed; + +/** + * struct ieee80211_vht_mcs_info - VHT MCS information + * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams + * @rx_highest: Indicates highest long GI VHT PPDU data rate + * STA can receive. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. + * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams + * @tx_highest: Indicates highest long GI VHT PPDU data rate + * STA can transmit. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest TX data rate supported. + */ +struct ieee80211_vht_mcs_info { + __le16 rx_mcs_map; + __le16 rx_highest; + __le16 tx_mcs_map; + __le16 tx_highest; +} __packed; + +#define IEEE80211_VHT_MCS_ZERO_TO_SEVEN_SUPPORT 0 +#define IEEE80211_VHT_MCS_ZERO_TO_EIGHT_SUPPORT 1 +#define IEEE80211_VHT_MCS_ZERO_TO_NINE_SUPPORT 2 +#define IEEE80211_VHT_MCS_NOT_SUPPORTED 3 + +/* 802.11ac VHT Capabilities */ +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 +#define IEEE80211_VHT_CAP_RXLDPC 0x00000010 +#define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 +#define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 +#define IEEE80211_VHT_CAP_TXSTBC 0x00000080 +#define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 +#define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 +#define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 +#define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 +#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 +#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 +#define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX 0x00006000 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENTION_MAX 0x00030000 +#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 +#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 +#define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 +#define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 +#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT 0x00800000 +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 +#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 +#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -1352,6 +1419,9 @@ enum ieee80211_eid { WLAN_EID_DSE_REGISTERED_LOCATION = 58, WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59, WLAN_EID_EXT_CHANSWITCH_ANN = 60, + + WLAN_EID_VHT_CAPABILITY = 191, + WLAN_EID_VHT_OPERATION = 192, }; /* Action category code */ -- cgit v1.2.3 From bf0c111ec80355ee9fe2e2bdb609a536b54768d8 Mon Sep 17 00:00:00 2001 From: Mahesh Palivela Date: Fri, 22 Jun 2012 07:27:46 +0000 Subject: cfg80211: allow advertising VHT capabilities Allow drivers to advertise their VHT capabilities and export them to userspace via nl80211. Signed-off-by: Mahesh Palivela Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 6 ++++++ include/net/cfg80211.h | 17 +++++++++++++++++ net/wireless/nl80211.c | 9 +++++++++ 3 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c0fc5d277338..23003272c70e 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1813,6 +1813,9 @@ enum nl80211_mpath_info { * @NL80211_BAND_ATTR_HT_CAPA: HT capabilities, as in the HT information IE * @NL80211_BAND_ATTR_HT_AMPDU_FACTOR: A-MPDU factor, as in 11n * @NL80211_BAND_ATTR_HT_AMPDU_DENSITY: A-MPDU density, as in 11n + * @NL80211_BAND_ATTR_VHT_MCS_SET: 32-byte attribute containing the MCS set as + * defined in 802.11ac + * @NL80211_BAND_ATTR_VHT_CAPA: VHT capabilities, as in the HT information IE * @NL80211_BAND_ATTR_MAX: highest band attribute currently defined * @__NL80211_BAND_ATTR_AFTER_LAST: internal use */ @@ -1826,6 +1829,9 @@ enum nl80211_band_attr { NL80211_BAND_ATTR_HT_AMPDU_FACTOR, NL80211_BAND_ATTR_HT_AMPDU_DENSITY, + NL80211_BAND_ATTR_VHT_MCS_SET, + NL80211_BAND_ATTR_VHT_CAPA, + /* keep last */ __NL80211_BAND_ATTR_AFTER_LAST, NL80211_BAND_ATTR_MAX = __NL80211_BAND_ATTR_AFTER_LAST - 1 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7d3cd3ce9a26..1fc89c4f930c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -210,6 +210,22 @@ struct ieee80211_sta_ht_cap { struct ieee80211_mcs_info mcs; }; +/** + * struct ieee80211_sta_vht_cap - STA's VHT capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11ac VHT capabilities for an STA. + * + * @vht_supported: is VHT supported by the STA + * @cap: VHT capabilities map as described in 802.11ac spec + * @vht_mcs: Supported VHT MCS rates + */ +struct ieee80211_sta_vht_cap { + bool vht_supported; + u32 cap; /* use IEEE80211_VHT_CAP_ */ + struct ieee80211_vht_mcs_info vht_mcs; +}; + /** * struct ieee80211_supported_band - frequency band definition * @@ -233,6 +249,7 @@ struct ieee80211_supported_band { int n_channels; int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; + struct ieee80211_sta_vht_cap vht_cap; }; /* diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 067c9fe02a7f..5c4a720f0442 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -921,6 +921,15 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, dev->wiphy.bands[band]->ht_cap.ampdu_density))) goto nla_put_failure; + /* add VHT info */ + if (dev->wiphy.bands[band]->vht_cap.vht_supported && + (nla_put(msg, NL80211_BAND_ATTR_VHT_MCS_SET, + sizeof(dev->wiphy.bands[band]->vht_cap.vht_mcs), + &dev->wiphy.bands[band]->vht_cap.vht_mcs) || + nla_put_u32(msg, NL80211_BAND_ATTR_VHT_CAPA, + dev->wiphy.bands[band]->vht_cap.cap))) + goto nla_put_failure; + /* add frequencies */ nl_freqs = nla_nest_start(msg, NL80211_BAND_ATTR_FREQS); if (!nl_freqs) -- cgit v1.2.3 From a31f2d17b331db970259e875b7223d3aba7e3821 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 29 Jun 2012 06:15:21 +0000 Subject: netlink: add netlink_kernel_cfg parameter to netlink_kernel_create This patch adds the following structure: struct netlink_kernel_cfg { unsigned int groups; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; }; That can be passed to netlink_kernel_create to set optional configurations for netlink kernel sockets. I've populated this structure by looking for NULL and zero parameters at the existing code. The remaining parameters that always need to be set are still left in the original interface. That includes optional parameters for the netlink socket creation. This allows easy extensibility of this interface in the future. This patch also adapts all callers to use this new interface. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- crypto/crypto_user.c | 7 +++++-- drivers/connector/connector.c | 13 +++++++++---- drivers/infiniband/core/netlink.c | 7 +++++-- drivers/scsi/scsi_netlink.c | 7 +++++-- drivers/scsi/scsi_transport_iscsi.c | 9 ++++++--- drivers/staging/gdm72xx/netlink_k.c | 6 ++++-- include/linux/netlink.h | 15 ++++++++++----- kernel/audit.c | 7 +++++-- lib/kobject_uevent.c | 5 ++++- net/bridge/netfilter/ebt_ulog.c | 6 ++++-- net/core/rtnetlink.c | 9 +++++++-- net/core/sock_diag.c | 8 ++++++-- net/decnet/netfilter/dn_rtmsg.c | 8 +++++--- net/ipv4/fib_frontend.c | 7 +++++-- net/ipv4/netfilter/ipt_ULOG.c | 8 +++++--- net/netfilter/nfnetlink.c | 7 +++++-- net/netlink/af_netlink.c | 16 ++++++++++------ net/netlink/genetlink.c | 10 +++++++--- net/xfrm/xfrm_user.c | 7 +++++-- security/selinux/netlink.c | 6 +++++- 20 files changed, 117 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 5a37eadb4e56..ba2c611154af 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -496,9 +496,12 @@ static void crypto_netlink_rcv(struct sk_buff *skb) static int __init crypto_user_init(void) { + struct netlink_kernel_cfg cfg = { + .input = crypto_netlink_rcv, + }; + crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, - 0, crypto_netlink_rcv, - NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!crypto_nlsk) return -ENOMEM; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 34e0e9e4d913..116cf8d02834 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -251,15 +251,20 @@ static const struct file_operations cn_file_ops = { .release = single_release }; +static struct cn_dev cdev = { + .input = cn_rx_skb, +}; + static int __devinit cn_init(void) { struct cn_dev *dev = &cdev; - - dev->input = cn_rx_skb; + struct netlink_kernel_cfg cfg = { + .groups = CN_NETLINK_USERS + 0xf, + .input = dev->input, + }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, - CN_NETLINK_USERS + 0xf, - dev->input, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!dev->nls) return -EIO; diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 1e691dca1820..3ae2bfd31015 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -173,8 +173,11 @@ static void ibnl_rcv(struct sk_buff *skb) int __init ibnl_init(void) { - nls = netlink_kernel_create(&init_net, NETLINK_RDMA, 0, ibnl_rcv, - NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = ibnl_rcv, + }; + + nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg); if (!nls) { pr_warn("Failed to create netlink socket\n"); return -ENOMEM; diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c index c77628afbf9f..8818dd681c19 100644 --- a/drivers/scsi/scsi_netlink.c +++ b/drivers/scsi/scsi_netlink.c @@ -486,6 +486,10 @@ void scsi_netlink_init(void) { int error; + struct netlink_kernel_cfg cfg = { + .input = scsi_nl_rcv_msg, + .groups = SCSI_NL_GRP_CNT, + }; INIT_LIST_HEAD(&scsi_nl_drivers); @@ -497,8 +501,7 @@ scsi_netlink_init(void) } scsi_nl_sock = netlink_kernel_create(&init_net, NETLINK_SCSITRANSPORT, - SCSI_NL_GRP_CNT, scsi_nl_rcv_msg, NULL, - THIS_MODULE); + THIS_MODULE, &cfg); if (!scsi_nl_sock) { printk(KERN_ERR "%s: register of receive handler failed\n", __func__); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 1cf640e575da..6042954d8f3b 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2936,7 +2936,10 @@ EXPORT_SYMBOL_GPL(iscsi_unregister_transport); static __init int iscsi_transport_init(void) { int err; - + struct netlink_kernel_cfg cfg = { + .groups = 1, + .input = iscsi_if_rx, + }; printk(KERN_INFO "Loading iSCSI transport class v%s.\n", ISCSI_TRANSPORT_VERSION); @@ -2966,8 +2969,8 @@ static __init int iscsi_transport_init(void) if (err) goto unregister_conn_class; - nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, 1, iscsi_if_rx, - NULL, THIS_MODULE); + nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, + THIS_MODULE, &cfg); if (!nls) { err = -ENOBUFS; goto unregister_session_class; diff --git a/drivers/staging/gdm72xx/netlink_k.c b/drivers/staging/gdm72xx/netlink_k.c index 2489bb5597ca..87c3a07ed80e 100644 --- a/drivers/staging/gdm72xx/netlink_k.c +++ b/drivers/staging/gdm72xx/netlink_k.c @@ -88,13 +88,15 @@ struct sock *netlink_init(int unit, void (*cb)(struct net_device *dev, u16 type, void *msg, int len)) { struct sock *sock; + struct netlink_kernel_cfg cfg = { + .input = netlink_rcv, + }; #if !defined(DEFINE_MUTEX) init_MUTEX(&netlink_mutex); #endif - sock = netlink_kernel_create(&init_net, unit, 0, netlink_rcv, NULL, - THIS_MODULE); + sock = netlink_kernel_create(&init_net, unit, THIS_MODULE, &cfg); if (sock) rcv_cb = cb; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index ed33f0901bc2..6085e4919cb3 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -174,11 +174,16 @@ struct netlink_skb_parms { extern void netlink_table_grab(void); extern void netlink_table_ungrab(void); -extern struct sock *netlink_kernel_create(struct net *net, - int unit,unsigned int groups, - void (*input)(struct sk_buff *skb), - struct mutex *cb_mutex, - struct module *module); +/* optional Netlink kernel configuration parameters */ +struct netlink_kernel_cfg { + unsigned int groups; + void (*input)(struct sk_buff *skb); + struct mutex *cb_mutex; +}; + +extern struct sock *netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg); extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/kernel/audit.c b/kernel/audit.c index 30b252a1fb61..4a3f28d2ca65 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -962,14 +962,17 @@ static void audit_receive(struct sk_buff *skb) static int __init audit_init(void) { int i; + struct netlink_kernel_cfg cfg = { + .input = audit_receive, + }; if (audit_initialized == AUDIT_DISABLED) return 0; printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); - audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0, - audit_receive, NULL, THIS_MODULE); + audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, + THIS_MODULE, &cfg); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 1a91efa6d121..0401d2916d9f 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -373,13 +373,16 @@ EXPORT_SYMBOL_GPL(add_uevent_var); static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; + struct netlink_kernel_cfg cfg = { + .groups = 1, + }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, - 1, NULL, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!ue_sk->sk) { printk(KERN_ERR "kobject_uevent: unable to create netlink socket!\n"); diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 1bd173218f7b..374bdcd77039 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -282,6 +282,9 @@ static int __init ebt_ulog_init(void) { int ret; int i; + struct netlink_kernel_cfg cfg = { + .groups = EBT_ULOG_MAXNLGROUPS, + }; if (nlbufsiz >= 128*1024) { pr_warning("Netlink buffer has to be <= 128kB," @@ -296,8 +299,7 @@ static int __init ebt_ulog_init(void) } ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - EBT_ULOG_MAXNLGROUPS, NULL, NULL, - THIS_MODULE); + THIS_MODULE, &cfg); if (!ebtulognl) ret = -ENOMEM; else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bc8a1cdaac98..2b325c340b44 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2353,8 +2353,13 @@ static struct notifier_block rtnetlink_dev_notifier = { static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .groups = RTNLGRP_MAX, + .input = rtnetlink_rcv, + .cb_mutex = &rtnl_mutex, + }; + + sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index ff2967acbfae..07a29eb34a41 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -171,8 +171,12 @@ EXPORT_SYMBOL_GPL(sock_diag_nlsk); static int __init sock_diag_init(void) { - sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0, - sock_diag_rcv, NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = sock_diag_rcv, + }; + + sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, + THIS_MODULE, &cfg); return sock_diag_nlsk == NULL ? -ENOMEM : 0; } diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index b8f7f5b8c350..11db0ecf342f 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -125,11 +125,13 @@ static struct nf_hook_ops dnrmg_ops __read_mostly = { static int __init dn_rtmsg_init(void) { int rv = 0; + struct netlink_kernel_cfg cfg = { + .groups = DNRNG_NLGRP_MAX, + .input = dnrmg_receive_user_skb, + }; dnrmg = netlink_kernel_create(&init_net, - NETLINK_DNRTMSG, DNRNG_NLGRP_MAX, - dnrmg_receive_user_skb, - NULL, THIS_MODULE); + NETLINK_DNRTMSG, THIS_MODULE, &cfg); if (dnrmg == NULL) { printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); return -ENOMEM; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ae528d1b293a..3e11ea225dad 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -976,8 +976,11 @@ static void nl_fib_input(struct sk_buff *skb) static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, - nl_fib_input, NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = nl_fib_input, + }; + + sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, THIS_MODULE, &cfg); if (sk == NULL) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 99b3f53f16a7..1109f7f6c254 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -381,6 +381,9 @@ static struct nf_logger ipt_ulog_logger __read_mostly = { static int __init ulog_tg_init(void) { int ret, i; + struct netlink_kernel_cfg cfg = { + .groups = ULOG_MAXNLGROUPS, + }; pr_debug("init module\n"); @@ -393,9 +396,8 @@ static int __init ulog_tg_init(void) for (i = 0; i < ULOG_MAXNLGROUPS; i++) setup_timer(&ulog_buffers[i].timer, ulog_timer, i); - nflognl = netlink_kernel_create(&init_net, - NETLINK_NFLOG, ULOG_MAXNLGROUPS, NULL, - NULL, THIS_MODULE); + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, + THIS_MODULE, &cfg); if (!nflognl) return -ENOMEM; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 3e797d1fcb94..700e4616a098 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -203,9 +203,12 @@ static void nfnetlink_rcv(struct sk_buff *skb) static int __net_init nfnetlink_net_init(struct net *net) { struct sock *nfnl; + struct netlink_kernel_cfg cfg = { + .groups = NFNLGRP_MAX, + .input = nfnetlink_rcv, + }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, NFNLGRP_MAX, - nfnetlink_rcv, NULL, THIS_MODULE); + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b3025a603d56..43a124feaad8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1503,14 +1503,16 @@ static void netlink_data_ready(struct sock *sk, int len) */ struct sock * -netlink_kernel_create(struct net *net, int unit, unsigned int groups, - void (*input)(struct sk_buff *skb), - struct mutex *cb_mutex, struct module *module) +netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; + struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; + unsigned int groups; BUG_ON(!nl_table); @@ -1532,16 +1534,18 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, sk = sock->sk; sk_change_net(sk, net); - if (groups < 32) + if (!cfg || cfg->groups < 32) groups = 32; + else + groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; - if (input) - nlk_sk(sk)->netlink_rcv = input; + if (cfg && cfg->input) + nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, net, 0)) goto out_sock_release; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2cc7c1ee7690..32761b53015e 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -915,10 +915,14 @@ static struct genl_multicast_group notify_grp = { static int __net_init genl_pernet_init(struct net *net) { + struct netlink_kernel_cfg cfg = { + .input = genl_rcv, + .cb_mutex = &genl_mutex, + }; + /* we'll bump the group number right afterwards */ - net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, 0, - genl_rcv, &genl_mutex, - THIS_MODULE); + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, + THIS_MODULE, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 540762726aaf..e75d8e47f35c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2959,9 +2959,12 @@ static struct xfrm_mgr netlink_mgr = { static int __net_init xfrm_user_net_init(struct net *net) { struct sock *nlsk; + struct netlink_kernel_cfg cfg = { + .groups = XFRMNLGRP_MAX, + .input = xfrm_netlink_rcv, + }; - nlsk = netlink_kernel_create(net, NETLINK_XFRM, XFRMNLGRP_MAX, - xfrm_netlink_rcv, NULL, THIS_MODULE); + nlsk = netlink_kernel_create(net, NETLINK_XFRM, THIS_MODULE, &cfg); if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c index 8a23a35b9c5b..8a77725423e0 100644 --- a/security/selinux/netlink.c +++ b/security/selinux/netlink.c @@ -111,8 +111,12 @@ void selnl_notify_policyload(u32 seqno) static int __init selnl_init(void) { + struct netlink_kernel_cfg cfg = { + .groups = SELNLGRP_MAX, + }; + selnl = netlink_kernel_create(&init_net, NETLINK_SELINUX, - SELNLGRP_MAX, NULL, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (selnl == NULL) panic("SELinux: Cannot create netlink socket."); netlink_set_nonroot(NETLINK_SELINUX, NL_NONROOT_RECV); -- cgit v1.2.3 From 03292745b02d1166e2a215504407e096b8427be5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 29 Jun 2012 06:15:22 +0000 Subject: netlink: add nlk->netlink_bind hook for module auto-loading This patch adds a hook in the binding path of netlink. This is used by ctnetlink to allow module autoloading for the case in which one user executes: conntrack -E So far, this resulted in nfnetlink loaded, but not nf_conntrack_netlink. I have received in the past many complains on this behaviour. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netfilter/nfnetlink.c | 29 +++++++++++++++++++++++++++++ net/netlink/af_netlink.c | 19 +++++++++++++++++++ 3 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6085e4919cb3..f74dd133788f 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -179,6 +179,7 @@ struct netlink_kernel_cfg { unsigned int groups; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; + void (*bind)(int group); }; extern struct sock *netlink_kernel_create(struct net *net, int unit, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 700e4616a098..5a2132b97fe9 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -39,6 +39,15 @@ static char __initdata nfversion[] = "0.30"; static const struct nfnetlink_subsystem __rcu *subsys_table[NFNL_SUBSYS_COUNT]; static DEFINE_MUTEX(nfnl_mutex); +static const int nfnl_group2type[NFNLGRP_MAX+1] = { + [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_DESTROY] = NFNL_SUBSYS_CTNETLINK, + [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, + [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, + [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, +}; + void nfnl_lock(void) { mutex_lock(&nfnl_mutex); @@ -200,12 +209,32 @@ static void nfnetlink_rcv(struct sk_buff *skb) netlink_rcv_skb(skb, &nfnetlink_rcv_msg); } +#ifdef CONFIG_MODULES +static void nfnetlink_bind(int group) +{ + const struct nfnetlink_subsystem *ss; + int type = nfnl_group2type[group]; + + rcu_read_lock(); + ss = nfnetlink_get_subsys(type); + if (!ss) { + rcu_read_unlock(); + request_module("nfnetlink-subsys-%d", type); + return; + } + rcu_read_unlock(); +} +#endif + static int __net_init nfnetlink_net_init(struct net *net) { struct sock *nfnl; struct netlink_kernel_cfg cfg = { .groups = NFNLGRP_MAX, .input = nfnetlink_rcv, +#ifdef CONFIG_MODULES + .bind = nfnetlink_bind, +#endif }; nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 43a124feaad8..5463969da45b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -80,6 +80,7 @@ struct netlink_sock { struct mutex *cb_mutex; struct mutex cb_def_mutex; void (*netlink_rcv)(struct sk_buff *skb); + void (*netlink_bind)(int group); struct module *module; }; @@ -124,6 +125,7 @@ struct netlink_table { unsigned int groups; struct mutex *cb_mutex; struct module *module; + void (*bind)(int group); int registered; }; @@ -444,6 +446,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, struct module *module = NULL; struct mutex *cb_mutex; struct netlink_sock *nlk; + void (*bind)(int group); int err = 0; sock->state = SS_UNCONNECTED; @@ -468,6 +471,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, else err = -EPROTONOSUPPORT; cb_mutex = nl_table[protocol].cb_mutex; + bind = nl_table[protocol].bind; netlink_unlock_table(); if (err < 0) @@ -483,6 +487,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, nlk = nlk_sk(sock->sk); nlk->module = module; + nlk->netlink_bind = bind; out: return err; @@ -683,6 +688,15 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_update_listeners(sk); netlink_table_ungrab(); + if (nlk->netlink_bind && nlk->groups[0]) { + int i; + + for (i=0; ingroups; i++) { + if (test_bit(i, nlk->groups)) + nlk->netlink_bind(i); + } + } + return 0; } @@ -1239,6 +1253,10 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); + + if (nlk->netlink_bind) + nlk->netlink_bind(val); + err = 0; break; } @@ -1559,6 +1577,7 @@ netlink_kernel_create(struct net *net, int unit, rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].cb_mutex = cb_mutex; nl_table[unit].module = module; + nl_table[unit].bind = cfg ? cfg->bind : NULL; nl_table[unit].registered = 1; } else { kfree(listeners); -- cgit v1.2.3 From bb35f67195fcdbe79faa7a15ce148a67c9ab923d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 29 Jun 2012 05:10:05 +0000 Subject: net: introduce new priv_flag indicating iface capable of change mac when running Introduce IFF_LIVE_ADDR_CHANGE priv_flag and use it to disable netif_running() check in eth_mac_addr() Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if.h | 2 ++ net/ethernet/eth.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index f995c663c493..1ec407b01e46 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -81,6 +81,8 @@ #define IFF_UNICAST_FLT 0x20000 /* Supports unicast filtering */ #define IFF_TEAM_PORT 0x40000 /* device used as team port */ #define IFF_SUPP_NOFCS 0x80000 /* device supports sending custom FCS */ +#define IFF_LIVE_ADDR_CHANGE 0x100000 /* device supports hardware address + * change when it's running */ #define IF_GET_IFACE 0x0001 /* for querying only */ diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 36e58800a9e3..db6a6c17d790 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -283,7 +283,7 @@ int eth_mac_addr(struct net_device *dev, void *p) { struct sockaddr *addr = p; - if (netif_running(dev)) + if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; -- cgit v1.2.3 From a59a4d1921664da63d801ba477950114c71c88c9 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 27 Jun 2012 21:14:38 +0000 Subject: phy: add the EEE support and the way to access to the MMD registers. This patch adds the support for the Energy-Efficient Ethernet (EEE) to the Physical Abstraction Layer. To support the EEE we have to access to the MMD registers 3.20 and 7.60/61. So two new functions have been added to read/write the MMD registers (clause 45). An Ethernet driver (I tested the stmmac) can invoke the phy_init_eee to properly check if the EEE is supported by the PHYs and it can also set the clock stop enable bit in the 3.0 register. The phy_get_eee_err can be used for reporting the number of time where the PHY failed to complete its normal wake sequence. In the end, this patch also adds the EEE ethtool support implementing: o phy_ethtool_set_eee o phy_ethtool_get_eee v1: initial patch v2: fixed some errors especially on naming convention v3: renamed again the mmd read/write functions thank to Ben's feedback v4: moved file to phy.c and added the ethtool support. v5: fixed phy_adv_to_eee, phy_eee_to_supported, phy_eee_to_adv return values according to ethtool API (thanks to Ben's feedback). Renamed some macros to avoid too long names. v6: fixed kernel-doc comments to be properly parsed. Fixed the phy_init_eee function: we need to check which link mode was autonegotiated and then the corresponding bits in 7.60 and 7.61 registers. v7: reviewed the way to get the negotiated settings. v8: fixed a problem in the phy_init_eee return value erroneously added when included the phy_read_status call. v9: do not remove the MDIO_AN_EEE_ADV_100TX and MDIO_AN_EEE_ADV_1000T and fixed the eee_{cap,lp,adv} declaration as "int" instead of u16. Signed-off-by: Giuseppe Cavallaro Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 281 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mdio.h | 28 ++++- include/linux/mii.h | 9 ++ include/linux/phy.h | 5 + 4 files changed, 319 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 2e1c23731ded..7ca2ff97c368 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -967,3 +968,283 @@ void phy_state_machine(struct work_struct *work) schedule_delayed_work(&phydev->state_queue, PHY_STATE_TIME * HZ); } + +static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad, + int addr) +{ + /* Write the desired MMD Devad */ + bus->write(bus, addr, MII_MMD_CTRL, devad); + + /* Write the desired MMD register address */ + bus->write(bus, addr, MII_MMD_DATA, prtad); + + /* Select the Function : DATA with no post increment */ + bus->write(bus, addr, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR)); +} + +/** + * phy_read_mmd_indirect - reads data from the MMD registers + * @bus: the target MII bus + * @prtad: MMD Address + * @devad: MMD DEVAD + * @addr: PHY address on the MII bus + * + * Description: it reads data from the MMD registers (clause 22 to access to + * clause 45) of the specified phy address. + * To read these register we have: + * 1) Write reg 13 // DEVAD + * 2) Write reg 14 // MMD Address + * 3) Write reg 13 // MMD Data Command for MMD DEVAD + * 3) Read reg 14 // Read MMD data + */ +static int phy_read_mmd_indirect(struct mii_bus *bus, int prtad, int devad, + int addr) +{ + u32 ret; + + mmd_phy_indirect(bus, prtad, devad, addr); + + /* Read the content of the MMD's selected register */ + ret = bus->read(bus, addr, MII_MMD_DATA); + + return ret; +} + +/** + * phy_write_mmd_indirect - writes data to the MMD registers + * @bus: the target MII bus + * @prtad: MMD Address + * @devad: MMD DEVAD + * @addr: PHY address on the MII bus + * @data: data to write in the MMD register + * + * Description: Write data from the MMD registers of the specified + * phy address. + * To write these register we have: + * 1) Write reg 13 // DEVAD + * 2) Write reg 14 // MMD Address + * 3) Write reg 13 // MMD Data Command for MMD DEVAD + * 3) Write reg 14 // Write MMD data + */ +static void phy_write_mmd_indirect(struct mii_bus *bus, int prtad, int devad, + int addr, u32 data) +{ + mmd_phy_indirect(bus, prtad, devad, addr); + + /* Write the data into MMD's selected register */ + bus->write(bus, addr, MII_MMD_DATA, data); +} + +static u32 phy_eee_to_adv(u16 eee_adv) +{ + u32 adv = 0; + + if (eee_adv & MDIO_EEE_100TX) + adv |= ADVERTISED_100baseT_Full; + if (eee_adv & MDIO_EEE_1000T) + adv |= ADVERTISED_1000baseT_Full; + if (eee_adv & MDIO_EEE_10GT) + adv |= ADVERTISED_10000baseT_Full; + if (eee_adv & MDIO_EEE_1000KX) + adv |= ADVERTISED_1000baseKX_Full; + if (eee_adv & MDIO_EEE_10GKX4) + adv |= ADVERTISED_10000baseKX4_Full; + if (eee_adv & MDIO_EEE_10GKR) + adv |= ADVERTISED_10000baseKR_Full; + + return adv; +} + +static u32 phy_eee_to_supported(u16 eee_caported) +{ + u32 supported = 0; + + if (eee_caported & MDIO_EEE_100TX) + supported |= SUPPORTED_100baseT_Full; + if (eee_caported & MDIO_EEE_1000T) + supported |= SUPPORTED_1000baseT_Full; + if (eee_caported & MDIO_EEE_10GT) + supported |= SUPPORTED_10000baseT_Full; + if (eee_caported & MDIO_EEE_1000KX) + supported |= SUPPORTED_1000baseKX_Full; + if (eee_caported & MDIO_EEE_10GKX4) + supported |= SUPPORTED_10000baseKX4_Full; + if (eee_caported & MDIO_EEE_10GKR) + supported |= SUPPORTED_10000baseKR_Full; + + return supported; +} + +static u16 phy_adv_to_eee(u32 adv) +{ + u16 reg = 0; + + if (adv & ADVERTISED_100baseT_Full) + reg |= MDIO_EEE_100TX; + if (adv & ADVERTISED_1000baseT_Full) + reg |= MDIO_EEE_1000T; + if (adv & ADVERTISED_10000baseT_Full) + reg |= MDIO_EEE_10GT; + if (adv & ADVERTISED_1000baseKX_Full) + reg |= MDIO_EEE_1000KX; + if (adv & ADVERTISED_10000baseKX4_Full) + reg |= MDIO_EEE_10GKX4; + if (adv & ADVERTISED_10000baseKR_Full) + reg |= MDIO_EEE_10GKR; + + return reg; +} + +/** + * phy_init_eee - init and check the EEE feature + * @phydev: target phy_device struct + * @clk_stop_enable: PHY may stop the clock during LPI + * + * Description: it checks if the Energy-Efficient Ethernet (EEE) + * is supported by looking at the MMD registers 3.20 and 7.60/61 + * and it programs the MMD register 3.0 setting the "Clock stop enable" + * bit if required. + */ +int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) +{ + int ret = -EPROTONOSUPPORT; + + /* According to 802.3az,the EEE is supported only in full duplex-mode. + * Also EEE feature is active when core is operating with MII, GMII + * or RGMII. + */ + if ((phydev->duplex == DUPLEX_FULL) && + ((phydev->interface == PHY_INTERFACE_MODE_MII) || + (phydev->interface == PHY_INTERFACE_MODE_GMII) || + (phydev->interface == PHY_INTERFACE_MODE_RGMII))) { + int eee_lp, eee_cap, eee_adv; + u32 lp, cap, adv; + int idx, status; + + /* Read phy status to properly get the right settings */ + status = phy_read_status(phydev); + if (status) + return status; + + /* First check if the EEE ability is supported */ + eee_cap = phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_ABLE, + MDIO_MMD_PCS, phydev->addr); + if (eee_cap < 0) + return eee_cap; + + cap = phy_eee_to_supported(eee_cap); + if (!cap) + goto eee_exit; + + /* Check which link settings negotiated and verify it in + * the EEE advertising registers. + */ + eee_lp = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_LPABLE, + MDIO_MMD_AN, phydev->addr); + if (eee_lp < 0) + return eee_lp; + + eee_adv = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV, + MDIO_MMD_AN, phydev->addr); + if (eee_adv < 0) + return eee_adv; + + adv = phy_eee_to_adv(eee_adv); + lp = phy_eee_to_adv(eee_lp); + idx = phy_find_setting(phydev->speed, phydev->duplex); + if ((lp & adv & settings[idx].setting)) + goto eee_exit; + + if (clk_stop_enable) { + /* Configure the PHY to stop receiving xMII + * clock while it is signaling LPI. + */ + int val = phy_read_mmd_indirect(phydev->bus, MDIO_CTRL1, + MDIO_MMD_PCS, + phydev->addr); + if (val < 0) + return val; + + val |= MDIO_PCS_CTRL1_CLKSTOP_EN; + phy_write_mmd_indirect(phydev->bus, MDIO_CTRL1, + MDIO_MMD_PCS, phydev->addr, val); + } + + ret = 0; /* EEE supported */ + } + +eee_exit: + return ret; +} +EXPORT_SYMBOL(phy_init_eee); + +/** + * phy_get_eee_err - report the EEE wake error count + * @phydev: target phy_device struct + * + * Description: it is to report the number of time where the PHY + * failed to complete its normal wake sequence. + */ +int phy_get_eee_err(struct phy_device *phydev) +{ + return phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_WK_ERR, + MDIO_MMD_PCS, phydev->addr); + +} +EXPORT_SYMBOL(phy_get_eee_err); + +/** + * phy_ethtool_get_eee - get EEE supported and status + * @phydev: target phy_device struct + * @data: ethtool_eee data + * + * Description: it reportes the Supported/Advertisement/LP Advertisement + * capabilities. + */ +int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data) +{ + int val; + + /* Get Supported EEE */ + val = phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_ABLE, + MDIO_MMD_PCS, phydev->addr); + if (val < 0) + return val; + data->supported = phy_eee_to_supported(val); + + /* Get advertisement EEE */ + val = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV, + MDIO_MMD_AN, phydev->addr); + if (val < 0) + return val; + data->advertised = phy_eee_to_adv(val); + + /* Get LP advertisement EEE */ + val = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_LPABLE, + MDIO_MMD_AN, phydev->addr); + if (val < 0) + return val; + data->lp_advertised = phy_eee_to_adv(val); + + return 0; +} +EXPORT_SYMBOL(phy_ethtool_get_eee); + +/** + * phy_ethtool_set_eee - set EEE supported and status + * @phydev: target phy_device struct + * @data: ethtool_eee data + * + * Description: it is to program the Advertisement EEE register. + */ +int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) +{ + int val; + + val = phy_adv_to_eee(data->advertised); + phy_write_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV, MDIO_MMD_AN, + phydev->addr, val); + + return 0; +} +EXPORT_SYMBOL(phy_ethtool_set_eee); diff --git a/include/linux/mdio.h b/include/linux/mdio.h index dfb947959ec9..7cccafe50e7b 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -43,7 +43,11 @@ #define MDIO_PKGID2 15 #define MDIO_AN_ADVERTISE 16 /* AN advertising (base page) */ #define MDIO_AN_LPA 19 /* AN LP abilities (base page) */ +#define MDIO_PCS_EEE_ABLE 20 /* EEE Capability register */ +#define MDIO_PCS_EEE_WK_ERR 22 /* EEE wake error counter */ #define MDIO_PHYXS_LNSTAT 24 /* PHY XGXS lane state */ +#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */ +#define MDIO_AN_EEE_LPABLE 61 /* EEE link partner ability */ /* Media-dependent registers. */ #define MDIO_PMA_10GBT_SWAPPOL 130 /* 10GBASE-T pair swap & polarity */ @@ -56,7 +60,6 @@ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ #define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */ #define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */ -#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -82,6 +85,7 @@ #define MDIO_AN_CTRL1_RESTART BMCR_ANRESTART #define MDIO_AN_CTRL1_ENABLE BMCR_ANENABLE #define MDIO_AN_CTRL1_XNP 0x2000 /* Enable extended next page */ +#define MDIO_PCS_CTRL1_CLKSTOP_EN 0x400 /* Stop the clock during LPI */ /* 10 Gb/s */ #define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00) @@ -237,9 +241,25 @@ #define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */ #define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */ -/* AN EEE Advertisement register. */ -#define MDIO_AN_EEE_ADV_100TX 0x0002 /* Advertise 100TX EEE cap */ -#define MDIO_AN_EEE_ADV_1000T 0x0004 /* Advertise 1000T EEE cap */ +/* EEE Supported/Advertisement/LP Advertisement registers. + * + * EEE capability Register (3.20), Advertisement (7.60) and + * Link partner ability (7.61) registers have and can use the same identical + * bit masks. + */ +#define MDIO_AN_EEE_ADV_100TX 0x0002 /* Advertise 100TX EEE cap */ +#define MDIO_AN_EEE_ADV_1000T 0x0004 /* Advertise 1000T EEE cap */ +/* Note: the two defines above can be potentially used by the user-land + * and cannot remove them now. + * So, we define the new generic MDIO_EEE_100TX and MDIO_EEE_1000T macros + * using the previous ones (that can be considered obsolete). + */ +#define MDIO_EEE_100TX MDIO_AN_EEE_ADV_100TX /* 100TX EEE cap */ +#define MDIO_EEE_1000T MDIO_AN_EEE_ADV_1000T /* 1000T EEE cap */ +#define MDIO_EEE_10GT 0x0008 /* 10GT EEE cap */ +#define MDIO_EEE_1000KX 0x0010 /* 1000KX EEE cap */ +#define MDIO_EEE_10GKX4 0x0020 /* 10G KX4 EEE cap */ +#define MDIO_EEE_10GKR 0x0040 /* 10G KR EEE cap */ /* LASI RX_ALARM control/status registers. */ #define MDIO_PMA_LASI_RX_PHYXSLFLT 0x0001 /* PHY XS RX local fault */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 2783eca629a0..8ef3a7a11592 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -21,6 +21,8 @@ #define MII_EXPANSION 0x06 /* Expansion register */ #define MII_CTRL1000 0x09 /* 1000BASE-T control */ #define MII_STAT1000 0x0a /* 1000BASE-T status */ +#define MII_MMD_CTRL 0x0d /* MMD Access Control Register */ +#define MII_MMD_DATA 0x0e /* MMD Access Data Register */ #define MII_ESTATUS 0x0f /* Extended Status */ #define MII_DCOUNTER 0x12 /* Disconnect counter */ #define MII_FCSCOUNTER 0x13 /* False carrier counter */ @@ -141,6 +143,13 @@ #define FLOW_CTRL_TX 0x01 #define FLOW_CTRL_RX 0x02 +/* MMD Access Control register fields */ +#define MII_MMD_CTRL_DEVAD_MASK 0x1f /* Mask MMD DEVAD*/ +#define MII_MMD_CTRL_ADDR 0x0000 /* Address */ +#define MII_MMD_CTRL_NOINCR 0x4000 /* no post increment */ +#define MII_MMD_CTRL_INCR_RDWT 0x8000 /* post increment on reads & writes */ +#define MII_MMD_CTRL_INCR_ON_WT 0xC000 /* post increment on writes only */ + /* This structure is used in all SIOCxMIIxxx ioctl calls */ struct mii_ioctl_data { __u16 phy_id; diff --git a/include/linux/phy.h b/include/linux/phy.h index 7eac80a2557b..c35299e4da8e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -554,6 +554,11 @@ int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_scan_fixups(struct phy_device *phydev); +int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); +int phy_get_eee_err(struct phy_device *phydev); +int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); +int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); + int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit v1.2.3 From 3a0c52a6d82cc41da965284412608c74aece34e4 Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Mon, 2 Jul 2012 09:32:32 +0300 Subject: cfg80211: add 802.11ad (60gHz band) support Add enumerations for both cfg80211 and nl80211. This expands wiphy.bands etc. arrays. Extend channel <-> frequency translation to cover 60g band and modify the rate check logic since there are no legacy mandatory rates (only MCS is used.) Signed-off-by: Vladimir Kondratiev Signed-off-by: Johannes Berg --- drivers/net/wireless/iwlegacy/3945-rs.c | 2 +- include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 2 ++ net/mac80211/tx.c | 2 ++ net/wireless/core.c | 10 ++++++++-- net/wireless/util.c | 35 +++++++++++++++++++++++++-------- 6 files changed, 42 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/iwlegacy/3945-rs.c b/drivers/net/wireless/iwlegacy/3945-rs.c index 4b10157d8686..d4fd29ad90dc 100644 --- a/drivers/net/wireless/iwlegacy/3945-rs.c +++ b/drivers/net/wireless/iwlegacy/3945-rs.c @@ -946,7 +946,7 @@ il3945_rate_scale_init(struct ieee80211_hw *hw, s32 sta_id) case IEEE80211_BAND_5GHZ: rs_sta->expected_tpt = il3945_expected_tpt_a; break; - case IEEE80211_NUM_BANDS: + default: BUG(); break; } diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 23003272c70e..74cc55c1bf28 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -2545,10 +2545,12 @@ enum nl80211_tx_rate_attributes { * enum nl80211_band - Frequency band * @NL80211_BAND_2GHZ: 2.4 GHz ISM band * @NL80211_BAND_5GHZ: around 5 GHz band (4.9 - 5.7 GHz) + * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 64.80 GHz) */ enum nl80211_band { NL80211_BAND_2GHZ, NL80211_BAND_5GHZ, + NL80211_BAND_60GHZ, }; /** diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fa269347355b..0b564e83a24b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -70,11 +70,13 @@ * * @IEEE80211_BAND_2GHZ: 2.4GHz ISM band * @IEEE80211_BAND_5GHZ: around 5GHz band (4.9-5.7) + * @IEEE80211_BAND_60GHZ: around 60 GHz band (58.32 - 64.80 GHz) * @IEEE80211_NUM_BANDS: number of defined bands */ enum ieee80211_band { IEEE80211_BAND_2GHZ = NL80211_BAND_2GHZ, IEEE80211_BAND_5GHZ = NL80211_BAND_5GHZ, + IEEE80211_BAND_60GHZ = NL80211_BAND_60GHZ, /* keep last */ IEEE80211_NUM_BANDS diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 4e753032e48d..4990f4fb5864 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -140,6 +140,8 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, if (r->flags & IEEE80211_RATE_MANDATORY_A) mrate = r->bitrate; break; + case IEEE80211_BAND_60GHZ: + /* TODO, for now fall through */ case IEEE80211_NUM_BANDS: WARN_ON(1); break; diff --git a/net/wireless/core.c b/net/wireless/core.c index ca2b95f24846..e13365f1fa63 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -468,8 +468,14 @@ int wiphy_register(struct wiphy *wiphy) continue; sband->band = band; - - if (WARN_ON(!sband->n_channels || !sband->n_bitrates)) + if (WARN_ON(!sband->n_channels)) + return -EINVAL; + /* + * on 60gHz band, there are no legacy rates, so + * n_bitrates is 0 + */ + if (WARN_ON(band != IEEE80211_BAND_60GHZ && + !sband->n_bitrates)) return -EINVAL; /* diff --git a/net/wireless/util.c b/net/wireless/util.c index a9260ac85cf1..0228c64e73d8 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -35,19 +35,29 @@ int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band) { /* see 802.11 17.3.8.3.2 and Annex J * there are overlapping channel numbers in 5GHz and 2GHz bands */ - if (band == IEEE80211_BAND_5GHZ) { - if (chan >= 182 && chan <= 196) - return 4000 + chan * 5; - else - return 5000 + chan * 5; - } else { /* IEEE80211_BAND_2GHZ */ + if (chan <= 0) + return 0; /* not supported */ + switch (band) { + case IEEE80211_BAND_2GHZ: if (chan == 14) return 2484; else if (chan < 14) return 2407 + chan * 5; + break; + case IEEE80211_BAND_5GHZ: + if (chan >= 182 && chan <= 196) + return 4000 + chan * 5; else - return 0; /* not supported */ + return 5000 + chan * 5; + break; + case IEEE80211_BAND_60GHZ: + if (chan < 5) + return 56160 + chan * 2160; + break; + default: + ; } + return 0; /* not supported */ } EXPORT_SYMBOL(ieee80211_channel_to_frequency); @@ -60,8 +70,12 @@ int ieee80211_frequency_to_channel(int freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else + else if (freq <= 45000) /* DMG band lower limit */ return (freq - 5000) / 5; + else if (freq >= 58320 && freq <= 64800) + return (freq - 56160) / 2160; + else + return 0; } EXPORT_SYMBOL(ieee80211_frequency_to_channel); @@ -137,6 +151,11 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband, } WARN_ON(want != 0 && want != 3 && want != 6); break; + case IEEE80211_BAND_60GHZ: + /* check for mandatory HT MCS 1..4 */ + WARN_ON(!sband->ht_cap.ht_supported); + WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); + break; case IEEE80211_NUM_BANDS: WARN_ON(1); break; -- cgit v1.2.3 From b188148c690e15284d5b20d384f950506d02e3e2 Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Mon, 2 Jul 2012 09:32:35 +0300 Subject: wireless: 60g protocol constants Provide various constants as defined by the 802.11ad: frame types, IE's, capability bits, action categories Introduce GCMP cipher, mandatory by 802.11ad Signed-off-by: Vladimir Kondratiev Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 90 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 89 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index abf0e5fe6d24..e02fc682bb68 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -47,6 +47,7 @@ #define IEEE80211_FCTL_MOREDATA 0x2000 #define IEEE80211_FCTL_PROTECTED 0x4000 #define IEEE80211_FCTL_ORDER 0x8000 +#define IEEE80211_FCTL_CTL_EXT 0x0f00 #define IEEE80211_SCTL_FRAG 0x000F #define IEEE80211_SCTL_SEQ 0xFFF0 @@ -54,6 +55,7 @@ #define IEEE80211_FTYPE_MGMT 0x0000 #define IEEE80211_FTYPE_CTL 0x0004 #define IEEE80211_FTYPE_DATA 0x0008 +#define IEEE80211_FTYPE_EXT 0x000c /* management */ #define IEEE80211_STYPE_ASSOC_REQ 0x0000 @@ -70,6 +72,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 #define IEEE80211_STYPE_PSPOLL 0x00A0 @@ -97,6 +100,18 @@ #define IEEE80211_STYPE_QOS_CFPOLL 0x00E0 #define IEEE80211_STYPE_QOS_CFACKPOLL 0x00F0 +/* extension, added by 802.11ad */ +#define IEEE80211_STYPE_DMG_BEACON 0x0000 + +/* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ +#define IEEE80211_CTL_EXT_POLL 0x2000 +#define IEEE80211_CTL_EXT_SPR 0x3000 +#define IEEE80211_CTL_EXT_GRANT 0x4000 +#define IEEE80211_CTL_EXT_DMG_CTS 0x5000 +#define IEEE80211_CTL_EXT_DMG_DTS 0x6000 +#define IEEE80211_CTL_EXT_SSW 0x8000 +#define IEEE80211_CTL_EXT_SSW_FBACK 0x9000 +#define IEEE80211_CTL_EXT_SSW_ACK 0xa000 /* miscellaneous IEEE 802.11 constants */ #define IEEE80211_MAX_FRAG_THRESHOLD 2352 @@ -1191,6 +1206,21 @@ struct ieee80211_vht_mcs_info { #define WLAN_CAPABILITY_QOS (1<<9) #define WLAN_CAPABILITY_SHORT_SLOT_TIME (1<<10) #define WLAN_CAPABILITY_DSSS_OFDM (1<<13) + +/* DMG (60gHz) 802.11ad */ +/* type - bits 0..1 */ +#define WLAN_CAPABILITY_DMG_TYPE_IBSS (1<<0) /* Tx by: STA */ +#define WLAN_CAPABILITY_DMG_TYPE_PBSS (2<<0) /* Tx by: PCP */ +#define WLAN_CAPABILITY_DMG_TYPE_AP (3<<0) /* Tx by: AP */ + +#define WLAN_CAPABILITY_DMG_CBAP_ONLY (1<<2) +#define WLAN_CAPABILITY_DMG_CBAP_SOURCE (1<<3) +#define WLAN_CAPABILITY_DMG_PRIVACY (1<<4) +#define WLAN_CAPABILITY_DMG_ECPAC (1<<5) + +#define WLAN_CAPABILITY_DMG_SPECTRUM_MGMT (1<<8) +#define WLAN_CAPABILITY_DMG_RADIO_MEASURE (1<<12) + /* measurement */ #define IEEE80211_SPCT_MSR_RPRT_MODE_LATE (1<<0) #define IEEE80211_SPCT_MSR_RPRT_MODE_INCAPABLE (1<<1) @@ -1200,7 +1230,6 @@ struct ieee80211_vht_mcs_info { #define IEEE80211_SPCT_MSR_RPRT_TYPE_CCA 1 #define IEEE80211_SPCT_MSR_RPRT_TYPE_RPI 2 - /* 802.11g ERP information element */ #define WLAN_ERP_NON_ERP_PRESENT (1<<0) #define WLAN_ERP_USE_PROTECTION (1<<1) @@ -1212,6 +1241,16 @@ enum { WLAN_ERP_PREAMBLE_LONG = 1, }; +/* Band ID, 802.11ad #8.4.1.45 */ +enum { + IEEE80211_BANDID_TV_WS = 0, /* TV white spaces */ + IEEE80211_BANDID_SUB1 = 1, /* Sub-1 GHz (excluding TV white spaces) */ + IEEE80211_BANDID_2G = 2, /* 2.4 GHz */ + IEEE80211_BANDID_3G = 3, /* 3.6 GHz */ + IEEE80211_BANDID_5G = 4, /* 4.9 and 5 GHz */ + IEEE80211_BANDID_60G = 5, /* 60 GHz */ +}; + /* Status codes */ enum ieee80211_statuscode { WLAN_STATUS_SUCCESS = 0, @@ -1263,6 +1302,17 @@ enum ieee80211_statuscode { WLAN_STATUS_ANTI_CLOG_REQUIRED = 76, WLAN_STATUS_FCG_NOT_SUPP = 78, WLAN_STATUS_STA_NO_TBTT = 78, + /* 802.11ad */ + WLAN_STATUS_REJECTED_WITH_SUGGESTED_CHANGES = 39, + WLAN_STATUS_REJECTED_FOR_DELAY_PERIOD = 47, + WLAN_STATUS_REJECT_WITH_SCHEDULE = 83, + WLAN_STATUS_PENDING_ADMITTING_FST_SESSION = 86, + WLAN_STATUS_PERFORMING_FST_NOW = 87, + WLAN_STATUS_PENDING_GAP_IN_BA_WINDOW = 88, + WLAN_STATUS_REJECT_U_PID_SETTING = 89, + WLAN_STATUS_REJECT_DSE_BAND = 96, + WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, + WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, }; @@ -1422,6 +1472,40 @@ enum ieee80211_eid { WLAN_EID_VHT_CAPABILITY = 191, WLAN_EID_VHT_OPERATION = 192, + + /* 802.11ad */ + WLAN_EID_NON_TX_BSSID_CAP = 83, + WLAN_EID_WAKEUP_SCHEDULE = 143, + WLAN_EID_EXT_SCHEDULE = 144, + WLAN_EID_STA_AVAILABILITY = 145, + WLAN_EID_DMG_TSPEC = 146, + WLAN_EID_DMG_AT = 147, + WLAN_EID_DMG_CAP = 148, + WLAN_EID_DMG_OPERATION = 151, + WLAN_EID_DMG_BSS_PARAM_CHANGE = 152, + WLAN_EID_DMG_BEAM_REFINEMENT = 153, + WLAN_EID_CHANNEL_MEASURE_FEEDBACK = 154, + WLAN_EID_AWAKE_WINDOW = 157, + WLAN_EID_MULTI_BAND = 158, + WLAN_EID_ADDBA_EXT = 159, + WLAN_EID_NEXT_PCP_LIST = 160, + WLAN_EID_PCP_HANDOVER = 161, + WLAN_EID_DMG_LINK_MARGIN = 162, + WLAN_EID_SWITCHING_STREAM = 163, + WLAN_EID_SESSION_TRANSITION = 164, + WLAN_EID_DYN_TONE_PAIRING_REPORT = 165, + WLAN_EID_CLUSTER_REPORT = 166, + WLAN_EID_RELAY_CAP = 167, + WLAN_EID_RELAY_XFER_PARAM_SET = 168, + WLAN_EID_BEAM_LINK_MAINT = 169, + WLAN_EID_MULTIPLE_MAC_ADDR = 170, + WLAN_EID_U_PID = 171, + WLAN_EID_DMG_LINK_ADAPT_ACK = 172, + WLAN_EID_QUIET_PERIOD_REQ = 175, + WLAN_EID_QUIET_PERIOD_RESP = 177, + WLAN_EID_EPAC_POLICY = 182, + WLAN_EID_CLISTER_TIME_OFF = 183, + WLAN_EID_ANTENNA_SECTOR_ID_PATTERN = 190, }; /* Action category code */ @@ -1438,7 +1522,10 @@ enum ieee80211_category { WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, WLAN_CATEGORY_SELF_PROTECTED = 15, + WLAN_CATEGORY_DMG = 16, WLAN_CATEGORY_WMM = 17, + WLAN_CATEGORY_FST = 18, + WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; @@ -1686,6 +1773,7 @@ enum ieee80211_sa_query_action { #define WLAN_CIPHER_SUITE_CCMP 0x000FAC04 #define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 #define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 +#define WLAN_CIPHER_SUITE_GCMP 0x000FAC08 #define WLAN_CIPHER_SUITE_SMS4 0x00147201 -- cgit v1.2.3 From f057bbb6f9ed0fb61ea11105c9ef0ed5ac1a354d Mon Sep 17 00:00:00 2001 From: Rostislav Lisovy Date: Wed, 4 Jul 2012 05:32:03 +0200 Subject: net: em_canid: Ematch rule to match CAN frames according to their identifiers This ematch makes it possible to classify CAN frames (AF_CAN) according to their identifiers. This functionality can not be easily achieved with existing classifiers, such as u32, because CAN identifier is always stored in native endianness, whereas u32 expects Network byte order. Signed-off-by: Rostislav Lisovy Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can.h | 3 + include/linux/pkt_cls.h | 5 +- net/sched/Kconfig | 10 ++ net/sched/Makefile | 1 + net/sched/em_canid.c | 240 ++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 257 insertions(+), 2 deletions(-) create mode 100644 net/sched/em_canid.c (limited to 'include/linux') diff --git a/include/linux/can.h b/include/linux/can.h index 1a66cf6112ae..018055efc034 100644 --- a/include/linux/can.h +++ b/include/linux/can.h @@ -38,6 +38,9 @@ */ typedef __u32 canid_t; +#define CAN_SFF_ID_BITS 11 +#define CAN_EFF_ID_BITS 29 + /* * Controller Area Network Error Message Frame Mask structure * diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h index defbde203d07..38fbd4bc20ab 100644 --- a/include/linux/pkt_cls.h +++ b/include/linux/pkt_cls.h @@ -451,8 +451,9 @@ enum { #define TCF_EM_U32 3 #define TCF_EM_META 4 #define TCF_EM_TEXT 5 -#define TCF_EM_VLAN 6 -#define TCF_EM_MAX 6 +#define TCF_EM_VLAN 6 +#define TCF_EM_CANID 7 +#define TCF_EM_MAX 7 enum { TCF_EM_PROG_TC diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e7a8976bf25c..4a5d2bd4f789 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -507,6 +507,16 @@ config NET_EMATCH_TEXT To compile this code as a module, choose M here: the module will be called em_text. +config NET_EMATCH_CANID + tristate "CAN Identifier" + depends on NET_EMATCH && CAN + ---help--- + Say Y here if you want to be able to classify CAN frames based + on CAN Identifier. + + To compile this code as a module, choose M here: the + module will be called em_canid. + config NET_CLS_ACT bool "Actions" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 5940a1992f0d..bcada751b4ef 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -55,3 +55,4 @@ obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o +obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c new file mode 100644 index 000000000000..bfd34e4c1afc --- /dev/null +++ b/net/sched/em_canid.c @@ -0,0 +1,240 @@ +/* + * em_canid.c Ematch rule to match CAN frames according to their CAN IDs + * + * This program is free software; you can distribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Idea: Oliver Hartkopp + * Copyright: (c) 2011 Czech Technical University in Prague + * (c) 2011 Volkswagen Group Research + * Authors: Michal Sojka + * Pavel Pisa + * Rostislav Lisovy + * Funded by: Volkswagen Group Research + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define EM_CAN_RULES_MAX 500 + +struct canid_match { + /* For each SFF CAN ID (11 bit) there is one record in this bitfield */ + DECLARE_BITMAP(match_sff, (1 << CAN_SFF_ID_BITS)); + + int rules_count; + int sff_rules_count; + int eff_rules_count; + + /* + * Raw rules copied from netlink message; Used for sending + * information to userspace (when 'tc filter show' is invoked) + * AND when matching EFF frames + */ + struct can_filter rules_raw[]; +}; + +/** + * em_canid_get_id() - Extracts Can ID out of the sk_buff structure. + */ +static canid_t em_canid_get_id(struct sk_buff *skb) +{ + /* CAN ID is stored within the data field */ + struct can_frame *cf = (struct can_frame *)skb->data; + + return cf->can_id; +} + +static void em_canid_sff_match_add(struct canid_match *cm, u32 can_id, + u32 can_mask) +{ + int i; + + /* + * Limit can_mask and can_id to SFF range to + * protect against write after end of array + */ + can_mask &= CAN_SFF_MASK; + can_id &= can_mask; + + /* Single frame */ + if (can_mask == CAN_SFF_MASK) { + set_bit(can_id, cm->match_sff); + return; + } + + /* All frames */ + if (can_mask == 0) { + bitmap_fill(cm->match_sff, (1 << CAN_SFF_ID_BITS)); + return; + } + + /* + * Individual frame filter. + * Add record (set bit to 1) for each ID that + * conforms particular rule + */ + for (i = 0; i < (1 << CAN_SFF_ID_BITS); i++) { + if ((i & can_mask) == can_id) + set_bit(i, cm->match_sff); + } +} + +static inline struct canid_match *em_canid_priv(struct tcf_ematch *m) +{ + return (struct canid_match *)m->data; +} + +static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m, + struct tcf_pkt_info *info) +{ + struct canid_match *cm = em_canid_priv(m); + canid_t can_id; + int match = 0; + int i; + const struct can_filter *lp; + + can_id = em_canid_get_id(skb); + + if (can_id & CAN_EFF_FLAG) { + for (i = 0, lp = cm->rules_raw; + i < cm->eff_rules_count; i++, lp++) { + if (!(((lp->can_id ^ can_id) & lp->can_mask))) { + match = 1; + break; + } + } + } else { /* SFF */ + can_id &= CAN_SFF_MASK; + match = (test_bit(can_id, cm->match_sff) ? 1 : 0); + } + + return match; +} + +static int em_canid_change(struct tcf_proto *tp, void *data, int len, + struct tcf_ematch *m) +{ + struct can_filter *conf = data; /* Array with rules */ + struct canid_match *cm; + struct canid_match *cm_old = (struct canid_match *)m->data; + int i; + + if (!len) + return -EINVAL; + + if (len % sizeof(struct can_filter)) + return -EINVAL; + + if (len > sizeof(struct can_filter) * EM_CAN_RULES_MAX) + return -EINVAL; + + cm = kzalloc(sizeof(struct canid_match) + len, GFP_KERNEL); + if (!cm) + return -ENOMEM; + + cm->rules_count = len / sizeof(struct can_filter); + + /* + * We need two for() loops for copying rules into two contiguous + * areas in rules_raw to process all eff rules with a simple loop. + * NB: The configuration interface supports sff and eff rules. + * We do not support filters here that match for the same can_id + * provided in a SFF and EFF frame (e.g. 0x123 / 0x80000123). + * For this (unusual case) two filters have to be specified. The + * SFF/EFF separation is done with the CAN_EFF_FLAG in the can_id. + */ + + /* Fill rules_raw with EFF rules first */ + for (i = 0; i < cm->rules_count; i++) { + if (conf[i].can_id & CAN_EFF_FLAG) { + memcpy(cm->rules_raw + cm->eff_rules_count, + &conf[i], + sizeof(struct can_filter)); + + cm->eff_rules_count++; + } + } + + /* append SFF frame rules */ + for (i = 0; i < cm->rules_count; i++) { + if (!(conf[i].can_id & CAN_EFF_FLAG)) { + memcpy(cm->rules_raw + + cm->eff_rules_count + + cm->sff_rules_count, + &conf[i], sizeof(struct can_filter)); + + cm->sff_rules_count++; + + em_canid_sff_match_add(cm, + conf[i].can_id, conf[i].can_mask); + } + } + + m->datalen = sizeof(struct canid_match) + len; + m->data = (unsigned long)cm; + + if (cm_old != NULL) { + pr_err("canid: Configuring an existing ematch!\n"); + kfree(cm_old); + } + + return 0; +} + +static void em_canid_destroy(struct tcf_proto *tp, struct tcf_ematch *m) +{ + struct canid_match *cm = em_canid_priv(m); + + kfree(cm); +} + +static int em_canid_dump(struct sk_buff *skb, struct tcf_ematch *m) +{ + struct canid_match *cm = em_canid_priv(m); + + /* + * When configuring this ematch 'rules_count' is set not to exceed + * 'rules_raw' array size + */ + if (nla_put_nohdr(skb, sizeof(struct can_filter) * cm->rules_count, + &cm->rules_raw) < 0) + return -EMSGSIZE; + + return 0; +} + +static struct tcf_ematch_ops em_canid_ops = { + .kind = TCF_EM_CANID, + .change = em_canid_change, + .match = em_canid_match, + .destroy = em_canid_destroy, + .dump = em_canid_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_canid_ops.link) +}; + +static int __init init_em_canid(void) +{ + return tcf_em_register(&em_canid_ops); +} + +static void __exit exit_em_canid(void) +{ + tcf_em_unregister(&em_canid_ops); +} + +MODULE_LICENSE("GPL"); + +module_init(init_em_canid); +module_exit(exit_em_canid); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_CANID); -- cgit v1.2.3 From 46ba5a25f521e3c50d7bb81b1abb977769047456 Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Wed, 27 Jun 2012 00:59:56 +0000 Subject: netfilter: nfnetlink_queue: do not allow to set unsupported flag bits Allow setting of only supported flag bits in queue->flags. Signed-off-by: Krishna Kumar Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_queue.h | 1 + net/netfilter/nfnetlink_queue_core.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index e0d8fd8d4d24..3b1c1360aedf 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -95,5 +95,6 @@ enum nfqnl_attr_config { /* Flags for NFQA_CFG_FLAGS */ #define NFQA_CFG_F_FAIL_OPEN (1 << 0) #define NFQA_CFG_F_CONNTRACK (1 << 1) +#define NFQA_CFG_F_MAX (1 << 2) #endif /* _NFNETLINK_QUEUE_H */ diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index a0b64920039d..c0496a55ad0c 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -910,6 +910,11 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); + if (flags >= NFQA_CFG_F_MAX) { + ret = -EOPNOTSUPP; + goto err_out_unlock; + } + spin_lock_bh(&queue->lock); queue->flags &= ~mask; queue->flags |= flags & mask; -- cgit v1.2.3 From 16917b87a23b429226527f393270047069d665e9 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 1 Jul 2012 03:18:50 +0000 Subject: net-next: Add netif_get_num_default_rss_queues Most multi-queue networking driver consider the number of online cpus when configuring RSS queues. This patch adds a wrapper to the number of cpus, setting an upper limit on the number of cpus a driver should consider (by default) when allocating resources for his queues. Signed-off-by: Yuval Mintz Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/core/dev.c | 11 +++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2c2ecea28a1b..ab0251d541ab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2119,6 +2119,9 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev, #endif } +#define DEFAULT_MAX_NUM_RSS_QUEUES (8) +extern int netif_get_num_default_rss_queues(void); + /* Use this variant when it is known for sure that it * is executing from hardware interrupt context or with hardware interrupts * disabled. diff --git a/net/core/dev.c b/net/core/dev.c index ed674e212b7a..69f7a1a393d8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1793,6 +1793,17 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif +/* netif_get_num_default_rss_queues - default number of RSS queues + * + * This routine should set an upper limit on the number of RSS queues + * used by default by multiqueue devices. + */ +int netif_get_num_default_rss_queues() +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; -- cgit v1.2.3 From 8eb41c8dfb9e2396d2452ada9023a83d610b9051 Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Thu, 5 Jul 2012 14:25:49 +0300 Subject: {nl,cfg}80211: support high bitrates Until now, a u16 value was used to represent bitrate value. With VHT bitrates this becomes too small. Introduce a new 32-bit bitrate attribute. nl80211 will report both the new and the old attribute, unless the bitrate doesn't fit into the old u16 attribute in which case only the new one will be reported. User space tools encouraged to prefer the 32-bit attribute, if available (since it won't be available on older kernels.) Signed-off-by: Vladimir Kondratiev [reword commit message and comments a bit] Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 9 +++++++++ include/net/cfg80211.h | 2 +- net/wireless/nl80211.c | 9 +++++++-- net/wireless/util.c | 2 +- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 74cc55c1bf28..db961a59247f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1638,12 +1638,20 @@ struct nl80211_sta_flag_update { * * These attribute types are used with %NL80211_STA_INFO_TXRATE * when getting information about the bitrate of a station. + * There are 2 attributes for bitrate, a legacy one that represents + * a 16-bit value, and new one that represents a 32-bit value. + * If the rate value fits into 16 bit, both attributes are reported + * with the same value. If the rate is too high to fit into 16 bits + * (>6.5535Gbps) only 32-bit attribute is included. + * User space tools encouraged to use the 32-bit attribute and fall + * back to the 16-bit one for compatibility with older kernels. * * @__NL80211_RATE_INFO_INVALID: attribute number 0 is reserved * @NL80211_RATE_INFO_BITRATE: total bitrate (u16, 100kbit/s) * @NL80211_RATE_INFO_MCS: mcs index for 802.11n (u8) * @NL80211_RATE_INFO_40_MHZ_WIDTH: 40 Mhz dualchannel bitrate * @NL80211_RATE_INFO_SHORT_GI: 400ns guard interval + * @NL80211_RATE_INFO_BITRATE32: total bitrate (u32, 100kbit/s) * @NL80211_RATE_INFO_MAX: highest rate_info number currently defined * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ @@ -1653,6 +1661,7 @@ enum nl80211_rate_info { NL80211_RATE_INFO_MCS, NL80211_RATE_INFO_40_MHZ_WIDTH, NL80211_RATE_INFO_SHORT_GI, + NL80211_RATE_INFO_BITRATE32, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0b564e83a24b..8837efc368f9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3487,7 +3487,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, int freq, * * return 0 if MCS index >= 32 */ -u16 cfg80211_calculate_bitrate(struct rate_info *rate); +u32 cfg80211_calculate_bitrate(struct rate_info *rate); /* Logging, debugging and troubleshooting/diagnostic helpers. */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 77102e66f1ea..2a5cdb60bc6e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2618,7 +2618,8 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) { struct nlattr *rate; - u16 bitrate; + u32 bitrate; + u16 bitrate_compat; rate = nla_nest_start(msg, attr); if (!rate) @@ -2626,8 +2627,12 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, /* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */ bitrate = cfg80211_calculate_bitrate(info); + /* report 16-bit bitrate only if we can */ + bitrate_compat = bitrate < (1UL << 16) ? bitrate : 0; if ((bitrate > 0 && - nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate)) || + nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate)) || + (bitrate_compat > 0 && + nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat)) || ((info->flags & RATE_INFO_FLAGS_MCS) && nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) || ((info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) && diff --git a/net/wireless/util.c b/net/wireless/util.c index 0228c64e73d8..6e52726f7fe3 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -900,7 +900,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, return err; } -u16 cfg80211_calculate_bitrate(struct rate_info *rate) +u32 cfg80211_calculate_bitrate(struct rate_info *rate) { int modulation, streams, bitrate; -- cgit v1.2.3 From c96d97f4d127b61def87b3ee056bec20cfc265d1 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 5 Jul 2012 04:03:44 +0000 Subject: net/mlx4: Set steering mode according to device capabilities Instead of checking the firmware supported steering mode in various places in the code, add a dedicated field in the mlx4 device capabilities structure which is written once during the initialization flow and read across the code. This also set the grounds for add new steering modes. Currently two modes are supported, and are named after the ConnectX HW versions A0 and B0. A0 steering uses mac_index, vlan_index and priority to steer traffic into pre-defined range of QPs. B0 steering uses Ethernet L2 hashing rules and is enabled only if the firmware supports both unicast and multicast B0 steering, The current steering modes are relevant for Ethernet traffic only, such that Infiniband steering remains untouched. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 108 ++++++++++++++++--------- drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +- drivers/net/ethernet/mellanox/mlx4/main.c | 16 +++- drivers/net/ethernet/mellanox/mlx4/mcg.c | 70 ++++++++-------- drivers/net/ethernet/mellanox/mlx4/port.c | 9 +-- include/linux/mlx4/device.h | 24 ++++++ 6 files changed, 148 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index bedcbb30d38f..44ff7cdb15e5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -265,7 +265,7 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) struct mlx4_en_mc_list *mclist, *tmp; u64 mcast_addr = 0; u8 mc_list[16] = {0}; - int err; + int err = 0; mutex_lock(&mdev->state_lock); if (!mdev->device_up) { @@ -300,16 +300,36 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) priv->flags |= MLX4_EN_FLAG_PROMISC; /* Enable promiscouos mode */ - if (!(mdev->dev->caps.flags & - MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port, - priv->base_qpn, 1); - else - err = mlx4_unicast_promisc_add(mdev->dev, priv->base_qpn, + switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: + err = mlx4_unicast_promisc_add(mdev->dev, + priv->base_qpn, priv->port); - if (err) - en_err(priv, "Failed enabling " - "promiscuous mode\n"); + if (err) + en_err(priv, "Failed enabling unicast promiscuous mode\n"); + + /* Add the default qp number as multicast + * promisc + */ + if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) { + err = mlx4_multicast_promisc_add(mdev->dev, + priv->base_qpn, + priv->port); + if (err) + en_err(priv, "Failed enabling multicast promiscuous mode\n"); + priv->flags |= MLX4_EN_FLAG_MC_PROMISC; + } + break; + + case MLX4_STEERING_MODE_A0: + err = mlx4_SET_PORT_qpn_calc(mdev->dev, + priv->port, + priv->base_qpn, + 1); + if (err) + en_err(priv, "Failed enabling promiscuous mode\n"); + break; + } /* Disable port multicast filter (unconditionally) */ err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, @@ -318,15 +338,6 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) en_err(priv, "Failed disabling " "multicast filter\n"); - /* Add the default qp number as multicast promisc */ - if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) { - err = mlx4_multicast_promisc_add(mdev->dev, priv->base_qpn, - priv->port); - if (err) - en_err(priv, "Failed entering multicast promisc mode\n"); - priv->flags |= MLX4_EN_FLAG_MC_PROMISC; - } - /* Disable port VLAN filter */ err = mlx4_SET_VLAN_FLTR(mdev->dev, priv); if (err) @@ -345,22 +356,31 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) priv->flags &= ~MLX4_EN_FLAG_PROMISC; /* Disable promiscouos mode */ - if (!(mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port, - priv->base_qpn, 0); - else - err = mlx4_unicast_promisc_remove(mdev->dev, priv->base_qpn, + switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: + err = mlx4_unicast_promisc_remove(mdev->dev, + priv->base_qpn, priv->port); - if (err) - en_err(priv, "Failed disabling promiscuous mode\n"); + if (err) + en_err(priv, "Failed disabling unicast promiscuous mode\n"); + /* Disable Multicast promisc */ + if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) { + err = mlx4_multicast_promisc_remove(mdev->dev, + priv->base_qpn, + priv->port); + if (err) + en_err(priv, "Failed disabling multicast promiscuous mode\n"); + priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC; + } + break; - /* Disable Multicast promisc */ - if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) { - err = mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn, - priv->port); + case MLX4_STEERING_MODE_A0: + err = mlx4_SET_PORT_qpn_calc(mdev->dev, + priv->port, + priv->base_qpn, 0); if (err) - en_err(priv, "Failed disabling multicast promiscuous mode\n"); - priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC; + en_err(priv, "Failed disabling promiscuous mode\n"); + break; } /* Enable port VLAN filter */ @@ -378,8 +398,16 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) /* Add the default qp number as multicast promisc */ if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) { - err = mlx4_multicast_promisc_add(mdev->dev, priv->base_qpn, - priv->port); + switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: + err = mlx4_multicast_promisc_add(mdev->dev, + priv->base_qpn, + priv->port); + break; + + case MLX4_STEERING_MODE_A0: + break; + } if (err) en_err(priv, "Failed entering multicast promisc mode\n"); priv->flags |= MLX4_EN_FLAG_MC_PROMISC; @@ -387,8 +415,16 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) } else { /* Disable Multicast promisc */ if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) { - err = mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn, - priv->port); + switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: + err = mlx4_multicast_promisc_remove(mdev->dev, + priv->base_qpn, + priv->port); + break; + + case MLX4_STEERING_MODE_A0: + break; + } if (err) en_err(priv, "Failed disabling multicast promiscuous mode\n"); priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 9c83bb8151ea..40e048bac024 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1124,7 +1124,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET); MLX4_PUT(inbox, param->log_mc_entry_sz, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); MLX4_PUT(inbox, param->log_mc_hash_sz, INIT_HCA_LOG_MC_HASH_SZ_OFFSET); - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) + if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0) MLX4_PUT(inbox, (u8) (1 << 3), INIT_HCA_UC_STEERING_OFFSET); MLX4_PUT(inbox, param->log_mc_table_sz, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 14d9c762b60f..f8125a82c0cb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -244,7 +244,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.reserved_srqs = dev_cap->reserved_srqs; dev->caps.max_sq_desc_sz = dev_cap->max_sq_desc_sz; dev->caps.max_rq_desc_sz = dev_cap->max_rq_desc_sz; - dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); /* * Subtract 1 from the limit because we need to allocate a * spare CQE so the HCA HW can tell the difference between an @@ -275,6 +274,21 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER && + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) { + dev->caps.steering_mode = MLX4_STEERING_MODE_B0; + } else { + dev->caps.steering_mode = MLX4_STEERING_MODE_A0; + + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) + mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags " + "set to use B0 steering. Falling back to A0 steering mode.\n"); + } + mlx4_dbg(dev, "Steering mode is: %s\n", + mlx4_steering_mode_str(dev->caps.steering_mode)); + dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); + /* Sense port always allowed on supported devices for ConnectX1 and 2 */ if (dev->pdev->device != 0x1003) dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index f4a8f98e402a..319c9d45d59a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -868,36 +868,50 @@ static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp, int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot) { - if (prot == MLX4_PROT_ETH && - !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)) - return 0; - if (prot == MLX4_PROT_ETH) - gid[7] |= (MLX4_MC_STEER << 1); + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_A0: + if (prot == MLX4_PROT_ETH) + return 0; - if (mlx4_is_mfunc(dev)) - return mlx4_QP_ATTACH(dev, qp, gid, 1, - block_mcast_loopback, prot); + case MLX4_STEERING_MODE_B0: + if (prot == MLX4_PROT_ETH) + gid[7] |= (MLX4_MC_STEER << 1); - return mlx4_qp_attach_common(dev, qp, gid, block_mcast_loopback, - prot, MLX4_MC_STEER); + if (mlx4_is_mfunc(dev)) + return mlx4_QP_ATTACH(dev, qp, gid, 1, + block_mcast_loopback, prot); + return mlx4_qp_attach_common(dev, qp, gid, + block_mcast_loopback, prot, + MLX4_MC_STEER); + + default: + return -EINVAL; + } } EXPORT_SYMBOL_GPL(mlx4_multicast_attach); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], enum mlx4_protocol prot) { - if (prot == MLX4_PROT_ETH && - !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)) - return 0; + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_A0: + if (prot == MLX4_PROT_ETH) + return 0; - if (prot == MLX4_PROT_ETH) - gid[7] |= (MLX4_MC_STEER << 1); + case MLX4_STEERING_MODE_B0: + if (prot == MLX4_PROT_ETH) + gid[7] |= (MLX4_MC_STEER << 1); - if (mlx4_is_mfunc(dev)) - return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot); + if (mlx4_is_mfunc(dev)) + return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot); + + return mlx4_qp_detach_common(dev, qp, gid, prot, + MLX4_MC_STEER); - return mlx4_qp_detach_common(dev, qp, gid, prot, MLX4_MC_STEER); + default: + return -EINVAL; + } } EXPORT_SYMBOL_GPL(mlx4_multicast_detach); @@ -905,10 +919,6 @@ int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot) { - if (prot == MLX4_PROT_ETH && - !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - return 0; - if (prot == MLX4_PROT_ETH) gid[7] |= (MLX4_UC_STEER << 1); @@ -924,10 +934,6 @@ EXPORT_SYMBOL_GPL(mlx4_unicast_attach); int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], enum mlx4_protocol prot) { - if (prot == MLX4_PROT_ETH && - !(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - return 0; - if (prot == MLX4_PROT_ETH) gid[7] |= (MLX4_UC_STEER << 1); @@ -968,9 +974,6 @@ static int mlx4_PROMISC(struct mlx4_dev *dev, u32 qpn, int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port) { - if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)) - return 0; - if (mlx4_is_mfunc(dev)) return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 1, port); @@ -980,9 +983,6 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_add); int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port) { - if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)) - return 0; - if (mlx4_is_mfunc(dev)) return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 0, port); @@ -992,9 +992,6 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_remove); int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port) { - if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - return 0; - if (mlx4_is_mfunc(dev)) return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 1, port); @@ -1004,9 +1001,6 @@ EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_add); int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port) { - if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) - return 0; - if (mlx4_is_mfunc(dev)) return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 0, port); diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index a8fb52992c64..58de7237f57a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -155,7 +155,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) return err; } - if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) { + if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { *qpn = info->base_qpn + index; return 0; } @@ -206,7 +206,7 @@ void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn) (unsigned long long) mac); mlx4_unregister_mac(dev, port, mac); - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) { + if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) { entry = radix_tree_lookup(&info->mac_tree, qpn); if (entry) { mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx," @@ -359,7 +359,7 @@ int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) int index = qpn - info->base_qpn; int err = 0; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) { + if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) { entry = radix_tree_lookup(&info->mac_tree, qpn); if (!entry) return -EINVAL; @@ -803,8 +803,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u32 m_promisc = (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) ? MCAST_DIRECT : MCAST_DEFAULT; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER && - dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) + if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) return 0; mailbox = mlx4_alloc_cmd_mailbox(dev); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6a8f002b8ed3..7f5c9ee42f96 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -70,6 +70,29 @@ enum { MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1) }; +/* Driver supports 2 diffrent device methods to manage traffic steering: + * - B0 steering mode - Common low level API for ib and (if supported) eth. + * - A0 steering mode - Limited low level API for eth. In case of IB, + * B0 mode is in use. + */ +enum { + MLX4_STEERING_MODE_A0, + MLX4_STEERING_MODE_B0 +}; + +static inline const char *mlx4_steering_mode_str(int steering_mode) +{ + switch (steering_mode) { + case MLX4_STEERING_MODE_A0: + return "A0 steering"; + + case MLX4_STEERING_MODE_B0: + return "B0 steering"; + default: + return "Unrecognize steering mode"; + } +} + enum { MLX4_DEV_CAP_FLAG_RC = 1LL << 0, MLX4_DEV_CAP_FLAG_UC = 1LL << 1, @@ -295,6 +318,7 @@ struct mlx4_caps { int num_amgms; int reserved_mcgs; int num_qp_per_mgm; + int steering_mode; int num_pds; int reserved_pds; int max_xrcds; -- cgit v1.2.3 From 8fcfb4db74352d3d447b7a559ad54f7577074d19 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 5 Jul 2012 04:03:45 +0000 Subject: net/mlx4_core: Add firmware commands to support device managed flow steering Add support for firmware commands to attach/detach a new device managed steering mode. Such network steering rules allow the user to provide an L2/L3/L4 flow specification to the firmware and have the device to steer traffic that matches that specification to the provided QP. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 19 ++++++++++++++ drivers/net/ethernet/mellanox/mlx4/mcg.c | 29 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/mlx4.h | 10 ++++++++ .../net/ethernet/mellanox/mlx4/resource_tracker.c | 24 ++++++++++++++++++ include/linux/mlx4/cmd.h | 4 +++ 5 files changed, 86 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 842c8ce9494e..7e94987d030c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1080,6 +1080,25 @@ static struct mlx4_cmd_info cmd_info[] = { .verify = NULL, .wrapper = NULL }, + /* flow steering commands */ + { + .opcode = MLX4_QP_FLOW_STEERING_ATTACH, + .has_inbox = true, + .has_outbox = false, + .out_is_imm = true, + .encode_slave_id = false, + .verify = NULL, + .wrapper = mlx4_QP_FLOW_STEERING_ATTACH_wrapper + }, + { + .opcode = MLX4_QP_FLOW_STEERING_DETACH, + .has_inbox = false, + .has_outbox = false, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, + .wrapper = mlx4_QP_FLOW_STEERING_DETACH_wrapper + }, }; static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave, diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 319c9d45d59a..3c59a33a98a5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -62,6 +62,35 @@ int mlx4_get_qp_per_mgm(struct mlx4_dev *dev) return 4 * (mlx4_get_mgm_entry_size(dev) / 16 - 2); } +static int mlx4_QP_FLOW_STEERING_ATTACH(struct mlx4_dev *dev, + struct mlx4_cmd_mailbox *mailbox, + u32 size, + u64 *reg_id) +{ + u64 imm; + int err = 0; + + err = mlx4_cmd_imm(dev, mailbox->dma, &imm, size, 0, + MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + if (err) + return err; + *reg_id = imm; + + return err; +} + +static int mlx4_QP_FLOW_STEERING_DETACH(struct mlx4_dev *dev, u64 regid) +{ + int err = 0; + + err = mlx4_cmd(dev, regid, 0, 0, + MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + + return err; +} + static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index, struct mlx4_cmd_mailbox *mailbox) { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index a425a984758f..c07e882e8369 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1118,6 +1118,16 @@ int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); +int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); int mlx4_get_mgm_entry_size(struct mlx4_dev *dev); int mlx4_get_qp_per_mgm(struct mlx4_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 6bdac2955f8b..a8ca960f4620 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2738,6 +2738,30 @@ ex_put: return err; } +int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + return mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, + vhcr->in_modifier, 0, + MLX4_QP_FLOW_STEERING_ATTACH, + MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); +} + +int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + return mlx4_cmd(dev, vhcr->in_param, 0, 0, + MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); +} + enum { BUSY_MAX_RETRIES = 10 }; diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 1f3860a8a109..260695186256 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -154,6 +154,10 @@ enum { /* set port opcode modifiers */ MLX4_SET_PORT_PRIO2TC = 0x8, MLX4_SET_PORT_SCHEDULER = 0x9, + + /* register/delete flow steering network rules */ + MLX4_QP_FLOW_STEERING_ATTACH = 0x65, + MLX4_QP_FLOW_STEERING_DETACH = 0x66, }; enum { -- cgit v1.2.3 From 0ff1fb654bec0cff62ddf81a8a8edec4263604a0 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 5 Jul 2012 04:03:46 +0000 Subject: {NET, IB}/mlx4: Add device managed flow steering firmware API The driver is modified to support three operation modes. If supported by firmware use the device managed flow steering API, that which we call device managed steering mode. Else, if the firmware supports the B0 steering mode use it, and finally, if none of the above, use the A0 steering mode. When the steering mode is device managed, the code is modified such that L2 based rules set by the mlx4_en driver for Ethernet unicast and multicast, and the IB stack multicast attach calls done through the mlx4_ib driver are all routed to use the device managed API. When attaching rule using device managed flow steering API, the firmware returns a 64 bit registration id, which is to be provided during detach. Currently the firmware is always programmed during HCA initialization to use standard L2 hashing. Future work should be done to allow configuring the flow-steering hash function with common, non proprietary means. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 62 +++- drivers/infiniband/hw/mlx4/mlx4_ib.h | 1 + drivers/infiniband/hw/mlx4/qp.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 21 +- drivers/net/ethernet/mellanox/mlx4/fw.c | 91 ++++- drivers/net/ethernet/mellanox/mlx4/fw.h | 3 + drivers/net/ethernet/mellanox/mlx4/main.c | 56 +++- drivers/net/ethernet/mellanox/mlx4/mcg.c | 365 ++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 13 + drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 + drivers/net/ethernet/mellanox/mlx4/port.c | 98 ++++-- drivers/net/ethernet/mellanox/mlx4/profile.c | 12 +- .../net/ethernet/mellanox/mlx4/resource_tracker.c | 6 + include/linux/mlx4/device.h | 108 +++++- 14 files changed, 758 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 3530c41fcd1f..8a3a2037b005 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -718,26 +718,53 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, return ret; } +struct mlx4_ib_steering { + struct list_head list; + u64 reg_id; + union ib_gid gid; +}; + static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { int err; struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); struct mlx4_ib_qp *mqp = to_mqp(ibqp); + u64 reg_id; + struct mlx4_ib_steering *ib_steering = NULL; + + if (mdev->dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL); + if (!ib_steering) + return -ENOMEM; + } - err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, - !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), - MLX4_PROT_IB_IPV6); + err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port, + !!(mqp->flags & + MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), + MLX4_PROT_IB_IPV6, ®_id); if (err) - return err; + goto err_malloc; err = add_gid_entry(ibqp, gid); if (err) goto err_add; + if (ib_steering) { + memcpy(ib_steering->gid.raw, gid->raw, 16); + ib_steering->reg_id = reg_id; + mutex_lock(&mqp->mutex); + list_add(&ib_steering->list, &mqp->steering_rules); + mutex_unlock(&mqp->mutex); + } return 0; err_add: - mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6); + mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + MLX4_PROT_IB_IPV6, reg_id); +err_malloc: + kfree(ib_steering); + return err; } @@ -765,9 +792,30 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) u8 mac[6]; struct net_device *ndev; struct mlx4_ib_gid_entry *ge; + u64 reg_id = 0; + + if (mdev->dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + struct mlx4_ib_steering *ib_steering; + + mutex_lock(&mqp->mutex); + list_for_each_entry(ib_steering, &mqp->steering_rules, list) { + if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) { + list_del(&ib_steering->list); + break; + } + } + mutex_unlock(&mqp->mutex); + if (&ib_steering->list == &mqp->steering_rules) { + pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n"); + return -EINVAL; + } + reg_id = ib_steering->reg_id; + kfree(ib_steering); + } - err = mlx4_multicast_detach(mdev->dev, - &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6); + err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + MLX4_PROT_IB_IPV6, reg_id); if (err) return err; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index ff36655d23d3..42df4f7a6a5b 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -163,6 +163,7 @@ struct mlx4_ib_qp { u8 state; int mlx_type; struct list_head gid_list; + struct list_head steering_rules; }; struct mlx4_ib_srq { diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 8d4ed24aef93..6af19f6c2b11 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -495,6 +495,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); INIT_LIST_HEAD(&qp->gid_list); + INIT_LIST_HEAD(&qp->steering_rules); qp->state = IB_QPS_RESET; if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 44ff7cdb15e5..eb5ed8e39873 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -463,7 +463,8 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) err = mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - MLX4_PROT_ETH); + MLX4_PROT_ETH, + mclist->reg_id); if (err) en_err(priv, "Fail to detach multicast address\n"); @@ -475,11 +476,14 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) if (mclist->action == MCLIST_ADD) { /* attach the address */ memcpy(&mc_list[10], mclist->addr, ETH_ALEN); + /* needed for B0 steering support */ mc_list[5] = priv->port; err = mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, - mc_list, 0, - MLX4_PROT_ETH); + mc_list, + priv->port, 0, + MLX4_PROT_ETH, + &mclist->reg_id); if (err) en_err(priv, "Fail to attach multicast address\n"); @@ -827,9 +831,10 @@ int mlx4_en_start_port(struct net_device *dev) /* Attach rx QP to bradcast address */ memset(&mc_list[10], 0xff, ETH_ALEN); - mc_list[5] = priv->port; + mc_list[5] = priv->port; /* needed for B0 steering support */ if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - 0, MLX4_PROT_ETH)) + priv->port, 0, MLX4_PROT_ETH, + &priv->broadcast_id)) mlx4_warn(mdev, "Failed Attaching Broadcast\n"); /* Must redo promiscuous mode setup. */ @@ -886,14 +891,14 @@ void mlx4_en_stop_port(struct net_device *dev) /* Detach All multicasts */ memset(&mc_list[10], 0xff, ETH_ALEN); - mc_list[5] = priv->port; + mc_list[5] = priv->port; /* needed for B0 steering support */ mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - MLX4_PROT_ETH); + MLX4_PROT_ETH, priv->broadcast_id); list_for_each_entry(mclist, &priv->curr_list, list) { memcpy(&mc_list[10], mclist->addr, ETH_ALEN); mc_list[5] = priv->port; mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, - mc_list, MLX4_PROT_ETH); + mc_list, MLX4_PROT_ETH, mclist->reg_id); } mlx4_en_clear_list(dev); list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 40e048bac024..1d70657058a5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -123,7 +123,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) static const char * const fname[] = { [0] = "RSS support", [1] = "RSS Toeplitz Hash Function support", - [2] = "RSS XOR Hash Function support" + [2] = "RSS XOR Hash Function support", + [3] = "Device manage flow steering support" }; int i; @@ -391,6 +392,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_RSVD_XRC_OFFSET 0x66 #define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68 +#define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76 +#define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80 #define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET 0x82 #define QUERY_DEV_CAP_AUX_ENTRY_SZ_OFFSET 0x84 @@ -474,6 +477,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->num_ports = field & 0xf; MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MSG_SZ_OFFSET); dev_cap->max_msg_sz = 1 << (field & 0x1f); + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET); + if (field & 0x80) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN; + dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f; + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET); + dev_cap->fs_max_num_qp_per_entry = field; MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET); dev_cap->stat_rate_support = stat_rate; MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); @@ -1061,6 +1070,15 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) +#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 +#define INIT_HCA_FS_PARAM_OFFSET 0x1d0 +#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) +#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) +#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b) +#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21) +#define INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22) +#define INIT_HCA_FS_IB_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x25) +#define INIT_HCA_FS_IB_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x26) #define INIT_HCA_TPT_OFFSET 0x0f0 #define INIT_HCA_DMPT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x00) #define INIT_HCA_LOG_MPT_SZ_OFFSET (INIT_HCA_TPT_OFFSET + 0x0b) @@ -1119,14 +1137,44 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) MLX4_PUT(inbox, param->rdmarc_base, INIT_HCA_RDMARC_BASE_OFFSET); MLX4_PUT(inbox, param->log_rd_per_qp, INIT_HCA_LOG_RD_OFFSET); - /* multicast attributes */ - - MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET); - MLX4_PUT(inbox, param->log_mc_entry_sz, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); - MLX4_PUT(inbox, param->log_mc_hash_sz, INIT_HCA_LOG_MC_HASH_SZ_OFFSET); - if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0) - MLX4_PUT(inbox, (u8) (1 << 3), INIT_HCA_UC_STEERING_OFFSET); - MLX4_PUT(inbox, param->log_mc_table_sz, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + /* steering attributes */ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= + cpu_to_be32(1 << + INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN); + + MLX4_PUT(inbox, param->mc_base, INIT_HCA_FS_BASE_OFFSET); + MLX4_PUT(inbox, param->log_mc_entry_sz, + INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_table_sz, + INIT_HCA_FS_LOG_TABLE_SZ_OFFSET); + /* Enable Ethernet flow steering + * with udp unicast and tcp unicast + */ + MLX4_PUT(inbox, param->fs_hash_enable_bits, + INIT_HCA_FS_ETH_BITS_OFFSET); + MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR, + INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET); + /* Enable IPoIB flow steering + * with udp unicast and tcp unicast + */ + MLX4_PUT(inbox, param->fs_hash_enable_bits, + INIT_HCA_FS_IB_BITS_OFFSET); + MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR, + INIT_HCA_FS_IB_NUM_ADDRS_OFFSET); + } else { + MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET); + MLX4_PUT(inbox, param->log_mc_entry_sz, + INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_hash_sz, + INIT_HCA_LOG_MC_HASH_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_table_sz, + INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0) + MLX4_PUT(inbox, (u8) (1 << 3), + INIT_HCA_UC_STEERING_OFFSET); + } /* TPT attributes */ @@ -1188,15 +1236,24 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev, MLX4_GET(param->rdmarc_base, outbox, INIT_HCA_RDMARC_BASE_OFFSET); MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET); - /* multicast attributes */ + /* steering attributes */ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { - MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET); - MLX4_GET(param->log_mc_entry_sz, outbox, - INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); - MLX4_GET(param->log_mc_hash_sz, outbox, - INIT_HCA_LOG_MC_HASH_SZ_OFFSET); - MLX4_GET(param->log_mc_table_sz, outbox, - INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET); + MLX4_GET(param->log_mc_entry_sz, outbox, + INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET); + MLX4_GET(param->log_mc_table_sz, outbox, + INIT_HCA_FS_LOG_TABLE_SZ_OFFSET); + } else { + MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET); + MLX4_GET(param->log_mc_entry_sz, outbox, + INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); + MLX4_GET(param->log_mc_hash_sz, outbox, + INIT_HCA_LOG_MC_HASH_SZ_OFFSET); + MLX4_GET(param->log_mc_table_sz, outbox, + INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + } /* TPT attributes */ diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 64c0399e4b78..83fcbbf1b169 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -78,6 +78,8 @@ struct mlx4_dev_cap { u16 wavelength[MLX4_MAX_PORTS + 1]; u64 trans_code[MLX4_MAX_PORTS + 1]; u16 stat_rate_support; + int fs_log_max_ucast_qp_range_size; + int fs_max_num_qp_per_entry; u64 flags; u64 flags2; int reserved_uars; @@ -165,6 +167,7 @@ struct mlx4_init_hca_param { u8 log_mpt_sz; u8 log_uar_sz; u8 uar_page_sz; /* log pg sz in 4k chunks */ + u8 fs_hash_enable_bits; }; struct mlx4_init_ib_param { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f8125a82c0cb..42645166bae2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -91,7 +91,9 @@ module_param_named(log_num_mgm_entry_size, MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num" " of qp per mcg, for example:" " 10 gives 248.range: 9<=" - " log_num_mgm_entry_size <= 12"); + " log_num_mgm_entry_size <= 12." + " Not in use with device managed" + " flow steering"); #define MLX4_VF (1 << 0) @@ -274,20 +276,27 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER && - dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) { - dev->caps.steering_mode = MLX4_STEERING_MODE_B0; + if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) { + dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED; + dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry; + dev->caps.fs_log_max_ucast_qp_range_size = + dev_cap->fs_log_max_ucast_qp_range_size; } else { - dev->caps.steering_mode = MLX4_STEERING_MODE_A0; + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER && + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) { + dev->caps.steering_mode = MLX4_STEERING_MODE_B0; + } else { + dev->caps.steering_mode = MLX4_STEERING_MODE_A0; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || - dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) - mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags " - "set to use B0 steering. Falling back to A0 steering mode.\n"); + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) + mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags " + "set to use B0 steering. Falling back to A0 steering mode.\n"); + } + dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); } mlx4_dbg(dev, "Steering mode is: %s\n", mlx4_steering_mode_str(dev->caps.steering_mode)); - dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); /* Sense port always allowed on supported devices for ConnectX1 and 2 */ if (dev->pdev->device != 0x1003) @@ -982,9 +991,11 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, } /* - * It's not strictly required, but for simplicity just map the - * whole multicast group table now. The table isn't very big - * and it's a lot easier than trying to track ref counts. + * For flow steering device managed mode it is required to use + * mlx4_init_icm_table. For B0 steering mode it's not strictly + * required, but for simplicity just map the whole multicast + * group table now. The table isn't very big and it's a lot + * easier than trying to track ref counts. */ err = mlx4_init_icm_table(dev, &priv->mcg_table.table, init_hca->mc_base, @@ -1220,7 +1231,26 @@ static int mlx4_init_hca(struct mlx4_dev *dev) goto err_stop_fw; } + priv->fs_hash_mode = MLX4_FS_L2_HASH; + + switch (priv->fs_hash_mode) { + case MLX4_FS_L2_HASH: + init_hca.fs_hash_enable_bits = 0; + break; + + case MLX4_FS_L2_L3_L4_HASH: + /* Enable flow steering with + * udp unicast and tcp unicast + */ + init_hca.fs_hash_enable_bits = + MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN; + break; + } + profile = default_profile; + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + profile.num_mcg = MLX4_FS_NUM_MCG; icm_size = mlx4_make_profile(dev, &profile, &dev_cap, &init_hca); diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 3c59a33a98a5..768a2a4530e8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -41,6 +41,7 @@ #define MGM_QPN_MASK 0x00FFFFFF #define MGM_BLCK_LB_BIT 30 +#define MLX4_MAC_MASK 0xffffffffffffULL static const u8 zero_gid[16]; /* automatically initialized to 0 */ @@ -54,7 +55,12 @@ struct mlx4_mgm { int mlx4_get_mgm_entry_size(struct mlx4_dev *dev) { - return min((1 << mlx4_log_num_mgm_entry_size), MLX4_MAX_MGM_ENTRY_SIZE); + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE; + else + return min((1 << mlx4_log_num_mgm_entry_size), + MLX4_MAX_MGM_ENTRY_SIZE); } int mlx4_get_qp_per_mgm(struct mlx4_dev *dev) @@ -643,6 +649,311 @@ static int find_entry(struct mlx4_dev *dev, u8 port, return err; } +struct mlx4_net_trans_rule_hw_ctrl { + __be32 ctrl; + __be32 vf_vep_port; + __be32 qpn; + __be32 reserved; +}; + +static void trans_rule_ctrl_to_hw(struct mlx4_net_trans_rule *ctrl, + struct mlx4_net_trans_rule_hw_ctrl *hw) +{ + static const u8 __promisc_mode[] = { + [MLX4_FS_PROMISC_NONE] = 0x0, + [MLX4_FS_PROMISC_UPLINK] = 0x1, + [MLX4_FS_PROMISC_FUNCTION_PORT] = 0x2, + [MLX4_FS_PROMISC_ALL_MULTI] = 0x3, + }; + + u32 dw = 0; + + dw = ctrl->queue_mode == MLX4_NET_TRANS_Q_LIFO ? 1 : 0; + dw |= ctrl->exclusive ? (1 << 2) : 0; + dw |= ctrl->allow_loopback ? (1 << 3) : 0; + dw |= __promisc_mode[ctrl->promisc_mode] << 8; + dw |= ctrl->priority << 16; + + hw->ctrl = cpu_to_be32(dw); + hw->vf_vep_port = cpu_to_be32(ctrl->port); + hw->qpn = cpu_to_be32(ctrl->qpn); +} + +struct mlx4_net_trans_rule_hw_ib { + u8 size; + u8 rsvd1; + __be16 id; + u32 rsvd2; + __be32 qpn; + __be32 qpn_mask; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +} __packed; + +struct mlx4_net_trans_rule_hw_eth { + u8 size; + u8 rsvd; + __be16 id; + u8 rsvd1[6]; + u8 dst_mac[6]; + u16 rsvd2; + u8 dst_mac_msk[6]; + u16 rsvd3; + u8 src_mac[6]; + u16 rsvd4; + u8 src_mac_msk[6]; + u8 rsvd5; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +} __packed; + +struct mlx4_net_trans_rule_hw_tcp_udp { + u8 size; + u8 rsvd; + __be16 id; + __be16 rsvd1[3]; + __be16 dst_port; + __be16 rsvd2; + __be16 dst_port_msk; + __be16 rsvd3; + __be16 src_port; + __be16 rsvd4; + __be16 src_port_msk; +} __packed; + +struct mlx4_net_trans_rule_hw_ipv4 { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +} __packed; + +struct _rule_hw { + union { + struct { + u8 size; + u8 rsvd; + __be16 id; + }; + struct mlx4_net_trans_rule_hw_eth eth; + struct mlx4_net_trans_rule_hw_ib ib; + struct mlx4_net_trans_rule_hw_ipv4 ipv4; + struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + }; +}; + +static int parse_trans_rule(struct mlx4_dev *dev, struct mlx4_spec_list *spec, + struct _rule_hw *rule_hw) +{ + static const u16 __sw_id_hw[] = { + [MLX4_NET_TRANS_RULE_ID_ETH] = 0xE001, + [MLX4_NET_TRANS_RULE_ID_IB] = 0xE005, + [MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003, + [MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002, + [MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004, + [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006 + }; + + static const size_t __rule_hw_sz[] = { + [MLX4_NET_TRANS_RULE_ID_ETH] = + sizeof(struct mlx4_net_trans_rule_hw_eth), + [MLX4_NET_TRANS_RULE_ID_IB] = + sizeof(struct mlx4_net_trans_rule_hw_ib), + [MLX4_NET_TRANS_RULE_ID_IPV6] = 0, + [MLX4_NET_TRANS_RULE_ID_IPV4] = + sizeof(struct mlx4_net_trans_rule_hw_ipv4), + [MLX4_NET_TRANS_RULE_ID_TCP] = + sizeof(struct mlx4_net_trans_rule_hw_tcp_udp), + [MLX4_NET_TRANS_RULE_ID_UDP] = + sizeof(struct mlx4_net_trans_rule_hw_tcp_udp) + }; + if (spec->id > MLX4_NET_TRANS_RULE_NUM) { + mlx4_err(dev, "Invalid network rule id. id = %d\n", spec->id); + return -EINVAL; + } + memset(rule_hw, 0, __rule_hw_sz[spec->id]); + rule_hw->id = cpu_to_be16(__sw_id_hw[spec->id]); + rule_hw->size = __rule_hw_sz[spec->id] >> 2; + + switch (spec->id) { + case MLX4_NET_TRANS_RULE_ID_ETH: + memcpy(rule_hw->eth.dst_mac, spec->eth.dst_mac, ETH_ALEN); + memcpy(rule_hw->eth.dst_mac_msk, spec->eth.dst_mac_msk, + ETH_ALEN); + memcpy(rule_hw->eth.src_mac, spec->eth.src_mac, ETH_ALEN); + memcpy(rule_hw->eth.src_mac_msk, spec->eth.src_mac_msk, + ETH_ALEN); + if (spec->eth.ether_type_enable) { + rule_hw->eth.ether_type_enable = 1; + rule_hw->eth.ether_type = spec->eth.ether_type; + } + rule_hw->eth.vlan_id = spec->eth.vlan_id; + rule_hw->eth.vlan_id_msk = spec->eth.vlan_id_msk; + break; + + case MLX4_NET_TRANS_RULE_ID_IB: + rule_hw->ib.qpn = spec->ib.r_qpn; + rule_hw->ib.qpn_mask = spec->ib.qpn_msk; + memcpy(&rule_hw->ib.dst_gid, &spec->ib.dst_gid, 16); + memcpy(&rule_hw->ib.dst_gid_msk, &spec->ib.dst_gid_msk, 16); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV6: + return -EOPNOTSUPP; + + case MLX4_NET_TRANS_RULE_ID_IPV4: + rule_hw->ipv4.src_ip = spec->ipv4.src_ip; + rule_hw->ipv4.src_ip_msk = spec->ipv4.src_ip_msk; + rule_hw->ipv4.dst_ip = spec->ipv4.dst_ip; + rule_hw->ipv4.dst_ip_msk = spec->ipv4.dst_ip_msk; + break; + + case MLX4_NET_TRANS_RULE_ID_TCP: + case MLX4_NET_TRANS_RULE_ID_UDP: + rule_hw->tcp_udp.dst_port = spec->tcp_udp.dst_port; + rule_hw->tcp_udp.dst_port_msk = spec->tcp_udp.dst_port_msk; + rule_hw->tcp_udp.src_port = spec->tcp_udp.src_port; + rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk; + break; + + default: + return -EINVAL; + } + + return __rule_hw_sz[spec->id]; +} + +static void mlx4_err_rule(struct mlx4_dev *dev, char *str, + struct mlx4_net_trans_rule *rule) +{ +#define BUF_SIZE 256 + struct mlx4_spec_list *cur; + char buf[BUF_SIZE]; + int len = 0; + + mlx4_err(dev, "%s", str); + len += snprintf(buf + len, BUF_SIZE - len, + "port = %d prio = 0x%x qp = 0x%x ", + rule->port, rule->priority, rule->qpn); + + list_for_each_entry(cur, &rule->list, list) { + switch (cur->id) { + case MLX4_NET_TRANS_RULE_ID_ETH: + len += snprintf(buf + len, BUF_SIZE - len, + "dmac = %pM ", &cur->eth.dst_mac); + if (cur->eth.ether_type) + len += snprintf(buf + len, BUF_SIZE - len, + "ethertype = 0x%x ", + be16_to_cpu(cur->eth.ether_type)); + if (cur->eth.vlan_id) + len += snprintf(buf + len, BUF_SIZE - len, + "vlan-id = %d ", + be16_to_cpu(cur->eth.vlan_id)); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV4: + if (cur->ipv4.src_ip) + len += snprintf(buf + len, BUF_SIZE - len, + "src-ip = %pI4 ", + &cur->ipv4.src_ip); + if (cur->ipv4.dst_ip) + len += snprintf(buf + len, BUF_SIZE - len, + "dst-ip = %pI4 ", + &cur->ipv4.dst_ip); + break; + + case MLX4_NET_TRANS_RULE_ID_TCP: + case MLX4_NET_TRANS_RULE_ID_UDP: + if (cur->tcp_udp.src_port) + len += snprintf(buf + len, BUF_SIZE - len, + "src-port = %d ", + be16_to_cpu(cur->tcp_udp.src_port)); + if (cur->tcp_udp.dst_port) + len += snprintf(buf + len, BUF_SIZE - len, + "dst-port = %d ", + be16_to_cpu(cur->tcp_udp.dst_port)); + break; + + case MLX4_NET_TRANS_RULE_ID_IB: + len += snprintf(buf + len, BUF_SIZE - len, + "dst-gid = %pI6\n", cur->ib.dst_gid); + len += snprintf(buf + len, BUF_SIZE - len, + "dst-gid-mask = %pI6\n", + cur->ib.dst_gid_msk); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV6: + break; + + default: + break; + } + } + len += snprintf(buf + len, BUF_SIZE - len, "\n"); + mlx4_err(dev, "%s", buf); + + if (len >= BUF_SIZE) + mlx4_err(dev, "Network rule error message was truncated, print buffer is too small.\n"); +} + +int mlx4_flow_attach(struct mlx4_dev *dev, + struct mlx4_net_trans_rule *rule, u64 *reg_id) +{ + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_spec_list *cur; + u32 size = 0; + int ret; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + memset(mailbox->buf, 0, sizeof(struct mlx4_net_trans_rule_hw_ctrl)); + trans_rule_ctrl_to_hw(rule, mailbox->buf); + + size += sizeof(struct mlx4_net_trans_rule_hw_ctrl); + + list_for_each_entry(cur, &rule->list, list) { + ret = parse_trans_rule(dev, cur, mailbox->buf + size); + if (ret < 0) { + mlx4_free_cmd_mailbox(dev, mailbox); + return -EINVAL; + } + size += ret; + } + + ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id); + if (ret == -ENOMEM) + mlx4_err_rule(dev, + "mcg table is full. Fail to register network rule.\n", + rule); + else if (ret) + mlx4_err_rule(dev, "Fail to register network rule.\n", rule); + + mlx4_free_cmd_mailbox(dev, mailbox); + + return ret; +} +EXPORT_SYMBOL_GPL(mlx4_flow_attach); + +int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) +{ + int err; + + err = mlx4_QP_FLOW_STEERING_DETACH(dev, reg_id); + if (err) + mlx4_err(dev, "Fail to detach network rule. registration id = 0x%llx\n", + reg_id); + return err; +} +EXPORT_SYMBOL_GPL(mlx4_flow_detach); + int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot, enum mlx4_steer_type steer) @@ -895,7 +1206,8 @@ static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp, } int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - int block_mcast_loopback, enum mlx4_protocol prot) + u8 port, int block_mcast_loopback, + enum mlx4_protocol prot, u64 *reg_id) { switch (dev->caps.steering_mode) { @@ -914,6 +1226,42 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], block_mcast_loopback, prot, MLX4_MC_STEER); + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + struct mlx4_spec_list spec = { {NULL} }; + __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .promisc_mode = MLX4_FS_PROMISC_NONE, + .priority = MLX4_DOMAIN_NIC, + }; + + rule.allow_loopback = ~block_mcast_loopback; + rule.port = port; + rule.qpn = qp->qpn; + INIT_LIST_HEAD(&rule.list); + + switch (prot) { + case MLX4_PROT_ETH: + spec.id = MLX4_NET_TRANS_RULE_ID_ETH; + memcpy(spec.eth.dst_mac, &gid[10], ETH_ALEN); + memcpy(spec.eth.dst_mac_msk, &mac_mask, ETH_ALEN); + break; + + case MLX4_PROT_IB_IPV6: + spec.id = MLX4_NET_TRANS_RULE_ID_IB; + memcpy(spec.ib.dst_gid, gid, 16); + memset(&spec.ib.dst_gid_msk, 0xff, 16); + break; + default: + return -EINVAL; + } + list_add_tail(&spec.list, &rule.list); + + return mlx4_flow_attach(dev, &rule, reg_id); + } + default: return -EINVAL; } @@ -921,7 +1269,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], EXPORT_SYMBOL_GPL(mlx4_multicast_attach); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - enum mlx4_protocol prot) + enum mlx4_protocol prot, u64 reg_id) { switch (dev->caps.steering_mode) { case MLX4_STEERING_MODE_A0: @@ -938,6 +1286,9 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], return mlx4_qp_detach_common(dev, qp, gid, prot, MLX4_MC_STEER); + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return mlx4_flow_detach(dev, reg_id); + default: return -EINVAL; } @@ -1042,6 +1393,10 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int err; + /* No need for mcg_table when fw managed the mcg table*/ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + return 0; err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms, dev->caps.num_amgms - 1, 0, 0); if (err) @@ -1054,5 +1409,7 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) void mlx4_cleanup_mcg_table(struct mlx4_dev *dev) { - mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap); + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index c07e882e8369..0084967be19e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -54,6 +54,17 @@ #define DRV_VERSION "1.1" #define DRV_RELDATE "Dec, 2011" +#define MLX4_FS_UDP_UC_EN (1 << 1) +#define MLX4_FS_TCP_UC_EN (1 << 2) +#define MLX4_FS_NUM_OF_L2_ADDR 8 +#define MLX4_FS_MGM_LOG_ENTRY_SIZE 7 +#define MLX4_FS_NUM_MCG (1 << 17) + +enum { + MLX4_FS_L2_HASH = 0, + MLX4_FS_L2_L3_L4_HASH, +}; + #define MLX4_NUM_UP 8 #define MLX4_NUM_TC 8 #define MLX4_RATELIMIT_UNITS 3 /* 100 Mbps */ @@ -704,6 +715,7 @@ struct mlx4_set_port_rqp_calc_context { struct mlx4_mac_entry { u64 mac; + u64 reg_id; }; struct mlx4_port_info { @@ -777,6 +789,7 @@ struct mlx4_priv { struct mutex bf_mutex; struct io_mapping *bf_mapping; int reserved_mtts; + int fs_hash_mode; }; static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 1bb00cd22d42..2d6dabe7f55d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -414,6 +414,7 @@ struct mlx4_en_mc_list { struct list_head list; enum mlx4_en_mclist_act action; u8 addr[ETH_ALEN]; + u64 reg_id; }; struct mlx4_en_frag_info { @@ -503,6 +504,7 @@ struct mlx4_en_priv { u64 stats_bitmap; struct list_head mc_list; struct list_head curr_list; + u64 broadcast_id; struct mlx4_en_stat_out_mbox hw_stats; int vids[128]; bool wol; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 58de7237f57a..a51d1b9bf1d1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -75,21 +75,54 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table) table->total = 0; } -static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) +static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, + u64 mac, int *qpn, u64 *reg_id) { - struct mlx4_qp qp; - u8 gid[16] = {0}; __be64 be_mac; int err; - qp.qpn = *qpn; - - mac &= 0xffffffffffffULL; + mac &= MLX4_MAC_MASK; be_mac = cpu_to_be64(mac << 16); - memcpy(&gid[10], &be_mac, ETH_ALEN); - gid[5] = port; - err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH); + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: { + struct mlx4_qp qp; + u8 gid[16] = {0}; + + qp.qpn = *qpn; + memcpy(&gid[10], &be_mac, ETH_ALEN); + gid[5] = port; + + err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH); + break; + } + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + struct mlx4_spec_list spec_eth = { {NULL} }; + __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + .promisc_mode = MLX4_FS_PROMISC_NONE, + .priority = MLX4_DOMAIN_NIC, + }; + + rule.port = port; + rule.qpn = *qpn; + INIT_LIST_HEAD(&rule.list); + + spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH; + memcpy(spec_eth.eth.dst_mac, &be_mac, ETH_ALEN); + memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN); + list_add_tail(&spec_eth.list, &rule.list); + + err = mlx4_flow_attach(dev, &rule, reg_id); + break; + } + default: + return -EINVAL; + } if (err) mlx4_warn(dev, "Failed Attaching Unicast\n"); @@ -97,19 +130,30 @@ static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) } static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port, - u64 mac, int qpn) + u64 mac, int qpn, u64 reg_id) { - struct mlx4_qp qp; - u8 gid[16] = {0}; - __be64 be_mac; + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: { + struct mlx4_qp qp; + u8 gid[16] = {0}; + __be64 be_mac; - qp.qpn = qpn; - mac &= 0xffffffffffffULL; - be_mac = cpu_to_be64(mac << 16); - memcpy(&gid[10], &be_mac, ETH_ALEN); - gid[5] = port; + qp.qpn = qpn; + mac &= MLX4_MAC_MASK; + be_mac = cpu_to_be64(mac << 16); + memcpy(&gid[10], &be_mac, ETH_ALEN); + gid[5] = port; - mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH); + mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH); + break; + } + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + mlx4_flow_detach(dev, reg_id); + break; + } + default: + mlx4_err(dev, "Invalid steering mode.\n"); + } } static int validate_index(struct mlx4_dev *dev, @@ -144,6 +188,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) struct mlx4_mac_entry *entry; int index = 0; int err = 0; + u64 reg_id; mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n", (unsigned long long) mac); @@ -167,7 +212,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) goto qp_err; } - err = mlx4_uc_steer_add(dev, port, mac, qpn); + err = mlx4_uc_steer_add(dev, port, mac, qpn, ®_id); if (err) goto steer_err; @@ -177,6 +222,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) goto alloc_err; } entry->mac = mac; + entry->reg_id = reg_id; err = radix_tree_insert(&info->mac_tree, *qpn, entry); if (err) goto insert_err; @@ -186,7 +232,7 @@ insert_err: kfree(entry); alloc_err: - mlx4_uc_steer_release(dev, port, mac, *qpn); + mlx4_uc_steer_release(dev, port, mac, *qpn, reg_id); steer_err: mlx4_qp_release_range(dev, *qpn, 1); @@ -212,7 +258,8 @@ void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn) mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx," " qpn %d\n", port, (unsigned long long) mac, qpn); - mlx4_uc_steer_release(dev, port, entry->mac, qpn); + mlx4_uc_steer_release(dev, port, entry->mac, + qpn, entry->reg_id); mlx4_qp_release_range(dev, qpn, 1); radix_tree_delete(&info->mac_tree, qpn); kfree(entry); @@ -363,11 +410,14 @@ int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) entry = radix_tree_lookup(&info->mac_tree, qpn); if (!entry) return -EINVAL; - mlx4_uc_steer_release(dev, port, entry->mac, qpn); + mlx4_uc_steer_release(dev, port, entry->mac, + qpn, entry->reg_id); mlx4_unregister_mac(dev, port, entry->mac); entry->mac = new_mac; + entry->reg_id = 0; mlx4_register_mac(dev, port, new_mac); - err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn); + err = mlx4_uc_steer_add(dev, port, entry->mac, + &qpn, &entry->reg_id); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c index b83bc928d52a..9ee4725363d5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/profile.c +++ b/drivers/net/ethernet/mellanox/mlx4/profile.c @@ -237,13 +237,19 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, init_hca->mtt_base = profile[i].start; break; case MLX4_RES_MCG: - dev->caps.num_mgms = profile[i].num >> 1; - dev->caps.num_amgms = profile[i].num >> 1; init_hca->mc_base = profile[i].start; init_hca->log_mc_entry_sz = ilog2(mlx4_get_mgm_entry_size(dev)); init_hca->log_mc_table_sz = profile[i].log_num; - init_hca->log_mc_hash_sz = profile[i].log_num - 1; + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + dev->caps.num_mgms = profile[i].num; + } else { + init_hca->log_mc_hash_sz = + profile[i].log_num - 1; + dev->caps.num_mgms = profile[i].num >> 1; + dev->caps.num_amgms = profile[i].num >> 1; + } break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index a8ca960f4620..5a6f3555d806 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2744,6 +2744,9 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + return -EOPNOTSUPP; return mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, @@ -2757,6 +2760,9 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + return -EOPNOTSUPP; return mlx4_cmd(dev, vhcr->in_param, 0, 0, MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7f5c9ee42f96..e45fc20bd01f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -70,14 +70,17 @@ enum { MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1) }; -/* Driver supports 2 diffrent device methods to manage traffic steering: +/* Driver supports 3 diffrent device methods to manage traffic steering: + * -device managed - High level API for ib and eth flow steering. FW is + * managing flow steering tables. * - B0 steering mode - Common low level API for ib and (if supported) eth. * - A0 steering mode - Limited low level API for eth. In case of IB, * B0 mode is in use. */ enum { MLX4_STEERING_MODE_A0, - MLX4_STEERING_MODE_B0 + MLX4_STEERING_MODE_B0, + MLX4_STEERING_MODE_DEVICE_MANAGED }; static inline const char *mlx4_steering_mode_str(int steering_mode) @@ -88,6 +91,10 @@ static inline const char *mlx4_steering_mode_str(int steering_mode) case MLX4_STEERING_MODE_B0: return "B0 steering"; + + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return "Device managed flow steering"; + default: return "Unrecognize steering mode"; } @@ -125,7 +132,8 @@ enum { enum { MLX4_DEV_CAP_FLAG2_RSS = 1LL << 0, MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1, - MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2 + MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, + MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3 }; #define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90) @@ -319,6 +327,7 @@ struct mlx4_caps { int reserved_mcgs; int num_qp_per_mgm; int steering_mode; + int fs_log_max_ucast_qp_range_size; int num_pds; int reserved_pds; int max_xrcds; @@ -647,9 +656,94 @@ int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], enum mlx4_protocol prot); int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - int block_mcast_loopback, enum mlx4_protocol protocol); + u8 port, int block_mcast_loopback, + enum mlx4_protocol protocol, u64 *reg_id); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - enum mlx4_protocol protocol); + enum mlx4_protocol protocol, u64 reg_id); + +enum { + MLX4_DOMAIN_UVERBS = 0x1000, + MLX4_DOMAIN_ETHTOOL = 0x2000, + MLX4_DOMAIN_RFS = 0x3000, + MLX4_DOMAIN_NIC = 0x5000, +}; + +enum mlx4_net_trans_rule_id { + MLX4_NET_TRANS_RULE_ID_ETH = 0, + MLX4_NET_TRANS_RULE_ID_IB, + MLX4_NET_TRANS_RULE_ID_IPV6, + MLX4_NET_TRANS_RULE_ID_IPV4, + MLX4_NET_TRANS_RULE_ID_TCP, + MLX4_NET_TRANS_RULE_ID_UDP, + MLX4_NET_TRANS_RULE_NUM, /* should be last */ +}; + +enum mlx4_net_trans_promisc_mode { + MLX4_FS_PROMISC_NONE = 0, + MLX4_FS_PROMISC_UPLINK, + MLX4_FS_PROMISC_FUNCTION_PORT, + MLX4_FS_PROMISC_ALL_MULTI, +}; + +struct mlx4_spec_eth { + u8 dst_mac[6]; + u8 dst_mac_msk[6]; + u8 src_mac[6]; + u8 src_mac_msk[6]; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +}; + +struct mlx4_spec_tcp_udp { + __be16 dst_port; + __be16 dst_port_msk; + __be16 src_port; + __be16 src_port_msk; +}; + +struct mlx4_spec_ipv4 { + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +}; + +struct mlx4_spec_ib { + __be32 r_qpn; + __be32 qpn_msk; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +}; + +struct mlx4_spec_list { + struct list_head list; + enum mlx4_net_trans_rule_id id; + union { + struct mlx4_spec_eth eth; + struct mlx4_spec_ib ib; + struct mlx4_spec_ipv4 ipv4; + struct mlx4_spec_tcp_udp tcp_udp; + }; +}; + +enum mlx4_net_trans_hw_rule_queue { + MLX4_NET_TRANS_Q_FIFO, + MLX4_NET_TRANS_Q_LIFO, +}; + +struct mlx4_net_trans_rule { + struct list_head list; + enum mlx4_net_trans_hw_rule_queue queue_mode; + bool exclusive; + bool allow_loopback; + enum mlx4_net_trans_promisc_mode promisc_mode; + u8 port; + u16 priority; + u32 qpn; +}; + int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); @@ -692,4 +786,8 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); +int mlx4_flow_attach(struct mlx4_dev *dev, + struct mlx4_net_trans_rule *rule, u64 *reg_id); +int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 592e49dda8122ab621cdc59cc429bdb968ee6364 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 5 Jul 2012 04:03:48 +0000 Subject: net/mlx4: Implement promiscuous mode with device managed flow-steering The device managed flow steering API has three promiscuous modes: 1. Uplink - captures all the packets that arrive to the port. 2. Allmulti - captures all multicast packets arriving to the port. 3. Function port - for future use, this mode is not implemented yet. Use these modes with the flow_attach and flow_detach firmware commands according to the promiscuous state of the netdevice. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 41 ++++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/mcg.c | 60 ++++++++++++++++++++++++++ include/linux/mlx4/device.h | 7 +++ 3 files changed, 108 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index eb5ed8e39873..b7945a80ad15 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -301,6 +301,16 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) /* Enable promiscouos mode */ switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + err = mlx4_flow_steer_promisc_add(mdev->dev, + priv->port, + priv->base_qpn, + MLX4_FS_PROMISC_UPLINK); + if (err) + en_err(priv, "Failed enabling promiscuous mode\n"); + priv->flags |= MLX4_EN_FLAG_MC_PROMISC; + break; + case MLX4_STEERING_MODE_B0: err = mlx4_unicast_promisc_add(mdev->dev, priv->base_qpn, @@ -357,6 +367,15 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) /* Disable promiscouos mode */ switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + err = mlx4_flow_steer_promisc_remove(mdev->dev, + priv->port, + MLX4_FS_PROMISC_UPLINK); + if (err) + en_err(priv, "Failed disabling promiscuous mode\n"); + priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC; + break; + case MLX4_STEERING_MODE_B0: err = mlx4_unicast_promisc_remove(mdev->dev, priv->base_qpn, @@ -399,6 +418,13 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) /* Add the default qp number as multicast promisc */ if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) { switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + err = mlx4_flow_steer_promisc_add(mdev->dev, + priv->port, + priv->base_qpn, + MLX4_FS_PROMISC_ALL_MULTI); + break; + case MLX4_STEERING_MODE_B0: err = mlx4_multicast_promisc_add(mdev->dev, priv->base_qpn, @@ -416,6 +442,12 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) /* Disable Multicast promisc */ if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) { switch (mdev->dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + err = mlx4_flow_steer_promisc_remove(mdev->dev, + priv->port, + MLX4_FS_PROMISC_ALL_MULTI); + break; + case MLX4_STEERING_MODE_B0: err = mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn, @@ -839,6 +871,15 @@ int mlx4_en_start_port(struct net_device *dev) /* Must redo promiscuous mode setup. */ priv->flags &= ~(MLX4_EN_FLAG_PROMISC | MLX4_EN_FLAG_MC_PROMISC); + if (mdev->dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + mlx4_flow_steer_promisc_remove(mdev->dev, + priv->port, + MLX4_FS_PROMISC_UPLINK); + mlx4_flow_steer_promisc_remove(mdev->dev, + priv->port, + MLX4_FS_PROMISC_ALL_MULTI); + } /* Schedule multicast task to populate multicast list */ queue_work(mdev->workqueue, &priv->mcast_task); diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 768a2a4530e8..bc62f536ffae 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1295,6 +1295,66 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], } EXPORT_SYMBOL_GPL(mlx4_multicast_detach); +int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, + u32 qpn, enum mlx4_net_trans_promisc_mode mode) +{ + struct mlx4_net_trans_rule rule; + u64 *regid_p; + + switch (mode) { + case MLX4_FS_PROMISC_UPLINK: + case MLX4_FS_PROMISC_FUNCTION_PORT: + regid_p = &dev->regid_promisc_array[port]; + break; + case MLX4_FS_PROMISC_ALL_MULTI: + regid_p = &dev->regid_allmulti_array[port]; + break; + default: + return -1; + } + + if (*regid_p != 0) + return -1; + + rule.promisc_mode = mode; + rule.port = port; + rule.qpn = qpn; + INIT_LIST_HEAD(&rule.list); + mlx4_err(dev, "going promisc on %x\n", port); + + return mlx4_flow_attach(dev, &rule, regid_p); +} +EXPORT_SYMBOL_GPL(mlx4_flow_steer_promisc_add); + +int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, + enum mlx4_net_trans_promisc_mode mode) +{ + int ret; + u64 *regid_p; + + switch (mode) { + case MLX4_FS_PROMISC_UPLINK: + case MLX4_FS_PROMISC_FUNCTION_PORT: + regid_p = &dev->regid_promisc_array[port]; + break; + case MLX4_FS_PROMISC_ALL_MULTI: + regid_p = &dev->regid_allmulti_array[port]; + break; + default: + return -1; + } + + if (*regid_p == 0) + return -1; + + ret = mlx4_flow_detach(dev, *regid_p); + if (ret == 0) + *regid_p = 0; + + return ret; +} +EXPORT_SYMBOL_GPL(mlx4_flow_steer_promisc_remove); + int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e45fc20bd01f..6f0d133cc7ad 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -542,6 +542,8 @@ struct mlx4_dev { u8 rev_id; char board_id[MLX4_BOARD_ID_LEN]; int num_vfs; + u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; + u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; }; struct mlx4_init_port_param { @@ -681,6 +683,7 @@ enum mlx4_net_trans_rule_id { enum mlx4_net_trans_promisc_mode { MLX4_FS_PROMISC_NONE = 0, MLX4_FS_PROMISC_UPLINK, + /* For future use. Not implemented yet */ MLX4_FS_PROMISC_FUNCTION_PORT, MLX4_FS_PROMISC_ALL_MULTI, }; @@ -744,6 +747,10 @@ struct mlx4_net_trans_rule { u32 qpn; }; +int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, + enum mlx4_net_trans_promisc_mode mode); +int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, + enum mlx4_net_trans_promisc_mode mode); int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); -- cgit v1.2.3 From d5bf9071e71a4db85a0eea6236ef94a29fc3eec9 Mon Sep 17 00:00:00 2001 From: Christian Hohnstaedt Date: Wed, 4 Jul 2012 05:44:34 +0000 Subject: phylib: Support registering a bunch of drivers If registering of one of them fails, all already registered drivers of this module will be unregistered. Use the new register/unregister functions in all drivers registering more than one driver. amd.c, realtek.c: Simplify: directly return registration result. Tested with broadcom.c All others compile-tested. Signed-off-by: Christian Hohnstaedt Signed-off-by: David S. Miller --- drivers/net/phy/amd.c | 8 +-- drivers/net/phy/bcm63xx.c | 31 ++++------- drivers/net/phy/bcm87xx.c | 24 +++------ drivers/net/phy/broadcom.c | 119 +++++++------------------------------------ drivers/net/phy/cicada.c | 35 ++++--------- drivers/net/phy/davicom.c | 41 ++++----------- drivers/net/phy/icplus.c | 31 ++++------- drivers/net/phy/lxt.c | 47 +++++------------ drivers/net/phy/marvell.c | 22 ++------ drivers/net/phy/micrel.c | 62 ++++------------------ drivers/net/phy/phy_device.c | 25 +++++++++ drivers/net/phy/realtek.c | 6 +-- drivers/net/phy/smsc.c | 64 ++++------------------- drivers/net/phy/ste10Xp.c | 21 +++----- drivers/net/phy/vitesse.c | 52 ++++++++----------- include/linux/phy.h | 2 + 16 files changed, 159 insertions(+), 431 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/amd.c b/drivers/net/phy/amd.c index cfabd5fe5372..a3fb5ceb6487 100644 --- a/drivers/net/phy/amd.c +++ b/drivers/net/phy/amd.c @@ -77,13 +77,7 @@ static struct phy_driver am79c_driver = { static int __init am79c_init(void) { - int ret; - - ret = phy_driver_register(&am79c_driver); - if (ret) - return ret; - - return 0; + return phy_driver_register(&am79c_driver); } static void __exit am79c_exit(void) diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index cd802eb25fd2..84c7a39b1c65 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -71,7 +71,8 @@ static int bcm63xx_config_intr(struct phy_device *phydev) return err; } -static struct phy_driver bcm63xx_1_driver = { +static struct phy_driver bcm63xx_driver[] = { +{ .phy_id = 0x00406000, .phy_id_mask = 0xfffffc00, .name = "Broadcom BCM63XX (1)", @@ -84,10 +85,8 @@ static struct phy_driver bcm63xx_1_driver = { .ack_interrupt = bcm63xx_ack_interrupt, .config_intr = bcm63xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -/* same phy as above, with just a different OUI */ -static struct phy_driver bcm63xx_2_driver = { +}, { + /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, .phy_id_mask = 0xfffffc00, .name = "Broadcom BCM63XX (2)", @@ -99,30 +98,18 @@ static struct phy_driver bcm63xx_2_driver = { .ack_interrupt = bcm63xx_ack_interrupt, .config_intr = bcm63xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; +} }; static int __init bcm63xx_phy_init(void) { - int ret; - - ret = phy_driver_register(&bcm63xx_1_driver); - if (ret) - goto out_63xx_1; - ret = phy_driver_register(&bcm63xx_2_driver); - if (ret) - goto out_63xx_2; - return ret; - -out_63xx_2: - phy_driver_unregister(&bcm63xx_1_driver); -out_63xx_1: - return ret; + return phy_drivers_register(bcm63xx_driver, + ARRAY_SIZE(bcm63xx_driver)); } static void __exit bcm63xx_phy_exit(void) { - phy_driver_unregister(&bcm63xx_1_driver); - phy_driver_unregister(&bcm63xx_2_driver); + phy_drivers_unregister(bcm63xx_driver, + ARRAY_SIZE(bcm63xx_driver)); } module_init(bcm63xx_phy_init); diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c index 9a90dcf31156..2167ce51818e 100644 --- a/drivers/net/phy/bcm87xx.c +++ b/drivers/net/phy/bcm87xx.c @@ -187,7 +187,8 @@ static int bcm8727_match_phy_device(struct phy_device *phydev) return phydev->c45_ids.device_ids[4] == PHY_ID_BCM8727; } -static struct phy_driver bcm8706_driver = { +static struct phy_driver bcm87xx_driver[] = { +{ .phy_id = PHY_ID_BCM8706, .phy_id_mask = 0xffffffff, .name = "Broadcom BCM8706", @@ -200,9 +201,7 @@ static struct phy_driver bcm8706_driver = { .did_interrupt = bcm87xx_did_interrupt, .match_phy_device = bcm8706_match_phy_device, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm8727_driver = { +}, { .phy_id = PHY_ID_BCM8727, .phy_id_mask = 0xffffffff, .name = "Broadcom BCM8727", @@ -215,25 +214,18 @@ static struct phy_driver bcm8727_driver = { .did_interrupt = bcm87xx_did_interrupt, .match_phy_device = bcm8727_match_phy_device, .driver = { .owner = THIS_MODULE }, -}; +} }; static int __init bcm87xx_init(void) { - int ret; - - ret = phy_driver_register(&bcm8706_driver); - if (ret) - goto err; - - ret = phy_driver_register(&bcm8727_driver); -err: - return ret; + return phy_drivers_register(bcm87xx_driver, + ARRAY_SIZE(bcm87xx_driver)); } module_init(bcm87xx_init); static void __exit bcm87xx_exit(void) { - phy_driver_unregister(&bcm8706_driver); - phy_driver_unregister(&bcm8727_driver); + phy_drivers_unregister(bcm87xx_driver, + ARRAY_SIZE(bcm87xx_driver)); } module_exit(bcm87xx_exit); diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 60338ff63092..f8c90ea75108 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -682,7 +682,8 @@ static int brcm_fet_config_intr(struct phy_device *phydev) return err; } -static struct phy_driver bcm5411_driver = { +static struct phy_driver broadcom_drivers[] = { +{ .phy_id = PHY_ID_BCM5411, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5411", @@ -695,9 +696,7 @@ static struct phy_driver bcm5411_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5421_driver = { +}, { .phy_id = PHY_ID_BCM5421, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5421", @@ -710,9 +709,7 @@ static struct phy_driver bcm5421_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5461_driver = { +}, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5461", @@ -725,9 +722,7 @@ static struct phy_driver bcm5461_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5464_driver = { +}, { .phy_id = PHY_ID_BCM5464, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5464", @@ -740,9 +735,7 @@ static struct phy_driver bcm5464_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5481_driver = { +}, { .phy_id = PHY_ID_BCM5481, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5481", @@ -755,9 +748,7 @@ static struct phy_driver bcm5481_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5482_driver = { +}, { .phy_id = PHY_ID_BCM5482, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5482", @@ -770,9 +761,7 @@ static struct phy_driver bcm5482_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm50610_driver = { +}, { .phy_id = PHY_ID_BCM50610, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM50610", @@ -785,9 +774,7 @@ static struct phy_driver bcm50610_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm50610m_driver = { +}, { .phy_id = PHY_ID_BCM50610M, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM50610M", @@ -800,9 +787,7 @@ static struct phy_driver bcm50610m_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm57780_driver = { +}, { .phy_id = PHY_ID_BCM57780, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM57780", @@ -815,9 +800,7 @@ static struct phy_driver bcm57780_driver = { .ack_interrupt = bcm54xx_ack_interrupt, .config_intr = bcm54xx_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcmac131_driver = { +}, { .phy_id = PHY_ID_BCMAC131, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCMAC131", @@ -830,9 +813,7 @@ static struct phy_driver bcmac131_driver = { .ack_interrupt = brcm_fet_ack_interrupt, .config_intr = brcm_fet_config_intr, .driver = { .owner = THIS_MODULE }, -}; - -static struct phy_driver bcm5241_driver = { +}, { .phy_id = PHY_ID_BCM5241, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5241", @@ -845,84 +826,18 @@ static struct phy_driver bcm5241_driver = { .ack_interrupt = brcm_fet_ack_interrupt, .config_intr = brcm_fet_config_intr, .driver = { .owner = THIS_MODULE }, -}; +} }; static int __init broadcom_init(void) { - int ret; - - ret = phy_driver_register(&bcm5411_driver); - if (ret) - goto out_5411; - ret = phy_driver_register(&bcm5421_driver); - if (ret) - goto out_5421; - ret = phy_driver_register(&bcm5461_driver); - if (ret) - goto out_5461; - ret = phy_driver_register(&bcm5464_driver); - if (ret) - goto out_5464; - ret = phy_driver_register(&bcm5481_driver); - if (ret) - goto out_5481; - ret = phy_driver_register(&bcm5482_driver); - if (ret) - goto out_5482; - ret = phy_driver_register(&bcm50610_driver); - if (ret) - goto out_50610; - ret = phy_driver_register(&bcm50610m_driver); - if (ret) - goto out_50610m; - ret = phy_driver_register(&bcm57780_driver); - if (ret) - goto out_57780; - ret = phy_driver_register(&bcmac131_driver); - if (ret) - goto out_ac131; - ret = phy_driver_register(&bcm5241_driver); - if (ret) - goto out_5241; - return ret; - -out_5241: - phy_driver_unregister(&bcmac131_driver); -out_ac131: - phy_driver_unregister(&bcm57780_driver); -out_57780: - phy_driver_unregister(&bcm50610m_driver); -out_50610m: - phy_driver_unregister(&bcm50610_driver); -out_50610: - phy_driver_unregister(&bcm5482_driver); -out_5482: - phy_driver_unregister(&bcm5481_driver); -out_5481: - phy_driver_unregister(&bcm5464_driver); -out_5464: - phy_driver_unregister(&bcm5461_driver); -out_5461: - phy_driver_unregister(&bcm5421_driver); -out_5421: - phy_driver_unregister(&bcm5411_driver); -out_5411: - return ret; + return phy_drivers_register(broadcom_drivers, + ARRAY_SIZE(broadcom_drivers)); } static void __exit broadcom_exit(void) { - phy_driver_unregister(&bcm5241_driver); - phy_driver_unregister(&bcmac131_driver); - phy_driver_unregister(&bcm57780_driver); - phy_driver_unregister(&bcm50610m_driver); - phy_driver_unregister(&bcm50610_driver); - phy_driver_unregister(&bcm5482_driver); - phy_driver_unregister(&bcm5481_driver); - phy_driver_unregister(&bcm5464_driver); - phy_driver_unregister(&bcm5461_driver); - phy_driver_unregister(&bcm5421_driver); - phy_driver_unregister(&bcm5411_driver); + phy_drivers_unregister(broadcom_drivers, + ARRAY_SIZE(broadcom_drivers)); } module_init(broadcom_init); diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c index d28173161c21..db472ffb6e89 100644 --- a/drivers/net/phy/cicada.c +++ b/drivers/net/phy/cicada.c @@ -102,7 +102,8 @@ static int cis820x_config_intr(struct phy_device *phydev) } /* Cicada 8201, a.k.a Vitesse VSC8201 */ -static struct phy_driver cis8201_driver = { +static struct phy_driver cis820x_driver[] = { +{ .phy_id = 0x000fc410, .name = "Cicada Cis8201", .phy_id_mask = 0x000ffff0, @@ -113,11 +114,8 @@ static struct phy_driver cis8201_driver = { .read_status = &genphy_read_status, .ack_interrupt = &cis820x_ack_interrupt, .config_intr = &cis820x_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; - -/* Cicada 8204 */ -static struct phy_driver cis8204_driver = { + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = 0x000fc440, .name = "Cicada Cis8204", .phy_id_mask = 0x000fffc0, @@ -128,32 +126,19 @@ static struct phy_driver cis8204_driver = { .read_status = &genphy_read_status, .ack_interrupt = &cis820x_ack_interrupt, .config_intr = &cis820x_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; + .driver = { .owner = THIS_MODULE,}, +} }; static int __init cicada_init(void) { - int ret; - - ret = phy_driver_register(&cis8204_driver); - if (ret) - goto err1; - - ret = phy_driver_register(&cis8201_driver); - if (ret) - goto err2; - return 0; - -err2: - phy_driver_unregister(&cis8204_driver); -err1: - return ret; + return phy_drivers_register(cis820x_driver, + ARRAY_SIZE(cis820x_driver)); } static void __exit cicada_exit(void) { - phy_driver_unregister(&cis8204_driver); - phy_driver_unregister(&cis8201_driver); + phy_drivers_unregister(cis820x_driver, + ARRAY_SIZE(cis820x_driver)); } module_init(cicada_init); diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c index 5f59cc064778..81c7bc010dd8 100644 --- a/drivers/net/phy/davicom.c +++ b/drivers/net/phy/davicom.c @@ -144,7 +144,8 @@ static int dm9161_ack_interrupt(struct phy_device *phydev) return (err < 0) ? err : 0; } -static struct phy_driver dm9161e_driver = { +static struct phy_driver dm91xx_driver[] = { +{ .phy_id = 0x0181b880, .name = "Davicom DM9161E", .phy_id_mask = 0x0ffffff0, @@ -153,9 +154,7 @@ static struct phy_driver dm9161e_driver = { .config_aneg = dm9161_config_aneg, .read_status = genphy_read_status, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver dm9161a_driver = { +}, { .phy_id = 0x0181b8a0, .name = "Davicom DM9161A", .phy_id_mask = 0x0ffffff0, @@ -164,9 +163,7 @@ static struct phy_driver dm9161a_driver = { .config_aneg = dm9161_config_aneg, .read_status = genphy_read_status, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver dm9131_driver = { +}, { .phy_id = 0x00181b80, .name = "Davicom DM9131", .phy_id_mask = 0x0ffffff0, @@ -177,38 +174,18 @@ static struct phy_driver dm9131_driver = { .ack_interrupt = dm9161_ack_interrupt, .config_intr = dm9161_config_intr, .driver = { .owner = THIS_MODULE,}, -}; +} }; static int __init davicom_init(void) { - int ret; - - ret = phy_driver_register(&dm9161e_driver); - if (ret) - goto err1; - - ret = phy_driver_register(&dm9161a_driver); - if (ret) - goto err2; - - ret = phy_driver_register(&dm9131_driver); - if (ret) - goto err3; - return 0; - - err3: - phy_driver_unregister(&dm9161a_driver); - err2: - phy_driver_unregister(&dm9161e_driver); - err1: - return ret; + return phy_drivers_register(dm91xx_driver, + ARRAY_SIZE(dm91xx_driver)); } static void __exit davicom_exit(void) { - phy_driver_unregister(&dm9161e_driver); - phy_driver_unregister(&dm9161a_driver); - phy_driver_unregister(&dm9131_driver); + phy_drivers_unregister(dm91xx_driver, + ARRAY_SIZE(dm91xx_driver)); } module_init(davicom_init); diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index 47f8e8939266..d5199cb4caec 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -202,7 +202,8 @@ static int ip101a_g_ack_interrupt(struct phy_device *phydev) return 0; } -static struct phy_driver ip175c_driver = { +static struct phy_driver icplus_driver[] = { +{ .phy_id = 0x02430d80, .name = "ICPlus IP175C", .phy_id_mask = 0x0ffffff0, @@ -213,9 +214,7 @@ static struct phy_driver ip175c_driver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ip1001_driver = { +}, { .phy_id = 0x02430d90, .name = "ICPlus IP1001", .phy_id_mask = 0x0ffffff0, @@ -227,9 +226,7 @@ static struct phy_driver ip1001_driver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ip101a_g_driver = { +}, { .phy_id = 0x02430c54, .name = "ICPlus IP101A/G", .phy_id_mask = 0x0ffffff0, @@ -243,28 +240,18 @@ static struct phy_driver ip101a_g_driver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, -}; +} }; static int __init icplus_init(void) { - int ret = 0; - - ret = phy_driver_register(&ip1001_driver); - if (ret < 0) - return -ENODEV; - - ret = phy_driver_register(&ip101a_g_driver); - if (ret < 0) - return -ENODEV; - - return phy_driver_register(&ip175c_driver); + return phy_drivers_register(icplus_driver, + ARRAY_SIZE(icplus_driver)); } static void __exit icplus_exit(void) { - phy_driver_unregister(&ip1001_driver); - phy_driver_unregister(&ip101a_g_driver); - phy_driver_unregister(&ip175c_driver); + phy_drivers_unregister(icplus_driver, + ARRAY_SIZE(icplus_driver)); } module_init(icplus_init); diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c index 6f6e8b616a62..6d1e3fcc43e2 100644 --- a/drivers/net/phy/lxt.c +++ b/drivers/net/phy/lxt.c @@ -149,7 +149,8 @@ static int lxt973_config_aneg(struct phy_device *phydev) return phydev->priv ? 0 : genphy_config_aneg(phydev); } -static struct phy_driver lxt970_driver = { +static struct phy_driver lxt97x_driver[] = { +{ .phy_id = 0x78100000, .name = "LXT970", .phy_id_mask = 0xfffffff0, @@ -160,10 +161,8 @@ static struct phy_driver lxt970_driver = { .read_status = genphy_read_status, .ack_interrupt = lxt970_ack_interrupt, .config_intr = lxt970_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver lxt971_driver = { + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = 0x001378e0, .name = "LXT971", .phy_id_mask = 0xfffffff0, @@ -173,10 +172,8 @@ static struct phy_driver lxt971_driver = { .read_status = genphy_read_status, .ack_interrupt = lxt971_ack_interrupt, .config_intr = lxt971_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver lxt973_driver = { + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = 0x00137a10, .name = "LXT973", .phy_id_mask = 0xfffffff0, @@ -185,39 +182,19 @@ static struct phy_driver lxt973_driver = { .probe = lxt973_probe, .config_aneg = lxt973_config_aneg, .read_status = genphy_read_status, - .driver = { .owner = THIS_MODULE,}, -}; + .driver = { .owner = THIS_MODULE,}, +} }; static int __init lxt_init(void) { - int ret; - - ret = phy_driver_register(&lxt970_driver); - if (ret) - goto err1; - - ret = phy_driver_register(&lxt971_driver); - if (ret) - goto err2; - - ret = phy_driver_register(&lxt973_driver); - if (ret) - goto err3; - return 0; - - err3: - phy_driver_unregister(&lxt971_driver); - err2: - phy_driver_unregister(&lxt970_driver); - err1: - return ret; + return phy_drivers_register(lxt97x_driver, + ARRAY_SIZE(lxt97x_driver)); } static void __exit lxt_exit(void) { - phy_driver_unregister(&lxt970_driver); - phy_driver_unregister(&lxt971_driver); - phy_driver_unregister(&lxt973_driver); + phy_drivers_unregister(lxt97x_driver, + ARRAY_SIZE(lxt97x_driver)); } module_init(lxt_init); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 418928d644bf..5d2a3f215887 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -826,28 +826,14 @@ static struct phy_driver marvell_drivers[] = { static int __init marvell_init(void) { - int ret; - int i; - - for (i = 0; i < ARRAY_SIZE(marvell_drivers); i++) { - ret = phy_driver_register(&marvell_drivers[i]); - - if (ret) { - while (i-- > 0) - phy_driver_unregister(&marvell_drivers[i]); - return ret; - } - } - - return 0; + return phy_drivers_register(marvell_drivers, + ARRAY_SIZE(marvell_drivers)); } static void __exit marvell_exit(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(marvell_drivers); i++) - phy_driver_unregister(&marvell_drivers[i]); + phy_drivers_unregister(marvell_drivers, + ARRAY_SIZE(marvell_drivers)); } module_init(marvell_init); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 9d6c80c8a0cf..cf287e0eb408 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -114,7 +114,8 @@ static int ks8051_config_init(struct phy_device *phydev) return 0; } -static struct phy_driver ks8737_driver = { +static struct phy_driver ksphy_driver[] = { +{ .phy_id = PHY_ID_KS8737, .phy_id_mask = 0x00fffff0, .name = "Micrel KS8737", @@ -126,9 +127,7 @@ static struct phy_driver ks8737_driver = { .ack_interrupt = kszphy_ack_interrupt, .config_intr = ks8737_config_intr, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ks8041_driver = { +}, { .phy_id = PHY_ID_KS8041, .phy_id_mask = 0x00fffff0, .name = "Micrel KS8041", @@ -141,9 +140,7 @@ static struct phy_driver ks8041_driver = { .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ks8051_driver = { +}, { .phy_id = PHY_ID_KS8051, .phy_id_mask = 0x00fffff0, .name = "Micrel KS8051", @@ -156,9 +153,7 @@ static struct phy_driver ks8051_driver = { .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ks8001_driver = { +}, { .phy_id = PHY_ID_KS8001, .name = "Micrel KS8001 or KS8721", .phy_id_mask = 0x00ffffff, @@ -170,9 +165,7 @@ static struct phy_driver ks8001_driver = { .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .driver = { .owner = THIS_MODULE,}, -}; - -static struct phy_driver ksz9021_driver = { +}, { .phy_id = PHY_ID_KSZ9021, .phy_id_mask = 0x000ffffe, .name = "Micrel KSZ9021 Gigabit PHY", @@ -185,51 +178,18 @@ static struct phy_driver ksz9021_driver = { .ack_interrupt = kszphy_ack_interrupt, .config_intr = ksz9021_config_intr, .driver = { .owner = THIS_MODULE, }, -}; +} }; static int __init ksphy_init(void) { - int ret; - - ret = phy_driver_register(&ks8001_driver); - if (ret) - goto err1; - - ret = phy_driver_register(&ksz9021_driver); - if (ret) - goto err2; - - ret = phy_driver_register(&ks8737_driver); - if (ret) - goto err3; - ret = phy_driver_register(&ks8041_driver); - if (ret) - goto err4; - ret = phy_driver_register(&ks8051_driver); - if (ret) - goto err5; - - return 0; - -err5: - phy_driver_unregister(&ks8041_driver); -err4: - phy_driver_unregister(&ks8737_driver); -err3: - phy_driver_unregister(&ksz9021_driver); -err2: - phy_driver_unregister(&ks8001_driver); -err1: - return ret; + return phy_drivers_register(ksphy_driver, + ARRAY_SIZE(ksphy_driver)); } static void __exit ksphy_exit(void) { - phy_driver_unregister(&ks8001_driver); - phy_driver_unregister(&ks8737_driver); - phy_driver_unregister(&ksz9021_driver); - phy_driver_unregister(&ks8041_driver); - phy_driver_unregister(&ks8051_driver); + phy_drivers_unregister(ksphy_driver, + ARRAY_SIZE(ksphy_driver)); } module_init(ksphy_init); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 47e02e7dc737..8af46e88a181 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1079,12 +1079,37 @@ int phy_driver_register(struct phy_driver *new_driver) } EXPORT_SYMBOL(phy_driver_register); +int phy_drivers_register(struct phy_driver *new_driver, int n) +{ + int i, ret = 0; + + for (i = 0; i < n; i++) { + ret = phy_driver_register(new_driver + i); + if (ret) { + while (i-- > 0) + phy_driver_unregister(new_driver + i); + break; + } + } + return ret; +} +EXPORT_SYMBOL(phy_drivers_register); + void phy_driver_unregister(struct phy_driver *drv) { driver_unregister(&drv->driver); } EXPORT_SYMBOL(phy_driver_unregister); +void phy_drivers_unregister(struct phy_driver *drv, int n) +{ + int i; + for (i = 0; i < n; i++) { + phy_driver_unregister(drv + i); + } +} +EXPORT_SYMBOL(phy_drivers_unregister); + static struct phy_driver genphy_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index f414ffb5b728..72f93470ea35 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -65,11 +65,7 @@ static struct phy_driver rtl821x_driver = { static int __init realtek_init(void) { - int ret; - - ret = phy_driver_register(&rtl821x_driver); - - return ret; + return phy_driver_register(&rtl821x_driver); } static void __exit realtek_exit(void) diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index fc3e7e96c88c..c6b06d311fee 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -61,7 +61,8 @@ static int lan911x_config_init(struct phy_device *phydev) return smsc_phy_ack_interrupt(phydev); } -static struct phy_driver lan83c185_driver = { +static struct phy_driver smsc_phy_driver[] = { +{ .phy_id = 0x0007c0a0, /* OUI=0x00800f, Model#=0x0a */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN83C185", @@ -83,9 +84,7 @@ static struct phy_driver lan83c185_driver = { .resume = genphy_resume, .driver = { .owner = THIS_MODULE, } -}; - -static struct phy_driver lan8187_driver = { +}, { .phy_id = 0x0007c0b0, /* OUI=0x00800f, Model#=0x0b */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8187", @@ -107,9 +106,7 @@ static struct phy_driver lan8187_driver = { .resume = genphy_resume, .driver = { .owner = THIS_MODULE, } -}; - -static struct phy_driver lan8700_driver = { +}, { .phy_id = 0x0007c0c0, /* OUI=0x00800f, Model#=0x0c */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8700", @@ -131,9 +128,7 @@ static struct phy_driver lan8700_driver = { .resume = genphy_resume, .driver = { .owner = THIS_MODULE, } -}; - -static struct phy_driver lan911x_int_driver = { +}, { .phy_id = 0x0007c0d0, /* OUI=0x00800f, Model#=0x0d */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN911x Internal PHY", @@ -155,9 +150,7 @@ static struct phy_driver lan911x_int_driver = { .resume = genphy_resume, .driver = { .owner = THIS_MODULE, } -}; - -static struct phy_driver lan8710_driver = { +}, { .phy_id = 0x0007c0f0, /* OUI=0x00800f, Model#=0x0f */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8710/LAN8720", @@ -179,53 +172,18 @@ static struct phy_driver lan8710_driver = { .resume = genphy_resume, .driver = { .owner = THIS_MODULE, } -}; +} }; static int __init smsc_init(void) { - int ret; - - ret = phy_driver_register (&lan83c185_driver); - if (ret) - goto err1; - - ret = phy_driver_register (&lan8187_driver); - if (ret) - goto err2; - - ret = phy_driver_register (&lan8700_driver); - if (ret) - goto err3; - - ret = phy_driver_register (&lan911x_int_driver); - if (ret) - goto err4; - - ret = phy_driver_register (&lan8710_driver); - if (ret) - goto err5; - - return 0; - -err5: - phy_driver_unregister (&lan911x_int_driver); -err4: - phy_driver_unregister (&lan8700_driver); -err3: - phy_driver_unregister (&lan8187_driver); -err2: - phy_driver_unregister (&lan83c185_driver); -err1: - return ret; + return phy_drivers_register(smsc_phy_driver, + ARRAY_SIZE(smsc_phy_driver)); } static void __exit smsc_exit(void) { - phy_driver_unregister (&lan8710_driver); - phy_driver_unregister (&lan911x_int_driver); - phy_driver_unregister (&lan8700_driver); - phy_driver_unregister (&lan8187_driver); - phy_driver_unregister (&lan83c185_driver); + return phy_drivers_unregister(smsc_phy_driver, + ARRAY_SIZE(smsc_phy_driver)); } MODULE_DESCRIPTION("SMSC PHY driver"); diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index 187a2fa814f2..5e1eb138916f 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -81,7 +81,8 @@ static int ste10Xp_ack_interrupt(struct phy_device *phydev) return 0; } -static struct phy_driver ste101p_pdriver = { +static struct phy_driver ste10xp_pdriver[] = { +{ .phy_id = STE101P_PHY_ID, .phy_id_mask = 0xfffffff0, .name = "STe101p", @@ -95,9 +96,7 @@ static struct phy_driver ste101p_pdriver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = {.owner = THIS_MODULE,} -}; - -static struct phy_driver ste100p_pdriver = { +}, { .phy_id = STE100P_PHY_ID, .phy_id_mask = 0xffffffff, .name = "STe100p", @@ -111,22 +110,18 @@ static struct phy_driver ste100p_pdriver = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = {.owner = THIS_MODULE,} -}; +} }; static int __init ste10Xp_init(void) { - int retval; - - retval = phy_driver_register(&ste100p_pdriver); - if (retval < 0) - return retval; - return phy_driver_register(&ste101p_pdriver); + return phy_drivers_register(ste10xp_pdriver, + ARRAY_SIZE(ste10xp_pdriver)); } static void __exit ste10Xp_exit(void) { - phy_driver_unregister(&ste100p_pdriver); - phy_driver_unregister(&ste101p_pdriver); + phy_drivers_unregister(ste10xp_pdriver, + ARRAY_SIZE(ste10xp_pdriver)); } module_init(ste10Xp_init); diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 0ec8e09cc2ac..2585c383e623 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -138,21 +138,6 @@ static int vsc82xx_config_intr(struct phy_device *phydev) return err; } -/* Vitesse 824x */ -static struct phy_driver vsc8244_driver = { - .phy_id = PHY_ID_VSC8244, - .name = "Vitesse VSC8244", - .phy_id_mask = 0x000fffc0, - .features = PHY_GBIT_FEATURES, - .flags = PHY_HAS_INTERRUPT, - .config_init = &vsc824x_config_init, - .config_aneg = &genphy_config_aneg, - .read_status = &genphy_read_status, - .ack_interrupt = &vsc824x_ack_interrupt, - .config_intr = &vsc82xx_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; - static int vsc8221_config_init(struct phy_device *phydev) { int err; @@ -165,8 +150,22 @@ static int vsc8221_config_init(struct phy_device *phydev) Options are 802.3Z SerDes or SGMII */ } -/* Vitesse 8221 */ -static struct phy_driver vsc8221_driver = { +/* Vitesse 824x */ +static struct phy_driver vsc82xx_driver[] = { +{ + .phy_id = PHY_ID_VSC8244, + .name = "Vitesse VSC8244", + .phy_id_mask = 0x000fffc0, + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = &vsc824x_config_init, + .config_aneg = &genphy_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &vsc824x_ack_interrupt, + .config_intr = &vsc82xx_config_intr, + .driver = { .owner = THIS_MODULE,}, +}, { + /* Vitesse 8221 */ .phy_id = PHY_ID_VSC8221, .phy_id_mask = 0x000ffff0, .name = "Vitesse VSC8221", @@ -177,26 +176,19 @@ static struct phy_driver vsc8221_driver = { .read_status = &genphy_read_status, .ack_interrupt = &vsc824x_ack_interrupt, .config_intr = &vsc82xx_config_intr, - .driver = { .owner = THIS_MODULE,}, -}; + .driver = { .owner = THIS_MODULE,}, +} }; static int __init vsc82xx_init(void) { - int err; - - err = phy_driver_register(&vsc8244_driver); - if (err < 0) - return err; - err = phy_driver_register(&vsc8221_driver); - if (err < 0) - phy_driver_unregister(&vsc8244_driver); - return err; + return phy_drivers_register(vsc82xx_driver, + ARRAY_SIZE(vsc82xx_driver)); } static void __exit vsc82xx_exit(void) { - phy_driver_unregister(&vsc8244_driver); - phy_driver_unregister(&vsc8221_driver); + return phy_drivers_unregister(vsc82xx_driver, + ARRAY_SIZE(vsc82xx_driver)); } module_init(vsc82xx_init); diff --git a/include/linux/phy.h b/include/linux/phy.h index c35299e4da8e..93b3cf77f564 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -533,7 +533,9 @@ int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); void phy_driver_unregister(struct phy_driver *drv); +void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver); +int phy_drivers_register(struct phy_driver *new_driver, int n); void phy_state_machine(struct work_struct *work); void phy_start_machine(struct phy_device *phydev, void (*handler)(struct net_device *)); -- cgit v1.2.3 From 89a54e48b9cbb44aed1bf6cd712e087b96b6ae65 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 Jun 2012 14:33:17 +0200 Subject: nl80211: prepare for non-netdev wireless devs In order to support a P2P device abstraction and Bluetooth high-speed AMPs, we need to have a way to identify virtual interfaces that don't have a netdev associated. Do this by adding a NL80211_ATTR_WDEV attribute to identify a wdev which may or may not also be a netdev. To simplify things, use a 64-bit value with the high 32 bits being the wiphy index for this new wdev identifier in the nl80211 API. Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 5 ++ include/net/cfg80211.h | 22 +++++--- net/wireless/core.c | 13 ++--- net/wireless/core.h | 6 +-- net/wireless/nl80211.c | 135 ++++++++++++++++++++++++++++++++++++++---------- net/wireless/sme.c | 4 +- net/wireless/util.c | 6 +-- 7 files changed, 144 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index db961a59247f..e791487ead37 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -771,6 +771,9 @@ enum nl80211_commands { * @NL80211_ATTR_IFNAME: network interface name * @NL80211_ATTR_IFTYPE: type of virtual interface, see &enum nl80211_iftype * + * @NL80211_ATTR_WDEV: wireless device identifier, used for pseudo-devices + * that don't have a netdev (u64) + * * @NL80211_ATTR_MAC: MAC address (various uses) * * @NL80211_ATTR_KEY_DATA: (temporal) key data; for TKIP this consists of @@ -1493,6 +1496,8 @@ enum nl80211_attrs { NL80211_ATTR_BG_SCAN_PERIOD, + NL80211_ATTR_WDEV, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 51f67a9003a9..a14e6a406681 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2341,17 +2341,25 @@ struct cfg80211_internal_bss; struct cfg80211_cached_keys; /** - * struct wireless_dev - wireless per-netdev state + * struct wireless_dev - wireless device state * - * This structure must be allocated by the driver/stack - * that uses the ieee80211_ptr field in struct net_device - * (this is intentional so it can be allocated along with - * the netdev.) + * For netdevs, this structure must be allocated by the driver + * that uses the ieee80211_ptr field in struct net_device (this + * is intentional so it can be allocated along with the netdev.) + * It need not be registered then as netdev registration will + * be intercepted by cfg80211 to see the new wireless device. + * + * For non-netdev uses, it must also be allocated by the driver + * in response to the cfg80211 callbacks that require it, as + * there's no netdev registration in that case it may not be + * allocated outside of callback operations that return it. * * @wiphy: pointer to hardware description * @iftype: interface type * @list: (private) Used to collect the interfaces - * @netdev: (private) Used to reference back to the netdev + * @netdev: (private) Used to reference back to the netdev, may be %NULL + * @identifier: (private) Identifier used in nl80211 to identify this + * wireless device if it has no netdev * @current_bss: (private) Used by the internal configuration code * @channel: (private) Used by the internal configuration code to track * the user-set AP, monitor and WDS channel @@ -2383,6 +2391,8 @@ struct wireless_dev { struct list_head list; struct net_device *netdev; + u32 identifier; + struct list_head mgmt_registrations; spinlock_t mgmt_registrations_lock; diff --git a/net/wireless/core.c b/net/wireless/core.c index e42a97b5b971..b110a8a242db 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -176,7 +176,7 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, if (!(rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK)) return -EOPNOTSUPP; - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); if (err) @@ -188,7 +188,7 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, /* failed -- clean up to old netns */ net = wiphy_net(&rdev->wiphy); - list_for_each_entry_continue_reverse(wdev, &rdev->netdev_list, + list_for_each_entry_continue_reverse(wdev, &rdev->wdev_list, list) { wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; err = dev_change_net_namespace(wdev->netdev, net, @@ -226,7 +226,7 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) rtnl_lock(); mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) + list_for_each_entry(wdev, &rdev->wdev_list, list) dev_close(wdev->netdev); mutex_unlock(&rdev->devlist_mtx); @@ -304,7 +304,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) mutex_init(&rdev->mtx); mutex_init(&rdev->devlist_mtx); mutex_init(&rdev->sched_scan_mtx); - INIT_LIST_HEAD(&rdev->netdev_list); + INIT_LIST_HEAD(&rdev->wdev_list); spin_lock_init(&rdev->bss_lock); INIT_LIST_HEAD(&rdev->bss_list); INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); @@ -622,7 +622,7 @@ void wiphy_unregister(struct wiphy *wiphy) __count == 0; })); mutex_lock(&rdev->devlist_mtx); - BUG_ON(!list_empty(&rdev->netdev_list)); + BUG_ON(!list_empty(&rdev->wdev_list)); mutex_unlock(&rdev->devlist_mtx); /* @@ -821,7 +821,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, spin_lock_init(&wdev->mgmt_registrations_lock); mutex_lock(&rdev->devlist_mtx); - list_add_rcu(&wdev->list, &rdev->netdev_list); + wdev->identifier = ++rdev->wdev_id; + list_add_rcu(&wdev->list, &rdev->wdev_list); rdev->devlist_generation++; /* can only change netns with wiphy */ dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/wireless/core.h b/net/wireless/core.h index 377dc394f48c..6b0170a5f05f 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -47,11 +47,11 @@ struct cfg80211_registered_device { /* wiphy index, internal only */ int wiphy_idx; - /* associate netdev list */ + /* associated wireless interfaces */ struct mutex devlist_mtx; /* protected by devlist_mtx or RCU */ - struct list_head netdev_list; - int devlist_generation; + struct list_head wdev_list; + int devlist_generation, wdev_id; int opencount; /* also protected by devlist_mtx */ wait_queue_head_t dev_wait; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2a5cdb60bc6e..35a9b15289f1 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -46,28 +46,60 @@ static struct genl_family nl80211_fam = { .post_doit = nl80211_post_doit, }; -/* internal helper: get rdev and dev */ -static int get_rdev_dev_by_ifindex(struct net *netns, struct nlattr **attrs, - struct cfg80211_registered_device **rdev, - struct net_device **dev) +/* returns ERR_PTR values */ +static struct wireless_dev * +__cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs) { - int ifindex; + struct cfg80211_registered_device *rdev; + struct wireless_dev *result = NULL; + bool have_ifidx = attrs[NL80211_ATTR_IFINDEX]; + bool have_wdev_id = attrs[NL80211_ATTR_WDEV]; + u64 wdev_id; + int wiphy_idx = -1; + int ifidx = -1; - if (!attrs[NL80211_ATTR_IFINDEX]) - return -EINVAL; + assert_cfg80211_lock(); - ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); - *dev = dev_get_by_index(netns, ifindex); - if (!*dev) - return -ENODEV; + if (!have_ifidx && !have_wdev_id) + return ERR_PTR(-EINVAL); - *rdev = cfg80211_get_dev_from_ifindex(netns, ifindex); - if (IS_ERR(*rdev)) { - dev_put(*dev); - return PTR_ERR(*rdev); + if (have_ifidx) + ifidx = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); + if (have_wdev_id) { + wdev_id = nla_get_u64(attrs[NL80211_ATTR_WDEV]); + wiphy_idx = wdev_id >> 32; } - return 0; + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + struct wireless_dev *wdev; + + if (wiphy_net(&rdev->wiphy) != netns) + continue; + + if (have_wdev_id && rdev->wiphy_idx != wiphy_idx) + continue; + + mutex_lock(&rdev->devlist_mtx); + list_for_each_entry(wdev, &rdev->wdev_list, list) { + if (have_ifidx && wdev->netdev && + wdev->netdev->ifindex == ifidx) { + result = wdev; + break; + } + if (have_wdev_id && wdev->identifier == (u32)wdev_id) { + result = wdev; + break; + } + } + mutex_unlock(&rdev->devlist_mtx); + + if (result) + break; + } + + if (result) + return result; + return ERR_PTR(-ENODEV); } static struct cfg80211_registered_device * @@ -79,13 +111,40 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs) assert_cfg80211_lock(); if (!attrs[NL80211_ATTR_WIPHY] && - !attrs[NL80211_ATTR_IFINDEX]) + !attrs[NL80211_ATTR_IFINDEX] && + !attrs[NL80211_ATTR_WDEV]) return ERR_PTR(-EINVAL); if (attrs[NL80211_ATTR_WIPHY]) rdev = cfg80211_rdev_by_wiphy_idx( nla_get_u32(attrs[NL80211_ATTR_WIPHY])); + if (attrs[NL80211_ATTR_WDEV]) { + u64 wdev_id = nla_get_u64(attrs[NL80211_ATTR_WDEV]); + struct wireless_dev *wdev; + bool found = false; + + tmp = cfg80211_rdev_by_wiphy_idx(wdev_id >> 32); + if (tmp) { + /* make sure wdev exists */ + mutex_lock(&tmp->devlist_mtx); + list_for_each_entry(wdev, &tmp->wdev_list, list) { + if (wdev->identifier != (u32)wdev_id) + continue; + found = true; + break; + } + mutex_unlock(&tmp->devlist_mtx); + + if (!found) + tmp = NULL; + + if (rdev && tmp != rdev) + return ERR_PTR(-EINVAL); + rdev = tmp; + } + } + if (attrs[NL80211_ATTR_IFINDEX]) { int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); netdev = dev_get_by_index(netns, ifindex); @@ -294,6 +353,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_NOACK_MAP] = { .type = NLA_U16 }, [NL80211_ATTR_INACTIVITY_TIMEOUT] = { .type = NLA_U16 }, [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, + [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, }; /* policy for the key attributes */ @@ -1674,6 +1734,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, struct net_device *dev) { void *hdr; + u64 wdev_id = (u64)dev->ieee80211_ptr->identifier | + ((u64)rdev->wiphy_idx << 32); hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_INTERFACE); if (!hdr) @@ -1684,6 +1746,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, nla_put_string(msg, NL80211_ATTR_IFNAME, dev->name) || nla_put_u32(msg, NL80211_ATTR_IFTYPE, dev->ieee80211_ptr->iftype) || + nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id) || nla_put_u32(msg, NL80211_ATTR_GENERATION, rdev->devlist_generation ^ (cfg80211_rdev_list_generation << 2))) @@ -1724,7 +1787,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx = 0; mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { if (if_idx < if_start) { if_idx++; continue; @@ -2350,7 +2413,7 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { if (wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO) continue; @@ -6660,8 +6723,8 @@ static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; struct net_device *dev; - int err; bool rtnl = ops->internal_flags & NL80211_FLAG_NEED_RTNL; if (rtnl) @@ -6676,21 +6739,39 @@ static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb, } info->user_ptr[0] = rdev; } else if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) { - err = get_rdev_dev_by_ifindex(genl_info_net(info), info->attrs, - &rdev, &dev); - if (err) { + mutex_lock(&cfg80211_mutex); + wdev = __cfg80211_wdev_from_attrs(genl_info_net(info), + info->attrs); + if (IS_ERR(wdev)) { + mutex_unlock(&cfg80211_mutex); if (rtnl) rtnl_unlock(); - return err; + return PTR_ERR(wdev); } + + if (!wdev->netdev) { + mutex_unlock(&cfg80211_mutex); + if (rtnl) + rtnl_unlock(); + return -EINVAL; + } + + dev = wdev->netdev; + rdev = wiphy_to_dev(wdev->wiphy); + if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && !netif_running(dev)) { - cfg80211_unlock_rdev(rdev); - dev_put(dev); + mutex_unlock(&cfg80211_mutex); if (rtnl) rtnl_unlock(); return -ENETDOWN; } + + dev_hold(dev); + cfg80211_lock_rdev(rdev); + + mutex_unlock(&cfg80211_mutex); + info->user_ptr[0] = rdev; info->user_ptr[1] = dev; } @@ -8483,7 +8564,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb, rcu_read_lock(); list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { - list_for_each_entry_rcu(wdev, &rdev->netdev_list, list) + list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) cfg80211_mlme_unregister_socket(wdev, notify->pid); if (rdev->ap_beacons_nlpid == notify->pid) rdev->ap_beacons_nlpid = 0; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f7e937ff8978..dec97981e689 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -51,7 +51,7 @@ static bool cfg80211_is_all_idle(void) */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) { cfg80211_lock_rdev(rdev); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) is_all_idle = false; @@ -221,7 +221,7 @@ void cfg80211_conn_work(struct work_struct *work) cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev_lock(wdev); if (!netif_running(wdev->netdev)) { wdev_unlock(wdev); diff --git a/net/wireless/util.c b/net/wireless/util.c index e31f1dba79ec..f7a0647bde9a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -793,7 +793,7 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) + list_for_each_entry(wdev, &rdev->wdev_list, list) cfg80211_process_wdev_events(wdev); mutex_unlock(&rdev->devlist_mtx); @@ -994,7 +994,7 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, mutex_lock(&rdev->devlist_mtx); - list_for_each_entry(wdev, &rdev->netdev_list, list) { + list_for_each_entry(wdev, &rdev->wdev_list, list) { if (!wdev->beacon_interval) continue; if (wdev->beacon_interval != beacon_int) { @@ -1050,7 +1050,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, break; } - list_for_each_entry(wdev_iter, &rdev->netdev_list, list) { + list_for_each_entry(wdev_iter, &rdev->wdev_list, list) { if (wdev_iter == wdev) continue; if (!netif_running(wdev_iter->netdev)) -- cgit v1.2.3 From 00eeedcf084a21bf436ff3147f11f0923c811155 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 30 Jun 2012 01:44:37 +0200 Subject: bcma: extend workaround for bcm4331 This patch is based on a recent version of the Broadcom SDK. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/driver_chipcommon_pmu.c | 3 +++ include/linux/bcma/bcma_driver_chipcommon.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index 61ce4054b3c3..f18df1f392ec 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -123,8 +123,11 @@ void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable) val |= BCMA_CHIPCTL_4331_EXTPA_EN; if (bus->chipinfo.pkg == 9 || bus->chipinfo.pkg == 11) val |= BCMA_CHIPCTL_4331_EXTPA_ON_GPIO2_5; + else if (bus->chipinfo.rev > 0) + val |= BCMA_CHIPCTL_4331_EXTPA_EN2; } else { val &= ~BCMA_CHIPCTL_4331_EXTPA_EN; + val &= ~BCMA_CHIPCTL_4331_EXTPA_EN2; val &= ~BCMA_CHIPCTL_4331_EXTPA_ON_GPIO2_5; } bcma_cc_write32(cc, BCMA_CC_CHIPCTL, val); diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 8bbfe31fbac8..1e523cc61860 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -321,6 +321,7 @@ #define BCMA_CHIPCTL_4331_OVR_PIPEAUXPWRDOWN BIT(9) /* override core control on pipe_AuxPowerDown */ #define BCMA_CHIPCTL_4331_PCIE_AUXCLKEN BIT(10) /* pcie_auxclkenable */ #define BCMA_CHIPCTL_4331_PCIE_PIPE_PLLDOWN BIT(11) /* pcie_pipe_pllpowerdown */ +#define BCMA_CHIPCTL_4331_EXTPA_EN2 BIT(12) /* 0 ext pa disable, 1 ext pa enabled */ #define BCMA_CHIPCTL_4331_BT_SHD0_ON_GPIO4 BIT(16) /* enable bt_shd0 at gpio4 */ #define BCMA_CHIPCTL_4331_BT_SHD1_ON_GPIO5 BIT(17) /* enable bt_shd1 at gpio5 */ -- cgit v1.2.3 From 4b4f5be2e49a604de11dee0ee9b3f151de061724 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 30 Jun 2012 01:44:38 +0200 Subject: bcma: add constants for chip ids The chip IDs are used all over bcma and no constants where defined. This patch adds the constants and makes bcma use them. Acked-by: Arend van Spriel Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/driver_chipcommon_pmu.c | 81 ++++++++++++++++++------------------ drivers/bcma/driver_mips.c | 8 ++-- drivers/bcma/driver_pci_host.c | 8 ++-- drivers/bcma/sprom.c | 18 ++++---- include/linux/bcma/bcma.h | 30 +++++++++++++ 5 files changed, 90 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index f18df1f392ec..89528cf4d145 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -59,10 +59,10 @@ static void bcma_pmu_pll_init(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; switch (bus->chipinfo.id) { - case 0x4313: - case 0x4331: - case 43224: - case 43225: + case BCMA_CHIP_ID_BCM4313: + case BCMA_CHIP_ID_BCM4331: + case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43225: break; default: pr_err("PLL init unknown for device 0x%04X\n", @@ -76,13 +76,13 @@ static void bcma_pmu_resources_init(struct bcma_drv_cc *cc) u32 min_msk = 0, max_msk = 0; switch (bus->chipinfo.id) { - case 0x4313: + case BCMA_CHIP_ID_BCM4313: min_msk = 0x200D; max_msk = 0xFFFF; break; - case 0x4331: - case 43224: - case 43225: + case BCMA_CHIP_ID_BCM4331: + case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43225: break; default: pr_err("PMU resource config unknown for device 0x%04X\n", @@ -101,10 +101,10 @@ void bcma_pmu_swreg_init(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; switch (bus->chipinfo.id) { - case 0x4313: - case 0x4331: - case 43224: - case 43225: + case BCMA_CHIP_ID_BCM4313: + case BCMA_CHIP_ID_BCM4331: + case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43225: break; default: pr_err("PMU switch/regulators init unknown for device " @@ -138,15 +138,15 @@ void bcma_pmu_workarounds(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; switch (bus->chipinfo.id) { - case 0x4313: + case BCMA_CHIP_ID_BCM4313: bcma_chipco_chipctl_maskset(cc, 0, ~0, 0x7); break; - case 0x4331: - case 43431: + case BCMA_CHIP_ID_BCM4331: + case BCMA_CHIP_ID_BCM43431: /* Ext PA lines must be enabled for tx on BCM4331 */ bcma_chipco_bcm4331_ext_pa_lines_ctl(cc, true); break; - case 43224: + case BCMA_CHIP_ID_BCM43224: if (bus->chipinfo.rev == 0) { pr_err("Workarounds for 43224 rev 0 not fully " "implemented\n"); @@ -155,7 +155,7 @@ void bcma_pmu_workarounds(struct bcma_drv_cc *cc) bcma_chipco_chipctl_maskset(cc, 0, ~0, 0xF0); } break; - case 43225: + case BCMA_CHIP_ID_BCM43225: break; default: pr_err("Workarounds unknown for device 0x%04X\n", @@ -194,17 +194,17 @@ u32 bcma_pmu_alp_clock(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; switch (bus->chipinfo.id) { - case 0x4716: - case 0x4748: - case 47162: - case 0x4313: - case 0x5357: - case 0x4749: - case 53572: + case BCMA_CHIP_ID_BCM4716: + case BCMA_CHIP_ID_BCM4748: + case BCMA_CHIP_ID_BCM47162: + case BCMA_CHIP_ID_BCM4313: + case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM4749: + case BCMA_CHIP_ID_BCM53572: /* always 20Mhz */ return 20000 * 1000; - case 0x5356: - case 0x5300: + case BCMA_CHIP_ID_BCM5356: + case BCMA_CHIP_ID_BCM4706: /* always 25Mhz */ return 25000 * 1000; default: @@ -227,7 +227,8 @@ static u32 bcma_pmu_clock(struct bcma_drv_cc *cc, u32 pll0, u32 m) BUG_ON(!m || m > 4); - if (bus->chipinfo.id == 0x5357 || bus->chipinfo.id == 0x4749) { + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM5357 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM4749) { /* Detect failure in clock setting */ tmp = bcma_cc_read32(cc, BCMA_CC_CHIPSTAT); if (tmp & 0x40000) @@ -259,22 +260,22 @@ u32 bcma_pmu_get_clockcontrol(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; switch (bus->chipinfo.id) { - case 0x4716: - case 0x4748: - case 47162: + case BCMA_CHIP_ID_BCM4716: + case BCMA_CHIP_ID_BCM4748: + case BCMA_CHIP_ID_BCM47162: return bcma_pmu_clock(cc, BCMA_CC_PMU4716_MAINPLL_PLL0, BCMA_CC_PMU5_MAINPLL_SSB); - case 0x5356: + case BCMA_CHIP_ID_BCM5356: return bcma_pmu_clock(cc, BCMA_CC_PMU5356_MAINPLL_PLL0, BCMA_CC_PMU5_MAINPLL_SSB); - case 0x5357: - case 0x4749: + case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM4749: return bcma_pmu_clock(cc, BCMA_CC_PMU5357_MAINPLL_PLL0, BCMA_CC_PMU5_MAINPLL_SSB); - case 0x5300: + case BCMA_CHIP_ID_BCM4706: return bcma_pmu_clock(cc, BCMA_CC_PMU4706_MAINPLL_PLL0, BCMA_CC_PMU5_MAINPLL_SSB); - case 53572: + case BCMA_CHIP_ID_BCM53572: return 75000000; default: pr_warn("No backplane clock specified for %04X device, " @@ -289,17 +290,17 @@ u32 bcma_pmu_get_clockcpu(struct bcma_drv_cc *cc) { struct bcma_bus *bus = cc->core->bus; - if (bus->chipinfo.id == 53572) + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM53572) return 300000000; if (cc->pmu.rev >= 5) { u32 pll; switch (bus->chipinfo.id) { - case 0x5356: + case BCMA_CHIP_ID_BCM5356: pll = BCMA_CC_PMU5356_MAINPLL_PLL0; break; - case 0x5357: - case 0x4749: + case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM4749: pll = BCMA_CC_PMU5357_MAINPLL_PLL0; break; default: @@ -307,7 +308,7 @@ u32 bcma_pmu_get_clockcpu(struct bcma_drv_cc *cc) break; } - /* TODO: if (bus->chipinfo.id == 0x5300) + /* TODO: if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4706) return si_4706_pmu_clock(sih, osh, cc, PMU4706_MAINPLL_PLL0, PMU5_MAINPLL_CPU); */ return bcma_pmu_clock(cc, pll, BCMA_CC_PMU5_MAINPLL_CPU); } diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c index c3e9dff4224e..73ed3017077f 100644 --- a/drivers/bcma/driver_mips.c +++ b/drivers/bcma/driver_mips.c @@ -22,15 +22,15 @@ /* The 47162a0 hangs when reading MIPS DMP registers registers */ static inline bool bcma_core_mips_bcm47162a0_quirk(struct bcma_device *dev) { - return dev->bus->chipinfo.id == 47162 && dev->bus->chipinfo.rev == 0 && - dev->id.id == BCMA_CORE_MIPS_74K; + return dev->bus->chipinfo.id == BCMA_CHIP_ID_BCM47162 && + dev->bus->chipinfo.rev == 0 && dev->id.id == BCMA_CORE_MIPS_74K; } /* The 5357b0 hangs when reading USB20H DMP registers */ static inline bool bcma_core_mips_bcm5357b0_quirk(struct bcma_device *dev) { - return (dev->bus->chipinfo.id == 0x5357 || - dev->bus->chipinfo.id == 0x4749) && + return (dev->bus->chipinfo.id == BCMA_CHIP_ID_BCM5357 || + dev->bus->chipinfo.id == BCMA_CHIP_ID_BCM4749) && dev->bus->chipinfo.pkg == 11 && dev->id.id == BCMA_CORE_USB20_HOST; } diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c index b9a86edfec39..d6e8a37e3e5f 100644 --- a/drivers/bcma/driver_pci_host.c +++ b/drivers/bcma/driver_pci_host.c @@ -215,7 +215,8 @@ static int bcma_extpci_write_config(struct bcma_drv_pci *pc, unsigned int dev, } else { writel(val, mmio); - if (chipid == 0x4716 || chipid == 0x4748) + if (chipid == BCMA_CHIP_ID_BCM4716 || + chipid == BCMA_CHIP_ID_BCM4748) readl(mmio); } @@ -434,13 +435,14 @@ void __devinit bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc) * as mips can't generate 64-bit address on the * backplane. */ - if (bus->chipinfo.id == 0x4716 || bus->chipinfo.id == 0x4748) { + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4716 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM4748) { pc_host->mem_resource.start = BCMA_SOC_PCI_MEM; pc_host->mem_resource.end = BCMA_SOC_PCI_MEM + BCMA_SOC_PCI_MEM_SZ - 1; pcicore_write32(pc, BCMA_CORE_PCI_SBTOPCI0, BCMA_CORE_PCI_SBTOPCI_MEM | BCMA_SOC_PCI_MEM); - } else if (bus->chipinfo.id == 0x5300) { + } else if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4706) { tmp = BCMA_CORE_PCI_SBTOPCI_MEM; tmp |= BCMA_CORE_PCI_SBTOPCI_PREF; tmp |= BCMA_CORE_PCI_SBTOPCI_BURST; diff --git a/drivers/bcma/sprom.c b/drivers/bcma/sprom.c index f16f42d36071..e1eb598ec702 100644 --- a/drivers/bcma/sprom.c +++ b/drivers/bcma/sprom.c @@ -468,11 +468,11 @@ static bool bcma_sprom_ext_available(struct bcma_bus *bus) /* older chipcommon revisions use chip status register */ chip_status = bcma_read32(bus->drv_cc.core, BCMA_CC_CHIPSTAT); switch (bus->chipinfo.id) { - case 0x4313: + case BCMA_CHIP_ID_BCM4313: present_mask = BCMA_CC_CHIPST_4313_SPROM_PRESENT; break; - case 0x4331: + case BCMA_CHIP_ID_BCM4331: present_mask = BCMA_CC_CHIPST_4331_SPROM_PRESENT; break; @@ -494,16 +494,16 @@ static bool bcma_sprom_onchip_available(struct bcma_bus *bus) chip_status = bcma_read32(bus->drv_cc.core, BCMA_CC_CHIPSTAT); switch (bus->chipinfo.id) { - case 0x4313: + case BCMA_CHIP_ID_BCM4313: present = chip_status & BCMA_CC_CHIPST_4313_OTP_PRESENT; break; - case 0x4331: + case BCMA_CHIP_ID_BCM4331: present = chip_status & BCMA_CC_CHIPST_4331_OTP_PRESENT; break; - case 43224: - case 43225: + case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43225: /* for these chips OTP is always available */ present = true; break; @@ -579,13 +579,15 @@ int bcma_sprom_get(struct bcma_bus *bus) if (!sprom) return -ENOMEM; - if (bus->chipinfo.id == 0x4331 || bus->chipinfo.id == 43431) + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4331 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM43431) bcma_chipco_bcm4331_ext_pa_lines_ctl(&bus->drv_cc, false); pr_debug("SPROM offset 0x%x\n", offset); bcma_sprom_read(bus, offset, sprom); - if (bus->chipinfo.id == 0x4331 || bus->chipinfo.id == 43431) + if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4331 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM43431) bcma_chipco_bcm4331_ext_pa_lines_ctl(&bus->drv_cc, true); err = bcma_sprom_valid(sprom); diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 12334f9190cb..03b2f30d2ace 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -137,6 +137,36 @@ struct bcma_host_ops { #define BCMA_MAX_NR_CORES 16 +/* Chip IDs of PCIe devices */ +#define BCMA_CHIP_ID_BCM4313 0x4313 +#define BCMA_CHIP_ID_BCM43224 43224 +#define BCMA_PKG_ID_BCM43224_FAB_CSM 0x8 +#define BCMA_PKG_ID_BCM43224_FAB_SMIC 0xa +#define BCMA_CHIP_ID_BCM43225 43225 +#define BCMA_CHIP_ID_BCM43227 43227 +#define BCMA_CHIP_ID_BCM43228 43228 +#define BCMA_CHIP_ID_BCM43421 43421 +#define BCMA_CHIP_ID_BCM43428 43428 +#define BCMA_CHIP_ID_BCM43431 43431 +#define BCMA_CHIP_ID_BCM43460 43460 +#define BCMA_CHIP_ID_BCM4331 0x4331 +#define BCMA_CHIP_ID_BCM6362 0x6362 +#define BCMA_CHIP_ID_BCM4360 0x4360 +#define BCMA_CHIP_ID_BCM4352 0x4352 + +/* Chip IDs of SoCs */ +#define BCMA_CHIP_ID_BCM4706 0x5300 +#define BCMA_CHIP_ID_BCM4716 0x4716 +#define BCMA_PKG_ID_BCM4716 8 +#define BCMA_PKG_ID_BCM4717 9 +#define BCMA_PKG_ID_BCM4718 10 +#define BCMA_CHIP_ID_BCM47162 47162 +#define BCMA_CHIP_ID_BCM4748 0x4748 +#define BCMA_CHIP_ID_BCM4749 0x4749 +#define BCMA_CHIP_ID_BCM5356 0x5356 +#define BCMA_CHIP_ID_BCM5357 0x5357 +#define BCMA_CHIP_ID_BCM53572 53572 + struct bcma_device { struct bcma_bus *bus; struct bcma_device_id id; -- cgit v1.2.3 From b9562545ef0b13c0440ccd8d6dd4111fb77cb17a Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 30 Jun 2012 01:44:41 +0200 Subject: bcma: complete workaround for BCMA43224 and BCM4313 This code is based on the Broadcom SDK and brcmsmac. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/driver_chipcommon_pmu.c | 22 +++++++++++++++++----- include/linux/bcma/bcma_driver_chipcommon.h | 8 ++++++++ 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index 2d9ac3e325ae..a8fcdf0222eb 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -139,7 +139,11 @@ void bcma_pmu_workarounds(struct bcma_drv_cc *cc) switch (bus->chipinfo.id) { case BCMA_CHIP_ID_BCM4313: - bcma_chipco_chipctl_maskset(cc, 0, ~0, 0x7); + /* enable 12 mA drive strenth for 4313 and set chipControl + register bit 1 */ + bcma_chipco_chipctl_maskset(cc, 0, + BCMA_CCTRL_4313_12MA_LED_DRIVE, + BCMA_CCTRL_4313_12MA_LED_DRIVE); break; case BCMA_CHIP_ID_BCM4331: case BCMA_CHIP_ID_BCM43431: @@ -147,12 +151,20 @@ void bcma_pmu_workarounds(struct bcma_drv_cc *cc) bcma_chipco_bcm4331_ext_pa_lines_ctl(cc, true); break; case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43421: + /* enable 12 mA drive strenth for 43224 and set chipControl + register bit 15 */ if (bus->chipinfo.rev == 0) { - pr_err("Workarounds for 43224 rev 0 not fully " - "implemented\n"); - bcma_chipco_chipctl_maskset(cc, 0, ~0, 0x00F000F0); + bcma_cc_maskset32(cc, BCMA_CC_CHIPCTL, + BCMA_CCTRL_43224_GPIO_TOGGLE, + BCMA_CCTRL_43224_GPIO_TOGGLE); + bcma_chipco_chipctl_maskset(cc, 0, + BCMA_CCTRL_43224A0_12MA_LED_DRIVE, + BCMA_CCTRL_43224A0_12MA_LED_DRIVE); } else { - bcma_chipco_chipctl_maskset(cc, 0, ~0, 0xF0); + bcma_chipco_chipctl_maskset(cc, 0, + BCMA_CCTRL_43224B0_12MA_LED_DRIVE, + BCMA_CCTRL_43224B0_12MA_LED_DRIVE); } break; case BCMA_CHIP_ID_BCM43225: diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 1e523cc61860..09f31ade1410 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -325,6 +325,14 @@ #define BCMA_CHIPCTL_4331_BT_SHD0_ON_GPIO4 BIT(16) /* enable bt_shd0 at gpio4 */ #define BCMA_CHIPCTL_4331_BT_SHD1_ON_GPIO5 BIT(17) /* enable bt_shd1 at gpio5 */ +/* 43224 chip-specific ChipControl register bits */ +#define BCMA_CCTRL_43224_GPIO_TOGGLE 0x8000 /* gpio[3:0] pins as btcoex or s/w gpio */ +#define BCMA_CCTRL_43224A0_12MA_LED_DRIVE 0x00F000F0 /* 12 mA drive strength */ +#define BCMA_CCTRL_43224B0_12MA_LED_DRIVE 0xF0 /* 12 mA drive strength for later 43224s */ + +/* 4313 Chip specific ChipControl register bits */ +#define BCMA_CCTRL_4313_12MA_LED_DRIVE 0x00000007 /* 12 mA drive strengh for later 4313 */ + /* Data for the PMU, if available. * Check availability with ((struct bcma_chipcommon)->capabilities & BCMA_CC_CAP_PMU) */ -- cgit v1.2.3 From c586e10992b2e5e2dfe7cca9be615818cfb98605 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 30 Jun 2012 01:44:44 +0200 Subject: bcma: add bcma_pmu_spuravoid_pllupdate() This function is needed by brcmsmac. This code is based on code from the Broadcom SDK. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/driver_chipcommon_pmu.c | 183 +++++++++++++++++++++++++++- include/linux/bcma/bcma_driver_chipcommon.h | 14 +++ 2 files changed, 196 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index 1a7a72fb77d6..35c9130746fb 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -3,7 +3,8 @@ * ChipCommon Power Management Unit driver * * Copyright 2009, Michael Buesch - * Copyright 2007, Broadcom Corporation + * Copyright 2007, 2011, Broadcom Corporation + * Copyright 2011, 2012, Hauke Mehrtens * * Licensed under the GNU/GPL. See COPYING for details. */ @@ -284,3 +285,183 @@ u32 bcma_pmu_get_clockcpu(struct bcma_drv_cc *cc) return bcma_pmu_get_clockcontrol(cc); } + +static void bcma_pmu_spuravoid_pll_write(struct bcma_drv_cc *cc, u32 offset, + u32 value) +{ + bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, offset); + bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, value); +} + +void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid) +{ + u32 tmp = 0; + u8 phypll_offset = 0; + u8 bcm5357_bcm43236_p1div[] = {0x1, 0x5, 0x5}; + u8 bcm5357_bcm43236_ndiv[] = {0x30, 0xf6, 0xfc}; + struct bcma_bus *bus = cc->core->bus; + + switch (bus->chipinfo.id) { + case BCMA_CHIP_ID_BCM5357: + case BCMA_CHIP_ID_BCM4749: + case BCMA_CHIP_ID_BCM53572: + /* 5357[ab]0, 43236[ab]0, and 6362b0 */ + + /* BCM5357 needs to touch PLL1_PLLCTL[02], + so offset PLL0_PLLCTL[02] by 6 */ + phypll_offset = (bus->chipinfo.id == BCMA_CHIP_ID_BCM5357 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM4749 || + bus->chipinfo.id == BCMA_CHIP_ID_BCM53572) ? 6 : 0; + + /* RMW only the P1 divider */ + bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, + BCMA_CC_PMU_PLL_CTL0 + phypll_offset); + tmp = bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA); + tmp &= (~(BCMA_CC_PMU1_PLL0_PC0_P1DIV_MASK)); + tmp |= (bcm5357_bcm43236_p1div[spuravoid] << BCMA_CC_PMU1_PLL0_PC0_P1DIV_SHIFT); + bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, tmp); + + /* RMW only the int feedback divider */ + bcma_cc_write32(cc, BCMA_CC_PLLCTL_ADDR, + BCMA_CC_PMU_PLL_CTL2 + phypll_offset); + tmp = bcma_cc_read32(cc, BCMA_CC_PLLCTL_DATA); + tmp &= ~(BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_MASK); + tmp |= (bcm5357_bcm43236_ndiv[spuravoid]) << BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_SHIFT; + bcma_cc_write32(cc, BCMA_CC_PLLCTL_DATA, tmp); + + tmp = 1 << 10; + break; + + case BCMA_CHIP_ID_BCM4331: + case BCMA_CHIP_ID_BCM43431: + if (spuravoid == 2) { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11500014); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x0FC00a08); + } else if (spuravoid == 1) { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11500014); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x0F600a08); + } else { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11100014); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x03000a08); + } + tmp = 1 << 10; + break; + + case BCMA_CHIP_ID_BCM43224: + case BCMA_CHIP_ID_BCM43225: + case BCMA_CHIP_ID_BCM43421: + if (spuravoid == 1) { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11500010); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x000C0C06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x0F600a08); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x2001E920); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } else { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11100010); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x000c0c06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x03000a08); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x200005c0); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } + tmp = 1 << 10; + break; + + case BCMA_CHIP_ID_BCM4716: + case BCMA_CHIP_ID_BCM4748: + case BCMA_CHIP_ID_BCM47162: + if (spuravoid == 1) { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11500060); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x080C0C06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x0F600000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x2001E924); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } else { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11100060); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x080c0c06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x03000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x200005c0); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } + + tmp = 3 << 9; + break; + + case BCMA_CHIP_ID_BCM43227: + case BCMA_CHIP_ID_BCM43228: + case BCMA_CHIP_ID_BCM43428: + /* LCNXN */ + /* PLL Settings for spur avoidance on/off mode, + no on2 support for 43228A0 */ + if (spuravoid == 1) { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x01100014); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x040C0C06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x03140A08); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00333333); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x202C2820); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } else { + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL0, + 0x11100014); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL1, + 0x040c0c06); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL2, + 0x03000a08); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL3, + 0x00000000); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL4, + 0x200005c0); + bcma_pmu_spuravoid_pll_write(cc, BCMA_CC_PMU_PLL_CTL5, + 0x88888815); + } + tmp = 1 << 10; + break; + default: + pr_err("unknown spuravoidance settings for chip 0x%04X, not changing PLL\n", + bus->chipinfo.id); + break; + } + + tmp |= bcma_cc_read32(cc, BCMA_CC_PMU_CTL); + bcma_cc_write32(cc, BCMA_CC_PMU_CTL, tmp); +} +EXPORT_SYMBOL_GPL(bcma_pmu_spuravoid_pllupdate); diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 09f31ade1410..12975eac403f 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -308,6 +308,19 @@ #define BCMA_CC_PPL_PCHI_OFF 5 #define BCMA_CC_PPL_PCHI_MASK 0x0000003f +#define BCMA_CC_PMU_PLL_CTL0 0 +#define BCMA_CC_PMU_PLL_CTL1 1 +#define BCMA_CC_PMU_PLL_CTL2 2 +#define BCMA_CC_PMU_PLL_CTL3 3 +#define BCMA_CC_PMU_PLL_CTL4 4 +#define BCMA_CC_PMU_PLL_CTL5 5 + +#define BCMA_CC_PMU1_PLL0_PC0_P1DIV_MASK 0x00f00000 +#define BCMA_CC_PMU1_PLL0_PC0_P1DIV_SHIFT 20 + +#define BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_MASK 0x1ff00000 +#define BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_SHIFT 20 + /* BCM4331 ChipControl numbers. */ #define BCMA_CHIPCTL_4331_BT_COEXIST BIT(0) /* 0 disable */ #define BCMA_CHIPCTL_4331_SECI BIT(1) /* 0 SECI is disabled (JATG functional) */ @@ -420,5 +433,6 @@ extern void bcma_chipco_chipctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set); extern void bcma_chipco_regctl_maskset(struct bcma_drv_cc *cc, u32 offset, u32 mask, u32 set); +extern void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid); #endif /* LINUX_BCMA_DRIVER_CC_H_ */ -- cgit v1.2.3 From 01d719a2287ec34f631800d10f1fad3c134c3e89 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 4 Jul 2012 00:14:04 +0200 Subject: NFC: Add ISO 14443 type B protocol Some devices (e.g. Sony's PaSoRi) can not do type B polling, so we have to make a distinction between ISO14443 type A and B poll modes. Cc: Eric Lapuyade Cc: Ilan Elias Signed-off-by: Samuel Ortiz --- drivers/nfc/nfcwilink.c | 7 ++++--- drivers/nfc/pn533.c | 12 +++++++----- drivers/nfc/pn544_hci.c | 1 + include/linux/nfc.h | 14 ++++++++------ net/nfc/hci/core.c | 2 +- net/nfc/nci/core.c | 5 +++-- net/nfc/nci/ntf.c | 5 ++++- 7 files changed, 28 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c index 1f74a77d040d..e7fd4938f9bc 100644 --- a/drivers/nfc/nfcwilink.c +++ b/drivers/nfc/nfcwilink.c @@ -535,9 +535,10 @@ static int nfcwilink_probe(struct platform_device *pdev) drv->pdev = pdev; protocols = NFC_PROTO_JEWEL_MASK - | NFC_PROTO_MIFARE_MASK | NFC_PROTO_FELICA_MASK - | NFC_PROTO_ISO14443_MASK - | NFC_PROTO_NFC_DEP_MASK; + | NFC_PROTO_MIFARE_MASK | NFC_PROTO_FELICA_MASK + | NFC_PROTO_ISO14443_MASK + | NFC_PROTO_ISO14443_B_MASK + | NFC_PROTO_NFC_DEP_MASK; drv->ndev = nci_allocate_device(&nfcwilink_ops, protocols, diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c index 84d8175db818..d606f52fec84 100644 --- a/drivers/nfc/pn533.c +++ b/drivers/nfc/pn533.c @@ -49,13 +49,15 @@ #define PN533_DEVICE_STD 0x1 #define PN533_DEVICE_PASORI 0x2 -#define PN533_ALL_PROTOCOLS (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK \ - | NFC_PROTO_FELICA_MASK | NFC_PROTO_ISO14443_MASK \ - | NFC_PROTO_NFC_DEP_MASK) +#define PN533_ALL_PROTOCOLS (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK |\ + NFC_PROTO_FELICA_MASK | NFC_PROTO_ISO14443_MASK |\ + NFC_PROTO_NFC_DEP_MASK |\ + NFC_PROTO_ISO14443_B_MASK) #define PN533_NO_TYPE_B_PROTOCOLS (NFC_PROTO_JEWEL_MASK | \ NFC_PROTO_MIFARE_MASK | \ NFC_PROTO_FELICA_MASK | \ + NFC_PROTO_ISO14443_MASK | \ NFC_PROTO_NFC_DEP_MASK) static const struct usb_device_id pn533_table[] = { @@ -987,7 +989,7 @@ static int pn533_target_found_type_b(struct nfc_target *nfc_tgt, u8 *tgt_data, if (!pn533_target_type_b_is_valid(tgt_type_b, tgt_data_len)) return -EPROTO; - nfc_tgt->supported_protocols = NFC_PROTO_ISO14443_MASK; + nfc_tgt->supported_protocols = NFC_PROTO_ISO14443_B_MASK; return 0; } @@ -1094,7 +1096,7 @@ static void pn533_poll_create_mod_list(struct pn533 *dev, if (im_protocols & NFC_PROTO_JEWEL_MASK) pn533_poll_add_mod(dev, PN533_POLL_MOD_106KBPS_JEWEL); - if (im_protocols & NFC_PROTO_ISO14443_MASK) + if (im_protocols & NFC_PROTO_ISO14443_B_MASK) pn533_poll_add_mod(dev, PN533_POLL_MOD_847KBPS_B); if (tm_protocols) diff --git a/drivers/nfc/pn544_hci.c b/drivers/nfc/pn544_hci.c index c67b55e224e0..aa71807189ba 100644 --- a/drivers/nfc/pn544_hci.c +++ b/drivers/nfc/pn544_hci.c @@ -869,6 +869,7 @@ static int __devinit pn544_hci_probe(struct i2c_client *client, NFC_PROTO_MIFARE_MASK | NFC_PROTO_FELICA_MASK | NFC_PROTO_ISO14443_MASK | + NFC_PROTO_ISO14443_B_MASK | NFC_PROTO_NFC_DEP_MASK; info->shdlc = nfc_shdlc_allocate(&pn544_shdlc_ops, diff --git a/include/linux/nfc.h b/include/linux/nfc.h index f4e6dd915b1c..6189f27e305b 100644 --- a/include/linux/nfc.h +++ b/include/linux/nfc.h @@ -136,8 +136,9 @@ enum nfc_attrs { #define NFC_PROTO_FELICA 3 #define NFC_PROTO_ISO14443 4 #define NFC_PROTO_NFC_DEP 5 +#define NFC_PROTO_ISO14443_B 6 -#define NFC_PROTO_MAX 6 +#define NFC_PROTO_MAX 7 /* NFC communication modes */ #define NFC_COMM_ACTIVE 0 @@ -149,11 +150,12 @@ enum nfc_attrs { #define NFC_RF_NONE 2 /* NFC protocols masks used in bitsets */ -#define NFC_PROTO_JEWEL_MASK (1 << NFC_PROTO_JEWEL) -#define NFC_PROTO_MIFARE_MASK (1 << NFC_PROTO_MIFARE) -#define NFC_PROTO_FELICA_MASK (1 << NFC_PROTO_FELICA) -#define NFC_PROTO_ISO14443_MASK (1 << NFC_PROTO_ISO14443) -#define NFC_PROTO_NFC_DEP_MASK (1 << NFC_PROTO_NFC_DEP) +#define NFC_PROTO_JEWEL_MASK (1 << NFC_PROTO_JEWEL) +#define NFC_PROTO_MIFARE_MASK (1 << NFC_PROTO_MIFARE) +#define NFC_PROTO_FELICA_MASK (1 << NFC_PROTO_FELICA) +#define NFC_PROTO_ISO14443_MASK (1 << NFC_PROTO_ISO14443) +#define NFC_PROTO_NFC_DEP_MASK (1 << NFC_PROTO_NFC_DEP) +#define NFC_PROTO_ISO14443_B_MASK (1 << NFC_PROTO_ISO14443_B) struct sockaddr_nfc { sa_family_t sa_family; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 4ccc518f56eb..36717cebfbb6 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -230,7 +230,7 @@ static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) } break; case NFC_HCI_RF_READER_B_GATE: - targets->supported_protocols = NFC_PROTO_ISO14443_MASK; + targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK; break; default: if (hdev->ops->target_from_gate) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 766a02b1dfa1..5bb4da680427 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -194,7 +194,7 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && - (protocols & NFC_PROTO_ISO14443_MASK)) { + (protocols & NFC_PROTO_ISO14443_B_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_B_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; @@ -486,7 +486,8 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, param.rf_protocol = NCI_RF_PROTOCOL_T2T; else if (protocol == NFC_PROTO_FELICA) param.rf_protocol = NCI_RF_PROTOCOL_T3T; - else if (protocol == NFC_PROTO_ISO14443) + else if (protocol == NFC_PROTO_ISO14443 || + protocol == NFC_PROTO_ISO14443_B) param.rf_protocol = NCI_RF_PROTOCOL_ISO_DEP; else param.rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 2ab196a9f228..af7a93b04393 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -170,7 +170,10 @@ static int nci_add_new_protocol(struct nci_dev *ndev, if (rf_protocol == NCI_RF_PROTOCOL_T2T) protocol = NFC_PROTO_MIFARE_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_ISO_DEP) - protocol = NFC_PROTO_ISO14443_MASK; + if (rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) + protocol = NFC_PROTO_ISO14443_MASK; + else + protocol = NFC_PROTO_ISO14443_B_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_T3T) protocol = NFC_PROTO_FELICA_MASK; else -- cgit v1.2.3 From ad7eee98bef92481581060801bdfd1b25a6106c0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 Jul 2012 06:18:44 +0000 Subject: etherdevice: introduce eth_broadcast_addr A lot of code has either the memset or an inefficient copy from a static array that contains the all-ones broadcast address. Introduce eth_broadcast_addr() to fill an address with all ones, making the code clearer and allowing us to get rid of some constant arrays. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 3d406e0ede6d..98a27cccedfd 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -137,6 +137,17 @@ static inline void random_ether_addr(u8 *addr) addr [0] |= 0x02; /* set local assignment bit (IEEE802) */ } +/** + * eth_broadcast_addr - Assign broadcast address + * @addr: Pointer to a six-byte array containing the Ethernet address + * + * Assign the broadcast address to the given address array. + */ +static inline void eth_broadcast_addr(u8 *addr) +{ + memset(addr, 0xff, ETH_ALEN); +} + /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag -- cgit v1.2.3 From b6242b9b45e84ef71c59002cd128c3197938cb2f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 10 Jul 2012 03:27:56 -0700 Subject: tcp: Remove tw->tw_peer No longer used. Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - net/ipv4/tcp_minisocks.c | 16 ++-------------- 2 files changed, 2 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 7d3bcedc062a..2de9cf46f9fc 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -506,7 +506,6 @@ struct tcp_timewait_sock { u32 tw_rcv_wnd; u32 tw_ts_recent; long tw_ts_recent_stamp; - struct inet_peer *tw_peer; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a51aa534dab1..65608863fdee 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -267,12 +267,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); bool recycle_ok = false; - bool recycle_on = false; - if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) { + if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) recycle_ok = tcp_remember_stamp(sk); - recycle_on = true; - } if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) tw = inet_twsk_alloc(sk, state); @@ -281,7 +278,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); struct inet_sock *inet = inet_sk(sk); - struct inet_peer *peer = NULL; tw->tw_transparent = inet->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; @@ -305,12 +301,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } #endif - if (recycle_on) - peer = icsk->icsk_af_ops->get_peer(sk); - tcptw->tw_peer = peer; - if (peer) - atomic_inc(&peer->refcnt); - #ifdef CONFIG_TCP_MD5SIG /* * The timewait bucket does not have the key DB from the @@ -362,11 +352,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) void tcp_twsk_destructor(struct sock *sk) { +#ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_peer) - inet_putpeer(twsk->tw_peer); -#ifdef CONFIG_TCP_MD5SIG if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); kfree_rcu(twsk->tw_md5_key, rcu); -- cgit v1.2.3 From 87a50699cb6d169591cc776fb82683a2c77cecac Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 10 Jul 2012 05:06:14 -0700 Subject: rtnetlink: Remove ts/tsage args to rtnl_put_cacheinfo(). Nobody provides non-zero values any longer. Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 +-- net/core/rtnetlink.c | 4 +--- net/decnet/dn_route.c | 2 +- net/ipv4/route.c | 3 +-- net/ipv6/route.c | 3 +-- 5 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index ea60b0854109..db71c4ad8624 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -619,8 +619,7 @@ extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, extern void rtnl_set_sk_err(struct net *net, u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, - u32 id, u32 ts, u32 tsage, long expires, - u32 error); + u32 id, long expires, u32 error); extern void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2b325c340b44..64127eee786d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -615,7 +615,7 @@ nla_put_failure: EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, - u32 ts, u32 tsage, long expires, u32 error) + long expires, u32 error) { struct rta_cacheinfo ci = { .rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse), @@ -623,8 +623,6 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, - .rta_ts = ts, - .rta_tsage = tsage, }; if (expires) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 707027fae8ab..b5594cc73ee1 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1590,7 +1590,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, goto errout; expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto errout; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d4834e2914a0..67b08745daf9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2931,8 +2931,7 @@ static int rt_fill_info(struct net *net, goto nla_put_failure; } - if (rtnl_put_cacheinfo(skb, &rt->dst, id, 0, 0, - expires, error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, id, expires, error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b7eb51e1a0e1..563f12c1c99c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2471,8 +2471,7 @@ static int rt6_fill_node(struct net *net, else expires = INT_MAX; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, - expires, rt->dst.error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); -- cgit v1.2.3 From 48ee3569f31d91084dc694fef5517eb782428083 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 11 Jul 2012 02:39:24 -0700 Subject: ipv6: Move ipv6 twsk accessors outside of CONFIG_IPV6 ifdefs. Fixes build when ipv6 is disabled. Reported-by: Fengguang Wu Signed-off-by: David S. Miller --- include/linux/ipv6.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8260ef779762..bc6c8fd8ed01 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -410,6 +410,22 @@ struct tcp6_sock { extern int inet6_sk_rebuild_header(struct sock *sk); +struct inet6_timewait_sock { + struct in6_addr tw_v6_daddr; + struct in6_addr tw_v6_rcv_saddr; +}; + +struct tcp6_timewait_sock { + struct tcp_timewait_sock tcp6tw_tcp; + struct inet6_timewait_sock tcp6tw_inet6; +}; + +static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk) +{ + return (struct inet6_timewait_sock *)(((u8 *)sk) + + inet_twsk(sk)->tw_ipv6_offset); +} + #if IS_ENABLED(CONFIG_IPV6) static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { @@ -459,28 +475,12 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only) #define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk)) -struct inet6_timewait_sock { - struct in6_addr tw_v6_daddr; - struct in6_addr tw_v6_rcv_saddr; -}; - -struct tcp6_timewait_sock { - struct tcp_timewait_sock tcp6tw_tcp; - struct inet6_timewait_sock tcp6tw_inet6; -}; - static inline u16 inet6_tw_offset(const struct proto *prot) { return prot->twsk_prot->twsk_obj_size - sizeof(struct inet6_timewait_sock); } -static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk) -{ - return (struct inet6_timewait_sock *)(((u8 *)sk) + - inet_twsk(sk)->tw_ipv6_offset); -} - static inline struct in6_addr *__inet6_rcv_saddr(const struct sock *sk) { return likely(sk->sk_state != TCP_TIME_WAIT) ? -- cgit v1.2.3 From 650cef38263c0f4c8970265354432be154eef425 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 9 Jul 2012 22:03:10 +0200 Subject: bcma: add PMU clock support for BCM4706 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Hauke Mehrtens Tested-by: Rafał Miłecki Signed-off-by: John W. Linville --- drivers/bcma/driver_chipcommon_pmu.c | 40 ++++++++++++++++++++++++++--- include/linux/bcma/bcma_driver_chipcommon.h | 14 ++++++++++ 2 files changed, 50 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index 74a87d530424..44326178db29 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -226,6 +226,36 @@ static u32 bcma_pmu_clock(struct bcma_drv_cc *cc, u32 pll0, u32 m) return (fc / div) * 1000000; } +static u32 bcma_pmu_clock_bcm4706(struct bcma_drv_cc *cc, u32 pll0, u32 m) +{ + u32 tmp, ndiv, p1div, p2div; + u32 clock; + + BUG_ON(!m || m > 4); + + /* Get N, P1 and P2 dividers to determine CPU clock */ + tmp = bcma_chipco_pll_read(cc, pll0 + BCMA_CC_PMU6_4706_PROCPLL_OFF); + ndiv = (tmp & BCMA_CC_PMU6_4706_PROC_NDIV_INT_MASK) + >> BCMA_CC_PMU6_4706_PROC_NDIV_INT_SHIFT; + p1div = (tmp & BCMA_CC_PMU6_4706_PROC_P1DIV_MASK) + >> BCMA_CC_PMU6_4706_PROC_P1DIV_SHIFT; + p2div = (tmp & BCMA_CC_PMU6_4706_PROC_P2DIV_MASK) + >> BCMA_CC_PMU6_4706_PROC_P2DIV_SHIFT; + + tmp = bcma_cc_read32(cc, BCMA_CC_CHIPSTAT); + if (tmp & BCMA_CC_CHIPST_4706_PKG_OPTION) + /* Low cost bonding: Fixed reference clock 25MHz and m = 4 */ + clock = (25000000 / 4) * ndiv * p2div / p1div; + else + /* Fixed reference clock 25MHz and m = 2 */ + clock = (25000000 / 2) * ndiv * p2div / p1div; + + if (m == BCMA_CC_PMU5_MAINPLL_SSB) + clock = clock / 4; + + return clock; +} + /* query bus clock frequency for PMU-enabled chipcommon */ u32 bcma_pmu_get_clockcontrol(struct bcma_drv_cc *cc) { @@ -245,8 +275,8 @@ u32 bcma_pmu_get_clockcontrol(struct bcma_drv_cc *cc) return bcma_pmu_clock(cc, BCMA_CC_PMU5357_MAINPLL_PLL0, BCMA_CC_PMU5_MAINPLL_SSB); case BCMA_CHIP_ID_BCM4706: - return bcma_pmu_clock(cc, BCMA_CC_PMU4706_MAINPLL_PLL0, - BCMA_CC_PMU5_MAINPLL_SSB); + return bcma_pmu_clock_bcm4706(cc, BCMA_CC_PMU4706_MAINPLL_PLL0, + BCMA_CC_PMU5_MAINPLL_SSB); case BCMA_CHIP_ID_BCM53572: return 75000000; default: @@ -267,6 +297,10 @@ u32 bcma_pmu_get_clockcpu(struct bcma_drv_cc *cc) if (cc->pmu.rev >= 5) { u32 pll; switch (bus->chipinfo.id) { + case BCMA_CHIP_ID_BCM4706: + return bcma_pmu_clock_bcm4706(cc, + BCMA_CC_PMU4706_MAINPLL_PLL0, + BCMA_CC_PMU5_MAINPLL_CPU); case BCMA_CHIP_ID_BCM5356: pll = BCMA_CC_PMU5356_MAINPLL_PLL0; break; @@ -279,8 +313,6 @@ u32 bcma_pmu_get_clockcpu(struct bcma_drv_cc *cc) break; } - /* TODO: if (bus->chipinfo.id == BCMA_CHIP_ID_BCM4706) - return si_4706_pmu_clock(sih, osh, cc, PMU4706_MAINPLL_PLL0, PMU5_MAINPLL_CPU); */ return bcma_pmu_clock(cc, pll, BCMA_CC_PMU5_MAINPLL_CPU); } diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 12975eac403f..fbd0d49dc4d2 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -88,6 +88,11 @@ #define BCMA_CC_CHIPST_4313_OTP_PRESENT 2 #define BCMA_CC_CHIPST_4331_SPROM_PRESENT 2 #define BCMA_CC_CHIPST_4331_OTP_PRESENT 4 +#define BCMA_CC_CHIPST_4706_PKG_OPTION BIT(0) /* 0: full-featured package 1: low-cost package */ +#define BCMA_CC_CHIPST_4706_SFLASH_PRESENT BIT(1) /* 0: parallel, 1: serial flash is present */ +#define BCMA_CC_CHIPST_4706_SFLASH_TYPE BIT(2) /* 0: 8b-p/ST-s flash, 1: 16b-p/Atmal-s flash */ +#define BCMA_CC_CHIPST_4706_MIPS_BENDIAN BIT(3) /* 0: little, 1: big endian */ +#define BCMA_CC_CHIPST_4706_PCIE1_DISABLE BIT(5) /* PCIE1 enable strap pin */ #define BCMA_CC_JCMD 0x0030 /* Rev >= 10 only */ #define BCMA_CC_JCMD_START 0x80000000 #define BCMA_CC_JCMD_BUSY 0x80000000 @@ -280,6 +285,15 @@ /* 4706 PMU */ #define BCMA_CC_PMU4706_MAINPLL_PLL0 0 +#define BCMA_CC_PMU6_4706_PROCPLL_OFF 4 /* The CPU PLL */ +#define BCMA_CC_PMU6_4706_PROC_P2DIV_MASK 0x000f0000 +#define BCMA_CC_PMU6_4706_PROC_P2DIV_SHIFT 16 +#define BCMA_CC_PMU6_4706_PROC_P1DIV_MASK 0x0000f000 +#define BCMA_CC_PMU6_4706_PROC_P1DIV_SHIFT 12 +#define BCMA_CC_PMU6_4706_PROC_NDIV_INT_MASK 0x00000ff8 +#define BCMA_CC_PMU6_4706_PROC_NDIV_INT_SHIFT 3 +#define BCMA_CC_PMU6_4706_PROC_NDIV_MODE_MASK 0x00000007 +#define BCMA_CC_PMU6_4706_PROC_NDIV_MODE_SHIFT 0 /* ALP clock on pre-PMU chips */ #define BCMA_CC_PMU_ALP_CLOCK 20000000 -- cgit v1.2.3 From 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Jul 2012 05:50:31 +0000 Subject: tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet Cc: Dave Taht Cc: Tom Herbert Cc: Matt Mathis Cc: Yuchung Cheng Cc: Nandita Dukkipati Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 14 +++ include/linux/tcp.h | 9 ++ include/net/sock.h | 2 + include/net/tcp.h | 4 + net/core/sock.c | 4 + net/ipv4/sysctl_net_ipv4.c | 7 ++ net/ipv4/tcp.c | 6 ++ net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_minisocks.c | 1 + net/ipv4/tcp_output.c | 154 ++++++++++++++++++++++++++++++++- net/ipv6/tcp_ipv6.c | 1 + 11 files changed, 202 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 47b6c79e9b05..e20c17a7d34e 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -551,6 +551,20 @@ tcp_thin_dupack - BOOLEAN Documentation/networking/tcp-thin.txt Default: 0 +tcp_limit_output_bytes - INTEGER + Controls TCP Small Queue limit per tcp socket. + TCP bulk sender tends to increase packets in flight until it + gets losses notifications. With SNDBUF autotuning, this can + result in a large amount of packets queued in qdisc/device + on the local machine, hurting latency of other flows, for + typical pfifo_fast qdiscs. + tcp_limit_output_bytes limits the number of bytes on qdisc + or device to reduce artificial RTT/cwnd and reduce bufferbloat. + Note: For GSO/TSO enabled flows, we try to have at least two + packets in flight. Reducing tcp_limit_output_bytes might also + reduce the size of individual GSO packet (64KB being the max) + Default: 131072 + UDP variables: udp_mem - vector of 3 INTEGERs: min, pressure, max diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2de9cf46f9fc..1888169e07c7 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -339,6 +339,9 @@ struct tcp_sock { u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ + struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + unsigned long tsq_flags; + /* Data for direct copy to user */ struct { struct sk_buff_head prequeue; @@ -494,6 +497,12 @@ struct tcp_sock { struct tcp_cookie_values *cookie_values; }; +enum tsq_flags { + TSQ_THROTTLED, + TSQ_QUEUED, + TSQ_OWNED, /* tcp_tasklet_func() found socket was locked */ +}; + static inline struct tcp_sock *tcp_sk(const struct sock *sk) { return (struct tcp_sock *)sk; diff --git a/include/net/sock.h b/include/net/sock.h index dcb54a0793ec..88de092df50f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -858,6 +858,8 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + void (*release_cb)(struct sock *sk); + /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 3618fefae049..439984b9af49 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,7 @@ extern int sysctl_tcp_cookie_size; extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; +extern int sysctl_tcp_limit_output_bytes; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -321,6 +322,8 @@ extern struct proto tcp_prot; extern void tcp_init_mem(struct net *net); +extern void tcp_tasklet_init(void); + extern void tcp_v4_err(struct sk_buff *skb, u32); extern void tcp_shutdown (struct sock *sk, int how); @@ -334,6 +337,7 @@ extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); extern int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +extern void tcp_release_cb(struct sock *sk); extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); diff --git a/net/core/sock.c b/net/core/sock.c index 929bdcc2383b..24039ac12426 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2159,6 +2159,10 @@ void release_sock(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); + + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + sk->sk_lock.owned = 0; if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 12aa0c5867c4..70730f7aeafe 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -598,6 +598,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_limit_output_bytes", + .data = &sysctl_tcp_limit_output_bytes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, #ifdef CONFIG_NET_DMA { .procname = "tcp_dma_copybreak", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d902da96d154..4252cd8f39fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -376,6 +376,7 @@ void tcp_init_sock(struct sock *sk) skb_queue_head_init(&tp->out_of_order_queue); tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); + INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev = TCP_TIMEOUT_INIT; @@ -796,6 +797,10 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, inet_csk(sk)->icsk_ext_hdr_len - tp->tcp_header_len); + /* TSQ : try to have two TSO segments in flight */ + xmit_size_goal = min_t(u32, xmit_size_goal, + sysctl_tcp_limit_output_bytes >> 1); + xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); /* We try hard to avoid divides here */ @@ -3574,4 +3579,5 @@ void __init tcp_init(void) tcp_secret_primary = &tcp_secret_one; tcp_secret_retiring = &tcp_secret_two; tcp_secret_secondary = &tcp_secret_two; + tcp_tasklet_init(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ddefd39ac0cf..01545a3fc0f2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2588,6 +2588,7 @@ struct proto tcp_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, + .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 65608863fdee..c66f2ede160e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -424,6 +424,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); + INIT_LIST_HEAD(&newtp->tsq_node); tcp_init_wl(newtp, treq->rcv_isn); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c465d3e51e28..03854abfd9d8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -50,6 +50,9 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1; */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; +/* Default TSQ limit of two TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 131072; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -65,6 +68,8 @@ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) @@ -783,6 +788,140 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb return size; } + +/* TCP SMALL QUEUES (TSQ) + * + * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) + * to reduce RTT and bufferbloat. + * We do this using a special skb destructor (tcp_wfree). + * + * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb + * needs to be reallocated in a driver. + * The invariant being skb->truesize substracted from sk->sk_wmem_alloc + * + * Since transmit from skb destructor is forbidden, we use a tasklet + * to process all sockets that eventually need to send more skbs. + * We use one tasklet per cpu, with its own queue of sockets. + */ +struct tsq_tasklet { + struct tasklet_struct tasklet; + struct list_head head; /* queue of tcp sockets */ +}; +static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); + +/* + * One tasklest per cpu tries to send more skbs. + * We run in tasklet context but need to disable irqs when + * transfering tsq->head because tcp_wfree() might + * interrupt us (non NAPI drivers) + */ +static void tcp_tasklet_func(unsigned long data) +{ + struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; + LIST_HEAD(list); + unsigned long flags; + struct list_head *q, *n; + struct tcp_sock *tp; + struct sock *sk; + + local_irq_save(flags); + list_splice_init(&tsq->head, &list); + local_irq_restore(flags); + + list_for_each_safe(q, n, &list) { + tp = list_entry(q, struct tcp_sock, tsq_node); + list_del(&tp->tsq_node); + + sk = (struct sock *)tp; + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } else { + /* defer the work to tcp_release_cb() */ + set_bit(TSQ_OWNED, &tp->tsq_flags); + } + bh_unlock_sock(sk); + + clear_bit(TSQ_QUEUED, &tp->tsq_flags); + sk_free(sk); + } +} + +/** + * tcp_release_cb - tcp release_sock() callback + * @sk: socket + * + * called from release_sock() to perform protocol dependent + * actions before socket release. + */ +void tcp_release_cb(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } +} +EXPORT_SYMBOL(tcp_release_cb); + +void __init tcp_tasklet_init(void) +{ + int i; + + for_each_possible_cpu(i) { + struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + + INIT_LIST_HEAD(&tsq->head); + tasklet_init(&tsq->tasklet, + tcp_tasklet_func, + (unsigned long)tsq); + } +} + +/* + * Write buffer destructor automatically called from kfree_skb. + * We cant xmit new skbs from this context, as we might already + * hold qdisc lock. + */ +void tcp_wfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) && + !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) { + unsigned long flags; + struct tsq_tasklet *tsq; + + /* Keep a ref on socket. + * This last ref will be released in tcp_tasklet_func() + */ + atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc); + + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = &__get_cpu_var(tsq_tasklet); + list_add(&tp->tsq_node, &tsq->head); + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + } else { + sock_wfree(skb); + } +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -844,7 +983,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); - skb_set_owner_w(skb, sk); + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? + tcp_wfree : sock_wfree; + atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); @@ -1780,6 +1924,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1800,6 +1945,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } + /* TSQ : sk_wmem_alloc accounts skb truesize, + * including skb overhead. But thats OK. + */ + if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + break; + } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 61175cb2478f..70458a9cd837 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1970,6 +1970,7 @@ struct proto tcpv6_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, + .release_cb = tcp_release_cb, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, -- cgit v1.2.3 From 6d4fa852a023080101f1665ea189dd1844c87fef Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Jul 2012 10:56:57 +0000 Subject: net: sched: add ipset ematch Can be used to match packets against netfilter ip sets created via ipset(8). skb->sk_iif is used as 'incoming interface', skb->dev is 'outgoing interface'. Since ipset is usually called from netfilter, the ematch initializes a fake xt_action_param, pulls the ip header into the linear area and also sets skb->data to the IP header (otherwise matching Layer 4 set types doesn't work). Tested-by: Mr Dash Four Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/pkt_cls.h | 3 +- net/sched/Kconfig | 10 ++++ net/sched/Makefile | 1 + net/sched/em_ipset.c | 135 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 148 insertions(+), 1 deletion(-) create mode 100644 net/sched/em_ipset.c (limited to 'include/linux') diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h index 38fbd4bc20ab..082eafaf026b 100644 --- a/include/linux/pkt_cls.h +++ b/include/linux/pkt_cls.h @@ -453,7 +453,8 @@ enum { #define TCF_EM_TEXT 5 #define TCF_EM_VLAN 6 #define TCF_EM_CANID 7 -#define TCF_EM_MAX 7 +#define TCF_EM_IPSET 8 +#define TCF_EM_MAX 8 enum { TCF_EM_PROG_TC diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 4a5d2bd4f789..62fb51face8a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -517,6 +517,16 @@ config NET_EMATCH_CANID To compile this code as a module, choose M here: the module will be called em_canid. +config NET_EMATCH_IPSET + tristate "IPset" + depends on NET_EMATCH && IP_SET + ---help--- + Say Y here if you want to be able to classify packets based on + ipset membership. + + To compile this code as a module, choose M here: the + module will be called em_ipset. + config NET_CLS_ACT bool "Actions" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index bcada751b4ef..978cbf004e80 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -56,3 +56,4 @@ obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o +obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c new file mode 100644 index 000000000000..3130320997e2 --- /dev/null +++ b/net/sched/em_ipset.c @@ -0,0 +1,135 @@ +/* + * net/sched/em_ipset.c ipset ematch + * + * Copyright (c) 2012 Florian Westphal + * + * 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. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len, + struct tcf_ematch *em) +{ + struct xt_set_info *set = data; + ip_set_id_t index; + + if (data_len != sizeof(*set)) + return -EINVAL; + + index = ip_set_nfnl_get_byindex(set->index); + if (index == IPSET_INVALID_ID) + return -ENOENT; + + em->datalen = sizeof(*set); + em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL); + if (em->data) + return 0; + + ip_set_nfnl_put(index); + return -ENOMEM; +} + +static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em) +{ + const struct xt_set_info *set = (const void *) em->data; + if (set) { + ip_set_nfnl_put(set->index); + kfree((void *) em->data); + } +} + +static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, + struct tcf_pkt_info *info) +{ + struct ip_set_adt_opt opt; + struct xt_action_param acpar; + const struct xt_set_info *set = (const void *) em->data; + struct net_device *dev, *indev = NULL; + int ret, network_offset; + + switch (skb->protocol) { + case htons(ETH_P_IP): + acpar.family = NFPROTO_IPV4; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + return 0; + acpar.thoff = ip_hdrlen(skb); + break; + case htons(ETH_P_IPV6): + acpar.family = NFPROTO_IPV6; + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + /* doesn't call ipv6_find_hdr() because ipset doesn't use thoff, yet */ + acpar.thoff = sizeof(struct ipv6hdr); + break; + default: + return 0; + } + + acpar.hooknum = 0; + + opt.family = acpar.family; + opt.dim = set->dim; + opt.flags = set->flags; + opt.cmdflags = 0; + opt.timeout = ~0u; + + network_offset = skb_network_offset(skb); + skb_pull(skb, network_offset); + + dev = skb->dev; + + rcu_read_lock(); + + if (dev && skb->skb_iif) + indev = dev_get_by_index_rcu(dev_net(dev), skb->skb_iif); + + acpar.in = indev ? indev : dev; + acpar.out = dev; + + ret = ip_set_test(set->index, skb, &acpar, &opt); + + rcu_read_unlock(); + + skb_push(skb, network_offset); + return ret; +} + +static struct tcf_ematch_ops em_ipset_ops = { + .kind = TCF_EM_IPSET, + .change = em_ipset_change, + .destroy = em_ipset_destroy, + .match = em_ipset_match, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_ipset_ops.link) +}; + +static int __init init_em_ipset(void) +{ + return tcf_em_register(&em_ipset_ops); +} + +static void __exit exit_em_ipset(void) +{ + tcf_em_unregister(&em_ipset_ops); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); +MODULE_DESCRIPTION("TC extended match for IP sets"); + +module_init(init_em_ipset); +module_exit(exit_em_ipset); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPSET); -- cgit v1.2.3 From 6e88e1357c788d40cd64a8c9080e81ca6c9eee0f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Jul 2012 05:34:02 +0000 Subject: team: use function team_port_txable() for determing enabled and up port Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 6 ++++++ drivers/net/team/team_mode_roundrobin.c | 6 +++--- include/linux/if_team.h | 1 + 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 9b94f53a9d4b..bc7afa51d052 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -677,6 +677,12 @@ bool team_port_enabled(struct team_port *port) } EXPORT_SYMBOL(team_port_enabled); +bool team_port_txable(struct team_port *port) +{ + return port->linkup && team_port_enabled(port); +} +EXPORT_SYMBOL(team_port_txable); + /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c index 52dd0ec9cd1f..0cf38e9b9d26 100644 --- a/drivers/net/team/team_mode_roundrobin.c +++ b/drivers/net/team/team_mode_roundrobin.c @@ -30,16 +30,16 @@ static struct team_port *__get_first_port_up(struct team *team, { struct team_port *cur; - if (port->linkup) + if (team_port_txable(port)) return port; cur = port; list_for_each_entry_continue_rcu(cur, &team->port_list, list) - if (cur->linkup) + if (team_port_txable(port)) return cur; list_for_each_entry_rcu(cur, &team->port_list, list) { if (cur == port) break; - if (cur->linkup) + if (team_port_txable(port)) return cur; } return NULL; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 99efd60fa8c9..dca426cb1e12 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -64,6 +64,7 @@ struct team_port { }; extern bool team_port_enabled(struct team_port *port); +extern bool team_port_txable(struct team_port *port); struct team_mode_ops { int (*init)(struct team *team); -- cgit v1.2.3 From 68c450426ae665653b06f62539e48727b696496f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Jul 2012 05:34:04 +0000 Subject: team: make team_port_enabled() and team_port_txable() static inline Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 12 ------------ include/linux/if_team.h | 11 +++++++++-- 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bc7afa51d052..3620c63f9345 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -671,18 +671,6 @@ static bool team_port_find(const struct team *team, return false; } -bool team_port_enabled(struct team_port *port) -{ - return port->index != -1; -} -EXPORT_SYMBOL(team_port_enabled); - -bool team_port_txable(struct team_port *port) -{ - return port->linkup && team_port_enabled(port); -} -EXPORT_SYMBOL(team_port_txable); - /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when diff --git a/include/linux/if_team.h b/include/linux/if_team.h index dca426cb1e12..dfa0c8e0ab84 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -63,8 +63,15 @@ struct team_port { long mode_priv[0]; }; -extern bool team_port_enabled(struct team_port *port); -extern bool team_port_txable(struct team_port *port); +static inline bool team_port_enabled(struct team_port *port) +{ + return port->index != -1; +} + +static inline bool team_port_txable(struct team_port *port) +{ + return port->linkup && team_port_enabled(port); +} struct team_mode_ops { int (*init)(struct team *team); -- cgit v1.2.3 From e1ac4b409037b128f9a3eca3b3ab5dbbb71a7e6f Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 11 Jul 2012 09:23:43 +0200 Subject: bcma: add trivial GBIT MAC COMMON driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GMAC COMMON core is present on BCM4706 and is used for example to access board PHYs (PHYs can not be accessed directly using GBIT MAC core). Signed-off-by: Rafał Miłecki Acked-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/Kconfig | 9 +++ drivers/bcma/Makefile | 1 + drivers/bcma/driver_gmac_cmn.c | 14 +++++ drivers/bcma/main.c | 8 +++ drivers/bcma/scan.c | 16 +++-- include/linux/bcma/bcma.h | 2 + include/linux/bcma/bcma_driver_gmac_cmn.h | 100 ++++++++++++++++++++++++++++++ 7 files changed, 144 insertions(+), 6 deletions(-) create mode 100644 drivers/bcma/driver_gmac_cmn.c create mode 100644 include/linux/bcma/bcma_driver_gmac_cmn.h (limited to 'include/linux') diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig index fb7c80fb721e..9319cde8d751 100644 --- a/drivers/bcma/Kconfig +++ b/drivers/bcma/Kconfig @@ -46,6 +46,15 @@ config BCMA_DRIVER_MIPS If unsure, say N +config BCMA_DRIVER_GMAC_CMN + bool "BCMA Broadcom GBIT MAC COMMON core driver" + depends on BCMA + help + Driver for the Broadcom GBIT MAC COMMON core attached to Broadcom + specific Advanced Microcontroller Bus. + + If unsure, say N + config BCMA_DEBUG bool "BCMA debugging" depends on BCMA diff --git a/drivers/bcma/Makefile b/drivers/bcma/Makefile index 82de24e5340c..d13803faf1d6 100644 --- a/drivers/bcma/Makefile +++ b/drivers/bcma/Makefile @@ -3,6 +3,7 @@ bcma-y += driver_chipcommon.o driver_chipcommon_pmu.o bcma-y += driver_pci.o bcma-$(CONFIG_BCMA_DRIVER_PCI_HOSTMODE) += driver_pci_host.o bcma-$(CONFIG_BCMA_DRIVER_MIPS) += driver_mips.o +bcma-$(CONFIG_BCMA_DRIVER_GMAC_CMN) += driver_gmac_cmn.o bcma-$(CONFIG_BCMA_HOST_PCI) += host_pci.o bcma-$(CONFIG_BCMA_HOST_SOC) += host_soc.o obj-$(CONFIG_BCMA) += bcma.o diff --git a/drivers/bcma/driver_gmac_cmn.c b/drivers/bcma/driver_gmac_cmn.c new file mode 100644 index 000000000000..834225f65e8f --- /dev/null +++ b/drivers/bcma/driver_gmac_cmn.c @@ -0,0 +1,14 @@ +/* + * Broadcom specific AMBA + * GBIT MAC COMMON Core + * + * Licensed under the GNU/GPL. See COPYING for details. + */ + +#include "bcma_private.h" +#include + +void __devinit bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc) +{ + mutex_init(&gc->phy_mutex); +} diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 151bddc57e16..758af9ccdef0 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -103,6 +103,7 @@ static int bcma_register_cores(struct bcma_bus *bus) case BCMA_CORE_PCI: case BCMA_CORE_PCIE: case BCMA_CORE_MIPS_74K: + case BCMA_CORE_4706_MAC_GBIT_COMMON: continue; } @@ -185,6 +186,13 @@ int __devinit bcma_bus_register(struct bcma_bus *bus) bcma_core_pci_init(&bus->drv_pci); } + /* Init GBIT MAC COMMON core */ + core = bcma_find_core(bus, BCMA_CORE_4706_MAC_GBIT_COMMON); + if (core) { + bus->drv_gmac_cmn.core = core; + bcma_core_gmac_cmn_init(&bus->drv_gmac_cmn); + } + /* Try to get SPROM */ err = bcma_sprom_get(bus); if (err == -ENOENT) { diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c index a0272bbfc4f6..3bc3ec26fd0e 100644 --- a/drivers/bcma/scan.c +++ b/drivers/bcma/scan.c @@ -21,6 +21,7 @@ struct bcma_device_id_name { }; static const struct bcma_device_id_name bcma_arm_device_names[] = { + { BCMA_CORE_4706_MAC_GBIT_COMMON, "BCM4706 GBit MAC Common" }, { BCMA_CORE_ARM_1176, "ARM 1176" }, { BCMA_CORE_ARM_7TDMI, "ARM 7TDMI" }, { BCMA_CORE_ARM_CM3, "ARM CM3" }, @@ -33,7 +34,6 @@ static const struct bcma_device_id_name bcma_bcm_device_names[] = { { BCMA_CORE_4706_MAC_GBIT, "BCM4706 GBit MAC" }, { BCMA_CORE_AMEMC, "AMEMC (DDR)" }, { BCMA_CORE_ALTA, "ALTA (I2S)" }, - { BCMA_CORE_4706_MAC_GBIT_COMMON, "BCM4706 GBit MAC Common" }, { BCMA_CORE_INVALID, "Invalid" }, { BCMA_CORE_CHIPCOMMON, "ChipCommon" }, { BCMA_CORE_ILINE20, "ILine 20" }, @@ -295,11 +295,15 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr, /* check if component is a core at all */ if (wrappers[0] + wrappers[1] == 0) { - /* we could save addrl of the router - if (cid == BCMA_CORE_OOB_ROUTER) - */ - bcma_erom_skip_component(bus, eromptr); - return -ENXIO; + /* Some specific cores don't need wrappers */ + switch (core->id.id) { + case BCMA_CORE_4706_MAC_GBIT_COMMON: + /* Not used yet: case BCMA_CORE_OOB_ROUTER: */ + break; + default: + bcma_erom_skip_component(bus, eromptr); + return -ENXIO; + } } if (bcma_erom_is_bridge(bus, eromptr)) { diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 03b2f30d2ace..1954a4e305a3 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -7,6 +7,7 @@ #include #include #include +#include #include /* SPROM sharing */ #include "bcma_regs.h" @@ -252,6 +253,7 @@ struct bcma_bus { struct bcma_drv_cc drv_cc; struct bcma_drv_pci drv_pci; struct bcma_drv_mips drv_mips; + struct bcma_drv_gmac_cmn drv_gmac_cmn; /* We decided to share SPROM struct with SSB as long as we do not need * any hacks for BCMA. This simplifies drivers code. */ diff --git a/include/linux/bcma/bcma_driver_gmac_cmn.h b/include/linux/bcma/bcma_driver_gmac_cmn.h new file mode 100644 index 000000000000..def894b83b0d --- /dev/null +++ b/include/linux/bcma/bcma_driver_gmac_cmn.h @@ -0,0 +1,100 @@ +#ifndef LINUX_BCMA_DRIVER_GMAC_CMN_H_ +#define LINUX_BCMA_DRIVER_GMAC_CMN_H_ + +#include + +#define BCMA_GMAC_CMN_STAG0 0x000 +#define BCMA_GMAC_CMN_STAG1 0x004 +#define BCMA_GMAC_CMN_STAG2 0x008 +#define BCMA_GMAC_CMN_STAG3 0x00C +#define BCMA_GMAC_CMN_PARSER_CTL 0x020 +#define BCMA_GMAC_CMN_MIB_MAX_LEN 0x024 +#define BCMA_GMAC_CMN_PHY_ACCESS 0x100 +#define BCMA_GMAC_CMN_PA_DATA_MASK 0x0000ffff +#define BCMA_GMAC_CMN_PA_ADDR_MASK 0x001f0000 +#define BCMA_GMAC_CMN_PA_ADDR_SHIFT 16 +#define BCMA_GMAC_CMN_PA_REG_MASK 0x1f000000 +#define BCMA_GMAC_CMN_PA_REG_SHIFT 24 +#define BCMA_GMAC_CMN_PA_WRITE 0x20000000 +#define BCMA_GMAC_CMN_PA_START 0x40000000 +#define BCMA_GMAC_CMN_PHY_CTL 0x104 +#define BCMA_GMAC_CMN_PC_EPA_MASK 0x0000001f +#define BCMA_GMAC_CMN_PC_MCT_MASK 0x007f0000 +#define BCMA_GMAC_CMN_PC_MCT_SHIFT 16 +#define BCMA_GMAC_CMN_PC_MTE 0x00800000 +#define BCMA_GMAC_CMN_GMAC0_RGMII_CTL 0x110 +#define BCMA_GMAC_CMN_CFP_ACCESS 0x200 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA0 0x210 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA1 0x214 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA2 0x218 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA3 0x21C +#define BCMA_GMAC_CMN_CFP_TCAM_DATA4 0x220 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA5 0x224 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA6 0x228 +#define BCMA_GMAC_CMN_CFP_TCAM_DATA7 0x22C +#define BCMA_GMAC_CMN_CFP_TCAM_MASK0 0x230 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK1 0x234 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK2 0x238 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK3 0x23C +#define BCMA_GMAC_CMN_CFP_TCAM_MASK4 0x240 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK5 0x244 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK6 0x248 +#define BCMA_GMAC_CMN_CFP_TCAM_MASK7 0x24C +#define BCMA_GMAC_CMN_CFP_ACTION_DATA 0x250 +#define BCMA_GMAC_CMN_TCAM_BIST_CTL 0x2A0 +#define BCMA_GMAC_CMN_TCAM_BIST_STATUS 0x2A4 +#define BCMA_GMAC_CMN_TCAM_CMP_STATUS 0x2A8 +#define BCMA_GMAC_CMN_TCAM_DISABLE 0x2AC +#define BCMA_GMAC_CMN_TCAM_TEST_CTL 0x2F0 +#define BCMA_GMAC_CMN_UDF_0_A3_A0 0x300 +#define BCMA_GMAC_CMN_UDF_0_A7_A4 0x304 +#define BCMA_GMAC_CMN_UDF_0_A8 0x308 +#define BCMA_GMAC_CMN_UDF_1_A3_A0 0x310 +#define BCMA_GMAC_CMN_UDF_1_A7_A4 0x314 +#define BCMA_GMAC_CMN_UDF_1_A8 0x318 +#define BCMA_GMAC_CMN_UDF_2_A3_A0 0x320 +#define BCMA_GMAC_CMN_UDF_2_A7_A4 0x324 +#define BCMA_GMAC_CMN_UDF_2_A8 0x328 +#define BCMA_GMAC_CMN_UDF_0_B3_B0 0x330 +#define BCMA_GMAC_CMN_UDF_0_B7_B4 0x334 +#define BCMA_GMAC_CMN_UDF_0_B8 0x338 +#define BCMA_GMAC_CMN_UDF_1_B3_B0 0x340 +#define BCMA_GMAC_CMN_UDF_1_B7_B4 0x344 +#define BCMA_GMAC_CMN_UDF_1_B8 0x348 +#define BCMA_GMAC_CMN_UDF_2_B3_B0 0x350 +#define BCMA_GMAC_CMN_UDF_2_B7_B4 0x354 +#define BCMA_GMAC_CMN_UDF_2_B8 0x358 +#define BCMA_GMAC_CMN_UDF_0_C3_C0 0x360 +#define BCMA_GMAC_CMN_UDF_0_C7_C4 0x364 +#define BCMA_GMAC_CMN_UDF_0_C8 0x368 +#define BCMA_GMAC_CMN_UDF_1_C3_C0 0x370 +#define BCMA_GMAC_CMN_UDF_1_C7_C4 0x374 +#define BCMA_GMAC_CMN_UDF_1_C8 0x378 +#define BCMA_GMAC_CMN_UDF_2_C3_C0 0x380 +#define BCMA_GMAC_CMN_UDF_2_C7_C4 0x384 +#define BCMA_GMAC_CMN_UDF_2_C8 0x388 +#define BCMA_GMAC_CMN_UDF_0_D3_D0 0x390 +#define BCMA_GMAC_CMN_UDF_0_D7_D4 0x394 +#define BCMA_GMAC_CMN_UDF_0_D11_D8 0x394 + +struct bcma_drv_gmac_cmn { + struct bcma_device *core; + + /* Drivers accessing BCMA_GMAC_CMN_PHY_ACCESS and + * BCMA_GMAC_CMN_PHY_CTL need to take that mutex first. */ + struct mutex phy_mutex; +}; + +/* Register access */ +#define gmac_cmn_read16(gc, offset) bcma_read16((gc)->core, offset) +#define gmac_cmn_read32(gc, offset) bcma_read32((gc)->core, offset) +#define gmac_cmn_write16(gc, offset, val) bcma_write16((gc)->core, offset, val) +#define gmac_cmn_write32(gc, offset, val) bcma_write32((gc)->core, offset, val) + +#ifdef CONFIG_BCMA_DRIVER_GMAC_CMN +extern void __devinit bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc); +#else +static inline void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc) { } +#endif + +#endif /* LINUX_BCMA_DRIVER_GMAC_CMN_H_ */ -- cgit v1.2.3 From 869dd4662f90514cb92b44a389e85c737b464e25 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Fri, 29 Jun 2012 00:50:24 -0400 Subject: tipc: remove print_buf and deprecated log buffer code The internal log buffer handling functions can now safely be removed since there is no code using it anymore. Requests to interact with the internal tipc log buffer over netlink (in config.c) will report 'obsolete command'. This represents the final removal of any references to a struct print_buf, and the removal of the struct itself. We also get rid of a TIPC specific Kconfig in the process. Finally, log.h is removed since it is not needed anymore. Signed-off-by: Erik Hugne Signed-off-by: Jon Maloy Signed-off-by: Paul Gortmaker --- include/linux/tipc_config.h | 4 +- net/tipc/Kconfig | 13 --- net/tipc/config.c | 8 +- net/tipc/core.c | 7 -- net/tipc/core.h | 27 ------ net/tipc/link.h | 1 - net/tipc/log.c | 213 -------------------------------------------- net/tipc/log.h | 66 -------------- 8 files changed, 4 insertions(+), 335 deletions(-) delete mode 100644 net/tipc/log.h (limited to 'include/linux') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 9730b0e51e46..c98928420100 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -102,8 +102,8 @@ #define TIPC_CMD_SET_LINK_TOL 0x4107 /* tx link_config, rx none */ #define TIPC_CMD_SET_LINK_PRI 0x4108 /* tx link_config, rx none */ #define TIPC_CMD_SET_LINK_WINDOW 0x4109 /* tx link_config, rx none */ -#define TIPC_CMD_SET_LOG_SIZE 0x410A /* tx unsigned, rx none */ -#define TIPC_CMD_DUMP_LOG 0x410B /* tx none, rx ultra_string */ +#define TIPC_CMD_SET_LOG_SIZE 0x410A /* obsoleted */ +#define TIPC_CMD_DUMP_LOG 0x410B /* obsoleted */ #define TIPC_CMD_RESET_LINK_STATS 0x410C /* tx link_name, rx none */ /* diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index e24519a54938..585460180ffb 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -41,17 +41,4 @@ config TIPC_PORTS Setting this to a smaller value saves some memory, setting it to higher allows for more ports. -config TIPC_LOG - int "Size of log buffer" - depends on TIPC_ADVANCED - range 0 32768 - default "0" - help - Size (in bytes) of TIPC's internal log buffer, which records the - occurrence of significant events. Can range from 0 to 32768 bytes; - default is 0. - - There is no need to enable the log buffer unless the node will be - managed remotely via TIPC. - endif # TIPC diff --git a/net/tipc/config.c b/net/tipc/config.c index 96cfbf834a10..a056a3852f71 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -334,12 +334,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SHOW_PORTS: rep_tlv_buf = tipc_port_get_ports(); break; - case TIPC_CMD_SET_LOG_SIZE: - rep_tlv_buf = tipc_log_resize_cmd(req_tlv_area, req_tlv_space); - break; - case TIPC_CMD_DUMP_LOG: - rep_tlv_buf = tipc_log_dump(); - break; case TIPC_CMD_SHOW_STATS: rep_tlv_buf = tipc_show_stats(); break; @@ -399,6 +393,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_GET_MAX_CLUSTERS: case TIPC_CMD_SET_MAX_NODES: case TIPC_CMD_GET_MAX_NODES: + case TIPC_CMD_SET_LOG_SIZE: + case TIPC_CMD_DUMP_LOG: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; diff --git a/net/tipc/core.c b/net/tipc/core.c index 3689cb4067c8..6586eac6a50e 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -46,9 +46,6 @@ #define CONFIG_TIPC_PORTS 8191 #endif -#ifndef CONFIG_TIPC_LOG -#define CONFIG_TIPC_LOG 0 -#endif /* global variables used by multiple sub-systems within TIPC */ int tipc_random; @@ -124,7 +121,6 @@ static void tipc_core_stop(void) tipc_nametbl_stop(); tipc_ref_table_stop(); tipc_socket_stop(); - tipc_log_resize(0); } /** @@ -160,9 +156,6 @@ static int __init tipc_init(void) { int res; - if (tipc_log_resize(CONFIG_TIPC_LOG) != 0) - pr_warn("Unable to create log buffer\n"); - pr_info("Activated (version " TIPC_MOD_VER ")\n"); tipc_own_addr = 0; diff --git a/net/tipc/core.h b/net/tipc/core.h index 4dcdb4859026..fd42e106c185 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -63,36 +63,9 @@ #define ULTRA_STRING_MAX_LEN 32768 struct tipc_msg; /* msg.h */ -struct print_buf; /* log.h */ - -/* - * TIPC system monitoring code - */ - -/* - * TIPC's print buffer subsystem supports the following print buffers: - * - * TIPC_NULL : null buffer (i.e. print nowhere) - * TIPC_CONS : system console - * TIPC_LOG : TIPC log buffer - * &buf : user-defined buffer (struct print_buf *) - * - * Note: TIPC_LOG is configured to echo its output to the system console; - * user-defined buffers can be configured to do the same thing. - */ -extern struct print_buf *const TIPC_NULL; -extern struct print_buf *const TIPC_CONS; -extern struct print_buf *const TIPC_LOG; int tipc_snprintf(char *buf, int len, const char *fmt, ...); -/* - * TIPC_OUTPUT is the destination print buffer for system messages. - */ -#ifndef TIPC_OUTPUT -#define TIPC_OUTPUT TIPC_LOG -#endif - /* * TIPC-specific error codes */ diff --git a/net/tipc/link.h b/net/tipc/link.h index 8024a56a1ebc..6e921121be06 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -37,7 +37,6 @@ #ifndef _TIPC_LINK_H #define _TIPC_LINK_H -#include "log.h" #include "msg.h" #include "node.h" diff --git a/net/tipc/log.c b/net/tipc/log.c index fa7ce927fda5..abef644f27d8 100644 --- a/net/tipc/log.c +++ b/net/tipc/log.c @@ -36,138 +36,6 @@ #include "core.h" #include "config.h" -#include "log.h" - -/* - * TIPC pre-defines the following print buffers: - * - * TIPC_NULL : null buffer (i.e. print nowhere) - * TIPC_CONS : system console - * TIPC_LOG : TIPC log buffer - * - * Additional user-defined print buffers are also permitted. - */ -static struct print_buf null_buf = { NULL, 0, NULL, 0 }; -struct print_buf *const TIPC_NULL = &null_buf; - -static struct print_buf cons_buf = { NULL, 0, NULL, 1 }; -struct print_buf *const TIPC_CONS = &cons_buf; - -static struct print_buf log_buf = { NULL, 0, NULL, 1 }; -struct print_buf *const TIPC_LOG = &log_buf; - -/* - * Locking policy when using print buffers. - * - * 1) tipc_printf() uses 'print_lock' to protect against concurrent access to - * 'print_string' when writing to a print buffer. This also protects against - * concurrent writes to the print buffer being written to. - * - * 2) tipc_log_XXX() leverages the aforementioned use of 'print_lock' to - * protect against all types of concurrent operations on their associated - * print buffer (not just write operations). - * - * Note: All routines of the form tipc_printbuf_XXX() are lock-free, and rely - * on the caller to prevent simultaneous use of the print buffer(s) being - * manipulated. - */ -static DEFINE_SPINLOCK(print_lock); - -static void tipc_printbuf_move(struct print_buf *pb_to, - struct print_buf *pb_from); - -/** - * tipc_printbuf_init - initialize print buffer to empty - * @pb: pointer to print buffer structure - * @raw: pointer to character array used by print buffer - * @size: size of character array - * - * Note: If the character array is too small (or absent), the print buffer - * becomes a null device that discards anything written to it. - */ -void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 size) -{ - pb->buf = raw; - pb->crs = raw; - pb->size = size; - pb->echo = 0; - - if (size < TIPC_PB_MIN_SIZE) { - pb->buf = NULL; - } else if (raw) { - pb->buf[0] = 0; - pb->buf[size - 1] = ~0; - } -} - -/** - * tipc_printbuf_reset - reinitialize print buffer to empty state - * @pb: pointer to print buffer structure - */ -static void tipc_printbuf_reset(struct print_buf *pb) -{ - if (pb->buf) { - pb->crs = pb->buf; - pb->buf[0] = 0; - pb->buf[pb->size - 1] = ~0; - } -} - -/** - * tipc_printbuf_empty - test if print buffer is in empty state - * @pb: pointer to print buffer structure - * - * Returns non-zero if print buffer is empty. - */ -static int tipc_printbuf_empty(struct print_buf *pb) -{ - return !pb->buf || (pb->crs == pb->buf); -} - -/** - * tipc_printbuf_move - move print buffer contents to another print buffer - * @pb_to: pointer to destination print buffer structure - * @pb_from: pointer to source print buffer structure - * - * Current contents of destination print buffer (if any) are discarded. - * Source print buffer becomes empty if a successful move occurs. - */ -static void tipc_printbuf_move(struct print_buf *pb_to, - struct print_buf *pb_from) -{ - int len; - - /* Handle the cases where contents can't be moved */ - if (!pb_to->buf) - return; - - if (!pb_from->buf) { - tipc_printbuf_reset(pb_to); - return; - } - - if (pb_to->size < pb_from->size) { - strcpy(pb_to->buf, "*** PRINT BUFFER MOVE ERROR ***"); - pb_to->buf[pb_to->size - 1] = ~0; - pb_to->crs = strchr(pb_to->buf, 0); - return; - } - - /* Copy data from char after cursor to end (if used) */ - len = pb_from->buf + pb_from->size - pb_from->crs - 2; - if ((pb_from->buf[pb_from->size - 1] == 0) && (len > 0)) { - strcpy(pb_to->buf, pb_from->crs + 1); - pb_to->crs = pb_to->buf + len; - } else - pb_to->crs = pb_to->buf; - - /* Copy data from start to cursor (always) */ - len = pb_from->crs - pb_from->buf; - strcpy(pb_to->crs, pb_from->buf); - pb_to->crs += len; - - tipc_printbuf_reset(pb_from); -} /** * tipc_snprintf - append formatted output to print buffer @@ -185,84 +53,3 @@ int tipc_snprintf(char *buf, int len, const char *fmt, ...) va_end(args); return i; } - -/** - * tipc_log_resize - change the size of the TIPC log buffer - * @log_size: print buffer size to use - */ -int tipc_log_resize(int log_size) -{ - int res = 0; - - spin_lock_bh(&print_lock); - kfree(TIPC_LOG->buf); - TIPC_LOG->buf = NULL; - if (log_size) { - if (log_size < TIPC_PB_MIN_SIZE) - log_size = TIPC_PB_MIN_SIZE; - res = TIPC_LOG->echo; - tipc_printbuf_init(TIPC_LOG, kmalloc(log_size, GFP_ATOMIC), - log_size); - TIPC_LOG->echo = res; - res = !TIPC_LOG->buf; - } - spin_unlock_bh(&print_lock); - - return res; -} - -/** - * tipc_log_resize_cmd - reconfigure size of TIPC log buffer - */ -struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, int req_tlv_space) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value > 32768) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (log size must be 0-32768)"); - if (tipc_log_resize(value)) - return tipc_cfg_reply_error_string( - "unable to create specified log (log size is now 0)"); - return tipc_cfg_reply_none(); -} - -/** - * tipc_log_dump - capture TIPC log buffer contents in configuration message - */ -struct sk_buff *tipc_log_dump(void) -{ - struct sk_buff *reply; - - spin_lock_bh(&print_lock); - if (!TIPC_LOG->buf) { - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_ultra_string("log not activated\n"); - } else if (tipc_printbuf_empty(TIPC_LOG)) { - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_ultra_string("log is empty\n"); - } else { - struct tlv_desc *rep_tlv; - struct print_buf pb; - int str_len; - - str_len = min(TIPC_LOG->size, 32768u); - spin_unlock_bh(&print_lock); - reply = tipc_cfg_reply_alloc(TLV_SPACE(str_len)); - if (reply) { - rep_tlv = (struct tlv_desc *)reply->data; - tipc_printbuf_init(&pb, TLV_DATA(rep_tlv), str_len); - spin_lock_bh(&print_lock); - tipc_printbuf_move(&pb, TIPC_LOG); - spin_unlock_bh(&print_lock); - str_len = strlen(TLV_DATA(rep_tlv)) + 1; - skb_put(reply, TLV_SPACE(str_len)); - TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); - } - } - return reply; -} diff --git a/net/tipc/log.h b/net/tipc/log.h deleted file mode 100644 index d1f5eb967fd8..000000000000 --- a/net/tipc/log.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * net/tipc/log.h: Include file for TIPC print buffer routines - * - * Copyright (c) 1997-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _TIPC_LOG_H -#define _TIPC_LOG_H - -/** - * struct print_buf - TIPC print buffer structure - * @buf: pointer to character array containing print buffer contents - * @size: size of character array - * @crs: pointer to first unused space in character array (i.e. final NUL) - * @echo: echo output to system console if non-zero - */ -struct print_buf { - char *buf; - u32 size; - char *crs; - int echo; -}; - -#define TIPC_PB_MIN_SIZE 64 /* minimum size for a print buffer's array */ -#define TIPC_PB_MAX_STR 512 /* max printable string (with trailing NUL) */ - -void tipc_printbuf_init(struct print_buf *pb, char *buf, u32 size); -int tipc_printbuf_validate(struct print_buf *pb); - -int tipc_log_resize(int log_size); - -struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, - int req_tlv_space); -struct sk_buff *tipc_log_dump(void); - -#endif -- cgit v1.2.3 From a6df1ae9383697c4eb1365176002f154982325ad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Jul 2012 01:41:36 +0000 Subject: tcp: add OFO snmp counters Add three SNMP TCP counters, to better track TCP behavior at global stage (netstat -s), when packets are received Out Of Order (OFO) TCPOFOQueue : Number of packets queued in OFO queue TCPOFODrop : Number of packets meant to be queued in OFO but dropped because socket rcvbuf limit hit. TCPOFOMerge : Number of packets in OFO that were merged with other packets. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 5 ++++- net/ipv4/proc.c | 3 +++ net/ipv4/tcp_input.c | 7 +++++-- 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 2e68f5ba0389..6e4c51123828 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -233,7 +233,10 @@ enum LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */ LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */ LINUX_MIB_TCPRETRANSFAIL, /* TCPRetransFail */ - LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */ + LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */ + LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */ + LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ + LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 8af0d44e4e22..dae25e7622cf 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -258,6 +258,9 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP), SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL), SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE), + SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE), + SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP), + SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 055ac49b8b40..cc4e12f1f2f7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4397,8 +4397,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_ECN_check_ce(tp, skb); - if (tcp_try_rmem_schedule(sk, skb->truesize)) { - /* TODO: should increment a counter */ + if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); __kfree_skb(skb); return; } @@ -4407,6 +4407,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tp->pred_flags = 0; inet_csk_schedule_ack(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); @@ -4460,6 +4461,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); __kfree_skb(skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); @@ -4498,6 +4500,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb1, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); __kfree_skb(skb1); } -- cgit v1.2.3 From 51d7cccf07238f5236c5b9269231a30dd5f8e714 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 16 Jul 2012 04:28:49 +0000 Subject: net: make sock diag per-namespace Before this patch sock_diag works for init_net only and dumps information about sockets from all namespaces. This patch expands sock_diag for all name-spaces. It creates a netlink kernel socket for each netns and filters data during dumping. v2: filter accoding with netns in all places remove an unused variable. Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Cc: Pavel Emelyanov CC: Eric Dumazet Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Andrew Vagin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 1 - include/net/net_namespace.h | 1 + net/core/sock_diag.c | 27 ++++++++++++++++++++------- net/ipv4/inet_diag.c | 21 ++++++++++++++++----- net/ipv4/udp_diag.c | 10 +++++++--- net/unix/diag.c | 9 +++++++-- 6 files changed, 51 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 6793fac5eab5..e3e395acc2fd 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -44,6 +44,5 @@ void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); -extern struct sock *sock_diag_nlsk; #endif /* KERNEL */ #endif diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ac9195e6a062..ae1cd6c9ba52 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -101,6 +101,7 @@ struct net { struct netns_xfrm xfrm; #endif struct netns_ipvs *ipvs; + struct sock *diag_nlsk; }; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 07a29eb34a41..9d8755e4a7a5 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -166,23 +166,36 @@ static void sock_diag_rcv(struct sk_buff *skb) mutex_unlock(&sock_diag_mutex); } -struct sock *sock_diag_nlsk; -EXPORT_SYMBOL_GPL(sock_diag_nlsk); - -static int __init sock_diag_init(void) +static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = sock_diag_rcv, }; - sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, THIS_MODULE, &cfg); - return sock_diag_nlsk == NULL ? -ENOMEM : 0; + return net->diag_nlsk == NULL ? -ENOMEM : 0; +} + +static void __net_exit diag_net_exit(struct net *net) +{ + netlink_kernel_release(net->diag_nlsk); + net->diag_nlsk = NULL; +} + +static struct pernet_operations diag_net_ops = { + .init = diag_net_init, + .exit = diag_net_exit, +}; + +static int __init sock_diag_init(void) +{ + return register_pernet_subsys(&diag_net_ops); } static void __exit sock_diag_exit(void) { - netlink_kernel_release(sock_diag_nlsk); + unregister_pernet_subsys(&diag_net_ops); } module_init(sock_diag_init); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 38064a285cca..570e61f9611f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -272,16 +272,17 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s int err; struct sock *sk; struct sk_buff *rep; + struct net *net = sock_net(in_skb->sk); err = -EINVAL; if (req->sdiag_family == AF_INET) { - sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0], + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); } #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { - sk = inet6_lookup(&init_net, hashinfo, + sk = inet6_lookup(net, hashinfo, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, @@ -317,7 +318,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s nlmsg_free(rep); goto out; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -724,6 +725,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, { int i, num; int s_i, s_num; + struct net *net = sock_net(skb->sk); s_i = cb->args[1]; s_num = num = cb->args[2]; @@ -743,6 +745,9 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, sk_nulls_for_each(sk, node, &ilb->head) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) { num++; continue; @@ -813,6 +818,8 @@ skip_listen_ht: sk_nulls_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next_normal; if (!(r->idiag_states & (1 << sk->sk_state))) @@ -839,6 +846,8 @@ next_normal: inet_twsk_for_each(tw, node, &head->twchain) { + if (!net_eq(twsk_net(tw), net)) + continue; if (num < s_num) goto next_dying; @@ -943,6 +952,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) { int hdrlen = sizeof(struct inet_diag_req); + struct net *net = sock_net(skb->sk); if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX || nlmsg_len(nlh) < hdrlen) @@ -963,7 +973,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) struct netlink_dump_control c = { .dump = inet_diag_dump_compat, }; - return netlink_dump_start(sock_diag_nlsk, skb, nlh, &c); + return netlink_dump_start(net->diag_nlsk, skb, nlh, &c); } } @@ -973,6 +983,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); + struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; @@ -991,7 +1002,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) struct netlink_dump_control c = { .dump = inet_diag_dump, }; - return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + return netlink_dump_start(net->diag_nlsk, skb, h, &c); } } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index a7f86a3cd502..16d0960062be 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -34,15 +34,16 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, int err = -EINVAL; struct sock *sk; struct sk_buff *rep; + struct net *net = sock_net(in_skb->sk); if (req->sdiag_family == AF_INET) - sk = __udp4_lib_lookup(&init_net, + sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_if, tbl); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) - sk = __udp6_lib_lookup(&init_net, + sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, @@ -75,7 +76,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, kfree_skb(rep); goto out; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -90,6 +91,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin struct inet_diag_req_v2 *r, struct nlattr *bc) { int num, s_num, slot, s_slot; + struct net *net = sock_net(skb->sk); s_slot = cb->args[0]; num = s_num = cb->args[1]; @@ -106,6 +108,8 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin sk_nulls_for_each(sk, node, &hslot->head) { struct inet_sock *inet = inet_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next; if (!(r->idiag_states & (1 << sk->sk_state))) diff --git a/net/unix/diag.c b/net/unix/diag.c index a74864eedfcd..750b13408449 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -177,6 +177,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct unix_diag_req *req; int num, s_num, slot, s_slot; + struct net *net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); @@ -192,6 +193,8 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) num = 0; sk_for_each(sk, node, &unix_socket_table[slot]) { + if (!net_eq(sock_net(sk), net)) + continue; if (num < s_num) goto next; if (!(req->udiag_states & (1 << sk->sk_state))) @@ -243,6 +246,7 @@ static int unix_diag_get_exact(struct sk_buff *in_skb, struct sock *sk; struct sk_buff *rep; unsigned int extra_len; + struct net *net = sock_net(in_skb->sk); if (req->udiag_ino == 0) goto out_nosk; @@ -273,7 +277,7 @@ again: goto again; } - err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -287,6 +291,7 @@ out_nosk: static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct unix_diag_req); + struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; @@ -295,7 +300,7 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) struct netlink_dump_control c = { .dump = unix_diag_dump, }; - return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + return netlink_dump_start(net->diag_nlsk, skb, h, &c); } else return unix_diag_get_exact(skb, h, nlmsg_data(h)); } -- cgit v1.2.3 From 0a4dd594982a321699000218715e28664ec49169 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 12 Jul 2012 19:33:05 +0000 Subject: etherdevice: Rename random_ether_addr to eth_random_addr Add some API symmetry to eth_broadcast_addr and add a #define to the old name for backward compatibility. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 98a27cccedfd..d426336d92d9 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -124,19 +124,21 @@ static inline bool is_valid_ether_addr(const u8 *addr) } /** - * random_ether_addr - Generate software assigned random Ethernet address + * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ -static inline void random_ether_addr(u8 *addr) +static inline void eth_random_addr(u8 *addr) { - get_random_bytes (addr, ETH_ALEN); - addr [0] &= 0xfe; /* clear multicast bit */ - addr [0] |= 0x02; /* set local assignment bit (IEEE802) */ + get_random_bytes(addr, ETH_ALEN); + addr[0] &= 0xfe; /* clear multicast bit */ + addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } +#define random_ether_addr(addr) eth_random_addr(addr) + /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address @@ -160,7 +162,7 @@ static inline void eth_broadcast_addr(u8 *addr) static inline void eth_hw_addr_random(struct net_device *dev) { dev->addr_assign_type |= NET_ADDR_RANDOM; - random_ether_addr(dev->dev_addr); + eth_random_addr(dev->dev_addr); } /** -- cgit v1.2.3 From 282f23c6ee343126156dd41218b22ece96d747e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Jul 2012 10:13:05 +0200 Subject: tcp: implement RFC 5961 3.2 Implement the RFC 5691 mitigation against Blind Reset attack using RST bit. Idea is to validate incoming RST sequence, to match RCV.NXT value, instead of previouly accepted window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND) If sequence is in window but not an exact match, send a "challenge ACK", so that the other part can resend an RST with the appropriate sequence. Add a new sysctl, tcp_challenge_ack_limit, to limit number of challenge ACK sent per second. Add a new SNMP counter to count number of challenge acks sent. (netstat -s | grep TCPChallengeACK) Signed-off-by: Eric Dumazet Cc: Kiran Kumar Kella Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 +++++ include/linux/snmp.h | 1 + include/net/tcp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/sysctl_net_ipv4.c | 7 +++++++ net/ipv4/tcp_input.c | 31 ++++++++++++++++++++++++++++++- 6 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e20c17a7d34e..e1e021594cff 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -565,6 +565,11 @@ tcp_limit_output_bytes - INTEGER reduce the size of individual GSO packet (64KB being the max) Default: 131072 +tcp_challenge_ack_limit - INTEGER + Limits number of Challenge ACK sent per second, as recommended + in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks) + Default: 100 + UDP variables: udp_mem - vector of 3 INTEGERs: min, pressure, max diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 6e4c51123828..673e0e928b2b 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -237,6 +237,7 @@ enum LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */ LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ + LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ __LINUX_MIB_MAX }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 439984b9af49..85c5090bfe25 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -254,6 +254,7 @@ extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; +extern int sysctl_tcp_challenge_ack_limit; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index dae25e7622cf..3e8e78f12a38 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -261,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE), SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP), SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), + SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 70730f7aeafe..3f6a1e762e9c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -605,6 +605,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_challenge_ack_limit", + .data = &sysctl_tcp_challenge_ack_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, #ifdef CONFIG_NET_DMA { .procname = "tcp_dma_copybreak", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cc4e12f1f2f7..c841a8990377 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -88,6 +88,9 @@ int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); +/* rfc5961 challenge ack rate limiting */ +int sysctl_tcp_challenge_ack_limit = 100; + int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -5247,6 +5250,23 @@ out: } #endif /* CONFIG_NET_DMA */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5283,7 +5303,16 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, /* Step 2: check RST bit */ if (th->rst) { - tcp_reset(sk); + /* RFC 5961 3.2 : + * If sequence number exactly matches RCV.NXT, then + * RESET the connection + * else + * Send a challenge ACK + */ + if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) + tcp_reset(sk); + else + tcp_send_challenge_ack(sk); goto discard; } -- cgit v1.2.3 From 84f10708f73254878246772cead70a2eb6a123f2 Mon Sep 17 00:00:00 2001 From: Thomas Pedersen Date: Thu, 12 Jul 2012 16:17:33 -0700 Subject: cfg80211: support TX error rate CQM Let the user configure serveral TX error conection quality monitoring parameters: % error rate, survey interval, and # of attempted packets. On exceeding the TX failure rate over the given interval, the driver will send a CQM notify event with the actual TX failure rate and packets attempted. Signed-off-by: Thomas Pedersen Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 16 ++++++++++ include/net/cfg80211.h | 21 ++++++++++++ net/wireless/mlme.c | 13 ++++++++ net/wireless/nl80211.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.h | 5 +++ 5 files changed, 140 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index e791487ead37..d6cfacc3ce4d 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1550,6 +1550,8 @@ enum nl80211_attrs { /* default RSSI threshold for scan results if none specified. */ #define NL80211_SCAN_RSSI_THOLD_OFF -300 +#define NL80211_CQM_TXE_MAX_INTVL 1800 + /** * enum nl80211_iftype - (virtual) interface types * @@ -2589,6 +2591,17 @@ enum nl80211_ps_state { * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event * @NL80211_ATTR_CQM_PKT_LOSS_EVENT: a u32 value indicating that this many * consecutive packets were not acknowledged by the peer + * @NL80211_ATTR_CQM_TXE_RATE: TX error rate in %. Minimum % of TX failures + * during the given %NL80211_ATTR_CQM_TXE_INTVL before an + * %NL80211_CMD_NOTIFY_CQM with reported %NL80211_ATTR_CQM_TXE_RATE and + * %NL80211_ATTR_CQM_TXE_PKTS is generated. + * @NL80211_ATTR_CQM_TXE_PKTS: number of attempted packets in a given + * %NL80211_ATTR_CQM_TXE_INTVL before %NL80211_ATTR_CQM_TXE_RATE is + * checked. + * @NL80211_ATTR_CQM_TXE_INTVL: interval in seconds. Specifies the periodic + * interval in which %NL80211_ATTR_CQM_TXE_PKTS and + * %NL80211_ATTR_CQM_TXE_RATE must be satisfied before generating an + * %NL80211_CMD_NOTIFY_CQM. Set to 0 to turn off TX error reporting. * @__NL80211_ATTR_CQM_AFTER_LAST: internal * @NL80211_ATTR_CQM_MAX: highest key attribute */ @@ -2598,6 +2611,9 @@ enum nl80211_attr_cqm { NL80211_ATTR_CQM_RSSI_HYST, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, NL80211_ATTR_CQM_PKT_LOSS_EVENT, + NL80211_ATTR_CQM_TXE_RATE, + NL80211_ATTR_CQM_TXE_PKTS, + NL80211_ATTR_CQM_TXE_INTVL, /* keep last */ __NL80211_ATTR_CQM_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0245208c2978..493fa0c79005 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1573,6 +1573,8 @@ struct cfg80211_gtk_rekey_data { * @set_power_mgmt: Configure WLAN power management. A timeout value of -1 * allows the driver to adjust the dynamic ps timeout value. * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. + * @set_cqm_txe_config: Configure connection quality monitor TX error + * thresholds. * @sched_scan_start: Tell the driver to start a scheduled scan. * @sched_scan_stop: Tell the driver to stop an ongoing scheduled * scan. The driver_initiated flag specifies whether the driver @@ -1783,6 +1785,10 @@ struct cfg80211_ops { struct net_device *dev, s32 rssi_thold, u32 rssi_hyst); + int (*set_cqm_txe_config)(struct wiphy *wiphy, + struct net_device *dev, + u32 rate, u32 pkts, u32 intvl); + void (*mgmt_frame_register)(struct wiphy *wiphy, struct wireless_dev *wdev, u16 frame_type, bool reg); @@ -3395,6 +3401,21 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, void cfg80211_cqm_pktloss_notify(struct net_device *dev, const u8 *peer, u32 num_packets, gfp_t gfp); +/** + * cfg80211_cqm_txe_notify - TX error rate event + * @dev: network device + * @peer: peer's MAC address + * @num_packets: how many packets were lost + * @rate: % of packets which failed transmission + * @intvl: interval (in s) over which the TX failure threshold was breached. + * @gfp: context flags + * + * Notify userspace when configured % TX failures over number of packets in a + * given interval is exceeded. + */ +void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, + u32 num_packets, u32 rate, u32 intvl, gfp_t gfp); + /** * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying * @dev: network device diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index abe9f82d5a82..1cdb1d5e6b0f 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -919,6 +919,19 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev, } EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify); +void cfg80211_cqm_txe_notify(struct net_device *dev, + const u8 *peer, u32 num_packets, + u32 rate, u32 intvl, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_send_cqm_txe_notify(rdev, dev, peer, num_packets, + rate, intvl, gfp); +} +EXPORT_SYMBOL(cfg80211_cqm_txe_notify); + void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index be8750f91d78..9216e45e53a0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6267,8 +6267,35 @@ nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { [NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_RATE] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_PKTS] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_TXE_INTVL] = { .type = NLA_U32 }, }; +static int nl80211_set_cqm_txe(struct genl_info *info, + u32 rate, u32 pkts, u32 intvl) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev; + struct net_device *dev = info->user_ptr[1]; + + if ((rate < 0 || rate > 100) || + (intvl < 0 || intvl > NL80211_CQM_TXE_MAX_INTVL)) + return -EINVAL; + + wdev = dev->ieee80211_ptr; + + if (!rdev->ops->set_cqm_txe_config) + return -EOPNOTSUPP; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + return rdev->ops->set_cqm_txe_config(wdev->wiphy, dev, + rate, pkts, intvl); +} + static int nl80211_set_cqm_rssi(struct genl_info *info, s32 threshold, u32 hysteresis) { @@ -6316,6 +6343,14 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info) threshold = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_THOLD]); hysteresis = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_HYST]); err = nl80211_set_cqm_rssi(info, threshold, hysteresis); + } else if (attrs[NL80211_ATTR_CQM_TXE_RATE] && + attrs[NL80211_ATTR_CQM_TXE_PKTS] && + attrs[NL80211_ATTR_CQM_TXE_INTVL]) { + u32 rate, pkts, intvl; + rate = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_RATE]); + pkts = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_PKTS]); + intvl = nla_get_u32(attrs[NL80211_ATTR_CQM_TXE_INTVL]); + err = nl80211_set_cqm_txe(info, rate, pkts, intvl); } else err = -EINVAL; @@ -8495,6 +8530,56 @@ void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void +nl80211_send_cqm_txe_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, u32 rate, u32 intvl, gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *pinfoattr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer)) + goto nla_put_failure; + + pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); + if (!pinfoattr) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_PKTS, num_packets)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_RATE, rate)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_CQM_TXE_INTVL, intvl)) + goto nla_put_failure; + + nla_nest_end(msg, pinfoattr); + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 89ce99675e61..9f2616fffb40 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -110,6 +110,11 @@ nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, u32 num_packets, gfp_t gfp); +void +nl80211_send_cqm_txe_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *peer, + u32 num_packets, u32 rate, u32 intvl, gfp_t gfp); + void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp); -- cgit v1.2.3 From 57b5ce072e7361218a8e2ea1d62960cbb71d9cff Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Thu, 12 Jul 2012 11:49:18 -0700 Subject: cfg80211: add cellular base station regulatory hint support Cellular base stations can provide hints to cfg80211 about where they think we are. This can be done for example on a cell phone. To enable these hints we simply allow them through as user regulatory hints but we allow userspace to clasify the hint as either coming directly from the user or coming from a cellular base station. This option is only available when you enable CONFIG_CFG80211_CERTIFICATION_ONUS. The base station hints themselves will not be processed by the core unless at least one device on the system supports this feature. Signed-off-by: Luis R. Rodriguez Signed-off-by: Johannes Berg --- include/linux/nl80211.h | 32 ++++++++++++++ include/net/regulatory.h | 5 +++ net/wireless/core.c | 1 + net/wireless/nl80211.c | 23 +++++++++- net/wireless/reg.c | 113 ++++++++++++++++++++++++++++++++++++++++++++--- net/wireless/reg.h | 5 ++- 6 files changed, 171 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index d6cfacc3ce4d..2f3878806403 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1245,6 +1245,12 @@ enum nl80211_commands { * @NL80211_ATTR_BG_SCAN_PERIOD: Background scan period in seconds * or 0 to disable background scan. * + * @NL80211_ATTR_USER_REG_HINT_TYPE: type of regulatory hint passed from + * userspace. If unset it is assumed the hint comes directly from + * a user. If set code could specify exactly what type of source + * was used to provide the hint. For the different types of + * allowed user regulatory hints see nl80211_user_reg_hint_type. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1498,6 +1504,8 @@ enum nl80211_attrs { NL80211_ATTR_WDEV, + NL80211_ATTR_USER_REG_HINT_TYPE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2060,6 +2068,26 @@ enum nl80211_dfs_regions { NL80211_DFS_JP = 3, }; +/** + * enum nl80211_user_reg_hint_type - type of user regulatory hint + * + * @NL80211_USER_REG_HINT_USER: a user sent the hint. This is always + * assumed if the attribute is not set. + * @NL80211_USER_REG_HINT_CELL_BASE: the hint comes from a cellular + * base station. Device drivers that have been tested to work + * properly to support this type of hint can enable these hints + * by setting the NL80211_FEATURE_CELL_BASE_REG_HINTS feature + * capability on the struct wiphy. The wireless core will + * ignore all cell base station hints until at least one device + * present has been registered with the wireless core that + * has listed NL80211_FEATURE_CELL_BASE_REG_HINTS as a + * supported feature. + */ +enum nl80211_user_reg_hint_type { + NL80211_USER_REG_HINT_USER = 0, + NL80211_USER_REG_HINT_CELL_BASE = 1, +}; + /** * enum nl80211_survey_info - survey information * @@ -2963,11 +2991,15 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_HT_IBSS: This driver supports IBSS with HT datarates. * @NL80211_FEATURE_INACTIVITY_TIMER: This driver takes care of freeing up * the connected inactive stations in AP mode. + * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested + * to work properly to suppport receiving regulatory hints from + * cellular base stations. */ enum nl80211_feature_flags { NL80211_FEATURE_SK_TX_STATUS = 1 << 0, NL80211_FEATURE_HT_IBSS = 1 << 1, NL80211_FEATURE_INACTIVITY_TIMER = 1 << 2, + NL80211_FEATURE_CELL_BASE_REG_HINTS = 1 << 3, }; /** diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a5f79933e211..7dcaa2794fde 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -52,6 +52,10 @@ enum environment_cap { * DFS master operation on a known DFS region (NL80211_DFS_*), * dfs_region represents that region. Drivers can use this and the * @alpha2 to adjust their device's DFS parameters as required. + * @user_reg_hint_type: if the @initiator was of type + * %NL80211_REGDOM_SET_BY_USER, this classifies the type + * of hint passed. This could be any of the %NL80211_USER_REG_HINT_* + * types. * @intersect: indicates whether the wireless core should intersect * the requested regulatory domain with the presently set regulatory * domain. @@ -70,6 +74,7 @@ enum environment_cap { struct regulatory_request { int wiphy_idx; enum nl80211_reg_initiator initiator; + enum nl80211_user_reg_hint_type user_reg_hint_type; char alpha2[2]; u8 dfs_region; bool intersect; diff --git a/net/wireless/core.c b/net/wireless/core.c index 71b684b5a675..c0307b05986c 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -542,6 +542,7 @@ int wiphy_register(struct wiphy *wiphy) } /* set up regulatory info */ + wiphy_regulatory_register(wiphy); regulatory_update(wiphy, NL80211_REGDOM_SET_BY_CORE); list_add_rcu(&rdev->list, &cfg80211_rdev_list); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9216e45e53a0..50b1a0e84f1a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -354,6 +354,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_INACTIVITY_TIMEOUT] = { .type = NLA_U16 }, [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, + [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -3582,6 +3583,7 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) { int r; char *data = NULL; + enum nl80211_user_reg_hint_type user_reg_hint_type; /* * You should only get this when cfg80211 hasn't yet initialized @@ -3601,7 +3603,21 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]); - r = regulatory_hint_user(data); + if (info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]) + user_reg_hint_type = + nla_get_u32(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]); + else + user_reg_hint_type = NL80211_USER_REG_HINT_USER; + + switch (user_reg_hint_type) { + case NL80211_USER_REG_HINT_USER: + case NL80211_USER_REG_HINT_CELL_BASE: + break; + default: + return -EINVAL; + } + + r = regulatory_hint_user(data, user_reg_hint_type); return r; } @@ -3971,6 +3987,11 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) cfg80211_regdomain->dfs_region))) goto nla_put_failure; + if (reg_last_request_cell_base() && + nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE, + NL80211_USER_REG_HINT_CELL_BASE)) + goto nla_put_failure; + nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) goto nla_put_failure; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index ad6f9029c564..83583a9c15d9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -97,9 +97,16 @@ const struct ieee80211_regdomain *cfg80211_regdomain; * - cfg80211_world_regdom * - cfg80211_regdom * - last_request + * - reg_num_devs_support_basehint */ static DEFINE_MUTEX(reg_mutex); +/* + * Number of devices that registered to the core + * that support cellular base station regulatory hints + */ +static int reg_num_devs_support_basehint; + static inline void assert_reg_lock(void) { lockdep_assert_held(®_mutex); @@ -911,6 +918,59 @@ static void handle_band(struct wiphy *wiphy, handle_channel(wiphy, initiator, band, i); } +static bool reg_request_cell_base(struct regulatory_request *request) +{ + if (request->initiator != NL80211_REGDOM_SET_BY_USER) + return false; + if (request->user_reg_hint_type != NL80211_USER_REG_HINT_CELL_BASE) + return false; + return true; +} + +bool reg_last_request_cell_base(void) +{ + assert_cfg80211_lock(); + + mutex_lock(®_mutex); + return reg_request_cell_base(last_request); + mutex_unlock(®_mutex); +} + +#ifdef CONFIG_CFG80211_CERTIFICATION_ONUS + +/* Core specific check */ +static int reg_ignore_cell_hint(struct regulatory_request *pending_request) +{ + if (!reg_num_devs_support_basehint) + return -EOPNOTSUPP; + + if (reg_request_cell_base(last_request)) { + if (!regdom_changes(pending_request->alpha2)) + return -EALREADY; + return 0; + } + return 0; +} + +/* Device specific check */ +static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) +{ + if (!(wiphy->features & NL80211_FEATURE_CELL_BASE_REG_HINTS)) + return true; + return false; +} +#else +static int reg_ignore_cell_hint(struct regulatory_request *pending_request) +{ + return -EOPNOTSUPP; +} +static int reg_dev_ignore_cell_hint(struct wiphy *wiphy) +{ + return true; +} +#endif + + static bool ignore_reg_update(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { @@ -944,6 +1004,9 @@ static bool ignore_reg_update(struct wiphy *wiphy, return true; } + if (reg_request_cell_base(last_request)) + return reg_dev_ignore_cell_hint(wiphy); + return false; } @@ -1307,6 +1370,13 @@ static int ignore_request(struct wiphy *wiphy, return 0; case NL80211_REGDOM_SET_BY_COUNTRY_IE: + if (reg_request_cell_base(last_request)) { + /* Trust a Cell base station over the AP's country IE */ + if (regdom_changes(pending_request->alpha2)) + return -EOPNOTSUPP; + return -EALREADY; + } + last_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); if (unlikely(!is_an_alpha2(pending_request->alpha2))) @@ -1351,6 +1421,12 @@ static int ignore_request(struct wiphy *wiphy, return REG_INTERSECT; case NL80211_REGDOM_SET_BY_USER: + if (reg_request_cell_base(pending_request)) + return reg_ignore_cell_hint(pending_request); + + if (reg_request_cell_base(last_request)) + return -EOPNOTSUPP; + if (last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) return REG_INTERSECT; /* @@ -1640,7 +1716,8 @@ static int regulatory_hint_core(const char *alpha2) } /* User hints */ -int regulatory_hint_user(const char *alpha2) +int regulatory_hint_user(const char *alpha2, + enum nl80211_user_reg_hint_type user_reg_hint_type) { struct regulatory_request *request; @@ -1654,6 +1731,7 @@ int regulatory_hint_user(const char *alpha2) request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_USER; + request->user_reg_hint_type = user_reg_hint_type; queue_regulatory_request(request); @@ -1906,7 +1984,7 @@ static void restore_regulatory_settings(bool reset_user) * settings, user regulatory settings takes precedence. */ if (is_an_alpha2(alpha2)) - regulatory_hint_user(user_alpha2); + regulatory_hint_user(user_alpha2, NL80211_USER_REG_HINT_USER); if (list_empty(&tmp_reg_req_list)) return; @@ -2081,9 +2159,16 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) else { if (is_unknown_alpha2(rd->alpha2)) pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); - else - pr_info("Regulatory domain changed to country: %c%c\n", - rd->alpha2[0], rd->alpha2[1]); + else { + if (reg_request_cell_base(last_request)) + pr_info("Regulatory domain changed " + "to country: %c%c by Cell Station\n", + rd->alpha2[0], rd->alpha2[1]); + else + pr_info("Regulatory domain changed " + "to country: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); + } } print_dfs_region(rd->dfs_region); print_rd_rules(rd); @@ -2293,6 +2378,18 @@ int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) } #endif /* CONFIG_HOTPLUG */ +void wiphy_regulatory_register(struct wiphy *wiphy) +{ + assert_cfg80211_lock(); + + mutex_lock(®_mutex); + + if (!reg_dev_ignore_cell_hint(wiphy)) + reg_num_devs_support_basehint++; + + mutex_unlock(®_mutex); +} + /* Caller must hold cfg80211_mutex */ void reg_device_remove(struct wiphy *wiphy) { @@ -2302,6 +2399,9 @@ void reg_device_remove(struct wiphy *wiphy) mutex_lock(®_mutex); + if (!reg_dev_ignore_cell_hint(wiphy)) + reg_num_devs_support_basehint--; + kfree(wiphy->regd); if (last_request) @@ -2367,7 +2467,8 @@ int __init regulatory_init(void) * as a user hint. */ if (!is_world_regdom(ieee80211_regdom)) - regulatory_hint_user(ieee80211_regdom); + regulatory_hint_user(ieee80211_regdom, + NL80211_USER_REG_HINT_USER); return 0; } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index e2aaaf525a22..519492fdda3c 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -22,9 +22,11 @@ bool is_world_regdom(const char *alpha2); bool reg_is_valid_request(const char *alpha2); bool reg_supported_dfs_region(u8 dfs_region); -int regulatory_hint_user(const char *alpha2); +int regulatory_hint_user(const char *alpha2, + enum nl80211_user_reg_hint_type user_reg_hint_type); int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env); +void wiphy_regulatory_register(struct wiphy *wiphy); void reg_device_remove(struct wiphy *wiphy); int __init regulatory_init(void); @@ -33,6 +35,7 @@ void regulatory_exit(void); int set_regdom(const struct ieee80211_regdomain *rd); void regulatory_update(struct wiphy *wiphy, enum nl80211_reg_initiator setby); +bool reg_last_request_cell_base(void); /** * regulatory_hint_found_beacon - hints a beacon was found on a channel -- cgit v1.2.3 From 0c24604b68fc7810d429d6c3657b6f148270e528 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Jul 2012 01:41:30 +0000 Subject: tcp: implement RFC 5961 4.2 Implement the RFC 5691 mitigation against Blind Reset attack using SYN bit. Section 4.2 of RFC 5961 advises to send a Challenge ACK and drop incoming packet, instead of resetting the session. Add a new SNMP counter to count number of challenge acks sent in response to SYN packets. (netstat -s | grep TCPSYNChallenge) Remove obsolete TCPAbortOnSyn, since we no longer abort a TCP session because of a SYN flag. Signed-off-by: Eric Dumazet Cc: Kiran Kumar Kella Signed-off-by: David S. Miller --- include/linux/snmp.h | 2 +- net/ipv4/proc.c | 2 +- net/ipv4/tcp_input.c | 32 +++++++++++++++----------------- 3 files changed, 17 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 673e0e928b2b..e5fcbd079e4a 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -208,7 +208,6 @@ enum LINUX_MIB_TCPDSACKOFOSENT, /* TCPDSACKOfoSent */ LINUX_MIB_TCPDSACKRECV, /* TCPDSACKRecv */ LINUX_MIB_TCPDSACKOFORECV, /* TCPDSACKOfoRecv */ - LINUX_MIB_TCPABORTONSYN, /* TCPAbortOnSyn */ LINUX_MIB_TCPABORTONDATA, /* TCPAbortOnData */ LINUX_MIB_TCPABORTONCLOSE, /* TCPAbortOnClose */ LINUX_MIB_TCPABORTONMEMORY, /* TCPAbortOnMemory */ @@ -238,6 +237,7 @@ enum LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ + LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 3e8e78f12a38..2a5240b2ea61 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -232,7 +232,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT), SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV), SNMP_MIB_ITEM("TCPDSACKOfoRecv", LINUX_MIB_TCPDSACKOFORECV), - SNMP_MIB_ITEM("TCPAbortOnSyn", LINUX_MIB_TCPABORTONSYN), SNMP_MIB_ITEM("TCPAbortOnData", LINUX_MIB_TCPABORTONDATA), SNMP_MIB_ITEM("TCPAbortOnClose", LINUX_MIB_TCPABORTONCLOSE), SNMP_MIB_ITEM("TCPAbortOnMemory", LINUX_MIB_TCPABORTONMEMORY), @@ -262,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP), SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), + SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c841a8990377..8aaec5536111 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5270,8 +5270,8 @@ static void tcp_send_challenge_ack(struct sock *sk) /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ -static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, int syn_inerr) +static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, + const struct tcphdr *th, int syn_inerr) { const u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); @@ -5323,20 +5323,22 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, /* step 3: check security and precedence [ignored] */ - /* step 4: Check for a SYN in window. */ - if (th->syn && !before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { + /* step 4: Check for a SYN + * RFC 5691 4.2 : Send a challenge ack + */ + if (th->syn) { if (syn_inerr) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONSYN); - tcp_reset(sk); - return -1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); + tcp_send_challenge_ack(sk); + goto discard; } - return 1; + return true; discard: __kfree_skb(skb); - return 0; + return false; } /* @@ -5366,7 +5368,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); - int res; if (sk->sk_rx_dst) { struct dst_entry *dst = sk->sk_rx_dst; @@ -5555,9 +5556,8 @@ slow_path: * Standard slow path. */ - res = tcp_validate_incoming(sk, skb, th, 1); - if (res <= 0) - return -res; + if (!tcp_validate_incoming(sk, skb, th, 1)) + return 0; step5: if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) @@ -5877,7 +5877,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int queued = 0; - int res; tp->rx_opt.saw_tstamp = 0; @@ -5932,9 +5931,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 0; } - res = tcp_validate_incoming(sk, skb, th, 0); - if (res <= 0) - return -res; + if (!tcp_validate_incoming(sk, skb, th, 0)) + return 0; /* step 5: check the ACK field */ if (th->ack) { -- cgit v1.2.3 From 30fdd8a082a00126a6feec994e43e8dc12f5bccb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 17 Jul 2012 05:22:35 +0000 Subject: netpoll: move np->dev and np->dev_name init into __netpoll_setup() Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 4 +--- include/linux/netpoll.h | 2 +- net/8021q/vlan_dev.c | 5 +---- net/bridge/br_device.c | 5 +---- net/core/netpoll.c | 10 +++++----- 5 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4ddcc3e41dab..1eb3979d0af5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1240,9 +1240,7 @@ static inline int slave_enable_netpoll(struct slave *slave) if (!np) goto out; - np->dev = slave->dev; - strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ); - err = __netpoll_setup(np); + err = __netpoll_setup(np, slave->dev); if (err) { kfree(np); goto out; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 5dfa091c3347..28f5389c924b 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -43,7 +43,7 @@ struct netpoll_info { void netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); -int __netpoll_setup(struct netpoll *np); +int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); int netpoll_trap(void); void netpoll_set_trap(int trap); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index da1bc9c3cf38..73a2a83ee2da 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -681,10 +681,7 @@ static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *n if (!netpoll) goto out; - netpoll->dev = real_dev; - strlcpy(netpoll->dev_name, real_dev->name, IFNAMSIZ); - - err = __netpoll_setup(netpoll); + err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 929e48aed444..f4be1bbfef26 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -246,10 +246,7 @@ int br_netpoll_enable(struct net_bridge_port *p) if (!np) goto out; - np->dev = p->dev; - strlcpy(np->dev_name, p->dev->name, IFNAMSIZ); - - err = __netpoll_setup(np); + err = __netpoll_setup(np, p->dev); if (err) { kfree(np); goto out; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index f9f40b932e4b..b4c90e42b443 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -715,14 +715,16 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { - struct net_device *ndev = np->dev; struct netpoll_info *npinfo; const struct net_device_ops *ops; unsigned long flags; int err; + np->dev = ndev; + strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { np_err(np, "%s doesn't support polling, aborting\n", @@ -851,13 +853,11 @@ int netpoll_setup(struct netpoll *np) np_info(np, "local IP %pI4\n", &np->local_ip); } - np->dev = ndev; - /* fill up the skb queue */ refill_skbs(); rtnl_lock(); - err = __netpoll_setup(np); + err = __netpoll_setup(np, ndev); rtnl_unlock(); if (err) -- cgit v1.2.3 From bd2d0837abc0206ecdd3f6b9fc8c25b55b63c96b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 17 Jul 2012 05:22:36 +0000 Subject: team: add netpoll support It's done in very similar way this is done in bonding and bridge. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 113 ++++++++++++++++++++++++++++++ drivers/net/team/team_mode_activebackup.c | 3 +- drivers/net/team/team_mode_broadcast.c | 7 +- drivers/net/team/team_mode_loadbalance.c | 3 +- drivers/net/team/team_mode_roundrobin.c | 3 +- include/linux/if_team.h | 33 +++++++++ 6 files changed, 152 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 3620c63f9345..1a13470dee07 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -787,6 +788,58 @@ static void team_port_leave(struct team *team, struct team_port *port) dev_put(team->dev); } +#ifdef CONFIG_NET_POLL_CONTROLLER +static int team_port_enable_netpoll(struct team *team, struct team_port *port) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*np), GFP_KERNEL); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, port->dev); + if (err) { + kfree(np); + return err; + } + port->np = np; + return err; +} + +static void team_port_disable_netpoll(struct team_port *port) +{ + struct netpoll *np = port->np; + + if (!np) + return; + port->np = NULL; + + /* Wait for transmitting packets to finish before freeing. */ + synchronize_rcu_bh(); + __netpoll_cleanup(np); + kfree(np); +} + +static struct netpoll_info *team_netpoll_info(struct team *team) +{ + return team->dev->npinfo; +} + +#else +static int team_port_enable_netpoll(struct team *team, struct team_port *port) +{ + return 0; +} +static void team_port_disable_netpoll(struct team_port *port) +{ +} +static struct netpoll_info *team_netpoll_info(struct team *team) +{ + return NULL; +} +#endif + static void __team_port_change_check(struct team_port *port, bool linkup); static int team_port_add(struct team *team, struct net_device *port_dev) @@ -853,6 +906,15 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_vids_add; } + if (team_netpoll_info(team)) { + err = team_port_enable_netpoll(team, port); + if (err) { + netdev_err(dev, "Failed to enable netpoll on device %s\n", + portname); + goto err_enable_netpoll; + } + } + err = netdev_set_master(port_dev, dev); if (err) { netdev_err(dev, "Device %s failed to set master\n", portname); @@ -892,6 +954,9 @@ err_handler_register: netdev_set_master(port_dev, NULL); err_set_master: + team_port_disable_netpoll(port); + +err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: @@ -932,6 +997,7 @@ static int team_port_del(struct team *team, struct net_device *port_dev) list_del_rcu(&port->list); netdev_rx_handler_unregister(port_dev); netdev_set_master(port_dev, NULL); + team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); dev_close(port_dev); team_port_leave(team, port); @@ -1307,6 +1373,48 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, uint16_t vid) return 0; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void team_poll_controller(struct net_device *dev) +{ +} + +static void __team_netpoll_cleanup(struct team *team) +{ + struct team_port *port; + + list_for_each_entry(port, &team->port_list, list) + team_port_disable_netpoll(port); +} + +static void team_netpoll_cleanup(struct net_device *dev) +{ + struct team *team = netdev_priv(dev); + + mutex_lock(&team->lock); + __team_netpoll_cleanup(team); + mutex_unlock(&team->lock); +} + +static int team_netpoll_setup(struct net_device *dev, + struct netpoll_info *npifo) +{ + struct team *team = netdev_priv(dev); + struct team_port *port; + int err; + + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) { + err = team_port_enable_netpoll(team, port); + if (err) { + __team_netpoll_cleanup(team); + break; + } + } + mutex_unlock(&team->lock); + return err; +} +#endif + static int team_add_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); @@ -1363,6 +1471,11 @@ static const struct net_device_ops team_netdev_ops = { .ndo_get_stats64 = team_get_stats64, .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = team_poll_controller, + .ndo_netpoll_setup = team_netpoll_setup, + .ndo_netpoll_cleanup = team_netpoll_cleanup, +#endif .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c index 253b8a5f3427..6262b4defd93 100644 --- a/drivers/net/team/team_mode_activebackup.c +++ b/drivers/net/team/team_mode_activebackup.c @@ -43,8 +43,7 @@ static bool ab_transmit(struct team *team, struct sk_buff *skb) active_port = rcu_dereference_bh(ab_priv(team)->active_port); if (unlikely(!active_port)) goto drop; - skb->dev = active_port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, active_port, skb)) return false; return true; diff --git a/drivers/net/team/team_mode_broadcast.c b/drivers/net/team/team_mode_broadcast.c index 5562345e9cef..c96e4d2967f0 100644 --- a/drivers/net/team/team_mode_broadcast.c +++ b/drivers/net/team/team_mode_broadcast.c @@ -29,8 +29,8 @@ static bool bc_transmit(struct team *team, struct sk_buff *skb) if (last) { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) { - skb2->dev = last->dev; - ret = dev_queue_xmit(skb2); + ret = team_dev_queue_xmit(team, last, + skb2); if (!sum_ret) sum_ret = ret; } @@ -39,8 +39,7 @@ static bool bc_transmit(struct team *team, struct sk_buff *skb) } } if (last) { - skb->dev = last->dev; - ret = dev_queue_xmit(skb); + ret = team_dev_queue_xmit(team, last, skb); if (!sum_ret) sum_ret = ret; } diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index 51a4b199c75c..cdc31b5ea15e 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -217,8 +217,7 @@ static bool lb_transmit(struct team *team, struct sk_buff *skb) port = select_tx_port_func(team, lb_priv, skb, hash); if (unlikely(!port)) goto drop; - skb->dev = port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, port, skb)) return false; lb_update_tx_stats(tx_bytes, lb_priv, get_lb_port_priv(port), hash); return true; diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c index 0cf38e9b9d26..ad7ed0ec544c 100644 --- a/drivers/net/team/team_mode_roundrobin.c +++ b/drivers/net/team/team_mode_roundrobin.c @@ -55,8 +55,7 @@ static bool rr_transmit(struct team *team, struct sk_buff *skb) port = __get_first_port_up(team, port); if (unlikely(!port)) goto drop; - skb->dev = port->dev; - if (dev_queue_xmit(skb)) + if (team_dev_queue_xmit(team, port, skb)) return false; return true; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index dfa0c8e0ab84..7fd0cdeb9444 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -13,6 +13,8 @@ #ifdef __KERNEL__ +#include + struct team_pcpu_stats { u64 rx_packets; u64 rx_bytes; @@ -60,6 +62,10 @@ struct team_port { unsigned int mtu; } orig; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *np; +#endif + long mode_priv[0]; }; @@ -73,6 +79,33 @@ static inline bool team_port_txable(struct team_port *port) return port->linkup && team_port_enabled(port); } +#ifdef CONFIG_NET_POLL_CONTROLLER +static inline void team_netpoll_send_skb(struct team_port *port, + struct sk_buff *skb) +{ + struct netpoll *np = port->np; + + if (np) + netpoll_send_skb(np, skb); +} +#else +static inline void team_netpoll_send_skb(struct team_port *port, + struct sk_buff *skb) +{ +} +#endif + +static inline int team_dev_queue_xmit(struct team *team, struct team_port *port, + struct sk_buff *skb) +{ + skb->dev = port->dev; + if (unlikely(netpoll_tx_running(port->dev))) { + team_netpoll_send_skb(port, skb); + return 0; + } + return dev_queue_xmit(skb); +} + struct team_mode_ops { int (*init)(struct team *team); void (*exit)(struct team *team); -- cgit v1.2.3 From 7eea1a23b47743be2dab4d29ad1f5b65f7ef3d7b Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Mon, 16 Jul 2012 11:46:52 +0200 Subject: bcma: cc: update defines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 51 ++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index fbd0d49dc4d2..3c80885fa829 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -24,7 +24,7 @@ #define BCMA_CC_FLASHT_NONE 0x00000000 /* No flash */ #define BCMA_CC_FLASHT_STSER 0x00000100 /* ST serial flash */ #define BCMA_CC_FLASHT_ATSER 0x00000200 /* Atmel serial flash */ -#define BCMA_CC_FLASHT_NFLASH 0x00000200 +#define BCMA_CC_FLASHT_NFLASH 0x00000200 /* NAND flash */ #define BCMA_CC_FLASHT_PARA 0x00000700 /* Parallel flash */ #define BCMA_CC_CAP_PLLT 0x00038000 /* PLL Type */ #define BCMA_PLLTYPE_NONE 0x00000000 @@ -45,6 +45,7 @@ #define BCMA_CC_CAP_PMU 0x10000000 /* PMU available (rev >= 20) */ #define BCMA_CC_CAP_ECI 0x20000000 /* ECI available (rev >= 20) */ #define BCMA_CC_CAP_SPROM 0x40000000 /* SPROM present */ +#define BCMA_CC_CAP_NFLASH 0x80000000 /* NAND flash present (rev >= 35 or BCM4706?) */ #define BCMA_CC_CORECTL 0x0008 #define BCMA_CC_CORECTL_UARTCLK0 0x00000001 /* Drive UART with internal clock */ #define BCMA_CC_CORECTL_SE 0x00000002 /* sync clk out enable (corerev >= 3) */ @@ -122,10 +123,58 @@ #define BCMA_CC_JCTL_EXT_EN 2 /* Enable external targets */ #define BCMA_CC_JCTL_EN 1 /* Enable Jtag master */ #define BCMA_CC_FLASHCTL 0x0040 +/* Start/busy bit in flashcontrol */ +#define BCMA_CC_FLASHCTL_OPCODE 0x000000ff +#define BCMA_CC_FLASHCTL_ACTION 0x00000700 +#define BCMA_CC_FLASHCTL_CS_ACTIVE 0x00001000 /* Chip Select Active, rev >= 20 */ #define BCMA_CC_FLASHCTL_START 0x80000000 #define BCMA_CC_FLASHCTL_BUSY BCMA_CC_FLASHCTL_START +/* Flashcontrol action + opcodes for ST flashes */ +#define BCMA_CC_FLASHCTL_ST_WREN 0x0006 /* Write Enable */ +#define BCMA_CC_FLASHCTL_ST_WRDIS 0x0004 /* Write Disable */ +#define BCMA_CC_FLASHCTL_ST_RDSR 0x0105 /* Read Status Register */ +#define BCMA_CC_FLASHCTL_ST_WRSR 0x0101 /* Write Status Register */ +#define BCMA_CC_FLASHCTL_ST_READ 0x0303 /* Read Data Bytes */ +#define BCMA_CC_FLASHCTL_ST_PP 0x0302 /* Page Program */ +#define BCMA_CC_FLASHCTL_ST_SE 0x02d8 /* Sector Erase */ +#define BCMA_CC_FLASHCTL_ST_BE 0x00c7 /* Bulk Erase */ +#define BCMA_CC_FLASHCTL_ST_DP 0x00b9 /* Deep Power-down */ +#define BCMA_CC_FLASHCTL_ST_RES 0x03ab /* Read Electronic Signature */ +#define BCMA_CC_FLASHCTL_ST_CSA 0x1000 /* Keep chip select asserted */ +#define BCMA_CC_FLASHCTL_ST_SSE 0x0220 /* Sub-sector Erase */ +/* Flashcontrol action + opcodes for Atmel flashes */ +#define BCMA_CC_FLASHCTL_AT_READ 0x07e8 +#define BCMA_CC_FLASHCTL_AT_PAGE_READ 0x07d2 +#define BCMA_CC_FLASHCTL_AT_STATUS 0x01d7 +#define BCMA_CC_FLASHCTL_AT_BUF1_WRITE 0x0384 +#define BCMA_CC_FLASHCTL_AT_BUF2_WRITE 0x0387 +#define BCMA_CC_FLASHCTL_AT_BUF1_ERASE_PROGRAM 0x0283 +#define BCMA_CC_FLASHCTL_AT_BUF2_ERASE_PROGRAM 0x0286 +#define BCMA_CC_FLASHCTL_AT_BUF1_PROGRAM 0x0288 +#define BCMA_CC_FLASHCTL_AT_BUF2_PROGRAM 0x0289 +#define BCMA_CC_FLASHCTL_AT_PAGE_ERASE 0x0281 +#define BCMA_CC_FLASHCTL_AT_BLOCK_ERASE 0x0250 +#define BCMA_CC_FLASHCTL_AT_BUF1_WRITE_ERASE_PROGRAM 0x0382 +#define BCMA_CC_FLASHCTL_AT_BUF2_WRITE_ERASE_PROGRAM 0x0385 +#define BCMA_CC_FLASHCTL_AT_BUF1_LOAD 0x0253 +#define BCMA_CC_FLASHCTL_AT_BUF2_LOAD 0x0255 +#define BCMA_CC_FLASHCTL_AT_BUF1_COMPARE 0x0260 +#define BCMA_CC_FLASHCTL_AT_BUF2_COMPARE 0x0261 +#define BCMA_CC_FLASHCTL_AT_BUF1_REPROGRAM 0x0258 +#define BCMA_CC_FLASHCTL_AT_BUF2_REPROGRAM 0x0259 #define BCMA_CC_FLASHADDR 0x0044 #define BCMA_CC_FLASHDATA 0x0048 +/* Status register bits for ST flashes */ +#define BCMA_CC_FLASHDATA_ST_WIP 0x01 /* Write In Progress */ +#define BCMA_CC_FLASHDATA_ST_WEL 0x02 /* Write Enable Latch */ +#define BCMA_CC_FLASHDATA_ST_BP_MASK 0x1c /* Block Protect */ +#define BCMA_CC_FLASHDATA_ST_BP_SHIFT 2 +#define BCMA_CC_FLASHDATA_ST_SRWD 0x80 /* Status Register Write Disable */ +/* Status register bits for Atmel flashes */ +#define BCMA_CC_FLASHDATA_AT_READY 0x80 +#define BCMA_CC_FLASHDATA_AT_MISMATCH 0x40 +#define BCMA_CC_FLASHDATA_AT_ID_MASK 0x38 +#define BCMA_CC_FLASHDATA_AT_ID_SHIFT 3 #define BCMA_CC_BCAST_ADDR 0x0050 #define BCMA_CC_BCAST_DATA 0x0054 #define BCMA_CC_GPIOPULLUP 0x0058 /* Rev >= 20 only */ -- cgit v1.2.3 From d3818c92afabecfe6b8e5d2e3734c8753522987c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Jul 2012 21:38:04 +0000 Subject: ipv6: fix inet6_csk_xmit() We should provide to inet6_csk_route_socket a struct flowi6 pointer, so that net6_csk_xmit() works correctly instead of sending garbage. Also add some consts Signed-off-by: Eric Dumazet Reported-by: Yuchung Cheng Cc: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++-- include/net/ip6_route.h | 3 ++- net/ipv6/inet6_connection_sock.c | 40 +++++++++++++++++++++------------------- 3 files changed, 25 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bc6c8fd8ed01..379e433e15e0 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -299,9 +299,9 @@ struct ipv6_pinfo { struct in6_addr rcv_saddr; struct in6_addr daddr; struct in6_pktinfo sticky_pktinfo; - struct in6_addr *daddr_cache; + const struct in6_addr *daddr_cache; #ifdef CONFIG_IPV6_SUBTREES - struct in6_addr *saddr_cache; + const struct in6_addr *saddr_cache; #endif __be32 flow_label; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index b6b6f7d6f3c0..5fa2af00634a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -158,7 +158,8 @@ extern void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); * Store a destination cache entry in a socket */ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt = (struct rt6_info *) dst; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 4a0c4d2d8b05..0251a6005be8 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); static inline void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) + const struct in6_addr *daddr, + const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); @@ -203,31 +204,31 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -static struct dst_entry *inet6_csk_route_socket(struct sock *sk) +static struct dst_entry *inet6_csk_route_socket(struct sock *sk, + struct flowi6 *fl6) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; - struct flowi6 fl6; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; - fl6.saddr = np->saddr; - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_sport = inet->inet_sport; - fl6.fl6_dport = inet->inet_dport; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = sk->sk_protocol; + fl6->daddr = np->daddr; + fl6->saddr = np->saddr; + fl6->flowlabel = np->flow_label; + IP6_ECN_flow_xmit(sk, fl6->flowlabel); + fl6->flowi6_oif = sk->sk_bound_dev_if; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_sport = inet->inet_sport; + fl6->fl6_dport = inet->inet_dport; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + final_p = fl6_update_dst(fl6, np->opt, &final); dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (!IS_ERR(dst)) __inet6_csk_dst_store(sk, dst, NULL, NULL); @@ -243,7 +244,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) struct dst_entry *dst; int res; - dst = inet6_csk_route_socket(sk); + dst = inet6_csk_route_socket(sk, &fl6); if (IS_ERR(dst)) { sk->sk_err_soft = -PTR_ERR(dst); sk->sk_route_caps = 0; @@ -265,12 +266,13 @@ EXPORT_SYMBOL_GPL(inet6_csk_xmit); struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) { - struct dst_entry *dst = inet6_csk_route_socket(sk); + struct flowi6 fl6; + struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6); if (IS_ERR(dst)) return NULL; dst->ops->update_pmtu(dst, sk, NULL, mtu); - return inet6_csk_route_socket(sk); + return inet6_csk_route_socket(sk, &fl6); } EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu); -- cgit v1.2.3 From 1181412c1a671ed4e8fb1736f17e6ec617c68059 Mon Sep 17 00:00:00 2001 From: Saurabh Date: Tue, 17 Jul 2012 09:44:54 +0000 Subject: net/ipv4: VTI support new module for ip_vti. New VTI tunnel kernel module, Kconfig and Makefile changes. Signed-off-by: Saurabh Mohan Reviewed-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 14 + net/ipv4/Kconfig | 11 + net/ipv4/Makefile | 1 + net/ipv4/ip_vti.c | 956 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 982 insertions(+) create mode 100644 net/ipv4/ip_vti.c (limited to 'include/linux') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 16b92d008bed..5efff60b6f56 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -80,4 +80,18 @@ enum { #define IFLA_GRE_MAX (__IFLA_GRE_MAX - 1) +/* VTI-mode i_flags */ +#define VTI_ISVTI 0x0001 + +enum { + IFLA_VTI_UNSPEC, + IFLA_VTI_LINK, + IFLA_VTI_IKEY, + IFLA_VTI_OKEY, + IFLA_VTI_LOCAL, + IFLA_VTI_REMOTE, + __IFLA_VTI_MAX, +}; + +#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1) #endif /* _IF_TUNNEL_H_ */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 20f1cb5c8aba..5a19aeb86094 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -310,6 +310,17 @@ config SYN_COOKIES If unsure, say N. +config NET_IPVTI + tristate "Virtual (secure) IP: tunneling" + select INET_TUNNEL + depends on INET_XFRM_MODE_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This can be used with xfrm mode tunnel to give + the notion of a secure tunnel for IPSEC and then use routing protocol + on top. + config INET_AH tristate "IP: AH transformation" select XFRM_ALGO diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 5a23e8b37106..a677d804e53e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_IP_MROUTE) += ipmr.o obj-$(CONFIG_NET_IPIP) += ipip.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o +obj-$(CONFIG_NET_IPVTI) += ip_vti.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_AH) += ah4.o obj-$(CONFIG_INET_ESP) += esp4.o diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c new file mode 100644 index 000000000000..c41b5c359936 --- /dev/null +++ b/net/ipv4/ip_vti.c @@ -0,0 +1,956 @@ +/* + * Linux NET3: IP/IP protocol decoder modified to support + * virtual tunnel interface + * + * Authors: + * Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +/* + This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c + + For comments look at net/ipv4/ip_gre.c --ANK + */ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#define HASH_SIZE 16 +#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1)) + +static struct rtnl_link_ops vti_link_ops __read_mostly; + +static int vti_net_id __read_mostly; +struct vti_net { + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel **tunnels[4]; + + struct net_device *fb_tunnel_dev; +}; + +static int vti_fb_tunnel_init(struct net_device *dev); +static int vti_tunnel_init(struct net_device *dev); +static void vti_tunnel_setup(struct net_device *dev); +static void vti_dev_free(struct net_device *dev); +static int vti_tunnel_bind_dev(struct net_device *dev); + +/* Locking : hash tables are protected by RCU and RTNL */ + +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; + +#define VTI_XMIT(stats1, stats2) do { \ + int err; \ + int pkt_len = skb->len; \ + err = dst_output(skb); \ + if (net_xmit_eval(err) == 0) { \ + u64_stats_update_begin(&(stats1)->syncp); \ + (stats1)->tx_bytes += pkt_len; \ + (stats1)->tx_packets++; \ + u64_stats_update_end(&(stats1)->syncp); \ + } else { \ + (stats2)->tx_errors++; \ + (stats2)->tx_aborted_errors++; \ + } \ +} while (0) + + +static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + return tot; +} + +static struct ip_tunnel *vti_tunnel_lookup(struct net *net, + __be32 remote, __be32 local) +{ + unsigned h0 = HASH(remote); + unsigned h1 = HASH(local); + struct ip_tunnel *t; + struct vti_net *ipn = net_generic(net, vti_net_id); + + for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + if (local == t->parms.iph.saddr && + remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + return t; + for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + return t; + + for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) + return t; + + for_each_ip_tunnel_rcu(ipn->tunnels_wc[0]) + if (t && (t->dev->flags&IFF_UP)) + return t; + return NULL; +} + +static struct ip_tunnel **__vti_bucket(struct vti_net *ipn, + struct ip_tunnel_parm *parms) +{ + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + unsigned h = 0; + int prio = 0; + + if (remote) { + prio |= 2; + h ^= HASH(remote); + } + if (local) { + prio |= 1; + h ^= HASH(local); + } + return &ipn->tunnels[prio][h]; +} + +static inline struct ip_tunnel **vti_bucket(struct vti_net *ipn, + struct ip_tunnel *t) +{ + return __vti_bucket(ipn, &t->parms); +} + +static void vti_tunnel_unlink(struct vti_net *ipn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = vti_bucket(ipn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static void vti_tunnel_link(struct vti_net *ipn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp = vti_bucket(ipn, t); + + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static struct ip_tunnel *vti_tunnel_locate(struct net *net, + struct ip_tunnel_parm *parms, + int create) +{ + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; + struct net_device *dev; + char name[IFNAMSIZ]; + struct vti_net *ipn = net_generic(net, vti_net_id); + + for (tp = __vti_bucket(ipn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { + if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) + return t; + } + if (!create) + return NULL; + + if (parms->name[0]) + strlcpy(name, parms->name, IFNAMSIZ); + else + strcpy(name, "vti%d"); + + dev = alloc_netdev(sizeof(*t), name, vti_tunnel_setup); + if (dev == NULL) + return NULL; + + dev_net_set(dev, net); + + nt = netdev_priv(dev); + nt->parms = *parms; + dev->rtnl_link_ops = &vti_link_ops; + + vti_tunnel_bind_dev(dev); + + if (register_netdevice(dev) < 0) + goto failed_free; + + dev_hold(dev); + vti_tunnel_link(ipn, nt); + return nt; + +failed_free: + free_netdev(dev); + return NULL; +} + +static void vti_tunnel_uninit(struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + + vti_tunnel_unlink(ipn, netdev_priv(dev)); + dev_put(dev); +} + +static int vti_err(struct sk_buff *skb, u32 info) +{ + + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + */ + struct iphdr *iph = (struct iphdr *)skb->data; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct ip_tunnel *t; + int err; + + switch (type) { + default: + case ICMP_PARAMETERPROB: + return 0; + + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_SR_FAILED: + case ICMP_PORT_UNREACH: + /* Impossible event. */ + return 0; + default: + /* All others are translated to HOST_UNREACH. */ + break; + } + break; + case ICMP_TIME_EXCEEDED: + if (code != ICMP_EXC_TTL) + return 0; + break; + } + + err = -ENOENT; + + rcu_read_lock(); + t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->parms.link, 0, IPPROTO_IPIP, 0); + err = 0; + goto out; + } + + err = 0; + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) + goto out; + + if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) + t->err_count++; + else + t->err_count = 1; + t->err_time = jiffies; +out: + rcu_read_unlock(); + return err; +} + +/* We dont digest the packet therefore let the packet pass */ +static int vti_rcv(struct sk_buff *skb) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + + rcu_read_lock(); + tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + if (tunnel != NULL) { + struct pcpu_tstats *tstats; + + tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + skb->dev = tunnel->dev; + rcu_read_unlock(); + return 1; + } + rcu_read_unlock(); + + return -1; +} + +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ + +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct pcpu_tstats *tstats; + struct iphdr *tiph = &tunnel->parms.iph; + u8 tos; + struct rtable *rt; /* Route to the other host */ + struct net_device *tdev; /* Device to other host */ + struct iphdr *old_iph = ip_hdr(skb); + __be32 dst = tiph->daddr; + struct flowi4 fl4; + + if (skb->protocol != htons(ETH_P_IP)) + goto tx_error; + + tos = old_iph->tos; + + memset(&fl4, 0, sizeof(fl4)); + flowi4_init_output(&fl4, tunnel->parms.link, + htonl(tunnel->parms.i_key), RT_TOS(tos), + RT_SCOPE_UNIVERSE, + IPPROTO_IPIP, 0, + dst, tiph->saddr, 0, 0); + rt = ip_route_output_key(dev_net(dev), &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!rt->dst.xfrm || + rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + tdev = rt->dst.dev; + + if (tdev == dev) { + ip_rt_put(rt); + dev->stats.collisions++; + goto tx_error; + } + + if (tunnel->err_count > 0) { + if (time_before(jiffies, + tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { + tunnel->err_count--; + dst_link_failure(skb); + } else + tunnel->err_count = 0; + } + + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + nf_reset(skb); + skb->dev = skb_dst(skb)->dev; + + tstats = this_cpu_ptr(dev->tstats); + VTI_XMIT(tstats, &dev->stats); + return NETDEV_TX_OK; + +tx_error_icmp: + dst_link_failure(skb); +tx_error: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int vti_tunnel_bind_dev(struct net_device *dev) +{ + struct net_device *tdev = NULL; + struct ip_tunnel *tunnel; + struct iphdr *iph; + + tunnel = netdev_priv(dev); + iph = &tunnel->parms.iph; + + if (iph->daddr) { + struct rtable *rt; + struct flowi4 fl4; + memset(&fl4, 0, sizeof(fl4)); + flowi4_init_output(&fl4, tunnel->parms.link, + htonl(tunnel->parms.i_key), + RT_TOS(iph->tos), RT_SCOPE_UNIVERSE, + IPPROTO_IPIP, 0, + iph->daddr, iph->saddr, 0, 0); + rt = ip_route_output_key(dev_net(dev), &fl4); + if (!IS_ERR(rt)) { + tdev = rt->dst.dev; + ip_rt_put(rt); + } + dev->flags |= IFF_POINTOPOINT; + } + + if (!tdev && tunnel->parms.link) + tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link); + + if (tdev) { + dev->hard_header_len = tdev->hard_header_len + + sizeof(struct iphdr); + dev->mtu = tdev->mtu; + } + dev->iflink = tunnel->parms.link; + return dev->mtu; +} + +static int +vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip_tunnel_parm p; + struct ip_tunnel *t; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + t = NULL; + if (dev == ipn->fb_tunnel_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, + sizeof(p))) { + err = -EFAULT; + break; + } + t = vti_tunnel_locate(net, &p, 0); + } + if (t == NULL) + t = netdev_priv(dev); + memcpy(&p, &t->parms, sizeof(p)); + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + + err = -EINVAL; + if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || + p.iph.ihl != 5) + goto done; + + t = vti_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); + + if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else { + if (((dev->flags&IFF_POINTOPOINT) && + !p.iph.daddr) || + (!(dev->flags&IFF_POINTOPOINT) && + p.iph.daddr)) { + err = -EINVAL; + break; + } + t = netdev_priv(dev); + vti_tunnel_unlink(ipn, t); + synchronize_net(); + t->parms.iph.saddr = p.iph.saddr; + t->parms.iph.daddr = p.iph.daddr; + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + t->parms.iph.protocol = IPPROTO_IPIP; + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + vti_tunnel_link(ipn, t); + netdev_state_change(dev); + } + } + + if (t) { + err = 0; + if (cmd == SIOCCHGTUNNEL) { + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + if (t->parms.link != p.link) { + t->parms.link = p.link; + vti_tunnel_bind_dev(dev); + netdev_state_change(dev); + } + } + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, + sizeof(p))) + err = -EFAULT; + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + + case SIOCDELTUNNEL: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + if (dev == ipn->fb_tunnel_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, + sizeof(p))) + goto done; + err = -ENOENT; + + t = vti_tunnel_locate(net, &p, 0); + if (t == NULL) + goto done; + err = -EPERM; + if (t->dev == ipn->fb_tunnel_dev) + goto done; + dev = t->dev; + } + unregister_netdevice(dev); + err = 0; + break; + + default: + err = -EINVAL; + } + +done: + return err; +} + +static int vti_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < 68 || new_mtu > 0xFFF8) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static const struct net_device_ops vti_netdev_ops = { + .ndo_init = vti_tunnel_init, + .ndo_uninit = vti_tunnel_uninit, + .ndo_start_xmit = vti_tunnel_xmit, + .ndo_do_ioctl = vti_tunnel_ioctl, + .ndo_change_mtu = vti_tunnel_change_mtu, + .ndo_get_stats64 = vti_get_stats64, +}; + +static void vti_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static void vti_tunnel_setup(struct net_device *dev) +{ + dev->netdev_ops = &vti_netdev_ops; + dev->destructor = vti_dev_free; + + dev->type = ARPHRD_TUNNEL; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); + dev->mtu = ETH_DATA_LEN; + dev->flags = IFF_NOARP; + dev->iflink = 0; + dev->addr_len = 4; + dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +static int vti_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); + memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; +} + +static int __net_init vti_fb_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct iphdr *iph = &tunnel->parms.iph; + struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id); + + tunnel->dev = dev; + strcpy(tunnel->parms.name, dev->name); + + iph->version = 4; + iph->protocol = IPPROTO_IPIP; + iph->ihl = 5; + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + dev_hold(dev); + rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + return 0; +} + +static struct xfrm_tunnel vti_handler __read_mostly = { + .handler = vti_rcv, + .err_handler = vti_err, + .priority = 1, +}; + +static void vti_destroy_tunnels(struct vti_net *ipn, struct list_head *head) +{ + int prio; + + for (prio = 1; prio < 4; prio++) { + int h; + for (h = 0; h < HASH_SIZE; h++) { + struct ip_tunnel *t; + + t = rtnl_dereference(ipn->tunnels[prio][h]); + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = rtnl_dereference(t->next); + } + } + } +} + +static int __net_init vti_init_net(struct net *net) +{ + int err; + struct vti_net *ipn = net_generic(net, vti_net_id); + + ipn->tunnels[0] = ipn->tunnels_wc; + ipn->tunnels[1] = ipn->tunnels_l; + ipn->tunnels[2] = ipn->tunnels_r; + ipn->tunnels[3] = ipn->tunnels_r_l; + + ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), + "ip_vti0", + vti_tunnel_setup); + if (!ipn->fb_tunnel_dev) { + err = -ENOMEM; + goto err_alloc_dev; + } + dev_net_set(ipn->fb_tunnel_dev, net); + + err = vti_fb_tunnel_init(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; + ipn->fb_tunnel_dev->rtnl_link_ops = &vti_link_ops; + + err = register_netdev(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; + return 0; + +err_reg_dev: + vti_dev_free(ipn->fb_tunnel_dev); +err_alloc_dev: + /* nothing */ + return err; +} + +static void __net_exit vti_exit_net(struct net *net) +{ + struct vti_net *ipn = net_generic(net, vti_net_id); + LIST_HEAD(list); + + rtnl_lock(); + vti_destroy_tunnels(ipn, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations vti_net_ops = { + .init = vti_init_net, + .exit = vti_exit_net, + .id = &vti_net_id, + .size = sizeof(struct vti_net), +}; + +static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + return 0; +} + +static void vti_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.protocol = IPPROTO_IPIP; + + if (!data) + return; + + if (data[IFLA_VTI_LINK]) + parms->link = nla_get_u32(data[IFLA_VTI_LINK]); + + if (data[IFLA_VTI_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); + + if (data[IFLA_VTI_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); + + if (data[IFLA_VTI_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_VTI_LOCAL]); + + if (data[IFLA_VTI_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_VTI_REMOTE]); + +} + +static int vti_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct ip_tunnel *nt; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + int mtu; + int err; + + nt = netdev_priv(dev); + vti_netlink_parms(data, &nt->parms); + + if (vti_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + mtu = vti_tunnel_bind_dev(dev); + if (!tb[IFLA_MTU]) + dev->mtu = mtu; + + err = register_netdevice(dev); + if (err) + goto out; + + dev_hold(dev); + vti_tunnel_link(ipn, nt); + +out: + return err; +} + +static int vti_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t, *nt; + struct net *net = dev_net(dev); + struct vti_net *ipn = net_generic(net, vti_net_id); + struct ip_tunnel_parm p; + int mtu; + + if (dev == ipn->fb_tunnel_dev) + return -EINVAL; + + nt = netdev_priv(dev); + vti_netlink_parms(data, &p); + + t = vti_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else { + t = nt; + + vti_tunnel_unlink(ipn, t); + t->parms.iph.saddr = p.iph.saddr; + t->parms.iph.daddr = p.iph.daddr; + t->parms.i_key = p.i_key; + t->parms.o_key = p.o_key; + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p.iph.saddr, 4); + memcpy(dev->broadcast, &p.iph.daddr, 4); + } + vti_tunnel_link(ipn, t); + netdev_state_change(dev); + } + + if (t->parms.link != p.link) { + t->parms.link = p.link; + mtu = vti_tunnel_bind_dev(dev); + if (!tb[IFLA_MTU]) + dev->mtu = mtu; + netdev_state_change(dev); + } + + return 0; +} + +static size_t vti_get_size(const struct net_device *dev) +{ + return + /* IFLA_VTI_LINK */ + nla_total_size(4) + + /* IFLA_VTI_IKEY */ + nla_total_size(4) + + /* IFLA_VTI_OKEY */ + nla_total_size(4) + + /* IFLA_VTI_LOCAL */ + nla_total_size(4) + + /* IFLA_VTI_REMOTE */ + nla_total_size(4) + + 0; +} + +static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm *p = &t->parms; + + nla_put_u32(skb, IFLA_VTI_LINK, p->link); + nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key); + nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key); + nla_put_be32(skb, IFLA_VTI_LOCAL, p->iph.saddr); + nla_put_be32(skb, IFLA_VTI_REMOTE, p->iph.daddr); + + return 0; +} + +static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { + [IFLA_VTI_LINK] = { .type = NLA_U32 }, + [IFLA_VTI_IKEY] = { .type = NLA_U32 }, + [IFLA_VTI_OKEY] = { .type = NLA_U32 }, + [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, +}; + +static struct rtnl_link_ops vti_link_ops __read_mostly = { + .kind = "vti", + .maxtype = IFLA_VTI_MAX, + .policy = vti_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = vti_tunnel_setup, + .validate = vti_tunnel_validate, + .newlink = vti_newlink, + .changelink = vti_changelink, + .get_size = vti_get_size, + .fill_info = vti_fill_info, +}; + +static int __init vti_init(void) +{ + int err; + + pr_info("IPv4 over IPSec tunneling driver\n"); + + err = register_pernet_device(&vti_net_ops); + if (err < 0) + return err; + err = xfrm4_mode_tunnel_input_register(&vti_handler); + if (err < 0) { + unregister_pernet_device(&vti_net_ops); + pr_info(KERN_INFO "vti init: can't register tunnel\n"); + } + + err = rtnl_link_register(&vti_link_ops); + if (err < 0) + goto rtnl_link_failed; + + return err; + +rtnl_link_failed: + xfrm4_mode_tunnel_input_deregister(&vti_handler); + unregister_pernet_device(&vti_net_ops); + return err; +} + +static void __exit vti_fini(void) +{ + rtnl_link_unregister(&vti_link_ops); + if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + pr_info("vti close: can't deregister tunnel\n"); + + unregister_pernet_device(&vti_net_ops); +} + +module_init(vti_init); +module_exit(vti_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("vti"); +MODULE_ALIAS_NETDEV("ip_vti0"); -- cgit v1.2.3 From af22d9de45caf8b2a99f2b27a927169c029528b4 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Wed, 18 Jul 2012 22:33:49 +0000 Subject: net/mlx4: Move MAC_MASK to a common place Define this macro is one common place instead of duplicating it over the code Signed-off-by: Amir Vadai Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/mcg.c | 1 - drivers/net/ethernet/mellanox/mlx4/port.c | 1 - drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 3 +-- include/linux/mlx4/driver.h | 2 ++ 5 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index dd6a77b21149..9d0b88eea02b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -34,12 +34,12 @@ #include #include #include +#include #include "mlx4_en.h" #include "en_port.h" #define EN_ETHTOOL_QP_ATTACH (1ull << 63) -#define EN_ETHTOOL_MAC_MASK 0xffffffffffffULL #define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff) #define EN_ETHTOOL_WORD_MASK cpu_to_be32(0xffffffff) @@ -751,7 +751,7 @@ static int mlx4_en_ethtool_to_net_trans_rule(struct net_device *dev, struct ethhdr *eth_spec; struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_spec_list *spec_l2; - __be64 mac_msk = cpu_to_be64(EN_ETHTOOL_MAC_MASK << 16); + __be64 mac_msk = cpu_to_be64(MLX4_MAC_MASK << 16); err = mlx4_en_validate_flow(dev, cmd); if (err) @@ -761,7 +761,7 @@ static int mlx4_en_ethtool_to_net_trans_rule(struct net_device *dev, if (!spec_l2) return -ENOMEM; - mac = priv->mac & EN_ETHTOOL_MAC_MASK; + mac = priv->mac & MLX4_MAC_MASK; be_mac = cpu_to_be64(mac << 16); spec_l2->id = MLX4_NET_TRANS_RULE_ID_ETH; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 5bac0dfafbd8..4ec3835e1bc2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -41,7 +41,6 @@ #define MGM_QPN_MASK 0x00FFFFFF #define MGM_BLCK_LB_BIT 30 -#define MLX4_MAC_MASK 0xffffffffffffULL static const u8 zero_gid[16]; /* automatically initialized to 0 */ diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index a51d1b9bf1d1..028833ffc56f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -39,7 +39,6 @@ #include "mlx4.h" #define MLX4_MAC_VALID (1ull << 63) -#define MLX4_MAC_MASK 0xffffffffffffULL #define MLX4_VLAN_VALID (1u << 31) #define MLX4_VLAN_MASK 0xfff diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index c3fa91986190..94ceddd17ab2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -41,13 +41,12 @@ #include #include #include +#include #include "mlx4.h" #include "fw.h" #define MLX4_MAC_VALID (1ull << 63) -#define MLX4_MAC_MASK 0x7fffffffffffffffULL -#define ETH_ALEN 6 struct mac_res { struct list_head list; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 5f1298b1b5ef..8dc485febc6b 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -37,6 +37,8 @@ struct mlx4_dev; +#define MLX4_MAC_MASK 0xffffffffffffULL + enum mlx4_dev_event { MLX4_DEV_EVENT_CATASTROPHIC_ERROR, MLX4_DEV_EVENT_PORT_UP, -- cgit v1.2.3 From 122733a189d687087364d6dc3ecc7c682554f6a0 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Wed, 18 Jul 2012 22:33:50 +0000 Subject: net/rps: Protect cpu_rmap.h from double inclusion Signed-off-by: Amir Vadai Signed-off-by: Or Gerlitz Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/cpu_rmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 473771a528c0..ac3bbb5b9502 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -1,3 +1,6 @@ +#ifndef __LINUX_CPU_RMAP_H +#define __LINUX_CPU_RMAP_H + /* * cpu_rmap.c: CPU affinity reverse-map support * Copyright 2011 Solarflare Communications Inc. @@ -71,3 +74,4 @@ extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); #endif +#endif /* __LINUX_CPU_RMAP_H */ -- cgit v1.2.3 From d9236c3f10490cd0b3fd4516af12ba62dcbae0b0 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Wed, 18 Jul 2012 22:33:51 +0000 Subject: {NET,IB}/mlx4: Add rmap support to mlx4_assign_eq Enable callers of mlx4_assign_eq to supply a pointer to cpu_rmap. If supplied, the assigned IRQ is tracked using rmap infrastructure. Signed-off-by: Amir Vadai Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 3 ++- drivers/net/ethernet/mellanox/mlx4/en_cq.c | 3 ++- drivers/net/ethernet/mellanox/mlx4/eq.c | 12 +++++++++++- include/linux/mlx4/device.h | 4 +++- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8a3a2037b005..a07b774e7864 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1159,7 +1159,8 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) sprintf(name, "mlx4-ib-%d-%d@%s", i, j, dev->pdev->bus->name); /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(dev, name, &ibdev->eq_table[eq])) { + if (mlx4_assign_eq(dev, name, NULL, + &ibdev->eq_table[eq])) { /* Use legacy (same as mlx4_en driver) */ pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq); ibdev->eq_table[eq] = diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 908a460d8db6..0ef615684021 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -91,7 +91,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, sprintf(name, "%s-%d", priv->dev->name, cq->ring); /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(mdev->dev, name, &cq->vector)) { + if (mlx4_assign_eq(mdev->dev, name, NULL, + &cq->vector)) { cq->vector = (cq->ring + 1 + priv->port) % mdev->dev->caps.num_comp_vectors; mlx4_warn(mdev, "Failed Assigning an EQ to " diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index bce98d9c0039..cd48337cbfc0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -39,6 +39,7 @@ #include #include +#include #include "mlx4.h" #include "fw.h" @@ -1060,7 +1061,8 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) } EXPORT_SYMBOL(mlx4_test_interrupts); -int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector) +int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, + int *vector) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -1074,6 +1076,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector) snprintf(priv->eq_table.irq_names + vec * MLX4_IRQNAME_SIZE, MLX4_IRQNAME_SIZE, "%s", name); +#ifdef CONFIG_RFS_ACCEL + if (rmap) { + err = irq_cpu_rmap_add(rmap, + priv->eq_table.eq[vec].irq); + if (err) + mlx4_warn(dev, "Failed adding irq rmap\n"); + } +#endif err = request_irq(priv->eq_table.eq[vec].irq, mlx4_msi_x_interrupt, 0, &priv->eq_table.irq_names[vec<<5], diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6f0d133cc7ad..4d7761f8c3f6 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -36,6 +36,7 @@ #include #include #include +#include #include @@ -784,7 +785,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); -int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector); +int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, + int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); -- cgit v1.2.3 From 2100c8d2d9db23c0a09901a782bb4e3b21bee298 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 19 Jul 2012 06:43:05 +0000 Subject: net-tcp: Fast Open base This patch impelements the common code for both the client and server. 1. TCP Fast Open option processing. Since Fast Open does not have an option number assigned by IANA yet, it shares the experiment option code 254 by implementing draft-ietf-tcpm-experimental-options with a 16 bits magic number 0xF989. This enables global experiments without clashing the scarce(2) experimental options available for TCP. When the draft status becomes standard (maybe), the client should switch to the new option number assigned while the server supports both numbers for transistion. 2. The new sysctl tcp_fastopen 3. A place holder init function Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 10 ++++++++++ include/net/tcp.h | 9 ++++++++- net/ipv4/Makefile | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ net/ipv4/tcp_fastopen.c | 11 +++++++++++ net/ipv4/tcp_input.c | 26 ++++++++++++++++++++++---- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 4 ++-- net/ipv4/tcp_output.c | 25 +++++++++++++++++++++---- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 12 files changed, 86 insertions(+), 16 deletions(-) create mode 100644 net/ipv4/tcp_fastopen.c (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1888169e07c7..12948f543839 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -243,6 +243,16 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) return (tcp_hdr(skb)->doff - 5) * 4; } +/* TCP Fast Open */ +#define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */ +#define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */ + +/* TCP Fast Open Cookie as stored in memory */ +struct tcp_fastopen_cookie { + s8 len; + u8 val[TCP_FASTOPEN_COOKIE_MAX]; +}; + /* This defines a selective acknowledgement block. */ struct tcp_sack_block_wire { __be32 start_seq; diff --git a/include/net/tcp.h b/include/net/tcp.h index 85c5090bfe25..5aed3718fde8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -170,6 +170,11 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */ +#define TCPOPT_EXP 254 /* Experimental */ +/* Magic number to be after the option value for sharing TCP + * experimental options. See draft-ietf-tcpm-experimental-options-00.txt + */ +#define TCPOPT_FASTOPEN_MAGIC 0xF989 /* * TCP option lengths @@ -180,6 +185,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */ #define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */ #define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN) @@ -222,6 +228,7 @@ extern int sysctl_tcp_retries1; extern int sysctl_tcp_retries2; extern int sysctl_tcp_orphan_retries; extern int sysctl_tcp_syncookies; +extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; extern int sysctl_tcp_rfc1337; @@ -418,7 +425,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); extern void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, const u8 **hvpp, - int estab); + int estab, struct tcp_fastopen_cookie *foc); extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index a677d804e53e..ae2ccf2890e4 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -7,7 +7,7 @@ obj-y := route.o inetpeer.o protocol.o \ ip_output.o ip_sockglue.o inet_hashtables.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ - tcp_minisocks.o tcp_cong.o tcp_metrics.o \ + tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ datagram.o raw.o udp.o udplite.o \ arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index eab2a7fb15d1..650e1528e1e6 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -293,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) goto out; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3f6a1e762e9c..5840c3255721 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -366,6 +366,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, #endif + { + .procname = "tcp_fastopen", + .data = &sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "tcp_tw_recycle", .data = &tcp_death_row.sysctl_tw_recycle, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c new file mode 100644 index 000000000000..a7f729c409d7 --- /dev/null +++ b/net/ipv4/tcp_fastopen.c @@ -0,0 +1,11 @@ +#include +#include + +int sysctl_tcp_fastopen; + +static int __init tcp_fastopen_init(void) +{ + return 0; +} + +late_initcall(tcp_fastopen_init); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fdd49f1b7a52..a06bb8959e7e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3732,7 +3732,8 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, - const u8 **hvpp, int estab) + const u8 **hvpp, int estab, + struct tcp_fastopen_cookie *foc) { const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); @@ -3839,8 +3840,25 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o break; } break; - } + case TCPOPT_EXP: + /* Fast Open option shares code 254 using a + * 16 bits magic number. It's valid only in + * SYN or SYN-ACK with an even size. + */ + if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || + get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC || + foc == NULL || !th->syn || (opsize & 1)) + break; + foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE; + if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && + foc->len <= TCP_FASTOPEN_COOKIE_MAX) + memcpy(foc->val, ptr + 2, foc->len); + else if (foc->len != 0) + foc->len = -1; + break; + + } ptr += opsize-2; length -= opsize; } @@ -3882,7 +3900,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, if (tcp_parse_aligned_timestamp(tp, th)) return true; } - tcp_parse_options(skb, &tp->rx_opt, hvpp, 1); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return true; } @@ -5637,7 +5655,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_cookie_values *cvp = tp->cookie_values; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL); if (th->ack) { /* rfc793: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d7d2fa50f07f..01aa77a97020 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1307,7 +1307,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index c66f2ede160e..5912ac3fd240 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -97,7 +97,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -534,7 +534,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 15a7c7bc3e58..4849be76ccd6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -385,15 +385,17 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) #define OPTION_COOKIE_EXTENSION (1 << 4) +#define OPTION_FAST_OPEN_COOKIE (1 << 8) struct tcp_out_options { - u8 options; /* bit field of OPTION_* */ + u16 options; /* bit field of OPTION_* */ + u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ - u16 mss; /* 0 to disable */ - __u32 tsval, tsecr; /* need to include OPTION_TS */ __u8 *hash_location; /* temporary pointer, overloaded */ + __u32 tsval, tsecr; /* need to include OPTION_TS */ + struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ }; /* The sysctl int routines are generic, so check consistency here. @@ -442,7 +444,7 @@ static u8 tcp_cookie_size_check(u8 desired) static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { - u8 options = opts->options; /* mungable copy */ + u16 options = opts->options; /* mungable copy */ /* Having both authentication and cookies for security is redundant, * and there's certainly not enough room. Instead, the cookie-less @@ -564,6 +566,21 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, tp->rx_opt.dsack = 0; } + + if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { + struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; + + *ptr++ = htonl((TCPOPT_EXP << 24) | + ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) | + TCPOPT_FASTOPEN_MAGIC); + + memcpy(ptr, foc->val, foc->len); + if ((foc->len & 3) == 2) { + u8 *align = ((u8 *)ptr) + foc->len; + align[0] = align[1] = TCPOPT_NOP; + } + ptr += (foc->len + 3) >> 2; + } } /* Compute TCP options for SYN packets. This is not the final diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7bf3cc427c28..bb46061c813a 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -177,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c9dabdd832d7..0302ec3fecfc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1033,7 +1033,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && -- cgit v1.2.3 From 783237e8daf13481ee234997cbbbb823872ac388 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 19 Jul 2012 06:43:07 +0000 Subject: net-tcp: Fast Open client - sending SYN-data This patch implements sending SYN-data in tcp_connect(). The data is from tcp_sendmsg() with flag MSG_FASTOPEN (implemented in a later patch). The length of the cookie in tcp_fastopen_req, init'd to 0, controls the type of the SYN. If the cookie is not cached (len==0), the host sends data-less SYN with Fast Open cookie request option to solicit a cookie from the remote. If cookie is not available (len > 0), the host sends a SYN-data with Fast Open cookie option. If cookie length is negative, the SYN will not include any Fast Open option (for fall back operations). To deal with middleboxes that may drop SYN with data or experimental TCP option, the SYN-data is only sent once. SYN retransmits do not include data or Fast Open options. The connection will fall back to regular TCP handshake. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + include/linux/tcp.h | 6 ++- include/net/tcp.h | 9 ++++ net/ipv4/af_inet.c | 10 ++++- net/ipv4/proc.c | 1 + net/ipv4/tcp_output.c | 115 ++++++++++++++++++++++++++++++++++++++++++++++---- 6 files changed, 130 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index e5fcbd079e4a..00bc189cb395 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -238,6 +238,7 @@ enum LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */ + LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */ __LINUX_MIB_MAX }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 12948f543839..1edf96afab44 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -386,7 +386,8 @@ struct tcp_sock { unused : 1; u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ - early_retrans_delayed:1; /* Delayed ER timer installed */ + early_retrans_delayed:1, /* Delayed ER timer installed */ + syn_fastopen:1; /* SYN includes Fast Open option */ /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ @@ -500,6 +501,9 @@ struct tcp_sock { struct tcp_md5sig_info __rcu *md5sig_info; #endif +/* TCP fastopen related information */ + struct tcp_fastopen_request *fastopen_req; + /* When the cookie options are generated and exchanged, then this * object holds a reference to them (cookie_values->kref). Also * contains related tcp_cookie_transactions fields. diff --git a/include/net/tcp.h b/include/net/tcp.h index e601da197361..867557b4244a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1289,6 +1289,15 @@ extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key); +struct tcp_fastopen_request { + /* Fast Open cookie. Size 0 means a cookie request */ + struct tcp_fastopen_cookie cookie; + struct msghdr *data; /* data in MSG_FASTOPEN */ + u16 copied; /* queued in tcp_connect() */ +}; + +void tcp_free_fastopen_req(struct tcp_sock *tp); + /* write queue abstraction */ static inline void tcp_write_queue_purge(struct sock *sk) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 07a02f6e9696..edc414625be2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -556,11 +556,12 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, } EXPORT_SYMBOL(inet_dgram_connect); -static long inet_wait_for_connect(struct sock *sk, long timeo) +static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -576,6 +577,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(sk), &wait); + sk->sk_write_pending -= writebias; return timeo; } @@ -634,8 +636,12 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + int writebias = (sk->sk_protocol == IPPROTO_TCP) && + tcp_sk(sk)->fastopen_req && + tcp_sk(sk)->fastopen_req->data ? 1 : 0; + /* Error code is set above */ - if (!timeo || !inet_wait_for_connect(sk, timeo)) + if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 2a5240b2ea61..957acd12250b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -262,6 +262,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), + SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4849be76ccd6..88693281da4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -596,6 +596,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? tcp_cookie_size_check(cvp->cookie_desired) : 0; + struct tcp_fastopen_request *fastopen = tp->fastopen_req; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); @@ -636,6 +637,16 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, remaining -= TCPOLEN_SACKPERM_ALIGNED; } + if (fastopen && fastopen->cookie.len >= 0) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = &fastopen->cookie; + remaining -= need; + tp->syn_fastopen = 1; + } + } /* Note that timestamps are required by the specification. * * Odd numbers of bytes are prohibited by the specification, ensuring @@ -2824,6 +2835,96 @@ void tcp_connect_init(struct sock *sk) tcp_clear_retrans(tp); } +static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + tcb->end_seq += skb->len; + skb_header_release(skb); + __tcp_add_write_queue_tail(sk, skb); + sk->sk_wmem_queued += skb->truesize; + sk_mem_charge(sk, skb->truesize); + tp->write_seq = tcb->end_seq; + tp->packets_out += tcp_skb_pcount(skb); +} + +/* Build and send a SYN with data and (cached) Fast Open cookie. However, + * queue a data-only packet after the regular SYN, such that regular SYNs + * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges + * only the SYN sequence, the data are retransmitted in the first ACK. + * If cookie is not cached or other error occurs, falls back to send a + * regular SYN with Fast Open cookie request option. + */ +static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_fastopen_request *fo = tp->fastopen_req; + int space, i, err = 0, iovlen = fo->data->msg_iovlen; + struct sk_buff *syn_data = NULL, *data; + + tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie); + if (fo->cookie.len <= 0) + goto fallback; + + /* MSS for SYN-data is based on cached MSS and bounded by PMTU and + * user-MSS. Reserve maximum option space for middleboxes that add + * private TCP options. The cost is reduced data space in SYN :( + */ + if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) + tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; + space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + MAX_TCP_OPTION_SPACE; + + syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + sk->sk_allocation); + if (syn_data == NULL) + goto fallback; + + for (i = 0; i < iovlen && syn_data->len < space; ++i) { + struct iovec *iov = &fo->data->msg_iov[i]; + unsigned char __user *from = iov->iov_base; + int len = iov->iov_len; + + if (syn_data->len + len > space) + len = space - syn_data->len; + else if (i + 1 == iovlen) + /* No more data pending in inet_wait_for_connect() */ + fo->data = NULL; + + if (skb_add_data(syn_data, from, len)) + goto fallback; + } + + /* Queue a data-only packet after the regular SYN for retransmission */ + data = pskb_copy(syn_data, sk->sk_allocation); + if (data == NULL) + goto fallback; + TCP_SKB_CB(data)->seq++; + TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); + tcp_connect_queue_skb(sk, data); + fo->copied = data->len; + + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + goto done; + } + syn_data = NULL; + +fallback: + /* Send a regular SYN with Fast Open cookie request option */ + if (fo->cookie.len > 0) + fo->cookie.len = 0; + err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); + if (err) + tp->syn_fastopen = 0; + kfree_skb(syn_data); +done: + fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ + return err; +} + /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { @@ -2841,17 +2942,13 @@ int tcp_connect(struct sock *sk) skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); + tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; + tcp_connect_queue_skb(sk, buff); TCP_ECN_send_syn(sk, buff); - /* Send it off. */ - TCP_SKB_CB(buff)->when = tcp_time_stamp; - tp->retrans_stamp = TCP_SKB_CB(buff)->when; - skb_header_release(buff); - __tcp_add_write_queue_tail(sk, buff); - sk->sk_wmem_queued += buff->truesize; - sk_mem_charge(sk, buff->truesize); - tp->packets_out += tcp_skb_pcount(buff); - err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + /* Send off SYN; include data in Fast Open. */ + err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : + tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; -- cgit v1.2.3 From cf60af03ca4e71134206809ea892e49b92a88896 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 19 Jul 2012 06:43:09 +0000 Subject: net-tcp: Fast Open client - sendmsg(MSG_FASTOPEN) sendmsg() (or sendto()) with MSG_FASTOPEN is a combo of connect(2) and write(2). The application should replace connect() with it to send data in the opening SYN packet. For blocking socket, sendmsg() blocks until all the data are buffered locally and the handshake is completed like connect() call. It returns similar errno like connect() if the TCP handshake fails. For non-blocking socket, it returns the number of bytes queued (and transmitted in the SYN-data packet) if cookie is available. If cookie is not available, it transmits a data-less SYN packet with Fast Open cookie request option and returns -EINPROGRESS like connect(). Using MSG_FASTOPEN on connecting or connected socket will result in simlar errno like repeating connect() calls. Therefore the application should only use this flag on new sockets. The buffer size of sendmsg() is independent of the MSS of the connection. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 11 ++++++ include/linux/socket.h | 1 + include/net/inet_common.h | 6 ++-- include/net/tcp.h | 3 ++ net/ipv4/af_inet.c | 19 ++++++++--- net/ipv4/tcp.c | 61 +++++++++++++++++++++++++++++++--- net/ipv4/tcp_ipv4.c | 3 ++ 7 files changed, 92 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e1e021594cff..03964e088180 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -468,6 +468,17 @@ tcp_syncookies - BOOLEAN SYN flood warnings in logs not being really flooded, your server is seriously misconfigured. +tcp_fastopen - INTEGER + Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data + in the opening SYN packet. To use this feature, the client application + must not use connect(). Instead, it should use sendmsg() or sendto() + with MSG_FASTOPEN flag which performs a TCP handshake automatically. + + The values (bitmap) are: + 1: Enables sending data in the opening SYN on the client + + Default: 0 + tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt will be retransmitted. Should not be higher than 255. Default value diff --git a/include/linux/socket.h b/include/linux/socket.h index 25d6322fb635..ba7b2e817cfa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -268,6 +268,7 @@ struct ucred { #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ #define MSG_EOF MSG_FIN +#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exit for file descriptor received through SCM_RIGHTS */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 22fac9892b16..234008782c8c 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -14,9 +14,11 @@ struct sockaddr; struct socket; extern int inet_release(struct socket *sock); -extern int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr, +extern int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); -extern int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, +extern int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags); +extern int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); extern int inet_accept(struct socket *sock, struct socket *newsock, int flags); extern int inet_sendmsg(struct kiocb *iocb, struct socket *sock, diff --git a/include/net/tcp.h b/include/net/tcp.h index 867557b4244a..c0258100d70c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -212,6 +212,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ #define TCP_INIT_CWND 10 +/* Bit Flags for sysctl_tcp_fastopen */ +#define TFO_CLIENT_ENABLE 1 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index edc414625be2..fe4582ca969a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -585,8 +585,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ -int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) +int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) { struct sock *sk = sock->sk; int err; @@ -595,8 +595,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; - lock_sock(sk); - if (uaddr->sa_family == AF_UNSPEC) { err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; @@ -663,7 +661,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; err = 0; out: - release_sock(sk); return err; sock_error: @@ -673,6 +670,18 @@ sock_error: sock->state = SS_DISCONNECTING; goto out; } +EXPORT_SYMBOL(__inet_stream_connect); + +int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + int err; + + lock_sock(sock->sk); + err = __inet_stream_connect(sock, uaddr, addr_len, flags); + release_sock(sock->sk); + return err; +} EXPORT_SYMBOL(inet_stream_connect); /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4252cd8f39fd..581ecf02c6b5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -270,6 +270,7 @@ #include #include +#include #include #include #include @@ -982,26 +983,67 @@ static inline int select_size(const struct sock *sk, bool sg) return tmp; } +void tcp_free_fastopen_req(struct tcp_sock *tp) +{ + if (tp->fastopen_req != NULL) { + kfree(tp->fastopen_req); + tp->fastopen_req = NULL; + } +} + +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +{ + struct tcp_sock *tp = tcp_sk(sk); + int err, flags; + + if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) + return -EOPNOTSUPP; + if (tp->fastopen_req != NULL) + return -EALREADY; /* Another Fast Open is in progress */ + + tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), + sk->sk_allocation); + if (unlikely(tp->fastopen_req == NULL)) + return -ENOBUFS; + tp->fastopen_req->data = msg; + + flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; + err = __inet_stream_connect(sk->sk_socket, msg->msg_name, + msg->msg_namelen, flags); + *size = tp->fastopen_req->copied; + tcp_free_fastopen_req(tp); + return err; +} + int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int iovlen, flags, err, copied; - int mss_now = 0, size_goal; + int iovlen, flags, err, copied = 0; + int mss_now = 0, size_goal, copied_syn = 0, offset = 0; bool sg; long timeo; lock_sock(sk); flags = msg->msg_flags; + if (flags & MSG_FASTOPEN) { + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + if (err == -EINPROGRESS && copied_syn > 0) + goto out; + else if (err) + goto out_err; + offset = copied_syn; + } + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); /* Wait for a connection to finish. */ if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) - goto out_err; + goto do_error; if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { @@ -1037,6 +1079,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, unsigned char __user *from = iov->iov_base; iov++; + if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */ + if (offset >= seglen) { + offset -= seglen; + continue; + } + seglen -= offset; + from += offset; + offset = 0; + } while (seglen > 0) { int copy = 0; @@ -1199,7 +1250,7 @@ out: if (copied && likely(!tp->repair)) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); - return copied; + return copied + copied_syn; do_fault: if (!skb->len) { @@ -1212,7 +1263,7 @@ do_fault: } do_error: - if (copied) + if (copied + copied_syn) goto out; out_err: err = sk_stream_error(sk, flags, err); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 01aa77a97020..1d8b75a58981 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1952,6 +1952,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tp->cookie_values = NULL; } + /* If socket is aborted during connect operation */ + tcp_free_fastopen_req(tp); + sk_sockets_allocated_dec(sk); sock_release_memcg(sk); } -- cgit v1.2.3 From 67da22d23fa6f3324e03bcd0580b914b2e4afbf3 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 19 Jul 2012 06:43:11 +0000 Subject: net-tcp: Fast Open client - cookie-less mode In trusted networks, e.g., intranet, data-center, the client does not need to use Fast Open cookie to mitigate DoS attacks. In cookie-less mode, sendmsg() with MSG_FASTOPEN flag will send SYN-data regardless of cookie availability. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 2 ++ include/linux/tcp.h | 1 + include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 8 ++++++-- net/ipv4/tcp_output.c | 6 +++++- 5 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 03964e088180..5f3ef7f7fcec 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -476,6 +476,8 @@ tcp_fastopen - INTEGER The values (bitmap) are: 1: Enables sending data in the opening SYN on the client + 5: Enables sending data in the opening SYN on the client regardless + of cookie availability. Default: 0 diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1edf96afab44..9febfb685c33 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -387,6 +387,7 @@ struct tcp_sock { u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ early_retrans_delayed:1, /* Delayed ER timer installed */ + syn_data:1, /* SYN includes data */ syn_fastopen:1; /* SYN includes Fast Open option */ /* RTT measurement */ diff --git a/include/net/tcp.h b/include/net/tcp.h index e07878d246aa..bc7c134ec054 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -214,6 +214,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 +#define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ extern struct inet_timewait_death_row tcp_death_row; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c49a4fc175bd..e67d685a6c0e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5650,7 +5650,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *data = tcp_write_queue_head(sk); + struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp; bool syn_drop; @@ -5665,6 +5665,9 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, mss = opt.mss_clamp; } + if (!tp->syn_fastopen) /* Ignore an unsolicited cookie */ + cookie->len = -1; + /* The SYN-ACK neither has cookie nor acknowledges the data. Presumably * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. @@ -5816,7 +5819,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_finish_connect(sk, skb); - if (tp->syn_fastopen && tcp_rcv_fastopen_synack(sk, skb, &foc)) + if ((tp->syn_fastopen || tp->syn_data) && + tcp_rcv_fastopen_synack(sk, skb, &foc)) return -1; if (sk->sk_write_pending || diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c5cfd5ec3184..27a32acfdb62 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2864,6 +2864,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) struct sk_buff *syn_data = NULL, *data; unsigned long last_syn_loss = 0; + tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, &syn_loss, &last_syn_loss); /* Recurring FO SYN losses: revert to regular handshake temporarily */ @@ -2873,7 +2874,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; } - if (fo->cookie.len <= 0) + if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) + fo->cookie.len = -1; + else if (fo->cookie.len <= 0) goto fallback; /* MSS for SYN-data is based on cached MSS and bounded by PMTU and @@ -2916,6 +2919,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) fo->copied = data->len; if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); goto done; } -- cgit v1.2.3 From 194b9a4cb91713ddb60c9f98f7212f6d8cb8e05f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 16 Jul 2012 12:58:31 +0200 Subject: can: mark bittiming_const pointer in struct can_priv as const This patch marks the bittiming_const pointer as in the struct can_pric as "const". This allows us to mark the struct can_bittiming_const in the CAN drivers as "const", too. Signed-off-by: Marc Kleine-Budde --- drivers/net/can/at91_can.c | 2 +- drivers/net/can/bfin_can.c | 2 +- drivers/net/can/c_can/c_can.c | 2 +- drivers/net/can/cc770/cc770.c | 2 +- drivers/net/can/flexcan.c | 2 +- drivers/net/can/janz-ican3.c | 2 +- drivers/net/can/mcp251x.c | 2 +- drivers/net/can/mscan/mscan.c | 2 +- drivers/net/can/pch_can.c | 2 +- drivers/net/can/sja1000/sja1000.c | 2 +- drivers/net/can/ti_hecc.c | 2 +- drivers/net/can/usb/ems_usb.c | 2 +- drivers/net/can/usb/esd_usb2.c | 2 +- drivers/net/can/usb/peak_usb/pcan_usb_core.h | 2 +- include/linux/can/dev.h | 2 +- 15 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 6ea905c2cf6d..fcff73a73b1d 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -170,7 +170,7 @@ static const struct at91_devtype_data at91_devtype_data[] __devinitconst = { }, }; -static struct can_bittiming_const at91_bittiming_const = { +static const struct can_bittiming_const at91_bittiming_const = { .name = KBUILD_MODNAME, .tseg1_min = 4, .tseg1_max = 16, diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c index ea3143895e6d..f2d6d258a286 100644 --- a/drivers/net/can/bfin_can.c +++ b/drivers/net/can/bfin_can.c @@ -44,7 +44,7 @@ struct bfin_can_priv { /* * bfin can timing parameters */ -static struct can_bittiming_const bfin_can_bittiming_const = { +static const struct can_bittiming_const bfin_can_bittiming_const = { .name = DRV_NAME, .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index eea660800a09..4c538e388655 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -189,7 +189,7 @@ enum c_can_bus_error_types { C_CAN_ERROR_PASSIVE, }; -static struct can_bittiming_const c_can_bittiming_const = { +static const struct can_bittiming_const c_can_bittiming_const = { .name = KBUILD_MODNAME, .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ .tseg1_max = 16, diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index a138db11cbf0..0f12abf6591c 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -90,7 +90,7 @@ static unsigned char cc770_obj_flags[CC770_OBJ_MAX] = { [CC770_OBJ_TX] = 0, }; -static struct can_bittiming_const cc770_bittiming_const = { +static const struct can_bittiming_const cc770_bittiming_const = { .name = KBUILD_MODNAME, .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 1b6f5621ce89..c8a6fc72606d 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -203,7 +203,7 @@ static struct flexcan_devtype_data fsl_imx6q_devtype_data = { .hw_ver = 10, }; -static struct can_bittiming_const flexcan_bittiming_const = { +static const struct can_bittiming_const flexcan_bittiming_const = { .name = DRV_NAME, .tseg1_min = 4, .tseg1_max = 16, diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 08c893cb7896..e7d1532d5f1b 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1490,7 +1490,7 @@ static const struct net_device_ops ican3_netdev_ops = { */ /* This structure was stolen from drivers/net/can/sja1000/sja1000.c */ -static struct can_bittiming_const ican3_bittiming_const = { +static const struct can_bittiming_const ican3_bittiming_const = { .name = DRV_NAME, .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 9120a36ec702..a580db29e503 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -214,7 +214,7 @@ static int mcp251x_enable_dma; /* Enable SPI DMA. Default: 0 (Off) */ module_param(mcp251x_enable_dma, int, S_IRUGO); MODULE_PARM_DESC(mcp251x_enable_dma, "Enable SPI DMA. Default: 0 (Off)"); -static struct can_bittiming_const mcp251x_bittiming_const = { +static const struct can_bittiming_const mcp251x_bittiming_const = { .name = DEVICE_NAME, .tseg1_min = 3, .tseg1_max = 16, diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 41a2a2dda7ea..2b104d5f422c 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -34,7 +34,7 @@ #include "mscan.h" -static struct can_bittiming_const mscan_bittiming_const = { +static const struct can_bittiming_const mscan_bittiming_const = { .name = "mscan", .tseg1_min = 4, .tseg1_max = 16, diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index 1226297e7676..48b3d62b34cb 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -184,7 +184,7 @@ struct pch_can_priv { int use_msi; }; -static struct can_bittiming_const pch_can_bittiming_const = { +static const struct can_bittiming_const pch_can_bittiming_const = { .name = KBUILD_MODNAME, .tseg1_min = 2, .tseg1_max = 16, diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 5e10472371ed..4c4f33d482d2 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -69,7 +69,7 @@ MODULE_AUTHOR("Oliver Hartkopp "); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION(DRV_NAME "CAN netdevice driver"); -static struct can_bittiming_const sja1000_bittiming_const = { +static const struct can_bittiming_const sja1000_bittiming_const = { .name = DRV_NAME, .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 4accd7ec6954..527dbcf95335 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -196,7 +196,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_CANGIM_SIL BIT(2) /* system interrupts to int line 1 */ /* CAN Bittiming constants as per HECC specs */ -static struct can_bittiming_const ti_hecc_bittiming_const = { +static const struct can_bittiming_const ti_hecc_bittiming_const = { .name = DRV_NAME, .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 7ae65fc80032..086fa321677a 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -889,7 +889,7 @@ static const struct net_device_ops ems_usb_netdev_ops = { .ndo_start_xmit = ems_usb_start_xmit, }; -static struct can_bittiming_const ems_usb_bittiming_const = { +static const struct can_bittiming_const ems_usb_bittiming_const = { .name = "ems_usb", .tseg1_min = 1, .tseg1_max = 16, diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 09b1da5bc512..bd36e5517173 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -871,7 +871,7 @@ static const struct net_device_ops esd_usb2_netdev_ops = { .ndo_start_xmit = esd_usb2_start_xmit, }; -static struct can_bittiming_const esd_usb2_bittiming_const = { +static const struct can_bittiming_const esd_usb2_bittiming_const = { .name = "esd_usb2", .tseg1_min = ESD_USB2_TSEG1_MIN, .tseg1_max = ESD_USB2_TSEG1_MAX, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index a948c5a89401..4c775b620be2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -45,7 +45,7 @@ struct peak_usb_adapter { char *name; u32 device_id; struct can_clock clock; - struct can_bittiming_const bittiming_const; + const struct can_bittiming_const bittiming_const; unsigned int ctrl_count; int (*intf_probe)(struct usb_interface *intf); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index ee5a771fb20d..2b2fc345afca 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -33,7 +33,7 @@ struct can_priv { struct can_device_stats can_stats; struct can_bittiming bittiming; - struct can_bittiming_const *bittiming_const; + const struct can_bittiming_const *bittiming_const; struct can_clock clock; enum can_state state; -- cgit v1.2.3 From 6f458dfb409272082c9bfa412f77ff2fc21c626f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jul 2012 05:45:50 +0000 Subject: tcp: improve latencies of timer triggered events Modern TCP stack highly depends on tcp_write_timer() having a small latency, but current implementation doesn't exactly meet the expectations. When a timer fires but finds the socket is owned by the user, it rearms itself for an additional delay hoping next run will be more successful. tcp_write_timer() for example uses a 50ms delay for next try, and it defeats many attempts to get predictable TCP behavior in term of latencies. Use the recently introduced tcp_release_cb(), so that the user owning the socket will call various handlers right before socket release. This will permit us to post a followup patch to address the tcp_tso_should_defer() syndrome (some deferred packets have to wait RTO timer to be transmitted, while cwnd should allow us to send them sooner) Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Nandita Dukkipati Cc: H.K. Jerry Chu Cc: John Heffner Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++- include/net/tcp.h | 2 ++ net/ipv4/tcp_output.c | 46 ++++++++++++++++++++------------- net/ipv4/tcp_timer.c | 70 +++++++++++++++++++++++++++------------------------ 4 files changed, 71 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9febfb685c33..2761856987b2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -515,7 +515,9 @@ struct tcp_sock { enum tsq_flags { TSQ_THROTTLED, TSQ_QUEUED, - TSQ_OWNED, /* tcp_tasklet_func() found socket was locked */ + TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */ + TCP_WRITE_TIMER_DEFERRED, /* tcp_write_timer() found socket was owned */ + TCP_DELACK_TIMER_DEFERRED, /* tcp_delack_timer() found socket was owned */ }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index bc7c134ec054..e19124b84cd2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -350,6 +350,8 @@ extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, extern int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); extern void tcp_release_cb(struct sock *sk); +extern void tcp_write_timer_handler(struct sock *sk); +extern void tcp_delack_timer_handler(struct sock *sk); extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 27a32acfdb62..950aebfd9967 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -837,6 +837,13 @@ struct tsq_tasklet { }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); +static void tcp_tsq_handler(struct sock *sk) +{ + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | + TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) + tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); +} /* * One tasklest per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when @@ -864,16 +871,10 @@ static void tcp_tasklet_func(unsigned long data) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - if ((1 << sk->sk_state) & - (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | - TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, - tcp_current_mss(sk), - 0, 0, - GFP_ATOMIC); + tcp_tsq_handler(sk); } else { /* defer the work to tcp_release_cb() */ - set_bit(TSQ_OWNED, &tp->tsq_flags); + set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags); } bh_unlock_sock(sk); @@ -882,6 +883,9 @@ static void tcp_tasklet_func(unsigned long data) } } +#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) | \ + (1UL << TCP_WRITE_TIMER_DEFERRED) | \ + (1UL << TCP_DELACK_TIMER_DEFERRED)) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket @@ -892,16 +896,24 @@ static void tcp_tasklet_func(unsigned long data) void tcp_release_cb(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + unsigned long flags, nflags; - if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) { - if ((1 << sk->sk_state) & - (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | - TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, - tcp_current_mss(sk), - 0, 0, - GFP_ATOMIC); - } + /* perform an atomic operation only if at least one flag is set */ + do { + flags = tp->tsq_flags; + if (!(flags & TCP_DEFERRED_ALL)) + return; + nflags = flags & ~TCP_DEFERRED_ALL; + } while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags); + + if (flags & (1UL << TCP_TSQ_DEFERRED)) + tcp_tsq_handler(sk); + + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) + tcp_write_timer_handler(sk); + + if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) + tcp_delack_timer_handler(sk); } EXPORT_SYMBOL(tcp_release_cb); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index e911e6c523ec..6df36ad55a38 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -32,17 +32,6 @@ int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; int sysctl_tcp_thin_linear_timeouts __read_mostly; -static void tcp_write_timer(unsigned long); -static void tcp_delack_timer(unsigned long); -static void tcp_keepalive_timer (unsigned long data); - -void tcp_init_xmit_timers(struct sock *sk) -{ - inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, - &tcp_keepalive_timer); -} -EXPORT_SYMBOL(tcp_init_xmit_timers); - static void tcp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; @@ -205,21 +194,11 @@ static int tcp_write_timeout(struct sock *sk) return 0; } -static void tcp_delack_timer(unsigned long data) +void tcp_delack_timer_handler(struct sock *sk) { - struct sock *sk = (struct sock *)data; struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later. */ - icsk->icsk_ack.blocked = 1; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); - sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); - goto out_unlock; - } - sk_mem_reclaim_partial(sk); if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) @@ -260,7 +239,21 @@ static void tcp_delack_timer(unsigned long data) out: if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); -out_unlock: +} + +static void tcp_delack_timer(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + tcp_delack_timer_handler(sk); + } else { + inet_csk(sk)->icsk_ack.blocked = 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); + /* deleguate our work to tcp_release_cb() */ + set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags); + } bh_unlock_sock(sk); sock_put(sk); } @@ -450,19 +443,11 @@ out_reset_timer: out:; } -static void tcp_write_timer(unsigned long data) +void tcp_write_timer_handler(struct sock *sk) { - struct sock *sk = (struct sock *)data; struct inet_connection_sock *icsk = inet_csk(sk); int event; - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later */ - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20)); - goto out_unlock; - } - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) goto out; @@ -485,7 +470,19 @@ static void tcp_write_timer(unsigned long data) out: sk_mem_reclaim(sk); -out_unlock: +} + +static void tcp_write_timer(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + tcp_write_timer_handler(sk); + } else { + /* deleguate our work to tcp_release_cb() */ + set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags); + } bh_unlock_sock(sk); sock_put(sk); } @@ -602,3 +599,10 @@ out: bh_unlock_sock(sk); sock_put(sk); } + +void tcp_init_xmit_timers(struct sock *sk) +{ + inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, + &tcp_keepalive_timer); +} +EXPORT_SYMBOL(tcp_init_xmit_timers); -- cgit v1.2.3 From ee6ae1a1d58c70fc864bc777a36be56b0880ebff Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 20 Jul 2012 02:28:46 +0000 Subject: net: honour netif_set_real_num_tx_queues() retval In netif_copy_real_num_queues() the return value of netif_set_real_num_tx_queues() should be checked. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ab0251d541ab..eb06e58bed0b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2110,7 +2110,12 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, static inline int netif_copy_real_num_queues(struct net_device *to_dev, const struct net_device *from_dev) { - netif_set_real_num_tx_queues(to_dev, from_dev->real_num_tx_queues); + int err; + + err = netif_set_real_num_tx_queues(to_dev, + from_dev->real_num_tx_queues); + if (err) + return err; #ifdef CONFIG_RPS return netif_set_real_num_rx_queues(to_dev, from_dev->real_num_rx_queues); -- cgit v1.2.3 From 76ff5cc91935c51fcf1a6a99ffa28b97a6e7a884 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 20 Jul 2012 02:28:48 +0000 Subject: rtnl: allow to specify number of rx and tx queues on device creation This patch introduces IFLA_NUM_TX_QUEUES and IFLA_NUM_RX_QUEUES by which userspace can set number of rx and/or tx queues to be allocated for newly created netdevice. This overrides ops->get_num_[tr]x_queues() Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_link.h | 2 ++ net/core/rtnetlink.c | 15 +++++++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index f715750d0b87..ac173bd2ab65 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -140,6 +140,8 @@ enum { IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ #define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, __IFLA_MAX }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index db5a8ad8a79b..5bb1ebca2eb0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -771,6 +771,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_PROMISCUITY */ + + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(ext_filter_mask @@ -889,6 +891,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u32(skb, IFLA_GROUP, dev->group) || nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || + nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || + nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || (dev->ifindex != dev->iflink && nla_put_u32(skb, IFLA_LINK, dev->iflink)) || (dev->master && @@ -1106,6 +1110,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_AF_SPEC] = { .type = NLA_NESTED }, [IFLA_EXT_MASK] = { .type = NLA_U32 }, [IFLA_PROMISCUITY] = { .type = NLA_U32 }, + [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, + [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1627,9 +1633,14 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; - if (ops->get_num_tx_queues) + if (tb[IFLA_NUM_TX_QUEUES]) + num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); + else if (ops->get_num_tx_queues) num_tx_queues = ops->get_num_tx_queues(); - if (ops->get_num_rx_queues) + + if (tb[IFLA_NUM_RX_QUEUES]) + num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]); + else if (ops->get_num_rx_queues) num_rx_queues = ops->get_num_rx_queues(); err = -ENOMEM; -- cgit v1.2.3 From 6c85f2bdda2086d804e198a3f31b685bc2f86b04 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 20 Jul 2012 02:28:51 +0000 Subject: team: add multiqueue support Largely copied from bonding code. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 65 +++++++++++++++++++++++++++++++++++++++++++++---- include/linux/if_team.h | 8 ++++++ 2 files changed, 68 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 813e1319095f..b104c05225f7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #define DRV_NAME "team" @@ -1121,6 +1122,22 @@ static const struct team_option team_options[] = { }, }; +static struct lock_class_key team_netdev_xmit_lock_key; +static struct lock_class_key team_netdev_addr_lock_key; + +static void team_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *unused) +{ + lockdep_set_class(&txq->_xmit_lock, &team_netdev_xmit_lock_key); +} + +static void team_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &team_netdev_addr_lock_key); + netdev_for_each_tx_queue(dev, team_set_lockdep_class_one, NULL); +} + static int team_init(struct net_device *dev) { struct team *team = netdev_priv(dev); @@ -1148,6 +1165,8 @@ static int team_init(struct net_device *dev) goto err_options_register; netif_carrier_off(dev); + team_set_lockdep_class(dev); + return 0; err_options_register: @@ -1216,6 +1235,29 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + /* + * This helper function exists to help dev_pick_tx get the correct + * destination queue. Using a helper function skips a call to + * skb_tx_hash and will put the skbs in the queue we expect on their + * way down to the team driver. + */ + u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; + + /* + * Save the original txq to restore before passing to the driver + */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + + if (unlikely(txq >= dev->real_num_tx_queues)) { + do { + txq -= dev->real_num_tx_queues; + } while (txq >= dev->real_num_tx_queues); + } + return txq; +} + static void team_change_rx_flags(struct net_device *dev, int change) { struct team *team = netdev_priv(dev); @@ -1469,6 +1511,7 @@ static const struct net_device_ops team_netdev_ops = { .ndo_open = team_open, .ndo_stop = team_close, .ndo_start_xmit = team_xmit, + .ndo_select_queue = team_select_queue, .ndo_change_rx_flags = team_change_rx_flags, .ndo_set_rx_mode = team_set_rx_mode, .ndo_set_mac_address = team_set_mac_address, @@ -1543,12 +1586,24 @@ static int team_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static unsigned int team_get_num_tx_queues(void) +{ + return TEAM_DEFAULT_NUM_TX_QUEUES; +} + +static unsigned int team_get_num_rx_queues(void) +{ + return TEAM_DEFAULT_NUM_RX_QUEUES; +} + static struct rtnl_link_ops team_link_ops __read_mostly = { - .kind = DRV_NAME, - .priv_size = sizeof(struct team), - .setup = team_setup, - .newlink = team_newlink, - .validate = team_validate, + .kind = DRV_NAME, + .priv_size = sizeof(struct team), + .setup = team_setup, + .newlink = team_newlink, + .validate = team_validate, + .get_num_tx_queues = team_get_num_tx_queues, + .get_num_rx_queues = team_get_num_rx_queues, }; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 7fd0cdeb9444..6960fc1841a7 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -14,6 +14,7 @@ #ifdef __KERNEL__ #include +#include struct team_pcpu_stats { u64 rx_packets; @@ -98,6 +99,10 @@ static inline void team_netpoll_send_skb(struct team_port *port, static inline int team_dev_queue_xmit(struct team *team, struct team_port *port, struct sk_buff *skb) { + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); + skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); + skb->dev = port->dev; if (unlikely(netpoll_tx_running(port->dev))) { team_netpoll_send_skb(port, skb); @@ -236,6 +241,9 @@ extern void team_options_unregister(struct team *team, extern int team_mode_register(const struct team_mode *mode); extern void team_mode_unregister(const struct team_mode *mode); +#define TEAM_DEFAULT_NUM_TX_QUEUES 16 +#define TEAM_DEFAULT_NUM_RX_QUEUES 16 + #endif /* __KERNEL__ */ #define TEAM_STRING_MAX_LEN 32 -- cgit v1.2.3 From b09e786bd1dd66418b69348cb110f3a64764626a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 19 Jul 2012 06:13:36 +0000 Subject: tun: fix a crash bug and a memory leak This patch fixes a crash tun_chr_close -> netdev_run_todo -> tun_free_netdev -> sk_release_kernel -> sock_release -> iput(SOCK_INODE(sock)) introduced by commit 1ab5ecb90cb6a3df1476e052f76a6e8f6511cb3d The problem is that this socket is embedded in struct tun_struct, it has no inode, iput is called on invalid inode, which modifies invalid memory and optionally causes a crash. sock_release also decrements sockets_in_use, this causes a bug that "sockets: used" field in /proc/*/net/sockstat keeps on decreasing when creating and closing tun devices. This patch introduces a flag SOCK_EXTERNALLY_ALLOCATED that instructs sock_release to not free the inode and not decrement sockets_in_use, fixing both memory corruption and sockets_in_use underflow. It should be backported to 3.3 an 3.4 stabke. Signed-off-by: Mikulas Patocka Cc: stable@kernel.org Signed-off-by: David S. Miller --- drivers/net/tun.c | 3 +++ include/linux/net.h | 1 + net/socket.c | 3 +++ 3 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 961fad1f7053..f3a454c3295a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -358,6 +358,8 @@ static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); + BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED, &tun->socket.flags)); + sk_release_kernel(tun->socket.sk); } @@ -1115,6 +1117,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); + set_bit(SOCK_EXTERNALLY_ALLOCATED, &tun->socket.flags); err = -ENOMEM; sk = sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL, &tun_proto); diff --git a/include/linux/net.h b/include/linux/net.h index e9ac2df079ba..dc95700de5df 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -72,6 +72,7 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define SOCK_EXTERNALLY_ALLOCATED 5 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/net/socket.c b/net/socket.c index 6e0ccc09b313..0452dca4cd24 100644 --- a/net/socket.c +++ b/net/socket.c @@ -522,6 +522,9 @@ void sock_release(struct socket *sock) if (rcu_dereference_protected(sock->wq, 1)->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); + if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags)) + return; + this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); -- cgit v1.2.3 From a353e0ce0fd42d8859260666d1e9b10f2abd4698 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 20 Jul 2012 09:23:07 +0000 Subject: skbuff: add an api to orphan frags Many places do if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY)) skb_copy_ubufs(skb, gfp_mask); to copy and invoke frag destructors if necessary. Add an inline helper for this. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 642cb7355df3..d205c4be7f5b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1666,6 +1666,22 @@ static inline void skb_orphan(struct sk_buff *skb) skb->sk = NULL; } +/** + * skb_orphan_frags - orphan the frags contained in a buffer + * @skb: buffer to orphan frags from + * @gfp_mask: allocation mask for replacement pages + * + * For each frag in the SKB which needs a destructor (i.e. has an + * owner) create a copy of that frag and release the original + * page by calling the destructor. + */ +static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + /** * __skb_queue_purge - empty a list * @list: list to empty -- cgit v1.2.3 From 406a3c638ce8b17d9704052c07955490f732c2b8 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 20 Jul 2012 10:39:25 +0000 Subject: net: netprio_cgroup: rework update socket logic Instead of updating the sk_cgrp_prioidx struct field on every send this only updates the field when a task is moved via cgroup infrastructure. This allows sockets that may be used by a kernel worker thread to be managed. For example in the iscsi case today a user can put iscsid in a netprio cgroup and control traffic will be sent with the correct sk_cgrp_prioidx value set but as soon as data is sent the kernel worker thread isssues a send and sk_cgrp_prioidx is updated with the kernel worker threads value which is the default case. It seems more correct to only update the field when the user explicitly sets it via control group infrastructure. This allows the users to manage sockets that may be used with other threads. Signed-off-by: John Fastabend Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/linux/net.h | 1 + include/net/netprio_cgroup.h | 4 ++-- net/core/netprio_cgroup.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ net/core/sock.c | 6 ++--- net/socket.c | 5 ++--- 5 files changed, 61 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index dc95700de5df..99276c3dc89a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -248,6 +248,7 @@ extern int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); extern int sock_map_fd(struct socket *sock, int flags); extern struct socket *sockfd_lookup(int fd, int *err); +extern struct socket *sock_from_file(struct file *file, int *err); #define sockfd_put(sock) fput(sock->file) extern int net_ratelimit(void); diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index d58fdec47597..2719dec6b5a8 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -35,7 +35,7 @@ struct cgroup_netprio_state { extern int net_prio_subsys_id; #endif -extern void sock_update_netprioidx(struct sock *sk); +extern void sock_update_netprioidx(struct sock *sk, struct task_struct *task); #if IS_BUILTIN(CONFIG_NETPRIO_CGROUP) @@ -82,7 +82,7 @@ static inline u32 task_netprioidx(struct task_struct *p) #endif /* CONFIG_NETPRIO_CGROUP */ #else -#define sock_update_netprioidx(sk) +#define sock_update_netprioidx(sk, task) #endif #endif /* _NET_CLS_CGROUP_H */ diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index b2e9caa1ad1a..63d15e8f80e9 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -25,6 +25,8 @@ #include #include +#include + #define PRIOIDX_SZ 128 static unsigned long prioidx_map[PRIOIDX_SZ]; @@ -272,6 +274,56 @@ out_free_devname: return ret; } +void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +{ + struct task_struct *p; + char *tmp = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); + + if (!tmp) { + pr_warn("Unable to attach cgrp due to alloc failure!\n"); + return; + } + + cgroup_taskset_for_each(p, cgrp, tset) { + unsigned int fd; + struct fdtable *fdt; + struct files_struct *files; + + task_lock(p); + files = p->files; + if (!files) { + task_unlock(p); + continue; + } + + rcu_read_lock(); + fdt = files_fdtable(files); + for (fd = 0; fd < fdt->max_fds; fd++) { + char *path; + struct file *file; + struct socket *sock; + unsigned long s; + int rv, err = 0; + + file = fcheck_files(files, fd); + if (!file) + continue; + + path = d_path(&file->f_path, tmp, PAGE_SIZE); + rv = sscanf(path, "socket:[%lu]", &s); + if (rv <= 0) + continue; + + sock = sock_from_file(file, &err); + if (!err) + sock_update_netprioidx(sock->sk, p); + } + rcu_read_unlock(); + task_unlock(p); + } + kfree(tmp); +} + static struct cftype ss_files[] = { { .name = "prioidx", @@ -289,6 +341,7 @@ struct cgroup_subsys net_prio_subsys = { .name = "net_prio", .create = cgrp_create, .destroy = cgrp_destroy, + .attach = net_prio_attach, #ifdef CONFIG_NETPRIO_CGROUP .subsys_id = net_prio_subsys_id, #endif diff --git a/net/core/sock.c b/net/core/sock.c index 24039ac12426..2676a88f533e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1180,12 +1180,12 @@ void sock_update_classid(struct sock *sk) } EXPORT_SYMBOL(sock_update_classid); -void sock_update_netprioidx(struct sock *sk) +void sock_update_netprioidx(struct sock *sk, struct task_struct *task) { if (in_interrupt()) return; - sk->sk_cgrp_prioidx = task_netprioidx(current); + sk->sk_cgrp_prioidx = task_netprioidx(task); } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif @@ -1215,7 +1215,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); - sock_update_netprioidx(sk); + sock_update_netprioidx(sk, current); } return sk; diff --git a/net/socket.c b/net/socket.c index 0452dca4cd24..dfe5b66c97e0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -398,7 +398,7 @@ int sock_map_fd(struct socket *sock, int flags) } EXPORT_SYMBOL(sock_map_fd); -static struct socket *sock_from_file(struct file *file, int *err) +struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) return file->private_data; /* set in sock_map_fd */ @@ -406,6 +406,7 @@ static struct socket *sock_from_file(struct file *file, int *err) *err = -ENOTSOCK; return NULL; } +EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot @@ -554,8 +555,6 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, sock_update_classid(sock->sk); - sock_update_netprioidx(sock->sk); - si->sock = sock; si->scm = NULL; si->msg = msg; -- cgit v1.2.3 From 563d34d05786263893ba4a1042eb9b9374127cf5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jul 2012 09:48:52 +0200 Subject: tcp: dont drop MTU reduction indications MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ICMP messages generated in output path if frame length is bigger than mtu are actually lost because socket is owned by user (doing the xmit) One example is the ipgre_tunnel_xmit() calling icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); We had a similar case fixed in commit a34a101e1e6 (ipv6: disable GSO on sockets hitting dst_allfrag). Problem of such fix is that it relied on retransmit timers, so short tcp sessions paid a too big latency increase price. This patch uses the tcp_release_cb() infrastructure so that MTU reduction messages (ICMP messages) are not lost, and no extra delay is added in TCP transmits. Reported-by: Maciej Żenczykowski Diagnosed-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: Nandita Dukkipati Cc: Tom Herbert Cc: Tore Anderson Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ include/net/sock.h | 1 + net/ipv4/tcp_ipv4.c | 19 +++++++++++++++---- net/ipv4/tcp_output.c | 6 +++++- net/ipv6/tcp_ipv6.c | 40 ++++++++++++++++++++++++---------------- 5 files changed, 51 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2761856987b2..eb125a4c30b3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -493,6 +493,9 @@ struct tcp_sock { u32 probe_seq_start; u32 probe_seq_end; } mtu_probe; + u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG + * while socket was owned by user. + */ #ifdef CONFIG_TCP_MD5SIG /* TCP AF-Specific parts; only used by MD5 Signature support so far */ @@ -518,6 +521,9 @@ enum tsq_flags { TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */ TCP_WRITE_TIMER_DEFERRED, /* tcp_write_timer() found socket was owned */ TCP_DELACK_TIMER_DEFERRED, /* tcp_delack_timer() found socket was owned */ + TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call + * tcp_v{4|6}_mtu_reduced() + */ }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) diff --git a/include/net/sock.h b/include/net/sock.h index 88de092df50f..e067f8c18f88 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -859,6 +859,7 @@ struct proto { struct sk_buff *skb); void (*release_cb)(struct sock *sk); + void (*mtu_reduced)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 59110caeb074..bc5432e3c778 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -275,12 +275,15 @@ failure: EXPORT_SYMBOL(tcp_v4_connect); /* - * This routine does path mtu discovery as defined in RFC1191. + * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. + * It can be called through tcp_release_cb() if socket was owned by user + * at the time tcp_v4_err() was called to handle ICMP message. */ -static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) +static void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); + u32 mtu = tcp_sk(sk)->mtu_info; /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs * send out by Linux are always <576bytes so they should go through @@ -373,8 +376,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. + * We do take care of PMTU discovery (RFC1191) special case : + * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && + type != ICMP_DEST_UNREACH && + code != ICMP_FRAG_NEEDED) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) @@ -409,8 +416,11 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ + tp->mtu_info = info; if (!sock_owned_by_user(sk)) - do_pmtu_discovery(sk, iph, info); + tcp_v4_mtu_reduced(sk); + else + set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); goto out; } @@ -2596,6 +2606,7 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 950aebfd9967..33cd065cfbd8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -885,7 +885,8 @@ static void tcp_tasklet_func(unsigned long data) #define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) | \ (1UL << TCP_WRITE_TIMER_DEFERRED) | \ - (1UL << TCP_DELACK_TIMER_DEFERRED)) + (1UL << TCP_DELACK_TIMER_DEFERRED) | \ + (1UL << TCP_MTU_REDUCED_DEFERRED)) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket @@ -914,6 +915,9 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) tcp_delack_timer_handler(sk); + + if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) + sk->sk_prot->mtu_reduced(sk); } EXPORT_SYMBOL(tcp_release_cb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0302ec3fecfc..f49476e2d884 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -315,6 +315,23 @@ failure: return err; } +static void tcp_v6_mtu_reduced(struct sock *sk) +{ + struct dst_entry *dst; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + + dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + if (!dst) + return; + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + tcp_sync_mss(sk, dst_mtu(dst)); + tcp_simple_retransmit(sk); + } +} + static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -342,7 +359,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } bh_lock_sock(sk); - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) @@ -371,21 +388,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst; - - if (sock_owned_by_user(sk)) - goto out; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) - goto out; - - dst = inet6_csk_update_pmtu(sk, ntohl(info)); - if (!dst) - goto out; - - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { - tcp_sync_mss(sk, dst_mtu(dst)); - tcp_simple_retransmit(sk); - } + tp->mtu_info = ntohl(info); + if (!sock_owned_by_user(sk)) + tcp_v6_mtu_reduced(sk); + else + set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags); goto out; } @@ -1949,6 +1956,7 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, -- cgit v1.2.3 From 320f5ea0cedc08ef65d67e056bcb9d181386ef2c Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 24 Jul 2012 13:44:01 +0800 Subject: genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP lockdep_is_held() is defined when CONFIG_LOCKDEP, not CONFIG_PROVE_LOCKING. Cc: "David S. Miller" Cc: Jesse Gross Signed-off-by: WANG Cong Signed-off-by: David S. Miller --- include/linux/genetlink.h | 2 +- net/netlink/genetlink.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 7a114016ac7d..5ab61c1eb6bf 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -85,7 +85,7 @@ enum { /* All generic netlink requests are serialized by a global lock. */ extern void genl_lock(void); extern void genl_unlock(void); -#ifdef CONFIG_PROVE_LOCKING +#ifdef CONFIG_LOCKDEP extern int lockdep_genl_is_held(void); #endif diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 62ebe3c6291c..fda497412fc3 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -33,7 +33,7 @@ void genl_unlock(void) } EXPORT_SYMBOL(genl_unlock); -#ifdef CONFIG_PROVE_LOCKING +#ifdef CONFIG_LOCKDEP int lockdep_genl_is_held(void) { return lockdep_is_held(&genl_mutex); -- cgit v1.2.3