From cb2518ca9f06dfcfa3d175773631bfb1e461bdc7 Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Wed, 15 Jan 2014 09:50:13 +0100 Subject: can: add ability to allocate CANFD frame in skb data This patch adds the ability of allocating a CANFD frame data structure in the skb data area. Signed-off-by: Stephane Grosjean Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index fb0ab651a041..dc5f9026b67f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -124,6 +124,8 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); +struct sk_buff *alloc_canfd_skb(struct net_device *dev, + struct canfd_frame **cfd); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); -- cgit v1.2.3 From d8ca16db6bb23d03fcb794df44bae64ae976f27c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Jan 2014 16:20:29 +0100 Subject: mac80211: add length check in ieee80211_is_robust_mgmt_frame() A few places weren't checking that the frame passed to the function actually has enough data even though the function clearly documents it must have a payload byte. Make this safer by changing the function to take an skb and checking the length inside. The old version is preserved for now as the rtl* drivers use it and don't have a correct skb. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e526a8cecb70..923c478030a3 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2192,10 +2192,10 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) } /** - * ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame + * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) */ -static inline bool ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) +static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) { if (ieee80211_is_disassoc(hdr->frame_control) || ieee80211_is_deauth(hdr->frame_control)) @@ -2223,6 +2223,17 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) return false; } +/** + * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame + * @skb: the skb containing the frame, length will be checked + */ +static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) +{ + if (skb->len < 25) + return false; + return _ieee80211_is_robust_mgmt_frame((void *)skb->data); +} + /** * ieee80211_is_public_action - check if frame is a public action frame * @hdr: the frame -- cgit v1.2.3 From b4ba544c8c1349afd44e10aebec03c90e9b71d98 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 24 Jan 2014 14:41:44 +0100 Subject: mac80211: fix bufferable MMPDU RX handling Action, disassoc and deauth frames are bufferable, and as such don't have the PM bit in the frame control field reserved which means we need to react to the bit when receiving in such a frame. Fix this by introducing a new helper ieee80211_is_bufferable_mmpdu() and using it for the RX path that currently ignores the PM bit in any non-data frames for doze->wake transitions, but listens to it in all frames for wake->doze transitions, both of which are wrong. Also use the new helper in the TX path to clean up the code. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 923c478030a3..1e3912d1b029 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -596,6 +596,20 @@ static inline int ieee80211_is_qos_nullfunc(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); } +/** + * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) +{ + /* IEEE 802.11-2012, definition of "bufferable management frame"; + * note that this ignores the IBSS special case. */ + return ieee80211_is_mgmt(fc) && + (ieee80211_is_action(fc) || + ieee80211_is_disassoc(fc) || + ieee80211_is_deauth(fc)); +} + /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder -- cgit v1.2.3 From 8c78e38025060a00155a73bf722152c156242490 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 4 Feb 2014 09:41:04 +0100 Subject: wireless: sort and extend element ID list The element ID list is currently almost sorted by amendment or similar topic, but the order is difficult to maintain and not very transparent. Sort the list by ID instead, and add a lot of missing IDs. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 170 +++++++++++++++++++++++++++++----------------- 1 file changed, 106 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 1e3912d1b029..5f349355ee54 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1650,51 +1650,22 @@ enum ieee80211_reasoncode { enum ieee80211_eid { WLAN_EID_SSID = 0, WLAN_EID_SUPP_RATES = 1, - WLAN_EID_FH_PARAMS = 2, + WLAN_EID_FH_PARAMS = 2, /* reserved now */ WLAN_EID_DS_PARAMS = 3, WLAN_EID_CF_PARAMS = 4, WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, - WLAN_EID_CHALLENGE = 16, - WLAN_EID_COUNTRY = 7, WLAN_EID_HP_PARAMS = 8, WLAN_EID_HP_TABLE = 9, WLAN_EID_REQUEST = 10, - WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, WLAN_EID_TSPEC = 13, WLAN_EID_TCLAS = 14, WLAN_EID_SCHEDULE = 15, - WLAN_EID_TS_DELAY = 43, - WLAN_EID_TCLAS_PROCESSING = 44, - WLAN_EID_QOS_CAPA = 46, - /* 802.11z */ - WLAN_EID_LINK_ID = 101, - /* 802.11s */ - WLAN_EID_MESH_CONFIG = 113, - WLAN_EID_MESH_ID = 114, - WLAN_EID_LINK_METRIC_REPORT = 115, - WLAN_EID_CONGESTION_NOTIFICATION = 116, - WLAN_EID_PEER_MGMT = 117, - WLAN_EID_CHAN_SWITCH_PARAM = 118, - WLAN_EID_MESH_AWAKE_WINDOW = 119, - WLAN_EID_BEACON_TIMING = 120, - WLAN_EID_MCCAOP_SETUP_REQ = 121, - WLAN_EID_MCCAOP_SETUP_RESP = 122, - WLAN_EID_MCCAOP_ADVERT = 123, - WLAN_EID_MCCAOP_TEARDOWN = 124, - WLAN_EID_GANN = 125, - WLAN_EID_RANN = 126, - WLAN_EID_PREQ = 130, - WLAN_EID_PREP = 131, - WLAN_EID_PERR = 132, - WLAN_EID_PXU = 137, - WLAN_EID_PXUC = 138, - WLAN_EID_AUTH_MESH_PEER_EXCH = 139, - WLAN_EID_MIC = 140, - + WLAN_EID_CHALLENGE = 16, + /* 17-31 reserved for challenge text extension */ WLAN_EID_PWR_CONSTRAINT = 32, WLAN_EID_PWR_CAPABILITY = 33, WLAN_EID_TPC_REQUEST = 34, @@ -1705,66 +1676,114 @@ enum ieee80211_eid { WLAN_EID_MEASURE_REPORT = 39, WLAN_EID_QUIET = 40, WLAN_EID_IBSS_DFS = 41, - WLAN_EID_ERP_INFO = 42, - WLAN_EID_EXT_SUPP_RATES = 50, - + WLAN_EID_TS_DELAY = 43, + WLAN_EID_TCLAS_PROCESSING = 44, WLAN_EID_HT_CAPABILITY = 45, - WLAN_EID_HT_OPERATION = 61, - WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, - + WLAN_EID_QOS_CAPA = 46, + /* 47 reserved for Broadcom */ WLAN_EID_RSN = 48, - WLAN_EID_MMIE = 76, - WLAN_EID_VENDOR_SPECIFIC = 221, - WLAN_EID_QOS_PARAMETER = 222, - + WLAN_EID_802_15_COEX = 49, + WLAN_EID_EXT_SUPP_RATES = 50, WLAN_EID_AP_CHAN_REPORT = 51, WLAN_EID_NEIGHBOR_REPORT = 52, WLAN_EID_RCPI = 53, + WLAN_EID_MOBILITY_DOMAIN = 54, + WLAN_EID_FAST_BSS_TRANSITION = 55, + WLAN_EID_TIMEOUT_INTERVAL = 56, + WLAN_EID_RIC_DATA = 57, + WLAN_EID_DSE_REGISTERED_LOCATION = 58, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59, + WLAN_EID_EXT_CHANSWITCH_ANN = 60, + WLAN_EID_HT_OPERATION = 61, + WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, WLAN_EID_BSS_AVG_ACCESS_DELAY = 63, WLAN_EID_ANTENNA_INFO = 64, WLAN_EID_RSNI = 65, WLAN_EID_MEASUREMENT_PILOT_TX_INFO = 66, WLAN_EID_BSS_AVAILABLE_CAPACITY = 67, WLAN_EID_BSS_AC_ACCESS_DELAY = 68, + WLAN_EID_TIME_ADVERTISEMENT = 69, WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, WLAN_EID_BSS_COEX_2040 = 72, WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, - WLAN_EID_EXT_CAPABILITY = 127, - - WLAN_EID_MOBILITY_DOMAIN = 54, - WLAN_EID_FAST_BSS_TRANSITION = 55, - WLAN_EID_TIMEOUT_INTERVAL = 56, - WLAN_EID_RIC_DATA = 57, WLAN_EID_RIC_DESCRIPTOR = 75, - - 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, - WLAN_EID_OPMODE_NOTIF = 199, - WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, - WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, - WLAN_EID_EXTENDED_BSS_LOAD = 193, - WLAN_EID_VHT_TX_POWER_ENVELOPE = 195, - WLAN_EID_AID = 197, - WLAN_EID_QUIET_CHANNEL = 198, - - /* 802.11ad */ + WLAN_EID_MMIE = 76, + WLAN_EID_ASSOC_COMEBACK_TIME = 77, + WLAN_EID_EVENT_REQUEST = 78, + WLAN_EID_EVENT_REPORT = 79, + WLAN_EID_DIAGNOSTIC_REQUEST = 80, + WLAN_EID_DIAGNOSTIC_REPORT = 81, + WLAN_EID_LOCATION_PARAMS = 82, WLAN_EID_NON_TX_BSSID_CAP = 83, + WLAN_EID_SSID_LIST = 84, + WLAN_EID_MULTI_BSSID_IDX = 85, + WLAN_EID_FMS_DESCRIPTOR = 86, + WLAN_EID_FMS_REQUEST = 87, + WLAN_EID_FMS_RESPONSE = 88, + WLAN_EID_QOS_TRAFFIC_CAPA = 89, + WLAN_EID_BSS_MAX_IDLE_PERIOD = 90, + WLAN_EID_TSF_REQUEST = 91, + WLAN_EID_TSF_RESPOSNE = 92, + WLAN_EID_WNM_SLEEP_MODE = 93, + WLAN_EID_TIM_BCAST_REQ = 94, + WLAN_EID_TIM_BCAST_RESP = 95, + WLAN_EID_COLL_IF_REPORT = 96, + WLAN_EID_CHANNEL_USAGE = 97, + WLAN_EID_TIME_ZONE = 98, + WLAN_EID_DMS_REQUEST = 99, + WLAN_EID_DMS_RESPONSE = 100, + WLAN_EID_LINK_ID = 101, + WLAN_EID_WAKEUP_SCHEDUL = 102, + /* 103 reserved */ + WLAN_EID_CHAN_SWITCH_TIMING = 104, + WLAN_EID_PTI_CONTROL = 105, + WLAN_EID_PU_BUFFER_STATUS = 106, + WLAN_EID_INTERWORKING = 107, + WLAN_EID_ADVERTISEMENT_PROTOCOL = 108, + WLAN_EID_EXPEDITED_BW_REQ = 109, + WLAN_EID_QOS_MAP_SET = 110, + WLAN_EID_ROAMING_CONSORTIUM = 111, + WLAN_EID_EMERGENCY_ALERT = 112, + WLAN_EID_MESH_CONFIG = 113, + WLAN_EID_MESH_ID = 114, + WLAN_EID_LINK_METRIC_REPORT = 115, + WLAN_EID_CONGESTION_NOTIFICATION = 116, + WLAN_EID_PEER_MGMT = 117, + WLAN_EID_CHAN_SWITCH_PARAM = 118, + WLAN_EID_MESH_AWAKE_WINDOW = 119, + WLAN_EID_BEACON_TIMING = 120, + WLAN_EID_MCCAOP_SETUP_REQ = 121, + WLAN_EID_MCCAOP_SETUP_RESP = 122, + WLAN_EID_MCCAOP_ADVERT = 123, + WLAN_EID_MCCAOP_TEARDOWN = 124, + WLAN_EID_GANN = 125, + WLAN_EID_RANN = 126, + WLAN_EID_EXT_CAPABILITY = 127, + /* 128, 129 reserved for Agere */ + WLAN_EID_PREQ = 130, + WLAN_EID_PREP = 131, + WLAN_EID_PERR = 132, + /* 133-136 reserved for Cisco */ + WLAN_EID_PXU = 137, + WLAN_EID_PXUC = 138, + WLAN_EID_AUTH_MESH_PEER_EXCH = 139, + WLAN_EID_MIC = 140, + WLAN_EID_DESTINATION_URI = 141, + WLAN_EID_UAPSD_COEX = 142, 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, + /* 149-150 reserved for Cisco */ WLAN_EID_DMG_OPERATION = 151, WLAN_EID_DMG_BSS_PARAM_CHANGE = 152, WLAN_EID_DMG_BEAM_REFINEMENT = 153, WLAN_EID_CHANNEL_MEASURE_FEEDBACK = 154, + /* 155-156 reserved for Cisco */ WLAN_EID_AWAKE_WINDOW = 157, WLAN_EID_MULTI_BAND = 158, WLAN_EID_ADDBA_EXT = 159, @@ -1781,11 +1800,34 @@ enum ieee80211_eid { WLAN_EID_MULTIPLE_MAC_ADDR = 170, WLAN_EID_U_PID = 171, WLAN_EID_DMG_LINK_ADAPT_ACK = 172, + /* 173 reserved for Symbol */ + WLAN_EID_MCCAOP_ADV_OVERVIEW = 174, WLAN_EID_QUIET_PERIOD_REQ = 175, + /* 176 reserved for Symbol */ WLAN_EID_QUIET_PERIOD_RESP = 177, + /* 178-179 reserved for Symbol */ + /* 180 reserved for ISO/IEC 20011 */ WLAN_EID_EPAC_POLICY = 182, WLAN_EID_CLISTER_TIME_OFF = 183, + WLAN_EID_INTER_AC_PRIO = 184, + WLAN_EID_SCS_DESCRIPTOR = 185, + WLAN_EID_QLOAD_REPORT = 186, + WLAN_EID_HCCA_TXOP_UPDATE_COUNT = 187, + WLAN_EID_HL_STREAM_ID = 188, + WLAN_EID_GCR_GROUP_ADDR = 189, WLAN_EID_ANTENNA_SECTOR_ID_PATTERN = 190, + WLAN_EID_VHT_CAPABILITY = 191, + WLAN_EID_VHT_OPERATION = 192, + WLAN_EID_EXTENDED_BSS_LOAD = 193, + WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, + WLAN_EID_VHT_TX_POWER_ENVELOPE = 195, + WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, + WLAN_EID_AID = 197, + WLAN_EID_QUIET_CHANNEL = 198, + WLAN_EID_OPMODE_NOTIF = 199, + + WLAN_EID_VENDOR_SPECIFIC = 221, + WLAN_EID_QOS_PARAMETER = 222, }; /* Action category code */ -- cgit v1.2.3 From 25a91d8d91911f84a03a039339b29537e7f1970d Mon Sep 17 00:00:00 2001 From: Fan Du Date: Sat, 18 Jan 2014 09:54:23 +0800 Subject: skbuff: Introduce skb_to_sgvec_nomark to map skb without mark new end As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given sglist without mark the sg which contain last skb data as the end. So the caller can mannipulate sg list as will when padding new data after the first call without calling sg_unmark_end to expend sg list. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..c574bf3bd6f6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -691,6 +691,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); -- cgit v1.2.3 From 6e201c857b68ea994c9ac85718eb3d50dcf40d92 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 12 Feb 2014 22:14:53 +0000 Subject: ethtool: Document the general convention for VLAs in kernel space Various ethtool command structures are declared with zero-length array at the end which are intended to be variable-length in userland (relying on lack of compiler bounds checking). However, in the kernel the structure and array are always allocated and passed to driver operations separately. Make that explicit. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c8e3e7e39c6b..0a114d05f68d 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,6 +183,9 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * hold the RTNL lock. * * See the structures used by these operations for further documentation. + * Note that for all operations using a structure ending with a zero- + * length array, the array is allocated separately in the kernel and + * is passed to the driver as an additional parameter. * * See &struct net_device and &struct net_device_ops for documentation * of the generic netdev features interface. -- cgit v1.2.3 From a9fa6e6ac29709e7a623b60695c172da675df045 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 11 Feb 2014 17:27:36 -0800 Subject: net: phy: add genphy_aneg_done() In preparation for allowing PHY drivers to potentially override their auto-negotiation done callback, move the contents of phy_aneg_done() to genphy_aneg_done() since that function really is the generic implementation based on the BMSR_ANEGCOMPLETE status. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 565188ca328f..c572842c9029 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -612,6 +612,7 @@ static inline int phy_read_status(struct phy_device *phydev) int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_aneg(struct phy_device *phydev); +int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); -- cgit v1.2.3 From 76a423a3f8f16bfc7fb86360a620be18c775b94d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 11 Feb 2014 17:27:37 -0800 Subject: net: phy: allow driver to implement their own aneg_done Some PHYs out there can be very quirky with respect to how they would report the auto-negotiation is completed. Allow drivers to override the generic aneg_done() implementation by providing their own. Since not all drivers have been updated yet to use genphy_aneg_done() as aneg_done() callback, we explicitely check that this callback is valid before calling into it. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index c572842c9029..eede6579cae7 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -417,6 +417,9 @@ struct phy_driver { */ int (*config_aneg)(struct phy_device *phydev); + /* Determines the auto negotiation result */ + int (*aneg_done)(struct phy_device *phydev); + /* Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); -- cgit v1.2.3 From 8a2fe56e8827f2b1eb1766702f0215074dd2767e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 11 Feb 2014 17:27:39 -0800 Subject: net: phy: re-design phy_modes to be self-contained of_get_phy_mode() uses a local array to map phy_interface_t values from include/linux/net/phy.h to a string which is read from the 'phy-mode' or 'phy-connection-type' property. In preparation for exposing the PHY interface mode through sysfs, perform the following: - mode phy_modes from drivers/of/of_net.c to include/linux/phy.h such that it is right below the phy_interface_t enum - make it a static inline function returning the string such that we can use it by just including include/linux/net/phy.h - add a PHY_INTERFACE_MODE_MAX enum value to guard the iteration in of_get_phy_mode() Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index eede6579cae7..ef7fa1131145 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -74,8 +74,50 @@ typedef enum { PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, + PHY_INTERFACE_MODE_MAX, } phy_interface_t; +/** + * It maps 'enum phy_interface_t' found in include/linux/phy.h + * into the device tree binding of 'phy-mode', so that Ethernet + * device driver can get phy interface from device tree. + */ +static inline const char *phy_modes(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_NA: + return ""; + case PHY_INTERFACE_MODE_MII: + return "mii"; + case PHY_INTERFACE_MODE_GMII: + return "gmii"; + case PHY_INTERFACE_MODE_SGMII: + return "sgmii"; + case PHY_INTERFACE_MODE_TBI: + return "tbi"; + case PHY_INTERFACE_MODE_REVMII: + return "rev-mii"; + case PHY_INTERFACE_MODE_RMII: + return "rmii"; + case PHY_INTERFACE_MODE_RGMII: + return "rgmii"; + case PHY_INTERFACE_MODE_RGMII_ID: + return "rgmii-id"; + case PHY_INTERFACE_MODE_RGMII_RXID: + return "rgmii-rxid"; + case PHY_INTERFACE_MODE_RGMII_TXID: + return "rgmii-txid"; + case PHY_INTERFACE_MODE_RTBI: + return "rtbi"; + case PHY_INTERFACE_MODE_SMII: + return "smii"; + case PHY_INTERFACE_MODE_XGMII: + return "xgmii"; + default: + return "unknown"; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_STATE_TIME 1 -- cgit v1.2.3 From b0ae009f3dc14643e56972cfc08c060dd72cc24d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 11 Feb 2014 17:27:41 -0800 Subject: net: phy: add "has_fixups" boolean property Add a boolean property which indicates if the PHY has had any fixup routine ran on it. We are later going to use that boolean to expose it as a sysfs property to help troubleshooting. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ef7fa1131145..42f1bc7eaeb0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -350,6 +350,7 @@ struct phy_device { struct phy_c45_device_ids c45_ids; bool is_c45; bool is_internal; + bool has_fixups; enum phy_state state; -- cgit v1.2.3 From fd70f72c66eeada848abaed9eb6bbdbaf57764e9 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 13 Feb 2014 16:08:42 -0800 Subject: net: phy: add MoCA PHY type Some Ethernet MACs are connected to a MoCA PHY which will handle the low-level job of sending Ethernet frames on the coaxial cable, these Ethernet MACs need to know about it to be properly configured. Add a new PHY mode "moca" and update the Device Tree parsing logic to look for it. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 42f1bc7eaeb0..f7fe54628424 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -74,6 +74,7 @@ typedef enum { PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, + PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -113,6 +114,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; + case PHY_INTERFACE_MODE_MOCA: + return "moca"; default: return "unknown"; } -- cgit v1.2.3 From 439d39a9ac8fbbba9c04581361188f33f21ced50 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 13 Feb 2014 16:08:44 -0800 Subject: net: phy: broadcom: extract register definitions The Broadcom BCM54xx register definitions are shared between BCM54xx and BCM7xx internal PHYs for which we are adding support. Extract these register definitions and put them in include/linux/brcmphy.h for use by the BCM7xxx internal PHY driver. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 677b4f01b2d0..104e3efe46af 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -33,4 +33,55 @@ #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 #define PHY_BCM_FLAGS_VALID 0x80000000 +/* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */ +#define MII_BCM54XX_ECR 0x10 /* BCM54xx extended control register */ +#define MII_BCM54XX_ECR_IM 0x1000 /* Interrupt mask */ +#define MII_BCM54XX_ECR_IF 0x0800 /* Interrupt force */ + +#define MII_BCM54XX_ESR 0x11 /* BCM54xx extended status register */ +#define MII_BCM54XX_ESR_IS 0x1000 /* Interrupt status */ + +#define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */ +#define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ +#define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ +#define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ + +#define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */ +#define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */ +#define MII_BCM54XX_IMR 0x1b /* BCM54xx interrupt mask register */ +#define MII_BCM54XX_INT_CRCERR 0x0001 /* CRC error */ +#define MII_BCM54XX_INT_LINK 0x0002 /* Link status changed */ +#define MII_BCM54XX_INT_SPEED 0x0004 /* Link speed change */ +#define MII_BCM54XX_INT_DUPLEX 0x0008 /* Duplex mode changed */ +#define MII_BCM54XX_INT_LRS 0x0010 /* Local receiver status changed */ +#define MII_BCM54XX_INT_RRS 0x0020 /* Remote receiver status changed */ +#define MII_BCM54XX_INT_SSERR 0x0040 /* Scrambler synchronization error */ +#define MII_BCM54XX_INT_UHCD 0x0080 /* Unsupported HCD negotiated */ +#define MII_BCM54XX_INT_NHCD 0x0100 /* No HCD */ +#define MII_BCM54XX_INT_NHCDL 0x0200 /* No HCD link */ +#define MII_BCM54XX_INT_ANPR 0x0400 /* Auto-negotiation page received */ +#define MII_BCM54XX_INT_LC 0x0800 /* All counters below 128 */ +#define MII_BCM54XX_INT_HC 0x1000 /* Counter above 32768 */ +#define MII_BCM54XX_INT_MDIX 0x2000 /* MDIX status change */ +#define MII_BCM54XX_INT_PSERR 0x4000 /* Pair swap error */ + +#define MII_BCM54XX_SHD 0x1c /* 0x1c shadow registers */ +#define MII_BCM54XX_SHD_WRITE 0x8000 +#define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) +#define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) + +/* + * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) + */ +#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 +#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400 +#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 + +#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 +#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 +#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 + +#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 + #endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From b560a58c45c66f68936127040e86b7f02e4c5332 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 13 Feb 2014 16:08:45 -0800 Subject: net: phy: add Broadcom BCM7xxx internal PHY driver This patch adds support for the Broadcom BCM7xxx Set Top Box SoCs internal PHYs. This driver supports the following generation of SoCs: - BCM7366, BCM7439, BCM7445 (28nm process) - all 40nm and 65nm (older MIPS-based SoCs) The PHYs on these SoCs require a bunch of workarounds to operate correctly, both during configuration time and at suspend/resume time, the driver handles that for us. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 104e3efe46af..6f76277baf39 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -13,10 +13,17 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM57780 0x03625d90 +#define PHY_ID_BCM7366 0x600d8490 +#define PHY_ID_BCM7439 0x600d8480 +#define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM7XXX_28 0x600d8400 + #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 #define PHY_BCM_OUI_2 0x0143bc00 #define PHY_BCM_OUI_3 0x03625c00 +#define PHY_BCM_OUI_4 0x600d0000 +#define PHY_BCM_OUI_5 0x03625e00 #define PHY_BCM_FLAGS_MODE_COPPER 0x00000001 @@ -31,6 +38,8 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +/* Broadcom BCM7xxx specific workarounds */ +#define PHY_BRCM_100MBPS_WAR 0x00010000 #define PHY_BCM_FLAGS_VALID 0x80000000 /* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */ -- cgit v1.2.3 From 1c213bd24ad04f4430031d20d740d7783162b099 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 13 Feb 2014 11:46:28 -0800 Subject: net: introduce netdev_alloc_pcpu_stats() for drivers There are many drivers calling alloc_percpu() to allocate pcpu stats and then initializing ->syncp. So just introduce a helper function for them. Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02ee6f92..430c51aed6a4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1726,6 +1726,20 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +#define netdev_alloc_pcpu_stats(type) \ +({ \ + typeof(type) *pcpu_stats = alloc_percpu(type); \ + if (pcpu_stats) { \ + int i; \ + for_each_possible_cpu(i) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, i); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ +}) + #include /* netdevice notifier chain. Please remember to update the rtnetlink -- cgit v1.2.3 From c0fdfb80382e4901473ce0e31d1e7833c1d297be Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 9 Feb 2014 20:59:04 -0500 Subject: tty: Fix ref counting for port krefs The tty core supports two models for handling tty_port lifetimes; the tty_port can use the kref supplied by tty_port (which will automatically destruct the tty_port when the ref count drops to zero) or it can destruct the tty_port manually. For tty drivers that choose to use the port kref to manage the tty_port lifetime, it is not possible to safely acquire a port reference conditionally. If the last reference is released after evaluating the condition but before acquiring the reference, a bogus reference will be held while the tty_port destruction commences. Rather, only acquire a port reference if the ref count is non-zero and allow the caller to distinguish if a reference has successfully been acquired. Cc: Jiri Slaby Signed-off-by: Peter Hurley Acked-by: Greg Kroah-Hartman Tested-By: Alexander Holler Signed-off-by: Marcel Holtmann --- include/linux/tty.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 90b4fdc8a61f..4781d7b27dd3 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -518,9 +518,9 @@ extern void tty_port_put(struct tty_port *port); static inline struct tty_port *tty_port_get(struct tty_port *port) { - if (port) - kref_get(&port->kref); - return port; + if (port && kref_get_unless_zero(&port->kref)) + return port; + return NULL; } /* If the cts flow control is enabled, return true. */ -- cgit v1.2.3 From 797ac07137d9ae8572008e21e6123a9ae17dae50 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 17 Feb 2014 13:34:02 -0800 Subject: net: phy: move PHY software reset to genphy_soft_reset As pointed out by Shaohui, this function is generic for 10/100/1000 PHYs, but 10G PHYs might have a slightly different reset sequence which prevents most of them from using this function. Move the BMCR_RESET based software resent sequence to genphy_soft_reset() in preparation for allowing PHY drivers to implement a soft_reset() callback. Reported-by: Shaohui Xie Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index f7fe54628424..bffe0ec1604f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -666,6 +666,7 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); +int genphy_soft_reset(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); -- cgit v1.2.3 From 9df81dd7583d14862d0cfb673a941b261f3b2112 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 17 Feb 2014 13:34:03 -0800 Subject: net: phy: allow PHY drivers to implement their own software reset As pointed out by Shaohui, most 10G PHYs out there have a non-standard compliant software reset sequence, eventually something much more complex than just toggling the BMCR_RESET bit. Allow PHY driver to implement their own soft_reset() callback to deal with that. If no callback is provided, call into genphy_soft_reset() which makes sure the existing behavior is kept intact. Reported-by: Shaohui Xie Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index bffe0ec1604f..24126c4b27b5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -439,6 +439,11 @@ struct phy_driver { u32 features; u32 flags; + /* + * Called to issue a PHY software reset + */ + int (*soft_reset)(struct phy_device *phydev); + /* * Called to initialize the PHY, * including after a reset -- cgit v1.2.3 From 9b2777d6089bcd7fb035847f907280560fe233c8 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 17 Feb 2014 11:34:08 +0100 Subject: ieee802154: add TX power control to wpan_phy Replace the current u8 transmit_power in wpan_phy with s8 transmit_power. The u8 field contained the actual tx power and a tolerance field, which no physical radio every used. Adjust sysfs entries to keep compatibility with userspace, give tolerances of +-1dB statically there. This patch only adds support for this in the at86rf230 driver and the RF212 chip. Configuration calculation for RF212 is also somewhat basic, but does the job - the RF212 datasheet gives a large table with suggested values for combinations of TX power and page/channel, if this does not work well, we might have to copy the whole table. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index fd4f2d1cdf6c..625d19e0a1de 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -70,6 +70,8 @@ enum { IEEE802154_ATTR_PHY_NAME, IEEE802154_ATTR_DEV_TYPE, + IEEE802154_ATTR_TXPOWER, + __IEEE802154_ATTR_MAX, }; @@ -122,6 +124,8 @@ enum { IEEE802154_ADD_IFACE, IEEE802154_DEL_IFACE, + IEEE802154_SET_PHYPARAMS, + __IEEE802154_CMD_MAX, }; -- cgit v1.2.3 From 84dda3c648fd55898064d76366b14f964cdc9d16 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 17 Feb 2014 11:34:10 +0100 Subject: ieee802154: add support for listen-before-talk in wpan_phy Listen-before-talk is an alternative to CSMA in uncoordinated networks and prescribed by european regulations if one wants to have a device with radio duty cycles above 10% (or less in some bands). Add a phy property to enable/disable LBT in the phy, including support in the at86rf230 driver for RF212 chips. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index 625d19e0a1de..326baee227f7 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -71,6 +71,7 @@ enum { IEEE802154_ATTR_DEV_TYPE, IEEE802154_ATTR_TXPOWER, + IEEE802154_ATTR_LBT_ENABLED, __IEEE802154_ATTR_MAX, }; -- cgit v1.2.3 From ba08fea53a43e02b590d89224afdad976dece841 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 17 Feb 2014 11:34:11 +0100 Subject: ieee802154: add support for CCA mode in wpan phys The standard describes four modes of clear channel assesment: "energy above threshold", "carrier found", and the logical and/or of these two. Support for CCA mode setting is included in the at86rf230 driver, predicated for RF212 chips. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index 326baee227f7..5edefc14bd83 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -72,6 +72,7 @@ enum { IEEE802154_ATTR_TXPOWER, IEEE802154_ATTR_LBT_ENABLED, + IEEE802154_ATTR_CCA_MODE, __IEEE802154_ATTR_MAX, }; -- cgit v1.2.3 From 6ca001978dce0d50ebac01a38d6287f241a520c6 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 17 Feb 2014 11:34:12 +0100 Subject: ieee802154: add support for setting CCA energy detection levels Since three of the four clear channel assesment modes make use of energy detection, provide an API to set the energy detection threshold. Driver support for this is available in at86rf230 for the RF212 chips. Since for these chips the minimal energy detection threshold depends on page and channel used, add a field to struct at86rf230_local that stores the minimal threshold. Actual ED thresholds are configured as offsets from this value. For RF212, setting the ED threshold will not work before a channel/page has been set due to the dependency of energy detection in the chip and the actual channel/page selected. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index 5edefc14bd83..0594a0ae71ba 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -73,6 +73,7 @@ enum { IEEE802154_ATTR_TXPOWER, IEEE802154_ATTR_LBT_ENABLED, IEEE802154_ATTR_CCA_MODE, + IEEE802154_ATTR_CCA_ED_LEVEL, __IEEE802154_ATTR_MAX, }; -- cgit v1.2.3 From 4244db1b0b7bc9ab7b67d8c1c38de6cf15bc87a8 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 17 Feb 2014 11:34:14 +0100 Subject: ieee802154: add netlink APIs for smartMAC configuration Introduce new netlink attributes for SET_PHY_ATTRS: * CSMA minimal backoff exponent * CSMA maximal backoff exponent * CSMA retry limit * frame retransmission limit The CSMA attributes shall correspond to minBE, maxBE and maxCSMABackoffs of 802.15.4, respectively. The frame retransmission shall correspond to maxFrameRetries of 802.15.4, unless given as -1: then the old behaviour of the stack shall apply. For RF2xy, the old behaviour is to not do channel sensing at all and simply send *right now*, which is not intended behaviour for most applications and actually prohibited for some channel/page combinations. For all values except frame retransmission limit, the defaults of 802.15.4 apply. Frame retransmission limits are set to -1 to indicate backward-compatible behaviour. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index 0594a0ae71ba..e110b8c266f5 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -74,6 +74,11 @@ enum { IEEE802154_ATTR_LBT_ENABLED, IEEE802154_ATTR_CCA_MODE, IEEE802154_ATTR_CCA_ED_LEVEL, + IEEE802154_ATTR_CSMA_RETRIES, + IEEE802154_ATTR_CSMA_MIN_BE, + IEEE802154_ATTR_CSMA_MAX_BE, + + IEEE802154_ATTR_FRAME_RETRIES, __IEEE802154_ATTR_MAX, }; -- cgit v1.2.3 From b075dd40c95d11c2c8690f6c4d6232fc0d9e7f56 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Tue, 18 Feb 2014 02:19:26 -0300 Subject: Bluetooth: allocate static minor for vhci Commit bfacbb9 (Bluetooth: Use devname:vhci module alias for virtual HCI driver) added the module alias to hci_vhci module so it's possible to create the /dev/vhci node. However creating an alias without specifying the minor doesn't allow us to create the node ahead, triggerring module auto-load when it's first accessed. Starting with depmod from kmod 16 we started to warn if there's a devname alias without specifying the major and minor. Let's do the same done for uhid, kvm, fuse and others, specifying a fixed minor. In systems with systemd as the init the following will happen: on early boot systemd will call "kmod static-nodes" to read /lib/modules/$(uname -r)/modules.devname and then create the nodes. When first accessed these "dead" nodes will trigger the module loading. Signed-off-by: Lucas De Marchi Acked-by: Greg Kroah-Hartman Signed-off-by: Marcel Holtmann --- include/linux/miscdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3737f7218f51..7bb6148d990f 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -23,6 +23,7 @@ #define TEMP_MINOR 131 /* Temperature Sensor */ #define RTC_MINOR 135 #define EFI_RTC_MINOR 136 /* EFI Time services */ +#define VHCI_MINOR 137 #define SUN_OPENPROM_MINOR 139 #define DMAPI_MINOR 140 /* DMAPI */ #define NVRAM_MINOR 144 -- cgit v1.2.3 From f8ff080dacecc5d0ce3579941b664bac3a4405c2 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Tue, 18 Feb 2014 07:48:45 +0100 Subject: bonding: remove useless updating of slave->dev->last_rx Now that all the logic is handled via last_arp_rx, we don't need to use last_rx. CC: Jay Vosburgh CC: Andy Gospodarek CC: "David S. Miller" Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 430c51aed6a4..891432a994c0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1312,13 +1312,7 @@ struct net_device { /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; /* Time of last Rx - * This should not be set in - * drivers, unless really needed, - * because network stack (bonding) - * use it if/when necessary, to - * avoid dirtying this cache line. - */ + unsigned long last_rx; /* Time of last Rx */ /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast -- cgit v1.2.3 From 0eb5db7ad302a24fe6f0eb4bfd235357047a28db Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 18 Feb 2014 18:06:48 +0000 Subject: netfilter: nfnetlink: add rcu_dereference_protected() helpers Add a lockdep_nfnl_is_held() function and a nfnl_dereference() macro for RCU dereferences protected by a NFNL subsystem mutex. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 28c74367e900..e955d4730625 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -44,6 +44,27 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); +#ifdef CONFIG_PROVE_LOCKING +int lockdep_nfnl_is_held(__u8 subsys_id); +#else +static inline int lockdep_nfnl_is_held(__u8 subsys_id) +{ + return 1; +} +#endif /* CONFIG_PROVE_LOCKING */ + +/* + * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex + * + * @p: The pointer to read, prior to dereferencing + * @ss: The nfnetlink subsystem ID + * + * Return the value of the specified RCU-protected pointer, but omit + * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because + * caller holds the NFNL subsystem mutex. + */ +#define nfnl_dereference(p, ss) \ + rcu_dereference_protected(p, lockdep_nfnl_is_held(ss)) #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) -- cgit v1.2.3 From 3f85944fe207d0225ef21a2c0951d4946fc9a95d Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 25 Feb 2014 18:17:50 +0200 Subject: net: Add sysfs file for port number Add a sysfs file to enable user space to query the device port number used by a netdevice instance. This is needed for devices that have multiple ports on the same PCI function. Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e4756553c18..5e84483c0650 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1279,6 +1279,10 @@ struct net_device { * that share the same link * layer address */ + unsigned short dev_port; /* Used to differentiate + * devices that share the same + * function + */ spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ -- cgit v1.2.3 From 363ec392352e55c61ce2799c3f15f89f9429bba7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Feb 2014 14:02:11 -0800 Subject: net: add skb_mstamp infrastructure ktime_get() is too expensive on some cases, and we'd like to get usec resolution timestamps in TCP stack. This patch adds a light weight facility using a combination of local_clock() and jiffies samples. Instead of : u64 t0, t1; t0 = ktime_get(); // stuff t1 = ktime_get(); delta_us = ktime_us_delta(t1, t0); use : struct skb_mstamp t0, t1; skb_mstamp_get(&t0); // stuff skb_mstamp_get(&t1); delta_us = skb_mstamp_us_delta(&t1, &t0); Note : local_clock() might have a (bounded) drift between cpus. Do not use this infra in place of ktime_get() without understanding the issues. Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Larry Brakmo Cc: Julian Anastasov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 11b6925f0e96..6d8ed22accb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,6 +32,7 @@ #include #include #include +#include #include /* A. Checksumming of received packets by device. @@ -356,11 +357,62 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * struct skb_mstamp - multi resolution time stamps + * @stamp_us: timestamp in us resolution + * @stamp_jiffies: timestamp in jiffies + */ +struct skb_mstamp { + union { + u64 v64; + struct { + u32 stamp_us; + u32 stamp_jiffies; + }; + }; +}; + +/** + * skb_mstamp_get - get current timestamp + * @cl: place to store timestamps + */ +static inline void skb_mstamp_get(struct skb_mstamp *cl) +{ + u64 val = local_clock(); + + do_div(val, NSEC_PER_USEC); + cl->stamp_us = (u32)val; + cl->stamp_jiffies = (u32)jiffies; +} + +/** + * skb_mstamp_delta - compute the difference in usec between two skb_mstamp + * @t1: pointer to newest sample + * @t0: pointer to oldest sample + */ +static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 delta_us = t1->stamp_us - t0->stamp_us; + u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; + + /* If delta_us is negative, this might be because interval is too big, + * or local_clock() drift is too big : fallback using jiffies. + */ + if (delta_us <= 0 || + delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) + + delta_us = jiffies_to_usecs(delta_jiffies); + + return delta_us; +} + + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @tstamp: Time we arrived + * @tstamp: Time we arrived/left * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -429,7 +481,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - ktime_t tstamp; + union { + ktime_t tstamp; + struct skb_mstamp skb_mstamp; + }; struct sock *sk; struct net_device *dev; -- cgit v1.2.3 From 740b0f1841f6e39085b711d41db9ffb07198682b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Feb 2014 14:02:48 -0800 Subject: tcp: switch rtt estimations to usec resolution Upcoming congestion controls for TCP require usec resolution for RTT estimations. Millisecond resolution is simply not enough these days. FQ/pacing in DC environments also require this change for finer control and removal of bimodal behavior due to the current hack in tcp_update_pacing_rate() for 'small rtt' TCP_CONG_RTT_STAMP is no longer needed. As Julian Anastasov pointed out, we need to keep user compatibility : tcp_metrics used to export RTT and RTTVAR in msec resolution, so we added RTT_US and RTTVAR_US. An iproute2 patch is needed to use the new attributes if provided by the kernel. In this example ss command displays a srtt of 32 usecs (10Gbit link) lpk51:~# ./ss -i dst lpk52 Netid State Recv-Q Send-Q Local Address:Port Peer Address:Port tcp ESTAB 0 1 10.246.11.51:42959 10.246.11.52:64614 cubic wscale:6,6 rto:201 rtt:0.032/0.001 ato:40 mss:1448 cwnd:10 send 3620.0Mbps pacing_rate 7240.0Mbps unacked:1 rcv_rtt:993 rcv_space:29559 Updated iproute2 ip command displays : lpk51:~# ./ip tcp_metrics | grep 10.246.11.52 10.246.11.52 age 561.914sec cwnd 10 rtt 274us rttvar 213us source 10.246.11.51 Old binary displays : lpk51:~# ip tcp_metrics | grep 10.246.11.52 10.246.11.52 age 561.914sec cwnd 10 rtt 250us rttvar 125us source 10.246.11.51 With help from Julian Anastasov, Stephen Hemminger and Yuchung Cheng Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Larry Brakmo Cc: Julian Anastasov Signed-off-by: David S. Miller --- include/linux/tcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4ad0706d40eb..239946868142 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -201,10 +201,10 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ - u32 srtt; /* smoothed round trip time << 3 */ - u32 mdev; /* medium deviation */ - u32 mdev_max; /* maximal mdev for the last rtt period */ - u32 rttvar; /* smoothed mdev_max */ + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 mdev_us; /* medium deviation */ + u32 mdev_max_us; /* maximal mdev for the last rtt period */ + u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ u32 packets_out; /* Packets which are "in flight" */ -- cgit v1.2.3 From 7aa98047df95d7caf0678e939cdd936dfb99cd06 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Tue, 25 Feb 2014 17:15:13 -0800 Subject: net: move net_device priv_flags out from UAPI These are private to userspace, and they're unstable anyway and can be shuffled at will (see 080e4130b1fb) so any userspace application relying on them is on crack. Test compiled with allyesconfig. mcgrof@drvbp1 /pub/mem/mcgrof/net-next (git::master)$ make allyesconfig mcgrof@drvbp1 /pub/mem/mcgrof/net-next (git::master)$ time make -j 20 ... BUILD arch/x86/boot/bzImage Setup is 16992 bytes (padded to 17408 bytes). System is 56153 kB CRC 721d2751 Kernel: arch/x86/boot/bzImage is ready (#1) real 19m35.744s user 280m37.984s sys 27m54.104s Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Ben Hutchings Cc: Florian Fainelli Cc: David Miller Signed-off-by: Luis R. Rodriguez Signed-off-by: David S. Miller --- include/linux/netdevice.h | 83 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e84483c0650..1a869488b8ae 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1147,6 +1147,89 @@ struct net_device_ops { void *priv); }; +/** + * enum net_device_priv_flags - &struct net_device priv_flags + * + * These are the &struct net_device, they are only set internally + * by drivers and used in the kernel. These flags are invisible to + * userspace, this means that the order of these flags can change + * during any kernel release. + * + * You should have a pretty good reason to be extending these flags. + * + * @IFF_802_1Q_VLAN: 802.1Q VLAN device + * @IFF_EBRIDGE: Ethernet bridging device + * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active + * @IFF_MASTER_8023AD: bonding master, 802.3ad + * @IFF_MASTER_ALB: bonding master, balance-alb + * @IFF_BONDING: bonding master or slave + * @IFF_SLAVE_NEEDARP: need ARPs for validation + * @IFF_ISATAP: ISATAP interface (RFC4214) + * @IFF_MASTER_ARPMON: bonding master, ARP mon in use + * @IFF_WAN_HDLC: WAN HDLC device + * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to + * release skb->dst + * @IFF_DONT_BRIDGE: disallow bridging this ether dev + * @IFF_DISABLE_NETPOLL: disable netpoll at run-time + * @IFF_MACVLAN_PORT: device used as macvlan port + * @IFF_BRIDGE_PORT: device used as bridge port + * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port + * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit + * @IFF_UNICAST_FLT: Supports unicast filtering + * @IFF_TEAM_PORT: device used as team port + * @IFF_SUPP_NOFCS: device supports sending custom FCS + * @IFF_LIVE_ADDR_CHANGE: device supports hardware address + * change when it's running + * @IFF_MACVLAN: Macvlan device + */ +enum netdev_priv_flags { + IFF_802_1Q_VLAN = 1<<0, + IFF_EBRIDGE = 1<<1, + IFF_SLAVE_INACTIVE = 1<<2, + IFF_MASTER_8023AD = 1<<3, + IFF_MASTER_ALB = 1<<4, + IFF_BONDING = 1<<5, + IFF_SLAVE_NEEDARP = 1<<6, + IFF_ISATAP = 1<<7, + IFF_MASTER_ARPMON = 1<<8, + IFF_WAN_HDLC = 1<<9, + IFF_XMIT_DST_RELEASE = 1<<10, + IFF_DONT_BRIDGE = 1<<11, + IFF_DISABLE_NETPOLL = 1<<12, + IFF_MACVLAN_PORT = 1<<13, + IFF_BRIDGE_PORT = 1<<14, + IFF_OVS_DATAPATH = 1<<15, + IFF_TX_SKB_SHARING = 1<<16, + IFF_UNICAST_FLT = 1<<17, + IFF_TEAM_PORT = 1<<18, + IFF_SUPP_NOFCS = 1<<19, + IFF_LIVE_ADDR_CHANGE = 1<<20, + IFF_MACVLAN = 1<<21, +}; + +#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN +#define IFF_EBRIDGE IFF_EBRIDGE +#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE +#define IFF_MASTER_8023AD IFF_MASTER_8023AD +#define IFF_MASTER_ALB IFF_MASTER_ALB +#define IFF_BONDING IFF_BONDING +#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP +#define IFF_ISATAP IFF_ISATAP +#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON +#define IFF_WAN_HDLC IFF_WAN_HDLC +#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE +#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE +#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL +#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT +#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT +#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH +#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING +#define IFF_UNICAST_FLT IFF_UNICAST_FLT +#define IFF_TEAM_PORT IFF_TEAM_PORT +#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS +#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE +#define IFF_MACVLAN IFF_MACVLAN + /* * The DEVICE structure. * Actually, this whole structure is a big mistake. It mixes I/O -- cgit v1.2.3 From 946651cba26779864bcdbd7e12502f5a36c2de37 Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Sat, 15 Feb 2014 00:05:52 +0100 Subject: wl1251: split wl251 platform data to a separate structure Move the wl1251 part of the wl12xx platform data structure into a new structure specifically for wl1251. Change the platform data built-in block and board files accordingly. Signed-off-by: Luciano Coelho Acked-by: Tony Lindgren Reviewed-by: Felipe Balbi Reviewed-by: Sebastian Reichel Reviewed-by: Pavel Machek Signed-off-by: John W. Linville --- include/linux/wl12xx.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h index a54fe82e704b..b516b4fa22de 100644 --- a/include/linux/wl12xx.h +++ b/include/linux/wl12xx.h @@ -48,11 +48,15 @@ enum { WL12XX_TCXOCLOCK_33_6 = 7, /* 33.6 MHz */ }; -struct wl12xx_platform_data { +struct wl1251_platform_data { void (*set_power)(bool enable); /* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */ int irq; bool use_eeprom; +}; + +struct wl12xx_platform_data { + int irq; int board_ref_clock; int board_tcxo_clock; unsigned long platform_quirks; @@ -68,6 +72,10 @@ int wl12xx_set_platform_data(const struct wl12xx_platform_data *data); struct wl12xx_platform_data *wl12xx_get_platform_data(void); +int wl1251_set_platform_data(const struct wl1251_platform_data *data); + +struct wl1251_platform_data *wl1251_get_platform_data(void); + #else static inline @@ -82,6 +90,18 @@ struct wl12xx_platform_data *wl12xx_get_platform_data(void) return ERR_PTR(-ENODATA); } +static inline +int wl1251_set_platform_data(const struct wl1251_platform_data *data) +{ + return -ENOSYS; +} + +static inline +struct wl1251_platform_data *wl1251_get_platform_data(void) +{ + return ERR_PTR(-ENODATA); +} + #endif #endif -- cgit v1.2.3 From 1d207cd30b65fdd60d952cb9e100b6f776564f06 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sat, 15 Feb 2014 00:05:53 +0100 Subject: wl1251: move power GPIO handling into the driver Move the power GPIO handling from the board code into the driver. This is a dependency for device tree support. Signed-off-by: Sebastian Reichel Reviewed-by: Pavel Machek Acked-by: Tony Lindgren Signed-off-by: John W. Linville --- include/linux/wl12xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h index b516b4fa22de..a9c723be1acf 100644 --- a/include/linux/wl12xx.h +++ b/include/linux/wl12xx.h @@ -49,7 +49,7 @@ enum { }; struct wl1251_platform_data { - void (*set_power)(bool enable); + int power_gpio; /* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */ int irq; bool use_eeprom; -- cgit v1.2.3 From 3ebe8e257307a87c33460aa7d2b75dadd374ed9c Mon Sep 17 00:00:00 2001 From: "Zhao, Gang" Date: Tue, 18 Feb 2014 21:36:03 +0800 Subject: ieee80211: remove function ieee80211_{dsss_chan_to_freq, freq_to_dsss_chan} Function ieee80211_{dsss_chan_to_freq, freq_to_dsss_chan} have been replaced with ieee80211_{channel_to_frequency, frequency_to_channel}. There should be no users of the two functions now. So remove them. Cc: Johannes Berg Signed-off-by: Zhao, Gang Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 5f349355ee54..06299048c4f4 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2307,42 +2307,6 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC; } -/** - * ieee80211_dsss_chan_to_freq - get channel center frequency - * @channel: the DSSS channel - * - * Convert IEEE802.11 DSSS channel to the center frequency (MHz). - * Ref IEEE 802.11-2007 section 15.6 - */ -static inline int ieee80211_dsss_chan_to_freq(int channel) -{ - if ((channel > 0) && (channel < 14)) - return 2407 + (channel * 5); - else if (channel == 14) - return 2484; - else - return -1; -} - -/** - * ieee80211_freq_to_dsss_chan - get channel - * @freq: the frequency - * - * Convert frequency (MHz) to IEEE802.11 DSSS channel - * Ref IEEE 802.11-2007 section 15.6 - * - * This routine selects the channel with the closest center frequency. - */ -static inline int ieee80211_freq_to_dsss_chan(int freq) -{ - if ((freq >= 2410) && (freq < 2475)) - return (freq - 2405) / 5; - else if ((freq >= 2482) && (freq < 2487)) - return 14; - else - return -1; -} - /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs -- cgit v1.2.3 From 9813337a4b16ea5b1701b1d00f7e410f5decdfa5 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Sun, 2 Mar 2014 10:25:01 +0200 Subject: net/mlx4: Replace mlx4_en_mac_to_u64() with mlx4_mac_to_u64() Currently, the EN driver uses a private static function mlx4_en_mac_to_u64(). Move it to a common include file (driver.h) for mlx4_en and mlx4_ib for further use. Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index c257e1b211be..022055c8fb26 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -64,4 +64,16 @@ void mlx4_unregister_interface(struct mlx4_interface *intf); void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); +static inline u64 mlx4_mac_to_u64(u8 *addr) +{ + u64 mac = 0; + int i; + + for (i = 0; i < ETH_ALEN; i++) { + mac <<= 8; + mac |= addr[i]; + } + return mac; +} + #endif /* MLX4_DRIVER_H */ -- cgit v1.2.3 From ec5709403e6893acb4f7ca40514ebd29c3116836 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Sun, 2 Mar 2014 10:25:04 +0200 Subject: net/mlx4_en: Use union for BlueFlame WQE When BlueFlame is turned on, control segment of the TX WQE is changed, and the second line of it is used for QPN. Changed code to use a union in the mlx4_wqe_ctrl_seg instead of casting. This makes the code clearer and solves the static checker warning: drivers/net/ethernet/mellanox/mlx4/en_tx.c:839 mlx4_en_xmit() warn: potential memory corrupting cast 4 vs 2 bytes CC: Dan Carpenter Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/qp.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 59f8ba84568b..b66e7610d4ee 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -270,9 +270,14 @@ enum { struct mlx4_wqe_ctrl_seg { __be32 owner_opcode; - __be16 vlan_tag; - u8 ins_vlan; - u8 fence_size; + union { + struct { + __be16 vlan_tag; + u8 ins_vlan; + u8 fence_size; + }; + __be32 bf_qpn; + }; /* * High 24 bits are SRC remote buffer; low 8 bits are flags: * [7] SO (strong ordering) -- cgit v1.2.3 From f3baa393ffc9a7aefc0bf767729382085e81f606 Mon Sep 17 00:00:00 2001 From: Simon Wunderlich Date: Mon, 3 Mar 2014 17:23:11 +0100 Subject: UAPI: add MPLS label stack definition Labels for the Multiprotocol Label Switching are defined in RFC 3032 which was superseded by RFC 5462. Add the definition to UAPI and a stub header for include/linux. Signed-off-by: Simon Wunderlich Signed-off-by: Mathias Kretschmer Signed-off-by: David S. Miller --- include/linux/mpls.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/mpls.h (limited to 'include/linux') diff --git a/include/linux/mpls.h b/include/linux/mpls.h new file mode 100644 index 000000000000..9999145bc190 --- /dev/null +++ b/include/linux/mpls.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_MPLS_H +#define _LINUX_MPLS_H + +#include + +#endif /* _LINUX_MPLS_H */ -- cgit v1.2.3 From 3b02b56cd5988d569731f6c0c26992296e46b758 Mon Sep 17 00:00:00 2001 From: Vytas Dauksa Date: Tue, 17 Dec 2013 14:01:43 +0000 Subject: netfilter: ipset: add hash:ip,mark data type to ipset Introduce packet mark support with new ip,mark hash set. This includes userspace and kernelspace code, hash:ip,mark set tests and man page updates. The intended use of ip,mark set is similar to the ip:port type, but for protocols which don't use a predictable port number. Instead of port number it matches a firewall mark determined by a layer 7 filtering program like opendpi. As well as allowing or blocking traffic it will also be used for accounting packets and bytes sent for each protocol. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0c7d01eae56c..4ac00d4aa87e 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -39,11 +39,13 @@ enum ip_set_feature { IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG), IPSET_TYPE_IFACE_FLAG = 5, IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG), - IPSET_TYPE_NOMATCH_FLAG = 6, + IPSET_TYPE_MARK_FLAG = 6, + IPSET_TYPE_MARK = (1 << IPSET_TYPE_MARK_FLAG), + IPSET_TYPE_NOMATCH_FLAG = 7, IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG), /* Strictly speaking not a feature, but a flag for dumping: * this settype must be dumped last */ - IPSET_DUMP_LAST_FLAG = 7, + IPSET_DUMP_LAST_FLAG = 8, IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), }; @@ -171,8 +173,6 @@ struct ip_set_type { char name[IPSET_MAXNAMELEN]; /* Protocol version */ u8 protocol; - /* Set features to control swapping */ - u8 features; /* Set type dimension */ u8 dimension; /* @@ -182,6 +182,8 @@ struct ip_set_type { u8 family; /* Type revisions */ u8 revision_min, revision_max; + /* Set features to control swapping */ + u16 features; /* Create set */ int (*create)(struct net *net, struct ip_set *set, -- cgit v1.2.3 From af284ece87365f3a69723f5bcc1bcdb505b5eb5d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Thu, 13 Feb 2014 12:19:56 +0100 Subject: netfilter: ipset: Prepare the kernel for create option flags when no extension is needed Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 4ac00d4aa87e..f476bcec25ea 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -219,6 +219,8 @@ struct ip_set { u8 revision; /* Extensions */ u8 extensions; + /* Create flags */ + u8 flags; /* Default timeout value, if enabled */ u32 timeout; /* Element data size */ -- cgit v1.2.3 From 07cf8f5ae2657ac495b906c68ff3441ff8ba80ba Mon Sep 17 00:00:00 2001 From: Josh Hunt Date: Fri, 28 Feb 2014 22:14:57 -0500 Subject: netfilter: ipset: add forceadd kernel support for hash set types Adds a new property for hash set types, where if a set is created with the 'forceadd' option and the set becomes full the next addition to the set may succeed and evict a random entry from the set. To keep overhead low eviction is done very simply. It checks to see which bucket the new entry would be added. If the bucket's pos value is non-zero (meaning there's at least one entry in the bucket) it replaces the first entry in the bucket. If pos is zero, then it continues down the normal add process. This property is useful if you have a set for 'ban' lists where it may not matter if you release some entries from the set early. Signed-off-by: Josh Hunt Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index f476bcec25ea..96afc29184be 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -65,6 +65,7 @@ enum ip_set_extension { #define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) #define SET_WITH_COUNTER(s) ((s)->extensions & IPSET_EXT_COUNTER) #define SET_WITH_COMMENT(s) ((s)->extensions & IPSET_EXT_COMMENT) +#define SET_WITH_FORCEADD(s) ((s)->flags & IPSET_CREATE_FLAG_FORCEADD) /* Extension id, in size order */ enum ip_set_ext_id { @@ -255,6 +256,8 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) cadt_flags |= IPSET_FLAG_WITH_COUNTERS; if (SET_WITH_COMMENT(set)) cadt_flags |= IPSET_FLAG_WITH_COMMENT; + if (SET_WITH_FORCEADD(set)) + cadt_flags |= IPSET_FLAG_WITH_FORCEADD; if (!cadt_flags) return 0; -- cgit v1.2.3 From 9859ccd2c8be63ce939522e63e265f2b0caa1109 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 28 Feb 2014 16:36:23 +0100 Subject: can: introduce the data bitrate configuration for CAN FD As CAN FD offers a second bitrate for the data section of the CAN frame the infrastructure for storing and configuring this second bitrate is introduced. Improved the readability of the if-statement by inserting some newlines. Signed-off-by: Oliver Hartkopp Acked-by: Stephane Grosjean Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index dc5f9026b67f..8adaee96f292 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -33,8 +33,9 @@ enum can_mode { struct can_priv { struct can_device_stats can_stats; - struct can_bittiming bittiming; - const struct can_bittiming_const *bittiming_const; + struct can_bittiming bittiming, data_bittiming; + const struct can_bittiming_const *bittiming_const, + *data_bittiming_const; struct can_clock clock; enum can_state state; @@ -45,6 +46,7 @@ struct can_priv { struct timer_list restart_timer; int (*do_set_bittiming)(struct net_device *dev); + int (*do_set_data_bittiming)(struct net_device *dev); int (*do_set_mode)(struct net_device *dev, enum can_mode mode); int (*do_get_state)(const struct net_device *dev, enum can_state *state); -- cgit v1.2.3 From bc05a8944a344acdb81a65de055ca6febbf9657c Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 28 Feb 2014 16:36:24 +0100 Subject: can: allow to change the device mtu for CAN FD capable devices The configuration for CAN FD depends on CAN_CTRLMODE_FD enabled in the driver specific ctrlmode_supported capabilities. The configuration can be done either with the 'fd { on | off }' option in the 'ip' tool from iproute2 or by setting the CAN netdevice MTU to CAN_MTU (16) or to CANFD_MTU (72). Signed-off-by: Oliver Hartkopp Acked-by: Stephane Grosjean Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 8adaee96f292..3ce5e526525f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -113,6 +113,7 @@ struct can_priv *safe_candev_priv(struct net_device *dev); int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); +int can_change_mtu(struct net_device *dev, int new_mtu); int register_candev(struct net_device *dev); void unregister_candev(struct net_device *dev); -- cgit v1.2.3 From 693350c2ffe42a21185070b1e8ab77959b45d61e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 10 Mar 2014 09:41:46 -0700 Subject: netdev: set __percpu attribute on netdev_alloc_pcpu_stats This patch fixes sparse warnings in vlan driver. It propagates the sparse __percpu attribute from alloc_percpu into netdev_alloc_pcpu_stats. I expect it may trigger additional sparse warnings from other drivers that are missing the __percpu attribute. Signed-off-by: Stephen Hemminger Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a869488b8ae..b8d8c805fd75 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1812,7 +1812,7 @@ struct pcpu_sw_netstats { #define netdev_alloc_pcpu_stats(type) \ ({ \ - typeof(type) *pcpu_stats = alloc_percpu(type); \ + typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ if (pcpu_stats) { \ int i; \ for_each_possible_cpu(i) { \ -- cgit v1.2.3 From 6ee51a4e866bbb0921180b457ed16cd172859346 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 12 Mar 2014 12:00:37 +0200 Subject: mlx4: Adjust QP1 multiplexing for RoCE/SRIOV This requires the following modifications: 1. Fix build_mlx4_header to properly fill in the ETH fields 2. Adjust mux and demux QP1 flow to support RoCE. This commit still assumes only one GID per slave for RoCE. The commit enabling multiple GIDs is a subsequent commit, and is done separately because of its complexity. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 5edd2c68274d..fbe6cda00ba7 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -48,6 +48,8 @@ #define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 +#define MLX4_ROCE_MAX_GIDS 128 + enum { MLX4_FLAG_MSI_X = 1 << 0, MLX4_FLAG_OLD_PORT_CMDS = 1 << 1, @@ -1182,6 +1184,8 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); +int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id); +int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid); int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, u32 max_range_qpn); -- cgit v1.2.3 From 9cd593529c8652785bc9962acc79b6b176741f99 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 12 Mar 2014 12:00:38 +0200 Subject: mlx4_core: For RoCE, allow slaves to set the GID entry at that slave's index For IB transport, the host determines the slave GIDs. For ETH (RoCE), however, the slave's GID is determined by the IP address that the slave itself assigns to the ETH device used by RoCE. In this case, the slave must be able to write its GIDs to the HCA gid table (at the GID indices that slave "owns"). This commit adds processing for the SET_PORT_GID_TABLE opcode modifier for the SET_PORT command wrapper (so that slaves may modify their GIDS for RoCE). Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index fbe6cda00ba7..e4853650679d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1184,8 +1184,11 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); -int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id); -int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid); + +int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, + int *slave_id); +int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, + u8 *gid); int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, u32 max_range_qpn); -- cgit v1.2.3 From b6ffaeffaea4d92f05f5ba1ef54df407cb7c8517 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 12 Mar 2014 12:00:39 +0200 Subject: mlx4: In RoCE allow guests to have multiple GIDS The GIDs are statically distributed, as follows: PF: gets 16 GIDs VFs: Remaining GIDS are divided evenly between VFs activated by the driver. If the division is not even, lower-numbered VFs get an extra GID. For an IB interface, the number of gids per guest remains as before: one gid per guest. Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e4853650679d..86e02e5c2c77 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -49,6 +49,7 @@ #define MIN_MSIX_P_PORT 5 #define MLX4_ROCE_MAX_GIDS 128 +#define MLX4_ROCE_PF_GIDS 16 enum { MLX4_FLAG_MSI_X = 1 << 0, -- cgit v1.2.3 From 5ea8bbfc49291b7e23161fe4de0bf3e4a4e34b18 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 12 Mar 2014 12:00:41 +0200 Subject: mlx4: Implement IP based gids support for RoCE/SRIOV Since there is no connection between the MAC/VLAN and the GID when using IP-based addressing, the proxy QP1 (running on the slave) must pass the source-mac, destination-mac, and vlan_id information separately from the GID. Additionally, the Host must pass the remote source-mac and vlan_id back to the slave, This is achieved as follows: Outgoing MADs: 1. Source MAC: obtained from the CQ completion structure (struct ib_wc, smac field). 2. Destination MAC: obtained from the tunnel header 3. vlan_id: obtained from the tunnel header. Incoming MADs 1. The source (i.e., remote) MAC and vlan_id are passed in the tunnel header to the proxy QP1. VST mode support: For outgoing MADs, the vlan_id obtained from the header is discarded, and the vlan_id specified by the Hypervisor is used instead. For incoming MADs, the incoming vlan_id (in the wc) is discarded, and the "invalid" vlan (0xffff) is substituted when forwarding to the slave. Signed-off-by: Moni Shoua Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 7 +++++++ include/linux/mlx4/device.h | 3 ++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 79a347238168..009985628257 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -240,6 +240,13 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf); int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state); +/* + * mlx4_get_slave_default_vlan - + * return true if VST ( default vlan) + * if VST, will return vlan & qos (if not NULL) + */ +bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave, + u16 *vlan, u8 *qos); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 86e02e5c2c77..f211b51dc726 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -632,7 +632,8 @@ struct mlx4_eth_av { u8 hop_limit; __be32 sl_tclass_flowlabel; u8 dgid[16]; - u32 reserved4[2]; + u8 s_mac[6]; + u8 reserved4[2]; __be16 vlan; u8 mac[ETH_ALEN]; }; -- cgit v1.2.3 From 57a7744e09867ebcfa0ccf1d6d529caa7728d552 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 13 Mar 2014 21:26:42 -0700 Subject: net: Replace u64_stats_fetch_begin_bh to u64_stats_fetch_begin_irq Replace the bh safe variant with the hard irq safe variant. We need a hard irq safe variant to deal with netpoll transmitting packets from hard irq context, and we need it in most if not all of the places using the bh safe variant. Except on 32bit uni-processor the code is exactly the same so don't bother with a bh variant, just have a hard irq safe variant that everyone can use. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 7bfabd20204c..4b4439e75f45 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -27,8 +27,8 @@ * (On UP, there is no seqcount_t protection, a reader allowing interrupts could * read partial values) * - * 7) For softirq uses, readers can use u64_stats_fetch_begin_bh() and - * u64_stats_fetch_retry_bh() helpers + * 7) For irq and softirq uses, readers can use u64_stats_fetch_begin_irq() and + * u64_stats_fetch_retry_irq() helpers * * Usage : * @@ -114,31 +114,31 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, } /* - * In case softirq handlers can update u64 counters, readers can use following helpers + * In case irq handlers can update u64 counters, readers can use following helpers * - SMP 32bit arches use seqcount protection, irq safe. - * - UP 32bit must disable BH. + * - UP 32bit must disable irqs. * - 64bit have no problem atomically reading u64 values, irq safe. */ -static inline unsigned int u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp) +static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_begin(&syncp->seq); #else #if BITS_PER_LONG==32 - local_bh_disable(); + local_irq_disable(); #endif return 0; #endif } -static inline bool u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp, +static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_retry(&syncp->seq, start); #else #if BITS_PER_LONG==32 - local_bh_enable(); + local_irq_enable(); #endif return false; #endif -- cgit v1.2.3 From a797ca1eadeef7f4fdba2ab5d143d56cc3ec5da3 Mon Sep 17 00:00:00 2001 From: Franky Lin Date: Sat, 15 Mar 2014 17:18:17 +0100 Subject: brcmfmac: add BCM4354 SDIO interface support BCM4354 is an a/b/g/n/ac 2x2 WiFi chip. This patch adds support for it through SDIO interface. Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Arend Van Spriel Signed-off-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index d8836623f36a..0f01fe065424 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -31,6 +31,7 @@ #define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_43362 43362 +#define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -- cgit v1.2.3 From ff6076314339e079806d9d2f3de9c9b768e94db1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Mar 2014 20:47:49 -0700 Subject: netpoll: Add netpoll_rx_processing Add a helper netpoll_rx_processing that reports when netpoll has receive side processing to perform. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netpoll.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index fbfdb9d8d3a7..479d15c97770 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -82,14 +82,24 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) local_irq_restore(flags); } - +#ifdef CONFIG_NETPOLL_TRAP +static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) +{ + return !list_empty(&npinfo->rx_np); +} +#else +static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) +{ + return false; +} +#endif #ifdef CONFIG_NETPOLL static inline bool netpoll_rx_on(struct sk_buff *skb) { struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); - return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags); + return npinfo && (netpoll_rx_processing(npinfo) || npinfo->rx_flags); } static inline bool netpoll_rx(struct sk_buff *skb) @@ -105,8 +115,8 @@ static inline bool netpoll_rx(struct sk_buff *skb) npinfo = rcu_dereference_bh(skb->dev->npinfo); spin_lock(&npinfo->rx_lock); - /* check rx_flags again with the lock held */ - if (npinfo->rx_flags && __netpoll_rx(skb, npinfo)) + /* check rx_processing again with the lock held */ + if (netpoll_rx_processing(npinfo) && __netpoll_rx(skb, npinfo)) ret = true; spin_unlock(&npinfo->rx_lock); -- cgit v1.2.3 From b6bacd550c33124ea76291bd84ac42c8d30767eb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Mar 2014 20:48:28 -0700 Subject: netpoll: Don't drop all received packets. Change the strategy of netpoll from dropping all packets received during netpoll_poll_dev to calling napi poll with a budget of 0 (to avoid processing drivers rx queue), and to ignore packets received with netif_rx (those will safely be placed on the backlog queue). All of the netpoll supporting drivers have been reviewed to ensure either thay use netif_rx or that a budget of 0 is supported by their napi poll routine and that a budget of 0 will not process the drivers rx queues. Not dropping packets makes NETPOLL_RX_DROP unnecesary so it is removed. npinfo->rx_flags is removed as rx_flags with just the NETPOLL_RX_ENABLED flag becomes just a redundant mirror of list_empty(&npinfo->rx_np). Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netpoll.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 479d15c97770..154f9776056c 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -39,7 +39,6 @@ struct netpoll { struct netpoll_info { atomic_t refcnt; - unsigned long rx_flags; spinlock_t rx_lock; struct semaphore dev_lock; struct list_head rx_np; /* netpolls that registered an rx_skb_hook */ @@ -99,7 +98,7 @@ static inline bool netpoll_rx_on(struct sk_buff *skb) { struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); - return npinfo && (netpoll_rx_processing(npinfo) || npinfo->rx_flags); + return npinfo && netpoll_rx_processing(npinfo); } static inline bool netpoll_rx(struct sk_buff *skb) -- cgit v1.2.3 From ad8d475244b4112a0f5331e78d043d3a4c9eb37e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Mar 2014 20:49:43 -0700 Subject: netpoll: Move netpoll_trap under CONFIG_NETPOLL_TRAP Now that we no longer need to receive packets to safely drain the network drivers receive queue move netpoll_trap and netpoll_set_trap under CONFIG_NETPOLL_TRAP Making netpoll_trap and netpoll_set_trap noop inline functions when CONFIG_NETPOLL_TRAP is not set. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netpoll.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 154f9776056c..ab9aaaff8d04 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -65,8 +65,6 @@ void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp); int netpoll_setup(struct netpoll *np); -int netpoll_trap(void); -void netpoll_set_trap(int trap); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free_async(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); @@ -82,11 +80,20 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) } #ifdef CONFIG_NETPOLL_TRAP +int netpoll_trap(void); +void netpoll_set_trap(int trap); static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) { return !list_empty(&npinfo->rx_np); } #else +static inline int netpoll_trap(void) +{ + return 0; +} +static inline void netpoll_set_trap(int trap) +{ +} static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) { return false; -- cgit v1.2.3 From e1bd4d3d7dd2a4a0e731ffe07c439927c23f16ea Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Mar 2014 20:50:58 -0700 Subject: netpoll: Move all receive processing under CONFIG_NETPOLL_TRAP Make rx_skb_hook, and rx in struct netpoll depend on CONFIG_NETPOLL_TRAP Make rx_lock, rx_np, and neigh_tx in struct netpoll_info depend on CONFIG_NETPOLL_TRAP Make the functions netpoll_rx_on, netpoll_rx, and netpoll_receive_skb no-ops when CONFIG_NETPOLL_TRAP is not set. Only build netpoll_neigh_reply, checksum_udp service_neigh_queue, pkt_is_ns, and __netpoll_rx when CONFIG_NETPOLL_TRAP is defined. Add helper functions netpoll_trap_setup, netpoll_trap_setup_info, netpoll_trap_cleanup, and netpoll_trap_cleanup_info that initialize and cleanup the struct netpoll and struct netpoll_info receive specific fields when CONFIG_NETPOLL_TRAP is enabled and do nothing otherwise. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netpoll.h | 73 +++++++++++++++++++++++++++---------------------- 1 file changed, 40 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index ab9aaaff8d04..a0632af88d8b 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -24,32 +24,38 @@ struct netpoll { struct net_device *dev; char dev_name[IFNAMSIZ]; const char *name; - void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb, - int offset, int len); union inet_addr local_ip, remote_ip; bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; - struct list_head rx; /* rx_np list element */ struct work_struct cleanup_work; + +#ifdef CONFIG_NETPOLL_TRAP + void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb, + int offset, int len); + struct list_head rx; /* rx_np list element */ +#endif }; struct netpoll_info { atomic_t refcnt; - spinlock_t rx_lock; struct semaphore dev_lock; - struct list_head rx_np; /* netpolls that registered an rx_skb_hook */ - struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ struct sk_buff_head txq; struct delayed_work tx_work; struct netpoll *netpoll; struct rcu_head rcu; + +#ifdef CONFIG_NETPOLL_TRAP + spinlock_t rx_lock; + struct list_head rx_np; /* netpolls that registered an rx_skb_hook */ + struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ +#endif }; #ifdef CONFIG_NETPOLL @@ -68,7 +74,6 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free_async(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo); void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev); static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) @@ -82,25 +87,12 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) #ifdef CONFIG_NETPOLL_TRAP int netpoll_trap(void); void netpoll_set_trap(int trap); +int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo); static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) { return !list_empty(&npinfo->rx_np); } -#else -static inline int netpoll_trap(void) -{ - return 0; -} -static inline void netpoll_set_trap(int trap) -{ -} -static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) -{ - return false; -} -#endif -#ifdef CONFIG_NETPOLL static inline bool netpoll_rx_on(struct sk_buff *skb) { struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); @@ -138,6 +130,33 @@ static inline int netpoll_receive_skb(struct sk_buff *skb) return 0; } +#else +static inline int netpoll_trap(void) +{ + return 0; +} +static inline void netpoll_set_trap(int trap) +{ +} +static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) +{ + return false; +} +static inline bool netpoll_rx(struct sk_buff *skb) +{ + return false; +} +static inline bool netpoll_rx_on(struct sk_buff *skb) +{ + return false; +} +static inline int netpoll_receive_skb(struct sk_buff *skb) +{ + return 0; +} +#endif + +#ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) { struct net_device *dev = napi->dev; @@ -166,18 +185,6 @@ static inline bool netpoll_tx_running(struct net_device *dev) } #else -static inline bool netpoll_rx(struct sk_buff *skb) -{ - return false; -} -static inline bool netpoll_rx_on(struct sk_buff *skb) -{ - return false; -} -static inline int netpoll_receive_skb(struct sk_buff *skb) -{ - return 0; -} static inline void *netpoll_poll_lock(struct napi_struct *napi) { return NULL; -- cgit v1.2.3 From 9c62a68d13119a1ca9718381d97b0cb415ff4e9d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Mar 2014 20:51:52 -0700 Subject: netpoll: Remove dead packet receive code (CONFIG_NETPOLL_TRAP) The netpoll packet receive code only becomes active if the netpoll rx_skb_hook is implemented, and there is not a single implementation of the netpoll rx_skb_hook in the kernel. All of the out of tree implementations I have found all call netpoll_poll which was removed from the kernel in 2011, so this change should not add any additional breakage. There are problems with the netpoll packet receive code. __netpoll_rx does not call dev_kfree_skb_irq or dev_kfree_skb_any in hard irq context. netpoll_neigh_reply leaks every skb it receives. Reception of packets does not work successfully on stacked devices (aka bonding, team, bridge, and vlans). Given that the netpoll packet receive code is buggy, there are no out of tree users that will be merged soon, and the code has not been used for in tree for a decade let's just remove it. Reverting this commit can server as a starting point for anyone who wants to resurrect netpoll packet reception support. Acked-by: Eric Dumazet Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 ---------- include/linux/netpoll.h | 84 ----------------------------------------------- 2 files changed, 101 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b8d8c805fd75..4b6d12c7b803 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1979,9 +1979,6 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -#ifdef CONFIG_NETPOLL_TRAP -int netpoll_trap(void); -#endif int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) @@ -2186,12 +2183,6 @@ static inline void netif_tx_start_all_queues(struct net_device *dev) static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue) { -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) { - netif_tx_start_queue(dev_queue); - return; - } -#endif if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) __netif_schedule(dev_queue->qdisc); } @@ -2435,10 +2426,6 @@ static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index) static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) - return; -#endif netif_tx_stop_queue(txq); } @@ -2473,10 +2460,6 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) - return; -#endif if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) __netif_schedule(txq->qdisc); } diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index a0632af88d8b..1b475a5a7239 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -31,12 +31,6 @@ struct netpoll { u8 remote_mac[ETH_ALEN]; struct work_struct cleanup_work; - -#ifdef CONFIG_NETPOLL_TRAP - void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb, - int offset, int len); - struct list_head rx; /* rx_np list element */ -#endif }; struct netpoll_info { @@ -50,12 +44,6 @@ struct netpoll_info { struct netpoll *netpoll; struct rcu_head rcu; - -#ifdef CONFIG_NETPOLL_TRAP - spinlock_t rx_lock; - struct list_head rx_np; /* netpolls that registered an rx_skb_hook */ - struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ -#endif }; #ifdef CONFIG_NETPOLL @@ -84,78 +72,6 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) local_irq_restore(flags); } -#ifdef CONFIG_NETPOLL_TRAP -int netpoll_trap(void); -void netpoll_set_trap(int trap); -int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo); -static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) -{ - return !list_empty(&npinfo->rx_np); -} - -static inline bool netpoll_rx_on(struct sk_buff *skb) -{ - struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); - - return npinfo && netpoll_rx_processing(npinfo); -} - -static inline bool netpoll_rx(struct sk_buff *skb) -{ - struct netpoll_info *npinfo; - unsigned long flags; - bool ret = false; - - local_irq_save(flags); - - if (!netpoll_rx_on(skb)) - goto out; - - npinfo = rcu_dereference_bh(skb->dev->npinfo); - spin_lock(&npinfo->rx_lock); - /* check rx_processing again with the lock held */ - if (netpoll_rx_processing(npinfo) && __netpoll_rx(skb, npinfo)) - ret = true; - spin_unlock(&npinfo->rx_lock); - -out: - local_irq_restore(flags); - return ret; -} - -static inline int netpoll_receive_skb(struct sk_buff *skb) -{ - if (!list_empty(&skb->dev->napi_list)) - return netpoll_rx(skb); - return 0; -} - -#else -static inline int netpoll_trap(void) -{ - return 0; -} -static inline void netpoll_set_trap(int trap) -{ -} -static inline bool netpoll_rx_processing(struct netpoll_info *npinfo) -{ - return false; -} -static inline bool netpoll_rx(struct sk_buff *skb) -{ - return false; -} -static inline bool netpoll_rx_on(struct sk_buff *skb) -{ - return false; -} -static inline int netpoll_receive_skb(struct sk_buff *skb) -{ - return 0; -} -#endif - #ifdef CONFIG_NETPOLL static inline void *netpoll_poll_lock(struct napi_struct *napi) { -- cgit v1.2.3 From aa475b0ef34a8230b8cc3a298bf67c668540d689 Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Wed, 19 Mar 2014 13:14:40 +0200 Subject: wireless: max MSDU size for DMG networks In the 802.11ad, aka DMG (Dynamic Multi-Gigabit), aka 60Ghz spec, maximum MSDU size extended to 7920 bytes. add #define for this. Signed-off-by: Vladimir Kondratiev Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 5f349355ee54..cde7ede8e554 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -154,6 +154,10 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) 802.11e clarifies the figure in section 7.1.2. The frame body is up to 2304 octets long (maximum MSDU size) plus any crypt overhead. */ #define IEEE80211_MAX_DATA_LEN 2304 +/* 802.11ad extends maximum MSDU size for DMG (freq > 40Ghz) networks + * to 7920 bytes, see 8.2.3 General frame format + */ +#define IEEE80211_MAX_DATA_LEN_DMG 7920 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 -- cgit v1.2.3 From 1ab95d37bcc3ff2d69e3871e4f056bab7aed0b85 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Wed, 19 Mar 2014 18:11:50 +0200 Subject: net/mlx4: Add data structures to support N-Ports per VF Adds the required data structures to support VFs with N (1 or 2) ports instead of always using the number of physical ports. Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index f211b51dc726..b3044f32aef1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -84,6 +84,7 @@ enum { enum { MLX4_MAX_NUM_PF = 16, MLX4_MAX_NUM_VF = 64, + MLX4_MAX_NUM_VF_P_PORT = 64, MLX4_MFUNC_MAX = 80, MLX4_MAX_EQ_NUM = 1024, MLX4_MFUNC_EQ_NUM = 4, @@ -664,6 +665,11 @@ struct mlx4_quotas { int xrcd; }; +struct mlx4_vf_dev { + u8 min_port; + u8 n_ports; +}; + struct mlx4_dev { struct pci_dev *pdev; unsigned long flags; @@ -679,6 +685,7 @@ struct mlx4_dev { int oper_log_mgm_entry_size; u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; + struct mlx4_vf_dev *dev_vfs; }; struct mlx4_eqe { -- cgit v1.2.3 From f74462acf8f390528c8b7937f227c6c90d017f3b Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Wed, 19 Mar 2014 18:11:51 +0200 Subject: net/mlx4: Add utils for N-Port VFs This patch adds the following utils: 1. Convert slave_id -> VF 2. Get the active ports by slave_id 3. Convert slave's port to real port 4. Get the slave's port from real port 5. Get all slaves that uses the i'th real port 6. Get all slaves that uses the i'th real port exclusively Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b3044f32aef1..122c7cabaee7 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1204,4 +1204,31 @@ int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, cycle_t mlx4_read_clock(struct mlx4_dev *dev); +struct mlx4_active_ports { + DECLARE_BITMAP(ports, MLX4_MAX_PORTS); +}; +/* Returns a bitmap of the physical ports which are assigned to slave */ +struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave); + +/* Returns the physical port that represents the virtual port of the slave, */ +/* or a value < 0 in case of an error. If a slave has 2 ports, the identity */ +/* mapping is returned. */ +int mlx4_slave_convert_port(struct mlx4_dev *dev, int slave, int port); + +struct mlx4_slaves_pport { + DECLARE_BITMAP(slaves, MLX4_MFUNC_MAX); +}; +/* Returns a bitmap of all slaves that are assigned to port. */ +struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev, + int port); + +/* Returns a bitmap of all slaves that are assigned exactly to all the */ +/* the ports that are set in crit_ports. */ +struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv( + struct mlx4_dev *dev, + const struct mlx4_active_ports *crit_ports); + +/* Returns the slave's virtual port that represents the physical port. */ +int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 449fc48866f7d84b0d9a19201de18a4dd4d3488c Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Wed, 19 Mar 2014 18:11:52 +0200 Subject: net/mlx4: Adapt code for N-Port VF Adds support for N-Port VFs, this includes: 1. Adding support in the wrapped FW command In wrapped commands, we need to verify and convert the slave's port into the real physical port. Furthermore, when sending the response back to the slave, a reverse conversion should be made. 2. Adjusting sqpn for QP1 para-virtualization The slave assumes that sqpn is used for QP1 communication. If the slave is assigned to a port != (first port), we need to adjust the sqpn that will direct its QP1 packets into the correct endpoint. 3. Adjusting gid[5] to modify the port for raw ethernet In B0 steering, gid[5] contains the port. It needs to be adjusted into the physical port. 4. Adjusting number of ports in the query / ports caps in the FW commands When a slave queries the hardware, it needs to view only the physical ports it's assigned to. 5. Adjusting the sched_qp according to the port number The QP port is encoded in the sched_qp, thus in modify_qp we need to encode the correct port in sched_qp. Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 122c7cabaee7..6b3998396b99 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1231,4 +1231,5 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv( /* Returns the slave's virtual port that represents the physical port. */ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port); +int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port); #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 259fef033ffe4e70bf7f358c53400a09f1b5384e Mon Sep 17 00:00:00 2001 From: Ben Chan Date: Wed, 19 Mar 2014 14:00:06 -0700 Subject: net: cdc_ncm: respect operator preferred MTU reported by MBIM According to "Universal Serial Bus Communications Class Subclass Specification for Mobile Broadband Interface Model, Revision 1.0, Errata-1" published by USB-IF, the wMTU field of the MBIM extended functional descriptor indicates the operator preferred MTU for IP data streams. This patch modifies cdc_ncm_setup to ensure that the MTU value set on the usbnet device does not exceed the operator preferred MTU indicated by wMTU if the MBIM device exposes a MBIM extended functional descriptor. Signed-off-by: Ben Chan Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index c3fa80745996..bdf05fb36729 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -93,6 +93,7 @@ struct cdc_ncm_ctx { const struct usb_cdc_ncm_desc *func_desc; const struct usb_cdc_mbim_desc *mbim_desc; + const struct usb_cdc_mbim_extended_desc *mbim_extended_desc; const struct usb_cdc_ether_desc *ether_desc; struct usb_interface *control; -- cgit v1.2.3 From 6092315dfdec5185881605d15a0e200d6e90eb66 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Thu, 20 Mar 2014 22:21:52 +0100 Subject: ptp: introduce programmable pins. This patch adds a pair of new ioctls to the PTP Hardware Clock device interface. Using the ioctls, user space programs can query each pin to find out its current function and also reprogram a different function if desired. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 38a993508327..0d8ff3fb84ba 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -49,7 +49,11 @@ struct ptp_clock_request { * @n_alarm: The number of programmable alarms. * @n_ext_ts: The number of external time stamp channels. * @n_per_out: The number of programmable periodic signals. + * @n_pins: The number of programmable pins. * @pps: Indicates whether the clock supports a PPS callback. + * @pin_config: Array of length 'n_pins'. If the number of + * programmable pins is nonzero, then drivers must + * allocate and initialize this array. * * clock operations * @@ -70,6 +74,18 @@ struct ptp_clock_request { * parameter request: Desired resource to enable or disable. * parameter on: Caller passes one to enable or zero to disable. * + * @verify: Confirm that a pin can perform a given function. The PTP + * Hardware Clock subsystem maintains the 'pin_config' + * array on behalf of the drivers, but the PHC subsystem + * assumes that every pin can perform every function. This + * hook gives drivers a way of telling the core about + * limitations on specific pins. This function must return + * zero if the function can be assigned to this pin, and + * nonzero otherwise. + * parameter pin: index of the pin in question. + * parameter func: the desired function to use. + * parameter chan: the function channel index to use. + * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). * @@ -83,13 +99,17 @@ struct ptp_clock_info { int n_alarm; int n_ext_ts; int n_per_out; + int n_pins; int pps; + struct ptp_pin_desc *pin_config; int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime)(struct ptp_clock_info *ptp, struct timespec *ts); int (*settime)(struct ptp_clock_info *ptp, const struct timespec *ts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); + int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan); }; struct ptp_clock; @@ -156,4 +176,17 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); +/** + * ptp_find_pin() - obtain the pin index of a given auxiliary function + * + * @ptp: The clock obtained from ptp_clock_register(). + * @func: One of the ptp_pin_function enumerated values. + * @chan: The particular functional channel to find. + * Return: Pin index in the range of zero to ptp_clock_caps.n_pins - 1, + * or -1 if the auxiliary function cannot be found. + */ + +int ptp_find_pin(struct ptp_clock *ptp, + enum ptp_pin_function func, unsigned int chan); + #endif -- cgit v1.2.3 From fb7c03dfc48eb81bda368561f4ca162749d127c9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 20 Mar 2014 19:50:33 -0700 Subject: if_vlan: Call dev_kfree_skb_any instead of kfree_skb. Replace kfree_skb with dev_kfree_skb_any in vlan_insert_tag as vlan_insert_tag can be called from hard irq context (netpoll) and from other contexts. dev_kfree_skb_any is used as vlan_insert_tag only frees the skb if the skb can not be modified to insert a tag, in which case vlan_insert_tag drops the skb. Signed-off-by: "Eric W. Biederman" --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index bbedfb56bd66..d3d2306f00bf 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -288,7 +288,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) { - kfree_skb(skb); + dev_kfree_skb_any(skb); return NULL; } veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN); -- cgit v1.2.3 From 61b905da33ae25edb6b9d2a5de21e34c3a77efe3 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 24 Mar 2014 15:34:47 -0700 Subject: net: Rename skb->rxhash to skb->hash The packet hash can be considered a property of the packet, not just on RX path. This patch changes name of rxhash and l4_rxhash skbuff fields to be hash and l4_hash respectively. This includes changing uses of the field in the code which don't call the access functions. Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Cc: Mahesh Bandewar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 03db95ab8a8c..aa2c22cb8158 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -444,11 +444,11 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @tc_verd: traffic control verdict - * @rxhash: the packet hash computed on receive + * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed - * @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport + * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not @@ -537,7 +537,7 @@ struct sk_buff { int skb_iif; - __u32 rxhash; + __u32 hash; __be16 vlan_proto; __u16 vlan_tci; @@ -556,7 +556,7 @@ struct sk_buff { #endif __u8 pfmemalloc:1; __u8 ooo_okay:1; - __u8 l4_rxhash:1; + __u8 l4_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; __u8 no_fcs:1; @@ -815,40 +815,40 @@ enum pkt_hash_types { static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { - skb->l4_rxhash = (type == PKT_HASH_TYPE_L4); - skb->rxhash = hash; + skb->l4_hash = (type == PKT_HASH_TYPE_L4); + skb->hash = hash; } void __skb_get_hash(struct sk_buff *skb); static inline __u32 skb_get_hash(struct sk_buff *skb) { - if (!skb->l4_rxhash) + if (!skb->l4_hash) __skb_get_hash(skb); - return skb->rxhash; + return skb->hash; } static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { - return skb->rxhash; + return skb->hash; } static inline void skb_clear_hash(struct sk_buff *skb) { - skb->rxhash = 0; - skb->l4_rxhash = 0; + skb->hash = 0; + skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { - if (!skb->l4_rxhash) + if (!skb->l4_hash) skb_clear_hash(skb); } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { - to->rxhash = from->rxhash; - to->l4_rxhash = from->l4_rxhash; + to->hash = from->hash; + to->l4_hash = from->l4_hash; }; #ifdef NET_SKBUFF_DATA_USES_OFFSET -- cgit v1.2.3 From 71e415e44c1f9b7a4f05dac4f8038575dbef0c6f Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Tue, 25 Mar 2014 17:44:42 +0800 Subject: vlan: make a new function vlan_dev_vlan_proto() and export The vlan support 2 proto: 802.1q and 802.1ad, so make a new function called vlan_dev_vlan_proto() which could return the vlan proto for input dev. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index d3d2306f00bf..13bbbde00e68 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -110,6 +110,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); +extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings @@ -216,6 +217,12 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev) return 0; } +static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) +{ + BUG(); + return 0; +} + static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { -- cgit v1.2.3 From 1edb9ca69e8a7988900fc0283e10550b5592164d Mon Sep 17 00:00:00 2001 From: Siva Reddy Date: Tue, 25 Mar 2014 12:10:54 -0700 Subject: net: sxgbe: add basic framework for Samsung 10Gb ethernet driver This patch adds support for Samsung 10Gb ethernet driver(sxgbe). - sxgbe core initialization - Tx and Rx support - MDIO support - ISRs for Tx and Rx - ifconfig support to driver Signed-off-by: Siva Reddy Kallam Signed-off-by: Vipul Pandya Signed-off-by: Girish K S Neatening-by: Joe Perches Signed-off-by: Byungho An Signed-off-by: David S. Miller --- include/linux/sxgbe_platform.h | 54 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 include/linux/sxgbe_platform.h (limited to 'include/linux') diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h new file mode 100644 index 000000000000..a62442cf0037 --- /dev/null +++ b/include/linux/sxgbe_platform.h @@ -0,0 +1,54 @@ +/* + * 10G controller driver for Samsung EXYNOS SoCs + * + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Author: Siva Reddy Kallam + * + * 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. + */ +#ifndef __SXGBE_PLATFORM_H__ +#define __SXGBE_PLATFORM_H__ + +/* MDC Clock Selection define*/ +#define SXGBE_CSR_100_150M 0x0 /* MDC = clk_scr_i/62 */ +#define SXGBE_CSR_150_250M 0x1 /* MDC = clk_scr_i/102 */ +#define SXGBE_CSR_250_300M 0x2 /* MDC = clk_scr_i/122 */ +#define SXGBE_CSR_300_350M 0x3 /* MDC = clk_scr_i/142 */ +#define SXGBE_CSR_350_400M 0x4 /* MDC = clk_scr_i/162 */ +#define SXGBE_CSR_400_500M 0x5 /* MDC = clk_scr_i/202 */ + +/* Platfrom data for platform device structure's + * platform_data field + */ +struct sxgbe_mdio_bus_data { + unsigned int phy_mask; + int *irqs; + int probed_phy_irq; +}; + +struct sxgbe_dma_cfg { + int pbl; + int fixed_burst; + int burst_map; + int adv_addr_mode; +}; + +struct sxgbe_plat_data { + char *phy_bus_name; + int bus_id; + int phy_addr; + int interface; + struct sxgbe_mdio_bus_data *mdio_bus_data; + struct sxgbe_dma_cfg *dma_cfg; + int clk_csr; + int pmt; + int force_sf_dma_mode; + int force_thresh_dma_mode; + int riwt_off; +}; + +#endif /* __SXGBE_PLATFORM_H__ */ -- cgit v1.2.3 From d18f141a1a7cfa5ffad8433e43062b05a8d1b82a Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 27 Mar 2014 14:02:03 +0200 Subject: mlx4: Add support for CONFIG_DEV command Introduce the CONFIG_DEV firmware command which we will use to configure the UDP port assumed by the firmware for the VXLAN offloads. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 009985628257..c8450366c130 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -125,6 +125,7 @@ enum { /* miscellaneous commands */ MLX4_CMD_DIAG_RPRT = 0x30, MLX4_CMD_NOP = 0x31, + MLX4_CMD_CONFIG_DEV = 0x3a, MLX4_CMD_ACCESS_MEM = 0x2e, MLX4_CMD_SET_VEP = 0x52, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6b3998396b99..d986c975616f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1232,4 +1232,6 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv( int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port); int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port); + +int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port); #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 1b136de120dda625109f2afe1e3d04e256be9ec1 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 27 Mar 2014 14:02:04 +0200 Subject: net/mlx4: Implement vxlan ndo calls Add implementation for the add/del vxlan port ndo calls, using the CONFIG_DEV firmware command. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d986c975616f..ba87bd21295a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1142,7 +1142,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc); int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, u8 *pg, u16 *ratelimit); -int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering); +int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable); int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); -- cgit v1.2.3 From 015f0688f57ca4d499047d335b8052a733e17a4d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Mar 2014 08:45:56 -0700 Subject: net: net: add a core netdev->tx_dropped counter Dropping packets in __dev_queue_xmit() when transmit queue is stopped (NIC TX ring buffer full or BQL limit reached) currently outputs a syslog message. It would be better to get a precise count of such events available in netdevice stats so that monitoring tools can have a clue. This extends the work done in caf586e5f23ce ("net: add a core netdev->rx_dropped counter") 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 4b6d12c7b803..159c7e7945f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1311,9 +1311,10 @@ struct net_device { int iflink; struct net_device_stats stats; - atomic_long_t rx_dropped; /* dropped packets by core network - * Do not use this in drivers. - */ + + /* dropped packets by core network, Do not use this in drivers */ + atomic_long_t rx_dropped; + atomic_long_t tx_dropped; #ifdef CONFIG_WIRELESS_EXT /* List of functions to handle Wireless Extensions (instead of ioctl). -- cgit v1.2.3 From a8779ec1c5e60548b7b661a8d74a8cecf7775690 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Mar 2014 15:36:38 -0700 Subject: netpoll: Remove gfp parameter from __netpoll_setup The gfp parameter was added in: commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af Author: Amerigo Wang Date: Fri Aug 10 01:24:37 2012 +0000 netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup() slave_enable_netpoll() and __netpoll_setup() may be called with read_lock() held, so should use GFP_ATOMIC to allocate memory. Eric suggested to pass gfp flags to __netpoll_setup(). Cc: Eric Dumazet Cc: "David S. Miller" Reported-by: Dan Carpenter Signed-off-by: Eric Dumazet Signed-off-by: Cong Wang Signed-off-by: David S. Miller The reason for the gfp parameter was removed in: commit c4cdef9b7183159c23c7302aaf270d64c549f557 Author: dingtianhong Date: Tue Jul 23 15:25:27 2013 +0800 bonding: don't call slave_xxx_netpoll under spinlocks The slave_xxx_netpoll will call synchronize_rcu_bh(), so the function may schedule and sleep, it should't be called under spinlocks. bond_netpoll_setup() and bond_netpoll_cleanup() are always protected by rtnl lock, it is no need to take the read lock, as the slave list couldn't be changed outside rtnl lock. Signed-off-by: Ding Tianhong Cc: Jay Vosburgh Cc: Andy Gospodarek Signed-off-by: David S. Miller Nothing else that calls __netpoll_setup or ndo_netpoll_setup requires a gfp paramter, so remove the gfp parameter from both of these functions making the code clearer. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- include/linux/netpoll.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 159c7e7945f8..0d8c8718980a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1037,8 +1037,7 @@ struct net_device_ops { #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info, - gfp_t gfp); + struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 1b475a5a7239..893b9e66060e 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -57,7 +57,7 @@ static inline void netpoll_rx_enable(struct net_device *dev) { return; } 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, struct net_device *ndev, gfp_t gfp); +int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free_async(struct netpoll *np); -- cgit v1.2.3 From 66b5552fc2dfbaa6445b1bdadd10c9305ce261bd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Mar 2014 15:39:03 -0700 Subject: netpoll: Rename netpoll_rx_enable/disable to netpoll_poll_disable/enable The netpoll_rx_enable and netpoll_rx_disable functions have always controlled polling the network drivers transmit and receive queues. Rename them to netpoll_poll_enable and netpoll_poll_disable to make their functionality clear. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netpoll.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 893b9e66060e..b25ee9ffdbe6 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -47,11 +47,11 @@ struct netpoll_info { }; #ifdef CONFIG_NETPOLL -extern void netpoll_rx_disable(struct net_device *dev); -extern void netpoll_rx_enable(struct net_device *dev); +extern void netpoll_poll_disable(struct net_device *dev); +extern void netpoll_poll_enable(struct net_device *dev); #else -static inline void netpoll_rx_disable(struct net_device *dev) { return; } -static inline void netpoll_rx_enable(struct net_device *dev) { return; } +static inline void netpoll_poll_disable(struct net_device *dev) { return; } +static inline void netpoll_poll_enable(struct net_device *dev) { return; } #endif void netpoll_send_udp(struct netpoll *np, const char *msg, int len); -- cgit v1.2.3 From 5efeac44cfca62f66a1b2919fc8ec7f7c726d15b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Mar 2014 15:42:20 -0700 Subject: netpoll: Respect NETIF_F_LLTX Stop taking the transmit lock when a network device has specified NETIF_F_LLTX. If no locks needed to trasnmit a packet this is the ideal scenario for netpoll as all packets can be trasnmitted immediately. Even if some locks are needed in ndo_start_xmit skipping any unnecessary serialization is desirable for netpoll as it makes it more likely a debugging packet may be trasnmitted immediately instead of being deferred until later. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0d8c8718980a..4cd5e9e13c87 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2909,6 +2909,11 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } \ } +#define HARD_TX_TRYLOCK(dev, txq) \ + (((dev->features & NETIF_F_LLTX) == 0) ? \ + __netif_tx_trylock(txq) : \ + true ) + #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ -- cgit v1.2.3 From f8bbbfc3b97f4c7a6c7c23185e520b22bfc3a21d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:18 +0100 Subject: net: filter: add jited flag to indicate jit compiled filters This patch adds a jited flag into sk_filter struct in order to indicate whether a filter is currently jited or not. The size of sk_filter is not being expanded as the 32 bit 'len' member allows upper bits to be reused since a filter can currently only grow as large as BPF_MAXINSNS. Therefore, there's enough room also for other in future needed flags to reuse 'len' field if necessary. The jited flag also allows for having alternative interpreter functions running as currently, we can only detect jit compiled filters by testing fp->bpf_func to not equal the address of sk_run_filter(). Joint work with Alexei Starovoitov. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Cc: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index e568c8ef896b..e65e23087367 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -25,7 +25,8 @@ struct sock; struct sk_filter { atomic_t refcnt; - unsigned int len; /* Number of filter blocks */ + u32 jited:1, /* Is our filter JIT'ed? */ + len:31; /* Number of filter blocks */ struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct sock_filter *filter); -- cgit v1.2.3 From a3ea269b8bcdbb0c5fa2fd449a436e7987446975 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:19 +0100 Subject: net: filter: keep original BPF program around In order to open up the possibility to internally transform a BPF program into an alternative and possibly non-trivial reversible representation, we need to keep the original BPF program around, so that it can be passed back to user space w/o the need of a complex decoder. The reason for that use case resides in commit a8fc92778080 ("sk-filter: Add ability to get socket filter program (v2)"), that is, the ability to retrieve the currently attached BPF filter from a given socket used mainly by the checkpoint-restore project, for example. Therefore, we add two helpers sk_{store,release}_orig_filter for taking care of that. In the sk_unattached_filter_create() case, there's no such possibility/requirement to retrieve a loaded BPF program. Therefore, we can spare us the work in that case. This approach will simplify and slightly speed up both, sk_get_filter() and sock_diag_put_filterinfo() handlers as we won't need to successively decode filters anymore through sk_decode_filter(). As we still need sk_decode_filter() later on, we're keeping it around. Joint work with Alexei Starovoitov. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Cc: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/filter.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index e65e23087367..93a9792e27bc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -19,14 +19,19 @@ struct compat_sock_fprog { }; #endif +struct sock_fprog_kern { + u16 len; + struct sock_filter *filter; +}; + struct sk_buff; struct sock; -struct sk_filter -{ +struct sk_filter { atomic_t refcnt; u32 jited:1, /* Is our filter JIT'ed? */ len:31; /* Number of filter blocks */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct sock_filter *filter); @@ -42,14 +47,20 @@ static inline unsigned int sk_filter_size(unsigned int proglen) offsetof(struct sk_filter, insns[proglen])); } +#define sk_filter_proglen(fprog) \ + (fprog->len * sizeof(fprog->filter[0])) + extern int sk_filter(struct sock *sk, struct sk_buff *skb); extern unsigned int sk_run_filter(const struct sk_buff *skb, const struct sock_filter *filter); + extern int sk_unattached_filter_create(struct sk_filter **pfp, struct sock_fprog *fprog); extern void sk_unattached_filter_destroy(struct sk_filter *fp); + extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); + extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); -- cgit v1.2.3 From fbc907f0b1386c02e00516aa78a0fa6b0454fd0b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:20 +0100 Subject: net: filter: move filter accounting to filter core This patch basically does two things, i) removes the extern keyword from the include/linux/filter.h file to be more consistent with the rest of Joe's changes, and ii) moves filter accounting into the filter core framework. Filter accounting mainly done through sk_filter_{un,}charge() take care of the case when sockets are being cloned through sk_clone_lock() so that removal of the filter on one socket won't result in eviction as it's still referenced by the other. These functions actually belong to net/core/filter.c and not include/net/sock.h as we want to keep all that in a central place. It's also not in fast-path so uninlining them is fine and even allows us to get rd of sk_filter_release_rcu()'s EXPORT_SYMBOL and a forward declaration. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/filter.h | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 93a9792e27bc..9bde3ed19fe6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -50,28 +50,32 @@ static inline unsigned int sk_filter_size(unsigned int proglen) #define sk_filter_proglen(fprog) \ (fprog->len * sizeof(fprog->filter[0])) -extern int sk_filter(struct sock *sk, struct sk_buff *skb); -extern unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *filter); +int sk_filter(struct sock *sk, struct sk_buff *skb); +unsigned int sk_run_filter(const struct sk_buff *skb, + const struct sock_filter *filter); -extern int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog *fprog); -extern void sk_unattached_filter_destroy(struct sk_filter *fp); +int sk_unattached_filter_create(struct sk_filter **pfp, + struct sock_fprog *fprog); +void sk_unattached_filter_destroy(struct sk_filter *fp); -extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); -extern int sk_detach_filter(struct sock *sk); +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int sk_detach_filter(struct sock *sk); -extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); -extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); -extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); +int sk_chk_filter(struct sock_filter *filter, unsigned int flen); +int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, + unsigned int len); +void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to); + +void sk_filter_charge(struct sock *sk, struct sk_filter *fp); +void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); #ifdef CONFIG_BPF_JIT #include #include #include -extern void bpf_jit_compile(struct sk_filter *fp); -extern void bpf_jit_free(struct sk_filter *fp); +void bpf_jit_compile(struct sk_filter *fp); +void bpf_jit_free(struct sk_filter *fp); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) -- cgit v1.2.3 From e62d2df084e2849edffb206559725fa81bb569a8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:21 +0100 Subject: net: ptp: use sk_unattached_filter_create() for BPF This patch migrates an open-coded sk_run_filter() implementation with proper use of the BPF API, that is, sk_unattached_filter_create(). This migration is needed, as we will be internally transforming the filter to a different representation, and therefore needs to be decoupled. It is okay to do so as skb_timestamping_init() is called during initialization of the network stack in core initcall via sock_init(). This would effectively also allow for PTP filters to be jit compiled if bpf_jit_enable is set. For better readability, there are also some newlines introduced, also ptp_classify.h is only in kernel space. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Richard Cochran Cc: Jiri Benc Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 1dc420ba213a..3decfa4d3732 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -27,11 +27,7 @@ #include #include #include -#ifdef __KERNEL__ #include -#else -#include -#endif #define PTP_CLASS_NONE 0x00 /* not a PTP event message */ #define PTP_CLASS_V1 0x01 /* protocol version 1 */ -- cgit v1.2.3 From 164d8c6665213c931645578310256da7b1259331 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:22 +0100 Subject: net: ptp: do not reimplement PTP/BPF classifier There are currently pch_gbe, cpts, and ixp4xx_eth drivers that open-code and reimplement a BPF classifier for the PTP protocol. Since all of them effectively do the very same thing and load the very same PTP/BPF filter, we can just consolidate that code by introducing ptp_classify_raw() in the time-stamping core framework which can be used in drivers. As drivers get initialized after bootstrapping the core networking subsystem, they can make use of ptp_insns wrapped through ptp_classify_raw(), which allows to simplify and remove PTP classifier setup code in drivers. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Richard Cochran Cc: Jiri Benc Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 3decfa4d3732..6d3b0a2ef9ce 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -80,14 +80,6 @@ #define OP_RETA (BPF_RET | BPF_A) #define OP_RETK (BPF_RET | BPF_K) -static inline int ptp_filter_init(struct sock_filter *f, int len) -{ - if (OP_LDH == f[0].code) - return sk_chk_filter(f, len); - else - return 0; -} - #define PTP_FILTER \ {OP_LDH, 0, 0, OFF_ETYPE }, /* */ \ {OP_JEQ, 0, 12, ETH_P_IP }, /* f goto L20 */ \ @@ -133,4 +125,6 @@ static inline int ptp_filter_init(struct sock_filter *f, int len) {OP_RETA, 0, 0, 0 }, /* */ \ /*L6x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, +unsigned int ptp_classify_raw(const struct sk_buff *skb); + #endif -- cgit v1.2.3 From 77e0114ae9ae08685c503772a57af21d299c6701 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 Mar 2014 18:58:24 +0100 Subject: net: isdn: use sk_unattached_filter api Similarly as in ppp, we need to migrate the ISDN/PPP code to make use of the sk_unattached_filter api in order to decouple having direct filter structure access. By using sk_unattached_filter_{create,destroy}, we can allow for the possibility to jit compile filters for faster filter verdicts as well. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Karsten Keil Cc: isdn4linux@listserv.isdn4linux.de Signed-off-by: David S. Miller --- include/linux/isdn_ppp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/isdn_ppp.h b/include/linux/isdn_ppp.h index d5f62bc5f4be..8e10f57f109f 100644 --- a/include/linux/isdn_ppp.h +++ b/include/linux/isdn_ppp.h @@ -180,9 +180,8 @@ struct ippp_struct { struct slcompress *slcomp; #endif #ifdef CONFIG_IPPP_FILTER - struct sock_filter *pass_filter; /* filter for packets to pass */ - struct sock_filter *active_filter; /* filter for pkts to reset idle */ - unsigned pass_len, active_len; + struct sk_filter *pass_filter; /* filter for packets to pass */ + struct sk_filter *active_filter; /* filter for pkts to reset idle */ #endif unsigned long debug; struct isdn_ppp_compressor *compressor,*decompressor; -- cgit v1.2.3 From bd4cf0ed331a275e9bf5a49e6d0fd55dffc551b8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 28 Mar 2014 18:58:25 +0100 Subject: net: filter: rework/optimize internal BPF interpreter's instruction set This patch replaces/reworks the kernel-internal BPF interpreter with an optimized BPF instruction set format that is modelled closer to mimic native instruction sets and is designed to be JITed with one to one mapping. Thus, the new interpreter is noticeably faster than the current implementation of sk_run_filter(); mainly for two reasons: 1. Fall-through jumps: BPF jump instructions are forced to go either 'true' or 'false' branch which causes branch-miss penalty. The new BPF jump instructions have only one branch and fall-through otherwise, which fits the CPU branch predictor logic better. `perf stat` shows drastic difference for branch-misses between the old and new code. 2. Jump-threaded implementation of interpreter vs switch statement: Instead of single table-jump at the top of 'switch' statement, gcc will now generate multiple table-jump instructions, which helps CPU branch predictor logic. Note that the verification of filters is still being done through sk_chk_filter() in classical BPF format, so filters from user- or kernel space are verified in the same way as we do now, and same restrictions/constraints hold as well. We reuse current BPF JIT compilers in a way that this upgrade would even be fine as is, but nevertheless allows for a successive upgrade of BPF JIT compilers to the new format. The internal instruction set migration is being done after the probing for JIT compilation, so in case JIT compilers are able to create a native opcode image, we're going to use that, and in all other cases we're doing a follow-up migration of the BPF program's instruction set, so that it can be transparently run in the new interpreter. In short, the *internal* format extends BPF in the following way (more details can be taken from the appended documentation): - Number of registers increase from 2 to 10 - Register width increases from 32-bit to 64-bit - Conditional jt/jf targets replaced with jt/fall-through - Adds signed > and >= insns - 16 4-byte stack slots for register spill-fill replaced with up to 512 bytes of multi-use stack space - Introduction of bpf_call insn and register passing convention for zero overhead calls from/to other kernel functions - Adds arithmetic right shift and endianness conversion insns - Adds atomic_add insn - Old tax/txa insns are replaced with 'mov dst,src' insn Performance of two BPF filters generated by libpcap resp. bpf_asm was measured on x86_64, i386 and arm32 (other libpcap programs have similar performance differences): fprog #1 is taken from Documentation/networking/filter.txt: tcpdump -i eth0 port 22 -dd fprog #2 is taken from 'man tcpdump': tcpdump -i eth0 'tcp port 22 and (((ip[2:2] - ((ip[0]&0xf)<<2)) - ((tcp[12]&0xf0)>>2)) != 0)' -dd Raw performance data from BPF micro-benchmark: SK_RUN_FILTER on the same SKB (cache-hit) or 10k SKBs (cache-miss); time in ns per call, smaller is better: --x86_64-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 90 101 192 202 new BPF 31 71 47 97 old BPF jit 12 34 17 44 new BPF jit TBD --i386-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 107 136 227 252 new BPF 40 119 69 172 --arm32-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 202 300 475 540 new BPF 180 270 330 470 old BPF jit 26 182 37 202 new BPF jit TBD Thus, without changing any userland BPF filters, applications on top of AF_PACKET (or other families) such as libpcap/tcpdump, cls_bpf classifier, netfilter's xt_bpf, team driver's load-balancing mode, and many more will have better interpreter filtering performance. While we are replacing the internal BPF interpreter, we also need to convert seccomp BPF in the same step to make use of the new internal structure since it makes use of lower-level API details without being further decoupled through higher-level calls like sk_unattached_filter_{create,destroy}(), for example. Just as for normal socket filtering, also seccomp BPF experiences a time-to-verdict speedup: 05-sim-long_jumps.c of libseccomp was used as micro-benchmark: seccomp_rule_add_exact(ctx,... seccomp_rule_add_exact(ctx,... rc = seccomp_load(ctx); for (i = 0; i < 10000000; i++) syscall(199, 100); 'short filter' has 2 rules 'large filter' has 200 rules 'short filter' performance is slightly better on x86_64/i386/arm32 'large filter' is much faster on x86_64 and i386 and shows no difference on arm32 --x86_64-- short filter old BPF: 2.7 sec 39.12% bench libc-2.15.so [.] syscall 8.10% bench [kernel.kallsyms] [k] sk_run_filter 6.31% bench [kernel.kallsyms] [k] system_call 5.59% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller 4.37% bench [kernel.kallsyms] [k] trace_hardirqs_off_caller 3.70% bench [kernel.kallsyms] [k] __secure_computing 3.67% bench [kernel.kallsyms] [k] lock_is_held 3.03% bench [kernel.kallsyms] [k] seccomp_bpf_load new BPF: 2.58 sec 42.05% bench libc-2.15.so [.] syscall 6.91% bench [kernel.kallsyms] [k] system_call 6.25% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller 6.07% bench [kernel.kallsyms] [k] __secure_computing 5.08% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp --arm32-- short filter old BPF: 4.0 sec 39.92% bench [kernel.kallsyms] [k] vector_swi 16.60% bench [kernel.kallsyms] [k] sk_run_filter 14.66% bench libc-2.17.so [.] syscall 5.42% bench [kernel.kallsyms] [k] seccomp_bpf_load 5.10% bench [kernel.kallsyms] [k] __secure_computing new BPF: 3.7 sec 35.93% bench [kernel.kallsyms] [k] vector_swi 21.89% bench libc-2.17.so [.] syscall 13.45% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 6.25% bench [kernel.kallsyms] [k] __secure_computing 3.96% bench [kernel.kallsyms] [k] syscall_trace_exit --x86_64-- large filter old BPF: 8.6 seconds 73.38% bench [kernel.kallsyms] [k] sk_run_filter 10.70% bench libc-2.15.so [.] syscall 5.09% bench [kernel.kallsyms] [k] seccomp_bpf_load 1.97% bench [kernel.kallsyms] [k] system_call new BPF: 5.7 seconds 66.20% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 16.75% bench libc-2.15.so [.] syscall 3.31% bench [kernel.kallsyms] [k] system_call 2.88% bench [kernel.kallsyms] [k] __secure_computing --i386-- large filter old BPF: 5.4 sec new BPF: 3.8 sec --arm32-- large filter old BPF: 13.5 sec 73.88% bench [kernel.kallsyms] [k] sk_run_filter 10.29% bench [kernel.kallsyms] [k] vector_swi 6.46% bench libc-2.17.so [.] syscall 2.94% bench [kernel.kallsyms] [k] seccomp_bpf_load 1.19% bench [kernel.kallsyms] [k] __secure_computing 0.87% bench [kernel.kallsyms] [k] sys_getuid new BPF: 13.5 sec 76.08% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 10.98% bench [kernel.kallsyms] [k] vector_swi 5.87% bench libc-2.17.so [.] syscall 1.77% bench [kernel.kallsyms] [k] __secure_computing 0.93% bench [kernel.kallsyms] [k] sys_getuid BPF filters generated by seccomp are very branchy, so the new internal BPF performance is better than the old one. Performance gains will be even higher when BPF JIT is committed for the new structure, which is planned in future work (as successive JIT migrations). BPF has also been stress-tested with trinity's BPF fuzzer. Joint work with Daniel Borkmann. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Cc: Hagen Paul Pfeifer Cc: Kees Cook Cc: Paul Moore Cc: Ingo Molnar Cc: H. Peter Anvin Cc: linux-kernel@vger.kernel.org Acked-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/filter.h | 74 ++++++++++++++++++++++++++++++++++++++++++------- include/linux/seccomp.h | 1 - 2 files changed, 64 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9bde3ed19fe6..262dcbb75ffe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -9,13 +9,58 @@ #include #include -#ifdef CONFIG_COMPAT -/* - * A struct sock_filter is architecture independent. +/* Internally used and optimized filter representation with extended + * instruction set based on top of classic BPF. */ + +/* instruction classes */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG 11 + +/* BPF program can access up to 512 bytes of stack space. */ +#define MAX_BPF_STACK 512 + +/* Arg1, context and stack frame pointer register positions. */ +#define ARG1_REG 1 +#define CTX_REG 6 +#define FP_REG 10 + +struct sock_filter_int { + __u8 code; /* opcode */ + __u8 a_reg:4; /* dest register */ + __u8 x_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +#ifdef CONFIG_COMPAT +/* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; - compat_uptr_t filter; /* struct sock_filter * */ + compat_uptr_t filter; /* struct sock_filter * */ }; #endif @@ -26,6 +71,7 @@ struct sock_fprog_kern { struct sk_buff; struct sock; +struct seccomp_data; struct sk_filter { atomic_t refcnt; @@ -34,9 +80,10 @@ struct sk_filter { struct sock_fprog_kern *orig_prog; /* Original BPF program */ struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, - const struct sock_filter *filter); + const struct sock_filter_int *filter); union { - struct sock_filter insns[0]; + struct sock_filter insns[0]; + struct sock_filter_int insnsi[0]; struct work_struct work; }; }; @@ -50,9 +97,18 @@ static inline unsigned int sk_filter_size(unsigned int proglen) #define sk_filter_proglen(fprog) \ (fprog->len * sizeof(fprog->filter[0])) +#define SK_RUN_FILTER(filter, ctx) \ + (*filter->bpf_func)(ctx, filter->insnsi) + int sk_filter(struct sock *sk, struct sk_buff *skb); -unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *filter); + +u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, + const struct sock_filter_int *insni); +u32 sk_run_filter_int_skb(const struct sk_buff *ctx, + const struct sock_filter_int *insni); + +int sk_convert_filter(struct sock_filter *prog, int len, + struct sock_filter_int *new_prog, int *new_len); int sk_unattached_filter_create(struct sk_filter **pfp, struct sock_fprog *fprog); @@ -86,7 +142,6 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } -#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else #include static inline void bpf_jit_compile(struct sk_filter *fp) @@ -96,7 +151,6 @@ static inline void bpf_jit_free(struct sk_filter *fp) { kfree(fp); } -#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns) #endif static inline int bpf_tell_extensions(void) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 6f19cfd1840e..4054b0994071 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -76,7 +76,6 @@ static inline int seccomp_mode(struct seccomp *s) #ifdef CONFIG_SECCOMP_FILTER extern void put_seccomp_filter(struct task_struct *tsk); extern void get_seccomp_filter(struct task_struct *tsk); -extern u32 seccomp_bpf_load(int off); #else /* CONFIG_SECCOMP_FILTER */ static inline void put_seccomp_filter(struct task_struct *tsk) { -- cgit v1.2.3 From 1ee481fb4cf8044632fa869bafc41345afa5957b Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Thu, 27 Mar 2014 17:32:29 -0400 Subject: net: Allow modules to use is_skb_forwardable Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 06287c110241..29b579fb5196 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2629,6 +2629,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb); extern int netdev_budget; -- cgit v1.2.3 From 339e022396d58f4b4f9b4200ea5309768934bb33 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 28 Mar 2014 14:25:58 -0700 Subject: net: export NET_ADDR_* values to user-space API NET_ADDR_* values are exported in the /sys/class/net//addr_assign_type sysfs attributes, and as such constitutes an user-space ABI. Move the NET_ADDR_* definitions from include/linux/netdevice.h to include/uapi/linux/netdevice.h Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 29b579fb5196..34cae3ee74f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -63,13 +63,6 @@ struct wireless_dev; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); -/* hardware address assignment types */ -#define NET_ADDR_PERM 0 /* address is permanent (default) */ -#define NET_ADDR_RANDOM 1 /* address is generated randomly */ -#define NET_ADDR_STOLEN 2 /* address is stolen from other device */ -#define NET_ADDR_SET 3 /* address is set using - * dev_set_mac_address() */ - /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ -- cgit v1.2.3 From 2d3b479df41a10e2f41f9259fcba775bd34de6e4 Mon Sep 17 00:00:00 2001 From: david decotigny Date: Sat, 29 Mar 2014 09:48:35 -0700 Subject: net-sysfs: expose number of carrier on/off changes This allows to monitor carrier on/off transitions and detect link flapping issues: - new /sys/class/net/X/carrier_changes - new rtnetlink IFLA_CARRIER_CHANGES (getlink) Tested: - grep . /sys/class/net/*/carrier_changes + ip link set dev X down/up + plug/unplug cable - updated iproute2: prints IFLA_CARRIER_CHANGES - iproute2 20121211-2 (debian): unchanged behavior Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 34cae3ee74f1..45537ed7a5b3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1308,6 +1308,9 @@ struct net_device { atomic_long_t rx_dropped; atomic_long_t tx_dropped; + /* Stats to monitor carrier on<->off transitions */ + atomic_t carrier_changes; + #ifdef CONFIG_WIRELESS_EXT /* List of functions to handle Wireless Extensions (instead of ioctl). * See for details. Jean II */ -- cgit v1.2.3 From a50e233c50dbc881abaa0e4070789064e8d12d70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Mar 2014 21:28:21 -0700 Subject: net-gro: restore frag0 optimization Main difference between napi_frags_skb() and napi_gro_receive() is that the later is called while ethernet header was already pulled by the NIC driver (eth_type_trans() was called before napi_gro_receive()) Jerry Chu in commit 299603e8370a ("net-gro: Prepare GRO stack for the upcoming tunneling support") tried to remove this difference by calling eth_type_trans() from napi_frags_skb() instead of doing this later from napi_frags_finish() Goal was that napi_gro_complete() could call ptype->callbacks.gro_complete(skb, 0) (offset of first network header = 0) Also, xxx_gro_receive() handlers all use off = skb_gro_offset(skb) to point to their own header, for the current skb and ones held in gro_list Problem is this cleanup work defeated the frag0 optimization: It turns out the consecutive pskb_may_pull() calls are too expensive. This patch brings back the frag0 stuff in napi_frags_skb(). As all skb have their mac header in skb head, we no longer need skb_gro_mac_header() Reported-by: Michal Schmidt Fixes: 299603e8370a ("net-gro: Prepare GRO stack for the upcoming tunneling support") Signed-off-by: Eric Dumazet Cc: Jerry Chu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 45537ed7a5b3..775cc956ff78 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2014,11 +2014,6 @@ static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, return skb->data + offset; } -static inline void *skb_gro_mac_header(struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb); -} - static inline void *skb_gro_network_header(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + -- cgit v1.2.3 From e462ded699aa2cca04b68fbf203ea4675d4c44d4 Mon Sep 17 00:00:00 2001 From: Phoebe Buckheister Date: Mon, 31 Mar 2014 21:37:46 +0200 Subject: mac802154: make csma/cca parameters per-wpan Commit 9b2777d6089bcd (ieee802154: add TX power control to wpan_phy) and following erroneously added CSMA and CCA parameters for 802.15.4 devices as PHY parameters, while they are actually MAC parameters and can differ for any two WPAN instances. Since it is now sensible to have multiple WPAN devices with differing CSMA/CCA parameters, make these parameters MAC parameters instead. Signed-off-by: Phoebe Buckheister Signed-off-by: David S. Miller --- include/linux/nl802154.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index e110b8c266f5..c8d7f3965fff 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -132,7 +132,7 @@ enum { IEEE802154_ADD_IFACE, IEEE802154_DEL_IFACE, - IEEE802154_SET_PHYPARAMS, + IEEE802154_SET_MACPARAMS, __IEEE802154_CMD_MAX, }; -- cgit v1.2.3 From 408eccce32044ee3285a7f6a812723ba3540c3e7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 1 Apr 2014 16:20:23 +0200 Subject: net: ptp: move PTP classifier in its own file This commit fixes a build error reported by Fengguang, that is triggered when CONFIG_NETWORK_PHY_TIMESTAMPING is not set: ERROR: "ptp_classify_raw" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined! The fix is to introduce its own file for the PTP BPF classifier, so that PTP_1588_CLOCK and/or NETWORK_PHY_TIMESTAMPING can select it independently from each other. IXP4xx driver on ARM needs to select it as well since it does not seem to select PTP_1588_CLOCK or similar that would pull it in automatically. This also allows for hiding all of the internals of the BPF PTP program inside that file, and only exporting relevant API bits to drivers. This patch also adds a kdoc documentation of ptp_classify_raw() API to make it clear that it can return PTP_CLASS_* defines. Also, the BPF program has been translated into bpf_asm code, so that it can be more easily read and altered (extensively documented in [1]). In the kernel tree under tools/net/ we have bpf_asm and bpf_dbg tools, so the commented program can simply be translated via `./bpf_asm -c prog` where prog is a file that contains the commented code. This makes it easily readable/verifiable and when there's a need to change something, jump offsets etc do not need to be replaced manually which can be very error prone. Instead, a newly translated version via bpf_asm can simply replace the old code. I have checked opcode diffs before/after and it's the very same filter. [1] Documentation/networking/filter.txt Fixes: 164d8c666521 ("net: ptp: do not reimplement PTP/BPF classifier") Reported-by: Fengguang Wu Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Richard Cochran Cc: Jiri Benc Acked-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 95 ++++++++++---------------------------------- include/linux/skbuff.h | 2 - 2 files changed, 22 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 6d3b0a2ef9ce..7dfed71d76a6 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -23,11 +23,8 @@ #ifndef _PTP_CLASSIFY_H_ #define _PTP_CLASSIFY_H_ -#include -#include #include -#include -#include +#include #define PTP_CLASS_NONE 0x00 /* not a PTP event message */ #define PTP_CLASS_V1 0x01 /* protocol version 1 */ @@ -40,7 +37,7 @@ #define PTP_CLASS_PMASK 0xf0 /* mask for the packet type field */ #define PTP_CLASS_V1_IPV4 (PTP_CLASS_V1 | PTP_CLASS_IPV4) -#define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /*probably DNE*/ +#define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /* probably DNE */ #define PTP_CLASS_V2_IPV4 (PTP_CLASS_V2 | PTP_CLASS_IPV4) #define PTP_CLASS_V2_IPV6 (PTP_CLASS_V2 | PTP_CLASS_IPV6) #define PTP_CLASS_V2_L2 (PTP_CLASS_V2 | PTP_CLASS_L2) @@ -49,82 +46,34 @@ #define PTP_EV_PORT 319 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ -#define OFF_ETYPE 12 -#define OFF_IHL 14 -#define OFF_FRAG 20 -#define OFF_PROTO4 23 -#define OFF_NEXT 6 -#define OFF_UDP_DST 2 - #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 #define OFF_PTP_CONTROL 32 /* PTPv1 only */ -#define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) - +/* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 #define UDP_HLEN 8 - -#define RELOFF_DST4 (ETH_HLEN + OFF_UDP_DST) -#define OFF_DST6 (ETH_HLEN + IP6_HLEN + OFF_UDP_DST) +#define OFF_IHL 14 #define OFF_PTP6 (ETH_HLEN + IP6_HLEN + UDP_HLEN) +#define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) -#define OP_AND (BPF_ALU | BPF_AND | BPF_K) -#define OP_JEQ (BPF_JMP | BPF_JEQ | BPF_K) -#define OP_JSET (BPF_JMP | BPF_JSET | BPF_K) -#define OP_LDB (BPF_LD | BPF_B | BPF_ABS) -#define OP_LDH (BPF_LD | BPF_H | BPF_ABS) -#define OP_LDHI (BPF_LD | BPF_H | BPF_IND) -#define OP_LDX (BPF_LDX | BPF_B | BPF_MSH) -#define OP_OR (BPF_ALU | BPF_OR | BPF_K) -#define OP_RETA (BPF_RET | BPF_A) -#define OP_RETK (BPF_RET | BPF_K) - -#define PTP_FILTER \ - {OP_LDH, 0, 0, OFF_ETYPE }, /* */ \ - {OP_JEQ, 0, 12, ETH_P_IP }, /* f goto L20 */ \ - {OP_LDB, 0, 0, OFF_PROTO4 }, /* */ \ - {OP_JEQ, 0, 9, IPPROTO_UDP }, /* f goto L10 */ \ - {OP_LDH, 0, 0, OFF_FRAG }, /* */ \ - {OP_JSET, 7, 0, 0x1fff }, /* t goto L11 */ \ - {OP_LDX, 0, 0, OFF_IHL }, /* */ \ - {OP_LDHI, 0, 0, RELOFF_DST4 }, /* */ \ - {OP_JEQ, 0, 4, PTP_EV_PORT }, /* f goto L12 */ \ - {OP_LDHI, 0, 0, ETH_HLEN + UDP_HLEN }, /* */ \ - {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ - {OP_OR, 0, 0, PTP_CLASS_IPV4 }, /* */ \ - {OP_RETA, 0, 0, 0 }, /* */ \ -/*L1x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, /* */ \ -/*L20*/ {OP_JEQ, 0, 9, ETH_P_IPV6 }, /* f goto L40 */ \ - {OP_LDB, 0, 0, ETH_HLEN + OFF_NEXT }, /* */ \ - {OP_JEQ, 0, 6, IPPROTO_UDP }, /* f goto L30 */ \ - {OP_LDH, 0, 0, OFF_DST6 }, /* */ \ - {OP_JEQ, 0, 4, PTP_EV_PORT }, /* f goto L31 */ \ - {OP_LDH, 0, 0, OFF_PTP6 }, /* */ \ - {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ - {OP_OR, 0, 0, PTP_CLASS_IPV6 }, /* */ \ - {OP_RETA, 0, 0, 0 }, /* */ \ -/*L3x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, /* */ \ -/*L40*/ {OP_JEQ, 0, 9, ETH_P_8021Q }, /* f goto L50 */ \ - {OP_LDH, 0, 0, OFF_ETYPE + 4 }, /* */ \ - {OP_JEQ, 0, 15, ETH_P_1588 }, /* f goto L60 */ \ - {OP_LDB, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ - {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ - {OP_JEQ, 0, 12, 0 }, /* f goto L6x */ \ - {OP_LDH, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ - {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ - {OP_OR, 0, 0, PTP_CLASS_VLAN }, /* */ \ - {OP_RETA, 0, 0, 0 }, /* */ \ -/*L50*/ {OP_JEQ, 0, 7, ETH_P_1588 }, /* f goto L61 */ \ - {OP_LDB, 0, 0, ETH_HLEN }, /* */ \ - {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ - {OP_JEQ, 0, 4, 0 }, /* f goto L6x */ \ - {OP_LDH, 0, 0, ETH_HLEN }, /* */ \ - {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ - {OP_OR, 0, 0, PTP_CLASS_L2 }, /* */ \ - {OP_RETA, 0, 0, 0 }, /* */ \ -/*L6x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, - +#if defined(CONFIG_NET_PTP_CLASSIFY) +/** + * ptp_classify_raw - classify a PTP packet + * @skb: buffer + * + * Runs a minimal BPF dissector to classify a network packet to + * determine the PTP class. In case the skb does not contain any + * PTP protocol data, PTP_CLASS_NONE will be returned, otherwise + * PTP_CLASS_V1_IPV{4,6}, PTP_CLASS_V2_IPV{4,6} or + * PTP_CLASS_V2_{L2,VLAN}, depending on the packet content. + */ unsigned int ptp_classify_raw(const struct sk_buff *skb); +void __init ptp_classifier_init(void); +#else +static inline void ptp_classifier_init(void) +{ +} #endif +#endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 18ef0224fb6a..31edf63937a1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2630,8 +2630,6 @@ static inline ktime_t net_invalid_timestamp(void) return ktime_set(0, 0); } -void skb_timestamping_init(void); - #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); -- cgit v1.2.3 From 574f7194f693cd80de96a39f0c43dbb346c38a15 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 1 Apr 2014 12:20:24 -0700 Subject: net: Add a test to see if a skb is freeable in irq context Currently netpoll and skb_release_head_state assume that a skb is freeable in hard irq context except when skb->destructor is set. The reality is far from this. So add a function skb_irq_freeable to compute the full test and in the process be the living documentation of what the requirements are of actually freeing a skb in hard irq context. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 31edf63937a1..350eebe770d9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2831,6 +2831,19 @@ static inline void skb_init_secmark(struct sk_buff *skb) { } #endif +static inline bool skb_irq_freeable(const struct sk_buff *skb) +{ + return !skb->destructor && +#if IS_ENABLED(CONFIG_XFRM) + !skb->sp && +#endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + !skb->nfct && +#endif + !skb->_skb_refdst && + !skb_has_frag_list(skb); +} + static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; -- cgit v1.2.3