From cd67cd5eb25ae9a7bafbfd3d52d4c05e1d80af3b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 6 Feb 2015 09:44:44 +0200 Subject: ipvs: use 64-bit rates in stats IPVS stats are limited to 2^(32-10) conns/s and packets/s, 2^(32-5) bytes/s. It is time to use 64 bits: * Change all conn/packet kernel counters to 64-bit and update them in u64_stats_update_{begin,end} section * In kernel use struct ip_vs_kstats instead of the user-space struct ip_vs_stats_user and use new func ip_vs_export_stats_user to export it to sockopt users to preserve compatibility with 32-bit values * Rename cpu counters "ustats" to "cnt" * To netlink users provide additionally 64-bit stats: IPVS_SVC_ATTR_STATS64 and IPVS_DEST_ATTR_STATS64. Old stats remain for old binaries. * We can use ip_vs_copy_stats in ip_vs_stats_percpu_show Thanks to Chris Caputo for providing initial patch for ip_vs_est.c Signed-off-by: Chris Caputo Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 50 ++++++++++++++++++++++++++++++---------------- include/uapi/linux/ip_vs.h | 7 ++++++- 2 files changed, 39 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 615b20b58545..a627fe690c19 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -365,15 +365,15 @@ struct ip_vs_seq { /* counters per cpu */ struct ip_vs_counters { - __u32 conns; /* connections scheduled */ - __u32 inpkts; /* incoming packets */ - __u32 outpkts; /* outgoing packets */ + __u64 conns; /* connections scheduled */ + __u64 inpkts; /* incoming packets */ + __u64 outpkts; /* outgoing packets */ __u64 inbytes; /* incoming bytes */ __u64 outbytes; /* outgoing bytes */ }; /* Stats per cpu */ struct ip_vs_cpu_stats { - struct ip_vs_counters ustats; + struct ip_vs_counters cnt; struct u64_stats_sync syncp; }; @@ -383,23 +383,40 @@ struct ip_vs_estimator { u64 last_inbytes; u64 last_outbytes; - u32 last_conns; - u32 last_inpkts; - u32 last_outpkts; - - u32 cps; - u32 inpps; - u32 outpps; - u32 inbps; - u32 outbps; + u64 last_conns; + u64 last_inpkts; + u64 last_outpkts; + + u64 cps; + u64 inpps; + u64 outpps; + u64 inbps; + u64 outbps; +}; + +/* + * IPVS statistics object, 64-bit kernel version of struct ip_vs_stats_user + */ +struct ip_vs_kstats { + u64 conns; /* connections scheduled */ + u64 inpkts; /* incoming packets */ + u64 outpkts; /* outgoing packets */ + u64 inbytes; /* incoming bytes */ + u64 outbytes; /* outgoing bytes */ + + u64 cps; /* current connection rate */ + u64 inpps; /* current in packet rate */ + u64 outpps; /* current out packet rate */ + u64 inbps; /* current in byte rate */ + u64 outbps; /* current out byte rate */ }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_kstats kstats; /* kernel statistics */ struct ip_vs_estimator est; /* estimator */ struct ip_vs_cpu_stats __percpu *cpustats; /* per cpu counters */ spinlock_t lock; /* spin lock */ - struct ip_vs_stats_user ustats0; /* reset values */ + struct ip_vs_kstats kstats0; /* reset values */ }; struct dst_entry; @@ -1388,8 +1405,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); -void ip_vs_read_estimator(struct ip_vs_stats_user *dst, - struct ip_vs_stats *stats); +void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); /* Various IPVS packet transmitters (from ip_vs_xmit.c) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index cabe95d5b461..3199243f2028 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -358,6 +358,8 @@ enum { IPVS_SVC_ATTR_PE_NAME, /* name of ct retriever */ + IPVS_SVC_ATTR_STATS64, /* nested attribute for service stats */ + __IPVS_SVC_ATTR_MAX, }; @@ -387,6 +389,8 @@ enum { IPVS_DEST_ATTR_ADDR_FAMILY, /* Address family of address */ + IPVS_DEST_ATTR_STATS64, /* nested attribute for dest stats */ + __IPVS_DEST_ATTR_MAX, }; @@ -410,7 +414,8 @@ enum { /* * Attributes used to describe service or destination entry statistics * - * Used inside nested attributes IPVS_SVC_ATTR_STATS and IPVS_DEST_ATTR_STATS + * Used inside nested attributes IPVS_SVC_ATTR_STATS, IPVS_DEST_ATTR_STATS, + * IPVS_SVC_ATTR_STATS64 and IPVS_DEST_ATTR_STATS64. */ enum { IPVS_STATS_ATTR_UNSPEC = 0, -- cgit v1.2.3 From 306f7aa1807be7588f115d7cafa475f65e72e3d1 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Feb 2015 14:39:15 +0100 Subject: ieee802154: correct ieee802154_is_valid_psdu_len This patch corrects the ieee802154_is_valid_psdu_len function that this function also checks on reserved values 6-8 for validation the psdu length. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 6e82d888287c..40b0ab953937 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -28,7 +28,8 @@ #include #define IEEE802154_MTU 127 -#define IEEE802154_MIN_PSDU_LEN 5 +#define IEEE802154_ACK_PSDU_LEN 5 +#define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff @@ -204,11 +205,18 @@ enum { /** * ieee802154_is_valid_psdu_len - check if psdu len is valid + * available lengths: + * 0-4 Reserved + * 5 MPDU (Acknowledgment) + * 6-8 Reserved + * 9-127 MPDU + * * @len: psdu len with (MHR + payload + MFR) */ static inline bool ieee802154_is_valid_psdu_len(const u8 len) { - return (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU); + return (len == IEEE802154_ACK_PSDU_LEN || + (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU)); } /** -- cgit v1.2.3 From ba5bf17e8343c0b5b87a1240aa75c35c76b88e5e Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Feb 2015 14:39:16 +0100 Subject: ieee802154: cleanup ieee802154_be64_to_le64 This patch cleanups the ieee802154_be64_to_le64 function. This patch removes an unnecessary temporary variable. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 850647811749..c5c64455bcfa 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -233,9 +234,7 @@ struct ieee802154_ops { */ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) { - __le64 tmp = (__force __le64)swab64p(be64_src); - - memcpy(le64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN); + __put_unaligned_memmove64(swab64p(be64_src), le64_dst); } /** -- cgit v1.2.3 From b976796950c7a41fe1b6b51236ddd08dd6480b80 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Feb 2015 14:39:17 +0100 Subject: ieee802154: cleanup ieee802154_le64_to_be64 This patch cleanups the ieee802154_le64_to_be64 function. This patch removes an unnecessary temporary variable. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index c5c64455bcfa..fb4e8a3d6229 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -244,9 +244,7 @@ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) */ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) { - __be64 tmp = (__force __be64)swab64p(le64_src); - - memcpy(be64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN); + __put_unaligned_memmove64(swab64p(le64_src), be64_dst); } /* Basic interface to register ieee802154 hwice */ -- cgit v1.2.3 From a44fecbd52a4d9c36f07eb2161c153047d8765d4 Mon Sep 17 00:00:00 2001 From: Tedd Ho-Jeong An Date: Fri, 13 Feb 2015 09:20:50 -0800 Subject: Bluetooth: Add shutdown callback before closing the device This callback allows a vendor to send the vendor specific commands before cloing the hci interface. Signed-off-by: Tedd Ho-Jeong An Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 52863c3e0b13..5f1ca3359c1a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -373,6 +373,7 @@ struct hci_dev { int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); int (*setup)(struct hci_dev *hdev); + int (*shutdown)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); -- cgit v1.2.3 From fba7ecf09bc458b15f9d578e4213c8c349f9592d Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 18 Feb 2015 14:53:55 +0200 Subject: Bluetooth: Convert hci_cb_list_lock to a mutex We'll soon need to be able to sleep inside the loops that iterate the hci_cb list, so neither a spinlock, rwlock or rcu are usable. This patch changes the lock to a mutex which permits sleeping while holding the lock. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5f1ca3359c1a..137a18226975 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -499,7 +499,7 @@ struct hci_conn_params { extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; -extern rwlock_t hci_cb_list_lock; +extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); @@ -1160,12 +1160,12 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, @@ -1181,24 +1181,24 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, hci_proto_encrypt_cfm(conn, status, encrypt); - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, @@ -1206,12 +1206,12 @@ static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, { struct hci_cb *cb; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline bool eir_has_data_type(u8 *data, size_t data_len, u8 type) -- cgit v1.2.3 From 354fe804edb29625eee6dd7b1f3c72b43392704d Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 18 Feb 2015 14:53:56 +0200 Subject: Bluetooth: Convert L2CAP security callback to use hci_cb There's no reason to have the custom hci_proto_auth/encrypt_cfm helpers when the hci_cb list works equally well. This patch adds L2CAP to the hci_cb list and makes l2cap_security_cfm a private function of l2cap_core.c. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 40 ++++++---------------------------------- 1 file changed, 6 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 137a18226975..4a2db5e62699 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -506,7 +506,6 @@ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); void l2cap_connect_cfm(struct hci_conn *hcon, u8 status); int l2cap_disconn_ind(struct hci_conn *hcon); void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason); -int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt); int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); @@ -1107,35 +1106,6 @@ static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason) conn->disconn_cfm_cb(conn, reason); } -static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status) -{ - __u8 encrypt; - - if (conn->type != ACL_LINK && conn->type != LE_LINK) - return; - - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) - return; - - encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; - l2cap_security_cfm(conn, status, encrypt); - - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); -} - -static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, - __u8 encrypt) -{ - if (conn->type != ACL_LINK && conn->type != LE_LINK) - return; - - l2cap_security_cfm(conn, status, encrypt); - - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); -} - /* ----- HCI callbacks ----- */ struct hci_cb { struct list_head list; @@ -1153,8 +1123,6 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) struct hci_cb *cb; __u8 encrypt; - hci_proto_auth_cfm(conn, status); - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return; @@ -1166,6 +1134,9 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, @@ -1179,14 +1150,15 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, if (conn->pending_sec_level > conn->sec_level) conn->sec_level = conn->pending_sec_level; - hci_proto_encrypt_cfm(conn, status, encrypt); - mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) -- cgit v1.2.3 From 539c496d88f7f96d42abde4e9d901c8f8167d615 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 18 Feb 2015 14:53:57 +0200 Subject: Bluetooth: Convert connect_cfm to be triggered through hci_cb This patch moves all the connect_cfm callbacks to be based on the hci_cb list. This means making l2cap_connect_cfm private to l2cap_core.c and sco_connect_cb private to sco.c respectively. Since the hci_conn type filtering isn't done any more on the wrapper level the callbacks themselves need to check that they were passed a relevant type of connection. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 40 ++++++++++++++++------------------------ 1 file changed, 16 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4a2db5e62699..0f00f0e9f257 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -503,13 +503,11 @@ extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); -void l2cap_connect_cfm(struct hci_conn *hcon, u8 status); int l2cap_disconn_ind(struct hci_conn *hcon); void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason); int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_connect_cfm(struct hci_conn *hcon, __u8 status); void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason); int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); @@ -1050,28 +1048,6 @@ static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, } } -static inline void hci_proto_connect_cfm(struct hci_conn *conn, __u8 status) -{ - switch (conn->type) { - case ACL_LINK: - case LE_LINK: - l2cap_connect_cfm(conn, status); - break; - - case SCO_LINK: - case ESCO_LINK: - sco_connect_cfm(conn, status); - break; - - default: - BT_ERR("unknown link type %d", conn->type); - break; - } - - if (conn->connect_cfm_cb) - conn->connect_cfm_cb(conn, status); -} - static inline int hci_proto_disconn_ind(struct hci_conn *conn) { if (conn->type != ACL_LINK && conn->type != LE_LINK) @@ -1112,12 +1088,28 @@ struct hci_cb { char *name; + void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; +static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) +{ + struct hci_cb *cb; + + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->connect_cfm) + cb->connect_cfm(conn, status); + } + mutex_unlock(&hci_cb_list_lock); + + if (conn->connect_cfm_cb) + conn->connect_cfm_cb(conn, status); +} + static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; -- cgit v1.2.3 From 3a6d576be9fe02b0c3ffa89ef6eac048e14eec84 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 18 Feb 2015 14:53:58 +0200 Subject: Bluetooth: Convert disconn_cfm to be triggered through hci_cb This patch moves all the disconn_cfm callbacks to be based on the hci_cb list. This means making l2cap_disconn_cfm private to l2cap_core.c and sco_conn_cb private to sco.c respectively. Since the hci_conn type filtering isn't done any more on the wrapper level the callbacks themselves need to check that they were passed a relevant type of connection. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 44 +++++++++++++++------------------------- 1 file changed, 16 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 0f00f0e9f257..a7bf77384464 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -504,11 +504,9 @@ extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); -void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason); int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason); int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); /* ----- Inquiry cache ----- */ @@ -1056,32 +1054,6 @@ static inline int hci_proto_disconn_ind(struct hci_conn *conn) return l2cap_disconn_ind(conn); } -static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason) -{ - switch (conn->type) { - case ACL_LINK: - case LE_LINK: - l2cap_disconn_cfm(conn, reason); - break; - - case SCO_LINK: - case ESCO_LINK: - sco_disconn_cfm(conn, reason); - break; - - /* L2CAP would be handled for BREDR chan */ - case AMP_LINK: - break; - - default: - BT_ERR("unknown link type %d", conn->type); - break; - } - - if (conn->disconn_cfm_cb) - conn->disconn_cfm_cb(conn, reason); -} - /* ----- HCI callbacks ----- */ struct hci_cb { struct list_head list; @@ -1089,6 +1061,7 @@ struct hci_cb { char *name; void (*connect_cfm) (struct hci_conn *conn, __u8 status); + void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); @@ -1110,6 +1083,21 @@ static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) conn->connect_cfm_cb(conn, status); } +static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) +{ + struct hci_cb *cb; + + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->disconn_cfm) + cb->disconn_cfm(conn, reason); + } + mutex_unlock(&hci_cb_list_lock); + + if (conn->disconn_cfm_cb) + conn->disconn_cfm_cb(conn, reason); +} + static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; -- cgit v1.2.3 From 7129069e84056ba28954550beb208b2645863299 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 20 Feb 2015 13:26:23 +0200 Subject: Bluetooth: Rename hci_send_to_control to hci_send_to_channel The hci_send_to_control() can be made more general purpose with a small change of passing the desired HCI channel as a parameter to it. This allows using it for the monitor channel as well as e.g. 6lowpan in the future. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a7bf77384464..a831c8ad10f1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1265,7 +1265,8 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); -void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk); +void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, + struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); -- cgit v1.2.3 From 959d10f6bbf6ab5b8813c4e37540a2e43ca2ae96 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Feb 2015 03:19:24 -0800 Subject: igmp: add __ip_mc_{join|leave}_group() There is a need to perform igmp join/leave operations while RTNL is held. Make ip_mc_{join|leave}_group() wrappers around __ip_mc_{join|leave}_group() to avoid the proliferation of work queues. For example, vxlan_igmp_join() could possibly be removed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 2c677afeea47..b5a6470e686c 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -111,7 +111,9 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); extern int igmp_rcv(struct sk_buff *); +extern int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); +extern int __ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, -- cgit v1.2.3 From 059a2440fd3cf4ec57735db2c0a90401cde84fca Mon Sep 17 00:00:00 2001 From: Bojan Prtvar Date: Sun, 22 Feb 2015 11:46:35 +0100 Subject: net: Remove state argument from skb_find_text() Although it is clear that textsearch state is intentionally passed to skb_find_text() as uninitialized argument, it was never used by the callers. Therefore, we can simplify skb_find_text() by making it local variable. Signed-off-by: Bojan Prtvar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 30007afe70b3..d898b32dedcc 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -870,8 +870,7 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, void skb_abort_seq_read(struct skb_seq_state *st); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, - unsigned int to, struct ts_config *config, - struct ts_state *state); + unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. -- cgit v1.2.3 From 14c9551a32eba086c9f20c9d6a8e378481f15333 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 23 Feb 2015 17:50:11 -0800 Subject: bonding: Implement port churn-machine (AD standard 43.4.17). The Churn Detection machines detect the situation where a port is operable, but the Actor and Partner have not attached the link to an Aggregator and brought the link into operation within a bound time period. Under normal operation of the LACP, agreement between Actor and Partner should be reached very rapidly. Continued failure to reach agreement can be symptomatic of device failure. Actor-churn-detection state-machine Reviewed-by: Nikolay Aleksandrov =================================== BEGIN=True + PortEnable=False | v +------------------------+ ActorPort.Sync=True +------------------+ | ACTOR_CHURN_MONITOR | ---------------------> | NO_ACTOR_CHURN | |========================| |==================| | ActorChurn=False | ActorPort.Sync=False | ActorChurn=False | | ActorChurn.Timer=Start | <--------------------- | | +------------------------+ +------------------+ | ^ | | ActorChurn.Timer=Expired | | ActorPort.Sync=True | | | +-----------------+ | | | ACTOR_CHURN | | | |=================| | +--------------> | ActorChurn=True | ------------+ | | +-----------------+ Similar for the Partner-churn-detection. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f04cdbb7848e..c2a40a172fcd 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -82,6 +82,13 @@ typedef enum { AD_TRANSMIT /* tx Machine */ } tx_states_t; +/* churn machine states(43.4.17 in the 802.3ad standard) */ +typedef enum { + AD_CHURN_MONITOR, /* monitoring for churn */ + AD_CHURN, /* churn detected (error) */ + AD_NO_CHURN /* no churn (no error) */ +} churn_state_t; + /* rx indication types */ typedef enum { AD_TYPE_LACPDU = 1, /* type lacpdu */ @@ -229,6 +236,12 @@ typedef struct port { u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_churn_actor_timer_counter; + u16 sm_churn_partner_timer_counter; + u32 churn_actor_count; + u32 churn_partner_count; + churn_state_t sm_churn_actor_state; + churn_state_t sm_churn_partner_state; struct slave *slave; /* pointer to the bond slave that this port belongs to */ struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ @@ -262,6 +275,22 @@ struct ad_slave_info { u16 id; }; +static inline const char *bond_3ad_churn_desc(churn_state_t state) +{ + static const char *const churn_description[] = { + "monitoring", + "churned", + "none", + "unknown" + }; + int max_size = sizeof(churn_description) / sizeof(churn_description[0]); + + if (state >= max_size) + state = max_size - 1; + + return churn_description[state]; +} + /* ========== AD Exported functions to the main bonding code ========== */ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); void bond_3ad_bind_slave(struct slave *slave); -- cgit v1.2.3 From d752c364571743d696c2a54a449ce77550c35ac5 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Mon, 23 Feb 2015 15:02:34 -0300 Subject: ipvs: allow rescheduling of new connections when port reuse is detected Currently, when TCP/SCTP port reusing happens, IPVS will find the old entry and use it for the new one, behaving like a forced persistence. But if you consider a cluster with a heavy load of small connections, such reuse will happen often and may lead to a not optimal load balancing and might prevent a new node from getting a fair load. This patch introduces a new sysctl, conn_reuse_mode, that allows controlling how to proceed when port reuse is detected. The default value will allow rescheduling of new connections only if the old entry was in TIME_WAIT state for TCP or CLOSED for SCTP. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a627fe690c19..20fd23398537 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -941,6 +941,7 @@ struct netns_ipvs { int sysctl_nat_icmp_send; int sysctl_pmtu_disc; int sysctl_backup_only; + int sysctl_conn_reuse_mode; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1059,6 +1060,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs) ipvs->sysctl_backup_only; } +static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_conn_reuse_mode; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1126,6 +1132,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) +{ + return 1; +} + #endif /* IPVS core functions -- cgit v1.2.3 From b73adef67765b72f2a0d01ef15aff9d784dc85da Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 24 Feb 2015 13:15:33 -0800 Subject: net: dsa: integrate with SWITCHDEV for HW bridging In order to support bridging offloads in DSA switch drivers, select NET_SWITCHDEV to get access to the port_stp_update and parent_get_id NDOs that we are required to implement. To facilitate the integratation at the DSA driver level, we implement 3 types of operations: - port_join_bridge - port_leave_bridge - port_stp_update DSA will resolve which switch ports that are currently bridge port members as some Switch hardware/drivers need to know about that to limit the register programming to just the relevant registers (especially for slow MDIO buses). We also take care of setting the correct STP state when slave network devices are brought up/down while being bridge members. Finally, when a port is leaving the bridge, we make sure we set in BR_STATE_FORWARDING state, otherwise the bridge layer would leave it disabled as a result of having left the bridge. Signed-off-by: Florian Fainelli Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: David S. Miller --- include/net/dsa.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ed3c34bbb67a..92be34791963 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -275,6 +275,16 @@ struct dsa_switch_driver { int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); + + /* + * Bridge integration + */ + int (*port_join_bridge)(struct dsa_switch *ds, int port, + u32 br_port_mask); + int (*port_leave_bridge)(struct dsa_switch *ds, int port, + u32 br_port_mask); + int (*port_stp_update)(struct dsa_switch *ds, int port, + u8 state); }; void register_switch_driver(struct dsa_switch_driver *type); -- cgit v1.2.3 From d79d21073626cf022943e5c4c10a97cdf7cb8465 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 24 Feb 2015 23:02:02 -0800 Subject: net: dsa: Introduce dsa_is_port_initialized To avoid race conditions when using the ds->ports[] array, we need to check if the accessed port has been initialized. Introduce and use helper function dsa_is_port_initialized for that purpose and use it where needed. Signed-off-by: Guenter Roeck Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 92be34791963..c542c131d551 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -165,6 +165,11 @@ static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port); } +static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) +{ + return ds->phys_port_mask & (1 << p) && ds->ports[p]; +} + static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; -- cgit v1.2.3 From 4cd3928a8bee83d86fb3865bb243ab2ff1dd0eb6 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 27 Feb 2015 10:11:13 +0200 Subject: Bluetooth: Update New CSRK event to match latest specification The 'master' parameter of the New CSRK event was recently renamed to 'type', with the old values kept for backwards compatibility as unauthenticated local/remote keys. This patch updates the code to take into account the two new (authenticated) values and ensures they get used based on the security level of the connection that the respective keys get distributed over. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 +- include/net/bluetooth/mgmt.h | 7 ++++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a831c8ad10f1..acec9140c3f9 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -108,7 +108,7 @@ struct bt_uuid { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 master; + u8 type; u8 val[16]; }; diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e218a30f2061..fe8eef00e9ca 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -647,9 +647,14 @@ struct mgmt_ev_new_irk { struct mgmt_irk_info irk; } __packed; +#define MGMT_CSRK_LOCAL_UNAUTHENTICATED 0x00 +#define MGMT_CSRK_REMOTE_UNAUTHENTICATED 0x01 +#define MGMT_CSRK_LOCAL_AUTHENTICATED 0x02 +#define MGMT_CSRK_REMOTE_AUTHENTICATED 0x03 + struct mgmt_csrk_info { struct mgmt_addr_info addr; - __u8 master; + __u8 type; __u8 val[16]; } __packed; -- cgit v1.2.3 From ccdaeb2b176f7db491a6f8e8b1c51f9393525f7d Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 27 Feb 2015 09:58:26 +0100 Subject: at86rf230: add support for external xtal trim This patch adds support for setting the xtal trim register. Some at86rf2xx transceiver boards needs fine tuning the xtal capacitor. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/spi/at86rf230.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index cd519a11c2c6..b63fe6f5fdc8 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -22,6 +22,7 @@ struct at86rf230_platform_data { int rstn; int slp_tr; int dig2; + u8 xtal_trim; }; #endif -- cgit v1.2.3 From 723b8e460d87e957f251dc5764f4ab86af6ab44e Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 24 Feb 2015 09:17:31 -0800 Subject: udp: In udp_flow_src_port use random hash value if skb_get_hash fails In the unlikely event that skb_get_hash is unable to deduce a hash in udp_flow_src_port we use a consistent random value instead. This is specified in GRE/UDP draft section 3.2.1: https://tools.ietf.org/html/draft-ietf-tsvwg-gre-in-udp-encap-04 Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/udp.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 07f9b70962f6..32d8d9f07f76 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -194,6 +194,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*)(const struct sock *, const struct sock *), unsigned int hash2_nulladdr); +u32 udp_flow_hashrnd(void); + static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, int min, int max, bool use_eth) { @@ -205,12 +207,19 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } hash = skb_get_hash(skb); - if (unlikely(!hash) && use_eth) { - /* Can't find a normal hash, caller has indicated an Ethernet - * packet so use that to compute a hash. - */ - hash = jhash(skb->data, 2 * ETH_ALEN, - (__force u32) skb->protocol); + if (unlikely(!hash)) { + if (use_eth) { + /* Can't find a normal hash, caller has indicated an + * Ethernet packet so use that to compute a hash. + */ + hash = jhash(skb->data, 2 * ETH_ALEN, + (__force u32) skb->protocol); + } else { + /* Can't derive any sort of hash for the packet, set + * to some consistent random value. + */ + hash = udp_flow_hashrnd(); + } } /* Since this is being sent on the wire obfuscate hash a bit -- cgit v1.2.3 From 46a4dee074b58c4256dbf6c2dbf199c372f85b04 Mon Sep 17 00:00:00 2001 From: Madhu Challa Date: Wed, 25 Feb 2015 09:58:34 -0800 Subject: igmp v6: add __ipv6_sock_mc_join and __ipv6_sock_mc_drop Based on the igmp v4 changes from Eric Dumazet. 959d10f6bbf6("igmp: add __ip_mc_{join|leave}_group()") These changes are needed to perform igmp v6 join/leave while RTNL is held. Make ipv6_sock_mc_join and ipv6_sock_mc_drop wrappers around __ipv6_sock_mc_join and __ipv6_sock_mc_drop to avoid proliferation of work queues. Signed-off-by: Madhu Challa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4c9fe224d73b..b7673065c074 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -940,4 +940,12 @@ int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif +int ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int __ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int ipv6_sock_mc_drop(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int __ipv6_sock_mc_drop(struct sock *sk, int ifindex, + const struct in6_addr *addr); #endif /* _NET_IPV6_H */ -- cgit v1.2.3 From 93a714d6b53d87872e552dbb273544bdeaaf6e12 Mon Sep 17 00:00:00 2001 From: Madhu Challa Date: Wed, 25 Feb 2015 09:58:35 -0800 Subject: multicast: Extend ip address command to enable multicast group join/leave on Joining multicast group on ethernet level via "ip maddr" command would not work if we have an Ethernet switch that does igmp snooping since the switch would not replicate multicast packets on ports that did not have IGMP reports for the multicast addresses. Linux vxlan interfaces created via "ip link add vxlan" have the group option that enables then to do the required join. By extending ip address command with option "autojoin" we can get similar functionality for openvswitch vxlan interfaces as well as other tunneling mechanisms that need to receive multicast traffic. The kernel code is structured similar to how the vxlan driver does a group join / leave. example: ip address add 224.1.1.10/24 dev eth5 autojoin ip address del 224.1.1.10/24 dev eth5 Signed-off-by: Madhu Challa Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/netns/ipv6.h | 1 + include/uapi/linux/if_addr.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index dbe225478adb..1b26c6c3fd7c 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -49,6 +49,7 @@ struct netns_ipv4 { struct sock *fibnl; struct sock * __percpu *icmp_sk; + struct sock *mc_autojoin_sk; struct inet_peer_base *peers; struct tcpm_hash_bucket *tcp_metrics_hash; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 69ae41f2098c..ca0db12cd089 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -67,6 +67,7 @@ struct netns_ipv6 { struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; + struct sock *mc_autojoin_sk; #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES struct mr6_table *mrt6; diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index dea10a87dfd1..40fdfea39714 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -50,6 +50,7 @@ enum { #define IFA_F_PERMANENT 0x80 #define IFA_F_MANAGETEMPADDR 0x100 #define IFA_F_NOPREFIXROUTE 0x200 +#define IFA_F_MCAUTOJOIN 0x400 struct ifa_cacheinfo { __u32 ifa_prefered; -- cgit v1.2.3 From 56315f9e6e3a0ba0483c2e1f53333d5275268cb1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 25 Feb 2015 15:31:31 -0800 Subject: fib_trie: Convert fib_alias to hlist from list There isn't any advantage to having it as a list and by making it an hlist we make the fib_alias more compatible with the list_info in terms of the type of list used. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 5bd120e4bc0a..cba4b7c32935 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -136,7 +136,7 @@ struct fib_result { u32 tclassid; struct fib_info *fi; struct fib_table *table; - struct list_head *fa_head; + struct hlist_head *fa_head; }; struct fib_result_nl { -- cgit v1.2.3 From 6588af614e7b79294fbcd4a666a7422c0c854e80 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 26 Feb 2015 19:34:37 +0000 Subject: usbnet: Fix tx_packets stat for FLAG_MULTI_FRAME drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the usbnet core does not update the tx_packets statistic for drivers with FLAG_MULTI_PACKET and there is no hook in the TX completion path where they could do this. cdc_ncm and dependent drivers are bumping tx_packets stat on the transmit path while asix and sr9800 aren't updating it at all. Add a packet count in struct skb_data so these drivers can fill it in, initialise it to 1 for other drivers, and add the packet count to the tx_packets statistic on completion. Signed-off-by: Ben Hutchings Tested-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index d9a4905e01d0..ff3fb2bd0e90 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -228,8 +228,20 @@ struct skb_data { /* skb->cb is one of these */ struct usbnet *dev; enum skb_state state; size_t length; + unsigned long packets; }; +/* Drivers that set FLAG_MULTI_PACKET must call this in their + * tx_fixup method before returning an skb. + */ +static inline void +usbnet_set_skb_tx_stats(struct sk_buff *skb, unsigned long packets) +{ + struct skb_data *entry = (struct skb_data *) skb->cb; + + entry->packets = packets; +} + extern int usbnet_open(struct net_device *net); extern int usbnet_stop(struct net_device *net); extern netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, -- cgit v1.2.3 From 5f852eb536ad651b8734559dcf4353514cb0bea3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 26 Feb 2015 14:10:18 -0800 Subject: tcp: tso: remove tp->tso_deferred TSO relies on ability to defer sending a small amount of packets. Heuristic is to wait for future ACKS in hope to send more packets at once. Current algorithm uses a per socket tso_deferred field as a pseudo timer. This pseudo timer relies on future ACK, but there is no guarantee we receive them in time. Fix would be to use a real timer, but cost of such timer is probably too expensive for typical cases. This patch changes the logic to test the time of last transmit, because we should not add bursts of more than 1ms for any given flow. We've used this patch for about two years at Google, before FQ/pacing as it would reduce a fair amount of bursts. Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1a7adb411647..97dbf16f7d9d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -236,7 +236,6 @@ struct tcp_sock { u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ u32 fackets_out; /* FACK'd packets */ - u32 tso_deferred; /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; -- cgit v1.2.3 From 31f909a2c0abfc1a1a76b2981d28ac85d33210e7 Mon Sep 17 00:00:00 2001 From: Masashi Honma Date: Tue, 24 Feb 2015 22:42:16 +0900 Subject: nl/mac80211: allow zero plink timeout to disable STA expiration Both wpa_supplicant and mac80211 have and inactivity timer. By default wpa_supplicant will be timed out in 5 minutes and mac80211's it is 30 minutes. If wpa_supplicant uses a longer timer than mac80211, it will get unexpected disconnection by mac80211. Using 0xffffffff instead as the configured value could solve this w/o changing the code, but due to integer overflow in the expression used this doesn't work. The expression is: (current jiffies) > (frame Rx jiffies + NL80211_MESHCONF_PLINK_TIMEOUT * 250) On 32bit system, the right side would overflow and be a very small value if NL80211_MESHCONF_PLINK_TIMEOUT is sufficiently large, causing unexpectedly early disconnections. Instead allow disabling the inactivity timer to avoid this situation, by passing the (previously invalid and useless) value 0. Signed-off-by: Masashi Honma [reword/rewrap commit log] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 68b294e83944..2dcf9bba317c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3092,7 +3092,8 @@ enum nl80211_mesh_power_mode { * * @NL80211_MESHCONF_PLINK_TIMEOUT: If no tx activity is seen from a STA we've * established peering with for longer than this time (in seconds), then - * remove it from the STA's list of peers. Default is 30 minutes. + * remove it from the STA's list of peers. You may set this to 0 to disable + * the removal of the STA. Default is 30 minutes. * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use */ -- cgit v1.2.3 From 36ef906ee8fefbfac3844206e66d8450e6221c69 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Feb 2015 10:54:33 +0100 Subject: wext: add checked wrappers for adding events/points to streams These checked wrappers are necessary for the next patch, which will use them to avoid sending out partial scan results. Signed-off-by: Johannes Berg --- include/net/iw_handler.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index a830b01baba4..8f81bbbc38fc 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -519,6 +519,17 @@ iwe_stream_add_event(struct iw_request_info *info, char *stream, char *ends, return stream; } +static inline char * +iwe_stream_add_event_check(struct iw_request_info *info, char *stream, + char *ends, struct iw_event *iwe, int event_len) +{ + char *res = iwe_stream_add_event(info, stream, ends, iwe, event_len); + + if (res == stream) + return ERR_PTR(-E2BIG); + return res; +} + /*------------------------------------------------------------------*/ /* * Wrapper to add an short Wireless Event containing a pointer to a @@ -545,6 +556,17 @@ iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, return stream; } +static inline char * +iwe_stream_add_point_check(struct iw_request_info *info, char *stream, + char *ends, struct iw_event *iwe, char *extra) +{ + char *res = iwe_stream_add_point(info, stream, ends, iwe, extra); + + if (res == stream) + return ERR_PTR(-E2BIG); + return res; +} + /*------------------------------------------------------------------*/ /* * Wrapper to add a value to a Wireless Event in a stream of events. -- cgit v1.2.3 From a2c83fff582ae133d9f5bb187404ea9ce4da1f96 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:42 +0100 Subject: ebpf: constify various function pointer structs We can move bpf_map_ops and bpf_verifier_ops and other structs into ro section, bpf_map_type_list and bpf_prog_type_list into read mostly. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bbfceb756452..78446860f796 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -32,13 +32,13 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - struct bpf_map_ops *ops; + const struct bpf_map_ops *ops; struct work_struct work; }; struct bpf_map_type_list { struct list_head list_node; - struct bpf_map_ops *ops; + const struct bpf_map_ops *ops; enum bpf_map_type type; }; @@ -109,7 +109,7 @@ struct bpf_verifier_ops { struct bpf_prog_type_list { struct list_head list_node; - struct bpf_verifier_ops *ops; + const struct bpf_verifier_ops *ops; enum bpf_prog_type type; }; @@ -121,7 +121,7 @@ struct bpf_prog_aux { atomic_t refcnt; bool is_gpl_compatible; enum bpf_prog_type prog_type; - struct bpf_verifier_ops *ops; + const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; u32 used_map_cnt; struct bpf_prog *prog; @@ -138,8 +138,8 @@ struct bpf_prog *bpf_prog_get(u32 ufd); int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); /* verifier prototypes for helper functions called from eBPF programs */ -extern struct bpf_func_proto bpf_map_lookup_elem_proto; -extern struct bpf_func_proto bpf_map_update_elem_proto; -extern struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_lookup_elem_proto; +extern const struct bpf_func_proto bpf_map_update_elem_proto; +extern const struct bpf_func_proto bpf_map_delete_elem_proto; #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From f1a66f85b74c5ef7b503f746ea97742dacd56419 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:43 +0100 Subject: ebpf: export BPF_PSEUDO_MAP_FD to uapi We need to export BPF_PSEUDO_MAP_FD to user space, as it's used in the ELF BPF loader where instructions are being loaded that need map fixups. An initial stage loads all maps into the kernel, and later on replaces related instructions in the eBPF blob with BPF_PSEUDO_MAP_FD as source register and the actual fd as immediate value. The kernel verifier recognizes this keyword and replaces the map fd with a real pointer internally. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 -- include/uapi/linux/bpf.h | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index caac2087a4d5..5e3863d5f666 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -145,8 +145,6 @@ struct bpf_prog_aux; .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) -#define BPF_PSEUDO_MAP_FD 1 - /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 45da7ec7d274..0248180bf2e2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -120,6 +120,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_SOCKET_FILTER, }; +#define BPF_PSEUDO_MAP_FD 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ -- cgit v1.2.3 From 0fc174dea54546e2b1146e1197da1b6d4bc48107 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:44 +0100 Subject: ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs Socket filter code and other subsystems with upcoming eBPF support should not need to deal with the fact that we have CONFIG_BPF_SYSCALL defined or not. Having the bpf syscall as a config option is a nice thing and I'd expect it to stay that way for expert users (I presume one day the default setting of it might change, though), but code making use of it should not care if it's actually enabled or not. Instead, hide this via header files and let the rest deal with it. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 78446860f796..9c458144cdb4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -113,8 +113,6 @@ struct bpf_prog_type_list { enum bpf_prog_type type; }; -void bpf_register_prog_type(struct bpf_prog_type_list *tl); - struct bpf_prog; struct bpf_prog_aux { @@ -129,11 +127,25 @@ struct bpf_prog_aux { }; #ifdef CONFIG_BPF_SYSCALL +void bpf_register_prog_type(struct bpf_prog_type_list *tl); + void bpf_prog_put(struct bpf_prog *prog); +struct bpf_prog *bpf_prog_get(u32 ufd); #else -static inline void bpf_prog_put(struct bpf_prog *prog) {} +static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) +{ +} + +static inline struct bpf_prog *bpf_prog_get(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void bpf_prog_put(struct bpf_prog *prog) +{ +} #endif -struct bpf_prog *bpf_prog_get(u32 ufd); + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); -- cgit v1.2.3 From 96be4325f443dbbfeb37d2a157675ac0736531a1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:46 +0100 Subject: ebpf: add sched_cls_type and map it to sk_filter's verifier ops As discussed recently and at netconf/netdev01, we want to prevent making bpf_verifier_ops registration available for modules, but have them at a controlled place inside the kernel instead. The reason for this is, that out-of-tree modules can go crazy and define and register any verfifier ops they want, doing all sorts of crap, even bypassing available GPLed eBPF helper functions. We don't want to offer such a shiny playground, of course, but keep strict control to ourselves inside the core kernel. This also encourages us to design eBPF user helpers carefully and generically, so they can be shared among various subsystems using eBPF. For the eBPF traffic classifier (cls_bpf), it's a good start to share the same helper facilities as we currently do in eBPF for socket filters. That way, we have BPF_PROG_TYPE_SCHED_CLS look like it's own type, thus one day if there's a good reason to diverge the set of helper functions from the set available to socket filters, we keep ABI compatibility. In future, we could place all bpf_prog_type_list at a central place, perhaps. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0248180bf2e2..3fa1af8a58d7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -118,6 +118,7 @@ enum bpf_map_type { enum bpf_prog_type { BPF_PROG_TYPE_UNSPEC, BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_SCHED_CLS, }; #define BPF_PSEUDO_MAP_FD 1 -- cgit v1.2.3 From 24701ecea76b0b93bd9667486934ec310825f558 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:47 +0100 Subject: ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 +--- include/linux/filter.h | 4 +++- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9c458144cdb4..a1a7ff2df328 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -117,11 +117,9 @@ struct bpf_prog; struct bpf_prog_aux { atomic_t refcnt; - bool is_gpl_compatible; - enum bpf_prog_type prog_type; + u32 used_map_cnt; const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; - u32 used_map_cnt; struct bpf_prog *prog; struct work_struct work; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5e3863d5f666..9ee8c67ea249 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -308,9 +308,11 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ bool jited; /* Is our filter JIT'ed? */ + bool gpl_compatible; /* Is our filter GPL compatible? */ u32 len; /* Number of filter blocks */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ + enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); /* Instructions for interpreter */ -- cgit v1.2.3 From e2e9b6541dd4b31848079da80fe2253daaafb549 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:48 +0100 Subject: cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include #include #include #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann Cc: Jamal Hadi Salim Cc: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 25731dfb3fcc..bf08e76bf505 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -397,6 +397,8 @@ enum { TCA_BPF_CLASSID, TCA_BPF_OPS_LEN, TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, __TCA_BPF_MAX, }; -- cgit v1.2.3 From 287f3a943fef58c5c73e42545169443be379222f Mon Sep 17 00:00:00 2001 From: Simon Farnsworth Date: Sun, 1 Mar 2015 10:54:39 +0000 Subject: pppoe: Use workqueue to die properly when a PADT is received When a PADT frame is received, the socket may not be in a good state to close down the PPP interface. The current implementation handles this by simply blocking all further PPP traffic, and hoping that the lack of traffic will trigger the user to investigate. Use schedule_work to get to a process context from which we clear down the PPP interface, in a fashion analogous to hangup on a TTY-based PPP interface. This causes pppd to disconnect immediately, and allows tools to take immediate corrective action. Note that pppd's rp_pppoe.so plugin has code in it to disable the session when it disconnects; however, as a consequence of this patch, the session is already disabled before rp_pppoe.so is asked to disable the session. The result is a harmless error message: Failed to disconnect PPPoE socket: 114 Operation already in progress This message is safe to ignore, as long as the error is 114 Operation already in progress; in that specific case, it means that the PPPoE session has already been disabled before pppd tried to disable it. Signed-off-by: Simon Farnsworth Tested-by: Dan Williams Tested-by: Christoph Schulz Signed-off-by: David S. Miller --- include/linux/if_pppox.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index aff7ad8a4ea3..66a7d7600f43 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -19,6 +19,7 @@ #include #include #include +#include #include static inline struct pppoe_hdr *pppoe_hdr(const struct sk_buff *skb) @@ -32,6 +33,7 @@ struct pppoe_opt { struct pppoe_addr pa; /* what this socket is bound to*/ struct sockaddr_pppox relay; /* what socket data will be relayed to (PPPoE relaying) */ + struct work_struct padt_work;/* Work item for handling PADT */ }; struct pptp_opt { -- cgit v1.2.3 From 49a6fe055739a77ef910c283efb99928423c97a0 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 1 Mar 2015 14:58:25 +0200 Subject: net: bluetooth: compact struct bt_skb_cb by inlining struct hci_req_ctrl struct hci_req_ctrl is never used outside of struct bt_skb_cb; Inlining it frees 8 bytes on a 64 bit system in skb->cb[] allowing the addition of more ancillary data. Signed-off-by: Eyal Birger Reviewed-by: Shmulik Ladkani Signed-off-by: David S. Miller --- include/net/bluetooth/bluetooth.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e00455aab18c..09893668e6ea 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -275,21 +275,17 @@ struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); -struct hci_req_ctrl { - bool start; - u8 event; - hci_req_complete_t complete; -}; - struct bt_skb_cb { __u8 pkt_type; __u8 incoming; __u16 opcode; __u16 expect; __u8 force_active; + bool req_start; + u8 req_event; + hci_req_complete_t req_complete; struct l2cap_chan *chan; struct l2cap_ctrl control; - struct hci_req_ctrl req; bdaddr_t bdaddr; __le16 psm; }; -- cgit v1.2.3 From 6368c235777456ddaeaa61360186d8d03a61cb18 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 1 Mar 2015 14:58:26 +0200 Subject: net: bluetooth: compact struct bt_skb_cb by converting boolean fields to bit fields Convert boolean fields incoming and req_start to bit fields and move force_active in order save space in bt_skb_cb in an effort to use a portion of skb->cb[] for storing skb->dropcount. Signed-off-by: Eyal Birger Signed-off-by: David S. Miller --- include/net/bluetooth/bluetooth.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 09893668e6ea..4500bf88ff55 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -277,11 +277,11 @@ typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); struct bt_skb_cb { __u8 pkt_type; - __u8 incoming; + __u8 force_active; __u16 opcode; __u16 expect; - __u8 force_active; - bool req_start; + __u8 incoming:1; + __u8 req_start:1; u8 req_event; hci_req_complete_t req_complete; struct l2cap_chan *chan; -- cgit v1.2.3 From b4772ef879a8f7d8c56118c2ae5a296fcf6f81d2 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 1 Mar 2015 14:58:29 +0200 Subject: net: use common macro for assering skb->cb[] available size in protocol families As part of an effort to move skb->dropcount to skb->cb[] use a common macro in protocol families using skb->cb[] for ancillary data to validate available room in skb->cb[]. Signed-off-by: Eyal Birger Signed-off-by: David S. Miller --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index ab186b1d31ff..a2502d248641 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2078,6 +2078,9 @@ static inline int sock_intr_errno(long timeo) return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } +#define sock_skb_cb_check_size(size) \ + BUILD_BUG_ON((size) > FIELD_SIZEOF(struct sk_buff, cb)) + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, -- cgit v1.2.3 From 3bc3b96f3b455bd14a8ccd83ffffc85625aba641 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 1 Mar 2015 14:58:30 +0200 Subject: net: add common accessor for setting dropcount on packets As part of an effort to move skb->dropcount to skb->cb[], use a common function in order to set dropcount in struct sk_buff. Signed-off-by: Eyal Birger Signed-off-by: David S. Miller --- include/net/sock.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index a2502d248641..0996fe451e5f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2081,6 +2081,12 @@ static inline int sock_intr_errno(long timeo) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > FIELD_SIZEOF(struct sk_buff, cb)) +static inline void +sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) +{ + skb->dropcount = atomic_read(&sk->sk_drops); +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, -- cgit v1.2.3 From 744d5a3e9fe2690dd85d9991dbb078301694658b Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 1 Mar 2015 14:58:31 +0200 Subject: net: move skb->dropcount to skb->cb[] Commit 977750076d98 ("af_packet: add interframe drop cmsg (v6)") unionized skb->mark and skb->dropcount in order to allow recording of the socket drop count while maintaining struct sk_buff size. skb->dropcount was introduced since there was no available room in skb->cb[] in packet sockets. However, its introduction led to the inability to export skb->mark, or any other aliased field to userspace if so desired. Moving the dropcount metric to skb->cb[] eliminates this problem at the expense of 4 bytes less in skb->cb[] for protocol families using it. Signed-off-by: Eyal Birger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- include/net/sock.h | 18 ++++++++++++++++-- 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d898b32dedcc..bba1330757c0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -492,7 +492,6 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking * @mark: Generic packet mark - * @dropcount: total number of sk_receive_queue overflows * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) @@ -641,7 +640,6 @@ struct sk_buff { #endif union { __u32 mark; - __u32 dropcount; __u32 reserved_tailroom; }; diff --git a/include/net/sock.h b/include/net/sock.h index 0996fe451e5f..38369d3580a1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2078,13 +2078,27 @@ static inline int sock_intr_errno(long timeo) return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } +struct sock_skb_cb { + u32 dropcount; +}; + +/* Store sock_skb_cb at the end of skb->cb[] so protocol families + * using skb->cb[] would keep using it directly and utilize its + * alignement guarantee. + */ +#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ + sizeof(struct sock_skb_cb))) + +#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ + SOCK_SKB_CB_OFFSET)) + #define sock_skb_cb_check_size(size) \ - BUILD_BUG_ON((size) > FIELD_SIZEOF(struct sk_buff, cb)) + BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { - skb->dropcount = atomic_read(&sk->sk_drops); + SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, -- cgit v1.2.3 From 4186721d02b71ae943e60bbf50d3488fd5fd6adb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 8 Feb 2015 17:11:47 +0100 Subject: bcma: add helpers bringing PCIe hosted bus up / down MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bringing PCIe hosted bus up requires operating on host-related core. Since we plan to support PCIe Gen 2 devices we should provide a helper picking the correct one (PCIE or PCIE2). Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 3 +++ include/linux/bcma/bcma_driver_pci.h | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 994739da827f..037620b3f113 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -434,6 +434,9 @@ static inline struct bcma_device *bcma_find_core(struct bcma_bus *bus, return bcma_find_core_unit(bus, coreid, 0); } +extern void bcma_host_pci_up(struct bcma_bus *bus); +extern void bcma_host_pci_down(struct bcma_bus *bus); + extern bool bcma_core_is_enabled(struct bcma_device *core); extern void bcma_core_disable(struct bcma_device *core, u32 flags); extern int bcma_core_enable(struct bcma_device *core, u32 flags); diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 3f809ae372c4..23af893e9b86 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -242,8 +242,6 @@ extern void bcma_core_pci_early_init(struct bcma_drv_pci *pc); extern void bcma_core_pci_init(struct bcma_drv_pci *pc); extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable); -extern void bcma_core_pci_up(struct bcma_bus *bus); -extern void bcma_core_pci_down(struct bcma_bus *bus); extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); -- cgit v1.2.3 From 5b6ff664c8959d715e785b9465b042407a5d87a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 8 Feb 2015 17:11:48 +0100 Subject: bcma: change IRQ control function to accept bus as an argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It doesn't operate on PCI core, but PCI host device, so there is no point of passing core related struct. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 23af893e9b86..6b8bca67851f 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -240,7 +240,7 @@ struct bcma_drv_pci { extern void bcma_core_pci_early_init(struct bcma_drv_pci *pc); extern void bcma_core_pci_init(struct bcma_drv_pci *pc); -extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, +extern int bcma_core_pci_irq_ctl(struct bcma_bus *bus, struct bcma_device *core, bool enable); extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); -- cgit v1.2.3 From 804e27dee49e20c0addd1b7276654220cc3768ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 8 Feb 2015 17:11:49 +0100 Subject: bcma: support bringing up bus hosted on PCIe Gen 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_pcie2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_pcie2.h b/include/linux/bcma/bcma_driver_pcie2.h index 5988b05781c3..d8c43294c527 100644 --- a/include/linux/bcma/bcma_driver_pcie2.h +++ b/include/linux/bcma/bcma_driver_pcie2.h @@ -143,6 +143,8 @@ struct bcma_drv_pcie2 { struct bcma_device *core; + + u16 reqsize; }; #define pcie2_read16(pcie2, offset) bcma_read16((pcie2)->core, offset) -- cgit v1.2.3 From 1b784140474e4fc94281a49e96c67d29df0efbde Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 2 Mar 2015 15:37:48 +0800 Subject: net: Remove iocb argument from sendmsg and recvmsg After TIPC doesn't depend on iocb argument in its internal implementations of sendmsg() and recvmsg() hooks defined in proto structure, no any user is using iocb argument in them at all now. Then we can drop the redundant iocb argument completely from kinds of implementations of both sendmsg() and recvmsg() in the entire networking stack. Cc: Christoph Hellwig Suggested-by: Al Viro Signed-off-by: Ying Xue Signed-off-by: David S. Miller --- include/linux/net.h | 10 ++++------ include/net/af_vsock.h | 4 ++-- include/net/bluetooth/bluetooth.h | 8 ++++---- include/net/inet_common.h | 7 +++---- include/net/ping.h | 7 +++---- include/net/sock.h | 16 +++++++--------- include/net/tcp.h | 7 +++---- include/net/udp.h | 3 +-- 8 files changed, 27 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 17d83393afcc..e74114bcca68 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -120,7 +120,6 @@ struct socket { struct vm_area_struct; struct page; -struct kiocb; struct sockaddr; struct msghdr; struct module; @@ -162,8 +161,8 @@ struct proto_ops { int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); #endif - int (*sendmsg) (struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len); + int (*sendmsg) (struct socket *sock, struct msghdr *m, + size_t total_len); /* Notes for implementing recvmsg: * =============================== * msg->msg_namelen should get updated by the recvmsg handlers @@ -172,9 +171,8 @@ struct proto_ops { * handlers can assume that msg.msg_name is either NULL or has * a minimum size of sizeof(struct sockaddr_storage). */ - int (*recvmsg) (struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len, - int flags); + int (*recvmsg) (struct socket *sock, struct msghdr *m, + size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); ssize_t (*sendpage) (struct socket *sock, struct page *page, diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 0d87674fb775..172632dd9930 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -100,8 +100,8 @@ struct vsock_transport { /* DGRAM. */ int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); - int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk, - struct msghdr *msg, size_t len, int flags); + int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); bool (*dgram_allow)(u32 cid, u32 port); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 4500bf88ff55..6bb97df16d2d 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -245,10 +245,10 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); -int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags); -int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags); +int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); uint bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b2828a06a5a6..4a92423eefa5 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -21,12 +21,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags); -int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size); +int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); -int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags); +int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); diff --git a/include/net/ping.h b/include/net/ping.h index cc16d413f681..ac80cb45e630 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -75,12 +75,11 @@ void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); -int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len); +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len); int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); -int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); +int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); bool ping_rcv(struct sk_buff *skb); diff --git a/include/net/sock.h b/include/net/sock.h index 38369d3580a1..250822cc1e02 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -958,10 +958,9 @@ struct proto { int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif - int (*sendmsg)(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len); - int (*recvmsg)(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, + int (*sendmsg)(struct sock *sk, struct msghdr *msg, + size_t len); + int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, @@ -1562,9 +1561,8 @@ int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int); -int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); -int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, - int); +int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); +int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, @@ -1576,8 +1574,8 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags); +int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int compat_sock_common_getsockopt(struct socket *sock, int level, diff --git a/include/net/tcp.h b/include/net/tcp.h index 8d6b983d5099..f87599d5af82 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -349,8 +349,7 @@ void tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); -int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size); +int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tcp_release_cb(struct sock *sk); @@ -430,8 +429,8 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); -int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len); +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len); void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); diff --git a/include/net/udp.h b/include/net/udp.h index 32d8d9f07f76..6d4ed18e1427 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -238,8 +238,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); void udp_err(struct sk_buff *, u32); -int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); +int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); -- cgit v1.2.3 From 61e021f3b86cbbcc04cbe8ac7b7da2b8c94b5e8e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 2 Mar 2015 15:21:55 +0100 Subject: ebpf: move CONFIG_BPF_SYSCALL-only function declarations Masami noted that it would be better to hide the remaining CONFIG_BPF_SYSCALL-only function declarations within the BPF header ifdef, w/o else path dummy alternatives since these functions are not supposed to have a user outside of CONFIG_BPF_SYSCALL. Suggested-by: Masami Hiramatsu Reference: http://article.gmane.org/gmane.linux.kernel.api/8658 Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a1a7ff2df328..a884f5a2c503 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -42,10 +42,6 @@ struct bpf_map_type_list { enum bpf_map_type type; }; -void bpf_register_map_type(struct bpf_map_type_list *tl); -void bpf_map_put(struct bpf_map *map); -struct bpf_map *bpf_map_get(struct fd f); - /* function argument constraints */ enum bpf_arg_type { ARG_ANYTHING = 0, /* any argument is ok */ @@ -126,9 +122,16 @@ struct bpf_prog_aux { #ifdef CONFIG_BPF_SYSCALL void bpf_register_prog_type(struct bpf_prog_type_list *tl); +void bpf_register_map_type(struct bpf_map_type_list *tl); -void bpf_prog_put(struct bpf_prog *prog); struct bpf_prog *bpf_prog_get(u32 ufd); +void bpf_prog_put(struct bpf_prog *prog); + +struct bpf_map *bpf_map_get(struct fd f); +void bpf_map_put(struct bpf_map *map); + +/* verify correctness of eBPF program */ +int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); #else static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) { @@ -142,10 +145,7 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd) static inline void bpf_prog_put(struct bpf_prog *prog) { } -#endif - -/* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); +#endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; -- cgit v1.2.3 From 46d4e47abee04c24055114d50e408078a09c4d36 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:04:31 -0600 Subject: ax25: Make ax25_header and ax25_rebuild_header static The only user is in ax25_ip.c so stop exporting these functions. Cc: Ralf Baechle Cc: linux-hams@vger.kernel.org Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ax25.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index bf0396e9a5d3..7385a64b61b8 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -366,9 +366,6 @@ int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); /* ax25_ip.c */ -int ax25_hard_header(struct sk_buff *, struct net_device *, unsigned short, - const void *, const void *, unsigned int); -int ax25_rebuild_header(struct sk_buff *); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ -- cgit v1.2.3 From 3b6a94bed0029a6b48055d89b8dea0567abca0ac Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:05:28 -0600 Subject: ax25: Refactor to use private neighbour operations. AX25 already has it's own private arp cache operations to isolate it's abuse of dev_rebuild_header to transmit packets. Add a function ax25_neigh_construct that will allow all of the ax25 devices to force using these operations, so that the generic arp code does not need to. Cc: Ralf Baechle Cc: linux-hams@vger.kernel.org Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ax25.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 7385a64b61b8..45feeba7a325 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -12,6 +12,7 @@ #include #include #include +#include #define AX25_T1CLAMPLO 1 #define AX25_T1CLAMPHI (30 * HZ) @@ -366,7 +367,11 @@ int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); /* ax25_ip.c */ +int ax25_neigh_construct(struct neighbour *neigh); extern const struct header_ops ax25_header_ops; +struct ax25_neigh_priv { + struct neigh_ops ops; +}; /* ax25_out.c */ ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, -- cgit v1.2.3 From def6775369fab9d36817b9a6bc58cab67f53f1dc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:07:37 -0600 Subject: neigh: Move neigh_compat_output into ax25_ip.c The only caller is now is ax25_neigh_construct so move neigh_compat_output into ax25_ip.c make it static and rename it ax25_neigh_output. Cc: Ralf Baechle Cc: linux-hams@vger.kernel.org Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 76f708486aae..bc66babb5f27 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -268,7 +268,6 @@ void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); -int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, -- cgit v1.2.3 From d476059e77d1af48453a58f9de1e36f2eaff6450 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:11:09 -0600 Subject: net: Kill dev_rebuild_header Now that there are no more users kill dev_rebuild_header and all of it's implementations. This is long overdue. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 1 - include/linux/netdevice.h | 12 +----------- 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 1d869d185a0d..606563ef8a72 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -35,7 +35,6 @@ extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); -int eth_rebuild_header(struct sk_buff *skb); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5897b4ea5a3f..2007f3b44d05 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -261,7 +261,6 @@ struct header_ops { unsigned short type, const void *daddr, const void *saddr, unsigned int len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); - int (*rebuild)(struct sk_buff *skb); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, @@ -1346,7 +1345,7 @@ enum netdev_priv_flags { * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations * @fwd_ops: Management operations - * @header_ops: Includes callbacks for creating,parsing,rebuilding,etc + * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * * @flags: Interface flags (a la BSD) @@ -2399,15 +2398,6 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } -static inline int dev_rebuild_header(struct sk_buff *skb) -{ - const struct net_device *dev = skb->dev; - - if (!dev->header_ops || !dev->header_ops->rebuild) - return 0; - return dev->header_ops->rebuild(skb); -} - typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) -- cgit v1.2.3 From 59b2af26b9f674749216fd3bfba19d842de3671c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:12:05 -0600 Subject: arp: Kill arp_find There are no more callers so kill this function. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/arp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/arp.h b/include/net/arp.h index 73c49864076b..21ee1860abbc 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -47,7 +47,6 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 } void arp_init(void); -int arp_find(unsigned char *haddr, struct sk_buff *skb); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, -- cgit v1.2.3 From bdf53c58490bb52e17636eca8ad18d2c38ec3cb8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 2 Mar 2015 00:13:22 -0600 Subject: neigh: Don't require dst in neigh_hh_init - Add protocol to neigh_tbl so that dst->ops->protocol is not needed - Acquire the device from neigh->dev This results in a neigh_hh_init that will cache the samve values regardless of the packets flowing through it. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index bc66babb5f27..9f912e4d4232 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -193,6 +193,7 @@ struct neigh_table { int family; int entry_size; int key_len; + __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); -- cgit v1.2.3 From ee586bbc28fb7128133457cf711880d13a3b7ce4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 16 Feb 2015 18:54:04 +0100 Subject: netfilter: reject: don't send icmp error if csum is invalid tcp resets are never emitted if the packet that triggers the reject/reset has an invalid checksum. For icmp error responses there was no such check. It allows to distinguish icmp response generated via iptables -I INPUT -p udp --dport 42 -j REJECT and those emitted by network stack (won't respond if csum is invalid, REJECT does). Arguably its possible to avoid this by using conntrack and only using REJECT with -m conntrack NEW/RELATED. However, this doesn't work when connection tracking is not in use or when using nf_conntrack_checksum=0. Furthermore, sending errors in response to invalid csums doesn't make much sense so just add similar test as in nf_send_reset. Validate csum if needed and only send the response if it is ok. Reference: http://bugzilla.redhat.com/show_bug.cgi?id=1169829 Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_reject.h | 6 +----- include/net/netfilter/ipv6/nf_reject.h | 11 ++--------- 2 files changed, 3 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 03e928a55229..864127573c32 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -5,11 +5,7 @@ #include #include -static inline void nf_send_unreach(struct sk_buff *skb_in, int code) -{ - icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); -} - +void nf_send_unreach(struct sk_buff *skb_in, int code, int hook); void nf_send_reset(struct sk_buff *oldskb, int hook); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 23216d48abf9..0ae445d3f217 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -3,15 +3,8 @@ #include -static inline void -nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code, - unsigned int hooknum) -{ - if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) - skb_in->dev = net->loopback_dev; - - icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); -} +void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code, + unsigned int hooknum); void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook); -- cgit v1.2.3 From 6eb18137643fee5f182d85c818062b4feddfb76b Mon Sep 17 00:00:00 2001 From: Dedy Lansky Date: Sun, 8 Feb 2015 15:52:03 +0200 Subject: cfg80211: add bss_type and privacy arguments in cfg80211_get_bss() 802.11ad adds new a network type (PBSS) and changes the capability field interpretation for the DMG (60G) band. The same 2 bits that were interpreted as "ESS" and "IBSS" before are re-used as a 2-bit field with 3 valid values (and 1 reserved). Valid values are: "IBSS", "PBSS" (new) and "AP". In order to get the BSS struct for the new PBSS networks, change the cfg80211_get_bss() function to take a new enum ieee80211_bss_type argument with the valid network types, as "capa_mask" and "capa_val" no longer work correctly (the search must be band-aware now.) The remaining bits in "capa_mask" and "capa_val" are used only for privacy matching so replace those two with a privacy enum as well. Signed-off-by: Dedy Lansky [rewrite commit log, tiny fixes] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 39 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 64e09e1e8099..28fff56f5606 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -214,6 +214,39 @@ enum ieee80211_rate_flags { IEEE80211_RATE_SUPPORTS_10MHZ = 1<<6, }; +/** + * enum ieee80211_bss_type - BSS type filter + * + * @IEEE80211_BSS_TYPE_ESS: Infrastructure BSS + * @IEEE80211_BSS_TYPE_PBSS: Personal BSS + * @IEEE80211_BSS_TYPE_IBSS: Independent BSS + * @IEEE80211_BSS_TYPE_MBSS: Mesh BSS + * @IEEE80211_BSS_TYPE_ANY: Wildcard value for matching any BSS type + */ +enum ieee80211_bss_type { + IEEE80211_BSS_TYPE_ESS, + IEEE80211_BSS_TYPE_PBSS, + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_BSS_TYPE_MBSS, + IEEE80211_BSS_TYPE_ANY +}; + +/** + * enum ieee80211_privacy - BSS privacy filter + * + * @IEEE80211_PRIVACY_ON: privacy bit set + * @IEEE80211_PRIVACY_OFF: privacy bit clear + * @IEEE80211_PRIVACY_ANY: Wildcard value for matching any privacy setting + */ +enum ieee80211_privacy { + IEEE80211_PRIVACY_ON, + IEEE80211_PRIVACY_OFF, + IEEE80211_PRIVACY_ANY +}; + +#define IEEE80211_PRIVACY(x) \ + ((x) ? IEEE80211_PRIVACY_ON : IEEE80211_PRIVACY_OFF) + /** * struct ieee80211_rate - bitrate definition * @@ -4012,14 +4045,16 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, - u16 capa_mask, u16 capa_val); + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy); static inline struct cfg80211_bss * cfg80211_get_ibss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *ssid, size_t ssid_len) { return cfg80211_get_bss(wiphy, channel, NULL, ssid, ssid_len, - WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS); + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY_ANY); } /** -- cgit v1.2.3 From ffc1199122d83d60ad99f9c55df32feb650b7bff Mon Sep 17 00:00:00 2001 From: "Janusz.Dziedzic@tieto.com" Date: Sat, 21 Feb 2015 16:52:39 +0100 Subject: cfg80211: add VHT support for IBSS Add NL80211_EXT_FEATURE_VHT_IBSS flag and VHT support for IBSS. Signed-off-by: Janusz Dziedzic Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 2dcf9bba317c..8ee31f108407 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4328,11 +4328,13 @@ enum nl80211_feature_flags { /** * enum nl80211_ext_feature_index - bit index of extended features. + * @NL80211_EXT_FEATURE_VHT_IBSS: This driver supports IBSS with VHT datarates. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ enum nl80211_ext_feature_index { + NL80211_EXT_FEATURE_VHT_IBSS, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 6c09e791b21309a1ad71f9702b766dae12a3cb0a Mon Sep 17 00:00:00 2001 From: Ahmad Kholaif Date: Thu, 26 Feb 2015 15:26:53 +0200 Subject: cfg80211: Allow NL80211_ATTR_IFINDEX to be added to vendor events This modifies cfg80211_vendor_event_alloc() with an additional argument struct wireless_dev *wdev. __cfg80211_alloc_event_skb() is modified to take in *wdev argument, if wdev != NULL, both the NL80211_ATTR_IFINDEX and wdev identifier are added to the vendor event. These changes make it easier for drivers to add ifindex indication in vendor events cleanly. This also updates all existing users of cfg80211_vendor_event_alloc() and __cfg80211_alloc_event_skb() in the kernel tree. Signed-off-by: Ahmad Kholaif Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 28fff56f5606..12a6121ea76e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4295,6 +4295,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, int approxlen); struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, + struct wireless_dev *wdev, enum nl80211_commands cmd, enum nl80211_attrs attr, int vendor_event_idx, @@ -4349,6 +4350,7 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); /** * cfg80211_vendor_event_alloc - allocate vendor-specific event skb * @wiphy: the wiphy + * @wdev: the wireless device * @event_idx: index of the vendor event in the wiphy's vendor_events * @approxlen: an upper bound of the length of the data that will * be put into the skb @@ -4357,16 +4359,20 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); * This function allocates and pre-fills an skb for an event on the * vendor-specific multicast group. * + * If wdev != NULL, both the ifindex and identifier of the specified + * wireless device are added to the event message before the vendor data + * attribute. + * * When done filling the skb, call cfg80211_vendor_event() with the * skb to send the event. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * -cfg80211_vendor_event_alloc(struct wiphy *wiphy, int approxlen, - int event_idx, gfp_t gfp) +cfg80211_vendor_event_alloc(struct wiphy *wiphy, struct wireless_dev *wdev, + int approxlen, int event_idx, gfp_t gfp) { - return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_VENDOR, + return __cfg80211_alloc_event_skb(wiphy, wdev, NL80211_CMD_VENDOR, NL80211_ATTR_VENDOR_DATA, event_idx, approxlen, gfp); } @@ -4467,7 +4473,7 @@ static inline int cfg80211_testmode_reply(struct sk_buff *skb) static inline struct sk_buff * cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, int approxlen, gfp_t gfp) { - return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_TESTMODE, + return __cfg80211_alloc_event_skb(wiphy, NULL, NL80211_CMD_TESTMODE, NL80211_ATTR_TESTDATA, -1, approxlen, gfp); } -- cgit v1.2.3 From 5fc7432991a86678b38a2d700edbe8bcd29cc579 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 27 Feb 2015 15:32:43 +0100 Subject: nl80211: add notes about userspace API/ABI modifications Add notes about userspace ABI/API modifications, including the fact that we decided that API submissions should come with a driver implementation. Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8ee31f108407..90c5aeb3cca7 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -25,6 +25,19 @@ * */ +/* + * This header file defines the userspace API to the wireless stack. Please + * be careful not to break things - i.e. don't move anything around or so + * unless you can demonstrate that it breaks neither API nor ABI. + * + * Additions to the API should be accompanied by actual implementations in + * an upstream driver, so that example implementations exist in case there + * are ever concerns about the precise semantics of the API or changes are + * needed, and to ensure that code for dead (no longer implemented) API + * can actually be identified and removed. + * Nonetheless, semantics should also be documented carefully in this file. + */ + #include #define NL80211_GENL_NAME "nl80211" -- cgit v1.2.3 From 2ecc3905e6c51f545a44cc621216b5dfd7f94c50 Mon Sep 17 00:00:00 2001 From: Alexander Bondar Date: Sun, 1 Mar 2015 09:10:00 +0200 Subject: mac80211: Update beacon's timing and DTIM count on every beacon Beacon's timestamp, device system time associated with this beacon and DTIM count parameters are not updated in the associated vif context if the latest beacon's content is identical to the previously received. It make sense to update these changing parameters on every beacon so the driver can get most updated values. This may be necessary, for example, to avoid either beacons' drift effect or device time stamp overrun. IMPORTANT: Three sync_* parameters - sync_ts, sync_device_ts and sync_dtim_count would possibly be out of sync by the time the driver will use them. The synchronized view is currently guaranteed only in certain callbacks. Signed-off-by: Alexander Bondar Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d52914b75331..3a029f0e303d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -337,12 +337,15 @@ enum ieee80211_rssi_event { * HW flag %IEEE80211_HW_TIMING_BEACON_ONLY is set, then this can * only come from a beacon, but might not become valid until after * association when a beacon is received (which is notified with the - * %BSS_CHANGED_DTIM flag.) + * %BSS_CHANGED_DTIM flag.). See also sync_dtim_count important notice. * @sync_device_ts: the device timestamp corresponding to the sync_tsf, * the driver/device can use this to calculate synchronisation - * (see @sync_tsf) + * (see @sync_tsf). See also sync_dtim_count important notice. * @sync_dtim_count: Only valid when %IEEE80211_HW_TIMING_BEACON_ONLY * is requested, see @sync_tsf/@sync_device_ts. + * IMPORTANT: These three sync_* parameters would possibly be out of sync + * by the time the driver will use them. The synchronized view is currently + * guaranteed only in certain callbacks. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an -- cgit v1.2.3 From 1d5da757da860a6916adbf68b09e868062b4b3b8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 09:41:47 -0600 Subject: ax25: Stop using magic neighbour cache operations. Before the ax25 stack calls dev_queue_xmit it always calls ax25_type_trans which sets skb->protocol to ETH_P_AX25. Which means that by looking at the protocol type it is possible to detect IP packets that have not been munged by the ax25 stack in ndo_start_xmit and call a function to munge them. Rename ax25_neigh_xmit to ax25_ip_xmit and tweak the return type and value to be appropriate for an ndo_start_xmit function. Update all of the ax25 devices to test the protocol type for ETH_P_IP and return ax25_ip_xmit as the first thing they do. This preserves the existing semantics of IP packet processing, but the timing will be a little different as the IP packets now pass through the qdisc layer before reaching the ax25 ip packet processing. Remove the now unnecessary ax25 neighbour table operations. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ax25.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 45feeba7a325..16a923a3a43a 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -367,11 +367,8 @@ int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); /* ax25_ip.c */ -int ax25_neigh_construct(struct neighbour *neigh); +netdev_tx_t ax25_ip_xmit(struct sk_buff *skb); extern const struct header_ops ax25_header_ops; -struct ax25_neigh_priv { - struct neigh_ops ops; -}; /* ax25_out.c */ ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, -- cgit v1.2.3 From 60395a20ffd74166ea373ea91418d6f98fa7fdfb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 17:10:44 -0600 Subject: neigh: Factor out ___neigh_lookup_noref While looking at the mpls code I found myself writing yet another version of neigh_lookup_noref. We currently have __ipv4_lookup_noref and __ipv6_lookup_noref. So to make my work a little easier and to make it a smidge easier to verify/maintain the mpls code in the future I stopped and wrote ___neigh_lookup_noref. Then I rewote __ipv4_lookup_noref and __ipv6_lookup_noref in terms of this new function. I tested my new version by verifying that the same code is generated in ip_finish_output2 and ip6_finish_output2 where these functions are inlined. To get to ___neigh_lookup_noref I added a new neighbour cache table function key_eq. So that the static size of the key would be available. I also added __neigh_lookup_noref for people who want to to lookup a neighbour table entry quickly but don't know which neibhgour table they are going to look up. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/arp.h | 19 ++++-------------- include/net/ndisc.h | 19 +----------------- include/net/neighbour.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 57 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/net/arp.h b/include/net/arp.h index 21ee1860abbc..5e0f891d476c 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -9,28 +9,17 @@ extern struct neigh_table arp_tbl; -static inline u32 arp_hashfn(u32 key, const struct net_device *dev, u32 hash_rnd) +static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { + u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); - return val * hash_rnd; + return val * hash_rnd[0]; } static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { - struct neigh_hash_table *nht = rcu_dereference_bh(arp_tbl.nht); - struct neighbour *n; - u32 hash_val; - - hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift); - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (n->dev == dev && *(u32 *)n->primary_key == key) - return n; - } - - return NULL; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 6bbda34d5e59..b3a7751251b4 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -156,24 +156,7 @@ static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, _ static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { - struct neigh_hash_table *nht; - const u32 *p32 = pkey; - struct neighbour *n; - u32 hash_val; - - nht = rcu_dereference_bh(nd_tbl.nht); - hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - u32 *n32 = (u32 *) n->primary_key; - if (n->dev == dev && - ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | - (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0) - return n; - } - - return NULL; + return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 9f912e4d4232..14e3f017966b 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -197,6 +197,7 @@ struct neigh_table { __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); + bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); @@ -247,6 +248,57 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 + +static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) +{ + return *(const u16 *)n->primary_key == *(const u16 *)pkey; +} + +static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) +{ + return *(const u32 *)n->primary_key == *(const u32 *)pkey; +} + +static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) +{ + const u32 *n32 = (const u32 *)n->primary_key; + const u32 *p32 = pkey; + + return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | + (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; +} + +static inline struct neighbour *___neigh_lookup_noref( + struct neigh_table *tbl, + bool (*key_eq)(const struct neighbour *n, const void *pkey), + __u32 (*hash)(const void *pkey, + const struct net_device *dev, + __u32 *hash_rnd), + const void *pkey, + struct net_device *dev) +{ + struct neigh_hash_table *nht = rcu_dereference_bh(tbl->nht); + struct neighbour *n; + u32 hash_val; + + hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { + if (n->dev == dev && key_eq(n, pkey)) + return n; + } + + return NULL; +} + +static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, + const void *pkey, + struct net_device *dev) +{ + return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); +} + void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, -- cgit v1.2.3 From 4fd3d7d9e868ffbdb0e7a67c5c8e9dfdcd846a62 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 17:11:16 -0600 Subject: neigh: Add helper function neigh_xmit For MPLS I am building the code so that either the neighbour mac address can be specified or we can have a next hop in ipv4 or ipv6. The kind of next hop we have is indicated by the neighbour table pointer. A neighbour table pointer of NULL is a link layer address. A non-NULL neighbour table pointer indicates which neighbour table and thus which address family the next hop address is in that we need to look up. The code either sends a packet directly or looks up the appropriate neighbour table entry and sends the packet. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/neighbour.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 14e3f017966b..afb8237b0a8c 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -358,6 +358,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); +int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); @@ -511,4 +512,6 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } + + #endif -- cgit v1.2.3 From 0189197f441602acdca3f97750d392a895b778fd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 19:10:47 -0600 Subject: mpls: Basic routing support This change adds a new Kconfig option MPLS_ROUTING. The core of this change is the code to look at an mpls packet received from another machine. Look that packet up in a routing table and forward the packet on. Support of MPLS over ATM is not considered or attempted here. This implemntation follows RFC3032 and implements the MPLS shim header that can pass over essentially any network. What RFC3021 refers to as the as the Incoming Label Map (ILM) I call net->mpls.platform_label[]. What RFC3031 refers to as the Next Label Hop Forwarding Entry (NHLFE) I call mpls_route. Though calling it the label fordwarding information base (lfib) might also be valid. Further the implemntation forwards packets as described in RFC3032. There is no need and given the original motivation for MPLS a strong discincentive to have a flexible label forwarding path. In essence the logic is the topmost label is read, looked up, removed, and replaced by 0 or more new lables and the sent out the specified interface to it's next hop. Quite a few optional features are not implemented here. Among them are generation of ICMP errors when the TTL is exceeded or the packet is larger than the next hop MTU (those conditions are detected and the packets are dropped instead of generating an icmp error). The traffic class field is always set to 0. The implementation focuses on IP over MPLS and does not handle egress of other kinds of protocols. Instead of implementing coordination with the neighbour table and sorting out how to input next hops in a different address family (for which there is value). I was lazy and implemented a next hop mac address instead. The code is simpler and there are flavor of MPLS such as MPLS-TP where neither an IPv4 nor an IPv6 next hop is appropriate so a next hop by mac address would need to be implemented at some point. Two new definitions AF_MPLS and PF_MPLS are exposed to userspace. Decoding the mpls header must be done by first byeswapping a 32bit bit endian word into the local cpu endian and then bit shifting to extract the pieces. There is no C bit-field that can represent a wire format mpls header on a little endian machine as the low bits of the 20bit label wind up in the wrong half of third byte. Therefore internally everything is deal with in cpu native byte order except when writing to and reading from a packet. For management simplicity if a label is configured to forward out an interface that is down the packet is dropped early. Similarly if an network interface is removed rt_dev is updated to NULL (so no reference is preserved) and any packets for that label are dropped. Keeping the label entries in the kernel allows the kernel label table to function as the definitive source of which labels are allocated and which are not. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/socket.h | 2 ++ include/net/net_namespace.h | 4 ++++ include/net/netns/mpls.h | 15 +++++++++++++++ 3 files changed, 21 insertions(+) create mode 100644 include/net/netns/mpls.h (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 5c19cba34dce..fab4d0ddf4ed 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -181,6 +181,7 @@ struct ucred { #define AF_WANPIPE 25 /* Wanpipe API Sockets */ #define AF_LLC 26 /* Linux LLC */ #define AF_IB 27 /* Native InfiniBand address */ +#define AF_MPLS 28 /* MPLS */ #define AF_CAN 29 /* Controller Area Network */ #define AF_TIPC 30 /* TIPC sockets */ #define AF_BLUETOOTH 31 /* Bluetooth sockets */ @@ -226,6 +227,7 @@ struct ucred { #define PF_WANPIPE AF_WANPIPE #define PF_LLC AF_LLC #define PF_IB AF_IB +#define PF_MPLS AF_MPLS #define PF_CAN AF_CAN #define PF_TIPC AF_TIPC #define PF_BLUETOOTH AF_BLUETOOTH diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 36faf4990c4b..2cb9acb618e9 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -26,6 +26,7 @@ #endif #include #include +#include #include struct user_namespace; @@ -129,6 +130,9 @@ struct net { #endif #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; +#endif +#if IS_ENABLED(CONFIG_MPLS) + struct netns_mpls mpls; #endif struct sock *diag_nlsk; atomic_t fnhe_genid; diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h new file mode 100644 index 000000000000..f90aaf8d4f89 --- /dev/null +++ b/include/net/netns/mpls.h @@ -0,0 +1,15 @@ +/* + * mpls in net namespaces + */ + +#ifndef __NETNS_MPLS_H__ +#define __NETNS_MPLS_H__ + +struct mpls_route; + +struct netns_mpls { + size_t platform_labels; + struct mpls_route __rcu * __rcu *platform_label; +}; + +#endif /* __NETNS_MPLS_H__ */ -- cgit v1.2.3 From 7720c01f3f590116882e251f13c7e1d5602f8643 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 19:11:20 -0600 Subject: mpls: Add a sysctl to control the size of the mpls label table This sysctl gives two benefits. By defaulting the table size to 0 mpls even when compiled in and enabled defaults to not forwarding any packets. This prevents unpleasant surprises for users. The other benefit is that as mpls labels are allocated locally a dense table a small dense label table may be used which saves memory and is extremely simple and efficient to implement. This sysctl allows userspace to choose the restrictions on the label table size userspace applications need to cope with. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/netns/mpls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index f90aaf8d4f89..d29203651c01 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -6,10 +6,12 @@ #define __NETNS_MPLS_H__ struct mpls_route; +struct ctl_table_header; struct netns_mpls { size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; + struct ctl_table_header *ctl; }; #endif /* __NETNS_MPLS_H__ */ -- cgit v1.2.3 From 03c0566542f4c7a45ce3193f27cbf5700b506c18 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 19:13:56 -0600 Subject: mpls: Netlink commands to add, remove, and dump routes This change adds two new netlink routing attributes: RTA_VIA and RTA_NEWDST. RTA_VIA specifies the specifies the next machine to send a packet to like RTA_GATEWAY. RTA_VIA differs from RTA_GATEWAY in that it includes the address family of the address of the next machine to send a packet to. Currently the MPLS code supports addresses in AF_INET, AF_INET6 and AF_PACKET. For AF_INET and AF_INET6 the destination mac address is acquired from the neighbour table. For AF_PACKET the destination mac_address is specified in the netlink configuration. I think raw destination mac address support with the family AF_PACKET will prove useful. There is MPLS-TP which is defined to operate on machines that do not support internet packets of any flavor. Further seem to be corner cases where it can be useful. At this point I don't care much either way. RTA_NEWDST specifies the destination address to forward the packet with. MPLS typically changes it's destination address at every hop. For a swap operation RTA_NEWDST is specified with a length of one label. For a push operation RTA_NEWDST is specified with two or more labels. For a pop operation RTA_NEWDST is not specified or equivalently an emtpy RTAN_NEWDST is specified. Those new netlink attributes are used to implement handling of rt-netlink RTM_NEWROUTE, RTM_DELROUTE, and RTM_GETROUTE messages, to maintain the MPLS label table. rtm_to_route_config parses a netlink RTM_NEWROUTE or RTM_DELROUTE message, verify no unhandled attributes or unhandled values are present and sets up the data structures for mpls_route_add and mpls_route_del. I did my best to match up with the existing conventions with the caveats that MPLS addresses are all destination-specific-addresses, and so don't properly have a scope. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 5cc5d66bf519..bad65550ae3e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -303,6 +303,8 @@ enum rtattr_type_t { RTA_TABLE, RTA_MARK, RTA_MFC_STATS, + RTA_VIA, + RTA_NEWDST, __RTA_MAX }; @@ -344,6 +346,12 @@ struct rtnexthop { #define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len)) #define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0))) +/* RTA_VIA */ +struct rtvia { + __kernel_sa_family_t rtvia_family; + __u8 rtvia_addr[0]; +}; + /* RTM_CACHEINFO */ struct rta_cacheinfo { -- cgit v1.2.3 From 8de147dc8e2adea82b8a1a2a08fcc983330f6770 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 3 Mar 2015 19:14:31 -0600 Subject: mpls: Multicast route table change notifications Unlike IPv4 this code notifies on all cases where mpls routes are added or removed and it never automatically removes routes. Avoiding both the userspace confusion that is caused by omitting route updates and the possibility of a flood of netlink traffic when an interface goes doew. For now reserved labels are handled automatically and userspace is not notified. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index bad65550ae3e..06f75a407f74 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -631,6 +631,8 @@ enum rtnetlink_groups { #define RTNLGRP_IPV6_NETCONF RTNLGRP_IPV6_NETCONF RTNLGRP_MDB, #define RTNLGRP_MDB RTNLGRP_MDB + RTNLGRP_MPLS_ROUTE, +#define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From 98fc43864af9e74116eec81c290db048cded15d8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 1 Mar 2015 09:10:13 +0200 Subject: nl80211: prohibit mixing 'any' and regular wowlan triggers If the device supports waking up on 'any' signal - i.e. it continues operating as usual and wakes up the host on pretty much anything that happens, then it makes no sense to also configure the more restricted WoWLAN mode where the device operates more autonomously but also in a more restricted fashion. Currently only cw2100 supports both 'any' and other triggers, but it seems to be broken as it doesn't configure anything to the device, so we can't currently get into a situation where both even can correctly be configured. This is about to change (Intel devices are going to support both and have different behaviour depending on configuration) so make sure the conflicting modes cannot be configured. (It seems that cw2100 advertises 'any' and 'disconnect' as a means of saying that's what it will always do, but that isn't really the way this API was meant to be used nor does it actually mean anything as 'any' always implies 'disconnect' already, and the driver doesn't change device configuration in any way depending on the settings.) Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 90c5aeb3cca7..37e7f39441e5 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3708,6 +3708,8 @@ struct nl80211_pattern_support { * @NL80211_WOWLAN_TRIG_ANY: wake up on any activity, do not really put * the chip into a special state -- works best with chips that have * support for low-power operation already (flag) + * Note that this mode is incompatible with all of the others, if + * any others are even supported by the device. * @NL80211_WOWLAN_TRIG_DISCONNECT: wake up on disconnect, the way disconnect * is detected is implementation-specific (flag) * @NL80211_WOWLAN_TRIG_MAGIC_PKT: wake up on magic packet (6x 0xff, followed -- cgit v1.2.3 From 3384d757d41521a3dee274ed2802bcd285ed8e62 Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Sun, 1 Mar 2015 09:10:15 +0200 Subject: mac80211: allow iterating inactive interfaces Sometimes the driver might want to modify private data in interfaces that are down. One possible use-case is cleaning up interface state after HW recovery. Some interfaces that were up before the recovery took place might be down now, but they might still be "dirty". Introduce a new iterate_interfaces() API and a new ACTIVE iterator flag. This way the internal implementation of the both active and inactive APIs remains the same. Signed-off-by: Arik Nemtsov Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3a029f0e303d..d1d6fbc13b1c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4346,12 +4346,32 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw); * haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all * interfaces, even if they haven't been re-added to the driver yet. + * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up). */ enum ieee80211_interface_iteration_flags { IEEE80211_IFACE_ITER_NORMAL = 0, IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0), + IEEE80211_IFACE_ITER_ACTIVE = BIT(1), }; +/** + * ieee80211_iterate_interfaces - iterate interfaces + * + * This function iterates over the interfaces associated with a given + * hardware and calls the callback for them. This includes active as well as + * inactive interfaces. This function allows the iterator function to sleep. + * Will iterate over a new interface during add_interface(). + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags + * @iterator: the iterator function to call + * @data: first argument of the iterator function + */ +void ieee80211_iterate_interfaces(struct ieee80211_hw *hw, u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data); + /** * ieee80211_iterate_active_interfaces - iterate active interfaces * @@ -4367,11 +4387,16 @@ enum ieee80211_interface_iteration_flags { * @iterator: the iterator function to call * @data: first argument of the iterator function */ -void ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw, - u32 iter_flags, - void (*iterator)(void *data, u8 *mac, - struct ieee80211_vif *vif), - void *data); +static inline void +ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw, u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data) +{ + ieee80211_iterate_interfaces(hw, + iter_flags | IEEE80211_IFACE_ITER_ACTIVE, + iterator, data); +} /** * ieee80211_iterate_active_interfaces_atomic - iterate active interfaces -- cgit v1.2.3 From 64a8cef41a8ce694b59ec75ae52688f58925693c Mon Sep 17 00:00:00 2001 From: SenthilKumar Jegadeesan Date: Mon, 2 Mar 2015 13:29:40 +0530 Subject: mac80211: provide station PMF configuration to driver Some device drivers offload part of aggregation including AddBA/DelBA negotiations to firmware. In such scenario, the PMF configuration of the station needs to be provided to driver to enable encryption of AddBA/DelBA action frames. Signed-off-by: SenthilKumar Jegadeesan [fix commit log, documentation] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d1d6fbc13b1c..a7756e45465e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1491,6 +1491,7 @@ struct ieee80211_sta_rates { * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. + * @mfp: indicates whether the STA uses management frame protection or not. */ struct ieee80211_sta { u32 supp_rates[IEEE80211_NUM_BANDS]; @@ -1507,6 +1508,7 @@ struct ieee80211_sta { struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; + bool mfp; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); -- cgit v1.2.3 From a7e53531234dc206bb75abb5305a72665dd4d75d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 4 Mar 2015 15:02:44 -0800 Subject: fib_trie: Make fib_table rcu safe The fib_table was wrapped in several places with an rcu_read_lock/rcu_read_unlock however after looking over the code I found several spots where the tables were being accessed as just standard pointers without any protections. This change fixes that so that all of the proper protections are in place when accessing the table to take RCU replacement or removal of the table into account. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ip_fib.h | 70 +++++++++++++++++++++++++++++------------------- include/net/netns/ipv4.h | 7 ++--- 2 files changed, 46 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index cba4b7c32935..825cb2800908 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -185,6 +185,7 @@ struct fib_table { u32 tb_id; int tb_default; int tb_num_default; + struct rcu_head rcu; unsigned long tb_data[0]; }; @@ -206,12 +207,16 @@ void fib_free_table(struct fib_table *tb); static inline struct fib_table *fib_get_table(struct net *net, u32 id) { + struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; - return hlist_entry(ptr->first, struct fib_table, tb_hlist); + + tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); + + return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) @@ -222,15 +227,19 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id) static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res) { - int err = -ENETUNREACH; + struct fib_table *tb; + int err; rcu_read_lock(); - if (!fib_table_lookup(fib_get_table(net, RT_TABLE_LOCAL), flp, res, - FIB_LOOKUP_NOREF) || - !fib_table_lookup(fib_get_table(net, RT_TABLE_MAIN), flp, res, - FIB_LOOKUP_NOREF)) - err = 0; + for (err = 0; !err; err = -ENETUNREACH) { + tb = fib_get_table(net, RT_TABLE_LOCAL); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; + tb = fib_get_table(net, RT_TABLE_MAIN); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; + } rcu_read_unlock(); @@ -249,28 +258,33 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) { - if (!net->ipv4.fib_has_custom_rules) { - int err = -ENETUNREACH; - - rcu_read_lock(); - - res->tclassid = 0; - if ((net->ipv4.fib_local && - !fib_table_lookup(net->ipv4.fib_local, flp, res, - FIB_LOOKUP_NOREF)) || - (net->ipv4.fib_main && - !fib_table_lookup(net->ipv4.fib_main, flp, res, - FIB_LOOKUP_NOREF)) || - (net->ipv4.fib_default && - !fib_table_lookup(net->ipv4.fib_default, flp, res, - FIB_LOOKUP_NOREF))) - err = 0; - - rcu_read_unlock(); - - return err; + struct fib_table *tb; + int err; + + if (net->ipv4.fib_has_custom_rules) + return __fib_lookup(net, flp, res); + + rcu_read_lock(); + + res->tclassid = 0; + + for (err = 0; !err; err = -ENETUNREACH) { + tb = rcu_dereference_rtnl(net->ipv4.fib_local); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; + + tb = rcu_dereference_rtnl(net->ipv4.fib_main); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; + + tb = rcu_dereference_rtnl(net->ipv4.fib_default); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; } - return __fib_lookup(net, flp, res); + + rcu_read_unlock(); + + return err; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1b26c6c3fd7c..db1db158a00e 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -7,6 +7,7 @@ #include #include +#include struct tcpm_hash_bucket; struct ctl_table_header; @@ -38,9 +39,9 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rules_ops *rules_ops; bool fib_has_custom_rules; - struct fib_table *fib_local; - struct fib_table *fib_main; - struct fib_table *fib_default; + struct fib_table __rcu *fib_local; + struct fib_table __rcu *fib_main; + struct fib_table __rcu *fib_default; #endif #ifdef CONFIG_IP_ROUTE_CLASSID int fib_num_tclassid_users; -- cgit v1.2.3 From 82f8b651a94d5c7090563fe55cfdb286c461a16c Mon Sep 17 00:00:00 2001 From: Jakub Pawlowski Date: Wed, 4 Mar 2015 16:24:26 -0800 Subject: Bluetooth: fix service discovery behaviour for empty uuids filter This patch fixes service discovery behaviour, when provided uuid filter is empty and HCI_QUIRK_STRICT_DUPLICATE_FILTER is set. Before this patch, empty uuid filter was unable to trigger scan restart, and that caused inconsistent behaviour in applications. Example: two DBus clients call BlueZ, one to find all devices with service abcd, second to find all devices with rssi smaller than -90. Sum of those filters, that is passed to mgmt_service_scan is empty filter, with no rssi or uuids set. That caused kernel not to restart scan when quirk was set. That was inconsistent with what happen when there's only one of those two filters set (scan is restarted and reports devices). To fix that, new variable hdev->discovery.result_filtering was introduced. It can indicate that filtered scan is running, no matter what uuid or rssi filter is set. Signed-off-by: Jakub Pawlowski Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index acec9140c3f9..15c761c1f82a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -76,6 +76,7 @@ struct discovery_state { u8 last_adv_data[HCI_MAX_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; + bool result_filtering; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; @@ -525,6 +526,7 @@ static inline void discovery_init(struct hci_dev *hdev) static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { + hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; -- cgit v1.2.3 From c32ec2a11321978c34296d9a6bd5b0c31a2eb182 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 4 Mar 2015 12:14:41 +0100 Subject: bcma: make bcma_host_pci_(up|down) calls safe for every config MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We were providing declarations but actual code was compiled only with CONFIG_BCMA_HOST_PCI set. This could result in: ERROR: "bcma_host_pci_down" [drivers/net/wireless/brcm80211/brcmsmac/brcmsmac.ko] undefined! ERROR: "bcma_host_pci_up" [drivers/net/wireless/brcm80211/brcmsmac/brcmsmac.ko] undefined! ERROR: "bcma_host_pci_down" [drivers/net/wireless/b43/b43.ko] undefined! ERROR: "bcma_host_pci_up" [drivers/net/wireless/b43/b43.ko] undefined! Reported-by: Arnd Bergmann Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 037620b3f113..44057b45ed32 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -434,8 +434,17 @@ static inline struct bcma_device *bcma_find_core(struct bcma_bus *bus, return bcma_find_core_unit(bus, coreid, 0); } +#ifdef CONFIG_BCMA_HOST_PCI extern void bcma_host_pci_up(struct bcma_bus *bus); extern void bcma_host_pci_down(struct bcma_bus *bus); +#else +static inline void bcma_host_pci_up(struct bcma_bus *bus) +{ +} +static inline void bcma_host_pci_down(struct bcma_bus *bus) +{ +} +#endif extern bool bcma_core_is_enabled(struct bcma_device *core); extern void bcma_core_disable(struct bcma_device *core, u32 flags); -- cgit v1.2.3 From 0a4e699a41f767dff76ca7dc1019b9ca6de3eb42 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 4 Mar 2015 14:24:52 +0100 Subject: bcma: move internal function declarations to private header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These functions are not exported nor used anywhere, so there is no reason to put them in public headers. Also drop unused bcma_chipco_(suspend|resume). Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 11 ----------- include/linux/bcma/bcma_driver_gmac_cmn.h | 6 ------ include/linux/bcma/bcma_driver_mips.h | 15 --------------- include/linux/bcma/bcma_driver_pci.h | 2 -- include/linux/bcma/bcma_driver_pcie2.h | 2 -- 5 files changed, 36 deletions(-) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index db6fa217f98b..6cceedf65ca2 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -663,14 +663,6 @@ struct bcma_drv_cc_b { #define bcma_cc_maskset32(cc, offset, mask, set) \ bcma_cc_write32(cc, offset, (bcma_cc_read32(cc, offset) & (mask)) | (set)) -extern void bcma_core_chipcommon_init(struct bcma_drv_cc *cc); -extern void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc); - -extern void bcma_chipco_suspend(struct bcma_drv_cc *cc); -extern void bcma_chipco_resume(struct bcma_drv_cc *cc); - -void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable); - extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks); extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc); @@ -690,9 +682,6 @@ u32 bcma_chipco_gpio_pullup(struct bcma_drv_cc *cc, u32 mask, u32 value); u32 bcma_chipco_gpio_pulldown(struct bcma_drv_cc *cc, u32 mask, u32 value); /* PMU support */ -extern void bcma_pmu_init(struct bcma_drv_cc *cc); -extern void bcma_pmu_early_init(struct bcma_drv_cc *cc); - extern void bcma_chipco_pll_write(struct bcma_drv_cc *cc, u32 offset, u32 value); extern void bcma_chipco_pll_maskset(struct bcma_drv_cc *cc, u32 offset, diff --git a/include/linux/bcma/bcma_driver_gmac_cmn.h b/include/linux/bcma/bcma_driver_gmac_cmn.h index 4dd1f33e36a2..4354d4ea6713 100644 --- a/include/linux/bcma/bcma_driver_gmac_cmn.h +++ b/include/linux/bcma/bcma_driver_gmac_cmn.h @@ -91,10 +91,4 @@ struct bcma_drv_gmac_cmn { #define gmac_cmn_write16(gc, offset, val) bcma_write16((gc)->core, offset, val) #define gmac_cmn_write32(gc, offset, val) bcma_write32((gc)->core, offset, val) -#ifdef CONFIG_BCMA_DRIVER_GMAC_CMN -extern void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc); -#else -static inline void bcma_core_gmac_cmn_init(struct bcma_drv_gmac_cmn *gc) { } -#endif - #endif /* LINUX_BCMA_DRIVER_GMAC_CMN_H_ */ diff --git a/include/linux/bcma/bcma_driver_mips.h b/include/linux/bcma/bcma_driver_mips.h index 0b3b32aeeb8a..8eea7f9e33b4 100644 --- a/include/linux/bcma/bcma_driver_mips.h +++ b/include/linux/bcma/bcma_driver_mips.h @@ -39,21 +39,6 @@ struct bcma_drv_mips { u8 early_setup_done:1; }; -#ifdef CONFIG_BCMA_DRIVER_MIPS -extern void bcma_core_mips_init(struct bcma_drv_mips *mcore); -extern void bcma_core_mips_early_init(struct bcma_drv_mips *mcore); - -extern unsigned int bcma_core_mips_irq(struct bcma_device *dev); -#else -static inline void bcma_core_mips_init(struct bcma_drv_mips *mcore) { } -static inline void bcma_core_mips_early_init(struct bcma_drv_mips *mcore) { } - -static inline unsigned int bcma_core_mips_irq(struct bcma_device *dev) -{ - return 0; -} -#endif - extern u32 bcma_cpu_clock(struct bcma_drv_mips *mcore); #endif /* LINUX_BCMA_DRIVER_MIPS_H_ */ diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 6b8bca67851f..8e90004fdfd7 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -238,8 +238,6 @@ struct bcma_drv_pci { #define pcicore_write16(pc, offset, val) bcma_write16((pc)->core, offset, val) #define pcicore_write32(pc, offset, val) bcma_write32((pc)->core, offset, val) -extern void bcma_core_pci_early_init(struct bcma_drv_pci *pc); -extern void bcma_core_pci_init(struct bcma_drv_pci *pc); extern int bcma_core_pci_irq_ctl(struct bcma_bus *bus, struct bcma_device *core, bool enable); extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); diff --git a/include/linux/bcma/bcma_driver_pcie2.h b/include/linux/bcma/bcma_driver_pcie2.h index d8c43294c527..31e6d17ab798 100644 --- a/include/linux/bcma/bcma_driver_pcie2.h +++ b/include/linux/bcma/bcma_driver_pcie2.h @@ -155,6 +155,4 @@ struct bcma_drv_pcie2 { #define pcie2_set32(pcie2, offset, set) bcma_set32((pcie2)->core, offset, set) #define pcie2_mask32(pcie2, offset, mask) bcma_mask32((pcie2)->core, offset, mask) -void bcma_core_pcie2_init(struct bcma_drv_pcie2 *pcie2); - #endif /* LINUX_BCMA_DRIVER_PCIE2_H_ */ -- cgit v1.2.3 From 842a9ae08a25671db3d4f689eed68b4d64be15b5 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Wed, 4 Mar 2015 12:54:21 +0200 Subject: bridge: Extend Proxy ARP design to allow optional rules for Wi-Fi This extends the design in commit 958501163ddd ("bridge: Add support for IEEE 802.11 Proxy ARP") with optional set of rules that are needed to meet the IEEE 802.11 and Hotspot 2.0 requirements for ProxyARP. The previously added BR_PROXYARP behavior is left as-is and a new BR_PROXYARP_WIFI alternative is added so that this behavior can be configured from user space when required. In addition, this enables proxyarp functionality for unicast ARP requests for both BR_PROXYARP and BR_PROXYARP_WIFI since it is possible to use unicast as well as broadcast for these frames. The key differences in functionality: BR_PROXYARP: - uses the flag on the bridge port on which the request frame was received to determine whether to reply - block bridge port flooding completely on ports that enable proxy ARP BR_PROXYARP_WIFI: - uses the flag on the bridge port to which the target device of the request belongs - block bridge port flooding selectively based on whether the proxyarp functionality replied Signed-off-by: Jouni Malinen Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index a57bca2ea97e..dad8b00beed2 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -44,6 +44,7 @@ struct br_ip_list { #define BR_PROMISC BIT(7) #define BR_PROXYARP BIT(8) #define BR_LEARNING_SYNC BIT(9) +#define BR_PROXYARP_WIFI BIT(10) extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index dfd0bb22e554..756436e1ce89 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -247,6 +247,7 @@ enum { IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ IFLA_BRPORT_PROXYARP, /* proxy ARP */ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 43270b1bc5f1e33522dacf3d3b9175c29404c36c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 2 Mar 2015 14:40:39 +0100 Subject: netfilter: ipt_CLUSTERIP: deprecate it in favour of xt_cluster xt_cluster supersedes ipt_CLUSTERIP since it can be also used in gateway configurations (not only from the backend side). ipt_CLUSTER is also known to leak the netdev that it uses on device removal, which requires a rather large fix to workaround the problem: http://patchwork.ozlabs.org/patch/358629/ So let's deprecate this so we can probably kill code this in the future. Signed-off-by: Pablo Neira Ayuso --- include/net/netns/x_tables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h index c24060ee411e..4d6597ad6067 100644 --- a/include/net/netns/x_tables.h +++ b/include/net/netns/x_tables.h @@ -9,6 +9,7 @@ struct ebt_table; struct netns_xt { struct list_head tables[NFPROTO_NUMPROTO]; bool notrack_deprecated_warning; + bool clusterip_deprecated_warning; #if defined(CONFIG_BRIDGE_NF_EBTABLES) || \ defined(CONFIG_BRIDGE_NF_EBTABLES_MODULE) struct ebt_table *broute_table; -- cgit v1.2.3 From 1a1e1a12199ca27cebe87677b4c2153a3d2bacf2 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 3 Mar 2015 20:10:06 +0000 Subject: netfilter: nf_tables: cleanup nf_tables.h The transaction related definitions are squeezed in between the rule and expression definitions, which are closely related and should be next to each other. The transaction definitions actually don't belong into that file at all since it defines the global objects and API and transactions are internal to nf_tables_api, but for now simply move them to a seperate section. Similar, the chain types are in between a set of registration functions, they belong to the chain section. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 174 +++++++++++++++++++------------------- 1 file changed, 87 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9eaaa7884586..04188b47629d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -393,74 +393,6 @@ struct nft_rule { __attribute__((aligned(__alignof__(struct nft_expr)))); }; -/** - * struct nft_trans - nf_tables object update in transaction - * - * @list: used internally - * @msg_type: message type - * @ctx: transaction context - * @data: internal information related to the transaction - */ -struct nft_trans { - struct list_head list; - int msg_type; - struct nft_ctx ctx; - char data[0]; -}; - -struct nft_trans_rule { - struct nft_rule *rule; -}; - -#define nft_trans_rule(trans) \ - (((struct nft_trans_rule *)trans->data)->rule) - -struct nft_trans_set { - struct nft_set *set; - u32 set_id; -}; - -#define nft_trans_set(trans) \ - (((struct nft_trans_set *)trans->data)->set) -#define nft_trans_set_id(trans) \ - (((struct nft_trans_set *)trans->data)->set_id) - -struct nft_trans_chain { - bool update; - char name[NFT_CHAIN_MAXNAMELEN]; - struct nft_stats __percpu *stats; - u8 policy; -}; - -#define nft_trans_chain_update(trans) \ - (((struct nft_trans_chain *)trans->data)->update) -#define nft_trans_chain_name(trans) \ - (((struct nft_trans_chain *)trans->data)->name) -#define nft_trans_chain_stats(trans) \ - (((struct nft_trans_chain *)trans->data)->stats) -#define nft_trans_chain_policy(trans) \ - (((struct nft_trans_chain *)trans->data)->policy) - -struct nft_trans_table { - bool update; - bool enable; -}; - -#define nft_trans_table_update(trans) \ - (((struct nft_trans_table *)trans->data)->update) -#define nft_trans_table_enable(trans) \ - (((struct nft_trans_table *)trans->data)->enable) - -struct nft_trans_elem { - struct nft_set *set; - struct nft_set_elem elem; -}; - -#define nft_trans_elem_set(trans) \ - (((struct nft_trans_elem *)trans->data)->set) -#define nft_trans_elem(trans) \ - (((struct nft_trans_elem *)trans->data)->elem) - static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; @@ -528,6 +460,25 @@ enum nft_chain_type { NFT_CHAIN_T_MAX }; +/** + * struct nf_chain_type - nf_tables chain type info + * + * @name: name of the type + * @type: numeric identifier + * @family: address family + * @owner: module owner + * @hook_mask: mask of valid hooks + * @hooks: hookfn overrides + */ +struct nf_chain_type { + const char *name; + enum nft_chain_type type; + int family; + struct module *owner; + unsigned int hook_mask; + nf_hookfn *hooks[NF_MAX_HOOKS]; +}; + int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_type type); int nft_chain_validate_hooks(const struct nft_chain *chain, @@ -614,25 +565,6 @@ struct nft_af_info { int nft_register_afinfo(struct net *, struct nft_af_info *); void nft_unregister_afinfo(struct nft_af_info *); -/** - * struct nf_chain_type - nf_tables chain type info - * - * @name: name of the type - * @type: numeric identifier - * @family: address family - * @owner: module owner - * @hook_mask: mask of valid hooks - * @hooks: hookfn overrides - */ -struct nf_chain_type { - const char *name; - enum nft_chain_type type; - int family; - struct module *owner; - unsigned int hook_mask; - nf_hookfn *hooks[NF_MAX_HOOKS]; -}; - int nft_register_chain_type(const struct nf_chain_type *); void nft_unregister_chain_type(const struct nf_chain_type *); @@ -657,4 +589,72 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +/** + * struct nft_trans - nf_tables object update in transaction + * + * @list: used internally + * @msg_type: message type + * @ctx: transaction context + * @data: internal information related to the transaction + */ +struct nft_trans { + struct list_head list; + int msg_type; + struct nft_ctx ctx; + char data[0]; +}; + +struct nft_trans_rule { + struct nft_rule *rule; +}; + +#define nft_trans_rule(trans) \ + (((struct nft_trans_rule *)trans->data)->rule) + +struct nft_trans_set { + struct nft_set *set; + u32 set_id; +}; + +#define nft_trans_set(trans) \ + (((struct nft_trans_set *)trans->data)->set) +#define nft_trans_set_id(trans) \ + (((struct nft_trans_set *)trans->data)->set_id) + +struct nft_trans_chain { + bool update; + char name[NFT_CHAIN_MAXNAMELEN]; + struct nft_stats __percpu *stats; + u8 policy; +}; + +#define nft_trans_chain_update(trans) \ + (((struct nft_trans_chain *)trans->data)->update) +#define nft_trans_chain_name(trans) \ + (((struct nft_trans_chain *)trans->data)->name) +#define nft_trans_chain_stats(trans) \ + (((struct nft_trans_chain *)trans->data)->stats) +#define nft_trans_chain_policy(trans) \ + (((struct nft_trans_chain *)trans->data)->policy) + +struct nft_trans_table { + bool update; + bool enable; +}; + +#define nft_trans_table_update(trans) \ + (((struct nft_trans_table *)trans->data)->update) +#define nft_trans_table_enable(trans) \ + (((struct nft_trans_table *)trans->data)->enable) + +struct nft_trans_elem { + struct nft_set *set; + struct nft_set_elem elem; +}; + +#define nft_trans_elem_set(trans) \ + (((struct nft_trans_elem *)trans->data)->set) +#define nft_trans_elem(trans) \ + (((struct nft_trans_elem *)trans->data)->elem) + #endif /* _NET_NF_TABLES_H */ -- cgit v1.2.3 From 1cae565e8b746f484f1ff1b71d2a1c89d7cf0668 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 5 Mar 2015 15:05:36 +0100 Subject: netfilter: nf_tables: limit maximum table name length to 32 bytes Set the same as we use for chain names, it should be enough. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 04188b47629d..a143acafa5d9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -535,7 +535,7 @@ struct nft_table { u64 hgenerator; u32 use; u16 flags; - char name[]; + char name[NFT_TABLE_MAXNAMELEN]; }; /** diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 832bc46db78b..b9783931503b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1,6 +1,7 @@ #ifndef _LINUX_NF_TABLES_H #define _LINUX_NF_TABLES_H +#define NFT_TABLE_MAXNAMELEN 32 #define NFT_CHAIN_MAXNAMELEN 32 #define NFT_USERDATA_MAXLEN 256 -- cgit v1.2.3 From d0f91938bede204a343473792529e0db7d599836 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Thu, 5 Mar 2015 10:23:49 +0100 Subject: tipc: add ip/udp media type The ip/udp bearer can be configured in a point-to-point mode by specifying both local and remote ip/hostname, or it can be enabled in multicast mode, where links are established to all tipc nodes that have joined the same multicast group. The multicast IP address is generated based on the TIPC network ID, but can be overridden by using another multicast address as remote ip. Signed-off-by: Erik Hugne Reviewed-by: Jon Maloy Reviewed-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index 8d723824ad69..d4c8f142ba63 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -83,11 +83,20 @@ enum { TIPC_NLA_BEARER_NAME, /* string */ TIPC_NLA_BEARER_PROP, /* nest */ TIPC_NLA_BEARER_DOMAIN, /* u32 */ + TIPC_NLA_BEARER_UDP_OPTS, /* nest */ __TIPC_NLA_BEARER_MAX, TIPC_NLA_BEARER_MAX = __TIPC_NLA_BEARER_MAX - 1 }; +enum { + TIPC_NLA_UDP_UNSPEC, + TIPC_NLA_UDP_LOCAL, /* sockaddr_storage */ + TIPC_NLA_UDP_REMOTE, /* sockaddr_storage */ + + __TIPC_NLA_UDP_MAX, + TIPC_NLA_UDP_MAX = __TIPC_NLA_UDP_MAX - 1 +}; /* Socket info */ enum { TIPC_NLA_SOCK_UNSPEC, -- cgit v1.2.3 From 59299031038f3ea92cf484bc4a68d16ad4bb3050 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 5 Mar 2015 12:35:07 -0800 Subject: net: dsa: let switches specify their tagging protocol In order to support the new DSA device driver model, a dsa_switch should be able to advertise the type of tagging protocol supported by the underlying switch device. This also removes constraints on how tagging can be stacked to each other. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index c542c131d551..b525ac516559 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -127,6 +127,11 @@ struct dsa_switch { struct dsa_switch_tree *dst; int index; + /* + * Tagging protocol understood by this switch + */ + enum dsa_tag_protocol tag_protocol; + /* * Configuration data for this switch. */ -- cgit v1.2.3 From 37ed9493699cc5dafe1b8725858ef73176fdc9d2 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:13 -0800 Subject: rtnetlink: add RTNH_F_EXTERNAL flag for fib offload Add new RTNH_F_EXTERNAL flag to mark fib entries offloaded externally, for example to a switchdev switch device. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 06f75a407f74..c3722b024e73 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -334,6 +334,7 @@ struct rtnexthop { #define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ #define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ #define RTNH_F_ONLINK 4 /* Gateway is forced on link */ +#define RTNH_F_EXTERNAL 8 /* Route installed externally */ /* Macros to handle hexthops */ -- cgit v1.2.3 From 4586f1bb911ce219a4bc1c2a9d6eee2e058b2b51 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:14 -0800 Subject: netdevice: add IPv4 fib add/del ops Add two new ndo ops for IPv4 fib offload support, add and del. Add uses modifiy semantics if fib entry already offloaded. Drivers implementing the new ndo ops will return err<0 if programming device fails, for example if device's tables are full. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 625c8d71511b..45413784a3b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,6 +768,8 @@ struct netdev_phys_item_id { typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); +struct fib_info; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1031,6 +1033,14 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); * Called to notify switch device port of bridge port STP * state change. + * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to add/modify IPv4 route to switch device. + * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to delete IPv4 route from switch device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1192,6 +1202,18 @@ struct net_device_ops { struct netdev_phys_item_id *psid); int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); + int (*ndo_switch_fib_ipv4_add)(struct net_device *dev, + __be32 dst, + int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 tb_id); + int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, + __be32 dst, + int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 tb_id); #endif }; -- cgit v1.2.3 From 5e8d90497d65f528c54015644095ace6e330fd8e Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:15 -0800 Subject: switchdev: add IPv4 fib ndo ops wrappers Add IPv4 fib ndo wrapper funcs and stub them out for now. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/switchdev.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index cfcdac2e5d25..8d2ac663325a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -51,6 +51,11 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); +int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); + #else static inline int netdev_switch_parent_id_get(struct net_device *dev, @@ -109,6 +114,20 @@ static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device * return 0; } +static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + return 0; +} + +static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + return 0; +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ -- cgit v1.2.3 From 104616e74e0b464d449fdd2ee2f547d2fad71610 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:16 -0800 Subject: switchdev: don't support custom ip rules, for now Keep switchdev FIB offload model simple for now and don't allow custom ip rules. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 825cb2800908..1657604c5dd3 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -196,6 +196,7 @@ int fib_table_delete(struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct fib_table *table); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); @@ -308,6 +309,7 @@ static inline int fib_num_tclassid_users(struct net *net) return 0; } #endif +void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); -- cgit v1.2.3 From 448b128a14501543748514a4f9adedd3c0da2e85 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:18 -0800 Subject: ipv4: add net bool fib_offload_disabled If something goes wrong with IPv4 FIB offload, mark entire net offload disabled. This is brute force policy to basically shut down IPv4 FIB offload permanently if there is a problem offloading any route to an external device. We can refine the policy in the future, to handle failures on a per-device or per-route basis, but for now, this policy is per-net. What we're trying to avoid is an inconsistent split between the kernel's FIB and the offload device's FIB. We don't want the device to fwd a pkt inconsitent with what the kernel would do. An example of a split is if device has 10.0.0.0/16 and kernel has 10.0.0.0/16 and 10.0.0.0/24, the device wouldn't see the longest prefix 10.0.0.0/24 and potentially forward pkts incorrectly. Limited capacity or limited capability are two ways a route may fail to install to the offload device. We'll not differentiate between failures at this time, and treat any failure as fatal and mark the net as fib_offload_disabled. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index db1db158a00e..1085e12f940f 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -47,6 +47,7 @@ struct netns_ipv4 { int fib_num_tclassid_users; #endif struct hlist_head *fib_table_hash; + bool fib_offload_disabled; struct sock *fibnl; struct sock * __percpu *icmp_sk; -- cgit v1.2.3 From 8e05fd7166c6123334b7a739a697d677747aa462 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 5 Mar 2015 21:21:19 -0800 Subject: fib: hook IPv4 fib for hardware offload Call into the switchdev driver any time an IPv4 fib entry is added/modified/deleted from the kernel's FIB. The switchdev driver may or may not install the route to the offload device. In the case where the driver tries to install the route and something goes wrong (device's routing table is full, etc), then all of the offloaded routes will be flushed from the device, route forwarding falls back to the kernel, and no more routes are offloading. We can refine this logic later. For now, use the simplist model of offloading routes up to the point of failure, and then on failure, undo everything and mark IPv4 offloading disabled. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/switchdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8d2ac663325a..dc0a5cc7c2c5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -55,6 +55,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id); int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id); +void netdev_switch_fib_ipv4_abort(struct fib_info *fi); #else @@ -128,6 +129,10 @@ static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, return 0; } +void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +{ +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ -- cgit v1.2.3 From 05050753602626ed4c46271c689929b625f409e7 Mon Sep 17 00:00:00 2001 From: Ilan peer Date: Wed, 4 Mar 2015 00:32:06 -0500 Subject: cfg80211: Add API to change the indoor regulatory setting Previously, the indoor setting configuration assumed that as long as a station interface is connected, the indoor environment setting does not change. However, this assumption is problematic as: - It is possible that a station interface is connected to a mobile AP, e.g., softAP or a P2P GO, where it is possible that both the station and the mobile AP move out of the indoor environment making the indoor setting invalid. In such a case, user space has no way to invalidate the setting. - A station interface disconnection does not necessarily imply that the device is no longer operating in an indoor environment, e.g., it is possible that the station interface is roaming but is still stays indoor. To handle the above, extend the indoor configuration API to allow user space to indicate a change of indoor settings, and allow it to indicate weather it controls the indoor setting, such that: 1. If the user space process explicitly indicates that it is going to control the indoor setting, do not clear the indoor setting internally, unless the socket is released. The user space process should use the NL80211_ATTR_SOCKET_OWNER attribute in the command to state that it is going to control the indoor setting. 2. Reset the indoor setting when restoring the regulatory settings in case it is not owned by a user space process. Based on the above, a user space tool that continuously monitors the indoor settings, i.e., tracking power setting, location etc., can indicate environment changes to the regulatory core. It should be noted that currently user space is the only provided mechanism used to hint to the regulatory core over the indoor/outdoor environment -- while the country IEs do have an environment setting this has been completely ignored by the regulatory core by design for a while now since country IEs typically can contain bogus data. Acked-by: Luis R. Rodriguez Signed-off-by: ArikX Nemtsov Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 37e7f39441e5..ae16ba9cb1e3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1697,6 +1697,10 @@ enum nl80211_commands { * If set during scheduled scan start then the new scan req will be * owned by the netlink socket that created it and the scheduled scan will * be stopped when the socket is closed. + * If set during configuration of regulatory indoor operation then the + * regulatory indoor configuration would be owned by the netlink socket + * that configured the indoor setting, and the indoor operation would be + * cleared when the socket is closed. * * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is * the TDLS link initiator. @@ -1752,6 +1756,9 @@ enum nl80211_commands { * * @NL80211_ATTR_SCHED_SCAN_DELAY: delay before a scheduled scan (or a * WoWLAN net-detect scan) is started, u32 in seconds. + + * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device + * is operating in an indoor environment. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2120,6 +2127,8 @@ enum nl80211_attrs { NL80211_ATTR_SCHED_SCAN_DELAY, + NL80211_ATTR_REG_INDOOR, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 93690c227acf08a2a19cbaf9acbcd2210fbb8ded Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 6 Mar 2015 10:11:21 -0800 Subject: Bluetooth: Introduce controller setting information for static address Currently it is not possible to determine if the static address is used by the controller. It is also not possible to determine if using a static on a dual-mode controller with disabled BR/EDR is possible or not. To address this issue, introduce a new setting called static-address. If support for this setting is signaled that means that the kernel supports using static addresses. And if used on dual-mode controllers with BR/EDR disabled it means that a configured static address can be used. In addition utilize the same setting for the list of current active settings that indicates if a static address is configured and if that address will be actually used. With this in mind the existing Set Static Address management command has been extended to return the current settings. That way the caller of that command can easily determine if the programmed address will be used or if extra steps are required. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/mgmt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index fe8eef00e9ca..0c737e4b8f57 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -98,6 +98,7 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_DEBUG_KEYS 0x00001000 #define MGMT_SETTING_PRIVACY 0x00002000 #define MGMT_SETTING_CONFIGURATION 0x00004000 +#define MGMT_SETTING_STATIC_ADDRESS 0x00008000 #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 -- cgit v1.2.3 From 801c1e8da57499a9922223ee1882b2b59debd47c Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 6 Mar 2015 21:08:50 +0200 Subject: Bluetooth: Add mgmt HCI channel registration API This patch adds an API for registering HCI channels with mgmt-like semantics. For now the only user will be HCI_CHANNEL_CONTROL, but e.g. 6lowpan is intended to use this as well in the future. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 15c761c1f82a..0c84d48e5517 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1273,6 +1273,23 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); +struct hci_mgmt_handler { + int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); + bool var_len; + size_t data_len; +}; + +struct hci_mgmt_chan { + struct list_head list; + unsigned short channel; + size_t handler_count; + const struct hci_mgmt_handler *handlers; +}; + +int hci_mgmt_chan_register(struct hci_mgmt_chan *c); +void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); + /* Management interface */ #define DISCOV_TYPE_BREDR (BIT(BDADDR_BREDR)) #define DISCOV_TYPE_LE (BIT(BDADDR_LE_PUBLIC) | \ -- cgit v1.2.3 From 6d785aa345f525e1fdf098b7c590168f0b00f3f1 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 6 Mar 2015 21:08:51 +0200 Subject: Bluetooth: Convert mgmt to use HCI chan registration API This patch converts the existing mgmt code to use the newly introduced generic API for registering HCI channels with mgmt-like semantics. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 3 +++ include/net/bluetooth/hci_core.h | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 6bb97df16d2d..e598ca096ec9 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -354,6 +354,9 @@ void l2cap_exit(void); int sco_init(void); void sco_exit(void); +int mgmt_init(void); +void mgmt_exit(void); + void bt_sock_reclassify_lock(struct sock *sk, int proto); #endif /* __BLUETOOTH_H */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 0c84d48e5517..b2a183d201b7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1309,7 +1309,9 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ -int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); +int mgmt_control(struct hci_mgmt_chan *chan, struct sock *sk, + struct msghdr *msg, size_t msglen); + int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); -- cgit v1.2.3 From b9a245fb12315f8c6528b29a991a004859c982d5 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 6 Mar 2015 21:08:52 +0200 Subject: Bluetooth: Move all mgmt command quirks to handler table In order to completely generalize the mgmt command handling we need to move away command-specific information from mgmt_control() into the actual command table. This patch adds a new 'flags' field to the handler entries which can now contain the following command specific information: - Command takes variable length parameters - Command doesn't target any specific HCI device - Command can be sent when the HCI device is unconfigured After this the mgmt_control() function is completely generic and can potentially be reused by new HCI channels. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b2a183d201b7..afc641c5e55c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1273,11 +1273,15 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); +#define HCI_MGMT_VAR_LEN (1 << 0) +#define HCI_MGMT_NO_HDEV (1 << 1) +#define HCI_MGMT_UNCONFIGURED (1 << 2) + struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); - bool var_len; size_t data_len; + unsigned long flags; }; struct hci_mgmt_chan { -- cgit v1.2.3 From aaa4e70404c7b38a8792dc69af54afd7218b2ec0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 4 Mar 2015 10:16:43 -0600 Subject: DECnet: Only use neigh_ops for adding the link layer header Other users users of the neighbour table use neigh->output as the method to decided when and which link-layer header to place on a packet. DECnet has been using neigh->output to decide which DECnet headers to place on a packet depending which neighbour the packet is destined for. The DECnet usage isn't totally wrong but it can run into problems if the neighbour output function is run for a second time as the teql driver and the bridge netfilter code can do. Therefore to avoid pathologic problems later down the line and make the neighbour code easier to understand by refactoring the decnet output code to only use a neighbour method to add a link layer header to a packet. This is done by moving the neigbhour operations lookup from dn_to_neigh_output to dn_neigh_output_packet. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dn_neigh.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h index fac4e3f4a6d3..0f26aa707e62 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -22,6 +22,7 @@ int dn_neigh_router_hello(struct sk_buff *skb); int dn_neigh_endnode_hello(struct sk_buff *skb); void dn_neigh_pointopoint_hello(struct sk_buff *skb); int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); +int dn_to_neigh_output(struct sk_buff *skb); extern struct neigh_table dn_neigh_table; -- cgit v1.2.3 From dcd8fb8533ceb493146ce030d15f7965b82d0c27 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Fri, 6 Mar 2015 11:18:22 +0800 Subject: ipv4: Raise tcp PMTU probe mss base size Quotes from RFC4821 7.2. Selecting Initial Values It is RECOMMENDED that search_low be initially set to an MTU size that is likely to work over a very wide range of environments. Given today's technologies, a value of 1024 bytes is probably safe enough. The initial value for search_low SHOULD be configurable. Moreover, set a small value will introduce extra time for the search to converge. So set the initial probe base mss size to 1024 Bytes. Signed-off-by: Fan Du Acked-by: John Heffner Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index f87599d5af82..834089b0cffc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,7 +65,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_MIN_MSS 88U /* The least MTU to use for probing */ -#define TCP_BASE_MSS 512 +#define TCP_BASE_MSS 1024 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 -- cgit v1.2.3 From 6b58e0a5f32dedb609438bb9c9c82aa6e23381f2 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Fri, 6 Mar 2015 11:18:23 +0800 Subject: ipv4: Use binary search to choose tcp PMTU probe_size Current probe_size is chosen by doubling mss_cache, the probing process will end shortly with a sub-optimal mss size, and the link mtu will not be taken full advantage of, in return, this will make user to tweak tcp_base_mss with care. Use binary search to choose probe_size in a fine granularity manner, an optimal mss will be found to boost performance as its maxmium. In addition, introduce a sysctl_tcp_probe_threshold to control when probing will stop in respect to the width of search range. Test env: Docker instance with vxlan encapuslation(82599EB) iperf -c 10.0.0.24 -t 60 before this patch: 1.26 Gbits/sec After this patch: increase 26% 1.59 Gbits/sec Signed-off-by: Fan Du Acked-by: John Heffner Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1085e12f940f..e051d399fa17 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -87,6 +87,7 @@ struct netns_ipv4 { int sysctl_tcp_fwmark_accept; int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; + int sysctl_tcp_probe_threshold; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 834089b0cffc..1ad82e334e27 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -67,6 +67,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* The least MTU to use for probing */ #define TCP_BASE_MSS 1024 +/* Specify interval when tcp mtu probing will stop */ +#define TCP_PROBE_THRESHOLD 8 + /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 -- cgit v1.2.3 From 05cbc0db03e82128f2e7e353d4194dd24a1627fe Mon Sep 17 00:00:00 2001 From: Fan Du Date: Fri, 6 Mar 2015 11:18:24 +0800 Subject: ipv4: Create probe timer for tcp PMTU as per RFC4821 As per RFC4821 7.3. Selecting Probe Size, a probe timer should be armed once probing has converged. Once this timer expired, probing again to take advantage of any path PMTU change. The recommended probing interval is 10 minutes per RFC1981. Probing interval could be sysctled by sysctl_tcp_probe_interval. Eric Dumazet suggested to implement pseudo timer based on 32bits jiffies tcp_time_stamp instead of using classic timer for such rare event. Signed-off-by: Fan Du Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 ++ include/net/netns/ipv4.h | 1 + include/net/tcp.h | 3 +++ 3 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5976bdecf58b..b9a6b0a94cc6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -126,6 +126,8 @@ struct inet_connection_sock { /* Information on the current probe. */ int probe_size; + + u32 probe_timestamp; } icsk_mtup; u32 icsk_ca_priv[16]; u32 icsk_user_timeout; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index e051d399fa17..8f3a1a1a5a94 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -88,6 +88,7 @@ struct netns_ipv4 { int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; int sysctl_tcp_probe_threshold; + u32 sysctl_tcp_probe_interval; struct ping_group_range ping_group_range; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1ad82e334e27..2e11e38205c2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -67,6 +67,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* The least MTU to use for probing */ #define TCP_BASE_MSS 1024 +/* probing interval, default to 10 minutes as per RFC4821 */ +#define TCP_PROBE_INTERVAL 600 + /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 -- cgit v1.2.3 From 89650ad0047f039b3c3bc0f6a5823bb9c9738152 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Mar 2015 11:44:28 -0500 Subject: fib: make netdev_switch_fib_ipv4_abort in header file static inline When building without CONFIG_NET_SWITCHDEV, netdev_switch_fib_ipv4_abort is defined in the header file. It must be static inline to avoid build failure at link time. Fixes: 8e05fd7166c6 ("fib: hook IPv4 fib for hardware offload") Signed-off-by: Willem de Bruijn Acked-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index dc0a5cc7c2c5..933fac410a7a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -129,7 +129,7 @@ static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, return 0; } -void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +static inline void netdev_switch_fib_ipv4_abort(struct fib_info *fi) { } -- cgit v1.2.3 From c93682477bd861744589215515a63b81fdbd8948 Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Thu, 5 Mar 2015 20:16:11 +0200 Subject: net/dcb: Add IEEE QCN attribute As specified in 802.1Qau spec. Add this optional attribute to the DCB netlink layer. To allow for application to use the new attribute, NIC drivers should implement and register the callbacks ieee_getqcn, ieee_setqcn and ieee_getqcnstats. The QCN attribute holds a set of parameters for management, and a set of statistics to provide informative data on Congestion-Control defined by this spec. Signed-off-by: Shani Michaeli Signed-off-by: Shachar Raindel Signed-off-by: Or Gerlitz Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/net/dcbnl.h | 3 +++ include/uapi/linux/dcbnl.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) (limited to 'include') diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 597b88a94332..207d9ba1f92c 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -49,6 +49,9 @@ struct dcbnl_rtnl_ops { int (*ieee_setets) (struct net_device *, struct ieee_ets *); int (*ieee_getmaxrate) (struct net_device *, struct ieee_maxrate *); int (*ieee_setmaxrate) (struct net_device *, struct ieee_maxrate *); + int (*ieee_getqcn) (struct net_device *, struct ieee_qcn *); + int (*ieee_setqcn) (struct net_device *, struct ieee_qcn *); + int (*ieee_getqcnstats) (struct net_device *, struct ieee_qcn_stats *); int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index e711f20dc522..6497d7933d5b 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -78,6 +78,70 @@ struct ieee_maxrate { __u64 tc_maxrate[IEEE_8021QAZ_MAX_TCS]; }; +enum dcbnl_cndd_states { + DCB_CNDD_RESET = 0, + DCB_CNDD_EDGE, + DCB_CNDD_INTERIOR, + DCB_CNDD_INTERIOR_READY, +}; + +/* This structure contains the IEEE 802.1Qau QCN managed object. + * + *@rpg_enable: enable QCN RP + *@rppp_max_rps: maximum number of RPs allowed for this CNPV on this port + *@rpg_time_reset: time between rate increases if no CNMs received. + * given in u-seconds + *@rpg_byte_reset: transmitted data between rate increases if no CNMs received. + * given in Bytes + *@rpg_threshold: The number of times rpByteStage or rpTimeStage can count + * before RP rate control state machine advances states + *@rpg_max_rate: the maxinun rate, in Mbits per second, + * at which an RP can transmit + *@rpg_ai_rate: The rate, in Mbits per second, + * used to increase rpTargetRate in the RPR_ACTIVE_INCREASE + *@rpg_hai_rate: The rate, in Mbits per second, + * used to increase rpTargetRate in the RPR_HYPER_INCREASE state + *@rpg_gd: Upon CNM receive, flow rate is limited to (Fb/Gd)*CurrentRate. + * rpgGd is given as log2(Gd), where Gd may only be powers of 2 + *@rpg_min_dec_fac: The minimum factor by which the current transmit rate + * can be changed by reception of a CNM. + * value is given as percentage (1-100) + *@rpg_min_rate: The minimum value, in bits per second, for rate to limit + *@cndd_state_machine: The state of the congestion notification domain + * defense state machine, as defined by IEEE 802.3Qau + * section 32.1.1. In the interior ready state, + * the QCN capable hardware may add CN-TAG TLV to the + * outgoing traffic, to specifically identify outgoing + * flows. + */ + +struct ieee_qcn { + __u8 rpg_enable[IEEE_8021QAZ_MAX_TCS]; + __u32 rppp_max_rps[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_time_reset[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_byte_reset[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_threshold[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_max_rate[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_ai_rate[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_hai_rate[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_gd[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_min_dec_fac[IEEE_8021QAZ_MAX_TCS]; + __u32 rpg_min_rate[IEEE_8021QAZ_MAX_TCS]; + __u32 cndd_state_machine[IEEE_8021QAZ_MAX_TCS]; +}; + +/* This structure contains the IEEE 802.1Qau QCN statistics. + * + *@rppp_rp_centiseconds: the number of RP-centiseconds accumulated + * by RPs at this priority level on this Port + *@rppp_created_rps: number of active RPs(flows) that react to CNMs + */ + +struct ieee_qcn_stats { + __u64 rppp_rp_centiseconds[IEEE_8021QAZ_MAX_TCS]; + __u32 rppp_created_rps[IEEE_8021QAZ_MAX_TCS]; +}; + /* This structure contains the IEEE 802.1Qaz PFC managed object * * @pfc_cap: Indicates the number of traffic classes on the local device @@ -334,6 +398,8 @@ enum ieee_attrs { DCB_ATTR_IEEE_PEER_PFC, DCB_ATTR_IEEE_PEER_APP, DCB_ATTR_IEEE_MAXRATE, + DCB_ATTR_IEEE_QCN, + DCB_ATTR_IEEE_QCN_STATS, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) -- cgit v1.2.3 From d237baa1cbb3a2335357484c1d63a810a01947e2 Mon Sep 17 00:00:00 2001 From: Shani Michaeli Date: Thu, 5 Mar 2015 20:16:12 +0200 Subject: net/mlx4_core: Add basic elements for QCN Add device capability, firmware command opcode and etc prior elements needed for QCN suppprt. Disable SRIOV VF view/access for QCN is disabled. While here, remove a redundant offset definition into the QUERY_DEV_CAP mailbox. Signed-off-by: Shani Michaeli Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 13 +++++++++++++ include/linux/mlx4/device.h | 3 ++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 7b6d4e9ff603..7299e9548906 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -163,6 +163,9 @@ enum { MLX4_QP_FLOW_STEERING_ATTACH = 0x65, MLX4_QP_FLOW_STEERING_DETACH = 0x66, MLX4_FLOW_STEERING_IB_UC_QP_RANGE = 0x64, + + /* Update and read QCN parameters */ + MLX4_CMD_CONGESTION_CTRL_OPCODE = 0x68, }; enum { @@ -233,6 +236,16 @@ struct mlx4_config_dev_params { u8 rx_csum_flags_port_2; }; +enum mlx4_en_congestion_control_algorithm { + MLX4_CTRL_ALGO_802_1_QAU_REACTION_POINT = 0, +}; + +enum mlx4_en_congestion_control_opmod { + MLX4_CONGESTION_CONTROL_GET_PARAMS, + MLX4_CONGESTION_CONTROL_GET_STATISTICS, + MLX4_CONGESTION_CONTROL_SET_PARAMS = 4, +}; + struct mlx4_dev; struct mlx4_cmd_mailbox { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e4ebff7e9d02..1cc54822b931 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -203,7 +203,8 @@ enum { MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18, MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19, MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, - MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21 + MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21, + MLX4_DEV_CAP_FLAG2_QCN = 1LL << 22, }; enum { -- cgit v1.2.3 From b79bda3d38ae67940f1740f7e015f284eb551680 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 7 Mar 2015 16:25:56 -0600 Subject: neigh: Use neigh table index for neigh_packet_xmit Remove a little bit of unnecessary work when transmitting a packet with neigh_packet_xmit. Use the neighbour table index not the address family as a parameter. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index afb8237b0a8c..d48b8ec8b5f4 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -226,6 +226,7 @@ enum { NEIGH_ND_TABLE = 1, NEIGH_DN_TABLE = 2, NEIGH_NR_TABLES, + NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ }; static inline int neigh_parms_family(struct neigh_parms *p) -- cgit v1.2.3 From 8bd63cf1a426e69bf4f611b08978f721e46c194f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 5 Mar 2015 00:52:33 +0100 Subject: bridge: move mac header copying into br_netfilter The mac header only has to be copied back into the skb for fragments generated by ip_fragment(), which only happens for bridge forwarded packets with nf-call-iptables=1 && active nf_defrag. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index c755e4971fa3..332ef8ab37e9 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -44,36 +44,6 @@ static inline void nf_bridge_update_protocol(struct sk_buff *skb) skb->protocol = htons(ETH_P_PPP_SES); } -/* Fill in the header for fragmented IP packets handled by - * the IPv4 connection tracking code. - * - * Only used in br_forward.c - */ -static inline int nf_bridge_copy_header(struct sk_buff *skb) -{ - int err; - unsigned int header_size; - - nf_bridge_update_protocol(skb); - header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); - err = skb_cow_head(skb, header_size); - if (err) - return err; - - skb_copy_to_linear_data_offset(skb, -header_size, - skb->nf_bridge->data, header_size); - __skb_push(skb, nf_bridge_encap_header_len(skb)); - return 0; -} - -static inline int nf_bridge_maybe_copy_header(struct sk_buff *skb) -{ - if (skb->nf_bridge && - skb->nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT)) - return nf_bridge_copy_header(skb); - return 0; -} - static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE)) @@ -119,7 +89,6 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb) } #else -#define nf_bridge_maybe_copy_header(skb) (0) #define nf_bridge_pad(skb) (0) #define br_drop_fake_rtable(skb) do { } while (0) #endif /* CONFIG_BRIDGE_NETFILTER */ -- cgit v1.2.3 From 4a9d2f200862683d6680d5565f30c126625afe65 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 5 Mar 2015 00:52:34 +0100 Subject: netfilter: bridge: move nf_bridge_update_protocol to where its used no need to keep it in a header file. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 332ef8ab37e9..dd580a9a1add 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -36,14 +36,6 @@ static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) } } -static inline void nf_bridge_update_protocol(struct sk_buff *skb) -{ - if (skb->nf_bridge->mask & BRNF_8021Q) - skb->protocol = htons(ETH_P_8021Q); - else if (skb->nf_bridge->mask & BRNF_PPPoE) - skb->protocol = htons(ETH_P_PPP_SES); -} - static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE)) -- cgit v1.2.3 From e5de75bf88858f5b3ab11e2504b86ec059f03102 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 9 Mar 2015 12:30:12 +0100 Subject: netfilter: bridge: move DNAT helper to br_netfilter Only one caller, there is no need to keep this in a header. Move it to br_netfilter.c where this belongs to. Based on patch from Florian Westphal. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index dd580a9a1add..bb39113ea596 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -44,18 +44,6 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) } int br_handle_frame_finish(struct sk_buff *skb); -/* Only used in br_device.c */ -static inline int br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) -{ - struct nf_bridge_info *nf_bridge = skb->nf_bridge; - - skb_pull(skb, ETH_HLEN); - nf_bridge->mask ^= BRNF_BRIDGED_DNAT; - skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), - skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); - skb->dev = nf_bridge->physindev; - return br_handle_frame_finish(skb); -} /* This is called by the IP fragmenting code and it ensures there is * enough room for the encapsulating header (if there is one). */ -- cgit v1.2.3 From 1e052be69d045c8d0f82ff1116fd3e5a79661745 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 6 Mar 2015 11:47:59 -0800 Subject: net_sched: destroy proto tp when all filters are gone Kernel automatically creates a tp for each (kind, protocol, priority) tuple, which has handle 0, when we add a new filter, but it still is left there after we remove our own, unless we don't specify the handle (literally means all the filters under the tuple). For example this one is left: # tc filter show dev eth0 filter parent 8001: protocol arp pref 49152 basic The user-space is hard to clean up these for kernel because filters like u32 are organized in a complex way. So kernel is responsible to remove it after all filters are gone. Each type of filter has its own way to store the filters, so each type has to provide its way to check if all filters are gone. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c605d305c577..6d778efcfdfd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -213,7 +213,7 @@ struct tcf_proto_ops { const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); - void (*destroy)(struct tcf_proto*); + bool (*destroy)(struct tcf_proto*, bool); unsigned long (*get)(struct tcf_proto*, u32 handle); int (*change)(struct net *net, struct sk_buff *, @@ -399,7 +399,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); -void tcf_destroy(struct tcf_proto *tp); +bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); /* Reset all TX qdiscs greater then index of a device. */ -- cgit v1.2.3 From ddb3b6033ca68d71a5f0611b58b2642729342245 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 9 Mar 2015 13:14:37 -0500 Subject: net: Remove protocol from struct dst_ops After my change to neigh_hh_init to obtain the protocol from the neigh_table there are no more users of protocol in struct dst_ops. Remove the protocol field from dst_ops and all of it's initializers. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst_ops.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 1f99a1de0e4f..d64253914a6a 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -12,7 +12,6 @@ struct sock; struct dst_ops { unsigned short family; - __be16 protocol; unsigned int gc_thresh; int (*gc)(struct dst_ops *ops); -- cgit v1.2.3 From aa836df958886e57ff0d43fb3d79d1af4aec0cc8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 9 Mar 2015 14:31:20 -0700 Subject: net: core: add of_find_net_device_by_node() Add a helper function which allows getting the struct net_device pointer associated with a given struct device_node pointer. This is useful for instance for DSA Ethernet devices not backed by a platform_device, but a PCI device. Since we need to access net_class which is not accessible outside of net/core/net-sysfs.c, this helper function is also added here and gated with CONFIG_OF_NET. Network devices initialized with SET_NETDEV_DEV() are also taken into account by checking for dev->parent first and then falling back to checking the device pointer within struct net_device. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_net.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 34597c8c1a4c..9cd72aab76fe 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -9,8 +9,11 @@ #ifdef CONFIG_OF_NET #include + +struct net_device; extern int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); +extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else static inline int of_get_phy_mode(struct device_node *np) { @@ -21,6 +24,11 @@ static inline const void *of_get_mac_address(struct device_node *np) { return NULL; } + +static inline struct net_device *of_find_net_device_by_node(struct device_node *np) +{ + return NULL; +} #endif #endif /* __LINUX_OF_NET_H */ -- cgit v1.2.3 From 769a020289bc8f68b7e48faf8fee970346d71a3b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 9 Mar 2015 14:31:21 -0700 Subject: net: dsa: utilize of_find_net_device_by_node Using of_find_device_by_node() restricts the search to platform_device that match the specified device_node pointer. This is not even remotely true for network devices backed by a pci_device for instance. of_find_net_device_by_node() allows us to do a more thorough lookup to find the struct net_device corresponding to a particular device_node pointer. For symetry with the non-OF code path, we hold the net_device pointer in dsa_probe() just like what dev_to_net_dev() does when we call this function. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b525ac516559..47917e5e1e12 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -72,6 +72,7 @@ struct dsa_platform_data { * to the root switch chip of the tree. */ struct device *netdev; + struct net_device *of_netdev; /* * Info structs describing each of the switch chips -- cgit v1.2.3 From f8f2147150de303e814c0452075d467734d3544b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Mon, 9 Mar 2015 13:59:09 -0700 Subject: switchdev: add netlink flags to IPv4 FIB add op Pass in the netlink flags (NLM_F_*) into switchdev driver for IPv4 FIB add op to allow driver to 1) optimize hardware updates, 2) handle ip route prepend and append commands correctly. Suggested-by: Jamal Hadi Salim Suggested-by: Roopa Prabhu Signed-off-by: Scott Feldman Reviewed-by: Simon Horman Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- include/net/switchdev.h | 6 ++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 45413784a3b1..1354ae83efc8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1035,7 +1035,7 @@ struct fib_info; * state change. * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); + * u8 tos, u8 type, u32 nlflags, u32 tb_id); * Called to add/modify IPv4 route to switch device. * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, * int dst_len, struct fib_info *fi, @@ -1207,6 +1207,7 @@ struct net_device_ops { int dst_len, struct fib_info *fi, u8 tos, u8 type, + u32 nlflags, u32 tb_id); int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, __be32 dst, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 933fac410a7a..1a9382febcc3 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,7 @@ /* * include/net/switchdev.h - Switch device API * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -52,7 +53,7 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id); + u8 tos, u8 type, u32 nlflags, u32 tb_id); int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id); void netdev_switch_fib_ipv4_abort(struct fib_info *fi); @@ -117,7 +118,8 @@ static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device * static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) + u8 tos, u8 type, + u32 nlflags, u32 tb_id) { return 0; } -- cgit v1.2.3 From 59e33c2b021322db92ca27c4d9958e57630443b6 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 9 Mar 2015 15:44:13 -0700 Subject: net: phy: bcm7xxx: add alternate id for 7439 BCM7439 has an alternate PHY OUI: 0xae025080 which is to be found in some variants of this chip. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 7ccd928cc1f2..cab606617522 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -19,6 +19,7 @@ #define PHY_ID_BCM7425 0x03625e60 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7439 0x600d8480 +#define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 #define PHY_BCM_OUI_MASK 0xfffffc00 -- cgit v1.2.3 From a03a8dbe20eff6d57aae3147577bf84b52aba4e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 9 Mar 2015 23:04:15 +0100 Subject: netfilter: fix sparse warnings in reject handling make C=1 CF=-D__CHECK_ENDIAN__ shows following: net/bridge/netfilter/nft_reject_bridge.c:65:50: warning: incorrect type in argument 3 (different base types) net/bridge/netfilter/nft_reject_bridge.c:65:50: expected restricted __be16 [usertype] protocol [..] net/bridge/netfilter/nft_reject_bridge.c:102:37: warning: cast from restricted __be16 net/bridge/netfilter/nft_reject_bridge.c:102:37: warning: incorrect type in argument 1 (different base types) [..] net/bridge/netfilter/nft_reject_bridge.c:121:50: warning: incorrect type in argument 3 (different base types) [..] net/bridge/netfilter/nft_reject_bridge.c:168:52: warning: incorrect type in argument 3 (different base types) [..] net/bridge/netfilter/nft_reject_bridge.c:233:52: warning: incorrect type in argument 3 (different base types) [..] Caused by two (harmless) errors: 1. htons() instead of ntohs() 2. __be16 for protocol in nf_reject_ipXhdr_put API, use u8 instead. Reported-by: kbuild test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_reject.h | 2 +- include/net/netfilter/ipv6/nf_reject.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 864127573c32..77862c3645f0 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -12,7 +12,7 @@ const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int ttl); + __u8 protocol, int ttl); void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 0ae445d3f217..0ea4fa37db16 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -13,7 +13,7 @@ const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, unsigned int *otcplen, int hook); struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int hoplimit); + __u8 protocol, int hoplimit); void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth, unsigned int otcplen); -- cgit v1.2.3 From 491da2a477077357c8206a601559e2ea58f224db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Mar 2015 07:15:52 -0700 Subject: net: constify sock_diag_check_cookie() sock_diag_check_cookie() second parameter is constant Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 46cca4c06848..b5ad7d35a636 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -19,7 +19,7 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); -int sock_diag_check_cookie(void *sk, __u32 *cookie); +int sock_diag_check_cookie(void *sk, const __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); -- cgit v1.2.3 From 34160ea3f9c96b5ae71a11459f9b9f6c298b8930 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Mar 2015 07:15:54 -0700 Subject: inet_diag: add const to inet_diag_req_v2 diag dumpers should not modify the request. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 46da02410a09..ac48b10c9395 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -11,33 +11,34 @@ struct sk_buff; struct netlink_callback; struct inet_diag_handler { - void (*dump)(struct sk_buff *skb, - struct netlink_callback *cb, - struct inet_diag_req_v2 *r, - struct nlattr *bc); - - int (*dump_one)(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req); - - void (*idiag_get_info)(struct sock *sk, - struct inet_diag_msg *r, - void *info); - __u16 idiag_type; + void (*dump)(struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, + struct nlattr *bc); + + int (*dump_one)(struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req); + + void (*idiag_get_info)(struct sock *sk, + struct inet_diag_msg *r, + void *info); + __u16 idiag_type; }; struct inet_connection_sock; int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, - struct sk_buff *skb, struct inet_diag_req_v2 *req, - struct user_namespace *user_ns, - u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh); + struct sk_buff *skb, const struct inet_diag_req_v2 *req, + struct user_namespace *user_ns, + u32 pid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh); void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, - struct netlink_callback *cb, struct inet_diag_req_v2 *r, - struct nlattr *bc); + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, + struct nlattr *bc); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req); + struct sk_buff *in_skb, const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req); int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); -- cgit v1.2.3 From 406ef2a67bd0bb13d77d5e5d700e36a2caea09ae Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 10 Mar 2015 20:14:27 +0200 Subject: Bluetooth: Make Fast Connectable available while powered off To maximize the usability of the Fast Connectable feature we should make it possible to set (or unset) it at any given moment. This means removing the dependency on the 'connectable' setting as well as the 'powered' setting. The former makes also sense since page scan may get enabled through add_device even if 'connectable' is false. To keep the setting available over power cycles its flag also needs to be removed from the flags that are cleared upon HCI_Reset. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8e54f825153c..f76f45ae76c3 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -231,7 +231,7 @@ enum { * or the HCI device is closed. */ #define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ) | \ - BIT(HCI_FAST_CONNECTABLE) | BIT(HCI_LE_ADV)) + BIT(HCI_LE_ADV)) /* HCI timeouts */ #define HCI_DISCONN_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ -- cgit v1.2.3 From 55e76b38986a61259f3079afd0f9a865651a34fe Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 10 Mar 2015 22:34:40 +0200 Subject: Bluetooth: Add 'Already Paired' error for Pair Device command To make the behavior predictable when attempting to pair with a device for which we already have a Link Key or Long Term Key, this patch adds a new 'Already Paired' error which gets sent in such a scenario. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ include/net/bluetooth/mgmt.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index afc641c5e55c..5cc5a192359d 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -967,6 +967,8 @@ struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); void hci_smp_irks_clear(struct hci_dev *hdev); +bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type); + void hci_remote_oob_data_clear(struct hci_dev *hdev); struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 0c737e4b8f57..5bf6af9cee78 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -43,6 +43,7 @@ #define MGMT_STATUS_CANCELLED 0x10 #define MGMT_STATUS_INVALID_INDEX 0x11 #define MGMT_STATUS_RFKILLED 0x12 +#define MGMT_STATUS_ALREADY_PAIRED 0x13 struct mgmt_hdr { __le16 opcode; -- cgit v1.2.3 From 0ddcf43d5d4a03ded1ee3f6b3b72a0cbed4e90b1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 6 Mar 2015 13:47:00 -0800 Subject: ipv4: FIB Local/MAIN table collapse This patch is meant to collapse local and main into one by converting tb_data from an array to a pointer. Doing this allows us to point the local table into the main while maintaining the same variables in the table. As such the tb_data was converted from an array to a pointer, and a new array called data is added in order to still provide an object for tb_data to point to. In order to track the origin of the fib aliases a tb_id value was added in a hole that existed on 64b systems. Using this we can also reverse the merge in the event that custom FIB rules are enabled. With this patch I am seeing an improvement of 20ns to 30ns for routing lookups as long as custom rules are not enabled, with custom rules enabled we fall back to split tables and the original behavior. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/fib_rules.h | 2 +- include/net/ip_fib.h | 26 +++++++++----------------- 2 files changed, 10 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index e584de16e4c3..88d2ae526961 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -58,7 +58,7 @@ struct fib_rules_ops { struct sk_buff *, struct fib_rule_hdr *, struct nlattr **); - void (*delete)(struct fib_rule *); + int (*delete)(struct fib_rule *); int (*compare)(struct fib_rule *, struct fib_rule_hdr *, struct nlattr **); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 1657604c5dd3..54271ed0ed45 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -186,7 +186,8 @@ struct fib_table { int tb_default; int tb_num_default; struct rcu_head rcu; - unsigned long tb_data[0]; + unsigned long *tb_data; + unsigned long __data[0]; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, @@ -196,11 +197,10 @@ int fib_table_delete(struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct fib_table *table); +struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); - - #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) @@ -229,18 +229,13 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res) { struct fib_table *tb; - int err; + int err = -ENETUNREACH; rcu_read_lock(); - for (err = 0; !err; err = -ENETUNREACH) { - tb = fib_get_table(net, RT_TABLE_LOCAL); - if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) - break; - tb = fib_get_table(net, RT_TABLE_MAIN); - if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) - break; - } + tb = fib_get_table(net, RT_TABLE_MAIN); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + err = 0; rcu_read_unlock(); @@ -270,10 +265,6 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, res->tclassid = 0; for (err = 0; !err; err = -ENETUNREACH) { - tb = rcu_dereference_rtnl(net->ipv4.fib_local); - if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) - break; - tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) break; @@ -309,6 +300,7 @@ static inline int fib_num_tclassid_users(struct net *net) return 0; } #endif +int fib_unmerge(struct net *net); void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ @@ -320,7 +312,7 @@ void fib_select_multipath(struct fib_result *res); /* Exported by fib_trie.c */ void fib_trie_init(void); -struct fib_table *fib_trie_table(u32 id); +struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { -- cgit v1.2.3 From 988dfbd795cf08b00576c1ced4210281b2bccffc Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 10 Mar 2015 09:27:55 +1100 Subject: rhashtable: Move hash_rnd into bucket_table Currently hash_rnd is a parameter that users can set. However, no existing users set this parameter. It is also something that people are unlikely to want to set directly since it's just a random number. In preparation for allowing the reseeding/rehashing of rhashtable, this patch moves hash_rnd into bucket_table so that it's now an internal state rather than a parameter. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d438eeb08bff..5ef8ea551556 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -49,12 +49,14 @@ struct rhash_head { /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets + * @hash_rnd: Random seed to fold into hash * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets * @buckets: size * hash buckets */ struct bucket_table { size_t size; + u32 hash_rnd; unsigned int locks_mask; spinlock_t *locks; @@ -72,7 +74,6 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed - * @hash_rnd: Seed to use while hashing * @max_shift: Maximum number of shifts while expanding * @min_shift: Minimum number of shifts while shrinking * @nulls_base: Base value to generate nulls marker @@ -85,7 +86,6 @@ struct rhashtable_params { size_t key_len; size_t key_offset; size_t head_offset; - u32 hash_rnd; size_t max_shift; size_t min_shift; u32 nulls_base; -- cgit v1.2.3 From 33d6737761ea425d43f3b6e4561573a4020982f2 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 10 Mar 2015 16:57:11 -0700 Subject: of: mdio: export of_mdio_parse_addr Export of_mdio_parse_addr() which allows parsing a given Ethernet PHY node MDIO address, verify it is within the allowed range, and return its value. This is going to be useful for the DSA code which needs to deal with multiple layers of MDIO buses. Signed-off-by: Florian Fainelli Acked-by: Rob Herring Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index d449018d0726..8f2237eb3485 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -24,6 +24,7 @@ struct phy_device *of_phy_attach(struct net_device *dev, phy_interface_t iface); extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); +extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); #else /* CONFIG_OF */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) @@ -60,6 +61,12 @@ static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; } + +static inline int of_mdio_parse_addr(struct device *dev, + const struct device_node *np) +{ + return -ENOSYS; +} #endif /* CONFIG_OF */ #if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY) -- cgit v1.2.3 From 33cf7c90fe2f97afb1cadaa0cfb782cb9d1b9ee2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Mar 2015 18:53:14 -0700 Subject: net: add real socket cookies A long standing problem in netlink socket dumps is the use of kernel socket addresses as cookies. 1) It is a security concern. 2) Sockets can be reused quite quickly, so there is no guarantee a cookie is used once and identify a flow. 3) request sock, establish sock, and timewait socks for a given flow have different cookies. Part of our effort to bring better TCP statistics requires to switch to a different allocator. In this patch, I chose to use a per network namespace 64bit generator, and to use it only in the case a socket needs to be dumped to netlink. (This might be refined later if needed) Note that I tried to carry cookies from request sock, to establish sock, then timewait sockets. Signed-off-by: Eric Dumazet Cc: Eric Salo Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 4 ++-- include/net/inet_sock.h | 2 ++ include/net/inet_timewait_sock.h | 1 + include/net/net_namespace.h | 2 ++ include/net/sock.h | 3 +++ 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index b5ad7d35a636..083ac388098e 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -19,8 +19,8 @@ void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); -int sock_diag_check_cookie(void *sk, const __u32 *cookie); -void sock_diag_save_cookie(void *sk, __u32 *cookie); +int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); +void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index eb16c7beed1e..e565afdc14ad 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -77,6 +77,8 @@ struct inet_request_sock { #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if +#define ir_cookie req.__req_common.skc_cookie +#define ireq_net req.__req_common.skc_net kmemcheck_bitfield_begin(flags); u16 snd_wscale : 4, diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 6c566034e26d..b7ce1003c429 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -122,6 +122,7 @@ struct inet_timewait_sock { #define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr #define tw_dport __tw_common.skc_dport #define tw_num __tw_common.skc_num +#define tw_cookie __tw_common.skc_cookie int tw_timeout; volatile unsigned char tw_substate; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 2cb9acb618e9..e086f4030dd2 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -56,6 +56,8 @@ struct net { #endif spinlock_t rules_mod_lock; + atomic64_t cookie_gen; + struct list_head list; /* list of network namespaces */ struct list_head cleanup_list; /* namespaces on death row */ struct list_head exit_list; /* Use only net_mutex */ diff --git a/include/net/sock.h b/include/net/sock.h index 250822cc1e02..d996c633bec2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -199,6 +199,8 @@ struct sock_common { struct in6_addr skc_v6_rcv_saddr; #endif + atomic64_t skc_cookie; + /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -329,6 +331,7 @@ struct sock { #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +#define sk_cookie __sk_common.skc_cookie socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; -- cgit v1.2.3 From d299ce149c1aa6a2e2c8db44974a6a1c07d7303b Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 12 Mar 2015 11:00:10 +0900 Subject: vxlan: Correct path typo in comment Flags are used in the return path rather than the return patch. Fixes: af33c1adae1e ("vxlan: Eliminate dependency on UDP socket in transmit path") Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/net/vxlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index eabd3a038674..9564b779246f 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -130,7 +130,7 @@ struct vxlan_sock { #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 -/* Flags that are used in the receive patch. These flags must match in +/* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ -- cgit v1.2.3 From c78ba6d64c78634a875d1e316676667cabfea256 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 11 Mar 2015 15:39:21 +0100 Subject: ipv6: expose RFC4191 route preference via rtnetlink This makes it possible to retain the route preference when RAs are handled in userspace. Signed-off-by: Lubomir Rintel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index c3722b024e73..bea910f924dd 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -305,6 +305,7 @@ enum rtattr_type_t { RTA_MFC_STATS, RTA_VIA, RTA_NEWDST, + RTA_PREF, __RTA_MAX }; -- cgit v1.2.3 From efd7ef1c1929d7a0329d4349252863c04d6f1729 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 11 Mar 2015 23:04:08 -0500 Subject: net: Kill hold_net release_net hold_net and release_net were an idea that turned out to be useless. The code has been disabled since 2008. Kill the code it is long past due. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- include/net/fib_rules.h | 9 +-------- include/net/net_namespace.h | 29 ----------------------------- include/net/sock.h | 2 +- 4 files changed, 3 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1354ae83efc8..cede40d9cac9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1864,8 +1864,7 @@ static inline void dev_net_set(struct net_device *dev, struct net *net) { #ifdef CONFIG_NET_NS - release_net(dev->nd_net); - dev->nd_net = hold_net(net); + dev->nd_net = net; #endif } diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 88d2ae526961..6d67383a5114 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -95,17 +95,10 @@ static inline void fib_rule_get(struct fib_rule *rule) atomic_inc(&rule->refcnt); } -static inline void fib_rule_put_rcu(struct rcu_head *head) -{ - struct fib_rule *rule = container_of(head, struct fib_rule, rcu); - release_net(rule->fr_net); - kfree(rule); -} - static inline void fib_rule_put(struct fib_rule *rule) { if (atomic_dec_and_test(&rule->refcnt)) - call_rcu(&rule->rcu, fib_rule_put_rcu); + kfree_rcu(rule, rcu); } static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index e086f4030dd2..fab51ceeabf3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -49,11 +49,6 @@ struct net { atomic_t count; /* To decided when the network * namespace should be shut down. */ -#ifdef NETNS_REFCNT_DEBUG - atomic_t use_count; /* To track references we - * destroy on demand - */ -#endif spinlock_t rules_mod_lock; atomic64_t cookie_gen; @@ -236,30 +231,6 @@ int net_eq(const struct net *net1, const struct net *net2) #endif -#ifdef NETNS_REFCNT_DEBUG -static inline struct net *hold_net(struct net *net) -{ - if (net) - atomic_inc(&net->use_count); - return net; -} - -static inline void release_net(struct net *net) -{ - if (net) - atomic_dec(&net->use_count); -} -#else -static inline struct net *hold_net(struct net *net) -{ - return net; -} - -static inline void release_net(struct net *net) -{ -} -#endif - #ifdef CONFIG_NET_NS static inline void write_pnet(struct net **pnet, struct net *net) diff --git a/include/net/sock.h b/include/net/sock.h index d996c633bec2..95b2c1c220f9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2204,7 +2204,7 @@ static inline void sk_change_net(struct sock *sk, struct net *net) if (!net_eq(current_net, net)) { put_net(current_net); - sock_net_set(sk, hold_net(net)); + sock_net_set(sk, net); } } -- cgit v1.2.3 From 0c5c9fb55106333e773de8c9dd321fa8240caeb3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 11 Mar 2015 23:06:44 -0500 Subject: net: Introduce possible_net_t Having to say > #ifdef CONFIG_NET_NS > struct net *net; > #endif in structures is a little bit wordy and a little bit error prone. Instead it is possible to say: > typedef struct { > #ifdef CONFIG_NET_NS > struct net *net; > #endif > } possible_net_t; And then in a header say: > possible_net_t net; Which is cleaner and easier to use and easier to test, as the possible_net_t is always there no matter what the compile options. Further this allows read_pnet and write_pnet to be functions in all cases which is better at catching typos. This change adds possible_net_t, updates the definitions of read_pnet and write_pnet, updates optional struct net * variables that write_pnet uses on to have the type possible_net_t, and finally fixes up the b0rked users of read_pnet and write_pnet. Signed-off-by: "Eric W. Biederman" Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++------ include/net/cfg80211.h | 4 +--- include/net/genetlink.h | 4 +--- include/net/inet_hashtables.h | 4 +--- include/net/ip_vs.h | 8 ++++---- include/net/neighbour.h | 8 ++------ include/net/net_namespace.h | 23 +++++++++++++---------- include/net/netfilter/nf_conntrack.h | 5 ++--- include/net/sock.h | 4 +--- include/net/xfrm.h | 8 ++------ 10 files changed, 29 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cede40d9cac9..ddab1a2a07a0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1721,9 +1721,7 @@ struct net_device { struct netpoll_info __rcu *npinfo; #endif -#ifdef CONFIG_NET_NS - struct net *nd_net; -#endif + possible_net_t nd_net; /* mid-layer private */ union { @@ -1863,9 +1861,7 @@ struct net *dev_net(const struct net_device *dev) static inline void dev_net_set(struct net_device *dev, struct net *net) { -#ifdef CONFIG_NET_NS - dev->nd_net = net; -#endif + write_pnet(&dev->nd_net, net); } static inline bool netdev_uses_dsa(struct net_device *dev) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 64e09e1e8099..f977abec07f6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3183,10 +3183,8 @@ struct wiphy { const struct ieee80211_ht_cap *ht_capa_mod_mask; const struct ieee80211_vht_cap *vht_capa_mod_mask; -#ifdef CONFIG_NET_NS /* the network namespace this phy lives in currently */ - struct net *_net; -#endif + possible_net_t _net; #ifdef CONFIG_CFG80211_WEXT const struct iw_handler_def *wext; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 0574abd3db86..a9af1cc8c1bc 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -92,9 +92,7 @@ struct genl_info { struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; -#ifdef CONFIG_NET_NS - struct net * _net; -#endif + possible_net_t _net; void * user_ptr[2]; struct sock * dst_sk; }; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index dd1950a7e273..bcd64756e5fe 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -76,9 +76,7 @@ struct inet_ehash_bucket { * ports are created in O(1) time? I thought so. ;-) -DaveM */ struct inet_bind_bucket { -#ifdef CONFIG_NET_NS - struct net *ib_net; -#endif + possible_net_t ib_net; unsigned short port; signed char fastreuse; signed char fastreuseport; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 20fd23398537..4e3731ee4eac 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -47,13 +47,13 @@ static inline struct net *skb_net(const struct sk_buff *skb) * Start with the most likely hit * End with BUG */ - if (likely(skb->dev && skb->dev->nd_net)) + if (likely(skb->dev && dev_net(skb->dev))) return dev_net(skb->dev); if (skb_dst(skb) && skb_dst(skb)->dev) return dev_net(skb_dst(skb)->dev); WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", __func__, __LINE__); - if (likely(skb->sk && skb->sk->sk_net)) + if (likely(skb->sk && sock_net(skb->sk))) return sock_net(skb->sk); pr_err("There is no net ptr to find in the skb in %s() line:%d\n", __func__, __LINE__); @@ -71,11 +71,11 @@ static inline struct net *skb_sknet(const struct sk_buff *skb) #ifdef CONFIG_NET_NS #ifdef CONFIG_IP_VS_DEBUG /* Start with the most likely hit */ - if (likely(skb->sk && skb->sk->sk_net)) + if (likely(skb->sk && sock_net(skb->sk))) return sock_net(skb->sk); WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", __func__, __LINE__); - if (likely(skb->dev && skb->dev->nd_net)) + if (likely(skb->dev && dev_net(skb->dev))) return dev_net(skb->dev); pr_err("There is no net ptr to find in the skb in %s() line:%d\n", __func__, __LINE__); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index d48b8ec8b5f4..e7bdf5170802 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -65,9 +65,7 @@ enum { }; struct neigh_parms { -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); @@ -167,9 +165,7 @@ struct neigh_ops { struct pneigh_entry { struct pneigh_entry *next; -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; struct net_device *dev; u8 flags; u8 key[0]; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fab51ceeabf3..f733656404de 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -231,24 +231,27 @@ int net_eq(const struct net *net1, const struct net *net2) #endif +typedef struct { #ifdef CONFIG_NET_NS + struct net *net; +#endif +} possible_net_t; -static inline void write_pnet(struct net **pnet, struct net *net) +static inline void write_pnet(possible_net_t *pnet, struct net *net) { - *pnet = net; +#ifdef CONFIG_NET_NS + pnet->net = net; +#endif } -static inline struct net *read_pnet(struct net * const *pnet) +static inline struct net *read_pnet(const possible_net_t *pnet) { - return *pnet; -} - +#ifdef CONFIG_NET_NS + return pnet->net; #else - -#define write_pnet(pnet, net) do { (void)(net);} while (0) -#define read_pnet(pnet) (&init_net) - + return &init_net; #endif +} #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 74f271a172dd..095433b8a8b0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -95,9 +95,8 @@ struct nf_conn { /* Timer function; drops refcnt when it goes off. */ struct timer_list timeout; -#ifdef CONFIG_NET_NS - struct net *ct_net; -#endif + possible_net_t ct_net; + /* all members below initialized via memset */ u8 __nfct_init_offset[0]; diff --git a/include/net/sock.h b/include/net/sock.h index 95b2c1c220f9..9411c3421dd3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -190,9 +190,7 @@ struct sock_common { struct hlist_nulls_node skc_portaddr_node; }; struct proto *skc_prot; -#ifdef CONFIG_NET_NS - struct net *skc_net; -#endif + possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dc4865e90fe4..d0ac7d7be8a7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,9 +126,7 @@ struct xfrm_state_walk { /* Full description of state of transformer. */ struct xfrm_state { -#ifdef CONFIG_NET_NS - struct net *xs_net; -#endif + possible_net_t xs_net; union { struct hlist_node gclist; struct hlist_node bydst; @@ -522,9 +520,7 @@ struct xfrm_policy_queue { }; struct xfrm_policy { -#ifdef CONFIG_NET_NS - struct net *xp_net; -#endif + possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; -- cgit v1.2.3 From 80f1d68ccba70b1060c9c7360ca83da430f66bed Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 12 Mar 2015 17:21:42 +0100 Subject: ebpf: verifier: check that call reg with ARG_ANYTHING is initialized I noticed that a helper function with argument type ARG_ANYTHING does not need to have an initialized value (register). This can worst case lead to unintented stack memory leakage in future helper functions if they are not carefully designed, or unintended application behaviour in case the application developer was not careful enough to match a correct helper function signature in the API. The underlying issue is that ARG_ANYTHING should actually be split into two different semantics: 1) ARG_DONTCARE for function arguments that the helper function does not care about (in other words: the default for unused function arguments), and 2) ARG_ANYTHING that is an argument actually being used by a helper function and *guaranteed* to be an initialized register. The current risk is low: ARG_ANYTHING is only used for the 'flags' argument (r4) in bpf_map_update_elem() that internally does strict checking. Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a884f5a2c503..80f2e0fc3d02 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -44,7 +44,7 @@ struct bpf_map_type_list { /* function argument constraints */ enum bpf_arg_type { - ARG_ANYTHING = 0, /* any argument is ok */ + ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions @@ -58,6 +58,8 @@ enum bpf_arg_type { */ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + + ARG_ANYTHING, /* any (initialized) argument is ok */ }; /* type of values returned from helper functions */ -- cgit v1.2.3 From bd337c581b2b0d933d37f664bf55b342577fed3a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:03 -0700 Subject: ipv6: add missing ireq_net & ir_cookie initializations I forgot to update dccp_v6_conn_request() & cookie_v6_check(). They both need to set ireq->ireq_net and ireq->ir_cookie Lets clear ireq->ir_cookie in inet_reqsk_alloc() Signed-off-by: Eric Dumazet Fixes: 33cf7c90fe2f ("net: add real socket cookies") Signed-off-by: David S. Miller --- include/net/inet_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index e565afdc14ad..30f7170abbf3 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,6 +249,7 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops if (req != NULL) { kmemcheck_annotate_bitfield(ireq, flags); ireq->opt = NULL; + atomic64_set(&ireq->ir_cookie, 0); } return req; -- cgit v1.2.3 From 10feb428a5045d5eb18a5d755fbb8f0cc9645626 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:04 -0700 Subject: inet: add TCP_NEW_SYN_RECV state TCP_SYN_RECV state is currently used by fast open sockets. Initial TCP requests (the pseudo sockets created when a SYN is received) are not yet associated to a state. They are attached to their parent, and the parent is in TCP_LISTEN state. This commit adds TCP_NEW_SYN_RECV state, so that we can convert TCP stack to a different schem gradually. This state is not exported to user space. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp_states.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index b0b645988bd8..50e78a74d0df 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -25,6 +25,7 @@ enum { TCP_LAST_ACK, TCP_LISTEN, TCP_CLOSING, /* Now a valid state */ + TCP_NEW_SYN_RECV, TCP_MAX_STATES /* Leave at the end! */ }; @@ -44,7 +45,8 @@ enum { TCPF_CLOSE_WAIT = (1 << 8), TCPF_LAST_ACK = (1 << 9), TCPF_LISTEN = (1 << 10), - TCPF_CLOSING = (1 << 11) + TCPF_CLOSING = (1 << 11), + TCPF_NEW_SYN_RECV = (1 << 12), }; #endif /* _LINUX_TCP_STATES_H */ -- cgit v1.2.3 From d34ac51b76e8c7de6094cfb11780ef9c2b93469f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:05 -0700 Subject: inet: add ireq_state field to inet_request_sock We need to identify request sock when they'll be visible in global ehash table. ireq_state is an alias to req.__req_common.skc_state. Its value is set to TCP_NEW_SYN_RECV Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 30f7170abbf3..b31f01de5cd6 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -27,6 +27,7 @@ #include #include #include +#include /** struct ip_options - IP Options * @@ -79,6 +80,7 @@ struct inet_request_sock { #define ir_iif req.__req_common.skc_bound_dev_if #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net +#define ireq_state req.__req_common.skc_state kmemcheck_bitfield_begin(flags); u16 snd_wscale : 4, @@ -250,6 +252,7 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops kmemcheck_annotate_bitfield(ireq, flags); ireq->opt = NULL; atomic64_set(&ireq->ir_cookie, 0); + ireq->ireq_state = TCP_NEW_SYN_RECV; } return req; -- cgit v1.2.3 From 1e2e01172fd11b4dbfee746c0c8fbcaa9dbf22a0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:06 -0700 Subject: inet: add rsk_refcnt/ireq_refcnt to request socks When request socks will be in ehash, they'll need to be refcounted. This patch adds rsk_refcnt/ireq_refcnt macros, and adds reqsk_put() function, but nothing yet use them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 1 + include/net/request_sock.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b31f01de5cd6..9d6470c16a27 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -81,6 +81,7 @@ struct inet_request_sock { #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state +#define ireq_refcnt req.__req_common.skc_refcnt kmemcheck_bitfield_begin(flags); u16 snd_wscale : 4, diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 7f830ff67f08..e255ecf8bb40 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -49,6 +49,8 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); */ struct request_sock { struct sock_common __req_common; +#define rsk_refcnt __req_common.skc_refcnt + struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ @@ -86,6 +88,12 @@ static inline void reqsk_free(struct request_sock *req) __reqsk_free(req); } +static inline void reqsk_put(struct request_sock *req) +{ + if (atomic_dec_and_test(&req->rsk_refcnt)) + reqsk_free(req); +} + extern int sysctl_max_syn_backlog; /** struct listen_sock - listen state -- cgit v1.2.3 From 41b822c59e21414d829bcfd00df0c8f7f13b1b95 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:08 -0700 Subject: inet: prepare sock_edemux() & sock_gen_put() for new SYN_RECV state sock_edemux() & sock_gen_put() should be ready to cope with request socks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 +++++ include/net/sock.h | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index e255ecf8bb40..3275cf31f731 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -77,6 +77,11 @@ static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *op return req; } +static inline struct request_sock *inet_reqsk(struct sock *sk) +{ + return (struct request_sock *)sk; +} + static inline void __reqsk_free(struct request_sock *req) { kmem_cache_free(req->rsk_ops->slab, req); diff --git a/include/net/sock.h b/include/net/sock.h index 9411c3421dd3..f10832ca2e90 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1625,7 +1625,7 @@ static inline void sock_put(struct sock *sk) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets - * (TCP_TIMEWAIT, ESTABLISHED...) + * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); -- cgit v1.2.3 From 3f66b083a5b7f1a63540c24df3679c24f2e935a9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:10 -0700 Subject: inet: introduce ireq_family Before inserting request socks into general hash table, fill their socket family. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 9d6470c16a27..b3053fdd871e 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -82,6 +82,7 @@ struct inet_request_sock { #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state #define ireq_refcnt req.__req_common.skc_refcnt +#define ireq_family req.__req_common.skc_family kmemcheck_bitfield_begin(flags); u16 snd_wscale : 4, -- cgit v1.2.3 From a5b6846f9e1a080493210013385c28faecee36f0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 12 Mar 2015 15:28:40 +0100 Subject: rhashtable: kill ht->shift atomic operations Commit c0c09bfdc415 ("rhashtable: avoid unnecessary wakeup for worker queue") changed ht->shift to be atomic, which is actually unnecessary. Instead of leaving the current shift in the core rhashtable structure, it can be cached inside the individual bucket tables. There, it will only be initialized once during a new table allocation in the shrink/expansion slow path, and from then onward it stays immutable for the rest of the bucket table liftime. That allows shift to be non-atomic. The patch also moves hash_rnd management into the table setup. The rhashtable structure now consumes 3 instead of 4 cachelines. Signed-off-by: Daniel Borkmann Cc: Ying Xue Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5ef8ea551556..c93ff8ac474a 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -50,6 +50,7 @@ struct rhash_head { * struct bucket_table - Table of hash buckets * @size: Number of hash buckets * @hash_rnd: Random seed to fold into hash + * @shift: Current size (1 << shift) * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets * @buckets: size * hash buckets @@ -57,6 +58,7 @@ struct rhash_head { struct bucket_table { size_t size; u32 hash_rnd; + u32 shift; unsigned int locks_mask; spinlock_t *locks; @@ -99,7 +101,6 @@ struct rhashtable_params { * @tbl: Bucket table * @future_tbl: Table under construction during expansion/shrinking * @nelems: Number of elements in table - * @shift: Current size (1 << shift) * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping @@ -110,12 +111,11 @@ struct rhashtable { struct bucket_table __rcu *tbl; struct bucket_table __rcu *future_tbl; atomic_t nelems; - atomic_t shift; + bool being_destroyed; struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; struct list_head walkers; - bool being_destroyed; }; /** -- cgit v1.2.3 From 098a697b497e3154a1a583c1d34c67568acaadcc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 13 Mar 2015 00:07:44 -0500 Subject: tcp_metrics: Use a single hash table for all network namespaces. Now that all of the operations are safe on a single hash table accross network namespaces, allocate a single global hash table and update the code to use it. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 8f3a1a1a5a94..614a49be68a9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -54,8 +54,6 @@ struct netns_ipv4 { struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct tcpm_hash_bucket *tcp_metrics_hash; - unsigned int tcp_metrics_hash_log; struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER -- cgit v1.2.3 From cc91cb042ce5dab66fedeb94260b18f193ed33d9 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Thu, 12 Mar 2015 22:30:58 -0700 Subject: Bluetooth: Add support connectable advertising setting The patch adds a second advertising setting that allows switching of the controller into connectable mode independent of the global connectable setting. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index f76f45ae76c3..0f3413b285a5 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -217,6 +217,7 @@ enum { HCI_HS_ENABLED, HCI_LE_ENABLED, HCI_ADVERTISING, + HCI_ADVERTISING_CONNECTABLE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, -- cgit v1.2.3 From d7a5a11d7fa80beb43d5f7cb421c86f9b4d21200 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:00 -0700 Subject: Bluetooth: Introduce hci_dev_test_flag helper macro Instead of manually coding test_bit on hdev->dev_flags all the time, use hci_dev_test_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5cc5a192359d..05e95a75aba5 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -502,6 +502,8 @@ extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; +#define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) + /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); @@ -598,14 +600,14 @@ enum { static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - return test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + return hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && test_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } static inline bool hci_conn_sc_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - return test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + return hci_dev_test_flag(hdev, HCI_SC_ENABLED) && test_bit(HCI_CONN_SC_ENABLED, &conn->flags); } @@ -1025,10 +1027,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) -#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \ - !test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) -#define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ - test_bit(HCI_SC_ENABLED, &(dev)->dev_flags)) +#define hdev_is_powered(dev) (test_bit(HCI_UP, &(dev)->flags) && \ + !hci_dev_test_flag(dev, HCI_AUTO_OFF)) +#define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ + hci_dev_test_flag(dev, HCI_SC_ENABLED)) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 -- cgit v1.2.3 From a1536da255f16f42b8f069b2769134b32558b265 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:01 -0700 Subject: Bluetooth: Introduce hci_dev_set_flag helper macro Instead of manually coding set_bit on hdev->dev_flags all the time, use hci_dev_set_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 05e95a75aba5..bc2a7e918da7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -502,6 +502,7 @@ extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; +#define hci_dev_set_flag(hdev, nr) set_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) /* ----- HCI interface to upper protocols ----- */ -- cgit v1.2.3 From a358dc11d80ecaca443aa1fd2fd9d4f3425922e7 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:02 -0700 Subject: Bluetooth: Introduce hci_dev_clear_flag helper macro Instead of manually coding clear_bit on hdev->dev_flags all the time, use hci_dev_clear_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index bc2a7e918da7..535b23c73c92 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -503,6 +503,7 @@ extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), &(hdev)->dev_flags) +#define hci_dev_clear_flag(hdev, nr) clear_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) /* ----- HCI interface to upper protocols ----- */ -- cgit v1.2.3 From ce05d603af7c9b5be66a1f3358443e20e2a2ae7a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:03 -0700 Subject: Bluetooth: Introduce hci_dev_change_flag helper macro Instead of manually coding change_bit on hdev->dev_flags all the time, use hci_dev_change_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 535b23c73c92..92b2148702e6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -504,6 +504,7 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), &(hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), &(hdev)->dev_flags) +#define hci_dev_change_flag(hdev, nr) change_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) /* ----- HCI interface to upper protocols ----- */ -- cgit v1.2.3 From 516018a9c057a7c179dd6b4df917a6f5d43b3547 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:04 -0700 Subject: Bluetooth: Introduce hci_dev_test_and_change_flag helper macro Instead of manually coding test_and_change_bit on hdev->dev_flags all the time, use hci_dev_test_and_change_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 92b2148702e6..cd2682c64a4c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -507,6 +507,8 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_change_flag(hdev, nr) change_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) +#define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), &(hdev)->dev_flags) + /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); -- cgit v1.2.3 From a69d89272698d1c31ccb78348562af6461cf1eb7 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:05 -0700 Subject: Bluetooth: Introduce hci_dev_test_and_clear_flag helper macro Instead of manually coding test_and_clear_bit on hdev->dev_flags all the time, use hci_dev_test_and_clear_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index cd2682c64a4c..4b7632b15051 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -507,6 +507,7 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_change_flag(hdev, nr) change_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) +#define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), &(hdev)->dev_flags) /* ----- HCI interface to upper protocols ----- */ -- cgit v1.2.3 From 238be788fcb75870661ec165dc90f2a2674e7fcb Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 02:11:06 -0700 Subject: Bluetooth: Introduce hci_dev_test_and_set_flag helper macro Instead of manually coding test_and_set_bit on hdev->dev_flags all the time, use hci_dev_test_and_set_flag helper macro. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4b7632b15051..6db1333a114f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -507,6 +507,7 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_change_flag(hdev, nr) change_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) +#define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), &(hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), &(hdev)->dev_flags) -- cgit v1.2.3 From 9c51026509d7fd11d84e0035008e1a9768960f2b Mon Sep 17 00:00:00 2001 From: Syed Asifful Dayyan Date: Fri, 6 Mar 2015 18:40:42 +0100 Subject: brcmfmac: Add support for BCM4345 SDIO chipset. These changes add support for BCM4345 SDIO chipset. Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Arend Van Spriel Reviewed-by: Hante Meuleman Reviewed-by: Daniel (Deognyoun) Kim Signed-off-by: Syed Asifful Dayyan Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 996807963716..91397858dc95 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -33,6 +33,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 +#define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_VENDOR_ID_INTEL 0x0089 -- cgit v1.2.3 From 702131e2a393b45174be326f1dbe20b658b4f157 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 5 Mar 2015 18:25:10 +0100 Subject: bcma: move PCI IRQ control function to host specific code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function isn't really related to any bus core. It touches PCI device config registers only, so move it to the (PCI) host file. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 9 +++++++++ include/linux/bcma/bcma_driver_pci.h | 2 -- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 44057b45ed32..e34f906647d3 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -437,6 +437,8 @@ static inline struct bcma_device *bcma_find_core(struct bcma_bus *bus, #ifdef CONFIG_BCMA_HOST_PCI extern void bcma_host_pci_up(struct bcma_bus *bus); extern void bcma_host_pci_down(struct bcma_bus *bus); +extern int bcma_host_pci_irq_ctl(struct bcma_bus *bus, + struct bcma_device *core, bool enable); #else static inline void bcma_host_pci_up(struct bcma_bus *bus) { @@ -444,6 +446,13 @@ static inline void bcma_host_pci_up(struct bcma_bus *bus) static inline void bcma_host_pci_down(struct bcma_bus *bus) { } +static inline int bcma_host_pci_irq_ctl(struct bcma_bus *bus, + struct bcma_device *core, bool enable) +{ + if (bus->hosttype == BCMA_HOSTTYPE_PCI) + return -ENOTSUPP; + return 0; +} #endif extern bool bcma_core_is_enabled(struct bcma_device *core); diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 8e90004fdfd7..3a468687c170 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -238,8 +238,6 @@ struct bcma_drv_pci { #define pcicore_write16(pc, offset, val) bcma_write16((pc)->core, offset, val) #define pcicore_write32(pc, offset, val) bcma_write32((pc)->core, offset, val) -extern int bcma_core_pci_irq_ctl(struct bcma_bus *bus, - struct bcma_device *core, bool enable); extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); -- cgit v1.2.3 From 982a40f5c0bb03368989a6b1ae833b474854e931 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 5 Mar 2015 18:25:11 +0100 Subject: bcma: allow disabling (not building) PCI driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It isn't required for bcma bus on SoCs, so provide some empty functions and allow disabling it. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_pci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 3a468687c170..5ba6918ca20b 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -238,7 +238,13 @@ struct bcma_drv_pci { #define pcicore_write16(pc, offset, val) bcma_write16((pc)->core, offset, val) #define pcicore_write32(pc, offset, val) bcma_write32((pc)->core, offset, val) +#ifdef CONFIG_BCMA_DRIVER_PCI extern void bcma_core_pci_power_save(struct bcma_bus *bus, bool up); +#else +static inline void bcma_core_pci_power_save(struct bcma_bus *bus, bool up) +{ +} +#endif extern int bcma_core_pci_pcibios_map_irq(const struct pci_dev *dev); extern int bcma_core_pci_plat_dev_init(struct pci_dev *dev); -- cgit v1.2.3 From eacb44dff98559d4682072c0061e1ecb63687e9c Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 09:04:17 -0700 Subject: Bluetooth: Use DECLARE_BITMAP for hdev->dev_flags field The hdev->dev_flags field has outgrown itself on 32-bit systems. So instead of hacking around it, switch to using DECLARE_BITMAP. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 7 +------ include/net/bluetooth/hci_core.h | 24 +++++++++++++++--------- 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 0f3413b285a5..7a0272a6f0ba 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -226,14 +226,9 @@ enum { HCI_FAST_CONNECTABLE, HCI_BREDR_ENABLED, HCI_LE_SCAN_INTERRUPTED, + __HCI_NUM_FLAGS, }; -/* A mask for the flags that are supposed to remain when a reset happens - * or the HCI device is closed. - */ -#define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ) | \ - BIT(HCI_LE_ADV)) - /* HCI timeouts */ #define HCI_DISCONN_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ #define HCI_PAIRING_TIMEOUT msecs_to_jiffies(60000) /* 60 seconds */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6db1333a114f..889a489d913f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -354,7 +354,7 @@ struct hci_dev { struct rfkill *rfkill; unsigned long dbg_flags; - unsigned long dev_flags; + DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); struct delayed_work le_scan_disable; struct delayed_work le_scan_restart; @@ -502,14 +502,20 @@ extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; -#define hci_dev_set_flag(hdev, nr) set_bit((nr), &(hdev)->dev_flags) -#define hci_dev_clear_flag(hdev, nr) clear_bit((nr), &(hdev)->dev_flags) -#define hci_dev_change_flag(hdev, nr) change_bit((nr), &(hdev)->dev_flags) -#define hci_dev_test_flag(hdev, nr) test_bit((nr), &(hdev)->dev_flags) - -#define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), &(hdev)->dev_flags) -#define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), &(hdev)->dev_flags) -#define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), &(hdev)->dev_flags) +#define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) +#define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) +#define hci_dev_change_flag(hdev, nr) change_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_flag(hdev, nr) test_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) + +#define hci_dev_clear_volatile_flags(hdev) \ + do { \ + hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ + hci_dev_clear_flag(hdev, HCI_LE_ADV); \ + hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ + } while (0) /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); -- cgit v1.2.3 From b7cb93e52839ee44959adabc17c2a17422e6bd4b Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Fri, 13 Mar 2015 10:20:35 -0700 Subject: Bluetooth: Merge hdev->dbg_flags fields into hdev->dev_flags With the extension of hdev->dev_flags utilizing a bitmap now, the space is no longer restricted. Merge the hdev->dbg_flags into hdev->dev_flags to save space on 64-bit architectures. On 32-bit architectures no size reduction happens. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 14 +++++--------- include/net/bluetooth/hci_core.h | 1 - 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7a0272a6f0ba..d942fedbaedd 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -179,15 +179,6 @@ enum { HCI_RESET, }; -/* BR/EDR and/or LE controller flags: the flags defined here should represent - * states configured via debugfs for debugging and testing purposes only. - */ -enum { - HCI_DUT_MODE, - HCI_FORCE_BREDR_SMP, - HCI_FORCE_STATIC_ADDR, -}; - /* * BR/EDR and/or LE controller flags: the flags defined here should represent * states from the controller. @@ -226,6 +217,11 @@ enum { HCI_FAST_CONNECTABLE, HCI_BREDR_ENABLED, HCI_LE_SCAN_INTERRUPTED, + + HCI_DUT_MODE, + HCI_FORCE_BREDR_SMP, + HCI_FORCE_STATIC_ADDR, + __HCI_NUM_FLAGS, }; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 889a489d913f..6afbf5b014a1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -353,7 +353,6 @@ struct hci_dev { struct rfkill *rfkill; - unsigned long dbg_flags; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); struct delayed_work le_scan_disable; -- cgit v1.2.3 From 3f3c4bb5ec7c645d1151e1e8d6e56c71a050cf85 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 4 Mar 2015 21:19:59 +0100 Subject: mac802154: correct max sifs size handling This patch fix the max sifs size correction when the IEEE802154_HW_TX_OMIT_CKSUM flag is set. With this flag the sk_buff doesn't contain the CRC, because the transceiver will add the CRC while transmit. Also add some defines for the max sifs frame size value and frame check sequence according to 802.15.4 standard. Signed-off-by: Alexander Aring Acked-by: Marc Kleine-Budde Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 40b0ab953937..8872ca103d06 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -30,6 +30,7 @@ #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 +#define IEEE802154_FCS_LEN 2 #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff @@ -39,6 +40,7 @@ #define IEEE802154_LIFS_PERIOD 40 #define IEEE802154_SIFS_PERIOD 12 +#define IEEE802154_MAX_SIFS_FRAME_SIZE 18 #define IEEE802154_MAX_CHANNEL 26 #define IEEE802154_MAX_PAGE 31 -- cgit v1.2.3 From eddee5ba34eb6c9890ef106f19ead2b370e5342f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 14 Mar 2015 13:57:20 +1100 Subject: rhashtable: Fix walker behaviour during rehash Previously whenever the walker encountered a resize it simply snaps back to the beginning and starts again. However, this only works if the rehash started and completed while the walker was idle. If the walker attempts to restart while the rehash is still ongoing, we may miss objects that we shouldn't have. This patch fixes this by making the walker walk the old table followed by the new table just like all other readers. If a rehash is detected we will still signal our caller of the fact so they can prepare for duplicates but we will simply continue the walk onto the new table after the old one is finished either by us or by the rehasher. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c93ff8ac474a..4192682c1d5c 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -53,6 +53,7 @@ struct rhash_head { * @shift: Current size (1 << shift) * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets + * @walkers: List of active walkers * @buckets: size * hash buckets */ struct bucket_table { @@ -61,6 +62,7 @@ struct bucket_table { u32 shift; unsigned int locks_mask; spinlock_t *locks; + struct list_head walkers; struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; @@ -104,7 +106,6 @@ struct rhashtable_params { * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping - * @walkers: List of active walkers * @being_destroyed: True if table is set up for destruction */ struct rhashtable { @@ -115,17 +116,16 @@ struct rhashtable { struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; - struct list_head walkers; }; /** * struct rhashtable_walker - Hash table walker * @list: List entry on list of walkers - * @resize: Resize event occured + * @tbl: The table that we were walking over */ struct rhashtable_walker { struct list_head list; - bool resize; + struct bucket_table *tbl; }; /** -- cgit v1.2.3 From 9d901bc05153bbf33b5da2cd6266865e531f0545 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 14 Mar 2015 13:57:23 +1100 Subject: rhashtable: Free bucket tables asynchronously after rehash There is in fact no need to wait for an RCU grace period in the rehash function, since all insertions are guaranteed to go into the new table through spin locks. This patch uses call_rcu to free the old/rehashed table at our leisure. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 4192682c1d5c..a0abddd226b3 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -54,6 +54,7 @@ struct rhash_head { * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets * @walkers: List of active walkers + * @rcu: RCU structure for freeing the table * @buckets: size * hash buckets */ struct bucket_table { @@ -63,6 +64,7 @@ struct bucket_table { unsigned int locks_mask; spinlock_t *locks; struct list_head walkers; + struct rcu_head rcu; struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -- cgit v1.2.3 From 63d512d0cffcae40505d9448abd509972465e846 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 14 Mar 2015 13:57:24 +1100 Subject: rhashtable: Add rehash counter to bucket_table This patch adds a rehash counter to bucket_table to indicate the last bucket that has been rehashed. This serves two purposes: 1. Any bucket that has been rehashed can never gain a new object. 2. If the rehash counter reaches the size of the table, the table will forever remain empty. This patch also downsizes bucket_table->size to an unsigned int since we do not support sizes greater than 32 bits yet. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index a0abddd226b3..ed7562ad4ca0 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -49,6 +49,7 @@ struct rhash_head { /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets + * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash * @shift: Current size (1 << shift) * @locks_mask: Mask to apply before accessing locks[] @@ -58,7 +59,8 @@ struct rhash_head { * @buckets: size * hash buckets */ struct bucket_table { - size_t size; + unsigned int size; + unsigned int rehash; u32 hash_rnd; u32 shift; unsigned int locks_mask; -- cgit v1.2.3 From c4db8848af6af92f90462258603be844baeab44d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 14 Mar 2015 13:57:25 +1100 Subject: rhashtable: Move future_tbl into struct bucket_table This patch moves future_tbl to open up the possibility of having multiple rehashes on the same table. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index ed7562ad4ca0..1695378b3c5b 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -56,6 +56,7 @@ struct rhash_head { * @locks: Array of spinlocks protecting individual buckets * @walkers: List of active walkers * @rcu: RCU structure for freeing the table + * @future_tbl: Table under construction during rehashing * @buckets: size * hash buckets */ struct bucket_table { @@ -68,6 +69,8 @@ struct bucket_table { struct list_head walkers; struct rcu_head rcu; + struct bucket_table __rcu *future_tbl; + struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; @@ -105,7 +108,6 @@ struct rhashtable_params { /** * struct rhashtable - Hash table handle * @tbl: Bucket table - * @future_tbl: Table under construction during expansion/shrinking * @nelems: Number of elements in table * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously @@ -114,7 +116,6 @@ struct rhashtable_params { */ struct rhashtable { struct bucket_table __rcu *tbl; - struct bucket_table __rcu *future_tbl; atomic_t nelems; bool being_destroyed; struct rhashtable_params p; -- cgit v1.2.3 From 6befc6445ffc6868ee6e6d0e012fc149e88d96db Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:53 -0700 Subject: Bluetooth: Add flags field and setting function for HCI sockets To filter out certain actions for certain HCI sockets introcuce a flags field that allows to configure specific settings on individual sockets. Since the hci_pinfo structure is private in hci_sock.c, provide helper functions for setting and clearing a given flag. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/bluetooth.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e598ca096ec9..ae1f2ee1eaf3 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -335,6 +335,9 @@ out: int bt_to_errno(__u16 code); +void hci_sock_set_flag(struct sock *sk, int nr); +void hci_sock_clear_flag(struct sock *sk, int nr); + int hci_sock_init(void); void hci_sock_cleanup(void); -- cgit v1.2.3 From 17711c62915dd62ab83a5a83a64c0d6105d13b6c Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:54 -0700 Subject: Bluetooth: Provide hci_send_to_flagged_channel helper function The hci_send_to_flagged_channel helper function can be used to send packets to all channels that have a certain HCI socket flag set. This is especially useful for managment events that are limited to sockets that have first enabled certain functionality. This allows for filtering of events without confusing existing users. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6afbf5b014a1..d38f6e426e84 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1285,6 +1285,8 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, struct sock *skip_sk); +void hci_send_to_flagged_channel(unsigned short channel, struct sk_buff *skb, + int flag); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); -- cgit v1.2.3 From f920733885546af2fd8d4b3dd5f8a1ac029f6248 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:55 -0700 Subject: Bluetooth: Use special function to send filter management index events For sending Index Added, Index Removed, Unconfigured Index Added and Unconfigured Index Removed managment events the new helper functions allows taking into account if these events are enabled for a certain management socket or not. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index d942fedbaedd..0995ec755959 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -179,6 +179,12 @@ enum { HCI_RESET, }; +/* HCI socket flags */ +enum { + HCI_MGMT_INDEX_EVENTS, + HCI_MGMT_UNCONF_INDEX_EVENTS, +}; + /* * BR/EDR and/or LE controller flags: the flags defined here should represent * states from the controller. -- cgit v1.2.3 From ced85549c3a769dfb9d084bb8d6d9ca8075f8728 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:56 -0700 Subject: Bluetooth: Add support for extended index management events This introduces support for using Extended Index Added and Extended Index Removed events. These events contain the controller type and also the hardware bus information from the driver. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/mgmt.h | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 0995ec755959..b8318711135a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -183,6 +183,7 @@ enum { enum { HCI_MGMT_INDEX_EVENTS, HCI_MGMT_UNCONF_INDEX_EVENTS, + HCI_MGMT_EXT_INDEX_EVENTS, }; /* diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 5bf6af9cee78..8562f9ecf230 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -692,3 +692,12 @@ struct mgmt_ev_new_conn_param { #define MGMT_EV_UNCONF_INDEX_REMOVED 0x001e #define MGMT_EV_NEW_CONFIG_OPTIONS 0x001f + +struct mgmt_ev_ext_index { + __u8 type; + __u8 bus; +} __packed; + +#define MGMT_EV_EXT_INDEX_ADDED 0x0020 + +#define MGMT_EV_EXT_INDEX_REMOVED 0x0021 -- cgit v1.2.3 From 96f1474af040a4ec267efe141cbf264891e67e5a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:57 -0700 Subject: Bluetooth: Add support for extended index management command The Read Extended Contoller Index List command can be used for retrieving the complete list of local available controllers. This included configured, unconfigured and also AMP controllers. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/mgmt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 8562f9ecf230..2534bd4d22b2 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -505,6 +505,17 @@ struct mgmt_cp_start_service_discovery { } __packed; #define MGMT_START_SERVICE_DISCOVERY_SIZE 4 +#define MGMT_OP_READ_EXT_INDEX_LIST 0x003C +#define MGMT_READ_EXT_INDEX_LIST_SIZE 0 +struct mgmt_rp_read_ext_index_list { + __le16 num_controllers; + struct { + __le16 index; + __u8 type; + __u8 bus; + } entry[0]; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.2.3 From 50ebc055fa758c731e6e1ce174608327aab07aec Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:58 -0700 Subject: Bluetooth: Introduce trusted flag for management control sockets Providing a global trusted flag for management control sockets provides an easy way for identifying sockets and imposing restriction on it. For now all management sockets are trusted since they require CAP_NET_ADMIN. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b8318711135a..7a24acaafeea 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -181,6 +181,7 @@ enum { /* HCI socket flags */ enum { + HCI_SOCK_TRUSTED, HCI_MGMT_INDEX_EVENTS, HCI_MGMT_UNCONF_INDEX_EVENTS, HCI_MGMT_EXT_INDEX_EVENTS, -- cgit v1.2.3 From c08b1a1dba524c1cdef331c1f169db3a1b37bb4c Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:27:59 -0700 Subject: Bluetooth: Consolidate socket channel sending function back into one With the introduction of trusted socket flag for control and monitor channels, it is now possible to use a single function for sending packets to these sockets. And with that consolidate the handling. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d38f6e426e84..859005c9a8fc 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1284,9 +1284,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, - struct sock *skip_sk); -void hci_send_to_flagged_channel(unsigned short channel, struct sk_buff *skb, - int flag); + int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); -- cgit v1.2.3 From c85be545ea23a4fe590c89683242a9be823394e0 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:28:00 -0700 Subject: Bluetooth: Add hci_sock_test_flag helper function The management interface will need access to the socket flags and so provide a helper function for checking them. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/bluetooth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ae1f2ee1eaf3..d871ba313f64 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -337,6 +337,7 @@ int bt_to_errno(__u16 code); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); +int hci_sock_test_flag(struct sock *sk, int nr); int hci_sock_init(void); void hci_sock_cleanup(void); -- cgit v1.2.3 From c91041dc4efff71f29f1dd4c9a4a5e80b841395c Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:28:01 -0700 Subject: Bluetooth: Add support for untrusted access to management commands Some management commands are safe to be accessed from any user without special permissions. First step for allowing access to any of these commands from untrusted application is to mark them accordingly. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 859005c9a8fc..3546789c1616 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1291,7 +1291,8 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event); #define HCI_MGMT_VAR_LEN (1 << 0) #define HCI_MGMT_NO_HDEV (1 << 1) -#define HCI_MGMT_UNCONFIGURED (1 << 2) +#define HCI_MGMT_UNTRUSTED (1 << 2) +#define HCI_MGMT_UNCONFIGURED (1 << 3) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, -- cgit v1.2.3 From c927a10487477eeed0441e5c88147700e69e5db9 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:28:03 -0700 Subject: Bluetooth: Add support for trust verification of management commands Check the required trust level of each management command with the trust level of the management socket. If it does not match up, then return the newly introduced permission denied error. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/mgmt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 2534bd4d22b2..f3baad589db0 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -44,6 +44,7 @@ #define MGMT_STATUS_INVALID_INDEX 0x11 #define MGMT_STATUS_RFKILLED 0x12 #define MGMT_STATUS_ALREADY_PAIRED 0x13 +#define MGMT_STATUS_PERMISSION_DENIED 0x14 struct mgmt_hdr { __le16 opcode; -- cgit v1.2.3 From f6b7712eb660c50877a56772908326cd31125b21 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:28:05 -0700 Subject: Bluetooth: Send global configuration updates to all management users Changes to the global configuration updates like settings, class of device, name etc. can be received by every user. They are allowed to read them in the first place so provide the updates via events as well. Otherwise untrusted users start polling for updates and that is not a desired behavior. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7a24acaafeea..7f41c7741e76 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -185,6 +185,7 @@ enum { HCI_MGMT_INDEX_EVENTS, HCI_MGMT_UNCONF_INDEX_EVENTS, HCI_MGMT_EXT_INDEX_EVENTS, + HCI_MGMT_GENERIC_EVENTS, }; /* -- cgit v1.2.3 From a958452aa40c57a0407ecf84ba1bfa31ad532313 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 19:28:06 -0700 Subject: Bluetooth: Use BIT(n) macro instead of manually encoding (1 << n) The flags for the management command table used manual encoding of bits in the form of (1 << n). It is however preferred to use BIT(n) macro instead. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3546789c1616..ce94bcb33600 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1289,10 +1289,10 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); -#define HCI_MGMT_VAR_LEN (1 << 0) -#define HCI_MGMT_NO_HDEV (1 << 1) -#define HCI_MGMT_UNTRUSTED (1 << 2) -#define HCI_MGMT_UNCONFIGURED (1 << 3) +#define HCI_MGMT_VAR_LEN BIT(0) +#define HCI_MGMT_NO_HDEV BIT(1) +#define HCI_MGMT_UNTRUSTED BIT(2) +#define HCI_MGMT_UNCONFIGURED BIT(3) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, -- cgit v1.2.3 From d3d5305bfd1cb48c8f44207abb567276a1e09cc7 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 20:53:25 -0700 Subject: Bluetooth: Add simple version of Read Advertising Features command This adds support for the simplest possible version of Read Advertising Features management command. It allows basic testing of the interface. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/mgmt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index f3baad589db0..4d0ccd194c01 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -517,6 +517,17 @@ struct mgmt_rp_read_ext_index_list { } entry[0]; } __packed; +#define MGMT_OP_READ_ADV_FEATURES 0x0003D +#define MGMT_READ_ADV_FEATURES_SIZE 0 +struct mgmt_rp_read_adv_features { + __le32 supported_flags; + __u8 max_adv_data_len; + __u8 max_scan_rsp_len; + __u8 max_instances; + __u8 num_instances; + __u8 instance[0]; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.2.3 From 1471aae0d04d4e0df2bf1e5a5af861e28371b8b4 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 22:43:18 -0700 Subject: Bluetooth: Add defines for LE Bluetooth Device Address and LE Role The OOB data requires to include LE Bluetooth Device Address and LE Role and so add the type constants for these fields. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7f41c7741e76..af9893b704ff 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -456,6 +456,8 @@ enum { #define EIR_SSP_HASH_C 0x0E /* Simple Pairing Hash C */ #define EIR_SSP_RAND_R 0x0F /* Simple Pairing Randomizer R */ #define EIR_DEVICE_ID 0x10 /* device ID */ +#define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ +#define EIR_LE_ROLE 0x1C /* LE role */ /* Low Energy Advertising Flags */ #define LE_AD_LIMITED 0x01 /* Limited Discoverable */ -- cgit v1.2.3 From 4f0f155ceaf7e1b59d210a8afb24d4ea63ce13cc Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 14 Mar 2015 22:43:19 -0700 Subject: Bluetooth: Add simple version of Read Local OOB Extended Data command This adds support for the simplest possible version of Read Local OOB Extended Data management command. It includes all mandatory fields, but none of the actual pairing related ones. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/mgmt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 4d0ccd194c01..543c1ba3d892 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -506,6 +506,17 @@ struct mgmt_cp_start_service_discovery { } __packed; #define MGMT_START_SERVICE_DISCOVERY_SIZE 4 +#define MGMT_OP_READ_LOCAL_OOB_EXT_DATA 0x003B +struct mgmt_cp_read_local_oob_ext_data { + __u8 type; +} __packed; +#define MGMT_READ_LOCAL_OOB_EXT_DATA_SIZE 1 +struct mgmt_rp_read_local_oob_ext_data { + __u8 type; + __le16 eir_len; + __u8 eir[0]; +} __packed; + #define MGMT_OP_READ_EXT_INDEX_LIST 0x003C #define MGMT_READ_EXT_INDEX_LIST_SIZE 0 struct mgmt_rp_read_ext_index_list { -- cgit v1.2.3 From 03e69b508b6f7c51743055c9f61d1dfeadf4b635 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 14 Mar 2015 02:27:16 +0100 Subject: ebpf: add prandom helper for packet sampling This work is similar to commit 4cd3675ebf74 ("filter: added BPF random opcode") and adds a possibility for packet sampling in eBPF. Currently, this is only possible in classic BPF and useful to combine sampling with f.e. packet sockets, possible also with tc. Example function proto-type looks like: u32 (*prandom_u32)(void) = (void *)BPF_FUNC_get_prandom_u32; Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80f2e0fc3d02..50bf95e29a96 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -154,4 +154,6 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_get_prandom_u32_proto; + #endif /* _LINUX_BPF_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3fa1af8a58d7..1c2ca2b477c8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -165,6 +165,7 @@ enum bpf_func_id { BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ + BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From c04167ce2ca0ecaeaafef006cb0d65cf01b68e42 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 14 Mar 2015 02:27:17 +0100 Subject: ebpf: add helper for obtaining current processor id This patch adds the possibility to obtain raw_smp_processor_id() in eBPF. Currently, this is only possible in classic BPF where commit da2033c28226 ("filter: add SKF_AD_RXHASH and SKF_AD_CPU") has added facilities for this. Perhaps most importantly, this would also allow us to track per CPU statistics with eBPF maps, or to implement a poor-man's per CPU data structure through eBPF maps. Example function proto-type looks like: u32 (*smp_processor_id)(void) = (void *)BPF_FUNC_get_smp_processor_id; Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50bf95e29a96..30bfd331882a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -155,5 +155,6 @@ extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; +extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1c2ca2b477c8..de1f63668daf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -166,6 +166,7 @@ enum bpf_func_id { BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ + BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From 9bac3d6d548e5cc925570b263f35b70a00a00ffd Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 13 Mar 2015 11:57:42 -0700 Subject: bpf: allow extended BPF programs access skb fields introduce user accessible mirror of in-kernel 'struct sk_buff': struct __sk_buff { __u32 len; __u32 pkt_type; __u32 mark; __u32 queue_mapping; }; bpf programs can do: int bpf_prog(struct __sk_buff *skb) { __u32 var = skb->pkt_type; which will be compiled to bpf assembler as: dst_reg = *(u32 *)(src_reg + 4) // 4 == offsetof(struct __sk_buff, pkt_type) bpf verifier will check validity of access and will convert it to: dst_reg = *(u8 *)(src_reg + offsetof(struct sk_buff, __pkt_type_offset)) dst_reg &= 7 since skb->pkt_type is a bitfield. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 5 ++++- include/uapi/linux/bpf.h | 10 ++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 30bfd331882a..280a315de8d6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -103,6 +103,9 @@ struct bpf_verifier_ops { * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type); + + u32 (*convert_ctx_access)(int dst_reg, int src_reg, int ctx_off, + struct bpf_insn *insn); }; struct bpf_prog_type_list { @@ -133,7 +136,7 @@ struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index de1f63668daf..929545a27546 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -170,4 +170,14 @@ enum bpf_func_id { __BPF_FUNC_MAX_ID, }; +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From 4170604feec780d00e7511c24fa0f6e5c2e4ed75 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 15 Mar 2015 21:07:14 -0700 Subject: switchdev: add swdev ops As discussed at netconf, introduce swdev_ops as first step to move switchdev ops from ndo to swdev. This will keep switchdev from cluttering up ndo ops space. Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ include/net/switchdev.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddab1a2a07a0..9e8a2a933c68 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1577,6 +1577,9 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; const struct forwarding_accel_ops *fwd_ops; +#ifdef CONFIG_NET_SWITCHDEV + const struct swdev_ops *swdev_ops; +#endif const struct header_ops *header_ops; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1a9382febcc3..e5de53f92482 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -14,6 +14,44 @@ #include #include +struct fib_info; + +/** + * struct switchdev_ops - switchdev operations + * + * int (*swdev_parent_id_get)(struct net_device *dev, + * struct netdev_phys_item_id *psid); + * Called to get an ID of the switch chip this port is part of. + * If driver implements this, it indicates that it represents a port + * of a switch chip. + * + * int (*swdev_port_stp_update)(struct net_device *dev, u8 state); + * Called to notify switch device port of bridge port STP + * state change. + * + * int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 nlflags, u32 tb_id); + * Called to add/modify IPv4 route to switch device. + * + * int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to delete IPv4 route from switch device. + */ +struct swdev_ops { + int (*swdev_parent_id_get)(struct net_device *dev, + struct netdev_phys_item_id *psid); + int (*swdev_port_stp_update)(struct net_device *dev, u8 state); + int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, + u32 tb_id); + int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +}; + enum netdev_switch_notifier_type { NETDEV_SWITCH_FDB_ADD = 1, NETDEV_SWITCH_FDB_DEL, -- cgit v1.2.3 From 812a1c3ff3ee9d5100e0e71edb06681014e84a9b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Sun, 15 Mar 2015 21:07:16 -0700 Subject: netdev: remove ndo ops for switchdev Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e8a2a933c68..dd1d069758be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,8 +768,6 @@ struct netdev_phys_item_id { typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -struct fib_info; - /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1024,23 +1022,6 @@ struct fib_info; * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. - * - * int (*ndo_switch_parent_id_get)(struct net_device *dev, - * struct netdev_phys_item_id *psid); - * Called to get an ID of the switch chip this port is part of. - * If driver implements this, it indicates that it represents a port - * of a switch chip. - * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state); - * Called to notify switch device port of bridge port STP - * state change. - * int (*ndo_sw_parent_fib_ipv4_add)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 nlflags, u32 tb_id); - * Called to add/modify IPv4 route to switch device. - * int (*ndo_sw_parent_fib_ipv4_del)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); - * Called to delete IPv4 route from switch device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1197,25 +1178,6 @@ struct net_device_ops { netdev_features_t (*ndo_features_check) (struct sk_buff *skb, struct net_device *dev, netdev_features_t features); -#ifdef CONFIG_NET_SWITCHDEV - int (*ndo_switch_parent_id_get)(struct net_device *dev, - struct netdev_phys_item_id *psid); - int (*ndo_switch_port_stp_update)(struct net_device *dev, - u8 state); - int (*ndo_switch_fib_ipv4_add)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 nlflags, - u32 tb_id); - int (*ndo_switch_fib_ipv4_del)(struct net_device *dev, - __be32 dst, - int dst_len, - struct fib_info *fi, - u8 tos, u8 type, - u32 tb_id); -#endif }; /** -- cgit v1.2.3 From aefedc1a4cfe4c874b8a7ac743f9deedc289d9e6 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 15 Mar 2015 17:08:19 -0700 Subject: Bluetooth: Remove unneeded HCI_CONN_REMOTE_OOB connection flag The HCI_CONN_REMOTE_OOB connection flag is used to indicate if the pairing initiator has provided out-of-band data. However since that value is no longer used in any decision making, just remove it. It is actually unclear what purpose the OOB data present field from the HCI IO Capability Response event serves in the first place. If either side provided out-of-band data, then that data will be used for pairing. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ce94bcb33600..e4dc18eed446 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -596,7 +596,6 @@ enum { HCI_CONN_SC_ENABLED, HCI_CONN_AES_CCM, HCI_CONN_POWER_SAVE, - HCI_CONN_REMOTE_OOB, HCI_CONN_FLUSH_KEY, HCI_CONN_ENCRYPT, HCI_CONN_AUTH, -- cgit v1.2.3 From dc5a1ad7bd830b7789ba2950342bdecfe4787945 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Thu, 12 Mar 2015 08:53:24 +0200 Subject: mac80211: allow to get wireless_dev structure from ieee80211_vif This will allow mac80211 drivers to call cfg80211 APIs with the right handle. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a7756e45465e..157c0f151766 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1281,6 +1281,19 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) */ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); +/** + * ieee80211_vif_to_wdev - return a wdev struct from a vif + * @vif: the vif to get the wdev for + * + * This can be used by mac80211 drivers with direct cfg80211 APIs + * (like the vendor commands) that needs to get the wdev for a vif. + * + * Note that this function may return %NULL if the given wdev isn't + * associated with a vif that the driver knows about (e.g. monitor + * or AP_VLAN interfaces.) + */ +struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); + /** * enum ieee80211_key_flags - key flags * -- cgit v1.2.3 From f709bfcf6a292560ce187c33fd099ee495c0a404 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 16 Mar 2015 01:10:20 -0700 Subject: Bluetooth: Add constants for LE SC Confirmation and Random values The LE Secure Connections Confirmation Value and LE Secure Connections Random Value contants are required for the out-of-band data and so just define them. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index af9893b704ff..ce757303dc07 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -458,6 +458,8 @@ enum { #define EIR_DEVICE_ID 0x10 /* device ID */ #define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ #define EIR_LE_ROLE 0x1C /* LE role */ +#define EIR_LE_SC_CONFIRM 0x22 /* LE SC Confirmation Value */ +#define EIR_LE_SC_RANDOM 0x23 /* LE SC Random Value */ /* Low Energy Advertising Flags */ #define LE_AD_LIMITED 0x01 /* Limited Discoverable */ -- cgit v1.2.3 From c055d5b03bb4cb69d349d787c9787c0383abd8b2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 10 Mar 2015 05:08:19 +0100 Subject: netfilter: bridge: query conntrack about skb dnat ask conntrack instead of storing ipv4 address in nf_bridge_info->data. Ths avoids the need to use ->data during NF_PRE_ROUTING. Only two functions that need ->data remain. These will be addressed in followup patches. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index bb39113ea596..de123d769ffc 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -54,12 +54,6 @@ static inline unsigned int nf_bridge_pad(const struct sk_buff *skb) return 0; } -struct bridge_skb_cb { - union { - __be32 ipv4; - } daddr; -}; - static inline void br_drop_fake_rtable(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); -- cgit v1.2.3 From e4bb9bcbfb7d67431dfd49860f62770a7f40193b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 10 Mar 2015 10:36:48 +0100 Subject: netfilter: bridge: remove BRNF_STATE_BRIDGED flag Its not needed anymore since 2bf540b73ed5b ([NETFILTER]: bridge-netfilter: remove deferred hooks). Before this it was possible to have physoutdev set for locally generated packets -- this isn't the case anymore: BRNF_STATE_BRIDGED flag is set when we assign nf_bridge->physoutdev, so physoutdev != NULL means BRNF_STATE_BRIDGED is set. If physoutdev is NULL, then we are looking at locally-delivered and routed packet. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index de123d769ffc..ed0d3bf953c3 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -19,7 +19,6 @@ enum nf_br_hook_priorities { #define BRNF_PKT_TYPE 0x01 #define BRNF_BRIDGED_DNAT 0x02 -#define BRNF_BRIDGED 0x04 #define BRNF_NF_BRIDGE_PREROUTING 0x08 #define BRNF_8021Q 0x10 #define BRNF_PPPoE 0x20 -- cgit v1.2.3 From 1d0ab253872cdd3d8e7913f59c266c7fd01771d0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 Mar 2015 21:12:12 -0700 Subject: net: add sk_fullsock() helper We have many places where we want to check if a socket is not a timewait or request socket. Use a helper to avoid hard coding this. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index f10832ca2e90..e0360f5a53e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -67,6 +67,7 @@ #include #include #include +#include #include struct cgroup; @@ -2218,6 +2219,14 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb) return NULL; } +/* This helper checks if a socket is a full socket, + * ie _not_ a timewait or request socket. + */ +static inline bool sk_fullsock(const struct sock *sk) +{ + return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); -- cgit v1.2.3 From 13854e5a60461daee08ce99842b7f4d37553d911 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 Mar 2015 21:12:16 -0700 Subject: inet: add proper refcounting to request sock reqsk_put() is the generic function that should be used to release a refcount (and automatically call reqsk_free()) reqsk_free() might be called if refcount is known to be 0 or undefined. refcnt is set to one in inet_csk_reqsk_queue_add() As request socks are not yet in global ehash table, I added temporary debugging checks in reqsk_put() and reqsk_free() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 5 +++++ include/net/inet_sock.h | 5 +++++ include/net/request_sock.h | 13 +++++++------ 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b9a6b0a94cc6..191feec60205 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -275,6 +275,11 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, struct sock *child) { reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); + /* before letting lookups find us, make sure all req fields + * are committed to memory. + */ + smp_wmb(); + atomic_set(&req->rsk_refcnt, 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b3053fdd871e..3d8c09abb097 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -255,6 +255,11 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops ireq->opt = NULL; atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&ireq->ireq_refcnt, 0); } return req; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 3275cf31f731..56dc2faba47e 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -82,19 +82,20 @@ static inline struct request_sock *inet_reqsk(struct sock *sk) return (struct request_sock *)sk; } -static inline void __reqsk_free(struct request_sock *req) -{ - kmem_cache_free(req->rsk_ops->slab, req); -} - static inline void reqsk_free(struct request_sock *req) { + /* temporary debugging */ + WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); + req->rsk_ops->destructor(req); - __reqsk_free(req); + kmem_cache_free(req->rsk_ops->slab, req); } static inline void reqsk_put(struct request_sock *req) { + /* temporary debugging, until req sock are put into ehash table */ + WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 1); + if (atomic_dec_and_test(&req->rsk_refcnt)) reqsk_free(req); } -- cgit v1.2.3 From 72000df2c01d6927319ad7e3f43460f6d0227de5 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 16 Mar 2015 16:11:21 -0700 Subject: Bluetooth: Add support for Local OOB Extended Data Update events When a different user requests a new set of local out-of-band data, then inform all previous users that the data has been updated. To limit the scope of users, the updates are limited to previous users. If a user has never requested out-of-band data, it will also not see the update. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/mgmt.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index ce757303dc07..a6ea156dc7e9 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -186,6 +186,7 @@ enum { HCI_MGMT_UNCONF_INDEX_EVENTS, HCI_MGMT_EXT_INDEX_EVENTS, HCI_MGMT_GENERIC_EVENTS, + HCI_MGMT_OOB_DATA_EVENTS, }; /* diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 543c1ba3d892..a1a68671bf88 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -735,3 +735,10 @@ struct mgmt_ev_ext_index { #define MGMT_EV_EXT_INDEX_ADDED 0x0020 #define MGMT_EV_EXT_INDEX_REMOVED 0x0021 + +#define MGMT_EV_LOCAL_OOB_DATA_UPDATED 0x0022 +struct mgmt_ev_local_oob_data_updated { + __u8 type; + __le16 eir_len; + __u8 eir[0]; +} __packed; -- cgit v1.2.3 From e03826d5045e81a66a4fad7be9a8ecdaeb7911cf Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 17 Mar 2015 15:56:04 +0530 Subject: regulator: palmas: Correct TPS659038 register definition for REGEN2 The register offset for REGEN2_CTRL in different for TPS659038 chip as when compared with other Palmas family PMICs. In the case of TPS659038 the wrong offset pointed to PLLEN_CTRL and was causing a hang. Correcting the same. Signed-off-by: Keerthy Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/mfd/palmas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index fb0390a1a498..ee7b1ce7a6f8 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -2999,6 +2999,9 @@ enum usb_irq_events { #define PALMAS_GPADC_TRIM15 0x0E #define PALMAS_GPADC_TRIM16 0x0F +/* TPS659038 regen2_ctrl offset iss different from palmas */ +#define TPS659038_REGEN2_CTRL 0x12 + /* TPS65917 Interrupt registers */ /* Registers for function INTERRUPT */ -- cgit v1.2.3 From a2f4870697a5bcf4a87073ec6b32dd2928c1211d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:19 -0400 Subject: fs: make sure the timestamps for lazytime inodes eventually get written Jan Kara pointed out that if there is an inode which is constantly getting dirtied with I_DIRTY_PAGES, an inode with an updated timestamp will never be written since inode->dirtied_when is constantly getting updated. We fix this by adding an extra field to the inode, dirtied_time_when, so inodes with a stale dirtytime can get detected and handled. In addition, if we have a dirtytime inode caused by an atime update, and there is no write activity on the file system, we need to have a secondary system to make sure these inodes get written out. We do this by setting up a second delayed work structure which wakes up the CPU much more rarely compared to writeback_expire_centisecs. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b4d71b5e1ff2..f4131e8ead74 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -604,6 +604,7 @@ struct inode { struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ + unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ -- cgit v1.2.3 From 1efff914afac8a965ad63817ecf8861a927c2ace Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:32 -0400 Subject: fs: add dirtytime_expire_seconds sysctl Add a tuning knob so we can adjust the dirtytime expiration timeout, which is very useful for testing lazytime. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- include/linux/writeback.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 00048339c23e..b2dd371ec0ca 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -130,6 +130,7 @@ extern int vm_dirty_ratio; extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; +extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; @@ -146,6 +147,8 @@ extern int dirty_ratio_handler(struct ctl_table *table, int write, extern int dirty_bytes_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; int dirty_writeback_centisecs_handler(struct ctl_table *, int, -- cgit v1.2.3 From 695c4cb61926ddef2481dbcefef44498a7c1e5b5 Mon Sep 17 00:00:00 2001 From: Jakub Pawlowski Date: Tue, 17 Mar 2015 09:04:12 -0700 Subject: Bluetooth: Introduce HCI_QUIRK_SIMULTANEOUS_DISCOVERY Some controllers allow both LE scan and BR/EDR inquiry to run at the same time, while others allow only one, LE SCAN or BR/EDR inquiry at given time. Since this is specific to each controller, add a new quirk setting that allows drivers to tell the core wether given controller can do both LE scan and BR/EDR inquiry at same time. Signed-off-by: Jakub Pawlowski Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a6ea156dc7e9..06e7eee31ce4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -160,6 +160,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_STRICT_DUPLICATE_FILTER, + + /* When this quirk is set, LE scan and BR/EDR inquiry is done + * simultaneously, otherwise it's interleaved. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_SIMULTANEOUS_DISCOVERY, }; /* HCI device flags */ -- cgit v1.2.3 From d0f172b14afa7e0d8a19db5baa07e20b3ec8dcc8 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 17 Mar 2015 13:48:46 +0200 Subject: Bluetooth: Add helper to get HCI channel of a socket We'll need to have access to which HCI channel a socket is bound to, in order to manage pending mgmt commands in clean way. This patch adds a helper for the purpose. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index d871ba313f64..33a5e00025aa 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -338,6 +338,7 @@ int bt_to_errno(__u16 code); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); int hci_sock_test_flag(struct sock *sk, int nr); +unsigned short hci_sock_get_channel(struct sock *sk); int hci_sock_init(void); void hci_sock_cleanup(void); -- cgit v1.2.3 From 88b94ce925cb103851f39bfa7e23e09823573d30 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 17 Mar 2015 13:48:49 +0200 Subject: Bluetooth: Add hdev_init callback for HCI channels In order to make the mgmt command handling more generic we can't have a direct call to mgmt_init_hdev() from mgmt_control(). This patch adds a new callback to struct hci_mgmt_chan. And sets it to point to the mgmt_init_hdev() function for the HCI_CHANNEL_CONTROL instance. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e4dc18eed446..93e7b2b05a17 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1305,6 +1305,7 @@ struct hci_mgmt_chan { unsigned short channel; size_t handler_count; const struct hci_mgmt_handler *handlers; + void (*hdev_init) (struct sock *sk, struct hci_dev *hdev); }; int hci_mgmt_chan_register(struct hci_mgmt_chan *c); -- cgit v1.2.3 From fa4335d71a1408d0112c15874538f3f4e153ba01 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 17 Mar 2015 13:48:50 +0200 Subject: Bluetooth: Move generic mgmt command dispatcher to hci_sock.c The mgmt.c file should be reserved purely for HCI_CHANNEL_CONTROL. The mgmt_control() function in it is already completely generic and has a single user in hci_sock.c. This patch moves the function there and renames it a bit more appropriately to hci_mgmt_cmd() (as it's a command dispatcher). Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 93e7b2b05a17..b65c53de6a69 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1330,9 +1330,6 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ -int mgmt_control(struct hci_mgmt_chan *chan, struct sock *sk, - struct msghdr *msg, size_t msglen); - int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); -- cgit v1.2.3 From c24973957975403521ca76a776c2dfd12fbe9add Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 16 Mar 2015 18:06:02 -0700 Subject: bpf: allow BPF programs access 'protocol' and 'vlan_tci' fields as a follow on to patch 70006af95515 ("bpf: allow eBPF access skb fields") this patch allows 'protocol' and 'vlan_tci' fields to be accessible from extended BPF programs. The usage of 'protocol', 'vlan_present' and 'vlan_tci' fields is the same as corresponding SKF_AD_PROTOCOL, SKF_AD_VLAN_TAG_PRESENT and SKF_AD_VLAN_TAG accesses in classic BPF. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 929545a27546..1623047af463 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -178,6 +178,9 @@ struct __sk_buff { __u32 pkt_type; __u32 mark; __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; }; #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From adc17d6a6ca08d11f70f6c49f3d40b87b68fe53f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Mar 2015 21:06:18 -0700 Subject: inet: move ir_mark to fill a hole On 64bit arches, we can save 8 bytes in inet_request_sock by moving ir_mark to fill a hole. While we are at it, inet_request_mark() can get a const qualifier for listener socket. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 3d8c09abb097..c9ed91891887 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -94,11 +94,11 @@ struct inet_request_sock { acked : 1, no_srccheck: 1; kmemcheck_bitfield_end(flags); + u32 ir_mark; union { struct ip_options_rcu *opt; struct sk_buff *pktopts; }; - u32 ir_mark; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) @@ -106,13 +106,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } -static inline u32 inet_request_mark(struct sock *sk, struct sk_buff *skb) +static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) { + if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) return skb->mark; - } else { - return sk->sk_mark; - } + + return sk->sk_mark; } struct inet_cork { -- cgit v1.2.3 From 1bfc4438a7ef99e8a6cba0bd3a86249430256621 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Mar 2015 21:06:19 -0700 Subject: tcp: move tcp_openreq_init() to tcp_input.c This big helper is called once from tcp_conn_request(), there is no point having it in an include. Compiler will inline it anyway. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2e11e38205c2..9fe1d535cd6c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1137,31 +1137,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_openreq_init(struct request_sock *req, - struct tcp_options_received *rx_opt, - struct sk_buff *skb, struct sock *sk) -{ - struct inet_request_sock *ireq = inet_rsk(req); - - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; - tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->last_oow_ack_time = 0; - req->mss = rx_opt->mss_clamp; - req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - ireq->tstamp_ok = rx_opt->tstamp_ok; - ireq->sack_ok = rx_opt->sack_ok; - ireq->snd_wscale = rx_opt->snd_wscale; - ireq->wscale_ok = rx_opt->wscale_ok; - ireq->acked = 0; - ireq->ecn_ok = 0; - ireq->ir_rmt_port = tcp_hdr(skb)->source; - ireq->ir_num = ntohs(tcp_hdr(skb)->dest); - ireq->ir_mark = inet_request_mark(sk, skb); -} - extern void tcp_openreq_init_rwin(struct request_sock *req, struct sock *sk, struct dst_entry *dst); -- cgit v1.2.3 From 7970ddc8f9ffe149b392975da60739ccd1796dea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Mar 2015 21:06:20 -0700 Subject: tcp: uninline tcp_oow_rate_limited() tcp_oow_rate_limited() is hardly used in fast path, there is no point inlining it. Signed-of-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 32 ++------------------------------ 1 file changed, 2 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 9fe1d535cd6c..5b29835b81d8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1216,36 +1216,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, return true; } -/* Return true if we're currently rate-limiting out-of-window ACKs and - * thus shouldn't send a dupack right now. We rate-limit dupacks in - * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS - * attacks that send repeated SYNs or ACKs for the same connection. To - * do this, we do not send a duplicate SYNACK or ACK if the remote - * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. - */ -static inline bool tcp_oow_rate_limited(struct net *net, - const struct sk_buff *skb, - int mib_idx, u32 *last_oow_ack_time) -{ - /* Data packets without SYNs are not likely part of an ACK loop. */ - if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && - !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; - -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ -} +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { -- cgit v1.2.3 From 407640de2152e33341ce1131dac269672c3d50f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:26 -0700 Subject: inet: add sk_listener argument to inet_reqsk_alloc() listener socket can be used to set net pointer, and will be later used to hold a reference on listener. Add a const qualifier to first argument (struct request_sock_ops *), and factorize all write_pnet(&ireq->ireq_net, sock_net(sk)); Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c9ed91891887..cf7abb00941b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,16 +244,19 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops) +static inline struct request_sock * +inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = reqsk_alloc(ops); - struct inet_request_sock *ireq = inet_rsk(req); - if (req != NULL) { + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + kmemcheck_annotate_bitfield(ireq, flags); ireq->opt = NULL; atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() -- cgit v1.2.3 From e49bb337d77d54afebe4fe5b9008955e1337f83d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:27 -0700 Subject: inet: uninline inet_reqsk_alloc() inet_reqsk_alloc() is becoming fat and should not be inlined. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index cf7abb00941b..6fec7343070f 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,28 +244,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock * -inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) -{ - struct request_sock *req = reqsk_alloc(ops); - - if (req) { - struct inet_request_sock *ireq = inet_rsk(req); - - kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; - atomic64_set(&ireq->ir_cookie, 0); - ireq->ireq_state = TCP_NEW_SYN_RECV; - write_pnet(&ireq->ireq_net, sock_net(sk_listener)); - - /* Following is temporary. It is coupled with debugging - * helpers in reqsk_put() & reqsk_free() - */ - atomic_set(&ireq->ireq_refcnt, 0); - } - - return req; -} +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { -- cgit v1.2.3 From 4e9a578e5b6bdfa8b7fed7a41f28a86a7cffc85f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:28 -0700 Subject: inet: add rsk_listener field to struct request_sock Once we'll be able to lookup request sockets in ehash table, we'll need to get access to listener which created this request. This avoid doing a lookup to find the listener, which benefits for a more solid SO_REUSEPORT, and is needed once we no longer queue request sock into a listener private queue. Note that 'struct tcp_request_sock'->listener could be reduced to a single bit, as TFO listener should match req->rsk_listener. TFO will no longer need to hold a reference on the listener. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 56dc2faba47e..723d1cbdf20e 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -52,6 +52,7 @@ struct request_sock { #define rsk_refcnt __req_common.skc_refcnt struct request_sock *dl_next; + struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ @@ -67,13 +68,16 @@ struct request_sock { u32 peer_secid; }; -static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops) +static inline struct request_sock * +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); - if (req != NULL) + if (req) { req->rsk_ops = ops; - + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + } return req; } @@ -88,6 +92,8 @@ static inline void reqsk_free(struct request_sock *req) WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); req->rsk_ops->destructor(req); + if (req->rsk_listener) + sock_put(req->rsk_listener); kmem_cache_free(req->rsk_ops->slab, req); } -- cgit v1.2.3 From 9439ce00f208d95703a6725e4ea986dd90e37ffd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:29 -0700 Subject: tcp: rename struct tcp_request_sock listener The listener field in struct tcp_request_sock is a pointer back to the listener. We now have req->rsk_listener, so TCP only needs one boolean and not a full pointer. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 97dbf16f7d9d..f869ae8afbaf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -111,7 +111,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct sock *listener; /* needed for TFO */ + bool tfo_listener; u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ -- cgit v1.2.3 From 0470c8ca1d57927f2cc3e1d5add1fb2834609447 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:31 -0700 Subject: inet: fix request sock refcounting While testing last patch series, I found req sock refcounting was wrong. We must set skc_refcnt to 1 for all request socks added in hashes, but also on request sockets created by FastOpen or syncookies. It is tricky because we need to defer this initialization so that future RCU lookups do not try to take a refcount on a not yet fully initialized request socket. Also get rid of ireq_refcnt alias. Signed-off-by: Eric Dumazet Fixes: 13854e5a6046 ("inet: add proper refcounting to request sock") Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 5 ----- include/net/inet_sock.h | 1 - include/net/request_sock.h | 11 +++++++++++ 3 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 191feec60205..b9a6b0a94cc6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -275,11 +275,6 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, struct sock *child) { reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); - /* before letting lookups find us, make sure all req fields - * are committed to memory. - */ - smp_wmb(); - atomic_set(&req->rsk_refcnt, 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 6fec7343070f..b6c3737da4e9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -81,7 +81,6 @@ struct inet_request_sock { #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state -#define ireq_refcnt req.__req_common.skc_refcnt #define ireq_family req.__req_common.skc_family kmemcheck_bitfield_begin(flags); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 723d1cbdf20e..3fa4f824900a 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -77,6 +77,11 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_ops = ops; sock_hold(sk_listener); req->rsk_listener = sk_listener; + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&req->rsk_refcnt, 0); } return req; } @@ -292,6 +297,12 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, req->sk = NULL; req->dl_next = lopt->syn_table[hash]; + /* before letting lookups find us, make sure all req fields + * are committed to memory and refcnt initialized. + */ + smp_wmb(); + atomic_set(&req->rsk_refcnt, 1); + write_lock(&queue->syn_wait_lock); lopt->syn_table[hash] = req; write_unlock(&queue->syn_wait_lock); -- cgit v1.2.3 From cf39284d41f67964cf42b21bb386c012cf5b7f65 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 18 Mar 2015 08:57:41 +0800 Subject: regulator: Fix documentation for regmap in the config dev_get_regulator() does not exist, fix the typo. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index d4ad5b5a02bb..045f709cb89b 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -316,7 +316,7 @@ struct regulator_desc { * @driver_data: private regulator data * @of_node: OpenFirmware node to parse for device tree bindings (may be * NULL). - * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is + * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is * insufficient. * @ena_gpio_initialized: GPIO controlling regulator enable was properly * initialized, meaning that >= 0 is a valid gpio -- cgit v1.2.3 From 6aebd940840a4d3a0a8ffc5883d3892f4bd61e90 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 18 Mar 2015 20:01:15 +1100 Subject: rhashtable: Remove shift from bucket_table Keeping both size and shift is silly. We only need one. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 1695378b3c5b..f16e85692959 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -51,7 +51,6 @@ struct rhash_head { * @size: Number of hash buckets * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash - * @shift: Current size (1 << shift) * @locks_mask: Mask to apply before accessing locks[] * @locks: Array of spinlocks protecting individual buckets * @walkers: List of active walkers @@ -63,7 +62,6 @@ struct bucket_table { unsigned int size; unsigned int rehash; u32 hash_rnd; - u32 shift; unsigned int locks_mask; spinlock_t *locks; struct list_head walkers; -- cgit v1.2.3 From c2e213cff701fce71a0aba8de82f2c2a4acf52ae Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 18 Mar 2015 20:01:16 +1100 Subject: rhashtable: Introduce max_size/min_size This patch adds the parameters max_size and min_size which are meant to replace max_shift and min_shift. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index f16e85692959..81267fef85d7 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -85,6 +85,8 @@ struct rhashtable; * @head_offset: Offset of rhash_head in struct to be hashed * @max_shift: Maximum number of shifts while expanding * @min_shift: Minimum number of shifts while shrinking + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Function to hash key @@ -97,6 +99,8 @@ struct rhashtable_params { size_t head_offset; size_t max_shift; size_t min_shift; + unsigned int max_size; + unsigned int min_size; u32 nulls_base; size_t locks_mul; rht_hashfn_t hashfn; -- cgit v1.2.3 From e2e21c1c5808e5dfd88d3606cd6386cf85f6f5b1 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 18 Mar 2015 20:01:21 +1100 Subject: rhashtable: Remove max_shift and min_shift Now that nobody uses max_shift and min_shift, we can safely remove them. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 81267fef85d7..99425f2be708 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -83,8 +83,6 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed - * @max_shift: Maximum number of shifts while expanding - * @min_shift: Minimum number of shifts while shrinking * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker @@ -97,8 +95,6 @@ struct rhashtable_params { size_t key_len; size_t key_offset; size_t head_offset; - size_t max_shift; - size_t min_shift; unsigned int max_size; unsigned int min_size; u32 nulls_base; -- cgit v1.2.3 From f0b7d43c8a28155f50adb087a563cfc97566e477 Mon Sep 17 00:00:00 2001 From: Brad Campbell Date: Tue, 17 Mar 2015 16:25:46 -0400 Subject: cc2520: Add support for CC2591 amplifier. The TI CC2521 is an RF power amplifier that is designed to interface with the CC2520. Conveniently, it directly interfaces with the CC2520 and does not require any pins to be connected to a microcontroller/processor. Adding a CC2591 increases the CC2520's range, which is useful for border router and other wall-powered applications. Using the CC2591 with the CC2520 requires configuring the CC2520 GPIOs that are connected to the CC2591 to correctly set the CC2591 into TX and RX modes. Further, TI recommends that the CC2520_TXPOWER and CC2520_AGCCTRL1 registers are set differently to maximize the CC2591's performance. These settings are covered in TI Application Note AN065. This patch adds an optional `amplified` field to the cc2520 entry in the device tree. If present, the CC2520 will be configured to operate with a CC2591. The expected pin mapping is: CC2520 GPIO0 --> CC2591 EN CC2520 GPIO5 --> CC2591 PAEN Signed-off-by: Brad Campbell Acked-by: Varka Bhadram Signed-off-by: Marcel Holtmann --- include/linux/spi/cc2520.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/spi/cc2520.h b/include/linux/spi/cc2520.h index 85b8ee67e937..e741e8baad92 100644 --- a/include/linux/spi/cc2520.h +++ b/include/linux/spi/cc2520.h @@ -21,6 +21,7 @@ struct cc2520_platform_data { int sfd; int reset; int vreg; + bool amplified; }; #endif -- cgit v1.2.3 From 822b3b2ebfff8e9b3d006086c527738a7ca00cd0 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 18 Mar 2015 14:57:33 +0200 Subject: net: Add max rate tx queue attribute This adds a tx_maxrate attribute to the tx queue sysfs entry allowing for max-rate limiting. Along with DCB-ETS and BQL this provides another knob to tune queue performance. The limit units are Mbps. By default it is disabled. To disable the rate limitation after it has been set for a queue, it should be set to zero. Signed-off-by: John Fastabend Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd1d069758be..76c5de4978a8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -587,6 +587,7 @@ struct netdev_queue { #ifdef CONFIG_BQL struct dql dql; #endif + unsigned long tx_maxrate; } ____cacheline_aligned_in_smp; static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -1022,6 +1023,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. + * int (*ndo_set_tx_maxrate)(struct net_device *dev, + * int queue_index, u32 maxrate); + * Called when a user wants to set a max-rate limitation of specific + * TX queue. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1178,6 +1183,9 @@ struct net_device_ops { netdev_features_t (*ndo_features_check) (struct sk_buff *skb, struct net_device *dev, netdev_features_t features); + int (*ndo_set_tx_maxrate)(struct net_device *dev, + int queue_index, + u32 maxrate); }; /** -- cgit v1.2.3 From fc31e2560a2443410fe45c27116fae736541a7b5 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 18 Mar 2015 14:57:34 +0200 Subject: net/mlx4_core: Add basic support for QP max-rate limiting Add the low-level device commands and definitions used for QP max-rate limiting. This is done through the following elements: - read rate-limit device caps in QUERY_DEV_CAP: number of different rates and the min/max rates in Kbs/Mbs/Gbs units - enhance the QP context struct to contain rate limit units and value - allow to do run time rate-limit setting to QPs through the update-qp firmware command - QP rate-limiting is disallowed for VFs Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 17 +++++++++++++++++ include/linux/mlx4/qp.h | 14 ++++++++++---- 2 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 1cc54822b931..4550c67b92e4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -205,6 +205,7 @@ enum { MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21, MLX4_DEV_CAP_FLAG2_QCN = 1LL << 22, + MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23 }; enum { @@ -450,6 +451,21 @@ enum mlx4_module_id { MLX4_MODULE_ID_QSFP28 = 0x11, }; +enum { /* rl */ + MLX4_QP_RATE_LIMIT_NONE = 0, + MLX4_QP_RATE_LIMIT_KBS = 1, + MLX4_QP_RATE_LIMIT_MBS = 2, + MLX4_QP_RATE_LIMIT_GBS = 3 +}; + +struct mlx4_rate_limit_caps { + u16 num_rates; /* Number of different rates */ + u8 min_unit; + u16 min_val; + u8 max_unit; + u16 max_val; +}; + static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor) { return (major << 32) | (minor << 16) | subminor; @@ -565,6 +581,7 @@ struct mlx4_caps { u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; u32 vf_caps; + struct mlx4_rate_limit_caps rl_caps; }; struct mlx4_buf_list { diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 551f85456c11..1023ebe035b7 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -207,14 +207,16 @@ struct mlx4_qp_context { __be32 msn; __be16 rq_wqe_counter; __be16 sq_wqe_counter; - u32 reserved3[2]; + u32 reserved3; + __be16 rate_limit_params; + __be16 reserved4; __be32 param3; __be32 nummmcpeers_basemkey; u8 log_page_size; - u8 reserved4[2]; + u8 reserved5[2]; u8 mtt_base_addr_h; __be32 mtt_base_addr_l; - u32 reserved5[10]; + u32 reserved6[10]; }; struct mlx4_update_qp_context { @@ -229,6 +231,7 @@ struct mlx4_update_qp_context { enum { MLX4_UPD_QP_MASK_PM_STATE = 32, MLX4_UPD_QP_MASK_VSD = 33, + MLX4_UPD_QP_MASK_RATE_LIMIT = 35, }; enum { @@ -428,7 +431,8 @@ struct mlx4_wqe_inline_seg { enum mlx4_update_qp_attr { MLX4_UPDATE_QP_SMAC = 1 << 0, MLX4_UPDATE_QP_VSD = 1 << 1, - MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 2) - 1 + MLX4_UPDATE_QP_RATE_LIMIT = 1 << 2, + MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 3) - 1 }; enum mlx4_update_qp_params_flags { @@ -438,6 +442,8 @@ enum mlx4_update_qp_params_flags { struct mlx4_update_qp_params { u8 smac_index; u32 flags; + u16 rate_unit; + u16 rate_val; }; int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn, -- cgit v1.2.3 From 6eada0110c8984477f5f1e57a0b7f7b2fc841e30 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:33 -0700 Subject: netns: constify net_hash_mix() and various callers const qualifiers ease code review by making clear which objects are not written in a function. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/udp.h | 2 +- include/net/inet_hashtables.h | 6 +++--- include/net/netns/hash.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/udp.h b/include/linux/udp.h index 247cfdcc4b08..87c094961bd5 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -34,7 +34,7 @@ static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) -static inline int udp_hashfn(struct net *net, unsigned num, unsigned mask) +static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) { return (num + net_hash_mix(net)) & mask; } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index bcd64756e5fe..eb1963af0ebd 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -221,8 +221,8 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); -static inline int inet_bhashfn(struct net *net, const __u16 lport, - const int bhash_size) +static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, + const u32 bhash_size) { return (lport + net_hash_mix(net)) & (bhash_size - 1); } @@ -231,7 +231,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); /* These can have wildcards, don't try too hard. */ -static inline int inet_lhashfn(struct net *net, const unsigned short num) +static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) { return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); } diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index c06ac58ca107..69a6715d9f3f 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -5,7 +5,7 @@ struct net; -static inline unsigned int net_hash_mix(struct net *net) +static inline u32 net_hash_mix(const struct net *net) { #ifdef CONFIG_NET_NS /* @@ -13,7 +13,7 @@ static inline unsigned int net_hash_mix(struct net *net) * always zeroed */ - return (unsigned)(((unsigned long)net) >> L1_CACHE_SHIFT); + return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT); #else return 0; #endif -- cgit v1.2.3 From 5b441f76f1b83591e8cd9d60ba1df3a2aacde27f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:34 -0700 Subject: net: introduce sk_ehashfn() helper Goal is to unify IPv4/IPv6 inet_hash handling, and use common helpers for all kind of sockets (full sockets, timewait and request sockets) inet_sk_ehashfn() becomes sk_ehashfn() but still only copes with IPv4 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index eb1963af0ebd..ef993ef571ea 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -383,6 +383,8 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, iph->daddr, dport, inet_iif(skb)); } +u32 sk_ehashfn(const struct sock *sk); + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, -- cgit v1.2.3 From d1e559d0b1b0d02f76a6bd5b768a99dc834ae926 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:35 -0700 Subject: inet: add IPv6 support to sk_ehashfn() Intent is to converge IPv4 & IPv6 inet_hash functions to factorize code. IPv4 sockets initialize sk_rcv_saddr and sk_v6_daddr in this patch, thanks to new sk_daddr_set() and sk_rcv_saddr_set() helpers. __inet6_hash can now use sk_ehashfn() instead of a private inet6_sk_ehashfn() and will simply use __inet_hash() in a following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ef993ef571ea..06ad42182ec2 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -384,6 +384,25 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, } u32 sk_ehashfn(const struct sock *sk); +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport); + +static inline void sk_daddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_daddr = addr; /* alias of inet_daddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_daddr); +#endif +} + +static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_rcv_saddr = addr; /* alias of inet_rcv_saddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_rcv_saddr); +#endif +} int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, -- cgit v1.2.3 From 77a6a471bc18763cb2e80a8cc92f4c04eae37d32 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:36 -0700 Subject: ipv6: get rid of __inet6_hash() We can now use inet_hash() and __inet_hash() instead of private functions. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 2 -- include/net/inet_hashtables.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 9201afe083fa..7ff588ca6817 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -38,8 +38,6 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, return jhash_3words(lhash, fhash, ports, initval); } -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 06ad42182ec2..eee6c3399990 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -249,6 +249,7 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw); +int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw); void inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -- cgit v1.2.3 From b4d6444ea3b50bf368639432657bcf2b4e5e1062 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:37 -0700 Subject: inet: get rid of last __inet_hash_connect() argument We now always call __inet_hash_nolisten(), no need to pass it as an argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index eee6c3399990..73fe0f9525d9 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -409,9 +409,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, - struct inet_timewait_sock **), - int (*hash)(struct sock *sk, - struct inet_timewait_sock *twp)); + struct inet_timewait_sock **)); int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); -- cgit v1.2.3 From 08d2cc3b26554cae21f279b520ae5c2a3b2be421 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Mar 2015 14:05:38 -0700 Subject: inet: request sock should init IPv6/IPv4 addresses In order to be able to use sk_ehashfn() for request socks, we need to initialize their IPv6/IPv4 addresses. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 3fa4f824900a..e7ef86340514 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -91,6 +91,11 @@ static inline struct request_sock *inet_reqsk(struct sock *sk) return (struct request_sock *)sk; } +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; +} + static inline void reqsk_free(struct request_sock *req) { /* temporary debugging */ -- cgit v1.2.3 From 54ff9ef36bdf84d469a098cbf8e2a103fbc77054 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 18 Mar 2015 14:50:43 -0300 Subject: ipv4, ipv6: kill ip_mc_{join, leave}_group and ipv6_sock_mc_{join, drop} in favor of their inner __ ones, which doesn't grab rtnl. As these functions need to operate on a locked socket, we can't be grabbing rtnl by then. It's too late and doing so causes reversed locking. So this patch: - move rtnl handling to callers instead while already fixing some reversed locking situations, like on vxlan and ipvs code. - renames __ ones to not have the __ mark: __ip_mc_{join,leave}_group -> ip_mc_{join,leave}_group __ipv6_sock_mc_{join,drop} -> ipv6_sock_mc_{join,drop} Signed-off-by: Marcelo Ricardo Leitner Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 -- include/net/ipv6.h | 4 ---- 2 files changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index b5a6470e686c..2c677afeea47 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -111,9 +111,7 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); extern int igmp_rcv(struct sk_buff *); -extern int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); -extern int __ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b7673065c074..e7ba9758a345 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -942,10 +942,6 @@ void ipv6_sysctl_unregister(void); int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); -int __ipv6_sock_mc_join(struct sock *sk, int ifindex, - const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); -int __ipv6_sock_mc_drop(struct sock *sk, int ifindex, - const struct in6_addr *addr); #endif /* _NET_IPV6_H */ -- cgit v1.2.3 From db24a9044ee191c397dcd1c6574f56d67d7c8df5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 17 Mar 2015 20:23:15 -0600 Subject: net: add support for phys_port_name Similar to port id allow netdevices to specify port names and export the name via sysfs. Drivers can implement the netdevice operation to assist udev in having sane default names for the devices using the rule: $ cat /etc/udev/rules.d/80-net-setup-link.rules SUBSYSTEM=="net", ACTION=="add", ATTR{phys_port_name}!="", NAME="$attr{phys_port_name}" Use of phys_name versus phys_id was suggested-by Jiri Pirko. Signed-off-by: David Ahern Acked-by: Jiri Pirko Acked-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ include/uapi/linux/if_link.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 76c5de4978a8..ec8f9b5f6500 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1164,6 +1164,8 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_phys_port_name)(struct net_device *dev, + char *name, size_t len); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); @@ -2947,6 +2949,8 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); +int dev_get_phys_port_name(struct net_device *dev, + char *name, size_t len); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 756436e1ce89..7158fd00a109 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -147,6 +147,7 @@ enum { IFLA_CARRIER_CHANGES, IFLA_PHYS_SWITCH_ID, IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, __IFLA_MAX }; -- cgit v1.2.3 From 99c4a26a159b28fa46a3e746a9b41b297e73d261 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 18 Mar 2015 22:52:33 -0400 Subject: net: Fix high overhead of vlan sub-device teardown. When a networking device is taken down that has a non-trivial number of VLAN devices configured under it, we eat a full synchronize_net() for every such VLAN device. This is because of the call chain: NETDEV_DOWN notifier --> vlan_device_event() --> dev_change_flags() --> __dev_change_flags() --> __dev_close() --> __dev_close_many() --> dev_deactivate_many() --> synchronize_net() This is kind of rediculous because we already have infrastructure for batching doing operation X to a list of net devices so that we only incur one sync. So make use of that by exporting dev_close_many() and adjusting it's interfaace so that the caller can fully manage the batch list. Use this in vlan_device_event() and all the overhead goes away. Reported-by: Salam Noureddine Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec8f9b5f6500..76951c5fbedf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2156,6 +2156,7 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); +int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); -- cgit v1.2.3 From af615762e972be0c66cf1d156ca4fac13b93c0b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rg=20Thalheim?= Date: Wed, 18 Mar 2015 10:06:58 +0100 Subject: bridge: add ageing_time, stp_state, priority over netlink MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Jörg Thalheim Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7158fd00a109..f5f5edd5ae5f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -225,6 +225,9 @@ enum { IFLA_BR_FORWARD_DELAY, IFLA_BR_HELLO_TIME, IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 5067c0469c643512f24786990e315f9c15cc7d24 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 12 Mar 2015 10:32:18 -0700 Subject: ata: Add a new flag to destinguish sas controller SAS controller has its own tag allocation, which doesn't directly match to ATA tag, so SAS and SATA have different code path for ata tags. Originally we use port->scsi_host (98bd4be1) to destinguish SAS controller, but libsas set ->scsi_host too, so we can't use it for the destinguish, we add a new flag for this purpose. Without this patch, the following oops can happen because scsi-mq uses a host-wide tag map shared among all devices with some integer tag values >= ATA_MAX_QUEUE. These unexpectedly high tag values cause __ata_qc_from_tag() to return NULL, which is then dereferenced in ata_qc_new_init(). BUG: unable to handle kernel NULL pointer dereference at 0000000000000058 IP: [] ata_qc_new_init+0x3e/0x120 PGD 32adf0067 PUD 32adf1067 PMD 0 Oops: 0002 [#1] SMP DEBUG_PAGEALLOC Modules linked in: iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi igb i2c_algo_bit ptp pps_core pm80xx libsas scsi_transport_sas sg coretemp eeprom w83795 i2c_i801 CPU: 4 PID: 1450 Comm: cydiskbench Not tainted 4.0.0-rc3 #1 Hardware name: Supermicro X8DTH-i/6/iF/6F/X8DTH, BIOS 2.1b 05/04/12 task: ffff8800ba86d500 ti: ffff88032a064000 task.ti: ffff88032a064000 RIP: 0010:[] [] ata_qc_new_init+0x3e/0x120 RSP: 0018:ffff88032a067858 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffff8800ba0d2230 RCX: 000000000000002a RDX: ffffffff80505ae0 RSI: 0000000000000020 RDI: ffff8800ba0d2230 RBP: ffff88032a067868 R08: 0000000000000201 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800ba0d0000 R13: ffff8800ba0d2230 R14: ffffffff80505ae0 R15: ffff8800ba0d0000 FS: 0000000041223950(0063) GS:ffff88033e480000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000058 CR3: 000000032a0a3000 CR4: 00000000000006e0 Stack: ffff880329eee758 ffff880329eee758 ffff88032a0678a8 ffffffff80502dad ffff8800ba167978 ffff880329eee758 ffff88032bf9c520 ffff8800ba167978 ffff88032bf9c520 ffff88032bf9a290 ffff88032a0678b8 ffffffff80506909 Call Trace: [] ata_scsi_translate+0x3d/0x1b0 [] ata_sas_queuecmd+0x149/0x2a0 [] sas_queuecommand+0xa0/0x1f0 [libsas] [] scsi_dispatch_cmd+0xd4/0x1a0 [] scsi_queue_rq+0x66f/0x7f0 [] __blk_mq_run_hw_queue+0x208/0x3f0 [] blk_mq_run_hw_queue+0x88/0xc0 [] blk_mq_insert_request+0xc4/0x130 [] blk_execute_rq_nowait+0x73/0x160 [] sg_common_write+0x3da/0x720 [sg] [] sg_new_write+0x250/0x360 [sg] [] sg_write+0x13b/0x450 [sg] [] vfs_write+0xd1/0x1b0 [] SyS_write+0x54/0xc0 [] system_call_fastpath+0x12/0x17 tj: updated description. Fixes: 12cb5ce101ab ("libata: use blk taging") Reported-and-tested-by: Tony Battersby Signed-off-by: Shaohua Li Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index fc03efa64ffe..6b08cc106c21 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -232,6 +232,7 @@ enum { * led */ ATA_FLAG_NO_DIPM = (1 << 23), /* host not happy with DIPM */ ATA_FLAG_LOWTAG = (1 << 24), /* host wants lowest available tag */ + ATA_FLAG_SAS_HOST = (1 << 25), /* SAS host */ /* bits 24:31 of ap->flags are reserved for LLD specific flags */ -- cgit v1.2.3 From c6b570d97c0e77f570bb6b2ed30d372b2b1e9aae Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 9 Mar 2015 12:20:13 +0100 Subject: regmap: introduce regmap_name to fix syscon regmap trace events This patch fixes a NULL pointer dereference when enabling regmap event tracing in the presence of a syscon regmap, introduced by commit bdb0066df96e ("mfd: syscon: Decouple syscon interface from platform devices"). That patch introduced syscon regmaps that have their dev field set to NULL. The regmap trace events expect it to point to a valid struct device and feed it to dev_name(): $ echo 1 > /sys/kernel/debug/tracing/events/regmap/enable Unable to handle kernel NULL pointer dereference at virtual address 0000002c pgd = 80004000 [0000002c] *pgd=00000000 Internal error: Oops: 17 [#1] SMP ARM Modules linked in: coda videobuf2_vmalloc CPU: 0 PID: 304 Comm: kworker/0:2 Not tainted 4.0.0-rc2+ #9197 Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree) Workqueue: events_freezable thermal_zone_device_check task: 9f25a200 ti: 9f1ee000 task.ti: 9f1ee000 PC is at ftrace_raw_event_regmap_block+0x3c/0xe4 LR is at _regmap_raw_read+0x1bc/0x1cc pc : [<803636e8>] lr : [<80365f2c>] psr: 600f0093 sp : 9f1efd78 ip : 9f1efdb8 fp : 9f1efdb4 r10: 00000004 r9 : 00000001 r8 : 00000001 r7 : 00000180 r6 : 00000000 r5 : 9f00e3c0 r4 : 00000003 r3 : 00000001 r2 : 00000180 r1 : 00000000 r0 : 9f00e3c0 Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c5387d Table: 2d91004a DAC: 00000015 Process kworker/0:2 (pid: 304, stack limit = 0x9f1ee210) Stack: (0x9f1efd78 to 0x9f1f0000) fd60: 9f1efda4 9f1efd88 fd80: 800708c0 805f9510 80927140 800f0013 9f1fc800 9eb2f490 00000000 00000180 fda0: 808e3840 00000001 9f1efdfc 9f1efdb8 80365f2c 803636b8 805f8958 800708e0 fdc0: a00f0013 803636ac 9f16de00 00000180 80927140 9f1fc800 9f1fc800 9f1efe6c fde0: 9f1efe6c 9f732400 00000000 00000000 9f1efe1c 9f1efe00 80365f70 80365d7c fe00: 80365f3c 9f1fc800 9f1fc800 00000180 9f1efe44 9f1efe20 803656a4 80365f48 fe20: 9f1fc800 00000180 9f1efe6c 9f1efe6c 9f732400 00000000 9f1efe64 9f1efe48 fe40: 803657bc 80365634 00000001 9e95f910 9f1fc800 9f1efeb4 9f1efe8c 9f1efe68 fe60: 80452ac0 80365778 9f1efe8c 9f1efe78 9e93d400 9e93d5e8 9f1efeb4 9f72ef40 fe80: 9f1efeac 9f1efe90 8044e11c 80452998 8045298c 9e93d608 9e93d400 808e1978 fea0: 9f1efecc 9f1efeb0 8044fd14 8044e0d0 ffffffff 9f25a200 9e93d608 9e481380 fec0: 9f1efedc 9f1efed0 8044fde8 8044fcec 9f1eff1c 9f1efee0 80038d50 8044fdd8 fee0: 9f1ee020 9f72ef40 9e481398 00000000 00000008 9f72ef54 9f1ee020 9f72ef40 ff00: 9e481398 9e481380 00000008 9f72ef40 9f1eff5c 9f1eff20 80039754 80038bfc ff20: 00000000 9e481380 80894100 808e1662 00000000 9e4f2ec0 00000000 9e481380 ff40: 800396f8 00000000 00000000 00000000 9f1effac 9f1eff60 8003e020 80039704 ff60: ffffffff 00000000 ffffffff 9e481380 00000000 00000000 9f1eff78 9f1eff78 ff80: 00000000 00000000 9f1eff88 9f1eff88 9e4f2ec0 8003df30 00000000 00000000 ffa0: 00000000 9f1effb0 8000eb60 8003df3c 00000000 00000000 00000000 00000000 ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 ffe0: 00000000 00000000 00000000 00000000 00000013 00000000 ffffffff ffffffff Backtrace: [<803636ac>] (ftrace_raw_event_regmap_block) from [<80365f2c>] (_regmap_raw_read+0x1bc/0x1cc) r9:00000001 r8:808e3840 r7:00000180 r6:00000000 r5:9eb2f490 r4:9f1fc800 [<80365d70>] (_regmap_raw_read) from [<80365f70>] (_regmap_bus_read+0x34/0x6c) r10:00000000 r9:00000000 r8:9f732400 r7:9f1efe6c r6:9f1efe6c r5:9f1fc800 r4:9f1fc800 [<80365f3c>] (_regmap_bus_read) from [<803656a4>] (_regmap_read+0x7c/0x144) r6:00000180 r5:9f1fc800 r4:9f1fc800 r3:80365f3c [<80365628>] (_regmap_read) from [<803657bc>] (regmap_read+0x50/0x70) r9:00000000 r8:9f732400 r7:9f1efe6c r6:9f1efe6c r5:00000180 r4:9f1fc800 [<8036576c>] (regmap_read) from [<80452ac0>] (imx_get_temp+0x134/0x1a4) r6:9f1efeb4 r5:9f1fc800 r4:9e95f910 r3:00000001 [<8045298c>] (imx_get_temp) from [<8044e11c>] (thermal_zone_get_temp+0x58/0x74) r7:9f72ef40 r6:9f1efeb4 r5:9e93d5e8 r4:9e93d400 [<8044e0c4>] (thermal_zone_get_temp) from [<8044fd14>] (thermal_zone_device_update+0x34/0xec) r6:808e1978 r5:9e93d400 r4:9e93d608 r3:8045298c [<8044fce0>] (thermal_zone_device_update) from [<8044fde8>] (thermal_zone_device_check+0x1c/0x20) r5:9e481380 r4:9e93d608 [<8044fdcc>] (thermal_zone_device_check) from [<80038d50>] (process_one_work+0x160/0x3d4) [<80038bf0>] (process_one_work) from [<80039754>] (worker_thread+0x5c/0x4f4) r10:9f72ef40 r9:00000008 r8:9e481380 r7:9e481398 r6:9f72ef40 r5:9f1ee020 r4:9f72ef54 [<800396f8>] (worker_thread) from [<8003e020>] (kthread+0xf0/0x108) r10:00000000 r9:00000000 r8:00000000 r7:800396f8 r6:9e481380 r5:00000000 r4:9e4f2ec0 [<8003df30>] (kthread) from [<8000eb60>] (ret_from_fork+0x14/0x34) r7:00000000 r6:00000000 r5:8003df30 r4:9e4f2ec0 Code: e3140040 1a00001a e3140020 1a000016 (e596002c) ---[ end trace 193c15c2494ec960 ]--- Fixes: bdb0066df96e (mfd: syscon: Decouple syscon interface from platform devices) Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/trace/events/regmap.h | 123 +++++++++++++++++++++--------------------- 1 file changed, 61 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h index 23d561512f64..22317d2b52ab 100644 --- a/include/trace/events/regmap.h +++ b/include/trace/events/regmap.h @@ -7,27 +7,26 @@ #include #include -struct device; -struct regmap; +#include "../../../drivers/base/regmap/internal.h" /* * Log register events */ DECLARE_EVENT_CLASS(regmap_reg, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val), + TP_ARGS(map, reg, val), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( unsigned int, val ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( unsigned int, val ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->val = val; ), @@ -39,45 +38,45 @@ DECLARE_EVENT_CLASS(regmap_reg, DEFINE_EVENT(regmap_reg, regmap_reg_write, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DEFINE_EVENT(regmap_reg, regmap_reg_read_cache, - TP_PROTO(struct device *dev, unsigned int reg, + TP_PROTO(struct regmap *map, unsigned int reg, unsigned int val), - TP_ARGS(dev, reg, val) + TP_ARGS(map, reg, val) ); DECLARE_EVENT_CLASS(regmap_block, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count), + TP_ARGS(map, reg, count), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, reg ) - __field( int, count ) + __string( name, regmap_name(map) ) + __field( unsigned int, reg ) + __field( int, count ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->reg = reg; __entry->count = count; ), @@ -89,48 +88,48 @@ DECLARE_EVENT_CLASS(regmap_block, DEFINE_EVENT(regmap_block, regmap_hw_read_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_read_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_block, regmap_hw_write_done, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); TRACE_EVENT(regcache_sync, - TP_PROTO(struct device *dev, const char *type, + TP_PROTO(struct regmap *map, const char *type, const char *status), - TP_ARGS(dev, type, status), + TP_ARGS(map, type, status), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __string( status, status ) - __string( type, type ) - __field( int, type ) + __string( name, regmap_name(map) ) + __string( status, status ) + __string( type, type ) + __field( int, type ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __assign_str(status, status); __assign_str(type, type); ), @@ -141,17 +140,17 @@ TRACE_EVENT(regcache_sync, DECLARE_EVENT_CLASS(regmap_bool, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag), + TP_ARGS(map, flag), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( int, flag ) + __string( name, regmap_name(map) ) + __field( int, flag ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->flag = flag; ), @@ -161,32 +160,32 @@ DECLARE_EVENT_CLASS(regmap_bool, DEFINE_EVENT(regmap_bool, regmap_cache_only, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DEFINE_EVENT(regmap_bool, regmap_cache_bypass, - TP_PROTO(struct device *dev, bool flag), + TP_PROTO(struct regmap *map, bool flag), - TP_ARGS(dev, flag) + TP_ARGS(map, flag) ); DECLARE_EVENT_CLASS(regmap_async, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev), + TP_ARGS(map), TP_STRUCT__entry( - __string( name, dev_name(dev) ) + __string( name, regmap_name(map) ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); ), TP_printk("%s", __get_str(name)) @@ -194,50 +193,50 @@ DECLARE_EVENT_CLASS(regmap_async, DEFINE_EVENT(regmap_block, regmap_async_write_start, - TP_PROTO(struct device *dev, unsigned int reg, int count), + TP_PROTO(struct regmap *map, unsigned int reg, int count), - TP_ARGS(dev, reg, count) + TP_ARGS(map, reg, count) ); DEFINE_EVENT(regmap_async, regmap_async_io_complete, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_start, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); DEFINE_EVENT(regmap_async, regmap_async_complete_done, - TP_PROTO(struct device *dev), + TP_PROTO(struct regmap *map), - TP_ARGS(dev) + TP_ARGS(map) ); TRACE_EVENT(regcache_drop_region, - TP_PROTO(struct device *dev, unsigned int from, + TP_PROTO(struct regmap *map, unsigned int from, unsigned int to), - TP_ARGS(dev, from, to), + TP_ARGS(map, from, to), TP_STRUCT__entry( - __string( name, dev_name(dev) ) - __field( unsigned int, from ) - __field( unsigned int, to ) + __string( name, regmap_name(map) ) + __field( unsigned int, from ) + __field( unsigned int, to ) ), TP_fast_assign( - __assign_str(name, dev_name(dev)); + __assign_str(name, regmap_name(map)); __entry->from = from; __entry->to = to; ), -- cgit v1.2.3 From 25911556283e5093fca235d7ba03faae7ed5dbf2 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Wed, 18 Mar 2015 13:25:26 +0100 Subject: brcmfmac: add support for BCM43430 SDIO chipset This patch added support for the BCM43430 802.11n SDIO chipset. Reviewed-by: Hante Meuleman Reviewed-by: Daniel (Deognyoun) Kim Reviewed-by: Franky (Zhenhui) Lin Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 91397858dc95..83430f2ea757 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -33,6 +33,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 #define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 +#define SDIO_DEVICE_ID_BROADCOM_43430 0xa9a6 #define SDIO_DEVICE_ID_BROADCOM_4345 0x4345 #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 -- cgit v1.2.3 From 52452c542559ac980b48dbf22a30ee7fa0af507c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Mar 2015 19:04:19 -0700 Subject: inet: drop prev pointer handling in request sock When request sock are put in ehash table, the whole notion of having a previous request to update dl_next is pointless. Also, following patch will get rid of big purge timer, so we want to delete a request sock without holding listener lock. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 1 - include/net/inet_connection_sock.h | 11 ++++------- include/net/request_sock.h | 15 +++++++++++---- include/net/tcp.h | 3 +-- 4 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 74af137304be..15bd40878d2a 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -29,7 +29,6 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b9a6b0a94cc6..423a46106e57 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -257,7 +257,6 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const __be32 raddr, const __be32 laddr); @@ -310,17 +309,15 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); + reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); reqsk_free(req); } diff --git a/include/net/request_sock.h b/include/net/request_sock.h index e7ef86340514..65223905d139 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -50,6 +50,7 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash struct request_sock *dl_next; struct sock *rsk_listener; @@ -216,11 +217,16 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) } static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req, - struct request_sock **prev_req) + struct request_sock *req) { + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; + prev = &lopt->syn_table[req->rsk_hash]; + while (*prev != req) + prev = &(*prev)->dl_next; + *prev = req->dl_next; write_unlock(&queue->syn_wait_lock); } @@ -300,7 +306,6 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, req->num_retrans = 0; req->num_timeout = 0; req->sk = NULL; - req->dl_next = lopt->syn_table[hash]; /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. @@ -308,7 +313,9 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, smp_wmb(); atomic_set(&req->rsk_refcnt, 1); + req->rsk_hash = hash; write_lock(&queue->syn_wait_lock); + req->dl_next = lopt->syn_table[hash]; lopt->syn_table[hash] = req; write_unlock(&queue->syn_wait_lock); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b29835b81d8..082fd79132b7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,8 +406,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, struct request_sock **prev, - bool fastopen); + struct request_sock *req, bool fastopen); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); -- cgit v1.2.3 From fa76ce7328b289b6edd476e24eb52fd634261720 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Mar 2015 19:04:20 -0700 Subject: inet: get rid of central tcp/dccp listener timer One of the major issue for TCP is the SYNACK rtx handling, done by inet_csk_reqsk_queue_prune(), fired by the keepalive timer of a TCP_LISTEN socket. This function runs for awful long times, with socket lock held, meaning that other cpus needing this lock have to spin for hundred of ms. SYNACK are sent in huge bursts, likely to cause severe drops anyway. This model was OK 15 years ago when memory was very tight. We now can afford to have a timer per request sock. Timer invocations no longer need to lock the listener, and can be run from all cpus in parallel. With following patch increasing somaxconn width to 32 bits, I tested a listener with more than 4 million active request sockets, and a steady SYNFLOOD of ~200,000 SYN per second. Host was sending ~830,000 SYNACK per second. This is ~100 times more what we could achieve before this patch. Later, we will get rid of the listener hash and use ehash instead. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- include/net/inet_connection_sock.h | 15 ++----- include/net/request_sock.h | 87 +++++++++++++++++-------------------- 3 files changed, 46 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 15bd40878d2a..6d539e4e5ba7 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -28,7 +28,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); -struct request_sock *inet6_csk_search_req(const struct sock *sk, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 423a46106e57..7b5887cd1172 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -256,7 +256,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); -struct request_sock *inet_csk_search_req(const struct sock *sk, +struct request_sock *inet_csk_search_req(struct sock *sk, const __be16 rport, const __be32 raddr, const __be32 laddr); @@ -282,15 +282,13 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, static inline void inet_csk_reqsk_queue_removed(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0) - inet_csk_delete_keepalive_timer(sk); + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_added(struct sock *sk, const unsigned long timeout) { - if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0) - inet_csk_reset_keepalive_timer(sk, timeout); + reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) @@ -319,14 +317,9 @@ static inline void inet_csk_reqsk_queue_drop(struct sock *sk, { inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); - reqsk_free(req); + reqsk_put(req); } -void inet_csk_reqsk_queue_prune(struct sock *parent, - const unsigned long interval, - const unsigned long timeout, - const unsigned long max_rto); - void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 65223905d139..6a91261d9b7b 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -62,7 +62,7 @@ struct request_sock { u32 window_clamp; /* window clamp at creation time */ u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; - unsigned long expires; + struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; u32 secid; @@ -110,9 +110,6 @@ static inline void reqsk_free(struct request_sock *req) static inline void reqsk_put(struct request_sock *req) { - /* temporary debugging, until req sock are put into ehash table */ - WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 1); - if (atomic_dec_and_test(&req->rsk_refcnt)) reqsk_free(req); } @@ -124,12 +121,16 @@ extern int sysctl_max_syn_backlog; * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs */ struct listen_sock { - u8 max_qlen_log; + int qlen_inc; /* protected by listener lock */ + int young_inc;/* protected by listener lock */ + + /* following fields can be updated by timer */ + atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ + atomic_t young_dec; + + u8 max_qlen_log ____cacheline_aligned_in_smp; u8 synflood_warned; /* 2 bytes hole, try to use */ - int qlen; - int qlen_young; - int clock_hand; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -182,9 +183,7 @@ struct fastopen_queue { struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - rwlock_t syn_wait_lock; u8 rskq_defer_accept; - /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been * enabled on this listener. Check @@ -192,6 +191,9 @@ struct request_sock_queue { * to determine if TFO is enabled * right at this moment. */ + + /* temporary alignment, our goal is to get rid of this lock */ + rwlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -223,11 +225,15 @@ static inline void reqsk_queue_unlink(struct request_sock_queue *queue, struct request_sock **prev; write_lock(&queue->syn_wait_lock); + prev = &lopt->syn_table[req->rsk_hash]; while (*prev != req) prev = &(*prev)->dl_next; *prev = req->dl_next; + write_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); } static inline void reqsk_queue_add(struct request_sock_queue *queue, @@ -260,64 +266,53 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue return req; } -static inline int reqsk_queue_removed(struct request_sock_queue *queue, - struct request_sock *req) +static inline void reqsk_queue_removed(struct request_sock_queue *queue, + const struct request_sock *req) { struct listen_sock *lopt = queue->listen_opt; if (req->num_timeout == 0) - --lopt->qlen_young; - - return --lopt->qlen; + atomic_inc(&lopt->young_dec); + atomic_inc(&lopt->qlen_dec); } -static inline int reqsk_queue_added(struct request_sock_queue *queue) +static inline void reqsk_queue_added(struct request_sock_queue *queue) { struct listen_sock *lopt = queue->listen_opt; - const int prev_qlen = lopt->qlen; - lopt->qlen_young++; - lopt->qlen++; - return prev_qlen; + lopt->young_inc++; + lopt->qlen_inc++; } -static inline int reqsk_queue_len(const struct request_sock_queue *queue) +static inline int listen_sock_qlen(const struct listen_sock *lopt) { - return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; + return lopt->qlen_inc - atomic_read(&lopt->qlen_dec); } -static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) +static inline int listen_sock_young(const struct listen_sock *lopt) { - return queue->listen_opt->qlen_young; + return lopt->young_inc - atomic_read(&lopt->young_dec); } -static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +static inline int reqsk_queue_len(const struct request_sock_queue *queue) { - return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; + const struct listen_sock *lopt = queue->listen_opt; + + return lopt ? listen_sock_qlen(lopt) : 0; } -static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout) +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { - struct listen_sock *lopt = queue->listen_opt; - - req->expires = jiffies + timeout; - req->num_retrans = 0; - req->num_timeout = 0; - req->sk = NULL; - - /* before letting lookups find us, make sure all req fields - * are committed to memory and refcnt initialized. - */ - smp_wmb(); - atomic_set(&req->rsk_refcnt, 1); + return listen_sock_young(queue->listen_opt); +} - req->rsk_hash = hash; - write_lock(&queue->syn_wait_lock); - req->dl_next = lopt->syn_table[hash]; - lopt->syn_table[hash] = req; - write_unlock(&queue->syn_wait_lock); +static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +{ + return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; } +void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned long timeout); + #endif /* _REQUEST_SOCK_H */ -- cgit v1.2.3 From becb74f0acca19b5abfcb24dc602530f3deea66a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Mar 2015 19:04:21 -0700 Subject: net: increase sk_[max_]ack_backlog sk_ack_backlog & sk_max_ack_backlog were 16bit fields, meaning listen() backlog was limited to 65535. It is time to increase the width to allow much bigger backlog, if admins change /proc/sys/net/core/somaxconn & /proc/sys/net/ipv4/tcp_max_syn_backlog default values. Tested: echo 5000000 >/proc/sys/net/core/somaxconn echo 5000000 >/proc/sys/net/ipv4/tcp_max_syn_backlog Ran a SYNFLOOD test against a listener using listen(fd, 5000000) myhost~# grep request_sock_TCP /proc/slabinfo request_sock_TCP 4185642 4411940 304 13 1 : tunables 54 27 8 : slabdata 339380 339380 0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index e0360f5a53e9..3f9b8ce56948 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -405,8 +405,8 @@ struct sock { rwlock_t sk_callback_lock; int sk_err, sk_err_soft; - unsigned short sk_ack_backlog; - unsigned short sk_max_ack_backlog; + u32 sk_ack_backlog; + u32 sk_max_ack_backlog; __u32 sk_priority; #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) __u32 sk_cgrp_prioidx; -- cgit v1.2.3 From a736775db683174269c65c7c5cc8e5ee534e7681 Mon Sep 17 00:00:00 2001 From: Charlie Mooney Date: Fri, 20 Mar 2015 09:40:17 -0700 Subject: Input: add MT_TOOL_PALM Currently there are only two "tools" that can be specified by a multi-touch driver: MT_TOOL_FINGER and MT_TOOL_PEN. In working with Elan (The touch vendor) and discussing their next-gen devices it seems that it will be useful to have more tools so that their devices can give the upper layers of the stack hints as to what is touching the sensor. In particular they have new experimental firmware that can better differentiate between palms vs fingertips and would like to plumb a patch so that we can use their hints in higher-level gesture soft- ware. The firmware on the device can reasonably do a better job of palm detection because it has access to all of the raw sensor readings as opposed to just the width/pressure/etc that are exposed by the driver. As such, the firmware can characterize what a palm looks like in much finer-grained detail and this change would allow such a device to share its findings with the kernel. Signed-off-by: Charlie Mooney Acked-by: Peter Hutterer Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index a1d7e931ab72..2320b0ce7579 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -972,7 +972,8 @@ struct input_keymap_entry { */ #define MT_TOOL_FINGER 0 #define MT_TOOL_PEN 1 -#define MT_TOOL_MAX 1 +#define MT_TOOL_PALM 2 +#define MT_TOOL_MAX 2 /* * Values describing the status of a force-feedback effect -- cgit v1.2.3 From 488fb86ee91d3b1182c2e30a9f9b45da14eda46f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 20 Mar 2015 21:56:59 +1100 Subject: rhashtable: Make rhashtable_init params argument const This patch marks the rhashtable_init params argument const as there is no reason to modify it since we will always make a copy of it in the rhashtable. This patch also fixes a bug where we don't actually round up the value of min_size unless it is less than HASH_MIN_SIZE. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 99425f2be708..c85363c45fc0 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -181,7 +181,8 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, } #endif /* CONFIG_PROVE_LOCKING */ -int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); -- cgit v1.2.3 From 02fd97c3d4a8a14e222b0021c366db7041d28743 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 20 Mar 2015 21:57:00 +1100 Subject: rhashtable: Allow hash/comparison functions to be inlined This patch deals with the complaint that we make indirect function calls on the fast paths unnecessarily in rhashtable. We resolve it by moving the fast paths into inline functions that take struct rhashtable_param (which obviously must be the same set of parameters supplied to rhashtable_init) as an argument. The only remaining indirect call is to obj_hashfn (or key_hashfn it obj_hashfn is unset) on the rehash as well as the insert-during- rehash slow path. This patch also extends the support of vairable-length keys to include those where the key is fixed but scattered in the object. For example, in netlink we want to key off the namespace and the portid but they're not next to each other. This patch does this by directly using the object hash function as the indicator of whether the key is accessible or not. It also adds a new function obj_cmpfn to compare a key against an object. This means that the caller no longer needs to supply explicit compare functions. All this is done in a backwards compatible manner so no existing users are affected until they convert to the new interface. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 386 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 386 insertions(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c85363c45fc0..a7188eeb135b 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -22,6 +22,7 @@ #include #include #include +#include /* * The end of the chain is marked with a special nulls marks which has @@ -42,6 +43,9 @@ #define RHT_HASH_BITS 27 #define RHT_BASE_SHIFT RHT_HASH_BITS +/* Base bits plus 1 bit for nulls marker */ +#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) + struct rhash_head { struct rhash_head __rcu *next; }; @@ -72,8 +76,20 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); struct rhashtable; @@ -89,6 +105,7 @@ struct rhashtable; * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Function to hash key * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object */ struct rhashtable_params { size_t nelem_hint; @@ -101,6 +118,7 @@ struct rhashtable_params { size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; }; /** @@ -165,6 +183,83 @@ static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) return ((unsigned long) ptr) >> 1; } +static inline void *rht_obj(const struct rhashtable *ht, + const struct rhash_head *he) +{ + return (char *)he - ht->p.head_offset; +} + +static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, + unsigned int hash) +{ + return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); +} + +static inline unsigned int rht_key_hashfn( + struct rhashtable *ht, const struct bucket_table *tbl, + const void *key, const struct rhashtable_params params) +{ + return rht_bucket_index(tbl, params.hashfn(key, params.key_len ?: + ht->p.key_len, + tbl->hash_rnd)); +} + +static inline unsigned int rht_head_hashfn( + struct rhashtable *ht, const struct bucket_table *tbl, + const struct rhash_head *he, const struct rhashtable_params params) +{ + const char *ptr = rht_obj(ht, he); + + return likely(params.obj_hashfn) ? + rht_bucket_index(tbl, params.obj_hashfn(ptr, tbl->hash_rnd)) : + rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); +} + +/** + * rht_grow_above_75 - returns true if nelems > 0.75 * table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_75(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + /* Expand table when exceeding 75% load */ + return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) && + (!ht->p.max_size || tbl->size < ht->p.max_size); +} + +/** + * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_shrink_below_30(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + /* Shrink table beneath 30% load */ + return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) && + tbl->size > ht->p.min_size; +} + +/* The bucket lock is selected based on the hash and protects mutations + * on a group of hash buckets. + * + * A maximum of tbl->size/2 bucket locks is allocated. This ensures that + * a single lock always covers both buckets which may both contains + * entries which link to the same bucket of the old table during resizing. + * This allows to simplify the locking as locking the bucket in both + * tables during resize always guarantee protection. + * + * IMPORTANT: When holding the bucket lock of both the old and new table + * during expansions and shrinking, the old bucket lock must always be + * acquired first. + */ +static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl, + unsigned int hash) +{ + return &tbl->locks[hash & tbl->locks_mask]; +} + #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); @@ -184,6 +279,9 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); +int rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); @@ -356,4 +454,292 @@ void rhashtable_destroy(struct rhashtable *ht); rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ tbl, hash, member) +static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, + const void *obj) +{ + struct rhashtable *ht = arg->ht; + const char *ptr = obj; + + return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); +} + +/** + * rhashtable_lookup_fast - search hash table, inlined version + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; + const struct bucket_table *tbl; + struct rhash_head *he; + unsigned hash; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); +restart: + hash = rht_key_hashfn(ht, tbl, key, params); + rht_for_each_rcu(he, tbl, hash) { + if (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, he)) : + rhashtable_compare(&arg, rht_obj(ht, he))) + continue; + rcu_read_unlock(); + return rht_obj(ht, he); + } + + /* Ensure we see any new tables. */ + smp_rmb(); + + tbl = rht_dereference_rcu(tbl->future_tbl, ht); + if (unlikely(tbl)) + goto restart; + rcu_read_unlock(); + + return NULL; +} + +static inline int __rhashtable_insert_fast( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + struct rhashtable_compare_arg arg = { + .ht = ht, + .key = key, + }; + int err = -EEXIST; + struct bucket_table *tbl, *new_tbl; + struct rhash_head *head; + spinlock_t *lock; + unsigned hash; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + + spin_lock_bh(lock); + + /* Because we have already taken the bucket lock in tbl, + * if we find that future_tbl is not yet visible then + * that guarantees all other insertions of the same entry + * will also grab the bucket lock in tbl because until + * the rehash completes ht->tbl won't be changed. + */ + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); + if (unlikely(new_tbl)) { + err = rhashtable_insert_slow(ht, key, obj, new_tbl); + goto out; + } + + if (!key) + goto skip_lookup; + + rht_for_each(head, tbl, hash) { + if (unlikely(!(params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head))))) + goto out; + } + +skip_lookup: + err = 0; + + head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); + + RCU_INIT_POINTER(obj->next, head); + + rcu_assign_pointer(tbl->buckets[hash], obj); + + atomic_inc(&ht->nelems); + if (rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); + +out: + spin_unlock_bh(lock); + rcu_read_unlock(); + + return err; +} + +/** + * rhashtable_insert_fast - insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhashtable_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + return __rhashtable_insert_fast(ht, NULL, obj, params); +} + +/** + * rhashtable_lookup_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Locks down the bucket chain in both the old and new table if a resize + * is in progress to ensure that writers can't remove from the old table + * and can't insert to the new table during the atomic operation of search + * and insertion. Searches for duplicates in both the old and new table if + * a resize is in progress. + * + * This lookup function may only be used for fixed key hash table (key_len + * parameter set). It will BUG() if used inappropriately. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhashtable_lookup_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + const char *key = rht_obj(ht, obj); + + BUG_ON(ht->p.obj_hashfn); + + return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, + params); +} + +/** + * rhashtable_lookup_insert_key - search and insert object to hash table + * with explicit key + * @ht: hash table + * @key: key + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Locks down the bucket chain in both the old and new table if a resize + * is in progress to ensure that writers can't remove from the old table + * and can't insert to the new table during the atomic operation of search + * and insertion. Searches for duplicates in both the old and new table if + * a resize is in progress. + * + * Lookups may occur in parallel with hashtable mutations and resizing. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + * + * Returns zero on success. + */ +static inline int rhashtable_lookup_insert_key( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + BUG_ON(!ht->p.obj_hashfn || !key); + + return __rhashtable_insert_fast(ht, key, obj, params); +} + +static inline int __rhashtable_remove_fast( + struct rhashtable *ht, struct bucket_table *tbl, + struct rhash_head *obj, const struct rhashtable_params params) +{ + struct rhash_head __rcu **pprev; + struct rhash_head *he; + spinlock_t * lock; + unsigned hash; + int err = -ENOENT; + + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + + spin_lock_bh(lock); + + pprev = &tbl->buckets[hash]; + rht_for_each(he, tbl, hash) { + if (he != obj) { + pprev = &he->next; + continue; + } + + rcu_assign_pointer(*pprev, obj->next); + err = 0; + break; + } + + spin_unlock_bh(lock); + + return err; +} + +/** + * rhashtable_remove_fast - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhashtable_remove_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + struct bucket_table *tbl; + int err; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* Because we have already taken (and released) the bucket + * lock in old_tbl, if we find that future_tbl is not yet + * visible then that guarantees the entry to still be in + * the old tbl if it exists. + */ + while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) && + (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) + ; + + if (err) + goto out; + + atomic_dec(&ht->nelems); + if (rht_shrink_below_30(ht, tbl)) + schedule_work(&ht->run_work); + +out: + rcu_read_unlock(); + + return err; +} + #endif /* _LINUX_RHASHTABLE_H */ -- cgit v1.2.3 From dc0ee268d85026530720d8c874716287b7ede25b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 20 Mar 2015 21:57:06 +1100 Subject: rhashtable: Rip out obsolete out-of-line interface Now that all rhashtable users have been converted over to the inline interface, this patch removes the unused out-of-line interface. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index a7188eeb135b..c3034de2c235 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,14 +1,13 @@ /* * Resizable, Scalable, Concurrent Hash Table * + * Copyright (c) 2015 Herbert Xu * Copyright (c) 2014 Thomas Graf * Copyright (c) 2008-2014 Patrick McHardy * - * Based on the following paper by Josh Triplett, Paul E. McKenney - * and Jonathan Walpole: - * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf - * * Code partially derived from nft_hash + * Rewritten with rehash code from br_multicast plus single list + * pointer as suggested by Josh Triplett * * 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 @@ -282,22 +281,10 @@ int rhashtable_init(struct rhashtable *ht, int rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj, struct bucket_table *old_tbl); -void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); -bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); int rhashtable_expand(struct rhashtable *ht); int rhashtable_shrink(struct rhashtable *ht); -void *rhashtable_lookup(struct rhashtable *ht, const void *key); -void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, - bool (*compare)(void *, void *), void *arg); - -bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj); -bool rhashtable_lookup_compare_insert(struct rhashtable *ht, - struct rhash_head *obj, - bool (*compare)(void *, void *), - void *arg); - int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); -- cgit v1.2.3 From 6626af692692b52c8f9e20ad8201a3255e5ab25b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 20 Mar 2015 18:18:45 -0400 Subject: rhashtable: Fix undeclared EEXIST build error on ia64 We need to include linux/errno.h in rhashtable.h since it doesn't always get included otherwise. Reported-by: kbuild test robot Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c3034de2c235..89d102270570 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -18,6 +18,7 @@ #define _LINUX_RHASHTABLE_H #include +#include #include #include #include -- cgit v1.2.3 From 94caee8c312d96522bcdae88791aaa9ebcd5f22c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 20 Mar 2015 15:11:11 +0100 Subject: ebpf: add sched_act_type and map it to sk_filter's verifier ops In order to prepare eBPF support for tc action, we need to add sched_act_type, so that the eBPF verifier is aware of what helper function act_bpf may use, that it can load skb data and read out currently available skb fields. This is bascially analogous to 96be4325f443 ("ebpf: add sched_cls_type and map it to sk_filter's verifier ops"). BPF_PROG_TYPE_SCHED_CLS and BPF_PROG_TYPE_SCHED_ACT need to be separate since both will have a different set of functionality in future (classifier vs action), thus we won't run into ABI troubles when the point in time comes to diverge functionality from the classifier. The future plan for act_bpf would be that it will be able to write into skb->data and alter selected fields mirrored in struct __sk_buff. For an initial support, it's sufficient to map it to sk_filter_ops. Signed-off-by: Daniel Borkmann Cc: Jiri Pirko Reviewed-by: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1623047af463..3dd314a45d0d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -119,6 +119,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_UNSPEC, BPF_PROG_TYPE_SOCKET_FILTER, BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, }; #define BPF_PSEUDO_MAP_FD 1 -- cgit v1.2.3 From a8cb5f556b567974d75ea29c15181c445c541b1f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 20 Mar 2015 15:11:12 +0100 Subject: act_bpf: add initial eBPF support for actions This work extends the "classic" BPF programmable tc action by extending its scope also to native eBPF code! Together with commit e2e9b6541dd4 ("cls_bpf: add initial eBPF support for programmable classifiers") this adds the facility to implement fully flexible classifier and actions for tc that can be implemented in a C subset in user space, "safely" loaded into the kernel, and being run in native speed when JITed. Also, since eBPF maps can be shared between eBPF programs, it offers the possibility that cls_bpf and act_bpf can share data 1) between themselves and 2) between user space applications. That means that, f.e. customized runtime statistics can be collected in user space, but also more importantly classifier and action behaviour could be altered based on map input from the user space application. For the remaining details on the workflow and integration, see the cls_bpf commit e2e9b6541dd4. Preliminary iproute2 part can be found under [1]. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf-act Signed-off-by: Daniel Borkmann Cc: Jamal Hadi Salim Cc: Jiri Pirko Acked-by: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/tc_act/tc_bpf.h | 6 +++++- include/uapi/linux/tc_act/tc_bpf.h | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h index 86a070ffc930..a152e9858b2c 100644 --- a/include/net/tc_act/tc_bpf.h +++ b/include/net/tc_act/tc_bpf.h @@ -16,8 +16,12 @@ struct tcf_bpf { struct tcf_common common; struct bpf_prog *filter; + union { + u32 bpf_fd; + u16 bpf_num_ops; + }; struct sock_filter *bpf_ops; - u16 bpf_num_ops; + const char *bpf_name; }; #define to_bpf(a) \ container_of(a->priv, struct tcf_bpf, common) diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 5288bd77e63b..07f17cc70bb3 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -24,6 +24,8 @@ enum { TCA_ACT_BPF_PARMS, TCA_ACT_BPF_OPS_LEN, TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, __TCA_ACT_BPF_MAX, }; #define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) -- cgit v1.2.3 From d3593b5cef76db45c864de23c599b58198879e8c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Mar 2015 17:15:19 -0700 Subject: Revert "selinux: add a skb_owned_by() hook" This reverts commit ca10b9e9a8ca7342ee07065289cbe74ac128c169. No longer needed after commit eb8895debe1baba41fcb62c78a16f0c63c21662a ("tcp: tcp_make_synack() should use sock_wmalloc") When under SYNFLOOD, we build lot of SYNACK and hit false sharing because of multiple modifications done on sk_listener->sk_wmem_alloc Since tcp_make_synack() uses sock_wmalloc(), there is no need to call skb_set_owner_w() again, as this adds two atomic operations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/security.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index a1b7dbd127ff..25a079a7c3b3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1716,7 +1716,6 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); - void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2735,8 +2734,6 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); -void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); - #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2928,11 +2925,6 @@ static inline int security_tun_dev_open(void *security) { return 0; } - -static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) -{ -} - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -- cgit v1.2.3 From 13bb8e2eb37eb3badf5bf4b6bb90e485fbb6b1cd Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Fri, 20 Mar 2015 17:42:46 -0700 Subject: switchdev: kernel-doc cleanup on swithdev ops Suggested-by: Ben Hutchings Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/net/switchdev.h | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e5de53f92482..d2e69ee3019a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -19,25 +19,16 @@ struct fib_info; /** * struct switchdev_ops - switchdev operations * - * int (*swdev_parent_id_get)(struct net_device *dev, - * struct netdev_phys_item_id *psid); - * Called to get an ID of the switch chip this port is part of. - * If driver implements this, it indicates that it represents a port - * of a switch chip. + * @swdev_parent_id_get: Called to get an ID of the switch chip this port + * is part of. If driver implements this, it indicates that it + * represents a port of a switch chip. * - * int (*swdev_port_stp_update)(struct net_device *dev, u8 state); - * Called to notify switch device port of bridge port STP - * state change. + * @swdev_port_stp_update: Called to notify switch device port of bridge + * port STP state change. * - * int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 nlflags, u32 tb_id); - * Called to add/modify IPv4 route to switch device. + * @swdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. * - * int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, - * int dst_len, struct fib_info *fi, - * u8 tos, u8 type, u32 tb_id); - * Called to delete IPv4 route from switch device. + * @swdev_fib_ipv4_del: Called to delete IPv4 route from switch device. */ struct swdev_ops { int (*swdev_parent_id_get)(struct net_device *dev, -- cgit v1.2.3 From 8da86466b83787df0d4b89ec81c310de072d101c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki/=E5=90=89=E8=97=A4=E8=8B=B1=E6=98=8E?= Date: Thu, 19 Mar 2015 22:41:46 +0900 Subject: net: neighbour: Add mcast_resolicit to configure the number of multicast resolicitations in PROBE state. We send unicast neighbor (ARP or NDP) solicitations ucast_probes times in PROBE state. Zhu Yanjun reported that some implementation does not reply against them and the entry will become FAILED, which is undesirable. We had been dealt with such nodes by sending multicast probes mcast_ solicit times after unicast probes in PROBE state. In 2003, I made a change not to send them to improve compatibility with IPv6 NDP. Let's introduce per-protocol per-interface sysctl knob "mcast_ reprobe" to configure the number of multicast (re)solicitation for reconfirmation in PROBE state. The default is 0, since we have been doing so for 10+ years. Reported-by: Zhu Yanjun CC: Ulf Samuelsson Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 + include/uapi/linux/neighbour.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e7bdf5170802..bd33e66f49aa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -42,6 +42,7 @@ enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, + NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 3873a35509aa..2e35c61bbdd1 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -126,6 +126,7 @@ enum { NDTPA_PROXY_QLEN, /* u32 */ NDTPA_LOCKTIME, /* u64, msecs */ NDTPA_QUEUE_LENBYTES, /* u32 */ + NDTPA_MCAST_REPROBES, /* u32 */ __NDTPA_MAX }; #define NDTPA_MAX (__NDTPA_MAX - 1) -- cgit v1.2.3 From 8d0451638ad3f7ccd5250c1dd90e06ad487b2703 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 18 Mar 2015 20:55:31 +0100 Subject: netfilter: bridge: kill nf_bridge_pad The br_netfilter frag output function calls skb_cow_head() so in case it needs a larger headroom to e.g. re-add a previously stripped PPPOE or VLAN header things will still work (at cost of reallocation). We can then move nf_bridge_encap_header_len to br_netfilter. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index ed0d3bf953c3..2734977199ca 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -23,18 +23,6 @@ enum nf_br_hook_priorities { #define BRNF_8021Q 0x10 #define BRNF_PPPoE 0x20 -static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) -{ - switch (skb->protocol) { - case __cpu_to_be16(ETH_P_8021Q): - return VLAN_HLEN; - case __cpu_to_be16(ETH_P_PPP_SES): - return PPPOE_SES_HLEN; - default: - return 0; - } -} - static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE)) @@ -44,15 +32,6 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) int br_handle_frame_finish(struct sk_buff *skb); -/* This is called by the IP fragmenting code and it ensures there is - * enough room for the encapsulating header (if there is one). */ -static inline unsigned int nf_bridge_pad(const struct sk_buff *skb) -{ - if (skb->nf_bridge) - return nf_bridge_encap_header_len(skb); - return 0; -} - static inline void br_drop_fake_rtable(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -62,7 +41,6 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb) } #else -#define nf_bridge_pad(skb) (0) #define br_drop_fake_rtable(skb) do { } while (0) #endif /* CONFIG_BRIDGE_NETFILTER */ -- cgit v1.2.3 From 2b290bbb60847c0897c047b5214192810de529df Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 10 Mar 2015 04:48:20 +0100 Subject: can: use sock_efree instead of own destructor It is identical to the can destructor. Signed-off-by: Florian Westphal Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index cc00d15c6107..b6a52a4b457a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -44,16 +44,11 @@ static inline void can_skb_reserve(struct sk_buff *skb) skb_reserve(skb, sizeof(struct can_skb_priv)); } -static inline void can_skb_destructor(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) { if (sk) { sock_hold(sk); - skb->destructor = can_skb_destructor; + skb->destructor = sock_efree; skb->sk = sk; } } -- cgit v1.2.3 From c54eb70e3bb8cd0d7b8564bedab63e834656c567 Mon Sep 17 00:00:00 2001 From: Yegor Yefremov Date: Mon, 16 Mar 2015 09:38:13 +0100 Subject: can: add combined rx/tx LED trigger support Add -rxtx trigger, that will be activated both for tx as rx events. This trigger mimics "activity" LED for Ethernet devices. Signed-off-by: Yegor Yefremov Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 2 ++ include/linux/can/led.h | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c05ff0f9f9a5..c3a9c8fc60fa 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -61,6 +61,8 @@ struct can_priv { char tx_led_trig_name[CAN_LED_NAME_SZ]; struct led_trigger *rx_led_trig; char rx_led_trig_name[CAN_LED_NAME_SZ]; + struct led_trigger *rxtx_led_trig; + char rxtx_led_trig_name[CAN_LED_NAME_SZ]; #endif }; diff --git a/include/linux/can/led.h b/include/linux/can/led.h index e0475c5cbb92..146de4506d21 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -21,8 +21,10 @@ enum can_led_event { #ifdef CONFIG_CAN_LEDS -/* keep space for interface name + "-tx"/"-rx" suffix and null terminator */ -#define CAN_LED_NAME_SZ (IFNAMSIZ + 4) +/* keep space for interface name + "-tx"/"-rx"/"-rxtx" + * suffix and null terminator + */ +#define CAN_LED_NAME_SZ (IFNAMSIZ + 6) void can_led_event(struct net_device *netdev, enum can_led_event event); void devm_can_led_init(struct net_device *netdev); -- cgit v1.2.3 From 0345f93138b2224e0d7ce91fcffdb3dd23f364d7 Mon Sep 17 00:00:00 2001 From: "tadeusz.struk@intel.com" Date: Thu, 19 Mar 2015 12:31:25 -0700 Subject: net: socket: add support for async operations Add support for async operations. Signed-off-by: Tadeusz Struk Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index fab4d0ddf4ed..c9852ef7e317 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -51,6 +51,7 @@ struct msghdr { void *msg_control; /* ancillary data */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ unsigned int msg_flags; /* flags on received message */ + struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; struct user_msghdr { -- cgit v1.2.3 From 66db37391dad834a4f739984eec81af27a68b09c Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Thu, 19 Mar 2015 12:31:30 -0700 Subject: crypto: af_alg - Allow to link sgl Allow to link af_alg sgls. Signed-off-by: Tadeusz Struk Signed-off-by: David S. Miller --- include/crypto/if_alg.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 178525e5f430..018afb264ac2 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -58,8 +58,9 @@ struct af_alg_type { }; struct af_alg_sgl { - struct scatterlist sg[ALG_MAX_PAGES]; + struct scatterlist sg[ALG_MAX_PAGES + 1]; struct page *pages[ALG_MAX_PAGES]; + unsigned int npages; }; int af_alg_register_type(const struct af_alg_type *type); @@ -70,6 +71,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); +void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new); int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con); -- cgit v1.2.3 From 42cb80a2353f42913ae78074ffa1f1b4a49e5436 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 22 Mar 2015 10:22:19 -0700 Subject: inet: remove sk_listener parameter from syn_ack_timeout() It is not needed, and req->sk_listener points to the listener anyway. request_sock argument can be const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/dccp.h | 2 +- include/net/request_sock.h | 3 +-- include/net/tcp.h | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 439ff698000a..3dca24d3ac67 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -317,6 +317,6 @@ static inline const char *dccp_role(const struct sock *sk) return NULL; } -extern void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req); +extern void dccp_syn_ack_timeout(const struct request_sock *req); #endif /* _LINUX_DCCP_H */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 6a91261d9b7b..8603c350fad0 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -39,8 +39,7 @@ struct request_sock_ops { void (*send_reset)(struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); - void (*syn_ack_timeout)(struct sock *sk, - struct request_sock *req); + void (*syn_ack_timeout)(const struct request_sock *req); }; int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); diff --git a/include/net/tcp.h b/include/net/tcp.h index 082fd79132b7..1876262afd59 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -433,7 +433,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); +void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); void tcp_parse_options(const struct sk_buff *skb, -- cgit v1.2.3 From b282705336e03fc7b9377a278939594870a40f96 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 22 Mar 2015 10:22:21 -0700 Subject: net: convert syn_wait_lock to a spinlock This is a low hanging fruit, as we'll get rid of syn_wait_lock eventually. We hold syn_wait_lock for such small sections, that it makes no sense to use a read/write lock. A spin lock is simply faster. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 8603c350fad0..fe41f3ceb008 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -173,11 +173,6 @@ struct fastopen_queue { * %syn_wait_lock is necessary only to avoid proc interface having to grab the main * lock sock while browsing the listening hash (otherwise it's deadlock prone). * - * This lock is acquired in read mode only from listening_get_next() seq_file - * op and it's acquired in write mode _only_ from code that is actively - * changing rskq_accept_head. All readers that are holding the master sock lock - * don't need to grab this lock in read mode too as rskq_accept_head. writes - * are always protected from the main sock lock. */ struct request_sock_queue { struct request_sock *rskq_accept_head; @@ -192,7 +187,7 @@ struct request_sock_queue { */ /* temporary alignment, our goal is to get rid of this lock */ - rwlock_t syn_wait_lock ____cacheline_aligned_in_smp; + spinlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -223,14 +218,14 @@ static inline void reqsk_queue_unlink(struct request_sock_queue *queue, struct listen_sock *lopt = queue->listen_opt; struct request_sock **prev; - write_lock(&queue->syn_wait_lock); + spin_lock(&queue->syn_wait_lock); prev = &lopt->syn_table[req->rsk_hash]; while (*prev != req) prev = &(*prev)->dl_next; *prev = req->dl_next; - write_unlock(&queue->syn_wait_lock); + spin_unlock(&queue->syn_wait_lock); if (del_timer(&req->rsk_timer)) reqsk_put(req); } -- cgit v1.2.3 From 26e3736090e1037ac929787df21c05497479b77f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 22 Mar 2015 10:22:22 -0700 Subject: ipv4: tcp: handle ICMP messages on TCP_NEW_SYN_RECV request sockets tcp_v4_err() can restrict lookups to ehash table, and not to listeners. Note this patch creates the infrastructure, but this means that ICMP messages for request sockets are ignored until complete conversion. New tcp_req_err() helper is exported so that we can use it in IPv6 in following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1876262afd59..fe60e00e1919 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -447,6 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); +void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, -- cgit v1.2.3 From 85645bab57bfc6b0b43bb96a301c4ef83925c07d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 22 Mar 2015 10:22:24 -0700 Subject: ipv4: dccp: handle ICMP messages on DCCP_NEW_SYN_RECV request sockets dccp_v4_err() can restrict lookups to ehash table, and not to listeners. Note this patch creates the infrastructure, but this means that ICMP messages for request sockets are ignored until complete conversion. New dccp_req_err() helper is exported so that we can use it in IPv6 in following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/dccp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 3dca24d3ac67..221025423e6c 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -43,6 +43,7 @@ enum dccp_state { DCCP_CLOSING = TCP_CLOSING, DCCP_TIME_WAIT = TCP_TIME_WAIT, DCCP_CLOSED = TCP_CLOSE, + DCCP_NEW_SYN_RECV = TCP_NEW_SYN_RECV, DCCP_PARTOPEN = TCP_MAX_STATES, DCCP_PASSIVE_CLOSEREQ, /* clients receiving CloseReq */ DCCP_MAX_STATES @@ -57,6 +58,7 @@ enum { DCCPF_CLOSING = TCPF_CLOSING, DCCPF_TIME_WAIT = TCPF_TIME_WAIT, DCCPF_CLOSED = TCPF_CLOSE, + DCCPF_NEW_SYN_RECV = TCPF_NEW_SYN_RECV, DCCPF_PARTOPEN = (1 << DCCP_PARTOPEN), }; -- cgit v1.2.3 From 841a6664f213f76a9bc1bfd07a466d3dbe281a88 Mon Sep 17 00:00:00 2001 From: Arman Uguray Date: Mon, 23 Mar 2015 15:57:09 -0700 Subject: Bluetooth: Add definitions for Add/Remove Advertising API This patch adds definitions for the Add Advertising and Remove Advertising MGMT commands and events. Signed-off-by: Arman Uguray Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index a1a68671bf88..68abd4b0c25d 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -539,6 +539,30 @@ struct mgmt_rp_read_adv_features { __u8 instance[0]; } __packed; +#define MGMT_OP_ADD_ADVERTISING 0x003E +struct mgmt_cp_add_advertising { + __u8 instance; + __le32 flags; + __le16 duration; + __le16 timeout; + __u8 adv_data_len; + __u8 scan_rsp_len; + __u8 data[0]; +} __packed; +#define MGMT_ADD_ADVERTISING_SIZE 11 +struct mgmt_rp_add_advertising { + __u8 instance; +} __packed; + +#define MGMT_OP_REMOVE_ADVERTISING 0x003F +struct mgmt_cp_remove_advertising { + __u8 instance; +} __packed; +#define MGMT_REMOVE_ADVERTISING_SIZE 1 +struct mgmt_rp_remove_advertising { + __u8 instance; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -742,3 +766,13 @@ struct mgmt_ev_local_oob_data_updated { __le16 eir_len; __u8 eir[0]; } __packed; + +#define MGMT_EV_ADVERTISING_ADDED 0x0023 +struct mgmt_ev_advertising_added { + __u8 instance; +} __packed; + +#define MGMT_EV_ADVERTISING_REMOVED 0x0024 +struct mgmt_ev_advertising_removed { + __u8 instance; +} __packed; -- cgit v1.2.3 From 4453b006538d02ada8294a195bb2dc2ada498436 Mon Sep 17 00:00:00 2001 From: Arman Uguray Date: Mon, 23 Mar 2015 15:57:10 -0700 Subject: Bluetooth: Introduce HCI_ADVERTISING_INSTANCE setting and add AD flags This patch introduces the HCI_ADVERTISING_INSTANCE setting, which is set when an at least one advertising instance has been added using the "Add Advertising" mgmt command. This patch also adds a macro definition for the EIR_APPEARANCE field type. Signed-off-by: Arman Uguray Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 06e7eee31ce4..3acecf35420b 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -227,6 +227,7 @@ enum { HCI_LE_ENABLED, HCI_ADVERTISING, HCI_ADVERTISING_CONNECTABLE, + HCI_ADVERTISING_INSTANCE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, @@ -465,6 +466,7 @@ enum { #define EIR_SSP_HASH_C 0x0E /* Simple Pairing Hash C */ #define EIR_SSP_RAND_R 0x0F /* Simple Pairing Randomizer R */ #define EIR_DEVICE_ID 0x10 /* device ID */ +#define EIR_APPEARANCE 0x19 /* Device appearance */ #define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ #define EIR_LE_ROLE 0x1C /* LE role */ #define EIR_LE_SC_CONFIRM 0x22 /* LE SC Confirmation Value */ -- cgit v1.2.3 From 203fea0178d7e165dbe834d1bdd9d243018fd5bf Mon Sep 17 00:00:00 2001 From: Arman Uguray Date: Mon, 23 Mar 2015 15:57:11 -0700 Subject: Bluetooth: Add data structure for advertising instance This patch introduces a new data structure to represent advertising instances that were added using the "Add Advertising" mgmt command. Initially an hci_dev structure will support only one of these instances at a time, so the current instance is simply stored as a direct member of hci_dev. Signed-off-by: Arman Uguray Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b65c53de6a69..3a6d4e3d68fe 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -155,6 +155,15 @@ struct oob_data { u8 rand256[16]; }; +struct adv_info { + __u8 instance; + __u32 flags; + __u16 adv_data_len; + __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u16 scan_rsp_len; + __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; +}; + #define HCI_MAX_SHORT_NAME_LENGTH 10 /* Default LE RPA expiry time, 15 minutes */ @@ -364,6 +373,8 @@ struct hci_dev { __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; __u8 scan_rsp_data_len; + struct adv_info adv_instance; + __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; @@ -550,6 +561,11 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev) hdev->discovery.scan_duration = 0; } +static inline void adv_info_init(struct hci_dev *hdev) +{ + memset(&hdev->adv_instance, 0, sizeof(struct adv_info)); +} + bool hci_discovery_active(struct hci_dev *hdev); void hci_discovery_set_state(struct hci_dev *hdev, int state); -- cgit v1.2.3 From 912098a6308e37208b8dcc46c57c66d0778a854b Mon Sep 17 00:00:00 2001 From: Arman Uguray Date: Mon, 23 Mar 2015 15:57:15 -0700 Subject: Bluetooth: Add support for adv instance timeout This patch implements support for the timeout parameter of the Add Advertising command. Signed-off-by: Arman Uguray Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3a6d4e3d68fe..540c07feece7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -156,8 +156,10 @@ struct oob_data { }; struct adv_info { + struct delayed_work timeout_exp; __u8 instance; __u32 flags; + __u16 timeout; __u16 adv_data_len; __u8 adv_data[HCI_MAX_AD_LENGTH]; __u16 scan_rsp_len; -- cgit v1.2.3 From 682f048bd49449f4ab978664a7f69a44a74e3caa Mon Sep 17 00:00:00 2001 From: Alexander Drozdov Date: Mon, 23 Mar 2015 09:11:13 +0300 Subject: af_packet: pass checksum validation status to the user Introduce TP_STATUS_CSUM_VALID tp_status flag to tell the af_packet user that at least the transport header checksum has been already validated. For now, the flag may be set for incoming packets only. Signed-off-by: Alexander Drozdov Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index da2d668b8cf1..053bd102fbe0 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -99,6 +99,7 @@ struct tpacket_auxdata { #define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */ #define TP_STATUS_BLK_TMO (1 << 5) #define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */ +#define TP_STATUS_CSUM_VALID (1 << 7) /* Tx ring - header status */ #define TP_STATUS_AVAILABLE 0 -- cgit v1.2.3 From de91b25c8011089f5dd99b9d24743db1f550ca4b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 24 Mar 2015 00:50:20 +1100 Subject: rhashtable: Eliminate unnecessary branch in rht_key_hashfn When rht_key_hashfn is called from rhashtable itself and params is equal to ht->p, there is no point in checking params.key_len and falling back to ht->p.key_len. For some reason gcc couldn't figure out that params is the same as ht->p. So let's help it by only checking params.key_len when it's a constant. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 89d102270570..3851952781d7 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -199,8 +199,12 @@ static inline unsigned int rht_key_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const void *key, const struct rhashtable_params params) { - return rht_bucket_index(tbl, params.hashfn(key, params.key_len ?: - ht->p.key_len, + /* params must be equal to ht->p if it isn't constant. */ + unsigned key_len = __builtin_constant_p(params.key_len) ? + (params.key_len ?: ht->p.key_len) : + params.key_len; + + return rht_bucket_index(tbl, params.hashfn(key, key_len, tbl->hash_rnd)); } -- cgit v1.2.3 From 31ccde2dacea8375c3a7d6fffbf0060ee0d40214 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 24 Mar 2015 00:50:21 +1100 Subject: rhashtable: Allow hashfn to be unset Since every current rhashtable user uses jhash as their hash function, the fact that jhash is an inline function causes each user to generate a copy of its code. This function provides a solution to this problem by allowing hashfn to be unset. In which case rhashtable will automatically set it to jhash. Furthermore, if the key length is a multiple of 4, we will switch over to jhash2. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 3851952781d7..bc2488b98321 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #include #include +#include #include #include #include @@ -103,7 +104,7 @@ struct rhashtable; * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) - * @hashfn: Function to hash key + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object * @obj_cmpfn: Function to compare key with object */ @@ -125,6 +126,7 @@ struct rhashtable_params { * struct rhashtable - Hash table handle * @tbl: Bucket table * @nelems: Number of elements in table + * @key_len: Key length for hashfn * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping @@ -134,6 +136,7 @@ struct rhashtable { struct bucket_table __rcu *tbl; atomic_t nelems; bool being_destroyed; + unsigned int key_len; struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; @@ -199,13 +202,31 @@ static inline unsigned int rht_key_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const void *key, const struct rhashtable_params params) { + unsigned hash; + /* params must be equal to ht->p if it isn't constant. */ - unsigned key_len = __builtin_constant_p(params.key_len) ? - (params.key_len ?: ht->p.key_len) : - params.key_len; + if (!__builtin_constant_p(params.key_len)) + hash = ht->p.hashfn(key, ht->key_len, tbl->hash_rnd); + else if (params.key_len) { + unsigned key_len = params.key_len; + + if (params.hashfn) + hash = params.hashfn(key, key_len, tbl->hash_rnd); + else if (key_len & (sizeof(u32) - 1)) + hash = jhash(key, key_len, tbl->hash_rnd); + else + hash = jhash2(key, key_len / sizeof(u32), + tbl->hash_rnd); + } else { + unsigned key_len = ht->p.key_len; + + if (params.hashfn) + hash = params.hashfn(key, key_len, tbl->hash_rnd); + else + hash = jhash(key, key_len, tbl->hash_rnd); + } - return rht_bucket_index(tbl, params.hashfn(key, key_len, - tbl->hash_rnd)); + return rht_bucket_index(tbl, hash); } static inline unsigned int rht_head_hashfn( -- cgit v1.2.3 From b824478b2145be78ac19e1cf44e2b9036c7a9608 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 24 Mar 2015 00:50:26 +1100 Subject: rhashtable: Add multiple rehash support This patch adds the missing bits to allow multiple rehashes. The read-side as well as remove already handle this correctly. So it's only the rehasher and insertion that need modification to handle this. Note that this patch doesn't actually enable it so for now rehashing is still only performed by the worker thread. This patch also disables the explicit expand/shrink interface because the table is meant to expand and shrink automatically, and continuing to export these interfaces unnecessarily complicates the life of the rehasher since the rehash process is now composed of two parts. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index bc2488b98321..e8ffcdb5e239 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -308,9 +308,6 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj, struct bucket_table *old_tbl); -int rhashtable_expand(struct rhashtable *ht); -int rhashtable_shrink(struct rhashtable *ht); - int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); @@ -541,17 +538,22 @@ static inline int __rhashtable_insert_fast( rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); - hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - - spin_lock_bh(lock); - /* Because we have already taken the bucket lock in tbl, - * if we find that future_tbl is not yet visible then - * that guarantees all other insertions of the same entry - * will also grab the bucket lock in tbl because until - * the rehash completes ht->tbl won't be changed. + /* All insertions must grab the oldest table containing + * the hashed bucket that is yet to be rehashed. */ + for (;;) { + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + spin_lock_bh(lock); + + if (tbl->rehash <= hash) + break; + + spin_unlock_bh(lock); + tbl = rht_dereference_rcu(tbl->future_tbl, ht); + } + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { err = rhashtable_insert_slow(ht, key, obj, new_tbl); -- cgit v1.2.3 From ccd57b1bd32460d27bbb9c599e795628a3c66983 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 24 Mar 2015 00:50:28 +1100 Subject: rhashtable: Add immediate rehash during insertion This patch reintroduces immediate rehash during insertion. If we find during insertion that the table is full or the chain length exceeds a set limit (currently 16 but may be disabled with insecure_elasticity) then we will force an immediate rehash. The rehash will contain an expansion if the table utilisation exceeds 75%. If this rehash fails then the insertion will fail. Otherwise the insertion will be reattempted in the new hash table. Signed-off-by: Herbert Xu Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 42 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e8ffcdb5e239..f9ecf32bce55 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -103,6 +103,7 @@ struct rhashtable; * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker + * @insecure_elasticity: Set to true to disable chain length checks * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object @@ -116,6 +117,7 @@ struct rhashtable_params { unsigned int max_size; unsigned int min_size; u32 nulls_base; + bool insecure_elasticity; size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; @@ -127,6 +129,7 @@ struct rhashtable_params { * @tbl: Bucket table * @nelems: Number of elements in table * @key_len: Key length for hashfn + * @elasticity: Maximum chain length before rehash * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping @@ -137,6 +140,7 @@ struct rhashtable { atomic_t nelems; bool being_destroyed; unsigned int key_len; + unsigned int elasticity; struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; @@ -266,6 +270,17 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, tbl->size > ht->p.min_size; } +/** + * rht_grow_above_100 - returns true if nelems > table-size + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_100(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + return atomic_read(&ht->nelems) > tbl->size; +} + /* The bucket lock is selected based on the hash and protects mutations * on a group of hash buckets. * @@ -307,6 +322,7 @@ int rhashtable_init(struct rhashtable *ht, int rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj, struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -529,12 +545,14 @@ static inline int __rhashtable_insert_fast( .ht = ht, .key = key, }; - int err = -EEXIST; struct bucket_table *tbl, *new_tbl; struct rhash_head *head; spinlock_t *lock; + unsigned elasticity; unsigned hash; + int err; +restart: rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); @@ -557,20 +575,34 @@ static inline int __rhashtable_insert_fast( new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { err = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (err == -EAGAIN) + goto slow_path; goto out; } - if (!key) - goto skip_lookup; + if (unlikely(rht_grow_above_100(ht, tbl))) { +slow_path: + spin_unlock_bh(lock); + rcu_read_unlock(); + err = rhashtable_insert_rehash(ht); + if (err) + return err; + + goto restart; + } + err = -EEXIST; + elasticity = ht->elasticity; rht_for_each(head, tbl, hash) { - if (unlikely(!(params.obj_cmpfn ? + if (key && + unlikely(!(params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, head)) : rhashtable_compare(&arg, rht_obj(ht, head))))) goto out; + if (!--elasticity) + goto slow_path; } -skip_lookup: err = 0; head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); -- cgit v1.2.3 From 3d1bec99320d4e96897805440f8cf4f68eff226b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:00 +0100 Subject: ipv6: introduce secret_stable to ipv6_devconf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch implements the procfs logic for the stable_address knob: The secret is formatted as an ipv6 address and will be stored per interface and per namespace. We track initialized flag and return EIO errors until the secret is set. We don't inherit the secret to newly created namespaces. Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++++ include/uapi/linux/ipv6.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4d5169f5d7d1..82806c60aa42 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -53,6 +53,10 @@ struct ipv6_devconf { __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; + struct ipv6_stable_secret { + bool initialized; + struct in6_addr secret; + } stable_secret; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 437a6a4b125a..5efa54ae567c 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -170,6 +170,7 @@ enum { DEVCONF_ACCEPT_RA_FROM_LOCAL, DEVCONF_USE_OPTIMISTIC, DEVCONF_ACCEPT_RA_MTU, + DEVCONF_STABLE_SECRET, DEVCONF_MAX }; -- cgit v1.2.3 From 622c81d57b392cc9be836670eb464a4dfaa9adfe Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:01 +0100 Subject: ipv6: generation of stable privacy addresses for link-local and autoconf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch implements the stable privacy address generation for link-local and autoconf addresses as specified in RFC7217. RID = F(Prefix, Net_Iface, Network_ID, DAD_Counter, secret_key) is the RID (random identifier). As the hash function F we chose one round of sha1. Prefix will be either the link-local prefix or the router advertised one. As Net_Iface we use the MAC address of the device. DAD_Counter and secret_key are implemented as specified. We don't use Network_ID, as it couples the code too closely to other subsystems. It is specified as optional in the RFC. As Net_Iface we only use the MAC address: we simply have no stable identifier in the kernel we could possibly use: because this code might run very early, we cannot depend on names, as they might be changed by user space early on during the boot process. A new address generation mode is introduced, IN6_ADDR_GEN_MODE_STABLE_PRIVACY. With iproute2 one can switch back to none or eui64 address configuration mode although the stable_secret is already set. We refuse writes to ipv6/conf/all/stable_secret but only allow ipv6/conf/default/stable_secret and the interface specific file to be written to. The default stable_secret is used as the parameter for the namespace, the interface specific can overwrite the secret, e.g. when switching a network configuration from one system to another while inheriting the secret. Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index f5f5edd5ae5f..7ffb18df01ca 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -216,6 +216,7 @@ enum { enum in6_addr_gen_mode { IN6_ADDR_GEN_MODE_EUI64, IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, }; /* Bridge section */ -- cgit v1.2.3 From 64236f3f3d742469e4027b83a9515e84e9ab21b4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:02 +0100 Subject: ipv6: introduce IFA_F_STABLE_PRIVACY flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to mark appropriate addresses so we can do retries in case their DAD failed. Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/uapi/linux/if_addr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index 40fdfea39714..4318ab1635ce 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -51,6 +51,7 @@ enum { #define IFA_F_MANAGETEMPADDR 0x100 #define IFA_F_NOPREFIXROUTE 0x200 #define IFA_F_MCAUTOJOIN 0x400 +#define IFA_F_STABLE_PRIVACY 0x800 struct ifa_cacheinfo { __u32 ifa_prefered; -- cgit v1.2.3 From 8e8e676d0b3c7f074c719c7c05b20296b9b0b0b1 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:03 +0100 Subject: ipv6: collapse state_lock and lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/if_inet6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 98e5f9578f86..d89397a22903 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -41,13 +41,12 @@ enum { struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; - + /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; atomic_t refcnt; spinlock_t lock; - spinlock_t state_lock; int state; -- cgit v1.2.3 From 5f40ef77adb237954d615a76621df1b80a329b31 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:04 +0100 Subject: ipv6: do retries on stable privacy addresses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a DAD conflict is detected, we want to retry privacy stable address generation up to idgen_retries (= 3) times with a delay of idgen_delay (= 1 second). Add the logic to addrconf_dad_failure. By design, we don't clean up dad failed permanent addresses. Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/if_inet6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index d89397a22903..1c8b6820b694 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -52,6 +52,7 @@ struct inet6_ifaddr { __u32 flags; __u8 dad_probes; + __u8 stable_privacy_retry; __u16 scope; -- cgit v1.2.3 From 1855b7c3e8537c2a4f5a53c797624713bb3becb4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 23:36:05 +0100 Subject: ipv6: introduce idgen_delay and idgen_retries knobs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is specified by RFC 7217. Cc: Erik Kline Cc: Fernando Gont Cc: Lorenzo Colitti Cc: YOSHIFUJI Hideaki/吉藤英明 Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/netns/ipv6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index ca0db12cd089..d2527bf81142 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -32,6 +32,8 @@ struct netns_sysctl_ipv6 { int icmpv6_time; int anycast_src_echo_reply; int fwmark_reflect; + int idgen_retries; + int idgen_delay; }; struct netns_ipv6 { -- cgit v1.2.3 From ba7c95ea3870fe7b847466d39a049ab6f156aa2c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 24 Mar 2015 09:53:17 +1100 Subject: rhashtable: Fix sleeping inside RCU critical section in walk_stop The commit 963ecbd41a1026d99ec7537c050867428c397b89 ("rhashtable: Fix use-after-free in rhashtable_walk_stop") fixed a real bug but created another one because we may end up sleeping inside an RCU critical section. This patch fixes it properly by replacing the mutex with a spin lock that specifically protects the walker lists. Reported-by: Sasha Levin Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index f9ecf32bce55..d7be9cb0e91f 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -133,6 +133,7 @@ struct rhashtable_params { * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping + * @lock: Spin lock to protect walker list * @being_destroyed: True if table is set up for destruction */ struct rhashtable { @@ -144,6 +145,7 @@ struct rhashtable { struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; + spinlock_t lock; }; /** -- cgit v1.2.3 From 0117ec1970c5fa9c566045e7df8db76acc8f150e Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 23 Mar 2015 18:40:02 +0100 Subject: net: remove never used forwarding_accel_ops pointer from net_device Cc: John Fastabend Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ae69e7df867..08c4ab37189f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1342,7 +1342,6 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations - * @fwd_ops: Management operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1551,7 +1550,6 @@ struct net_device { #endif const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; - const struct forwarding_accel_ops *fwd_ops; #ifdef CONFIG_NET_SWITCHDEV const struct swdev_ops *swdev_ops; #endif -- cgit v1.2.3 From 27cd5452476978283decb19e429e81fc6c71e74b Mon Sep 17 00:00:00 2001 From: Michal Sekletar Date: Tue, 24 Mar 2015 14:48:41 +0100 Subject: filter: introduce SKF_AD_VLAN_TPID BPF extension If vlan offloading takes place then vlan header is removed from frame and its contents, both vlan_tci and vlan_proto, is available to user space via TPACKET interface. However, only vlan_tci can be used in BPF filters. This commit introduces a new BPF extension. It makes possible to load the value of vlan_proto (vlan TPID) to register A. Support for classic BPF and eBPF is being added, analogous to skb->protocol. Cc: Daniel Borkmann Cc: Alexei Starovoitov Cc: Jiri Pirko Signed-off-by: Michal Sekletar Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 1 + include/uapi/linux/filter.h | 3 ++- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9ee8c67ea249..fa11b3a367be 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -454,6 +454,7 @@ static inline u16 bpf_anc_helper(const struct sock_filter *ftest) BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); + BPF_ANCILLARY(VLAN_TPID); } /* Fallthrough. */ default: diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3dd314a45d0d..27dc4ec58840 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -182,6 +182,7 @@ struct __sk_buff { __u32 protocol; __u32 vlan_present; __u32 vlan_tci; + __u32 vlan_proto; }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h index 47785d5ecf17..34c7936ca114 100644 --- a/include/uapi/linux/filter.h +++ b/include/uapi/linux/filter.h @@ -77,7 +77,8 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_VLAN_TAG_PRESENT 48 #define SKF_AD_PAY_OFFSET 52 #define SKF_AD_RANDOM 56 -#define SKF_AD_MAX 60 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) -- cgit v1.2.3 From 58be8a583d8d316448bafa5926414cfb83c02dec Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 24 Mar 2015 14:18:16 +0100 Subject: rhashtable: Extend RCU read lock into rhashtable_insert_rehash() rhashtable_insert_rehash() requires RCU locks to be held in order to access ht->tbl and traverse to the last table. Fixes: ccd57b1bd324 ("rhashtable: Add immediate rehash during insertion") Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index d7be9cb0e91f..5976ab59b88f 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -585,8 +585,8 @@ restart: if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); - rcu_read_unlock(); err = rhashtable_insert_rehash(ht); + rcu_read_unlock(); if (err) return err; -- cgit v1.2.3 From 299e5c32a37a6bca8175db177117467bd1ce970a Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 24 Mar 2015 14:18:17 +0100 Subject: rhashtable: Use 'unsigned int' consistently Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5976ab59b88f..f89cda067cb9 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -208,13 +208,13 @@ static inline unsigned int rht_key_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const void *key, const struct rhashtable_params params) { - unsigned hash; + unsigned int hash; /* params must be equal to ht->p if it isn't constant. */ if (!__builtin_constant_p(params.key_len)) hash = ht->p.hashfn(key, ht->key_len, tbl->hash_rnd); else if (params.key_len) { - unsigned key_len = params.key_len; + unsigned int key_len = params.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, tbl->hash_rnd); @@ -224,7 +224,7 @@ static inline unsigned int rht_key_hashfn( hash = jhash2(key, key_len / sizeof(u32), tbl->hash_rnd); } else { - unsigned key_len = ht->p.key_len; + unsigned int key_len = ht->p.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, tbl->hash_rnd); @@ -512,7 +512,7 @@ static inline void *rhashtable_lookup_fast( }; const struct bucket_table *tbl; struct rhash_head *he; - unsigned hash; + unsigned int hash; rcu_read_lock(); @@ -550,8 +550,8 @@ static inline int __rhashtable_insert_fast( struct bucket_table *tbl, *new_tbl; struct rhash_head *head; spinlock_t *lock; - unsigned elasticity; - unsigned hash; + unsigned int elasticity; + unsigned int hash; int err; restart: @@ -718,7 +718,7 @@ static inline int __rhashtable_remove_fast( struct rhash_head __rcu **pprev; struct rhash_head *he; spinlock_t * lock; - unsigned hash; + unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); -- cgit v1.2.3 From ac833bddb591b9c7a0609f440f196375be184044 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 24 Mar 2015 14:18:18 +0100 Subject: rhashtable: Mark internal/private inline functions as such Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index f89cda067cb9..0e1f975ad101 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -539,6 +539,7 @@ restart: return NULL; } +/* Internal function, please use rhashtable_insert_fast() instead */ static inline int __rhashtable_insert_fast( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params) @@ -711,6 +712,7 @@ static inline int rhashtable_lookup_insert_key( return __rhashtable_insert_fast(ht, key, obj, params); } +/* Internal function, please use rhashtable_remove_fast() instead */ static inline int __rhashtable_remove_fast( struct rhashtable *ht, struct bucket_table *tbl, struct rhash_head *obj, const struct rhashtable_params params) -- cgit v1.2.3 From b5e2c150ac914f28a28833b57397bec0b0a2bd5f Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 24 Mar 2015 20:42:19 +0000 Subject: rhashtable: Disable automatic shrinking by default Introduce a new bool automatic_shrinking to require the user to explicitly opt-in to automatic shrinking of tables. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 0e1f975ad101..ae26c494e230 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -2,7 +2,7 @@ * Resizable, Scalable, Concurrent Hash Table * * Copyright (c) 2015 Herbert Xu - * Copyright (c) 2014 Thomas Graf + * Copyright (c) 2014-2015 Thomas Graf * Copyright (c) 2008-2014 Patrick McHardy * * Code partially derived from nft_hash @@ -104,6 +104,7 @@ struct rhashtable; * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker * @insecure_elasticity: Set to true to disable chain length checks + * @automatic_shrinking: Enable automatic shrinking of tables * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) * @obj_hashfn: Function to hash object @@ -118,6 +119,7 @@ struct rhashtable_params { unsigned int min_size; u32 nulls_base; bool insecure_elasticity; + bool automatic_shrinking; size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; @@ -784,7 +786,8 @@ static inline int rhashtable_remove_fast( goto out; atomic_dec(&ht->nelems); - if (rht_shrink_below_30(ht, tbl)) + if (unlikely(ht->p.automatic_shrinking && + rht_shrink_below_30(ht, tbl))) schedule_work(&ht->run_work); out: -- cgit v1.2.3 From 6b6f302ceda7a052dab545d6c69abf5f0d4a6cab Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 24 Mar 2015 14:18:20 +0100 Subject: rhashtable: Add rhashtable_free_and_destroy() rhashtable_destroy() variant which stops rehashes, iterates over the table and calls a callback to release resources. Avoids need for nft_hash to embed rhashtable internals and allows to get rid of the being_destroyed flag. It also saves a 2nd mutex lock upon destruction. Also fixes an RCU lockdep splash on nft set destruction due to calling rht_for_each_entry_safe() without holding bucket locks. Open code this loop as we need know that no mutations may occur in parallel. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index ae26c494e230..99f2e49a8a07 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -136,12 +136,10 @@ struct rhashtable_params { * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping * @lock: Spin lock to protect walker list - * @being_destroyed: True if table is set up for destruction */ struct rhashtable { struct bucket_table __rcu *tbl; atomic_t nelems; - bool being_destroyed; unsigned int key_len; unsigned int elasticity; struct rhashtable_params p; @@ -334,6 +332,9 @@ int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); void *rhashtable_walk_next(struct rhashtable_iter *iter); void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); +void rhashtable_free_and_destroy(struct rhashtable *ht, + void (*free_fn)(void *ptr, void *arg), + void *arg); void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ -- cgit v1.2.3 From 39f8e58e53be32ab758d30536e0bd2e6ce766462 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Mar 2015 15:58:55 -0700 Subject: tcp: md5: remove request sock argument of calc_md5_hash() Since request and established sockets now have same base, there is no need to pass two pointers to tcp_v4_md5_hash_skb() or tcp_v6_md5_hash_skb() Also add a const qualifier to their struct tcp_md5sig_key argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index fe60e00e1919..992be858c370 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1296,9 +1296,8 @@ struct tcp_md5sig_pool { }; /* - functions */ -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb); +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, @@ -1616,14 +1615,13 @@ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, struct sock *addr_sk); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); - int (*md5_parse) (struct sock *sk, - char __user *optval, - int optlen); + int (*calc_md5_hash)(char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); + int (*md5_parse)(struct sock *sk, + char __user *optval, + int optlen); #endif }; @@ -1632,11 +1630,10 @@ struct tcp_request_sock_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, struct request_sock *req); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); + int (*calc_md5_hash) (char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From fd3a154a00fb991872680f19021f5edbb40b4dbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Mar 2015 15:58:56 -0700 Subject: tcp: md5: get rid of tcp_v[46]_reqsk_md5_lookup() With request socks convergence, we no longer need different lookup methods. A request socket can use generic lookup function. Add const qualifier to 2nd tcp_v[46]_md5_lookup() parameter. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 992be858c370..42690daa924e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1303,7 +1303,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk); + const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, @@ -1614,7 +1614,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct sock *addr_sk); + const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, @@ -1628,8 +1628,8 @@ struct tcp_sock_af_ops { struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct request_sock *req); + struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, -- cgit v1.2.3 From 5ebb335dcbe63470c88c4f80f2d571089543b638 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 21 Mar 2015 15:19:15 +0000 Subject: netfilter: nf_tables: move struct net pointer to base chain The network namespace is only needed for base chains to get at the gencursor. Also convert to possible_net_t. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d756af559977..ace67a549b30 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -449,7 +449,6 @@ enum nft_chain_flags { * * @rules: list of rules in the chain * @list: used internally - * @net: net namespace that this chain belongs to * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain @@ -460,7 +459,6 @@ enum nft_chain_flags { struct nft_chain { struct list_head rules; struct list_head list; - struct net *net; struct nft_table *table; u64 handle; u32 use; @@ -512,6 +510,7 @@ struct nft_stats { * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops + * @pnet: net namespace that this chain belongs to * @type: chain type * @policy: default policy * @stats: per-cpu chain stats @@ -519,6 +518,7 @@ struct nft_stats { */ struct nft_base_chain { struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; + possible_net_t pnet; const struct nf_chain_type *type; u8 policy; struct nft_stats __percpu *stats; -- cgit v1.2.3 From 7e3ea6d5c4f4880dbdf85f4083f40d8a3dc9b906 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 25 Mar 2015 14:13:01 +0800 Subject: sctp: avoid to repeatedly declare external variables Move the declaration for external variables to sctp.h file avoiding to repeatedly declare them with extern keyword. Signed-off-by: Ying Xue Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 856f01cb51dd..c56a438c3a1e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -166,6 +166,9 @@ void sctp_remaddr_proc_exit(struct net *net); */ extern struct kmem_cache *sctp_chunk_cachep __read_mostly; extern struct kmem_cache *sctp_bucket_cachep __read_mostly; +extern long sysctl_sctp_mem[3]; +extern int sysctl_sctp_rmem[3]; +extern int sysctl_sctp_wmem[3]; /* * Section: Macros, externs, and inlines -- cgit v1.2.3 From 49f7b33e63fec9d16e7ee62ba8f8ab4159cbdc26 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 13:07:45 +0000 Subject: rhashtable: provide len to obj_hashfn nftables sets will be converted to use so called setextensions, moving the key to a non-fixed position. To hash it, the obj_hashfn must be used, however it so far doesn't receive the length parameter. Pass the key length to obj_hashfn() and convert existing users. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/rhashtable.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 99f2e49a8a07..e23d242d1230 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -88,7 +88,7 @@ struct rhashtable_compare_arg { }; typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, const void *obj); @@ -242,7 +242,9 @@ static inline unsigned int rht_head_hashfn( const char *ptr = rht_obj(ht, he); return likely(params.obj_hashfn) ? - rht_bucket_index(tbl, params.obj_hashfn(ptr, tbl->hash_rnd)) : + rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?: + ht->p.key_len, + tbl->hash_rnd)) : rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); } -- cgit v1.2.3 From 3ac4c07a24007f0f45d2082b745508768a8e21cf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 13:07:49 +0000 Subject: netfilter: nf_tables: add set extensions Add simple set extension infrastructure for maintaining variable sized and optional per element data. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 105 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ace67a549b30..038f8a67ca1f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -311,6 +311,111 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); +/** + * enum nft_set_extensions - set extension type IDs + * + * @NFT_SET_EXT_KEY: element key + * @NFT_SET_EXT_DATA: mapping data + * @NFT_SET_EXT_FLAGS: element flags + * @NFT_SET_EXT_NUM: number of extension types + */ +enum nft_set_extensions { + NFT_SET_EXT_KEY, + NFT_SET_EXT_DATA, + NFT_SET_EXT_FLAGS, + NFT_SET_EXT_NUM +}; + +/** + * struct nft_set_ext_type - set extension type + * + * @len: fixed part length of the extension + * @align: alignment requirements of the extension + */ +struct nft_set_ext_type { + u8 len; + u8 align; +}; + +extern const struct nft_set_ext_type nft_set_ext_types[]; + +/** + * struct nft_set_ext_tmpl - set extension template + * + * @len: length of extension area + * @offset: offsets of individual extension types + */ +struct nft_set_ext_tmpl { + u16 len; + u8 offset[NFT_SET_EXT_NUM]; +}; + +/** + * struct nft_set_ext - set extensions + * + * @offset: offsets of individual extension types + * @data: beginning of extension data + */ +struct nft_set_ext { + u8 offset[NFT_SET_EXT_NUM]; + char data[0]; +}; + +static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) +{ + memset(tmpl, 0, sizeof(*tmpl)); + tmpl->len = sizeof(struct nft_set_ext); +} + +static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, + unsigned int len) +{ + tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); + BUG_ON(tmpl->len > U8_MAX); + tmpl->offset[id] = tmpl->len; + tmpl->len += nft_set_ext_types[id].len + len; +} + +static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) +{ + nft_set_ext_add_length(tmpl, id, 0); +} + +static inline void nft_set_ext_init(struct nft_set_ext *ext, + const struct nft_set_ext_tmpl *tmpl) +{ + memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); +} + +static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return !!ext->offset[id]; +} + +static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return ext && __nft_set_ext_exists(ext, id); +} + +static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) +{ + return (void *)ext + ext->offset[id]; +} + +static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_KEY); +} + +static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_DATA); +} + +static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_FLAGS); +} /** * struct nft_expr_type - nf_tables expression type -- cgit v1.2.3 From fe2811ebeb97a7a76de0b2b35f13600169508393 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 13:07:50 +0000 Subject: netfilter: nf_tables: convert hash and rbtree to set extensions The set implementations' private struct will only contain the elements needed to maintain the search structure, all other elements are moved to the set extensions. Element allocation and initialization is performed centrally by nf_tables_api instead of by the different set implementations' ->insert() functions. A new "elemsize" member in the set ops specifies the amount of memory to reserve for internal usage. Destruction will also be moved out of the set implementations by a following patch. Except for element allocation, the patch is a simple conversion to using data from the extension area. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 038f8a67ca1f..ef3457c1cb62 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -140,8 +140,7 @@ struct nft_userdata { * * @cookie: implementation specific element cookie * @key: element key - * @data: element data (maps only) - * @flags: element flags (end of interval) + * @priv: element private data and extensions * * The cookie can be used to store a handle to the element for subsequent * removal. @@ -149,8 +148,7 @@ struct nft_userdata { struct nft_set_elem { void *cookie; struct nft_data key; - struct nft_data data; - u32 flags; + void *priv; }; struct nft_set; @@ -214,6 +212,7 @@ struct nft_set_estimate { * @destroy: destroy private data of set instance * @list: nf_tables_set_ops list node * @owner: module reference + * @elemsize: element private size * @features: features supported by the implementation */ struct nft_set_ops { @@ -241,6 +240,7 @@ struct nft_set_ops { struct list_head list; struct module *owner; + unsigned int elemsize; u32 features; }; @@ -417,6 +417,12 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } +static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, + void *elem) +{ + return elem + set->ops->elemsize; +} + /** * struct nft_expr_type - nf_tables expression type * -- cgit v1.2.3 From b6a7719aedd7e5c0f2df7641aa47386111682df4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 25 Mar 2015 17:07:44 +0100 Subject: ipv4: hash net ptr into fragmentation bucket selection As namespaces are sometimes used with overlapping ip address ranges, we should also use the namespace as input to the hash to select the ip fragmentation counter bucket. Cc: Eric Dumazet Cc: Flavio Leitner Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 025c61c0dffb..d0808a323763 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -318,9 +318,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } u32 ip_idents_reserve(u32 hash, int segs); -void __ip_select_ident(struct iphdr *iph, int segs); +void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); -static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) +static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, + struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -337,13 +338,14 @@ static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, in iph->id = 0; } } else { - __ip_select_ident(iph, segs); + __ip_select_ident(net, iph, segs); } } -static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +static inline void ip_select_ident(struct net *net, struct sk_buff *skb, + struct sock *sk) { - ip_select_ident_segs(skb, sk, 1); + ip_select_ident_segs(net, skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) -- cgit v1.2.3 From 5a352dd0a3aac03b443c94828dfd7144261c8636 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 25 Mar 2015 17:07:45 +0100 Subject: ipv6: hash net ptr into fragmentation bucket selection As namespaces are sometimes used with overlapping ip address ranges, we should also use the namespace as input to the hash to select the ip fragmentation counter bucket. Cc: Eric Dumazet Cc: Flavio Leitner Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ipv6.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e7ba9758a345..65142e6af440 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); -void ipv6_proxy_select_ident(struct sk_buff *skb); +void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, + struct rt6_info *rt); +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); -- cgit v1.2.3 From 074c238177a75f5e79af3b2cb6a84e54823ef950 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:42 -0700 Subject: mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman Reported-by: Dave Chinner Tested-by: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6d77432e14ff..a419b65770d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1625,11 +1625,11 @@ struct task_struct { /* * numa_faults_locality tracks if faults recorded during the last - * scan window were remote/local. The task scan period is adapted - * based on the locality of the faults with different weights - * depending on whether they were shared or private faults + * scan window were remote/local or failed to migrate. The task scan + * period is adapted based on the locality of the faults with different + * weights depending on whether they were shared or private faults */ - unsigned long numa_faults_locality[2]; + unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ @@ -1719,6 +1719,7 @@ struct task_struct { #define TNF_NO_GROUP 0x02 #define TNF_SHARED 0x04 #define TNF_FAULT_LOCAL 0x08 +#define TNF_MIGRATE_FAIL 0x10 #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); -- cgit v1.2.3 From 495099962138732c28449d07f3b1988836659851 Mon Sep 17 00:00:00 2001 From: Arman Uguray Date: Wed, 25 Mar 2015 18:53:39 -0700 Subject: Bluetooth: Add macros for advertising instance flags This patch adds macro definitions for possible advertising instance flags that can be passed to the "Add Advertising" command. Signed-off-by: Arman Uguray Signed-off-by: Marcel Holtmann --- include/net/bluetooth/mgmt.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 68abd4b0c25d..b831242d48a4 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -554,6 +554,14 @@ struct mgmt_rp_add_advertising { __u8 instance; } __packed; +#define MGMT_ADV_FLAG_CONNECTABLE BIT(0) +#define MGMT_ADV_FLAG_DISCOV BIT(1) +#define MGMT_ADV_FLAG_LIMITED_DISCOV BIT(2) +#define MGMT_ADV_FLAG_MANAGED_FLAGS BIT(3) +#define MGMT_ADV_FLAG_TX_POWER BIT(4) +#define MGMT_ADV_FLAG_APPEARANCE BIT(5) +#define MGMT_ADV_FLAG_LOCAL_NAME BIT(6) + #define MGMT_OP_REMOVE_ADVERTISING 0x003F struct mgmt_cp_remove_advertising { __u8 instance; -- cgit v1.2.3 From 61edafbb47e9f46fb850035b1f8f062564445704 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 14:08:47 +0000 Subject: netfilter: nf_tables: consolide set element destruction With the conversion to set extensions, it is now possible to consolidate the different set element destruction functions. The set implementations' ->remove() functions are changed to only take the element out of their internal data structures. Elements will be freed in a batched fashion after the global transaction's completion RCU grace period. This reduces the amount of grace periods required for nft_hash from N to zero additional ones, additionally this guarantees that the set elements' extensions of all implementations can be used under RCU protection. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ef3457c1cb62..6ac63323afd2 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -423,6 +423,8 @@ static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, return elem + set->ops->elemsize; } +void nft_set_elem_destroy(const struct nft_set *set, void *elem); + /** * struct nft_expr_type - nf_tables expression type * -- cgit v1.2.3 From b2832dd6621bf73eb8ad38389a94bd83a5983886 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 14:08:48 +0000 Subject: netfilter: nf_tables: return set extensions from ->lookup() Return the extension area from the ->lookup() function to allow to consolidate common actions. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 6ac63323afd2..f190d26bda7d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -200,6 +200,8 @@ struct nft_set_estimate { enum nft_set_class class; }; +struct nft_set_ext; + /** * struct nft_set_ops - nf_tables set operations * @@ -218,7 +220,7 @@ struct nft_set_estimate { struct nft_set_ops { bool (*lookup)(const struct nft_set *set, const struct nft_data *key, - struct nft_data *data); + const struct nft_set_ext **ext); int (*get)(const struct nft_set *set, struct nft_set_elem *elem); int (*insert)(const struct nft_set *set, -- cgit v1.2.3 From ea4bd995b0f2fc5677ff8085e92a5d2544b9937c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 14:08:49 +0000 Subject: netfilter: nf_tables: add transaction helper functions Add some helper functions for building the genmask as preparation for set transactions. Also add a little documentation how this stuff actually works. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f190d26bda7d..4c46a325874e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -720,6 +720,34 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +/* + * The gencursor defines two generations, the currently active and the + * next one. Objects contain a bitmask of 2 bits specifying the generations + * they're active in. A set bit means they're inactive in the generation + * represented by that bit. + * + * New objects start out as inactive in the current and active in the + * next generation. When committing the ruleset the bitmask is cleared, + * meaning they're active in all generations. When removing an object, + * it is set inactive in the next generation. After committing the ruleset, + * the objects are removed. + */ +static inline unsigned int nft_gencursor_next(const struct net *net) +{ + return net->nft.gencursor + 1 == 1 ? 1 : 0; +} + +static inline u8 nft_genmask_next(const struct net *net) +{ + return 1 << nft_gencursor_next(net); +} + +static inline u8 nft_genmask_cur(const struct net *net) +{ + /* Use ACCESS_ONCE() to prevent refetching the value for atomicity */ + return 1 << ACCESS_ONCE(net->nft.gencursor); +} + /** * struct nft_trans - nf_tables object update in transaction * -- cgit v1.2.3 From cc02e457bb86f7b6ffee3651bab22d104b60effb Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2015 14:08:50 +0000 Subject: netfilter: nf_tables: implement set transaction support Set elements are the last object type not supporting transaction support. Implement similar to the existing rule transactions: The global transaction counter keeps track of two generations, current and next. Each element contains a bitmask specifying in which generations it is inactive. New elements start out as inactive in the current generation and active in the next. On commit, the previous next generation becomes the current generation and the element becomes active. The bitmask is then cleared to indicate that the element is active in all future generations. If the transaction is aborted, the element is removed from the set before it becomes active. When removing an element, it gets marked as inactive in the next generation. On commit the next generation becomes active and the therefor the element inactive. It is then taken out of then set and released. On abort, the element is marked as active for the next generation again. Lookups ignore elements not active in the current generation. The current set types (hash/rbtree) both use a field in the extension area to store the generation mask. This (currently) does not require any additional memory since we have some free space in there. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4c46a325874e..b8cd60dcb4e1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -138,15 +138,10 @@ struct nft_userdata { /** * struct nft_set_elem - generic representation of set elements * - * @cookie: implementation specific element cookie * @key: element key * @priv: element private data and extensions - * - * The cookie can be used to store a handle to the element for subsequent - * removal. */ struct nft_set_elem { - void *cookie; struct nft_data key; void *priv; }; @@ -207,6 +202,8 @@ struct nft_set_ext; * * @lookup: look up an element within the set * @insert: insert new element into set + * @activate: activate new element in the next generation + * @deactivate: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elemeennts * @privsize: function to return size of set private data @@ -221,10 +218,12 @@ struct nft_set_ops { bool (*lookup)(const struct nft_set *set, const struct nft_data *key, const struct nft_set_ext **ext); - int (*get)(const struct nft_set *set, - struct nft_set_elem *elem); int (*insert)(const struct nft_set *set, const struct nft_set_elem *elem); + void (*activate)(const struct nft_set *set, + const struct nft_set_elem *elem); + void * (*deactivate)(const struct nft_set *set, + const struct nft_set_elem *elem); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, @@ -261,6 +260,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @nelems: number of elements * @policy: set parameterization (see enum nft_set_policies) * @ops: set ops + * @pnet: network namespace * @flags: set flags * @klen: key length * @dlen: data length @@ -277,6 +277,7 @@ struct nft_set { u16 policy; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; + possible_net_t pnet; u16 flags; u8 klen; u8 dlen; @@ -355,10 +356,12 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * + * @genmask: generation mask * @offset: offsets of individual extension types * @data: beginning of extension data */ struct nft_set_ext { + u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[0]; }; @@ -748,6 +751,22 @@ static inline u8 nft_genmask_cur(const struct net *net) return 1 << ACCESS_ONCE(net->nft.gencursor); } +/* + * Set element transaction helpers + */ + +static inline bool nft_set_elem_active(const struct nft_set_ext *ext, + u8 genmask) +{ + return !(ext->genmask & genmask); +} + +static inline void nft_set_elem_change_active(const struct nft_set *set, + struct nft_set_ext *ext) +{ + ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet)); +} + /** * struct nft_trans - nf_tables object update in transaction * -- cgit v1.2.3 From 1e9e39f4a29857a396ac7b669d109f697f66695e Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 26 Feb 2015 19:34:37 +0000 Subject: usbnet: Fix tx_packets stat for FLAG_MULTI_FRAME drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the usbnet core does not update the tx_packets statistic for drivers with FLAG_MULTI_PACKET and there is no hook in the TX completion path where they could do this. cdc_ncm and dependent drivers are bumping tx_packets stat on the transmit path while asix and sr9800 aren't updating it at all. Add a packet count in struct skb_data so these drivers can fill it in, initialise it to 1 for other drivers, and add the packet count to the tx_packets statistic on completion. Signed-off-by: Ben Hutchings Tested-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index d9a4905e01d0..ff3fb2bd0e90 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -228,8 +228,20 @@ struct skb_data { /* skb->cb is one of these */ struct usbnet *dev; enum skb_state state; size_t length; + unsigned long packets; }; +/* Drivers that set FLAG_MULTI_PACKET must call this in their + * tx_fixup method before returning an skb. + */ +static inline void +usbnet_set_skb_tx_stats(struct sk_buff *skb, unsigned long packets) +{ + struct skb_data *entry = (struct skb_data *) skb->cb; + + entry->packets = packets; +} + extern int usbnet_open(struct net_device *net); extern int usbnet_stop(struct net_device *net); extern netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, -- cgit v1.2.3 From 7a1e890e2168e33fb62d84528e996b8b4b478fea Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 25 Mar 2015 21:41:33 +0100 Subject: usbnet: Fix tx_bytes statistic running backward in cdc_ncm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cdc_ncm disagrees with usbnet about how much framing overhead should be counted in the tx_bytes statistics, and tries 'fix' this by decrementing tx_bytes on the transmit path. But statistics must never be decremented except due to roll-over; this will thoroughly confuse user-space. Also, tx_bytes is only incremented by usbnet in the completion path. Fix this by requiring drivers that set FLAG_MULTI_FRAME to set a tx_bytes delta along with the tx_packets count. Fixes: beeecd42c3b4 ("net: cdc_ncm/cdc_mbim: adding NCM protocol statistics") Signed-off-by: Ben Hutchings Signed-off-by: Bjørn Mork --- include/linux/usb/usbnet.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index ff3fb2bd0e90..6e0ce8c7b8cb 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -227,7 +227,7 @@ struct skb_data { /* skb->cb is one of these */ struct urb *urb; struct usbnet *dev; enum skb_state state; - size_t length; + long length; unsigned long packets; }; @@ -235,11 +235,13 @@ struct skb_data { /* skb->cb is one of these */ * tx_fixup method before returning an skb. */ static inline void -usbnet_set_skb_tx_stats(struct sk_buff *skb, unsigned long packets) +usbnet_set_skb_tx_stats(struct sk_buff *skb, + unsigned long packets, long bytes_delta) { struct skb_data *entry = (struct skb_data *) skb->cb; entry->packets = packets; + entry->length = bytes_delta; } extern int usbnet_open(struct net_device *net); -- cgit v1.2.3 From 41d25fe0927aabb1d4b671871a99a55bcd203257 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Mar 2015 15:08:47 -0700 Subject: tcp: tcp_syn_flood_action() can be static After commit 1fb6f159fd21 ("tcp: add tcp_conn_request"), tcp_syn_flood_action() is no longer used from IPv6. We can make it static, by moving it above tcp_conn_request() Signed-off-by: Eric Dumazet Reviewed-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/tcp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 42690daa924e..963303fb96ae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -529,8 +529,6 @@ int tcp_write_wakeup(struct sock *); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); -bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, - const char *proto); void tcp_push_one(struct sock *, unsigned int mss_now); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); -- cgit v1.2.3 From 4ad3e3634a6cbe916722c7113c5b488d52c7a3dc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Mar 2015 14:15:04 +0000 Subject: irqchip: gicv3-its: Fix PROP/PEND and BASE/CBASE confusion The ITS driver sometime mixes up the use of GICR_PROPBASE bitfields for the GICR_PENDBASE register, and GITS_BASER for GICR_CBASE. This does not lead to any observable bug because similar bits are at the same location, but this just make the code even harder to understand... This patch provides the required #defines and fixes the mixup. Signed-off-by: Marc Zyngier Link: https://lkml.kernel.org/r/1427465705-17126-4-git-send-email-marc.zyngier@arm.com Signed-off-by: Jason Cooper --- include/linux/irqchip/arm-gic-v3.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 781974afff9f..826a4bd63d4a 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -128,6 +128,19 @@ #define GICR_PROPBASER_RaWaWb (7U << 7) #define GICR_PROPBASER_IDBITS_MASK (0x1f) +#define GICR_PENDBASER_NonShareable (0U << 10) +#define GICR_PENDBASER_InnerShareable (1U << 10) +#define GICR_PENDBASER_OuterShareable (2U << 10) +#define GICR_PENDBASER_SHAREABILITY_MASK (3UL << 10) +#define GICR_PENDBASER_nCnB (0U << 7) +#define GICR_PENDBASER_nC (1U << 7) +#define GICR_PENDBASER_RaWt (2U << 7) +#define GICR_PENDBASER_RaWb (3U << 7) +#define GICR_PENDBASER_WaWt (4U << 7) +#define GICR_PENDBASER_WaWb (5U << 7) +#define GICR_PENDBASER_RaWaWt (6U << 7) +#define GICR_PENDBASER_RaWaWb (7U << 7) + /* * Re-Distributor registers, offsets from SGI_base */ -- cgit v1.2.3 From 241a386c7dbb8b0db400a1f92f2ebe3b10eb661d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Mar 2015 14:15:05 +0000 Subject: irqchip: gicv3-its: Use non-cacheable accesses when no shareability If the ITS or the redistributors report their shareability as zero, then it is important to make sure they will no generate any cacheable traffic, as this is unlikely to produce the expected result. Signed-off-by: Marc Zyngier Link: https://lkml.kernel.org/r/1427465705-17126-5-git-send-email-marc.zyngier@arm.com Signed-off-by: Jason Cooper --- include/linux/irqchip/arm-gic-v3.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 826a4bd63d4a..ffbc034c8810 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -126,6 +126,7 @@ #define GICR_PROPBASER_WaWb (5U << 7) #define GICR_PROPBASER_RaWaWt (6U << 7) #define GICR_PROPBASER_RaWaWb (7U << 7) +#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7) #define GICR_PROPBASER_IDBITS_MASK (0x1f) #define GICR_PENDBASER_NonShareable (0U << 10) @@ -140,6 +141,7 @@ #define GICR_PENDBASER_WaWb (5U << 7) #define GICR_PENDBASER_RaWaWt (6U << 7) #define GICR_PENDBASER_RaWaWb (7U << 7) +#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7) /* * Re-Distributor registers, offsets from SGI_base @@ -195,6 +197,7 @@ #define GITS_CBASER_WaWb (5UL << 59) #define GITS_CBASER_RaWaWt (6UL << 59) #define GITS_CBASER_RaWaWb (7UL << 59) +#define GITS_CBASER_CACHEABILITY_MASK (7UL << 59) #define GITS_CBASER_NonShareable (0UL << 10) #define GITS_CBASER_InnerShareable (1UL << 10) #define GITS_CBASER_OuterShareable (2UL << 10) @@ -211,6 +214,7 @@ #define GITS_BASER_WaWb (5UL << 59) #define GITS_BASER_RaWaWt (6UL << 59) #define GITS_BASER_RaWaWb (7UL << 59) +#define GITS_BASER_CACHEABILITY_MASK (7UL << 59) #define GITS_BASER_TYPE_SHIFT (56) #define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7) #define GITS_BASER_ENTRY_SIZE_SHIFT (48) -- cgit v1.2.3 From 339d82626d225e9b876665e4e89b7eb123e96b3d Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 26 Mar 2015 18:36:37 -0700 Subject: net: dsa: Add basic framework to support ndo_fdb functions Provide callbacks for ndo_fdb_add, ndo_fdb_del, and ndo_fdb_dump. Reviewed-by: Andrew Lunn Tested-by: Andrew Lunn Signed-off-by: Guenter Roeck Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 47917e5e1e12..fbca63ba8f73 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -296,6 +296,12 @@ struct dsa_switch_driver { u32 br_port_mask); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); + int (*fdb_add)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_del)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_getnext)(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static); }; void register_switch_driver(struct dsa_switch_driver *type); -- cgit v1.2.3 From 608cd71a9c7c9db76e78a792c5a4101e12fea43f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 26 Mar 2015 19:53:57 -0700 Subject: tc: bpf: generalize pedit action existing TC action 'pedit' can munge any bits of the packet. Generalize it for use in bpf programs attached as cls_bpf and act_bpf via bpf_skb_store_bytes() helper function. Signed-off-by: Alexei Starovoitov Reviewed-by: Jiri Pirko Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 280a315de8d6..d5cda067115a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -59,6 +59,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 27dc4ec58840..74aab6e0d964 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -168,6 +168,7 @@ enum bpf_func_id { BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ + BPF_FUNC_skb_store_bytes, /* int skb_store_bytes(skb, offset, from, len) */ __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From f5a7fb88e1f82542ca14ba93a1d4fa35471c60ca Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 27 Mar 2015 14:31:11 +0900 Subject: vlan: Introduce helper functions to check if skb is tagged Separate the two checks for single vlan and multiple vlans in netif_skb_features(). This allows us to move the check for multiple vlans to another function later. Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b11b28a30b9e..4265d440ec4d 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -561,4 +561,49 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, skb->protocol = htons(ETH_P_802_2); } +/** + * skb_vlan_tagged - check if skb is vlan tagged. + * @skb: skbuff to query + * + * Returns true if the skb is tagged, regardless of whether it is hardware + * accelerated or not. + */ +static inline bool skb_vlan_tagged(const struct sk_buff *skb) +{ + if (!skb_vlan_tag_present(skb) && + likely(skb->protocol != htons(ETH_P_8021Q) && + skb->protocol != htons(ETH_P_8021AD))) + return false; + + return true; +} + +/** + * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. + * @skb: skbuff to query + * + * Returns true if the skb is tagged with multiple vlan headers, regardless + * of whether it is hardware accelerated or not. + */ +static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + + if (!skb_vlan_tag_present(skb)) { + struct vlan_ethhdr *veh; + + if (likely(protocol != htons(ETH_P_8021Q) && + protocol != htons(ETH_P_8021AD))) + return false; + + veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } + + if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) + return false; + + return true; +} + #endif /* !(_LINUX_IF_VLAN_H_) */ -- cgit v1.2.3 From 8cb65d00086bfba22bac87ff18b751432fc74003 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 27 Mar 2015 14:31:12 +0900 Subject: net: Move check for multiple vlans to drivers To allow drivers to handle the features check for multiple tags, move the check to ndo_features_check(). As no drivers currently handle multiple tagged TSO, introduce dflt_features_check() and call it if the driver does not have ndo_features_check(). Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 4265d440ec4d..920e4457ce6e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -606,4 +606,26 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) return true; } +/** + * vlan_features_check - drop unsafe features for skb with multiple tags. + * @skb: skbuff to query + * @features: features to be checked + * + * Returns features without unsafe ones if the skb has multiple tags. + */ +static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, + netdev_features_t features) +{ + if (skb_vlan_tagged_multi(skb)) + features = netdev_intersect_features(features, + NETIF_F_SG | + NETIF_F_HIGHDMA | + NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + return features; +} + #endif /* !(_LINUX_IF_VLAN_H_) */ -- cgit v1.2.3 From e38f30256b36700aa63aa709dc091bf6eb69c257 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 27 Mar 2015 14:31:13 +0900 Subject: net: Introduce passthru_features_check As there are a number of (especially virtual) devices that don't need the multiple vlan check, introduce passthru_features_check() for convenience. Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08c4ab37189f..967bb4c8caf1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3657,6 +3657,9 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); +netdev_features_t passthru_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) -- cgit v1.2.3 From a818292952bbfad12ec5a32ab01330cb1ceed013 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 16 Mar 2015 23:23:34 +0200 Subject: mac80211: convert rssi_callback() to event_callback() We will be able to add more events, such as MLME events and others. The low level driver may be interested in knowing about these events to dump firmware data upon failures, or to change parameters in case connection attempts fail etc... Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 48 ++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 38 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 157c0f151766..7a966f3ed67a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -301,16 +301,43 @@ enum ieee80211_bss_change { #define IEEE80211_BSS_ARP_ADDR_LIST_LEN 4 /** - * enum ieee80211_rssi_event - RSSI threshold event - * An indicator for when RSSI goes below/above a certain threshold. - * @RSSI_EVENT_HIGH: AP's rssi crossed the high threshold set by the driver. - * @RSSI_EVENT_LOW: AP's rssi crossed the low threshold set by the driver. + * enum ieee80211_event_type - event to be notified to the low level driver + * @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver. */ -enum ieee80211_rssi_event { +enum ieee80211_event_type { + RSSI_EVENT, +}; + +/** + * enum ieee80211_rssi_event_data - relevant when event type is %RSSI_EVENT + * @RSSI_EVENT_HIGH: AP's rssi went below the threshold set by the driver. + * @RSSI_EVENT_LOW: AP's rssi went above the threshold set by the driver. + */ +enum ieee80211_rssi_event_data { RSSI_EVENT_HIGH, RSSI_EVENT_LOW, }; +/** + * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT + * @data: See &enum ieee80211_rssi_event_data + */ +struct ieee80211_rssi_event { + enum ieee80211_rssi_event_data data; +}; + +/** + * struct ieee80211_event - event to be sent to the driver + * @type The event itself. See &enum ieee80211_event_type. + * @rssi: relevant if &type is %RSSI_EVENT + */ +struct ieee80211_event { + enum ieee80211_event_type type; + union { + struct ieee80211_rssi_event rssi; + } u; +}; + /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * @@ -2862,8 +2889,9 @@ enum ieee80211_reconfig_type { * @set_bitrate_mask: Set a mask of rates to be used for rate control selection * when transmitting a frame. Currently only legacy rates are handled. * The callback can sleep. - * @rssi_callback: Notify driver when the average RSSI goes above/below - * thresholds that were registered previously. The callback can sleep. + * @event_callback: Notify driver about any event in mac80211. See + * &enum ieee80211_event_type for the different types. + * The callback can sleep. * * @release_buffered_frames: Release buffered frames according to the given * parameters. In the case where the driver buffers some frames for @@ -3159,9 +3187,9 @@ struct ieee80211_ops { bool (*tx_frames_pending)(struct ieee80211_hw *hw); int (*set_bitrate_mask)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask); - void (*rssi_callback)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - enum ieee80211_rssi_event rssi_event); + void (*event_callback)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + const struct ieee80211_event *event); void (*allow_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, -- cgit v1.2.3 From a9409093d23c822d13a73f8d2df7e6fa987ae485 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 16 Mar 2015 23:23:35 +0200 Subject: mac80211: notify the driver about authentication status This can allow the driver to take action based on the success / failure of the authentication. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7a966f3ed67a..6cddf7725bf2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -303,9 +303,11 @@ enum ieee80211_bss_change { /** * enum ieee80211_event_type - event to be notified to the low level driver * @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver. + * @MLME_EVENT: event related to MLME */ enum ieee80211_event_type { RSSI_EVENT, + MLME_EVENT, }; /** @@ -326,15 +328,49 @@ struct ieee80211_rssi_event { enum ieee80211_rssi_event_data data; }; +/** + * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT + * @AUTH_EVENT: the MLME operation is authentication + */ +enum ieee80211_mlme_event_data { + AUTH_EVENT, +}; + +/** + * enum ieee80211_mlme_event_status - relevant when event type is %MLME_EVENT + * @MLME_SUCCESS: the MLME operation completed successfully. + * @MLME_DENIED: the MLME operation was denied by the peer. + * @MLME_TIMEOUT: the MLME operation timed out. + */ +enum ieee80211_mlme_event_status { + MLME_SUCCESS, + MLME_DENIED, + MLME_TIMEOUT, +}; + +/** + * enum ieee80211_mlme_event - data attached to an %MLME_EVENT + * @data: See &enum ieee80211_mlme_event_data + * @status: See &enum ieee80211_mlme_event_status + * @reason: the reason code if applicable + */ +struct ieee80211_mlme_event { + enum ieee80211_mlme_event_data data; + enum ieee80211_mlme_event_status status; + u16 reason; +}; + /** * struct ieee80211_event - event to be sent to the driver * @type The event itself. See &enum ieee80211_event_type. * @rssi: relevant if &type is %RSSI_EVENT + * @mlme: relevant if &type is %AUTH_EVENT */ struct ieee80211_event { enum ieee80211_event_type type; union { struct ieee80211_rssi_event rssi; + struct ieee80211_mlme_event mlme; } u; }; -- cgit v1.2.3 From d0d1a12f9cc665f3fcac5288ab84429a91abd4e9 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 16 Mar 2015 23:23:36 +0200 Subject: mac80211: notify the driver about association status This can allow the driver to take action based on the success / failure of the association. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 6cddf7725bf2..dcddc4ac4184 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -331,9 +331,11 @@ struct ieee80211_rssi_event { /** * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT * @AUTH_EVENT: the MLME operation is authentication + * @ASSOC_EVENT: the MLME operation is association */ enum ieee80211_mlme_event_data { AUTH_EVENT, + ASSOC_EVENT, }; /** -- cgit v1.2.3 From a90faa9d6449f3861428bafeaf4d1fcf2be4ba7f Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 16 Mar 2015 23:23:37 +0200 Subject: mac80211: notify the driver about deauth This can allow the driver to take action based on the reason of the deauth. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dcddc4ac4184..94c8c62800c3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -332,10 +332,14 @@ struct ieee80211_rssi_event { * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT * @AUTH_EVENT: the MLME operation is authentication * @ASSOC_EVENT: the MLME operation is association + * @DEAUTH_RX_EVENT: deauth received.. + * @DEAUTH_TX_EVENT: deauth sent. */ enum ieee80211_mlme_event_data { AUTH_EVENT, ASSOC_EVENT, + DEAUTH_RX_EVENT, + DEAUTH_TX_EVENT, }; /** -- cgit v1.2.3 From 3a323d4e17dd5a84f6ad036e6f985d263ca973ed Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Wed, 18 Mar 2015 10:47:02 +0200 Subject: nl80211: small clarification of the sched_scan delay attribute Just clarify that the delay is only before the first cycle. Signed-off-by: Luciano Coelho Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index ae16ba9cb1e3..241220c43e86 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1754,8 +1754,9 @@ enum nl80211_commands { * should be contained in the result as the sum of the respective counters * over all channels. * - * @NL80211_ATTR_SCHED_SCAN_DELAY: delay before a scheduled scan (or a - * WoWLAN net-detect scan) is started, u32 in seconds. + * @NL80211_ATTR_SCHED_SCAN_DELAY: delay before the first cycle of a + * scheduled scan (or a WoWLAN net-detect scan) is started, u32 + * in seconds. * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. -- cgit v1.2.3 From a38700dd486f3def34cef47d00e2d360a04a7bc8 Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Wed, 18 Mar 2015 08:46:08 +0200 Subject: cfg/mac80211: add regulatory classes IE during TDLS setup Seems Broadcom TDLS peers (Nexus 5, Xperia Z3) refuse to allow TDLS connection when channel-switching is supported but the regulatory classes IE is missing from the setup request. Add a chandef to reg-class translation function to cfg80211 and use it to add the required IE during setup. For now add only the current regulatory class as supported - it is enough to resolve the compatibility issue. Signed-off-by: Arik Nemtsov Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 12a6121ea76e..c4d873b8f32d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4903,6 +4903,17 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, bool ieee80211_operating_class_to_band(u8 operating_class, enum ieee80211_band *band); +/** + * ieee80211_chandef_to_operating_class - convert chandef to operation class + * + * @chandef: the chandef to convert + * @op_class: a pointer to the resulting operating class + * + * Returns %true if the conversion was successful, %false otherwise. + */ +bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, + u8 *op_class); + /* * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested -- cgit v1.2.3 From 6bab2e19c5ffd1f21b28c2cabb3801a37b77ae69 Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Wed, 18 Mar 2015 11:13:39 +0100 Subject: cfg80211: pass name_assign_type to rdev_add_virtual_intf() This will expose in /sys whether the ifname of a device is set by userspace or generated by the kernel. The latter kind (wlanX, etc) is not deterministic, so userspace needs to rename these devices to names that are guaranteed to stay the same between reboots. The former, however should never be renamed, so userspace needs to be able to reliably tell the difference. Similar functionality was introduced for the rtnetlink core in commit 5517750f058e ("net: rtnetlink - make create_link take name_assign_type") Signed-off-by: Tom Gundersen Cc: Kalle Valo Cc: Brett Rudley Cc: Arend van Spriel Cc: Franky (Zhenhui) Lin Cc: Hante Meuleman Cc: Johannes Berg [reformat changelog to fit 72 cols] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c4d873b8f32d..ab667fbc743d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2456,6 +2456,7 @@ struct cfg80211_ops { struct wireless_dev * (*add_virtual_intf)(struct wiphy *wiphy, const char *name, + unsigned char name_assign_type, enum nl80211_iftype type, u32 *flags, struct vif_params *params); -- cgit v1.2.3 From 527871d7206dac2733d0bae52f5a328811d299ee Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 21 Mar 2015 08:09:55 +0100 Subject: mac80211: make sta.wme indicate whether QoS is used Indicating just the peer's capability is fairly pointless if the local device doesn't support it. Make the variable track both combined, and remove the 'local support' check in the TX path. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 94c8c62800c3..201bc68e0cff 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1557,7 +1557,8 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @wme: indicates whether the STA supports QoS/WME. + * @wme: indicates whether the STA supports QoS/WME (if local devices does, + * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid -- cgit v1.2.3 From f3f03330dee0526d82f2a0fd1a79d207ed1ac439 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 30 Mar 2015 18:46:29 +0200 Subject: nfsd: require an explicit option to enable pNFS Turns out sending out layouts to any client is a bad idea if they can't get at the storage device, so require explicit admin action to enable pNFS. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/uapi/linux/nfsd/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index 4742f2cb42f2..d3bd6ffec041 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -47,7 +47,7 @@ * exported filesystem. */ #define NFSEXP_V4ROOT 0x10000 -#define NFSEXP_NOPNFS 0x20000 +#define NFSEXP_PNFS 0x20000 /* All flags that we claim to support. (Note we don't support NOACL.) */ #define NFSEXP_ALLFLAGS 0x3FE7F -- cgit v1.2.3 From a4368ff3ed3b57e4b5e36d83b75604f68bbcdaad Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 30 Mar 2015 23:21:01 +0300 Subject: Bluetooth: Refactor L2CAP variables into l2cap_ctrl We're getting very close to the maximum possible size of bt_skb_cb. To prepare to shrink the struct with the help of a union this patch moves all L2CAP related variables into the l2cap_ctrl struct. To later add other 'ctrl' structs the L2CAP one is renamed simple 'l2cap' instead of 'control'. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 33a5e00025aa..d8367cc7c76e 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -269,6 +269,9 @@ struct l2cap_ctrl { __u16 reqseq; __u16 txseq; __u8 retries; + __le16 psm; + bdaddr_t bdaddr; + struct l2cap_chan *chan; }; struct hci_dev; @@ -284,10 +287,7 @@ struct bt_skb_cb { __u8 req_start:1; u8 req_event; hci_req_complete_t req_complete; - struct l2cap_chan *chan; - struct l2cap_ctrl control; - bdaddr_t bdaddr; - __le16 psm; + struct l2cap_ctrl l2cap; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) -- cgit v1.2.3 From db6e3e8d016823c6b0f773c70a69ce65807d8a44 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 30 Mar 2015 23:21:02 +0300 Subject: Bluetooth: Refactor HCI request variables into own struct In order to shrink the size of bt_skb_cb, this patch moves the HCI request related variables into their own req_ctrl struct. Additionall the L2CAP and HCI request structs are placed inside the same union since they will never be used at the same time for the same skb. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index d8367cc7c76e..eeaff4b5cb62 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -278,16 +278,22 @@ struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); +struct req_ctrl { + bool start; + u8 event; + hci_req_complete_t complete; +}; + struct bt_skb_cb { __u8 pkt_type; __u8 force_active; __u16 opcode; __u16 expect; __u8 incoming:1; - __u8 req_start:1; - u8 req_event; - hci_req_complete_t req_complete; - struct l2cap_ctrl l2cap; + union { + struct l2cap_ctrl l2cap; + struct req_ctrl req; + }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) -- cgit v1.2.3 From e9637415a92cf25ad800b7fdeddcd30cce7b44ab Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 30 Mar 2015 13:39:09 -0400 Subject: block: fix blk_stack_limits() regression due to lcm() change Linux 3.19 commit 69c953c ("lib/lcm.c: lcm(n,0)=lcm(0,n) is 0, not n") caused blk_stack_limits() to not properly stack queue_limits for stacked devices (e.g. DM). Fix this regression by establishing lcm_not_zero() and switching blk_stack_limits() over to using it. DM uses blk_set_stacking_limits() to establish the initial top-level queue_limits that are then built up based on underlying devices' limits using blk_stack_limits(). In the case of optimal_io_size (io_opt) blk_set_stacking_limits() establishes a default value of 0. With commit 69c953c, lcm(0, n) is no longer n, which compromises proper stacking of the underlying devices' io_opt. Test: $ modprobe scsi_debug dev_size_mb=10 num_tgts=1 opt_blks=1536 $ cat /sys/block/sde/queue/optimal_io_size 786432 $ dmsetup create node --table "0 100 linear /dev/sde 0" Before this fix: $ cat /sys/block/dm-5/queue/optimal_io_size 0 After this fix: $ cat /sys/block/dm-5/queue/optimal_io_size 786432 Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org # 3.19+ Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/lcm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/lcm.h b/include/linux/lcm.h index 7bf01d779b45..1ce79a7f1daa 100644 --- a/include/linux/lcm.h +++ b/include/linux/lcm.h @@ -4,5 +4,6 @@ #include unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__; +unsigned long lcm_not_zero(unsigned long a, unsigned long b) __attribute_const__; #endif /* _LCM_H */ -- cgit v1.2.3 From 92f1719407b90475b3be0b7b9c983dec2ff8351e Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 29 Mar 2015 23:11:51 +0200 Subject: ptp: introduce get/set time methods with explicit 64 bit seconds. Converting the PHC drivers over to the new methods is one step along the way to making them ready for 2038. Once all the drivers are up to date, then the old methods will be removed. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d8ff3fb84ba..7d6f8e66396f 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -64,12 +64,18 @@ struct ptp_clock_request { * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * - * @gettime: Reads the current time from the hardware clock. + * @gettime: Reads the current time from the hardware clock. (deprecated) * parameter ts: Holds the result. * - * @settime: Set the current time on the hardware clock. + * @settime: Set the current time on the hardware clock. (deprecated) * parameter ts: Time value to set. * + * @gettime64: Reads the current time from the hardware clock. + * parameter ts: Holds the result. + * + * @settime64: Set the current time on the hardware clock. + * parameter ts: Time value to set. + * * @enable: Request driver to enable or disable an ancillary feature. * parameter request: Desired resource to enable or disable. * parameter on: Caller passes one to enable or zero to disable. @@ -106,6 +112,8 @@ struct ptp_clock_info { 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 (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *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, -- cgit v1.2.3 From ed7c6317bc599502e1fdc7f5f95cb9a5550360a4 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 29 Mar 2015 23:12:13 +0200 Subject: ptp: remove 32 bit get/set methods. All of the PHC drivers have been converted to the new methods. This patch converts the three remaining callers within the core code and removes the older methods for good. As a result, the core PHC code is ready for the year 2038. However, some of the PHC drivers are not quite ready yet. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 7d6f8e66396f..b8b73066d137 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -64,12 +64,6 @@ struct ptp_clock_request { * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * - * @gettime: Reads the current time from the hardware clock. (deprecated) - * parameter ts: Holds the result. - * - * @settime: Set the current time on the hardware clock. (deprecated) - * parameter ts: Time value to set. - * * @gettime64: Reads the current time from the hardware clock. * parameter ts: Holds the result. * @@ -110,8 +104,6 @@ struct ptp_clock_info { 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 (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); int (*enable)(struct ptp_clock_info *ptp, -- cgit v1.2.3 From 8f55db48608b109ad8c7ff4b946ad39b3189a540 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 29 Mar 2015 16:59:23 +0200 Subject: tcp: simplify inetpeer_addr_base use In many places, the a6 field is typecasted to struct in6_addr. As the fields are in union anyway, just add in6_addr type to the union and get rid of the typecasting. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/inetpeer.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 80479abddf73..d5332ddcea3f 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -19,6 +19,7 @@ struct inetpeer_addr_base { union { __be32 a4; __be32 a6[4]; + struct in6_addr in6; }; }; @@ -151,7 +152,7 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, { struct inetpeer_addr daddr; - *(struct in6_addr *)daddr.addr.a6 = *v6daddr; + daddr.addr.in6 = *v6daddr; daddr.family = AF_INET6; return inet_getpeer(base, &daddr, create); } -- cgit v1.2.3 From 15e318bdc6dfb82914c82fb7ad00badaa8387d8e Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 29 Mar 2015 16:59:24 +0200 Subject: xfrm: simplify xfrm_address_t use In many places, the a6 field is typecasted to struct in6_addr. As the fields are in union anyway, just add in6_addr type to the union and get rid of the typecasting. Modifying the uapi header is okay, the union has still the same size. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/xfrm.h | 6 +++--- include/uapi/linux/xfrm.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d0ac7d7be8a7..461f83539493 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1025,7 +1025,7 @@ xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) case AF_INET: return addr->a4 == 0; case AF_INET6: - return ipv6_addr_any((struct in6_addr *)&addr->a6); + return ipv6_addr_any(&addr->in6); } return 0; } @@ -1238,8 +1238,8 @@ void xfrm_flowi_addr_get(const struct flowi *fl, memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: - *(struct in6_addr *)saddr->a6 = fl->u.ip6.saddr; - *(struct in6_addr *)daddr->a6 = fl->u.ip6.daddr; + saddr->in6 = fl->u.ip6.saddr; + daddr->in6 = fl->u.ip6.daddr; break; } } diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 02d5125a5ee8..2cd9e608d0d1 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -1,6 +1,7 @@ #ifndef _LINUX_XFRM_H #define _LINUX_XFRM_H +#include #include /* All of the structures in this file may not change size as they are @@ -13,6 +14,7 @@ typedef union { __be32 a4; __be32 a6[4]; + struct in6_addr in6; } xfrm_address_t; /* Ident of a specific xfrm_state. It is used on input to lookup -- cgit v1.2.3 From 930345ea630405aa6e6f42efcb149c3f360a6b67 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 29 Mar 2015 16:59:25 +0200 Subject: netlink: implement nla_put_in_addr and nla_put_in6_addr IP addresses are often stored in netlink attributes. Add generic functions to do that. For nla_put_in_addr, it would be nicer to pass struct in_addr but this is not used universally throughout the kernel, in way too many places __be32 is used to store IPv4 address. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/linux/netfilter/ipset/ip_set.h | 5 ++--- include/net/netlink.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index f1606fa6132d..34b172301558 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -483,7 +483,7 @@ static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr) if (!__nested) return -EMSGSIZE; - ret = nla_put_net32(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); + ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr); if (!ret) ipset_nest_end(skb, __nested); return ret; @@ -497,8 +497,7 @@ static inline int nla_put_ipaddr6(struct sk_buff *skb, int type, if (!__nested) return -EMSGSIZE; - ret = nla_put(skb, IPSET_ATTR_IPADDR_IPV6, - sizeof(struct in6_addr), ipaddrptr); + ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr); if (!ret) ipset_nest_end(skb, __nested); return ret; diff --git a/include/net/netlink.h b/include/net/netlink.h index e010ee8da41d..17fc76e5b05e 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -4,6 +4,7 @@ #include #include #include +#include /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) @@ -105,6 +106,8 @@ * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies) add msecs attribute to skb + * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb + * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute @@ -956,6 +959,32 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, return nla_put(skb, attrtype, sizeof(u64), &tmp); } +/** + * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket + * buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @addr: IPv4 address + */ +static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, + __be32 addr) +{ + return nla_put_be32(skb, attrtype, addr); +} + +/** + * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket + * buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @addr: IPv6 address + */ +static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, + const struct in6_addr *addr) +{ + return nla_put(skb, attrtype, sizeof(*addr), addr); +} + /** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute -- cgit v1.2.3 From 67b61f6c130a05b2cd4c3dfded49a751ff42c534 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 29 Mar 2015 16:59:26 +0200 Subject: netlink: implement nla_get_in_addr and nla_get_in6_addr Those are counterparts to nla_put_in_addr and nla_put_in6_addr. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/netlink.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 17fc76e5b05e..2a5dbcc90d1c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1127,6 +1127,27 @@ static inline unsigned long nla_get_msecs(const struct nlattr *nla) return msecs_to_jiffies((unsigned long) msecs); } +/** + * nla_get_in_addr - return payload of IPv4 address attribute + * @nla: IPv4 address netlink attribute + */ +static inline __be32 nla_get_in_addr(const struct nlattr *nla) +{ + return *(__be32 *) nla_data(nla); +} + +/** + * nla_get_in6_addr - return payload of IPv6 address attribute + * @nla: IPv6 address netlink attribute + */ +static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) +{ + struct in6_addr tmp; + + nla_memcpy(&tmp, nla, sizeof(tmp)); + return tmp; +} + /** * nla_nest_start - Start a new level of nested attributes * @skb: socket buffer to add attributes to -- cgit v1.2.3 From f9c72d10d6fbf949558cd088389a42213ed7b12d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 31 Mar 2015 12:03:28 -0400 Subject: sunrpc: make debugfs file creation failure non-fatal We currently have a problem that SELinux policy is being enforced when creating debugfs files. If a debugfs file is created as a side effect of doing some syscall, then that creation can fail if the SELinux policy for that process prevents it. This seems wrong. We don't do that for files under /proc, for instance, so Bruce has proposed a patch to fix that. While discussing that patch however, Greg K.H. stated: "No kernel code should care / fail if a debugfs function fails, so please fix up the sunrpc code first." This patch converts all of the sunrpc debugfs setup code to be void return functins, and the callers to not look for errors from those functions. This should allow rpc_clnt and rpc_xprt creation to work, even if the kernel fails to create debugfs files for some reason. Symptoms were failing krb5 mounts on systems using gss-proxy and selinux. Fixes: 388f0c776781 "sunrpc: add a debugfs rpc_xprt directory..." Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton Acked-by: Greg Kroah-Hartman Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/debug.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index c57d8ea0716c..59a7889e15db 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -60,17 +60,17 @@ struct rpc_xprt; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) void rpc_register_sysctl(void); void rpc_unregister_sysctl(void); -int sunrpc_debugfs_init(void); +void sunrpc_debugfs_init(void); void sunrpc_debugfs_exit(void); -int rpc_clnt_debugfs_register(struct rpc_clnt *); +void rpc_clnt_debugfs_register(struct rpc_clnt *); void rpc_clnt_debugfs_unregister(struct rpc_clnt *); -int rpc_xprt_debugfs_register(struct rpc_xprt *); +void rpc_xprt_debugfs_register(struct rpc_xprt *); void rpc_xprt_debugfs_unregister(struct rpc_xprt *); #else -static inline int +static inline void sunrpc_debugfs_init(void) { - return 0; + return; } static inline void @@ -79,10 +79,10 @@ sunrpc_debugfs_exit(void) return; } -static inline int +static inline void rpc_clnt_debugfs_register(struct rpc_clnt *clnt) { - return 0; + return; } static inline void @@ -91,10 +91,10 @@ rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt) return; } -static inline int +static inline void rpc_xprt_debugfs_register(struct rpc_xprt *xprt) { - return 0; + return; } static inline void -- cgit v1.2.3 From ffa88f37ffeaac398be68f9678b0e6046a5ba7f6 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 30 Mar 2015 17:45:22 +0300 Subject: net/mlx4_en: Move statistics bitmap setting to the Ethernet driver The statistics bitmap belongs to the Ethernet driver, move it there. Signed-off-by: Eran Ben Elisha Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 4550c67b92e4..49abbe28e230 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1300,7 +1300,6 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac); void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac); int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port); int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac); -void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap); int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, -- cgit v1.2.3 From 0b131561a7d639abb0a194d2d8fae839ce3b99e9 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 30 Mar 2015 17:45:25 +0300 Subject: net/mlx4_en: Add Flow control statistics display via ethtool Flow control per priority and Global pause counters are now visible via ethtool. The counters shows statistics regarding pauses in the device. Signed-off-by: Matan Barak Signed-off-by: Shani Michaeli Signed-off-by: Eran Ben Elisha Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 49abbe28e230..ab7ebec943b8 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -205,7 +205,8 @@ enum { MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21, MLX4_DEV_CAP_FLAG2_QCN = 1LL << 22, - MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23 + MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23, + MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN = 1LL << 24 }; enum { -- cgit v1.2.3 From a5581ef4c2eac6449188862e903eb46c7233582a Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 1 Apr 2015 07:50:29 +0200 Subject: can: introduce new raw socket option to join the given CAN filters The CAN_RAW socket can set multiple CAN identifier specific filters that lead to multiple filters in the af_can.c filter processing. These filters are indenpendent from each other which leads to logical OR'ed filters when applied. This socket option joines the given CAN filters in the way that only CAN frames are passed to user space that matched *all* given CAN filters. The semantic for the applied filters is therefore changed to a logical AND. This is useful especially when the filterset is a combination of filters where the CAN_INV_FILTER flag is set in order to notch single CAN IDs or CAN ID ranges from the incoming traffic. As the raw_rcv() function is executed from NET_RX softirq the introduced variables are implemented as per-CPU variables to avoid extensive locking at CAN frame reception time. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/raw.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index 78ec76fd89a6..8735f1080385 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -57,6 +57,7 @@ enum { CAN_RAW_LOOPBACK, /* local loopback (default:on) */ CAN_RAW_RECV_OWN_MSGS, /* receive my own msgs (default:off) */ CAN_RAW_FD_FRAMES, /* allow CAN FD frames (default:off) */ + CAN_RAW_JOIN_FILTERS, /* all filters must match to trigger */ }; #endif /* !_UAPI_CAN_RAW_H */ -- cgit v1.2.3 From 44ba06987c0b10faa998b9324850e8a6564c714d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Apr 2015 16:31:26 +0100 Subject: RxRPC: Handle VERSION Rx protocol packets Handle VERSION Rx protocol packets. We should respond to a VERSION packet with a string indicating the Rx version. This is a maximum of 64 characters and is padded out to 65 chars with NUL bytes. Note that other AFS clients use the version request as a NAT keepalive so we need to handle it rather than returning an abort. The standard formulation seems to be: built --
for example: " OpenAFS 1.6.2 built 2013-05-07 " (note the three extra spaces) as obtained with: rxdebug grand.mit.edu -version from the openafs package. Signed-off-by: David Howells --- include/rxrpc/packet.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h index f2902ef7ab75..4dce116bfd80 100644 --- a/include/rxrpc/packet.h +++ b/include/rxrpc/packet.h @@ -47,7 +47,8 @@ struct rxrpc_header { #define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */ #define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */ #define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */ -#define RXRPC_N_PACKET_TYPES 9 /* number of packet types (incl type 0) */ +#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ +#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ uint8_t flags; /* packet flags */ #define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ -- cgit v1.2.3 From e6214487492566b15ff24e97c6747bb2e5d9e040 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 2 Apr 2015 13:41:08 +0300 Subject: Bluetooth: Add second hci_request callback option for full skb This patch adds a second possible callback for HCI requests where the callback will receive the full skb of the last successfully completed HCI command. This API is useful for cases where we want to use a request to read some data and the existing hci_event.c handlers do not store it e.g. in the hci_dev struct. The reason the patch is a bit bigger than just adding the new API is because the hci_req_cmd_complete() functions required some refactoring to enable it: now hci_req_cmd_complete() is simply used to request the callback pointers if any, and the actual calling of them happens from a single place at the end of hci_event_packet(). The reason for this is that we need to pass the original skb (without any skb_pull, etc modifications done to it) and it's simplest to keep track of it within the hci_event_packet() function. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index eeaff4b5cb62..7dba80546f16 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -277,11 +277,14 @@ struct l2cap_ctrl { struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); +typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb); struct req_ctrl { bool start; u8 event; hci_req_complete_t complete; + hci_req_complete_skb_t complete_skb; }; struct bt_skb_cb { -- cgit v1.2.3 From f60cb30579d3401cab1ed36b42df5c0568ae0ba7 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 2 Apr 2015 13:41:09 +0300 Subject: Bluetooth: Convert hci_req_sync family of function to new request API Now that there's an API in place that allows passing the resulting skb to the request callback we can conveniently convert the hci_req_sync and related functions to use it. Since we still need to get the skb from the async callback into the sleeping _sync() function the patch adds another req_skb variable to hci_dev where the sync request state is tracked. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 540c07feece7..257ac04c00e1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -334,6 +334,7 @@ struct hci_dev { wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; + struct sk_buff *req_skb; void *smp_data; void *smp_bredr_data; -- cgit v1.2.3 From f7d9e97592aeb7742084814c5f37e25571b2d51d Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 2 Apr 2015 13:41:10 +0300 Subject: Bluetooth: Remove unneeded recv_event variable Now that the synchronous HCI requests use the new API and a new private variable the recv_evt member of hci_dev is no-longer needed. This patch removes it. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 257ac04c00e1..4cefee0b6330 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -326,7 +326,6 @@ struct hci_dev { struct sk_buff_head raw_q; struct sk_buff_head cmd_q; - struct sk_buff *recv_evt; struct sk_buff *sent_cmd; struct sk_buff *reassembly[NUM_REASSEMBLY]; -- cgit v1.2.3 From abe66a4d036933c7376b40b0d7bb5de0458331aa Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 2 Apr 2015 13:41:11 +0300 Subject: Bluetooth: Remove unused hci_req_pending() function The hci_req_pending() function has no users anymore, so simply remove it. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4cefee0b6330..12686e8e9343 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1284,8 +1284,6 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); -bool hci_req_pending(struct hci_dev *hdev); - struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u32 timeout); struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, -- cgit v1.2.3 From 1b9441f8ec426223f6f54f2af10ee01c8b743e5b Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Thu, 2 Apr 2015 13:41:13 +0300 Subject: Bluetooth: Convert local OOB data reading to use HCI request Now that there's a HCI request API available where the callback receives the resulting skb, we can convert the local OOB data reading to use this new API. This patch does the necessary update in mgmt.c (which also requires moving the callback higher up since it's now a static function) and removes the custom calls from hci_event.c that are no-longer necessary. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 12686e8e9343..93fd3e756b8a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1391,9 +1391,6 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); -void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, - u8 *rand192, u8 *hash256, u8 *rand256, - u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len); -- cgit v1.2.3 From a54acb3a6f853e8394c4cb7b6a4d93c88f13eefd Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:00 +0200 Subject: dev: introduce dev_get_iflink() The goal of this patch is to prepare the removal of the iflink field. It introduces a new ndo function, which will be implemented by virtual interfaces. There is no functional change into this patch. All readers of iflink field now call dev_get_iflink(). Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 967bb4c8caf1..788eb7a622ad 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1030,6 +1030,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific * TX queue. + * int (*ndo_get_iflink)(const struct net_device *dev); + * Called to get the iflink value of this device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1191,6 +1193,7 @@ struct net_device_ops { int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); + int (*ndo_get_iflink)(const struct net_device *dev); }; /** @@ -2149,6 +2152,7 @@ void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); +int dev_get_iflink(const struct net_device *dev); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); -- cgit v1.2.3 From ecf2c06a88d2ed534a87b84b8c1a467ab23352dd Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:01 +0200 Subject: ip6tnl,gre6,vti6: implement ndo_get_iflink Don't use dev->iflink anymore. CC: Steffen Klassert Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 76c091b53dae..1668be5937e6 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -71,6 +71,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw); __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); struct net *ip6_tnl_get_link_net(const struct net_device *dev); +int ip6_tnl_get_iflink(const struct net_device *dev); static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { -- cgit v1.2.3 From 1e99584b911cb6f3d2a681e2532d8dc3f9339c9c Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:02 +0200 Subject: ipip,gre,vti,sit: implement ndo_get_iflink Don't use dev->iflink anymore. CC: Steffen Klassert Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 2c47061a6954..d8214cb88bbc 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -142,6 +142,7 @@ int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); +int ip_tunnel_get_iflink(const struct net_device *dev); int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); -- cgit v1.2.3 From 7a66bbc96ce9ad8261fa5f7f6ae65370eb6866ee Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 2 Apr 2015 17:07:09 +0200 Subject: net: remove iflink field from struct net_device Now that all users of iflink have the ndo_get_iflink handler available, it's possible to remove this field. By default, dev_get_iflink() returns the ifindex of the interface. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 788eb7a622ad..846a1f5bc9db 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1538,7 +1538,7 @@ struct net_device { netdev_features_t mpls_features; int ifindex; - int iflink; + int group; struct net_device_stats stats; @@ -1741,7 +1741,6 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; - int group; struct pm_qos_request pm_qos_req; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 802f42a8d99254b8602bf65cc50e8333bf479f13 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:06 +0300 Subject: net/mlx4: Add RSS support for fragmented IP datagrams Enable RSS support for fragmented IP packets, when device supports it. Until now, fragmented IP packets were directed only to the default_qpn. Since IP fragments (datagram) have no upper protocols (L3 IP packets), hash is performed on 3-tuple - dst MAC, source IP and dest IP. The HW makes sure that this holds for the 1st fragment too, so all fragments go to the same QP. Signed-off-by: Ido Shamay 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') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index ab7ebec943b8..41eaafdfb1cd 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -174,6 +174,7 @@ enum { MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41, MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42, MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48, + MLX4_DEV_CAP_FLAG_RSS_IP_FRAG = 1LL << 52, MLX4_DEV_CAP_FLAG_SET_ETH_SCHED = 1LL << 53, MLX4_DEV_CAP_FLAG_SENSE_SUPPORT = 1LL << 55, MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59, -- cgit v1.2.3 From fccea6436a5bd16aed6f722efce13ec2c90427d7 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:08 +0300 Subject: net/mlx4: Make mlx4_is_eth visible inline funcion Currently implemented as static function in resource_tracker.c -- this change will allow other files in mlx4_core to use it as well. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 41eaafdfb1cd..0f7f13d6a03e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1002,6 +1002,11 @@ static inline int mlx4_is_slave(struct mlx4_dev *dev) return dev->flags & MLX4_FLAG_SLAVE; } +static inline int mlx4_is_eth(struct mlx4_dev *dev, int port) +{ + return dev->caps.port_type[port] == MLX4_PORT_TYPE_IB ? 0 : 1; +} + int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, struct mlx4_buf *buf, gfp_t gfp); void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); -- cgit v1.2.3 From 12a889c057504fbf307dd237aedb87263ef2848a Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:10 +0300 Subject: net/mlx4: New file for QoS related firmware commands Create two new files fw_qos.h and fw_qos.c in mlx4_core module. It gathers all relevant QoS firmware related commands etc, thus improving encapsulation of the mlx4_core module. For now it contains the QoS existing commands: mlx4_SET_PORT_SCHEDULER and mlx4_SET_PORT_PRIO2TC. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 0f7f13d6a03e..b676d0c0111a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -49,8 +49,6 @@ #define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 -#define MLX4_NUM_UP 8 -#define MLX4_NUM_TC 8 #define MLX4_MAX_100M_UNITS_VAL 255 /* * work around: can't set values * greater then this value when @@ -1311,9 +1309,6 @@ int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); -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 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); -- cgit v1.2.3 From 7e95bb99a8f969d4534867452793e44cc4731ca9 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:11 +0300 Subject: net/mlx4: Add mlx4_ALLOCATE_VPP implementation Implements device ALLOCATE_VPP command, to be used for granular QoS configuration of VFs by the PF device. Defines and queries the amount of VPPs assigned to each port, and the amount of VPPs assigned to each priority of each port. Once the total VPPs are split between the priorities of a port, they may be assigned with a share of the BW or a rate limit. Split into two functions (get/set) whoch are supplied with mlx4_alloc_vpp_context and physical port number. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 7299e9548906..e0f88a098fb8 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -68,6 +68,7 @@ enum { MLX4_CMD_UNMAP_ICM_AUX = 0xffb, MLX4_CMD_SET_ICM_SIZE = 0xffd, MLX4_CMD_ACCESS_REG = 0x3b, + MLX4_CMD_ALLOCATE_VPP = 0x80, /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, -- cgit v1.2.3 From 1c29146d3821be984030b49cf9509a269edc3b8b Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:12 +0300 Subject: net/mlx4: Add mlx4_SET_VPORT_QOS implementation Add the SET_VPORT_QOS device command, which is ntended for virtual granular QoS configuration per VF in SRIOV mode. The SET_VPORT_QOS command sets and queries QoS parameters of a VPort. Each priority allowed for a VPort is assigned with a share of the BW, and a BW limitation. QoS parameters can be modified at any time, but must be initialized before any QP is associated with the VPort. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index e0f88a098fb8..88326ed0033a 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -69,6 +69,7 @@ enum { MLX4_CMD_SET_ICM_SIZE = 0xffd, MLX4_CMD_ACCESS_REG = 0x3b, MLX4_CMD_ALLOCATE_VPP = 0x80, + MLX4_CMD_SET_VPORT_QOS = 0x81, /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, -- cgit v1.2.3 From d019fcb2244519d453694bfce868f3e717bfcebb Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:13 +0300 Subject: net/mlx4: Query device for QoS per VF support Checks in QUERY_DEV_CAP if the granular QoS per VF feature is supported by the device. Disabled for guests. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b676d0c0111a..c37208f7869f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -205,7 +205,8 @@ enum { MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21, MLX4_DEV_CAP_FLAG2_QCN = 1LL << 22, MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23, - MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN = 1LL << 24 + MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN = 1LL << 24, + MLX4_DEV_CAP_FLAG2_QOS_VPP = 1LL << 25, }; enum { -- cgit v1.2.3 From 08068cd5683f11e4505aa9c8cc6ed5942f8ad299 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:15 +0300 Subject: net/mlx4: Added qos_vport QP configuration in VST mode Granular QoS per VF feature introduce a new QP field, qos_vport. PF administrator can connect VF QPs to a certain QoS Vport, to inherit its proporties. Connecting QPs to the default QoS Vport (defined as 0) is always allowed, even when there are no allocated VPPs. At this point, only the default vport is connected to QPs. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/qp.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 1023ebe035b7..6fed539e5456 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -209,7 +209,8 @@ struct mlx4_qp_context { __be16 sq_wqe_counter; u32 reserved3; __be16 rate_limit_params; - __be16 reserved4; + u8 reserved4; + u8 qos_vport; __be32 param3; __be32 nummmcpeers_basemkey; u8 log_page_size; @@ -231,6 +232,7 @@ struct mlx4_update_qp_context { enum { MLX4_UPD_QP_MASK_PM_STATE = 32, MLX4_UPD_QP_MASK_VSD = 33, + MLX4_UPD_QP_MASK_QOS_VPP = 34, MLX4_UPD_QP_MASK_RATE_LIMIT = 35, }; @@ -432,7 +434,8 @@ enum mlx4_update_qp_attr { MLX4_UPDATE_QP_SMAC = 1 << 0, MLX4_UPDATE_QP_VSD = 1 << 1, MLX4_UPDATE_QP_RATE_LIMIT = 1 << 2, - MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 3) - 1 + MLX4_UPDATE_QP_QOS_VPORT = 1 << 3, + MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 4) - 1 }; enum mlx4_update_qp_params_flags { @@ -441,6 +444,7 @@ enum mlx4_update_qp_params_flags { struct mlx4_update_qp_params { u8 smac_index; + u8 qos_vport; u32 flags; u16 rate_unit; u16 rate_val; -- cgit v1.2.3 From cda373f4849d5dd6fedceb4aeba35682a0e1a833 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:16 +0300 Subject: net/mlx4_en: Enable TX rate limit per VF Support granular QoS per VF, by implementing the ndo_set_vf_rate. Enforce a rate limit per VF when called, and enabled only for VFs in VST mode with user priority supported by the device. We don't enforce VFs to be in VST mode at the moment of configuration, but rather save the given rate limit and enforce it when the VF is moved to VST with user priority which is supported (currently 0). VST<->VGT or VST qos value state changes are disallowed when a rate limit is configured. Minimum BW share is not supported yet. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 88326ed0033a..a788839f54bb 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -296,6 +296,8 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); +int mlx4_set_vf_rate(struct mlx4_dev *dev, int port, int vf, int min_tx_rate, + int max_tx_rate); 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); -- cgit v1.2.3 From 3742cc65512cd4897a63dce94104f9a6e74997a0 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:17 +0300 Subject: net/mlx4: Warn users of depracated QoS Firmware A new capability bit was introduced in the past to to differ devices using the QoS ETS feature. The old was deprecated since then. If driver sees device which set only the old capabilty, it will print warning to user suggesting to upgrade the FW. Signed-off-by: Ido Shamay 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') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c37208f7869f..15f46767342e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -207,6 +207,7 @@ enum { MLX4_DEV_CAP_FLAG2_QP_RATE_LIMIT = 1LL << 23, MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN = 1LL << 24, MLX4_DEV_CAP_FLAG2_QOS_VPP = 1LL << 25, + MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26, }; enum { -- cgit v1.2.3 From a130b59057320192b4b00ed0ba4bc8a38f66f289 Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:19 +0300 Subject: net/mlx4: Add SET_PORT opcode modifiers enumeration The calls to SET_PORT used hard-code numbers, when supplying command's opcode modifiers, fix that to use well defined constants. Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index a788839f54bb..62c4d4def474 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -188,7 +188,13 @@ enum { }; enum { - /* set port opcode modifiers */ + /* Set port opcode modifiers */ + MLX4_SET_PORT_IB_OPCODE = 0x0, + MLX4_SET_PORT_ETH_OPCODE = 0x1, +}; + +enum { + /* Set port Ethernet input modifiers */ MLX4_SET_PORT_GENERAL = 0x0, MLX4_SET_PORT_RQP_CALC = 0x1, MLX4_SET_PORT_MAC_TABLE = 0x2, -- cgit v1.2.3 From 51af33cfed248dc8f36fa82df06b85e10038a01e Mon Sep 17 00:00:00 2001 From: Ido Shamay Date: Thu, 2 Apr 2015 16:31:20 +0300 Subject: net/mlx4_en: Add interface identify support Add support for the interface ethtool identify feature. Make the physical port LED to blink with green and yellow colors. The device handles the LED blink by itself (synchrous use of set_phys_id), by returning 0 to ETHTOOL_ID_ACTIVE command. Signed-off-by: Eyal Grossman Signed-off-by: Ido Shamay 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') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 62c4d4def474..f62e7cf227c6 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -191,6 +191,7 @@ enum { /* Set port opcode modifiers */ MLX4_SET_PORT_IB_OPCODE = 0x0, MLX4_SET_PORT_ETH_OPCODE = 0x1, + MLX4_SET_PORT_BEACON_OPCODE = 0x4, }; enum { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 15f46767342e..b761be7c88c8 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -208,6 +208,7 @@ enum { MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN = 1LL << 24, MLX4_DEV_CAP_FLAG2_QOS_VPP = 1LL << 25, MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26, + MLX4_DEV_CAP_FLAG2_PORT_BEACON = 1LL << 27, }; enum { @@ -1311,6 +1312,7 @@ int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); +int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time); 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); -- cgit v1.2.3 From 78500b8c03236a18d454c9cc8a24cccca506b200 Mon Sep 17 00:00:00 2001 From: Muhammad Mahajna Date: Thu, 2 Apr 2015 16:31:22 +0300 Subject: net/mlx4_en: Add RX-ALL support Enabled when the device supports KEEP FCS and IGNORE FCS. When the flag is set, pass all received frames up the stack, even ones with invalid FCS, controlled by ethtool. Signed-off-by: Muhammad Mahajna Signed-off-by: Ido Shamay Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b761be7c88c8..f9ce34bec45b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -209,6 +209,7 @@ enum { MLX4_DEV_CAP_FLAG2_QOS_VPP = 1LL << 25, MLX4_DEV_CAP_FLAG2_ETS_CFG = 1LL << 26, MLX4_DEV_CAP_FLAG2_PORT_BEACON = 1LL << 27, + MLX4_DEV_CAP_FLAG2_IGNORE_FCS = 1LL << 28, }; enum { @@ -1313,6 +1314,8 @@ int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); int mlx4_SET_PORT_BEACON(struct mlx4_dev *dev, u8 port, u16 time); +int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, + u8 ignore_fcs_value); 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); -- cgit v1.2.3 From 64599cca51de08cef94bc13a0f98351e5bb01f41 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 2 Apr 2015 17:07:25 +0300 Subject: net/mlx5_core: Use coherent memory for command interface page Use coherent memory for the commands descriptor page. Take measures to make sure the page is aligned to MLX5_ADAPTER_PAGE_SIZE as required by the hardware. Reported-by: Yevgeny Kliteynik Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 166d9315fe4b..8d8ca6d9b03b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -232,6 +232,9 @@ struct mlx5_cmd_stats { }; struct mlx5_cmd { + void *cmd_alloc_buf; + dma_addr_t alloc_dma; + int alloc_size; void *cmd_buf; dma_addr_t dma; u16 cmdif_rev; -- cgit v1.2.3 From 302bdf68fc56a6330bc6b10ce435b4d466417537 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 2 Apr 2015 17:07:29 +0300 Subject: net/mlx5_core: Fix Mellanox copyright note Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/cmd.h | 2 +- include/linux/mlx5/cq.h | 2 +- include/linux/mlx5/device.h | 2 +- include/linux/mlx5/doorbell.h | 2 +- include/linux/mlx5/driver.h | 2 +- include/linux/mlx5/mlx5_ifc.h | 2 +- include/linux/mlx5/qp.h | 2 +- include/linux/mlx5/srq.h | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/cmd.h b/include/linux/mlx5/cmd.h index 2826a4b6071e..68cd08f02c2f 100644 --- a/include/linux/mlx5/cmd.h +++ b/include/linux/mlx5/cmd.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index f6b17ac601bd..72ee0d732a26 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4e5bd813bb9a..abf65c790421 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h index 163a818411e7..afc78a3f4462 100644 --- a/include/linux/mlx5/doorbell.h +++ b/include/linux/mlx5/doorbell.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8d8ca6d9b03b..8fedd39a9a60 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5f48b8f592c5..cb3ad17edd1f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2014, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 61f7a342d1bf..310b5f7fd6ae 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index e1a363a33663..f43ed054a3e0 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Mellanox Technologies inc. All rights reserved. + * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU -- cgit v1.2.3 From 233d05d28ad942929b6b4fbc48aa8dd083c16484 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 2 Apr 2015 17:07:32 +0300 Subject: net/mlx5_core: Move completion eqs from mlx5_ib to mlx5_core Preparation for ethernet driver. These functions will be used in drivers other than mlx5_ib. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8fedd39a9a60..f250f6580dad 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -410,7 +410,7 @@ struct mlx5_core_srq { struct mlx5_eq_table { void __iomem *update_ci; void __iomem *update_arm_ci; - struct list_head *comp_eq_head; + struct list_head comp_eqs_list; struct mlx5_eq pages_eq; struct mlx5_eq async_eq; struct mlx5_eq cmd_eq; @@ -725,6 +725,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); int mlx5_stop_eqs(struct mlx5_core_dev *dev); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -- cgit v1.2.3 From ce0f75093282c5dca1e79ae3e3e893deaea86166 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 2 Apr 2015 17:07:33 +0300 Subject: net/mlx5_core: Modify arm CQ in preparation for upcoming Ethernet driver Pass consumer index as a parameter to arm CQ Signed-off-by: Saeed Mahameed Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/cq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 72ee0d732a26..2695ced222df 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -137,14 +137,15 @@ enum { static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, void __iomem *uar_page, - spinlock_t *doorbell_lock) + spinlock_t *doorbell_lock, + u32 cons_index) { __be32 doorbell[2]; u32 sn; u32 ci; sn = cq->arm_sn & 3; - ci = cq->cons_index & 0xffffff; + ci = cons_index & 0xffffff; *cq->arm_db = cpu_to_be32(sn << 28 | cmd | ci); -- cgit v1.2.3 From 64613d9499c4887485d4350387919ea507330d90 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 2 Apr 2015 17:07:34 +0300 Subject: net/mlx5_core: Extend struct mlx5_interface to support multiple protocols Preparation for ethernet driver. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f250f6580dad..9a90e7523dc2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -781,14 +781,22 @@ enum { MAX_MR_CACHE_ENTRIES = 16, }; +enum { + MLX5_INTERFACE_PROTOCOL_IB = 0, + MLX5_INTERFACE_PROTOCOL_ETH = 1, +}; + struct mlx5_interface { void * (*add)(struct mlx5_core_dev *dev); void (*remove)(struct mlx5_core_dev *dev, void *context); void (*event)(struct mlx5_core_dev *dev, void *context, enum mlx5_dev_event event, unsigned long param); + void * (*get_dev)(void *context); + int protocol; struct list_head list; }; +void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); -- cgit v1.2.3 From e79d8429aac95a5cbe4c235795c7cd554c91f924 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 3 Apr 2015 22:17:17 +1030 Subject: netdevice: document NETDEV_TX_BUSY deprecation. This paraphrases DaveM (and steals some of his words) explaining why a device shouldn't return NETDEV_TX_BUSY, even though it looks so inviting to driver authors. See http://www.spinics.net/lists/netdev/msg322350.html Inspired-by: David Miller Signed-off-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 846a1f5bc9db..a710d22b174f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -795,7 +795,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, * struct net_device *dev); * Called when a packet needs to be transmitted. - * Must return NETDEV_TX_OK , NETDEV_TX_BUSY. + * Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop + * the queue before that can happen; it's for obsolete devices and weird + * corner cases, but the stack really does a non-trivial amount + * of useless work if you return NETDEV_TX_BUSY. * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * -- cgit v1.2.3 From 2e7056c433216f406b90a003aa0ba42e19d3bdcf Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 31 Mar 2015 14:19:10 -0700 Subject: jhash: Update jhash_[321]words functions to use correct initval Looking over the implementation for jhash2 and comparing it to jhash_3words I realized that the two hashes were in fact very different. Doing a bit of digging led me to "The new jhash implementation" in which lookup2 was supposed to have been replaced with lookup3. In reviewing the patch I noticed that jhash2 had originally initialized a and b to JHASH_GOLDENRATIO and c to initval, but after the patch a, b, and c were initialized to initval + (length << 2) + JHASH_INITVAL. However the changes in jhash_3words simply replaced the initialization of a and b with JHASH_INITVAL. This change corrects what I believe was an oversight so that a, b, and c in jhash_3words all have the same value added consisting of initval + (length << 2) + JHASH_INITVAL so that jhash2 and jhash_3words will now produce the same hash result given the same inputs. Fixes: 60d509c823cca ("The new jhash implementation") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/jhash.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 47cb09edec1a..348c6f47e4cc 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -145,11 +145,11 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) } -/* jhash_3words - hash exactly 3, 2 or 1 word(s) */ -static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) +/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { - a += JHASH_INITVAL; - b += JHASH_INITVAL; + a += initval; + b += initval; c += initval; __jhash_final(a, b, c); @@ -157,14 +157,19 @@ static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) return c; } +static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) +{ + return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); +} + static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { - return jhash_3words(a, b, 0, initval); + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { - return jhash_3words(a, 0, 0, initval); + return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ -- cgit v1.2.3 From bcad57182425426dd4aa14deb27f97acb329f3cd Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 3 Apr 2015 20:52:24 +0200 Subject: ebpf: add skb->priority to offset map for usage in {cls, act}_bpf This adds the ability to read out the skb->priority from an eBPF program, so that it can be taken into account from a tc filter or action for the use-case where the priority is not being used to directly override the filter classification in a qdisc, but to tag traffic otherwise for the classifier; the priority can be assigned from various places incl. user space, in future we may also mangle it from an eBPF program. Signed-off-by: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 74aab6e0d964..0db8580f3cca 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -184,6 +184,7 @@ struct __sk_buff { __u32 vlan_present; __u32 vlan_tci; __u32 vlan_proto; + __u32 priority; }; #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From a3bebdce4135a44d09e96ba66c40797c8f9fa902 Mon Sep 17 00:00:00 2001 From: Stas Sergeev Date: Wed, 1 Apr 2015 20:30:31 +0300 Subject: add fixed_phy_update_state() - update state of fixed_phy Currently fixed_phy uses a callback to periodically poll the link state. This patch adds the fixed_phy_update_state() API. It solves the following problems: - On link state interrupt, MAC driver can't update status. Instead it needs to provide the callback to periodically query the HW about the link state. It is more efficient to update status after interrupt. - The callback needs to be unregistered before phy_disconnect(), or otherwise it will be called with net_dev==NULL. phy_disconnect() does not have enough info to unregister the callback automatically. - The callback needs to be registered before of_phy_connect() to avoid running with outdated state, but of_phy_connect() returns the phy_device pointer, which is needed to register the callback. Registering it before of_phy_connect() will therefore require a hack to get the pointer earlier. Overall, this addition makes the subsequent patch that implements SGMII link status for mvneta, much cleaner. CC: Florian Fainelli CC: netdev@vger.kernel.org CC: linux-kernel@vger.kernel.org Signed-off-by: Stas Sergeev Signed-off-by: David S. Miller --- include/linux/phy_fixed.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 7e75bfe37cc7..fe5732d53eda 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -21,6 +21,9 @@ extern void fixed_phy_del(int phy_addr); extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); +extern int fixed_phy_update_state(struct phy_device *phydev, + const struct fixed_phy_status *status, + const struct fixed_phy_status *changed); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, struct fixed_phy_status *status) @@ -43,6 +46,12 @@ static inline int fixed_phy_set_link_update(struct phy_device *phydev, { return -ENODEV; } +static inline int fixed_phy_update_state(struct phy_device *phydev, + const struct fixed_phy_status *status, + const struct fixed_phy_status *changed) +{ + return -ENODEV; +} #endif /* CONFIG_FIXED_PHY */ #endif /* __PHY_FIXED_H */ -- cgit v1.2.3 From cfdfab314647b1755afedc33ab66f3f247e161ae Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 16:23:58 -0400 Subject: netfilter: Create and use nf_hook_state. Instead of passing a large number of arguments down into the nf_hook() entry points, create a structure which carries this state down through the hook processing layers. This makes is so that if we want to change the types or signatures of any of these pieces of state, there are less places that need to be changed. Signed-off-by: David S. Miller --- include/linux/netfilter.h | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2517ece98820..aee7ef1e23ed 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -44,6 +44,16 @@ int netfilter_init(void); struct sk_buff; struct nf_hook_ops; + +struct nf_hook_state { + unsigned int hook; + int thresh; + u_int8_t pf; + struct net_device *in; + struct net_device *out; + int (*okfn)(struct sk_buff *); +}; + typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, @@ -118,9 +128,7 @@ static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) } #endif -int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb, - struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh); +int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); /** * nf_hook_thresh - call a netfilter hook @@ -135,8 +143,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct net_device *outdev, int (*okfn)(struct sk_buff *), int thresh) { - if (nf_hooks_active(pf, hook)) - return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh); + if (nf_hooks_active(pf, hook)) { + struct nf_hook_state state = { + .hook = hook, + .thresh = thresh, + .pf = pf, + .in = indev, + .out = outdev, + .okfn = okfn + }; + + return nf_hook_slow(skb, &state); + } return 1; } -- cgit v1.2.3 From 1d1de89b9a4746f1dd055a3b8d073dd2f962a3b6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 16:31:01 -0400 Subject: netfilter: Use nf_hook_state in nf_queue_entry. That way we don't have to reinstantiate another nf_hook_state on the stack of the nf_reinject() path. Signed-off-by: David S. Miller --- include/net/netfilter/nf_queue.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 84a53d780306..d81d584157e1 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -12,12 +12,8 @@ struct nf_queue_entry { unsigned int id; struct nf_hook_ops *elem; - u_int8_t pf; + struct nf_hook_state state; u16 size; /* sizeof(entry) + saved route keys */ - unsigned int hook; - struct net_device *indev; - struct net_device *outdev; - int (*okfn)(struct sk_buff *); /* extra space to store route keys */ }; -- cgit v1.2.3 From 238e54c9cb9385a1ba99e92801f3615a2fb398b6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 20:32:56 -0400 Subject: netfilter: Make nf_hookfn use nf_hook_state. Pass the nf_hook_state all the way down into the hook functions themselves. Signed-off-by: David S. Miller --- include/linux/netfilter.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index aee7ef1e23ed..c480c43ad8f7 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -56,9 +56,7 @@ struct nf_hook_state { typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)); + const struct nf_hook_state *state); struct nf_hook_ops { struct list_head list; -- cgit v1.2.3 From d7cf4081ed454dba02cb632e492ecf5e29d1ee44 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 20:51:13 -0400 Subject: netfilter: Pass nf_hook_state through nf_nat_ipv4_{in,out,fn,local_fn}(). Signed-off-by: David S. Miller --- include/net/netfilter/nf_nat_l3proto.h | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index 340c013795a4..e596f35f14c9 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -44,40 +44,32 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, unsigned int hooknum); unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, -- cgit v1.2.3 From 1c491ba2592f621f21a693d43fab06302527fc0f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 20:56:08 -0400 Subject: netfilter: Pass nf_hook_state through ipt_do_table(). Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_tables.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 901e84db847d..4073510da485 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -65,8 +65,7 @@ struct ipt_error { extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table); #ifdef CONFIG_COMPAT -- cgit v1.2.3 From 8fe22382d1e73dc0ded8098ccf761c986149f72b Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 21:05:07 -0400 Subject: netfilter: Pass nf_hook_state through nf_nat_ipv6_{in,out,fn,local_fn}(). Signed-off-by: David S. Miller --- include/net/netfilter/nf_nat_l3proto.h | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index e596f35f14c9..a3127325f624 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -77,40 +77,32 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, unsigned int hooknum, unsigned int hdrlen); unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); #endif /* _NF_NAT_L3PROTO_H */ -- cgit v1.2.3 From 8f8a37152df49d541c43f010543f2b0176fcfb8e Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 21:09:51 -0400 Subject: netfilter: Pass nf_hook_state through ip6t_do_table(). Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6_tables.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 610208b18c05..b40d2b635778 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -31,8 +31,7 @@ extern struct xt_table *ip6t_register_table(struct net *net, extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table); /* Check for an extension */ -- cgit v1.2.3 From 073bfd56860446a2cb349bcf282fc17a36ca386c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 21:16:25 -0400 Subject: netfilter: Pass nf_hook_state through nft_set_pktinfo*(). Signed-off-by: David S. Miller --- include/net/netfilter/nf_tables.h | 7 +++---- include/net/netfilter/nf_tables_ipv4.h | 5 ++--- include/net/netfilter/nf_tables_ipv6.h | 5 ++--- 3 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index b8cd60dcb4e1..804981980393 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -26,12 +26,11 @@ struct nft_pktinfo { static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { pkt->skb = skb; - pkt->in = pkt->xt.in = in; - pkt->out = pkt->xt.out = out; + pkt->in = pkt->xt.in = state->in; + pkt->out = pkt->xt.out = state->out; pkt->ops = ops; pkt->xt.hooknum = ops->hooknum; pkt->xt.family = ops->pf; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index cba143fbd2e4..2df7f96902ee 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -8,12 +8,11 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { struct iphdr *ip; - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); ip = ip_hdr(pkt->skb); pkt->tprot = ip->protocol; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 74d976137658..97db2e3a5e65 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -8,13 +8,12 @@ static inline int nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); /* If malformed, drop it */ -- cgit v1.2.3 From b85c3dc9bd5347ad9540ec8d103b7c049c48b7cd Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 3 Apr 2015 21:18:46 -0400 Subject: netfilter: Pass nf_hook_state through arpt_do_table(). Signed-off-by: David S. Miller --- include/linux/netfilter_arp/arp_tables.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index cfb7191e6efa..c22a7fb8d0df 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -54,8 +54,7 @@ extern struct xt_table *arpt_register_table(struct net *net, extern void arpt_unregister_table(struct xt_table *table); extern unsigned int arpt_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table); #ifdef CONFIG_COMPAT -- cgit v1.2.3 From f60e5990d9c1424af9dbca60a23ba2a1c7c1ce90 Mon Sep 17 00:00:00 2001 From: "hannes@stressinduktion.org" Date: Wed, 1 Apr 2015 17:07:44 +0200 Subject: ipv6: protect skb->sk accesses from recursive dereference inside the stack We should not consult skb->sk for output decisions in xmit recursion levels > 0 in the stack. Otherwise local socket settings could influence the result of e.g. tunnel encapsulation process. ipv6 does not conform with this in three places: 1) ip6_fragment: we do consult ipv6_npinfo for frag_size 2) sk_mc_loop in ipv6 uses skb->sk and checks if we should loop the packet back to the local socket 3) ip6_skb_dst_mtu could query the settings from the user socket and force a wrong MTU Furthermore: In sk_mc_loop we could potentially land in WARN_ON(1) if we use a PF_PACKET socket ontop of an IPv6-backed vxlan device. Reuse xmit_recursion as we are currently only interested in protecting tunnel devices. Cc: Jiri Pirko Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++++ include/net/ip.h | 16 ---------------- include/net/ip6_route.h | 3 ++- include/net/sock.h | 2 ++ 4 files changed, 10 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dcf6ec27739b..278738873703 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2185,6 +2185,12 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +DECLARE_PER_CPU(int, xmit_recursion); +static inline int dev_recursion_level(void) +{ + return this_cpu_read(xmit_recursion); +} + struct net_device *dev_get_by_index(struct net *net, int ifindex); 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); diff --git a/include/net/ip.h b/include/net/ip.h index 025c61c0dffb..6cc1eafb153a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -453,22 +453,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk) #endif -static inline int sk_mc_loop(struct sock *sk) -{ - if (!sk) - return 1; - switch (sk->sk_family) { - case AF_INET: - return inet_sk(sk)->mc_loop; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - return inet6_sk(sk)->mc_loop; -#endif - } - WARN_ON(1); - return 1; -} - bool ip_call_ra_chain(struct sk_buff *skb); /* diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 1d09b46c1e48..eda131d179d9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -174,7 +174,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); diff --git a/include/net/sock.h b/include/net/sock.h index ab186b1d31ff..e4079c28e6b8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1762,6 +1762,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); +bool sk_mc_loop(struct sock *sk); + static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); -- cgit v1.2.3 From 91bc4822c3d61b9bb7ef66d3b77948a4f9177954 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Apr 2015 17:12:13 -0700 Subject: tc: bpf: add checksum helpers Commit 608cd71a9c7c ("tc: bpf: generalize pedit action") has added the possibility to mangle packet data to BPF programs in the tc pipeline. This patch adds two helpers bpf_l3_csum_replace() and bpf_l4_csum_replace() for fixing up the protocol checksums after the packet mangling. It also adds 'flags' argument to bpf_skb_store_bytes() helper to avoid unnecessary checksum recomputations when BPF programs adjusting l3/l4 checksums and documents all three helpers in uapi header. Moreover, a sample program is added to show how BPF programs can make use of the mangle and csum helpers. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0db8580f3cca..23df3e7f8e7d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -168,7 +168,43 @@ enum bpf_func_id { BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ - BPF_FUNC_skb_store_bytes, /* int skb_store_bytes(skb, offset, from, len) */ + + /** + * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->data + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_skb_store_bytes, + + /** + * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l3_csum_replace, + + /** + * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l4_csum_replace, __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From da18428498fb24438a23d982259461fe22bc1f46 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 21 Mar 2015 19:29:06 -0400 Subject: net: switch importing msghdr from userland to {compat_,}import_iovec() Signed-off-by: Al Viro --- include/net/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/compat.h b/include/net/compat.h index 42a9c8431177..48103cf94e97 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -40,7 +40,7 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *); #define compat_mmsghdr mmsghdr #endif /* defined(CONFIG_COMPAT) */ -ssize_t get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, +int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, struct sockaddr __user **, struct iovec **); asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *, unsigned int); -- cgit v1.2.3 From d8725c86aebaf3516e220760aaf5fefc73825188 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 11 Dec 2014 00:02:50 -0500 Subject: get rid of the size argument of sock_sendmsg() it's equal to iov_iter_count(&msg->msg_iter) in all cases Signed-off-by: Al Viro --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index e74114bcca68..738ea48be889 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -211,7 +211,7 @@ int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); void sock_release(struct socket *sock); -int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); +int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); -- cgit v1.2.3 From 01e97e6517053d7c0b9af5248e944a9209909cf5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 15 Dec 2014 21:39:31 -0500 Subject: new helper: msg_data_left() convert open-coded instances Signed-off-by: Al Viro --- include/linux/socket.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index c9852ef7e317..5bf59c8493b7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -139,6 +139,11 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg); } +static inline size_t msg_data_left(struct msghdr *msg) +{ + return iov_iter_count(&msg->msg_iter); +} + /* "Socket"-level control message types: */ #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ -- cgit v1.2.3