From cc7a21b6fbd945f8d8f61422ccd27203c1fafeb7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Jun 2020 12:02:59 -0700 Subject: ipv6: icmp6: avoid indirect call for icmpv6_send() If IPv6 is builtin, we do not need an expensive indirect call to reach icmp6_send(). v2: put inline keyword before the type to avoid sparse warnings. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 33d379602314..1b3371ae8193 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -13,12 +13,32 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #include #if IS_ENABLED(CONFIG_IPV6) -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); +#if IS_BUILTIN(CONFIG_IPV6) +void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct in6_addr *force_saddr); +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + icmp6_send(skb, type, code, info, NULL); +} +static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) +{ + BUILD_BUG_ON(fn != icmp6_send); + return 0; +} +static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) +{ + BUILD_BUG_ON(fn != icmp6_send); + return 0; +} +#else +extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); +#endif + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); -- cgit v1.2.3 From c746053d275c8b6ff1d713addabf049c9c9a58fc Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:45:58 +0100 Subject: net: phy: add support for probing MMDs >= 8 for devices-in-package Add support for probing MMDs above 7 for a valid devices-in-package specifier, but only probe the vendor MMDs for this if they also report that there the device is present in status register 2. This avoids issues where the MMD is implemented, but does not provide IEEE 802.3 compliant registers (such as the MV88X3310 PHY.) Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8c05d0fb5c00..abe318387331 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -388,6 +388,8 @@ enum phy_state { PHY_CABLETEST, }; +#define MDIO_MMD_NUM 32 + /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: Bit vector of devices present. -- cgit v1.2.3 From 320ed3bf900075614c43499dc01db8d25717b986 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:46:08 +0100 Subject: net: phy: split devices_in_package We have two competing requirements for the devices_in_package field. We want to use it as a bit array indicating which MMDs are present, but we also want to know if the Clause 22 registers are present. Since "devices in package" is a term used in the 802.3 specification, keep this as the as-specified values read from the PHY, and introduce a new member "mmds_present" to indicate which MMDs are actually present in the PHY, derived from the "devices in package" value. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index abe318387331..19d9e040ad84 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -392,11 +392,13 @@ enum phy_state { /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers - * @devices_in_package: Bit vector of devices present. + * @devices_in_package: IEEE 802.3 devices in package register value. + * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; + u32 mmds_present; u32 device_ids[8]; }; -- cgit v1.2.3 From 389a338999875b6e7b111096e8b6484434556449 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 18 Jun 2020 14:46:13 +0100 Subject: net: phy: read MMD ID from all present MMDs Expand the device_ids[] array to allow all MMD IDs to be read rather than just the first 8 MMDs, but only read the ID if the MDIO_STAT2 register reports that a device really is present here for these new devices to maintain compatibility with our current behaviour. Note that only a limited number of devices have MDIO_STAT2. 88X3310 PHY vendor MMDs do are marked as present in the devices_in_package, but do not contain IEE 802.3 compatible register sets in their lower space. This avoids reading incorrect values as MMD identifiers. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 19d9e040ad84..9248dd2ce4ca 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -399,7 +399,7 @@ enum phy_state { struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; - u32 device_ids[8]; + u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; -- cgit v1.2.3 From 41c48f3a98231738c5ce79f6f2aa6e40ba924d18 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 19 Jun 2020 14:11:43 -0700 Subject: bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com --- include/linux/bpf.h | 9 +++++++++ include/linux/bpf_verifier.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..1e1501ee53ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -92,6 +92,10 @@ struct bpf_map_ops { int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); + + /* BTF name and id of struct allocated by map_alloc */ + const char * const map_btf_name; + int *map_btf_id; }; struct bpf_map_memory { @@ -1109,6 +1113,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_ptr_to_map_access(void) +{ + return perfmon_capable(); +} + static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ca08db4ffb5f..53c7bd568c5d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -379,6 +379,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; -- cgit v1.2.3 From fa997825ebeca820f4001a9e6d285345d3a535ba Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 19 Jun 2020 03:32:50 +0000 Subject: net/mlx5: Constify mac address pointer Since none of the functions need to modify the input mac address, constify them. Signed-off-by: Parav Pandit Reviewed-by: Roi Dayan Signed-off-by: David S. Miller --- include/linux/mlx5/vport.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 8170da1e9f70..4db87bcfce7b 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -75,7 +75,7 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline); int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 min_inline); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, - u16 vport, u8 *addr); + u16 vport, const u8 *addr); int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From a602ea86e9f0d82f5c7ba1d3f7487d4097380b96 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Sun, 21 Jun 2020 10:59:51 +0300 Subject: net: phy: marvell: Add Marvell 88E1340S support Add support for this new phy ID. Signed-off-by: Maxim Kochetkov Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index af6b11d4d673..c4390e9cbf15 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -15,6 +15,7 @@ #define MARVELL_PHY_ID_88E1149R 0x01410e50 #define MARVELL_PHY_ID_88E1240 0x01410e30 #define MARVELL_PHY_ID_88E1318S 0x01410e90 +#define MARVELL_PHY_ID_88E1340S 0x01410dc0 #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 #define MARVELL_PHY_ID_88E1540 0x01410eb0 -- cgit v1.2.3 From f59babf95ef969a18744082ee16e4dfd17743c0b Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Sun, 21 Jun 2020 10:59:52 +0300 Subject: net: phy: marvell: Add Marvell 88E1548P support Add support for this new phy ID. Signed-off-by: Maxim Kochetkov Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index c4390e9cbf15..ff7b7607c8cf 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -20,6 +20,7 @@ #define MARVELL_PHY_ID_88E1510 0x01410dd0 #define MARVELL_PHY_ID_88E1540 0x01410eb0 #define MARVELL_PHY_ID_88E1545 0x01410ea0 +#define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 #define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 -- cgit v1.2.3 From d63cc24933c774ea464090af1998a7b63f11c166 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 8 Apr 2020 12:42:09 +0300 Subject: net/mlx5: Export resource dump interface Export some of the resource dump API. mlx5_ib driver will use it in downstream patches. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/rsc_dump.h | 48 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/mlx5/rsc_dump.h (limited to 'include/linux') diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h new file mode 100644 index 000000000000..87415fa754fe --- /dev/null +++ b/include/linux/mlx5/rsc_dump.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies inc. */ + +#include + +#ifndef __MLX5_RSC_DUMP +#define __MLX5_RSC_DUMP + +enum mlx5_sgmt_type { + MLX5_SGMT_TYPE_HW_CQPC, + MLX5_SGMT_TYPE_HW_SQPC, + MLX5_SGMT_TYPE_HW_RQPC, + MLX5_SGMT_TYPE_FULL_SRQC, + MLX5_SGMT_TYPE_FULL_CQC, + MLX5_SGMT_TYPE_FULL_EQC, + MLX5_SGMT_TYPE_FULL_QPC, + MLX5_SGMT_TYPE_SND_BUFF, + MLX5_SGMT_TYPE_RCV_BUFF, + MLX5_SGMT_TYPE_SRQ_BUFF, + MLX5_SGMT_TYPE_CQ_BUFF, + MLX5_SGMT_TYPE_EQ_BUFF, + MLX5_SGMT_TYPE_SX_SLICE, + MLX5_SGMT_TYPE_SX_SLICE_ALL, + MLX5_SGMT_TYPE_RDB, + MLX5_SGMT_TYPE_RX_SLICE_ALL, + MLX5_SGMT_TYPE_MENU, + MLX5_SGMT_TYPE_TERMINATE, + + MLX5_SGMT_TYPE_NUM, /* Keep last */ +}; + +struct mlx5_rsc_key { + enum mlx5_sgmt_type rsc; + int index1; + int index2; + int num_of_obj1; + int num_of_obj2; + int size; +}; + +struct mlx5_rsc_dump_cmd; + +struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev, + struct mlx5_rsc_key *key); +void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd); +int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, + struct page *page, int *size); +#endif /* __MLX5_RSC_DUMP */ -- cgit v1.2.3 From 608ca553c9a2008908120e0e45b1cfc4aefcfd49 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 8 Apr 2020 12:36:20 +0300 Subject: net/mlx5: Add support in query QP, CQ and MKEY segments Introduce new resource dump segments - PRM_QUERY_QP, PRM_QUERY_CQ and PRM_QUERY_MKEY. These segments contains the resource dump in PRM query format. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/rsc_dump.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/rsc_dump.h b/include/linux/mlx5/rsc_dump.h index 87415fa754fe..d11c0b228620 100644 --- a/include/linux/mlx5/rsc_dump.h +++ b/include/linux/mlx5/rsc_dump.h @@ -23,6 +23,9 @@ enum mlx5_sgmt_type { MLX5_SGMT_TYPE_SX_SLICE_ALL, MLX5_SGMT_TYPE_RDB, MLX5_SGMT_TYPE_RX_SLICE_ALL, + MLX5_SGMT_TYPE_PRM_QUERY_QP, + MLX5_SGMT_TYPE_PRM_QUERY_CQ, + MLX5_SGMT_TYPE_PRM_QUERY_MKEY, MLX5_SGMT_TYPE_MENU, MLX5_SGMT_TYPE_TERMINATE, -- cgit v1.2.3 From e678e9ddea96590888b034e2a7ad1128bf1ea1ea Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Tue, 23 Jun 2020 09:42:31 -0700 Subject: indirect_call_wrapper: extend indirect wrapper to support up to 4 calls There are many places where 2 annotations are not enough. This patch adds INDIRECT_CALL_3 and INDIRECT_CALL_4 to cover such cases. Signed-off-by: Brian Vazquez Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/indirect_call_wrapper.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 00d7e8e919c6..54c02c84906a 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -23,6 +23,16 @@ likely(f == f2) ? f2(__VA_ARGS__) : \ INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ }) +#define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ + ({ \ + likely(f == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + }) +#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ + ({ \ + likely(f == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + }) #define INDIRECT_CALLABLE_DECLARE(f) f #define INDIRECT_CALLABLE_SCOPE @@ -30,6 +40,8 @@ #else #define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALL_2(f, f2, f1, ...) f(__VA_ARGS__) +#define INDIRECT_CALL_3(f, f3, f2, f1, ...) f(__VA_ARGS__) +#define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALLABLE_DECLARE(f) #define INDIRECT_CALLABLE_SCOPE static #endif -- cgit v1.2.3 From 0cc8fecf041d3e5285380da62cc6662bdc942d8c Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Mon, 22 Jun 2020 20:35:32 +0530 Subject: net: phy: Allow mdio buses to auto-probe c45 devices The mdiobus_scan logic is currently hardcoded to only work with c22 devices. This works fairly well in most cases, but its possible that a c45 device doesn't respond despite being a standard phy. If the parent hardware is capable, it makes sense to scan for c22 devices before falling back to c45. As we want this to reflect the capabilities of the STA, lets add a field to the mii_bus structure to represent the capability. That way devices can opt into the extended scanning. Existing users should continue to default to c22 only scanning as long as they are zero'ing the structure before use. Signed-off-by: Jeremy Linton Signed-off-by: Calvin Johnson Signed-off-by: David S. Miller --- include/linux/phy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9248dd2ce4ca..7860d56c6bf5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,6 +298,14 @@ struct mii_bus { /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; + /* bus capabilities, used for probing */ + enum { + MDIOBUS_NO_CAP = 0, + MDIOBUS_C22, + MDIOBUS_C45, + MDIOBUS_C22_C45, + } probe_capabilities; + /* protect access to the shared element */ struct mutex shared_lock; -- cgit v1.2.3 From aad4a0a9513af962137c4842463d11ed491eec37 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Sat, 20 Jun 2020 18:30:51 +0300 Subject: tcp: Expose tcp_sock_set_keepidle_locked This is preparation for usage in bpf_setsockopt. v2: - remove redundant EXPORT_SYMBOL (Alexei Starovoitov) Signed-off-by: Dmitry Yakunin Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200620153052.9439-2-zeil@yandex-team.ru --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9aac824c523c..3bdec31ce8f4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); +int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); void tcp_sock_set_nodelay(struct sock *sk); -- cgit v1.2.3 From 0ef44e5cab8dbf0a0327871b48fe7c8425d0d885 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 23 Jun 2020 16:30:07 +0200 Subject: net: phy: add support for a common probe between shared PHYs Shared PHYs (PHYs in the same hardware package) may have shared registers and their drivers would usually need to share information. There is currently a way to have a shared (part of the) init, by using phy_package_init_once(). This patch extends the logic to share parts of the probe to allow sharing the initialization of locks or resources retrieval. Signed-off-by: Antoine Tenart Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7860d56c6bf5..6fb8f302978d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -244,7 +244,8 @@ struct phy_package_shared { }; /* used as bit number in atomic bitops */ -#define PHY_SHARED_F_INIT_DONE 0 +#define PHY_SHARED_F_INIT_DONE 0 +#define PHY_SHARED_F_PROBE_DONE 1 /* * The Bus class for PHYs. Devices which provide access to @@ -1566,14 +1567,25 @@ static inline int __phy_package_write(struct phy_device *phydev, return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); } -static inline bool phy_package_init_once(struct phy_device *phydev) +static inline bool __phy_package_set_once(struct phy_device *phydev, + unsigned int b) { struct phy_package_shared *shared = phydev->shared; if (!shared) return false; - return !test_and_set_bit(PHY_SHARED_F_INIT_DONE, &shared->flags); + return !test_and_set_bit(b, &shared->flags); +} + +static inline bool phy_package_init_once(struct phy_device *phydev) +{ + return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); +} + +static inline bool phy_package_probe_once(struct phy_device *phydev) +{ + return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } extern struct bus_type mdio_bus_type; -- cgit v1.2.3 From af7ec13833619e17f03aa73a785a2f871da6d66b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:09 -0700 Subject: bpf: Add bpf_skc_to_tcp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a tcp6_sock pointer. The return value could be NULL if the casting is illegal. A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added so the verifier is able to deduce proper return types for the helper. Different from the previous BTF_ID based helpers, the bpf_skc_to_tcp6_sock() argument can be several possible btf_ids. More specifically, all possible socket data structures with sock_common appearing in the first in the memory layout. This patch only added socket types related to tcp and udp. All possible argument btf_id and return value btf_id for helper bpf_skc_to_tcp6_sock() are pre-calculcated and cached. In the future, it is even possible to precompute these btf_id's at kernel build time. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com --- include/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e1501ee53ce..c0e38ad07848 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -265,6 +265,7 @@ enum bpf_return_type { RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ + RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -287,6 +288,12 @@ struct bpf_func_proto { enum bpf_arg_type arg_type[5]; }; int *btf_id; /* BTF ids of arguments */ + bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is + * valid. Often used if more + * than one btf id is permitted + * for this argument. + */ + int *ret_btf_id; /* return value btf_id */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -1524,6 +1531,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +void init_btf_sock_ids(struct btf *btf); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1549,6 +1557,9 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } +static inline void init_btf_sock_ids(struct btf *btf) +{ +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) @@ -1638,6 +1649,7 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 478cfbdf5f13dfe09cfd0b1cbac821f5e27f6108 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:11 -0700 Subject: bpf: Add bpf_skc_to_{tcp, tcp_timewait, tcp_request}_sock() helpers Three more helpers are added to cast a sock_common pointer to an tcp_sock, tcp_timewait_sock or a tcp_request_sock for tracing programs. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c0e38ad07848..c23998cf6699 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1650,6 +1650,9 @@ extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 0d4fad3e57df2bf61e8ffc8d12a34b1caf9b8835 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 23 Jun 2020 16:08:15 -0700 Subject: bpf: Add bpf_skc_to_udp6_sock() helper The helper is used in tracing programs to cast a socket pointer to a udp6_sock pointer. The return value could be NULL if the casting is illegal. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Cc: Eric Dumazet Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c23998cf6699..3d2ade703a35 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1653,6 +1653,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From c6d5d843d9b6e8dca3768250970f0d0a1e3d4fb0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 24 Jun 2020 11:06:54 +0100 Subject: net: phylink: add phylink_speed_(up|down) interface Add an interface for the phy_speed_(up|down) functions when a driver makes use of phylink. These pass the call through to phylib when we have a normal PHY attached (i.o.w., not a PHY on a SFP module.) Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index cc5b452a184e..b32b8b45421b 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -392,6 +392,8 @@ int phylink_init_eee(struct phylink *, bool); int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); +int phylink_speed_down(struct phylink *pl, bool sync); +int phylink_speed_up(struct phylink *pl); #define phylink_zero(bm) \ bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) -- cgit v1.2.3 From 92252eec913b2dd5e7b5de11ea3efa2e64d65cf4 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 24 Jun 2020 07:16:02 -0500 Subject: net: phy: Add a helper to return the index for of the internal delay Add a helper function that will return the index in the array for the passed in internal delay value. The helper requires the array, size and delay value. The helper will then return the index for the exact match or return the index for the index to the closest smaller value. Signed-off-by: Dan Murphy Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6fb8f302978d..2c00374dc996 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1443,6 +1443,10 @@ void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); + +s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, + const int *delay_values, int size, bool is_rx); + void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); -- cgit v1.2.3 From fe21b6c3a65ca74cc4d0909635649bea48b115b3 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 4 May 2020 09:43:48 -0700 Subject: i40e: Move client header location Move i40e_client.h to include/linux/net/intel/* since its shared between i40iw and i40e. Signed-off-by: Shiraz Saleem Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/net/intel/i40e_client.h | 203 ++++++++++++++++++++++++++++++++++ 1 file changed, 203 insertions(+) create mode 100644 include/linux/net/intel/i40e_client.h (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h new file mode 100644 index 000000000000..72994baf4941 --- /dev/null +++ b/include/linux/net/intel/i40e_client.h @@ -0,0 +1,203 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _I40E_CLIENT_H_ +#define _I40E_CLIENT_H_ + +#define I40E_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define I40E_CLIENT_VERSION_MAJOR 0 +#define I40E_CLIENT_VERSION_MINOR 01 +#define I40E_CLIENT_VERSION_BUILD 00 +#define I40E_CLIENT_VERSION_STR \ + __stringify(I40E_CLIENT_VERSION_MAJOR) "." \ + __stringify(I40E_CLIENT_VERSION_MINOR) "." \ + __stringify(I40E_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; +}; + +/* Structure to hold Lan device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *pf; + + /* All L2 params that could change during the life span of the PF + * and needs to be communicated to the client when they change + */ + struct i40e_qvlist_info *qvlist_info; + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ + u16 fw_maj_ver; /* firmware major version */ + u16 fw_min_ver; /* firmware minor version */ + u32 fw_build; /* firmware build number */ +}; + +#define I40E_CLIENT_RESET_LEVEL_PF 1 +#define I40E_CLIENT_RESET_LEVEL_CORE 2 +#define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + int (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u32 vf_id, u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset. + * The level helps determine the level of reset being requested. + */ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client, u32 level); + + /* API for the RDMA driver to set certain VSI flags that control + * PE Engine. + */ + int (*update_vsi_ctxt)(struct i40e_info *ldev, + struct i40e_client *client, + bool is_vf, u32 vf_id, + u32 flag, u32 valid_flag); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever PF is ready + * to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be called when netdev is unavailable or when unregister + * call comes in. If the close is happenening due to a reset being + * triggered set the reset bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mtu */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id, + u8 *msg, u16 len); + + /* called when a VF is reset by the PF */ + void (*vf_reset)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id); + + /* called when the number of VFs changes */ + void (*vf_enable)(struct i40e_info *ldev, + struct i40e_client *client, u32 num_vfs); + + /* returns true if VF is capable of specified offload */ + int (*vf_capable)(struct i40e_info *ldev, + struct i40e_client *client, u32 vf_id); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[I40E_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + const struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +static inline bool i40e_client_is_registered(struct i40e_client *client) +{ + return test_bit(__I40E_CLIENT_REGISTERED, &client->state); +} + +/* used by clients */ +int i40e_register_client(struct i40e_client *client); +int i40e_unregister_client(struct i40e_client *client); + +#endif /* _I40E_CLIENT_H_ */ -- cgit v1.2.3 From 3c98f9ee6bc280499cbcb6f8e42c001c3bd7caa1 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Mon, 6 Jan 2020 16:09:33 -0800 Subject: i40e: remove unused defines Remove all the unused defines as they are just dead weight. Signed-off-by: Jesse Brandeburg Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/net/intel/i40e_client.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 72994baf4941..f41387a8969f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -37,11 +37,6 @@ enum i40e_client_instance_state { struct i40e_ops; struct i40e_client; -/* HW does not define a type value for AEQ; only for RX/TX and CEQ. - * In order for us to keep the interface simple, SW will define a - * unique type value for AEQ. - */ -#define I40E_QUEUE_TYPE_PE_AEQ 0x80 #define I40E_QUEUE_INVALID_IDX 0xFFFF struct i40e_qv_info { @@ -56,7 +51,6 @@ struct i40e_qvlist_info { struct i40e_qv_info qv_info[1]; }; -#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF /* set of LAN parameters useful for clients managed by LAN */ @@ -87,7 +81,6 @@ struct i40e_info { u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 -#define I40E_CLIENT_FTYPE_VF 1 u8 ftype; /* function type, PF or VF */ void *pf; @@ -184,8 +177,6 @@ struct i40e_client { unsigned long state; /* client state */ atomic_t ref_cnt; /* Count of all the client devices of this kind */ u32 flags; -#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) -#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) u8 type; #define I40E_CLIENT_IWARP 0 const struct i40e_client_ops *ops; /* client ops provided by the client */ -- cgit v1.2.3 From 333740981f94fa80326cc8e5d2da105f17bc1dd5 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 26 Jun 2020 17:53:23 +0200 Subject: net: mdio: add a forward declaration for reset_control to mdio.h This header refers to struct reset_control but doesn't include any reset header. The structure definition is probably somehow indirectly pulled in since no warnings are reported but for the sake of correctness add the forward declaration for struct reset_control. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 36d2e0673d03..898cbf00332a 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -18,6 +18,7 @@ struct gpio_desc; struct mii_bus; +struct reset_control; /* Multiple levels of nesting are possible. However typically this is * limited to nested DSA like layer, a MUX layer, and the normal -- cgit v1.2.3 From 9205d7b1c1cffa827c23bdbf35e04c7cbe1e1f10 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 25 Jun 2020 22:59:41 -0700 Subject: net/mlx5: Avoid RDMA file inclusion in core driver mlx5 cq.h does not depend on RDMA verbs. Remove RDMA verbs file inclusion. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/cq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index b5a9399e07ee..7bfb67363434 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -33,7 +33,6 @@ #ifndef MLX5_CORE_CQ_H #define MLX5_CORE_CQ_H -#include #include #include -- cgit v1.2.3 From 2d1b69ed65ee033aa541518cc9f6a815296ac493 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 25 Jun 2020 22:59:43 -0700 Subject: net/mlx5: kTLS, Improve TLS params layout structures Add explicit WQE segment structures for the TLS static and progress params. According to the HW spec, TISN is not part of the progress params context, take it out of it. Rename the control segment tisn field as it could hold either a TIS or a TIR number. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 9 +++++++++ include/linux/mlx5/mlx5_ifc.h | 5 +---- include/linux/mlx5/qp.h | 2 +- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 1bc27aca648b..57db125e5802 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -458,6 +458,15 @@ enum { MLX5_OPC_MOD_TLS_TIR_PROGRESS_PARAMS = 0x2, }; +struct mlx5_wqe_tls_static_params_seg { + u8 ctx[MLX5_ST_SZ_BYTES(tls_static_params)]; +}; + +struct mlx5_wqe_tls_progress_params_seg { + __be32 tis_tir_num; + u8 ctx[MLX5_ST_SZ_BYTES(tls_progress_params)]; +}; + enum { MLX5_SET_PORT_RESET_QKEY = 0, MLX5_SET_PORT_GUID0 = 16, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 116bd9bb347f..a227518c70cf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10638,16 +10638,13 @@ struct mlx5_ifc_tls_static_params_bits { }; struct mlx5_ifc_tls_progress_params_bits { - u8 reserved_at_0[0x8]; - u8 tisn[0x18]; - u8 next_record_tcp_sn[0x20]; u8 hw_resync_tcp_sn[0x20]; u8 record_tracker_state[0x2]; u8 auth_state[0x2]; - u8 reserved_at_64[0x4]; + u8 reserved_at_44[0x4]; u8 hw_offset_record_number[0x18]; }; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index b8992b861ae6..36492a1342cf 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -209,7 +209,7 @@ struct mlx5_wqe_ctrl_seg { __be32 general_id; __be32 imm; __be32 umr_mkey; - __be32 tisn; + __be32 tis_tir_num; }; }; -- cgit v1.2.3 From ecc31c60240b9808a274befc5db6b8a249a6ade1 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 29 Jun 2020 23:46:16 +0300 Subject: ethtool: Add link extended state Currently, drivers can only tell whether the link is up/down using LINKSTATE_GET, but no additional information is given. Add attributes to LINKSTATE_GET command in order to allow drivers to expose the user more information in addition to link state to ease the debug process, for example, reason for link down state. Extended state consists of two attributes - link_ext_state and link_ext_substate. The idea is to avoid 'vendor specific' states in order to prevent drivers to use specific link_ext_state that can be in the future common link_ext_state. The substates allows drivers to add more information to the common link_ext_state. For example, vendor can expose 'Autoneg' as link_ext_state and add 'No partner detected during force mode' as link_ext_substate. If a driver cannot pinpoint the extended state with the substate accuracy, it is free to expose only the extended state and omit the substate attribute. Signed-off-by: Amit Cohen Reviewed-by: Jiri Pirko Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/ethtool.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a23b26eab479..48ad3b6a0150 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -86,6 +86,22 @@ struct net_device; u32 ethtool_op_get_link(struct net_device *dev); int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); + +/** + * struct ethtool_link_ext_state_info - link extended state and substate. + */ +struct ethtool_link_ext_state_info { + enum ethtool_link_ext_state link_ext_state; + union { + enum ethtool_link_ext_substate_autoneg autoneg; + enum ethtool_link_ext_substate_link_training link_training; + enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch; + enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; + enum ethtool_link_ext_substate_cable_issue cable_issue; + u8 __link_ext_substate; + }; +}; + /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table @@ -245,6 +261,11 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * @get_link: Report whether physical link is up. Will only be called if * the netdev is up. Should usually be set to ethtool_op_get_link(), * which uses netif_carrier_ok(). + * @get_link_ext_state: Report link extended state. Should set link_ext_state and + * link_ext_substate (link_ext_substate of 0 means link_ext_substate is unknown, + * do not attach ext_substate attribute to netlink message). If link_ext_state + * and link_ext_substate are unknown, return -ENODATA. If not implemented, + * link_ext_state and link_ext_substate will not be sent to userspace. * @get_eeprom: Read data from the device EEPROM. * Should fill in the magic field. Don't need to check len for zero * or wraparound. Fill in the data argument with the eeprom values @@ -384,6 +405,8 @@ struct ethtool_ops { void (*set_msglevel)(struct net_device *, u32); int (*nway_reset)(struct net_device *); u32 (*get_link)(struct net_device *); + int (*get_link_ext_state)(struct net_device *, + struct ethtool_link_ext_state_info *); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); -- cgit v1.2.3 From ab81e23cf77905896a5e51422eb58e8763507b85 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:07 +0300 Subject: net: qed: correct existing SPDX tags QLogic QED drivers source code is dual licensed under GPL-2.0/BSD-3-Clause. Correct already existing but wrong SPDX tags to match the actual license. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/fcoe_common.h | 2 +- include/linux/qed/qed_fcoe_if.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 98cfc195abe2..a669d7d84284 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015 QLogic Corporation */ diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 46082480a2c3..65d0317ef67e 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -1,4 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ + #ifndef _QED_FCOE_IF_H #define _QED_FCOE_IF_H #include -- cgit v1.2.3 From 1f4d4ed6acc5b74974fa038e5e9d2e19f3b532f3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:08 +0300 Subject: net: qed: convert to SPDX License Identifiers QLogic QED drivers source code is dual licensed under GPL-2.0/BSD-3-Clause. Remove all the boilerplates in the existing code and replace it with the correct SPDX tag. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 29 +---------------------------- include/linux/qed/eth_common.h | 29 +---------------------------- include/linux/qed/iscsi_common.h | 29 +---------------------------- include/linux/qed/iwarp_common.h | 29 +---------------------------- include/linux/qed/qed_chain.h | 29 +---------------------------- include/linux/qed/qed_eth_if.h | 29 +---------------------------- include/linux/qed/qed_if.h | 29 +---------------------------- include/linux/qed/qed_iov_if.h | 29 +---------------------------- include/linux/qed/qed_iscsi_if.h | 29 +---------------------------- include/linux/qed/qed_ll2_if.h | 29 +---------------------------- include/linux/qed/qed_rdma_if.h | 30 ++---------------------------- include/linux/qed/qede_rdma.h | 30 ++---------------------------- include/linux/qed/rdma_common.h | 29 +---------------------------- include/linux/qed/roce_common.h | 29 +---------------------------- include/linux/qed/storage_common.h | 29 +---------------------------- include/linux/qed/tcp_common.h | 29 +---------------------------- 16 files changed, 18 insertions(+), 448 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 2c4737e6694a..294d01eae5cb 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2016 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _COMMON_HSI_H diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 95f5fd615852..a9566ef3c2ce 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ETH_COMMON__ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 2f0a771a9176..7ca89fb9247f 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ISCSI_COMMON__ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h index c6cfd39cd910..23583e644257 100644 --- a/include/linux/qed/iwarp_common.h +++ b/include/linux/qed/iwarp_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __IWARP_COMMON__ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 6d15040c642c..e6e25197f7cb 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_CHAIN_H diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index a1310482c4ed..7803dedbcb52 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_ETH_IF_H diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8cb76405cbce..4a36608ff3a8 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_IF_H diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h index ac2e6a3199a3..c2ca8196def9 100644 --- a/include/linux/qed/qed_iov_if.h +++ b/include/linux/qed/qed_iov_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_IOV_IF_H diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index d0df1bec5357..89912c6c440c 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_ISCSI_IF_H diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 1313c34d9a68..79cac277e38b 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef _QED_LL2_IF_H diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 2d3ddd2b85e0..041a5b005a82 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -1,34 +1,8 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ + #ifndef _QED_RDMA_IF_H #define _QED_RDMA_IF_H #include diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 5a00c7a473bf..20ed7f2c55bb 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -1,34 +1,8 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qedr NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ + #ifndef QEDE_ROCE_H #define QEDE_ROCE_H diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 480a57eb36cc..3e3f01136c06 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __RDMA_COMMON__ diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 473fba76aa77..89065f023813 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __ROCE_COMMON__ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 9a973ffbbff5..34f069c79067 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __STORAGE_COMMON__ diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 4a4845193539..925e7cb7a582 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * - * 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 - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and /or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. */ #ifndef __TCP_COMMON__ -- cgit v1.2.3 From 663eacd899ac131dcfc2279184c1ce3c4fd2815f Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 29 Jun 2020 14:05:09 +0300 Subject: net: qed: update copyright years Set the actual copyright holder and years in all qed source files. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 1 + include/linux/qed/eth_common.h | 1 + include/linux/qed/fcoe_common.h | 1 + include/linux/qed/iscsi_common.h | 1 + include/linux/qed/iwarp_common.h | 1 + include/linux/qed/qed_chain.h | 1 + include/linux/qed/qed_eth_if.h | 1 + include/linux/qed/qed_fcoe_if.h | 1 + include/linux/qed/qed_if.h | 1 + include/linux/qed/qed_iov_if.h | 1 + include/linux/qed/qed_iscsi_if.h | 1 + include/linux/qed/qed_ll2_if.h | 1 + include/linux/qed/qed_rdma_if.h | 1 + include/linux/qed/qede_rdma.h | 1 + include/linux/qed/rdma_common.h | 1 + include/linux/qed/roce_common.h | 1 + include/linux/qed/storage_common.h | 1 + include/linux/qed/tcp_common.h | 1 + 18 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 294d01eae5cb..977807e1be53 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2016 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _COMMON_HSI_H diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index a9566ef3c2ce..cd1207ad4ada 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ETH_COMMON__ diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index a669d7d84284..68eda1c21cde 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __FCOE_COMMON__ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 7ca89fb9247f..157019f716f1 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ISCSI_COMMON__ diff --git a/include/linux/qed/iwarp_common.h b/include/linux/qed/iwarp_common.h index 23583e644257..14f9e4c0ddd9 100644 --- a/include/linux/qed/iwarp_common.h +++ b/include/linux/qed/iwarp_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __IWARP_COMMON__ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index e6e25197f7cb..92cdc79e5019 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_CHAIN_H diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 7803dedbcb52..812a4d751163 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_ETH_IF_H diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 65d0317ef67e..16752eca5cbd 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_FCOE_IF_H #define _QED_FCOE_IF_H diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4a36608ff3a8..5ca081cd2ed9 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_IF_H diff --git a/include/linux/qed/qed_iov_if.h b/include/linux/qed/qed_iov_if.h index c2ca8196def9..8e31a28e51b9 100644 --- a/include/linux/qed/qed_iov_if.h +++ b/include/linux/qed/qed_iov_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_IOV_IF_H diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 89912c6c440c..04180d9af560 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_ISCSI_IF_H diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 79cac277e38b..2f64ed79cee9 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_LL2_IF_H diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index 041a5b005a82..f464d85e88a4 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef _QED_RDMA_IF_H diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 20ed7f2c55bb..072da2f6da37 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qedr NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef QEDE_ROCE_H diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 3e3f01136c06..bab078b25834 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __RDMA_COMMON__ diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h index 89065f023813..ccddd7a96b67 100644 --- a/include/linux/qed/roce_common.h +++ b/include/linux/qed/roce_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __ROCE_COMMON__ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h index 34f069c79067..91896e8793bf 100644 --- a/include/linux/qed/storage_common.h +++ b/include/linux/qed/storage_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __STORAGE_COMMON__ diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h index 925e7cb7a582..2b2c87d10e0a 100644 --- a/include/linux/qed/tcp_common.h +++ b/include/linux/qed/tcp_common.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation + * Copyright (c) 2019-2020 Marvell International Ltd. */ #ifndef __TCP_COMMON__ -- cgit v1.2.3 From 8b11c20a658de159fcf18ebce4f2acfdf747ff25 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:41 +0200 Subject: phy: un-inline devm_mdiobus_register() Functions should only be static inline if they're very short. This devres helper is already over 10 lines and it will grow soon as we'll be improving upon its approach. Pull it into mdio_devres.c. Signed-off-by: Bartosz Golaszewski Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ecc7640705b9..7c75e1c90141 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -322,20 +322,9 @@ static inline struct mii_bus *mdiobus_alloc(void) } int __mdiobus_register(struct mii_bus *bus, struct module *owner); +int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) -static inline int devm_mdiobus_register(struct mii_bus *bus) -{ - int ret; - - if (!bus->is_managed) - return -EPERM; - - ret = mdiobus_register(bus); - if (!ret) - bus->is_managed_registered = 1; - - return ret; -} +#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); -- cgit v1.2.3 From ac3a68d56651c3dad2c12c7afce065fe15267f44 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:43 +0200 Subject: net: phy: don't abuse devres in devm_mdiobus_register() We currently have two managed helpers for mdiobus - devm_mdiobus_alloc() and devm_mdiobus_register(). The idea behind devres is that the release callback releases whatever resource the devm function allocates. In the mdiobus case however there's no devres associated with the device by devm_mdiobus_register(). Instead the release callback for devm_mdiobus_alloc(): _devm_mdiobus_free() unregisters the device if it is marked as managed. This all seems wrong. The managed structure shouldn't need to know or care about whether it's managed or not - and this is the case now for struct mii_bus. The devres wrapper should be opaque to the managed resource. This changeset makes devm_mdiobus_alloc() and devm_mdiobus_register() conform to common devres standards: devm_mdiobus_alloc() allocates a devres structure and registers a callback that will call mdiobus_free(). __devm_mdiobus_register() allocated another devres and registers a callback that will unregister the bus. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/phy.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7c75e1c90141..101a48fa6750 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -261,9 +261,6 @@ struct mii_bus { int (*reset)(struct mii_bus *bus); struct mdio_bus_stats stats[PHY_MAX_ADDR]; - unsigned int is_managed:1; /* is device-managed */ - unsigned int is_managed_registered:1; - /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time @@ -322,9 +319,11 @@ static inline struct mii_bus *mdiobus_alloc(void) } int __mdiobus_register(struct mii_bus *bus, struct module *owner); -int __devm_mdiobus_register(struct mii_bus *bus, struct module *owner); +int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, + struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) -#define devm_mdiobus_register(bus) __devm_mdiobus_register(bus, THIS_MODULE) +#define devm_mdiobus_register(dev, bus) \ + __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); @@ -335,7 +334,6 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) } struct mii_bus *mdio_find_bus(const char *mdio_name); -void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false -- cgit v1.2.3 From a0bd96f5aed2108505386733abe76f37362c2f50 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:44 +0200 Subject: of: mdio: remove the 'extern' keyword from function declarations The 'extern' keyword in headers doesn't have any benefit. Remove them all from the of_mdio.h header. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 0f61a4ac6bcf..ba8e157f24ad 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,27 +12,26 @@ #include #if IS_ENABLED(CONFIG_OF_MDIO) -extern bool of_mdiobus_child_is_phy(struct device_node *child); -extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -extern struct phy_device *of_phy_find_device(struct device_node *phy_np); -extern struct phy_device *of_phy_connect(struct net_device *dev, - struct device_node *phy_np, - void (*hndlr)(struct net_device *), - u32 flags, phy_interface_t iface); -extern struct phy_device * +bool of_mdiobus_child_is_phy(struct device_node *child); +int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); +struct phy_device *of_phy_find_device(struct device_node *phy_np); +struct phy_device * +of_phy_connect(struct net_device *dev, struct device_node *phy_np, + void (*hndlr)(struct net_device *), u32 flags, + phy_interface_t iface); +struct phy_device * of_phy_get_and_connect(struct net_device *dev, struct device_node *np, void (*hndlr)(struct net_device *)); -struct phy_device *of_phy_attach(struct net_device *dev, - struct device_node *phy_np, u32 flags, - phy_interface_t iface); - -extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); -extern int of_phy_register_fixed_link(struct device_node *np); -extern void of_phy_deregister_fixed_link(struct device_node *np); -extern bool of_phy_is_fixed_link(struct device_node *np); -extern int of_mdiobus_phy_device_register(struct mii_bus *mdio, - struct phy_device *phy, - struct device_node *child, u32 addr); +struct phy_device * +of_phy_attach(struct net_device *dev, struct device_node *phy_np, + u32 flags, phy_interface_t iface); + +struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); +int of_phy_register_fixed_link(struct device_node *np); +void of_phy_deregister_fixed_link(struct device_node *np); +bool of_phy_is_fixed_link(struct device_node *np); +int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, + struct device_node *child, u32 addr); static inline int of_mdio_parse_addr(struct device *dev, const struct device_node *np) -- cgit v1.2.3 From 14eeb6e086d6b9004c600e5f0f62bacb458ecfba Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 29 Jun 2020 14:03:45 +0200 Subject: of: mdio: provide devm_of_mdiobus_register() Implement a managed variant of of_mdiobus_register(). We need to make mdio_devres into its own module because otherwise we'd hit circular sumbol dependencies between phylib and of_mdio. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index ba8e157f24ad..1efb88d9f892 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -8,12 +8,15 @@ #ifndef __LINUX_OF_MDIO_H #define __LINUX_OF_MDIO_H +#include #include #include #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); +int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * of_phy_connect(struct net_device *dev, struct device_node *phy_np, -- cgit v1.2.3 From d141b8bc5773cbbaf5b8530f08f94fc10fff9e8c Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:43 -0700 Subject: perf: Expose get/put_callchain_entry() Sanitize and expose get/put_callchain_entry(). This would be used by bpf stack map. Suggested-by: Peter Zijlstra Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200630062846.664389-2-songliubraving@fb.com --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b4bb32082342..00ab5efa3833 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1244,6 +1244,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); +extern struct perf_callchain_entry *get_callchain_entry(int *rctx); +extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; -- cgit v1.2.3 From fa28dcb82a38f8e3993b0fae9106b1a80b59e4f0 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 29 Jun 2020 23:28:44 -0700 Subject: bpf: Introduce helper bpf_get_task_stack() Introduce helper bpf_get_task_stack(), which dumps stack trace of given task. This is different to bpf_get_stack(), which gets stack track of current task. One potential use case of bpf_get_task_stack() is to call it from bpf_iter__task and dump all /proc//stack to a seq_file. bpf_get_task_stack() uses stack_trace_save_tsk() instead of get_perf_callchain() for kernel stack. The benefit of this choice is that stack_trace_save_tsk() doesn't require changes in arch/. The downside of using stack_trace_save_tsk() is that stack_trace_save_tsk() dumps the stack trace to unsigned long array. For 32-bit systems, we need to translate it to u64 array. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200630062846.664389-3-songliubraving@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3d2ade703a35..0cd7f6884c5c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1627,6 +1627,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; +extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; -- cgit v1.2.3 From b1c7b87443c2c12c4fe095114736b8ad6f963f67 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Jul 2020 19:16:22 +0300 Subject: net: dsa: felix: support half-duplex link modes Ping tested: [ 11.808455] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Full - flow control rx/tx [ 11.816497] IPv6: ADDRCONF(NETDEV_CHANGE): swp0: link becomes ready [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x4 [ 18.844591] mscc_felix 0000:00:00.5 swp0: Link is Down [ 22.048337] mscc_felix 0000:00:00.5 swp0: Link is Up - 100Mbps/Half - flow control off [root@LS1028ARDB ~] # ip addr add 192.168.1.1/24 dev swp0 [root@LS1028ARDB ~] # ping 192.168.1.2 PING 192.168.1.2 (192.168.1.2): 56 data bytes (...) ^C--- 192.168.1.2 ping statistics --- 3 packets transmitted, 3 packets received, 0% packet loss round-trip min/avg/max = 0.383/0.611/1.051 ms [root@LS1028ARDB ~] # ethtool -s swp0 advertise 0x10 [ 355.637747] mscc_felix 0000:00:00.5 swp0: Link is Down [ 358.788034] mscc_felix 0000:00:00.5 swp0: Link is Up - 1Gbps/Half - flow control off [root@LS1028ARDB ~] # ping 192.168.1.2 PING 192.168.1.2 (192.168.1.2): 56 data bytes (...) ^C --- 192.168.1.2 ping statistics --- 16 packets transmitted, 16 packets received, 0% packet loss round-trip min/avg/max = 0.301/0.384/1.138 ms Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/fsl/enetc_mdio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index 4875dd38af7e..2d9203314865 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -15,6 +15,7 @@ #define ENETC_PCS_IF_MODE_SGMII_EN BIT(0) #define ENETC_PCS_IF_MODE_USE_SGMII_AN BIT(1) #define ENETC_PCS_IF_MODE_SGMII_SPEED(x) (((x) << 2) & GENMASK(3, 2)) +#define ENETC_PCS_IF_MODE_DUPLEX_HALF BIT(3) /* Not a mistake, the SerDes PLL needs to be set at 3.125 GHz by Reset * Configuration Word (RCW, outside Linux control) for 2.5G SGMII mode. The PCS -- cgit v1.2.3 From 5ab903418ad14732131df0af0d63f19b73e377ae Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 6 Jul 2020 18:38:19 +0300 Subject: net: qed: sanitize BE/LE data processing Current code assumes that both host and device operates in Little Endian in lots of places. While this is true for x86 platform, this doesn't mean we should not care about this. This commit addresses all parts of the code that were pointed out by sparse checker. All operations with restricted (__be*/__le*) types are now protected with explicit from/to CPU conversions, even if they're noops on common setups. I'm sure there are more such places, but this implies a deeper code investigation, and is a subject for future works. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5ca081cd2ed9..90e1060da02b 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1403,16 +1403,15 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info, enum igu_int_cmd int_cmd, u8 upd_flg) { - struct igu_prod_cons_update igu_ack = { 0 }; + u32 igu_ack; - igu_ack.sb_id_and_flags = - ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | - (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | - (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | - (IGU_SEG_ACCESS_REG << - IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); + igu_ack = ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | + (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | + (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | + (IGU_SEG_ACCESS_REG << + IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); - DIRECT_REG_WR(sb_info->igu_addr, igu_ack.sb_id_and_flags); + DIRECT_REG_WR(sb_info->igu_addr, igu_ack); /* Both segments (interrupts & acks) are written to same place address; * Need to guarantee all commands will be received (in-order) by HW. -- cgit v1.2.3 From 3970ed49a46bd0b062870edcc0894b2bd820371d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 7 Jul 2020 03:49:35 +0200 Subject: net: phy: Properly define genphy_c45_driver Avoid the W=1 warning that symbol 'genphy_c45_driver' was not declared. Should it be static? Declare it on the phy header file. Reviewed-by: Florian Fainelli Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 101a48fa6750..1592c3d0e12f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1385,6 +1385,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); +/* Generic C45 PHY driver */ +extern struct phy_driver genphy_c45_driver; + /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); -- cgit v1.2.3 From 4895d7808e7030c831f2ef83a3cc6ec0d46c30b1 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 5 Jul 2020 21:27:56 -0700 Subject: net: ethtool: Introduce ethtool_phy_ops In order to decouple ethtool from its PHY library dependency, define an ethtool_phy_ops singleton which can be overriden by the PHY library when it loads with an appropriate set of function pointers. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/ethtool.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 48ad3b6a0150..0c139a93b67a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -502,5 +502,30 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd, u32 *dev_speed, u8 *dev_duplex); +struct netlink_ext_ack; +struct phy_device; +struct phy_tdr_config; + +/** + * struct ethtool_phy_ops - Optional PHY device options + * @start_cable_test - Start a cable test + * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test + * + * All operations are optional (i.e. the function pointer may be set to %NULL) + * and callers must take this into account. Callers must hold the RTNL lock. + */ +struct ethtool_phy_ops { + int (*start_cable_test)(struct phy_device *phydev, + struct netlink_ext_ack *extack); + int (*start_cable_test_tdr)(struct phy_device *phydev, + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); +}; + +/** + * ethtool_set_ethtool_phy_ops - Set the ethtool_phy_ops singleton + * @ops: Ethtool PHY operations to set + */ +void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops); #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From f5836749c9c04a10decd2742845ad4870965fdef Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 6 Jul 2020 16:01:25 -0700 Subject: bpf: Add BPF_CGROUP_INET_SOCK_RELEASE hook Sometimes it's handy to know when the socket gets freed. In particular, we'd like to try to use a smarter allocation of ports for bpf_bind and explore the possibility of limiting the number of SOCK_DGRAM sockets the process can have. Implement BPF_CGROUP_INET_SOCK_RELEASE hook that triggers on inet socket release. It triggers only for userspace sockets (not in-kernel ones) and therefore has the same semantics as the existing BPF_CGROUP_INET_SOCK_CREATE. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200706230128.4073544-2-sdf@google.com --- include/linux/bpf-cgroup.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c66c545e161a..2c6f26670acc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -210,6 +210,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_CREATE) +#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ + BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET_SOCK_RELEASE) + #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, BPF_CGROUP_INET4_POST_BIND) @@ -401,6 +404,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) -- cgit v1.2.3 From bd36ed1c935144a0e3b788bba659258f666e7b5b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 8 Jul 2020 09:46:24 -0700 Subject: net: phy: Define PHY statistics ethtool_phy_ops Extend ethtool_phy_ops to include the 3 function pointers necessary for implementing PHY statistics. In a subsequent change we will uninline those functions. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/ethtool.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 0c139a93b67a..969a80211df6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -508,6 +508,9 @@ struct phy_tdr_config; /** * struct ethtool_phy_ops - Optional PHY device options + * @get_sset_count: Get number of strings that @get_strings will write. + * @get_strings: Return a set of strings that describe the requested objects + * @get_stats: Return extended statistics about the PHY device. * @start_cable_test - Start a cable test * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test * @@ -515,6 +518,10 @@ struct phy_tdr_config; * and callers must take this into account. Callers must hold the RTNL lock. */ struct ethtool_phy_ops { + int (*get_sset_count)(struct phy_device *dev); + int (*get_strings)(struct phy_device *dev, u8 *data); + int (*get_stats)(struct phy_device *dev, + struct ethtool_stats *stats, u64 *data); int (*start_cable_test)(struct phy_device *phydev, struct netlink_ext_ack *extack); int (*start_cable_test_tdr)(struct phy_device *phydev, -- cgit v1.2.3 From 17809516a03a045565ad6a80e6241754615871ac Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 8 Jul 2020 09:46:25 -0700 Subject: net: phy: Uninline PHY ethtool statistics operations Now that we have moved the PHY ethtool statistics to be dynamically registered, we no longer need to inline those for ethtool. This used to be done to avoid cross symbol referencing and allow ethtool to be decoupled from PHYLIB entirely. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 49 ++++--------------------------------------------- 1 file changed, 4 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1592c3d0e12f..0403eb799913 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1474,51 +1474,10 @@ int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif -/* Inline function for use within net/core/ethtool.c (built-in) */ -static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_strings(phydev, data); - mutex_unlock(&phydev->lock); - - return 0; -} - -static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) -{ - int ret; - - if (!phydev->drv) - return -EIO; - - if (phydev->drv->get_sset_count && - phydev->drv->get_strings && - phydev->drv->get_stats) { - mutex_lock(&phydev->lock); - ret = phydev->drv->get_sset_count(phydev); - mutex_unlock(&phydev->lock); - - return ret; - } - - return -EOPNOTSUPP; -} - -static inline int phy_ethtool_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, stats, data); - mutex_unlock(&phydev->lock); - - return 0; -} +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); +int phy_ethtool_get_sset_count(struct phy_device *phydev); +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data); static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { -- cgit v1.2.3 From 12fdafb817c6cde87a4fa0e674e66b0226a0889d Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Mon, 6 Jul 2020 20:42:33 -0700 Subject: net/mlx5: Added support for 100Gbps per lane link modes This patch exposes new link modes using 100Gbps per lane, including 100G, 200G and 400G modes. Signed-off-by: Meir Lichtinger Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index de9a272c9f3d..2d45a6af52a4 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -104,8 +104,11 @@ enum mlx5e_ext_link_mode { MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8, MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9, MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10, + MLX5E_100GAUI_1_100GBASE_CR_KR = 11, MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, + MLX5E_200GAUI_2_200GBASE_CR2_KR2 = 13, MLX5E_400GAUI_8 = 15, + MLX5E_400GAUI_4_400GBASE_CR4_KR4 = 16, MLX5E_EXT_LINK_MODES_NUMBER, }; -- cgit v1.2.3 From a2b992c828f7651db369ba8f0eb0818d70232636 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:44 -0700 Subject: debugfs: make sure we can remove u32_array files cleanly debugfs_create_u32_array() allocates a small structure to wrap the data and size information about the array. If users ever try to remove the file this leads to a leak since nothing ever frees this wrapper. That said there are no upstream users of debugfs_create_u32_array() that'd remove a u32 array file (we only have one u32 array user in CMA), so there is no real bug here. Make callers pass a wrapper they allocated. This way the lifetime management of the wrapper is on the caller, and we can avoid the potential leak in debugfs. CC: Chucheng Luo Signed-off-by: Jakub Kicinski Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/debugfs.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 63cb3606dea7..851dd1f9a8a5 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -38,6 +38,11 @@ struct debugfs_regset32 { struct device *dev; /* Optional device for Runtime PM */ }; +struct debugfs_u32_array { + u32 *array; + u32 n_elements; +}; + extern struct dentry *arch_debugfs_dir; #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ @@ -136,7 +141,8 @@ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, u32 elements); + struct dentry *parent, + struct debugfs_u32_array *array); struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, @@ -316,8 +322,8 @@ static inline bool debugfs_initialized(void) } static inline void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, - u32 elements) + struct dentry *parent, + struct debugfs_u32_array *array) { } -- cgit v1.2.3 From cc4e3835eff474aa274d6e1d18f69d9d296d3b76 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jul 2020 17:42:46 -0700 Subject: udp_tunnel: add central NIC RX port offload infrastructure Cater to devices which: (a) may want to sleep in the callbacks; (b) only have IPv4 support; (c) need all the programming to happen while the netdev is up. Drivers attach UDP tunnel offload info struct to their netdevs, where they declare how many UDP ports of various tunnel types they support. Core takes care of tracking which ports to offload. Use a fixed-size array since this matches what almost all drivers do, and avoids a complexity and uncertainty around memory allocations in an atomic context. Make sure that tunnel drivers don't try to replay the ports when new NIC netdev is registered. Automatic replays would mess up reference counting, and will be removed completely once all drivers are converted. v4: - use a #define NULL to avoid build issues with CONFIG_INET=n. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39e28e11863c..ac2cd3f49aba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -65,6 +65,8 @@ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; +struct udp_tunnel_nic_info; +struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; @@ -1836,6 +1838,10 @@ enum netdev_priv_flags { * * @macsec_ops: MACsec offloading ops * + * @udp_tunnel_nic_info: static structure describing the UDP tunnel + * offload capabilities of the device + * @udp_tunnel_nic: UDP tunnel offload state + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2134,6 +2140,8 @@ struct net_device { /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif + const struct udp_tunnel_nic_info *udp_tunnel_nic_info; + struct udp_tunnel_nic *udp_tunnel_nic; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 5a2798ab32ba2952cfe25701ee460bccbd434c75 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 11 Jul 2020 23:53:23 +0200 Subject: bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros Adding support to generate .BTF_ids section that will hold BTF ID lists for verifier. Adding macros that will help to define lists of BTF ID values placed in .BTF_ids section. They are initially filled with zeros (during compilation) and resolved later during the linking phase by resolve_btfids tool. Following defines list of one BTF ID value: BTF_ID_LIST(bpf_skb_output_btf_ids) BTF_ID(struct, sk_buff) It also defines following variable to access the list: extern u32 bpf_skb_output_btf_ids[]; The BTF_ID_UNUSED macro defines 4 zero bytes. It's used when we want to define 'unused' entry in BTF_ID_LIST, like: BTF_ID_LIST(bpf_skb_output_btf_ids) BTF_ID(struct, sk_buff) BTF_ID_UNUSED BTF_ID(struct, task_struct) Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200711215329.41165-4-jolsa@kernel.org --- include/linux/btf_ids.h | 87 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/linux/btf_ids.h (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h new file mode 100644 index 000000000000..fe019774f8a7 --- /dev/null +++ b/include/linux/btf_ids.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_BTF_IDS_H +#define _LINUX_BTF_IDS_H + +#include /* for __PASTE */ + +/* + * Following macros help to define lists of BTF IDs placed + * in .BTF_ids section. They are initially filled with zeros + * (during compilation) and resolved later during the + * linking phase by resolve_btfids tool. + * + * Any change in list layout must be reflected in resolve_btfids + * tool logic. + */ + +#define BTF_IDS_SECTION ".BTF_ids" + +#define ____BTF_ID(symbol) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".local " #symbol " ; \n" \ +".type " #symbol ", @object; \n" \ +".size " #symbol ", 4; \n" \ +#symbol ": \n" \ +".zero 4 \n" \ +".popsection; \n"); + +#define __BTF_ID(symbol) \ + ____BTF_ID(symbol) + +#define __ID(prefix) \ + __PASTE(prefix, __COUNTER__) + +/* + * The BTF_ID defines unique symbol for each ID pointing + * to 4 zero bytes. + */ +#define BTF_ID(prefix, name) \ + __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__)) + +/* + * The BTF_ID_LIST macro defines pure (unsorted) list + * of BTF IDs, with following layout: + * + * BTF_ID_LIST(list1) + * BTF_ID(type1, name1) + * BTF_ID(type2, name2) + * + * list1: + * __BTF_ID__type1__name1__1: + * .zero 4 + * __BTF_ID__type2__name2__2: + * .zero 4 + * + */ +#define __BTF_ID_LIST(name) \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".local " #name "; \n" \ +#name ":; \n" \ +".popsection; \n"); \ + +#define BTF_ID_LIST(name) \ +__BTF_ID_LIST(name) \ +extern u32 name[]; + +/* + * The BTF_ID_UNUSED macro defines 4 zero bytes. + * It's used when we want to define 'unused' entry + * in BTF_ID_LIST, like: + * + * BTF_ID_LIST(bpf_skb_output_btf_ids) + * BTF_ID(struct, sk_buff) + * BTF_ID_UNUSED + * BTF_ID(struct, task_struct) + */ + +#define BTF_ID_UNUSED \ +asm( \ +".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ +".zero 4 \n" \ +".popsection; \n"); + + +#endif -- cgit v1.2.3 From 079ef53673f2e3b3ee1728800311f20f28eed4f7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 14 Jul 2020 12:25:33 +0200 Subject: bpf: Fix build for disabled CONFIG_DEBUG_INFO_BTF option Stephen reported following linker warnings on powerpc build: ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/bpf/btf.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/bpf/stackmap.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `net/core/filter.o' being placed in section `.BTF_ids' ld: warning: orphan section `.BTF_ids' from `kernel/trace/bpf_trace.o' being placed in section `.BTF_ids' It's because we generated .BTF_ids section even when CONFIG_DEBUG_INFO_BTF is not enabled. Fixing this by generating empty btf_id arrays for this case. Reported-by: Stephen Rothwell Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/bpf/20200714102534.299280-1-jolsa@kernel.org --- include/linux/btf_ids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index fe019774f8a7..b3c73db9587c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#ifdef CONFIG_DEBUG_INFO_BTF + #include /* for __PASTE */ /* @@ -83,5 +85,12 @@ asm( \ ".zero 4 \n" \ ".popsection; \n"); +#else + +#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID(prefix, name) +#define BTF_ID_UNUSED + +#endif /* CONFIG_DEBUG_INFO_BTF */ #endif -- cgit v1.2.3 From 11bb2f7a45909f4f64afe471875672ae1b84a380 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 14 Jul 2020 12:25:34 +0200 Subject: bpf: Fix cross build for CONFIG_DEBUG_INFO_BTF option Stephen and 0-DAY CI Kernel Test Service reported broken cross build for arm (arm-linux-gnueabi-gcc (GCC) 9.3.0), with following output: /tmp/ccMS5uth.s: Assembler messages: /tmp/ccMS5uth.s:69: Error: unrecognized symbol type "" /tmp/ccMS5uth.s:82: Error: unrecognized symbol type "" Having '@object' for .type diretive is wrong because '@' is comment character for some architectures. Using STT_OBJECT instead that should work everywhere. Also using HOST* variables to build resolve_btfids so it's properly build in crossbuilds (stolen from objtool's Makefile). Reported-by: kernel test robot Reported-by: Stephen Rothwell Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/bpf/20200714102534.299280-2-jolsa@kernel.org --- include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index b3c73db9587c..1cdb56950ffe 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -23,7 +23,7 @@ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ ".local " #symbol " ; \n" \ -".type " #symbol ", @object; \n" \ +".type " #symbol ", STT_OBJECT; \n" \ ".size " #symbol ", 4; \n" \ #symbol ": \n" \ ".zero 4 \n" \ -- cgit v1.2.3 From 43364ef1a12a4236b7956b076649ddd080764cd1 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 14 Jul 2020 09:34:49 +0200 Subject: bridge: mrp: Extend bridge interface This patch adds a new flag(BR_MRP_LOST_IN_CONT) to the net bridge ports. This bit will be set when the port lost the continuity of MRP_InTest frames. Signed-off-by: Horatiu Vultur Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index b3a8d3054af0..6479a38e52fa 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_ISOLATED BIT(16) #define BR_MRP_AWARE BIT(17) #define BR_MRP_LOST_CONT BIT(18) +#define BR_MRP_LOST_IN_CONT BIT(19) #define BR_DEFAULT_AGEING_TIME (300 * HZ) -- cgit v1.2.3 From 8635764bcf0f109933b593d79ac2247b1e863d0a Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 15 Jul 2020 10:52:03 +0800 Subject: netpoll: Remove unused inline function netpoll_netdev_init() commit d565b0a1a9b6 ("net: Add Generic Receive Offload infrastructure") left behind this, remove it. Signed-off-by: YueHaibing Signed-off-by: David S. Miller --- include/linux/netpoll.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f47af135bd56..e6a2d72e0dc7 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -102,9 +102,6 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi) static inline void netpoll_poll_unlock(void *have) { } -static inline void netpoll_netdev_init(struct net_device *dev) -{ -} static inline bool netpoll_tx_running(struct net_device *dev) { return false; -- cgit v1.2.3 From 0d80b76184ac9f2dfb939e39ad1f961fc006b99d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:38 -0700 Subject: net: qed: drop duplicate words in comments Drop doubled word "the" in two comments. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_chain.h | 2 +- include/linux/qed/qed_if.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 92cdc79e5019..7071dc92b4e2 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -130,7 +130,7 @@ struct qed_chain { } pbl_sp; /* Address of first page of the chain - the address is required - * for fastpath operation [consume/produce] but only for the the SINGLE + * for fastpath operation [consume/produce] but only for the SINGLE * flavour which isn't considered fastpath [== SPQ]. */ void *p_virt_addr; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 90e1060da02b..8a6e3ad436d1 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -498,7 +498,7 @@ struct qed_fcoe_pf_params { u8 bdq_pbl_num_entries[2]; }; -/* Most of the the parameters below are described in the FW iSCSI / TCP HSI */ +/* Most of the parameters below are described in the FW iSCSI / TCP HSI */ struct qed_iscsi_pf_params { u64 glbl_q_params_addr; u64 bdq_pbl_base_addr[3]; -- cgit v1.2.3 From 2ff17117e60572d6974c766d6b1a225ec7d68795 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:39 -0700 Subject: net: skbuff.h: drop duplicate words in comments Drop doubled words in several comments. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0c0377fc00c2..6a82d4a8229e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1328,7 +1328,7 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a - * a map of mapsize to translate enum ip_conntrack_info states + * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void @@ -3812,7 +3812,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * must call this function to return the skb back to the stack with a * timestamp. * - * @skb: clone of the the original outgoing packet + * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ -- cgit v1.2.3 From 158e89639166461e225a855bce6e3ee6cd8bb1c0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:40 -0700 Subject: net: wimax: fix duplicate words in comments Drop doubled words in two comments. Fix a spello/typo. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/wimax/debug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index 4dd2c1cea6a9..cdae052bcdcd 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -184,8 +184,8 @@ do { \ /* - * CPP sintatic sugar to generate A_B like symbol names when one of - * the arguments is a a preprocessor #define. + * CPP syntactic sugar to generate A_B like symbol names when one of + * the arguments is a preprocessor #define. */ #define __D_PASTE__(varname, modulename) varname##_##modulename #define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename)) -- cgit v1.2.3 From 59632b220f2d61df274ed3a14a204e941051fdad Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 09:42:46 -0700 Subject: net: ipv6: drop duplicate word in comment Drop the doubled word "by" in a comment. Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2cb445a8fc9e..8d8f877e7f81 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -223,7 +223,7 @@ struct ipv6_pinfo { /* * Packed in 16bits. - * Omit one shift by by putting the signed field at MSB. + * Omit one shift by putting the signed field at MSB. */ #if defined(__BIG_ENDIAN_BITFIELD) __s16 hop_limit:9; -- cgit v1.2.3 From 9216477449f33cdbc9c9a99d49f500b7fbb81702 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 14 Jul 2020 15:56:38 +0200 Subject: bpf: cpumap: Add the possibility to attach an eBPF program to cpumap Introduce the capability to attach an eBPF program to cpumap entries. The idea behind this feature is to add the possibility to define on which CPU run the eBPF program if the underlying hw does not support RSS. Current supported verdicts are XDP_DROP and XDP_PASS. This patch has been tested on Marvell ESPRESSObin using xdp_redirect_cpu sample available in the kernel tree to identify possible performance regressions. Results show there are no observable differences in packet-per-second: $./xdp_redirect_cpu --progname xdp_cpu_map0 --dev eth0 --cpu 1 rx: 354.8 Kpps rx: 356.0 Kpps rx: 356.8 Kpps rx: 356.3 Kpps rx: 356.6 Kpps rx: 356.6 Kpps rx: 356.7 Kpps rx: 355.8 Kpps rx: 356.8 Kpps rx: 356.8 Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/5c9febdf903d810b3415732e5cd98491d7d9067a.1594734381.git.lorenzo@kernel.org --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c67c88ad35f8..54ad426dbea1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1272,6 +1272,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); +bool cpu_map_prog_allowed(struct bpf_map *map); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1432,6 +1433,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline bool cpu_map_prog_allowed(struct bpf_map *map) +{ + return false; +} + static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { -- cgit v1.2.3 From 9a6ad1ad71fbc5a52617e016a3608d71b91f62e8 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Mon, 18 Nov 2019 14:30:20 +0200 Subject: net/mlx5: Accel, Add core IPsec support for the Connect-X family This to set the base for downstream patches to support the new IPsec implementation of the Connect-X family. Following modifications made: - Remove accel layer dependency from MLX5_FPGA_IPSEC. - Introduce accel_ipsec_ops, each IPsec device will have to support these ops. Signed-off-by: Raed Salem Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 6 +++--- include/linux/mlx5/driver.h | 3 +++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 96ebaa94a92e..dacf69516002 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -126,7 +126,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_FPGA_IPSEC +#ifdef CONFIG_MLX5_ACCEL u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); @@ -152,5 +152,5 @@ static inline int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } -#endif -#endif +#endif /* CONFIG_MLX5_ACCEL */ +#endif /* __MLX5_ACCEL_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e6ca716635a..6a97ad601991 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -707,6 +707,9 @@ struct mlx5_core_dev { } roce; #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; +#endif +#ifdef CONFIG_MLX5_ACCEL + const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; -- cgit v1.2.3 From 78fb6122fa2b6b55fafee1b32cd94913ad72f8a4 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 8 Apr 2020 20:09:05 -0500 Subject: net/mlx5: Add IPsec related Flow steering entry's fields Add FTE actions IPsec ENCRYPT/DECRYPT Add ipsec_obj_id field in FTE Add new action field MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 5 ++++- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++-- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6c5aa0a21425..92d991d93757 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -207,7 +207,10 @@ struct mlx5_flow_act { u32 action; struct mlx5_modify_hdr *modify_hdr; struct mlx5_pkt_reformat *pkt_reformat; - uintptr_t esp_id; + union { + u32 ipsec_obj_id; + uintptr_t esp_id; + }; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 791766e15d5c..9e64710bc54f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 table_miss_action_domain[0x1]; u8 termination_table[0x1]; u8 reformat_and_fwd_to_table[0x1]; - u8 reserved_at_1a[0x6]; + u8 reserved_at_1a[0x2]; + u8 ipsec_encrypt[0x1]; + u8 ipsec_decrypt[0x1]; + u8 reserved_at_1e[0x2]; + u8 termination_table_raw_traffic[0x1]; u8 reserved_at_21[0x1]; u8 log_max_ft_size[0x6]; @@ -2965,6 +2969,8 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH = 0x100, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2 = 0x400, MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, + MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, + MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, }; enum { @@ -3006,7 +3012,8 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan_2; - u8 reserved_at_120[0xe0]; + u8 ipsec_obj_id[0x20]; + u8 reserved_at_140[0xc0]; struct mlx5_ifc_fte_match_param_bits match_value; @@ -5752,6 +5759,7 @@ enum { MLX5_ACTION_IN_FIELD_METADATA_REG_C_7 = 0x58, MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, + MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { -- cgit v1.2.3 From e506addeff844237d60545ef4f6141de21471caf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miguel=20Rodr=C3=ADguez=20P=C3=A9rez?= Date: Wed, 15 Jul 2020 20:40:57 +0200 Subject: net: cdc_ether: export usbnet_cdc_update_filter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This makes the function available to other drivers, like cdc_ncm. Signed-off-by: Miguel Rodríguez Pérez Acked-by: Oliver Neukum Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0bff3083278..3a856963a363 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -207,6 +207,7 @@ struct cdc_state { struct usb_interface *data; }; +extern void usbnet_cdc_update_filter(struct usbnet *dev); extern int usbnet_generic_cdc_bind(struct usbnet *, struct usb_interface *); extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf); extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); -- cgit v1.2.3 From 1ea2b748b5eb4f9b6c8f66d098f1277afb724336 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Wed, 15 Jul 2020 20:40:58 +0200 Subject: net: usbnet: export usbnet_set_rx_mode() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function can be reused by other usbnet minidrivers. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 3a856963a363..2e4f7721fc4e 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -274,6 +274,7 @@ extern int usbnet_set_link_ksettings(struct net_device *net, extern u32 usbnet_get_link(struct net_device *net); extern u32 usbnet_get_msglevel(struct net_device *); extern void usbnet_set_msglevel(struct net_device *, u32); +extern void usbnet_set_rx_mode(struct net_device *net); extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); -- cgit v1.2.3 From ce3aa9cc5109363099b7c4ac82e2c9768afcaf31 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:22 +0200 Subject: bpf, netns: Handle multiple link attachments Extend the BPF netns link callbacks to rebuild (grow/shrink) or update the prog_array at given position when link gets attached/updated/released. This let's us lift the limit of having just one link attached for the new attach type introduced by subsequent patch. No functional changes intended. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200717103536.397595-2-jakub@cloudflare.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54ad426dbea1..c8c9eabcd106 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -928,6 +928,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); +int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); +int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, + struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); -- cgit v1.2.3 From e9ddbb7707ff5891616240026062b8c1e29864ca Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:23 +0200 Subject: bpf: Introduce SK_LOOKUP program type with a dedicated attach point Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer when looking up a listening socket for a new connection request for connection oriented protocols, or when looking up an unconnected socket for a packet for connection-less protocols. When called, SK_LOOKUP BPF program can select a socket that will receive the packet. This serves as a mechanism to overcome the limits of what bind() API allows to express. Two use-cases driving this work are: (1) steer packets destined to an IP range, on fixed port to a socket 192.0.2.0/24, port 80 -> NGINX socket (2) steer packets destined to an IP address, on any port to a socket 198.51.100.1, any port -> L7 proxy socket In its run-time context program receives information about the packet that triggered the socket lookup. Namely IP version, L4 protocol identifier, and address 4-tuple. Context can be further extended to include ingress interface identifier. To select a socket BPF program fetches it from a map holding socket references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...) helper to record the selection. Transport layer then uses the selected socket as a result of socket lookup. In its basic form, SK_LOOKUP acts as a filter and hence must return either SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should look for a socket to receive the packet, or use the one selected by the program if available, while SK_DROP informs the transport layer that the lookup should fail. This patch only enables the user to attach an SK_LOOKUP program to a network namespace. Subsequent patches hook it up to run on local delivery path in ipv4 and ipv6 stacks. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com --- include/linux/bpf-netns.h | 3 +++ include/linux/bpf.h | 1 + include/linux/bpf_types.h | 2 ++ include/linux/filter.h | 17 +++++++++++++++++ 4 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 47d5b0c708c9..722f799c1a2e 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -8,6 +8,7 @@ enum netns_bpf_attach_type { NETNS_BPF_INVALID = -1, NETNS_BPF_FLOW_DISSECTOR = 0, + NETNS_BPF_SK_LOOKUP, MAX_NETNS_BPF_ATTACH_TYPE }; @@ -17,6 +18,8 @@ to_netns_bpf_attach_type(enum bpf_attach_type attach_type) switch (attach_type) { case BPF_FLOW_DISSECTOR: return NETNS_BPF_FLOW_DISSECTOR; + case BPF_SK_LOOKUP: + return NETNS_BPF_SK_LOOKUP; default: return NETNS_BPF_INVALID; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c8c9eabcd106..adb16bdc5f0a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -249,6 +249,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a18ae82a298a..a52a5688418e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, struct sk_reuseport_md, struct sk_reuseport_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup, + struct bpf_sk_lookup, struct bpf_sk_lookup_kern) #endif #if defined(CONFIG_BPF_JIT) BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops, diff --git a/include/linux/filter.h b/include/linux/filter.h index 0b0144752d78..fa1ea12ad2cd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1278,4 +1278,21 @@ struct bpf_sockopt_kern { s32 retval; }; +struct bpf_sk_lookup_kern { + u16 family; + u16 protocol; + struct { + __be32 saddr; + __be32 daddr; + } v4; + struct { + const struct in6_addr *saddr; + const struct in6_addr *daddr; + } v6; + __be16 sport; + u16 dport; + struct sock *selected_sk; + bool no_reuseport; +}; + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 1559b4aa1db443096af493c7d621dc156054babe Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:25 +0200 Subject: inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com --- include/linux/filter.h | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index fa1ea12ad2cd..c4f54c216347 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1295,4 +1295,95 @@ struct bpf_sk_lookup_kern { bool no_reuseport; }; +extern struct static_key_false bpf_sk_lookup_enabled; + +/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. + * + * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and + * SK_DROP. Their meaning is as follows: + * + * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result + * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup + * SK_DROP : terminate lookup with -ECONNREFUSED + * + * This macro aggregates return values and selected sockets from + * multiple BPF programs according to following rules in order: + * + * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, + * macro result is SK_PASS and last ctx.selected_sk is used. + * 2. If any program returned SK_DROP return value, + * macro result is SK_DROP. + * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. + * + * Caller must ensure that the prog array is non-NULL, and that the + * array as well as the programs it contains remain valid. + */ +#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_sk_lookup_kern *_ctx = &(ctx); \ + struct bpf_prog_array_item *_item; \ + struct sock *_selected_sk = NULL; \ + bool _no_reuseport = false; \ + struct bpf_prog *_prog; \ + bool _all_pass = true; \ + u32 _ret; \ + \ + migrate_disable(); \ + _item = &(array)->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + /* restore most recent selection */ \ + _ctx->selected_sk = _selected_sk; \ + _ctx->no_reuseport = _no_reuseport; \ + \ + _ret = func(_prog, _ctx); \ + if (_ret == SK_PASS && _ctx->selected_sk) { \ + /* remember last non-NULL socket */ \ + _selected_sk = _ctx->selected_sk; \ + _no_reuseport = _ctx->no_reuseport; \ + } else if (_ret == SK_DROP && _all_pass) { \ + _all_pass = false; \ + } \ + _item++; \ + } \ + _ctx->selected_sk = _selected_sk; \ + _ctx->no_reuseport = _no_reuseport; \ + migrate_enable(); \ + _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ + }) + +static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, + const __be32 saddr, const __be16 sport, + const __be32 daddr, const u16 dport, + struct sock **psk) +{ + struct bpf_prog_array *run_array; + struct sock *selected_sk = NULL; + bool no_reuseport = false; + + rcu_read_lock(); + run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); + if (run_array) { + struct bpf_sk_lookup_kern ctx = { + .family = AF_INET, + .protocol = protocol, + .v4.saddr = saddr, + .v4.daddr = daddr, + .sport = sport, + .dport = dport, + }; + u32 act; + + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + if (act == SK_PASS) { + selected_sk = ctx.selected_sk; + no_reuseport = ctx.no_reuseport; + } else { + selected_sk = ERR_PTR(-ECONNREFUSED); + } + } + rcu_read_unlock(); + *psk = selected_sk; + return no_reuseport; +} + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 1122702f02678597c4f1c7d316365ef502aafe08 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Fri, 17 Jul 2020 12:35:27 +0200 Subject: inet6: Run SK_LOOKUP BPF program on socket lookup Following ipv4 stack changes, run a BPF program attached to netns before looking up a listening socket. Program can return a listening socket to use as result of socket lookup, fail the lookup, or take no action. Suggested-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200717103536.397595-7-jakub@cloudflare.com --- include/linux/filter.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index c4f54c216347..8252572db918 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1386,4 +1386,43 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, return no_reuseport; } +#if IS_ENABLED(CONFIG_IPV6) +static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, + const struct in6_addr *saddr, + const __be16 sport, + const struct in6_addr *daddr, + const u16 dport, + struct sock **psk) +{ + struct bpf_prog_array *run_array; + struct sock *selected_sk = NULL; + bool no_reuseport = false; + + rcu_read_lock(); + run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); + if (run_array) { + struct bpf_sk_lookup_kern ctx = { + .family = AF_INET6, + .protocol = protocol, + .v6.saddr = saddr, + .v6.daddr = daddr, + .sport = sport, + .dport = dport, + }; + u32 act; + + act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); + if (act == SK_PASS) { + selected_sk = ctx.selected_sk; + no_reuseport = ctx.no_reuseport; + } else { + selected_sk = ERR_PTR(-ECONNREFUSED); + } + } + rcu_read_unlock(); + *psk = selected_sk; + return no_reuseport; +} +#endif /* IS_ENABLED(CONFIG_IPV6) */ + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From a06d30ae7af492497ffbca6abf1621d508b8fcaa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:10 +0200 Subject: net/atm: remove the atmdev_ops {get, set}sockopt methods All implementations of these two methods are dummies that always return -EINVAL. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/atmdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 8124815eb121..5d5ff2203fa2 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -176,11 +176,6 @@ struct atm_dev { #define ATM_OF_IMMED 1 /* Attempt immediate delivery */ #define ATM_OF_INRATE 2 /* Attempt in-rate delivery */ - -/* - * ioctl, getsockopt, and setsockopt are optional and can be set to NULL. - */ - struct atmdev_ops { /* only send is required */ void (*dev_close)(struct atm_dev *dev); int (*open)(struct atm_vcc *vcc); @@ -190,10 +185,6 @@ struct atmdev_ops { /* only send is required */ int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd, void __user *arg); #endif - int (*getsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen); - int (*setsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,unsigned int optlen); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); void (*phy_put)(struct atm_dev *dev,unsigned char value, -- cgit v1.2.3 From 4d295e54611509854a12c26f95a6f4430731d614 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:13 +0200 Subject: net: simplify cBPF setsockopt compat handling Add a helper that copies either a native or compat bpf_fprog from userspace after verifying the length, and remove the compat setsockopt handlers that now aren't required. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/filter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 0b0144752d78..4d049c8e1fbe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -502,13 +502,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) offsetof(TYPE, MEMBER); \ }) -#ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; -#endif struct sock_fprog_kern { u16 len; @@ -1278,4 +1276,6 @@ struct bpf_sockopt_kern { s32 retval; }; +int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len); + #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 8c918ffbbad49454ed26c53eb1b90bf98bb5e394 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:14 +0200 Subject: net: remove compat_sock_common_{get,set}sockopt Add the compat handling to sock_common_{get,set}sockopt instead, keyed of in_compat_syscall(). This allow to remove the now unused ->compat_{get,set}sockopt methods from struct proto_ops. Signed-off-by: Christoph Hellwig Acked-by: Matthieu Baerts Acked-by: Stefan Schmidt Signed-off-by: David S. Miller --- include/linux/net.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 016a9c5faa34..858ff1d98154 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -165,12 +165,6 @@ struct proto_ops { int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -#ifdef CONFIG_COMPAT - int (*compat_setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen); - int (*compat_getsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int __user *optlen); -#endif void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); -- cgit v1.2.3 From 55db9c0e853421fa71cac5e6855898601f78a1f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:15 +0200 Subject: net: remove compat_sys_{get,set}sockopt Now that the ->compat_{get,set}sockopt proto_ops methods are gone there is no good reason left to keep the compat syscalls separate. This fixes the odd use of unsigned int for the compat_setsockopt optlen and the missing sock_use_custom_sol_socket. It would also easily allow running the eBPF hooks for the compat syscalls, but such a large change in behavior does not belong into a consolidation patch like this one. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/compat.h | 4 ---- include/linux/syscalls.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index e90100c0de72..c4255d8a4a8a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -737,10 +737,6 @@ asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned flags, struct sockaddr __user *addr, int __user *addrlen); -asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, unsigned int optlen); -asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b951a87da987..aa46825c6f9d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1424,4 +1424,8 @@ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout); +int __sys_getsockopt(int fd, int level, int optname, char __user *optval, + int __user *optlen); +int __sys_setsockopt(int fd, int level, int optname, char __user *optval, + int optlen); #endif -- cgit v1.2.3 From 77d4df41d53e5c2af14db26f20fe50da52e382ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:20 +0200 Subject: netfilter: remove the compat_{get,set} methods All instances handle compat sockopts via in_compat_syscall() now, so remove the compat_{get,set} methods as well as the compat_nf_{get,set}sockopt wrappers. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index eb312e7ca36e..711b4d4486f0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -164,17 +164,9 @@ struct nf_sockopt_ops { int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); -#ifdef CONFIG_COMPAT - int (*compat_set)(struct sock *sk, int optval, - void __user *user, unsigned int len); -#endif int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); -#ifdef CONFIG_COMPAT - int (*compat_get)(struct sock *sk, int optval, - void __user *user, int *len); -#endif /* Use the module struct to lock set/get code in place */ struct module *owner; }; @@ -350,12 +342,6 @@ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -#ifdef CONFIG_COMPAT -int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, unsigned int len); -int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int *len); -#endif struct flowi; struct nf_queue_entry; -- cgit v1.2.3 From c34bc10d2535719ddf77d44ee849f6c7589583ba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 17 Jul 2020 08:23:21 +0200 Subject: netfilter: remove the compat argument to xt_copy_counters_from_user Lift the in_compat_syscall() from the callers instead. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5da88451853b..b8b943ee7b8b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -302,7 +302,7 @@ int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters_from_user(const void __user *user, unsigned int len, - struct xt_counters_info *info, bool compat); + struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, -- cgit v1.2.3 From eba75c587e811d3249c8bd50d22bb2266ccd3c0f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 10 Jul 2020 09:29:02 -0400 Subject: icmp: support rfc 4884 Add setsockopt SOL_IP/IP_RECVERR_4884 to return the offset to an extension struct if present. ICMP messages may include an extension structure after the original datagram. RFC 4884 standardized this behavior. It stores the offset in words to the extension header in u8 icmphdr.un.reserved[1]. The field is valid only for ICMP types destination unreachable, time exceeded and parameter problem, if length is at least 128 bytes and entire packet does not exceed 576 bytes. Return the offset to the start of the extension struct when reading an ICMP error from the error queue, if it matches the above constraints. Do not return the raw u8 field. Return the offset from the start of the user buffer, in bytes. The kernel does not return the network and transport headers, so subtract those. Also validate the headers. Return the offset regardless of validation, as an invalid extension must still not be misinterpreted as part of the original datagram. Note that !invalid does not imply valid. If the extension version does not match, no validation can take place, for instance. For backward compatibility, make this optional, set by setsockopt SOL_IP/IP_RECVERR_RFC4884. For API example and feature test, see github.com/wdebruij/kerneltools/blob/master/tests/recv_icmp_v2.c For forward compatibility, reserve only setsockopt value 1, leaving other bits for additional icmp extensions. Changes v1->v2: - convert word offset to byte offset from start of user buffer - return in ee_data as u8 may be insufficient - define extension struct and object header structs - return len only if constraints met - if returning len, also validate Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/icmp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 81ca84ce3119..8fc38a34cb20 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -15,6 +15,7 @@ #include #include +#include static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { @@ -35,4 +36,7 @@ static inline bool icmp_is_err(int type) return false; } +void ip_icmp_error_rfc4884(const struct sk_buff *skb, + struct sock_ee_data_rfc4884 *out); + #endif /* _LINUX_ICMP_H */ -- cgit v1.2.3 From a8b7b2d0b3fc965d823e362840e5451e2eb4a71b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 20 Jul 2020 10:10:41 +0200 Subject: sched: sch_api: add missing rcu read lock to silence the warning In case the qdisc_match_from_root function() is called from non-rcu path with rtnl mutex held, a suspiciout rcu usage warning appears: [ 241.504354] ============================= [ 241.504358] WARNING: suspicious RCU usage [ 241.504366] 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 Not tainted [ 241.504370] ----------------------------- [ 241.504378] net/sched/sch_api.c:270 RCU-list traversed in non-reader section!! [ 241.504382] other info that might help us debug this: [ 241.504388] rcu_scheduler_active = 2, debug_locks = 1 [ 241.504394] 1 lock held by tc/1391: [ 241.504398] #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0 [ 241.504431] stack backtrace: [ 241.504440] CPU: 0 PID: 1391 Comm: tc Not tainted 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 [ 241.504446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014 [ 241.504453] Call Trace: [ 241.504465] dump_stack+0x100/0x184 [ 241.504482] lockdep_rcu_suspicious+0x153/0x15d [ 241.504499] qdisc_match_from_root+0x293/0x350 Fix this by passing the rtnl held lockdep condition down to hlist_for_each_entry_rcu() Reported-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/hashtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 78b6ea5fa8ba..f6c666730b8c 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -173,9 +173,9 @@ static inline void hash_del_rcu(struct hlist_node *node) * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_rcu(name, obj, member, key) \ +#define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ - member) + member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing -- cgit v1.2.3 From e812916d3278baf03aabf10044661fc3b2848823 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:00 +0300 Subject: linkmode: introduce linkmode_intersects() Add a new helper to find intersections between Ethtool link modes, linkmode_intersects(), similar to the other linkmode helpers. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/linkmode.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index c664c27a29a0..f8397f300fcd 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -82,6 +82,12 @@ static inline int linkmode_equal(const unsigned long *src1, return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline int linkmode_intersects(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_intersects(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + static inline int linkmode_subset(const unsigned long *src1, const unsigned long *src2) { -- cgit v1.2.3 From bdb5d8ec47611ca61e168349f233e1dd1ed063f4 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:01 +0300 Subject: qed, qede, qedf: convert link mode from u32 to ETHTOOL_LINK_MODE Currently qed driver already ran out of 32 bits to store link modes, and this doesn't allow to add and support more speeds. Convert custom link mode to generic Ethtool bitmap and definitions (convenient Phylink shorthands are used for elegance and readability). This allowed us to drop all conversions/mappings between the driver and Ethtool. This involves changes in qede and qedf as well, as they used definitions from shared "qed_if.h". Suggested-by: Andrew Lunn Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 47 ++++++---------------------------------------- 1 file changed, 6 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8a6e3ad436d1..f82db1b92d45 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -661,42 +661,6 @@ enum qed_protocol { QED_PROTOCOL_FCOE, }; -enum qed_link_mode_bits { - QED_LM_FIBRE_BIT = BIT(0), - QED_LM_Autoneg_BIT = BIT(1), - QED_LM_Asym_Pause_BIT = BIT(2), - QED_LM_Pause_BIT = BIT(3), - QED_LM_1000baseT_Full_BIT = BIT(4), - QED_LM_10000baseT_Full_BIT = BIT(5), - QED_LM_10000baseKR_Full_BIT = BIT(6), - QED_LM_20000baseKR2_Full_BIT = BIT(7), - QED_LM_25000baseKR_Full_BIT = BIT(8), - QED_LM_40000baseLR4_Full_BIT = BIT(9), - QED_LM_50000baseKR2_Full_BIT = BIT(10), - QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_TP_BIT = BIT(12), - QED_LM_Backplane_BIT = BIT(13), - QED_LM_1000baseKX_Full_BIT = BIT(14), - QED_LM_10000baseKX4_Full_BIT = BIT(15), - QED_LM_10000baseR_FEC_BIT = BIT(16), - QED_LM_40000baseKR4_Full_BIT = BIT(17), - QED_LM_40000baseCR4_Full_BIT = BIT(18), - QED_LM_40000baseSR4_Full_BIT = BIT(19), - QED_LM_25000baseCR_Full_BIT = BIT(20), - QED_LM_25000baseSR_Full_BIT = BIT(21), - QED_LM_50000baseCR2_Full_BIT = BIT(22), - QED_LM_100000baseSR4_Full_BIT = BIT(23), - QED_LM_100000baseCR4_Full_BIT = BIT(24), - QED_LM_100000baseLR4_ER4_Full_BIT = BIT(25), - QED_LM_50000baseSR2_Full_BIT = BIT(26), - QED_LM_1000baseX_Full_BIT = BIT(27), - QED_LM_10000baseCR_Full_BIT = BIT(28), - QED_LM_10000baseSR_Full_BIT = BIT(29), - QED_LM_10000baseLR_Full_BIT = BIT(30), - QED_LM_10000baseLRM_Full_BIT = BIT(31), - QED_LM_COUNT = 32 -}; - struct qed_link_params { bool link_up; @@ -708,7 +672,9 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; - u32 adv_speeds; + + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); + u32 forced_speed; #define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) #define QED_LINK_PAUSE_RX_ENABLE BIT(1) @@ -726,10 +692,9 @@ struct qed_link_params { struct qed_link_output { bool link_up; - /* In QED_LM_* defs */ - u32 supported_caps; - u32 advertised_caps; - u32 lp_caps; + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps); u32 speed; /* In Mb/s */ u8 duplex; /* In DUPLEX defs */ -- cgit v1.2.3 From 37237b5b7104f91b519133d7862d1b5169a3ba8e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:06 +0300 Subject: qed: reformat several structures a bit Prior to adding new fields and bitfields, reformat the related structures according to the Linux style (spaces to tabs, lowercase hex, indentation etc.). Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 64 ++++++++++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f82db1b92d45..dde48f206d0d 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -662,51 +662,53 @@ enum qed_protocol { }; struct qed_link_params { - bool link_up; + bool link_up; -#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) -#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) -#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) -#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) -#define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) -#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) - u32 override_flags; - bool autoneg; + u32 override_flags; +#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) +#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) +#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) +#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) +#define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) + bool autoneg; __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); + u32 forced_speed; - u32 forced_speed; -#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) -#define QED_LINK_PAUSE_RX_ENABLE BIT(1) -#define QED_LINK_PAUSE_TX_ENABLE BIT(2) - u32 pause_config; -#define QED_LINK_LOOPBACK_NONE BIT(0) -#define QED_LINK_LOOPBACK_INT_PHY BIT(1) -#define QED_LINK_LOOPBACK_EXT_PHY BIT(2) -#define QED_LINK_LOOPBACK_EXT BIT(3) -#define QED_LINK_LOOPBACK_MAC BIT(4) - u32 loopback_mode; - struct qed_link_eee_params eee; + u32 pause_config; +#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) +#define QED_LINK_PAUSE_RX_ENABLE BIT(1) +#define QED_LINK_PAUSE_TX_ENABLE BIT(2) + + u32 loopback_mode; +#define QED_LINK_LOOPBACK_NONE BIT(0) +#define QED_LINK_LOOPBACK_INT_PHY BIT(1) +#define QED_LINK_LOOPBACK_EXT_PHY BIT(2) +#define QED_LINK_LOOPBACK_EXT BIT(3) +#define QED_LINK_LOOPBACK_MAC BIT(4) + + struct qed_link_eee_params eee; }; struct qed_link_output { - bool link_up; + bool link_up; __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_caps); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised_caps); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_caps); - u32 speed; /* In Mb/s */ - u8 duplex; /* In DUPLEX defs */ - u8 port; /* In PORT defs */ - bool autoneg; - u32 pause_config; + u32 speed; /* In Mb/s */ + u8 duplex; /* In DUPLEX defs */ + u8 port; /* In PORT defs */ + bool autoneg; + u32 pause_config; /* EEE - capability & param */ - bool eee_supported; - bool eee_active; - u8 sup_caps; - struct qed_link_eee_params eee; + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { -- cgit v1.2.3 From ae7e69379fd5a87141fd8c7f2efab8e73f2a9f7e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:07 +0300 Subject: qed: add support for Forward Error Correction Add all necessary routines for reading supported FEC modes from NVM and querying FEC control to the MFW (if the running version supports it). Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dde48f206d0d..f0b4cdc79299 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -661,6 +661,14 @@ enum qed_protocol { QED_PROTOCOL_FCOE, }; +enum qed_fec_mode { + QED_FEC_MODE_NONE = BIT(0), + QED_FEC_MODE_FIRECODE = BIT(1), + QED_FEC_MODE_RS = BIT(2), + QED_FEC_MODE_AUTO = BIT(3), + QED_FEC_MODE_UNSUPPORTED = BIT(4), +}; + struct qed_link_params { bool link_up; @@ -671,6 +679,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) #define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) +#define QED_LINK_OVERRIDE_FEC_CONFIG BIT(6) bool autoneg; __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_speeds); @@ -689,6 +698,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_MAC BIT(4) struct qed_link_eee_params eee; + u32 fec; }; struct qed_link_output { @@ -709,6 +719,9 @@ struct qed_link_output { bool eee_active; u8 sup_caps; struct qed_link_eee_params eee; + + u32 sup_fec; + u32 active_fec; }; struct qed_probe_params { -- cgit v1.2.3 From 98e675ec5a92a15f6f8ade41eda883cd39df5712 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:13 +0300 Subject: qed: add missing loopback modes These modes are relevant only for several boards, but may be reported by MFW as well as the others. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f0b4cdc79299..2e780159a5fb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -696,6 +696,11 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT_PHY BIT(2) #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) +#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_0123 BIT(5) +#define QED_LINK_LOOPBACK_CNIG_AH_ONLY_2301 BIT(6) +#define QED_LINK_LOOPBACK_PCS_AH_ONLY BIT(7) +#define QED_LINK_LOOPBACK_REVERSE_MAC_AH_ONLY BIT(8) +#define QED_LINK_LOOPBACK_INT_PHY_FEA_AH_ONLY BIT(9) struct qed_link_eee_params eee; u32 fec; -- cgit v1.2.3 From 99785a87fc7d27207c7dca0f0fe04386f1981690 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 20 Jul 2020 21:08:15 +0300 Subject: qed: add support for the extended speed and FEC modes Add all necessary code (NVM parsing, MFW and Ethtool reports etc.) to support extended speed and FEC modes. These new modes are supported by the new boards revisions and newer MFW versions. Misc: correct port type for MEDIA_KR. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 2e780159a5fb..a5c6854343e6 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -594,6 +594,7 @@ enum qed_hw_err_type { enum qed_dev_type { QED_DEV_TYPE_BB, QED_DEV_TYPE_AH, + QED_DEV_TYPE_E5, }; struct qed_dev_info { -- cgit v1.2.3 From bc4f0548f683a3d53359cef15f088d2d5bb4bc39 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:33:58 -0700 Subject: bpf: Compute bpf_skc_to_*() helper socket btf ids at build time Currently, socket types (struct tcp_sock, udp_sock, etc.) used by bpf_skc_to_*() helpers are computed when vmlinux_btf is first built in the kernel. Commit 5a2798ab32ba ("bpf: Add BTF_ID_LIST/BTF_ID/BTF_ID_UNUSED macros") implemented a mechanism to compute btf_ids at kernel build time which can simplify kernel implementation and reduce runtime overhead by removing in-kernel btf_id calculation. This patch did exactly this, removing in-kernel btf_id computation and utilizing build-time btf_id computation. If CONFIG_DEBUG_INFO_BTF is not defined, BTF_ID_LIST will define an array with size of 5, which is not enough for btf_sock_ids. So define its own static array if CONFIG_DEBUG_INFO_BTF is not defined. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163358.1393023-1-yhs@fb.com --- include/linux/bpf.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index adb16bdc5f0a..1df1c0fd3f28 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1541,7 +1541,6 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); -void init_btf_sock_ids(struct btf *btf); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1567,9 +1566,6 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } -static inline void init_btf_sock_ids(struct btf *btf) -{ -} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -- cgit v1.2.3 From 0f12e584b241285cf60a6227f3771fa444cfcf76 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:01 -0700 Subject: bpf: Add BTF_ID_LIST_GLOBAL in btf_ids.h Existing BTF_ID_LIST used a local static variable to store btf_ids. This patch provided a new macro BTF_ID_LIST_GLOBAL to store btf_ids in a global variable which can be shared among multiple files. The existing BTF_ID_LIST is still retained. Two reasons. First, BTF_ID_LIST is also used to build btf_ids for helper arguments which typically is an array of 5. Since typically different helpers have different signature, it makes little sense to share them. Second, some current computed btf_ids are indeed local. If later those btf_ids are shared between different files, they can use BTF_ID_LIST_GLOBAL then. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20200720163401.1393159-1-yhs@fb.com --- include/linux/btf_ids.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 1cdb56950ffe..77ab45baa095 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -57,17 +57,20 @@ asm( \ * .zero 4 * */ -#define __BTF_ID_LIST(name) \ +#define __BTF_ID_LIST(name, scope) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ -".local " #name "; \n" \ +"." #scope " " #name "; \n" \ #name ":; \n" \ ".popsection; \n"); \ #define BTF_ID_LIST(name) \ -__BTF_ID_LIST(name) \ +__BTF_ID_LIST(name, local) \ extern u32 name[]; +#define BTF_ID_LIST_GLOBAL(name) \ +__BTF_ID_LIST(name, globl) + /* * The BTF_ID_UNUSED macro defines 4 zero bytes. * It's used when we want to define 'unused' entry @@ -90,6 +93,7 @@ asm( \ #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED +#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From fce557bcef119a1bc5ab3cb02678cf454bcaf424 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:02 -0700 Subject: bpf: Make btf_sock_ids global tcp and udp bpf_iter can reuse some socket ids in btf_sock_ids, so make it global. I put the extern definition in btf_ids.h as a central place so it can be easily discovered by developers. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163402.1393427-1-yhs@fb.com --- include/linux/btf_ids.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 77ab45baa095..4867d549e3c1 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -97,4 +97,34 @@ asm( \ #endif /* CONFIG_DEBUG_INFO_BTF */ +#ifdef CONFIG_NET +/* Define a list of socket types which can be the argument for + * skc_to_*_sock() helpers. All these sockets should have + * sock_common as the first argument in its memory layout. + */ +#define BTF_SOCK_TYPE_xxx \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) + +enum { +#define BTF_SOCK_TYPE(name, str) name, +BTF_SOCK_TYPE_xxx +#undef BTF_SOCK_TYPE +MAX_BTF_SOCK_TYPE, +}; + +extern u32 btf_sock_ids[]; +#endif + #endif -- cgit v1.2.3 From 951cf368bcb11d6f817709660cf5cd914072c36f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 20 Jul 2020 09:34:03 -0700 Subject: bpf: net: Use precomputed btf_id for bpf iterators One additional field btf_id is added to struct bpf_ctx_arg_aux to store the precomputed btf_ids. The btf_id is computed at build time with BTF_ID_LIST or BTF_ID_LIST_GLOBAL macro definitions. All existing bpf iterators are changed to used pre-compute btf_ids. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200720163403.1393551-1-yhs@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1df1c0fd3f28..bae557ff2da8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -668,6 +668,7 @@ struct bpf_jit_poke_descriptor { struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; + u32 btf_id; }; struct bpf_prog_aux { -- cgit v1.2.3 From 1571e700fd610c39e8b50b0110b1ee9badb2fe6a Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:36 +0100 Subject: net: phylink: in-band pause mode advertisement update for PCS Re-code the pause in-band advertisement update in light of the addition of PCS support, so that we perform the minimum required; only the PCS configuration function needs to be called in this case, followed by the request to trigger a restart of negotiation if the programmed advertisement changed. We need to change the pcs_config() signature to pass whether resolved pause should be passed to the MAC for setups such as mvneta and mvpp2 where doing so overrides the MAC manual flow controls. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index b32b8b45421b..d9913d8e6b91 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -286,7 +286,8 @@ struct phylink_pcs_ops { struct phylink_link_state *state); int (*pcs_config)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, - const unsigned long *advertising); + const unsigned long *advertising, + bool permit_pause_to_mac); void (*pcs_an_restart)(struct phylink_config *config); void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, int speed, int duplex); @@ -317,9 +318,11 @@ void pcs_get_state(struct phylink_config *config, * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @interface: interface mode to be used * @advertising: adertisement ethtool link mode mask + * @permit_pause_to_mac: permit forwarding pause resolution to MAC * * Configure the PCS for the operating mode, the interface mode, and set - * the advertisement mask. + * the advertisement mask. @permit_pause_to_mac indicates whether the + * hardware may forward the pause mode resolution to the MAC. * * When operating in %MLO_AN_INBAND, inband should always be enabled, * otherwise inband should be disabled. -- cgit v1.2.3 From b7ad14c2fe2d4b2abee491e3adfa3d0123aa2d8c Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:41 +0100 Subject: net: phylink: re-implement interface configuration with PCS With PCS support, how we implement interface reconfiguration (or other major reconfiguration) is not up to the job; we end up reconfiguring the PCS for an interface change while the link could potentially be up. In order to solve this, add two additional MAC methods for major configuration, one to prepare for the change, and one to finish the change. This allows mvneta and mvpp2 to shutdown what they require prior to the MAC and PCS configuration calls, and then restart as appropriate. This impacts ksettings_set(), which now needs to identify whether the change is a minor tweak to the advertisement masks or whether the interface mode has changed, and call the appropriate function for that update. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index d9913d8e6b91..2f1315f32113 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -76,7 +76,9 @@ struct phylink_config { * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. * @mac_pcs_get_state: Read the current link state from the hardware. + * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. + * @mac_finish: finish a major reconfiguration of the interface. * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. @@ -89,8 +91,12 @@ struct phylink_mac_ops { struct phylink_link_state *state); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); + int (*mac_prepare)(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); + int (*mac_finish)(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); @@ -145,6 +151,31 @@ void validate(struct phylink_config *config, unsigned long *supported, void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); +/** + * mac_prepare() - prepare to change the PHY interface mode + * @config: a pointer to a &struct phylink_config. + * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. + * @iface: interface mode to switch to + * + * phylink will call this method at the beginning of a full initialisation + * of the link, which includes changing the interface mode or at initial + * startup time. It may be called for the current mode. The MAC driver + * should perform whatever actions are required, e.g. disabling the + * Serdes PHY. + * + * This will be the first call in the sequence: + * - mac_prepare() + * - mac_config() + * - pcs_config() + * - possible pcs_an_restart() + * - mac_finish() + * + * Returns zero on success, or negative errno on failure which will be + * reported to the kernel log. + */ +int mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); + /** * mac_config() - configure the MAC for the selected mode and state * @config: a pointer to a &struct phylink_config. @@ -220,6 +251,23 @@ void mac_pcs_get_state(struct phylink_config *config, void mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); +/** + * mac_finish() - finish a to change the PHY interface mode + * @config: a pointer to a &struct phylink_config. + * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. + * @iface: interface mode to switch to + * + * phylink will call this if it called mac_prepare() to allow the MAC to + * complete any necessary steps after the MAC and PCS have been configured + * for the @mode and @iface. E.g. a MAC driver may wish to re-enable the + * Serdes PHY here if it was previously disabled by mac_prepare(). + * + * Returns zero on success, or negative errno on failure which will be + * reported to the kernel log. + */ +int mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t iface); + /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. -- cgit v1.2.3 From 7137e18f6f889a67046d5004e1690a32d7d2108d Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:46 +0100 Subject: net: phylink: add struct phylink_pcs Add a way for MAC PCS to have private data while keeping independence from struct phylink_config, which is used for the MAC itself. We need this independence as we will have stand-alone code for PCS that is independent of the MAC. Introduce struct phylink_pcs, which is designed to be embedded in a driver private data structure. This structure does not include a mdio_device as there are PCS implementations such as the Marvell DSA and network drivers where this is not necessary. Reviewed-by: Ioana Ciornei Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 45 ++++++++++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2f1315f32113..057f78263a46 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -321,6 +321,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy, int speed, int duplex, bool tx_pause, bool rx_pause); #endif +struct phylink_pcs_ops; + +/** + * struct phylink_pcs - PHYLINK PCS instance + * @ops: a pointer to the &struct phylink_pcs_ops structure + * @poll: poll the PCS for link changes + * + * This structure is designed to be embedded within the PCS private data, + * and will be passed between phylink and the PCS. + */ +struct phylink_pcs { + const struct phylink_pcs_ops *ops; + bool poll; +}; + /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_get_state: read the current MAC PCS link state from the hardware. @@ -330,21 +345,21 @@ void mac_link_up(struct phylink_config *config, struct phy_device *phy, * (where necessary). */ struct phylink_pcs_ops { - void (*pcs_get_state)(struct phylink_config *config, + void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); - int (*pcs_config)(struct phylink_config *config, unsigned int mode, + int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising, bool permit_pause_to_mac); - void (*pcs_an_restart)(struct phylink_config *config); - void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, + void (*pcs_an_restart)(struct phylink_pcs *pcs); + void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); }; #if 0 /* For kernel-doc purposes only. */ /** * pcs_get_state() - Read the current inband link state from the hardware - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. * * Read the current inband link state from the MAC PCS, reporting the @@ -357,12 +372,12 @@ struct phylink_pcs_ops { * When present, this overrides mac_pcs_get_state() in &struct * phylink_mac_ops. */ -void pcs_get_state(struct phylink_config *config, +void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); /** * pcs_config() - Configure the PCS mode and advertisement - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @interface: interface mode to be used * @advertising: adertisement ethtool link mode mask @@ -382,21 +397,21 @@ void pcs_get_state(struct phylink_config *config, * * For most 10GBASE-R, there is no advertisement. */ -int (*pcs_config)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); +int pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, const unsigned long *advertising); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * * When PCS ops are present, this overrides mac_an_restart() in &struct * phylink_mac_ops. */ -void (*pcs_an_restart)(struct phylink_config *config); +void pcs_an_restart(struct phylink_pcs *pcs); /** * pcs_link_up() - program the PCS for the resolved link configuration - * @config: a pointer to a &struct phylink_config. + * @pcs: a pointer to a &struct phylink_pcs. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @speed: link speed @@ -407,14 +422,14 @@ void (*pcs_an_restart)(struct phylink_config *config); * mode without in-band AN needs to be manually configured for the link * and duplex setting. Otherwise, this should be a no-op. */ -void (*pcs_link_up)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, int speed, int duplex); +void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); #endif struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -void phylink_add_pcs(struct phylink *, const struct phylink_pcs_ops *ops); +void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); -- cgit v1.2.3 From 93eaceb0fcf87b7f70924f9da3ec27e3c73be53d Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 21 Jul 2020 12:04:51 +0100 Subject: net: phylink: add interface to configure clause 22 PCS PHY Add an interface to configure the advertisement for a clause 22 PCS PHY, and set the AN enable flag in the BMCR appropriately. Reviewed-by: Ioana Ciornei Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 057f78263a46..1aad2aea4610 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -478,6 +478,9 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, phy_interface_t interface, const unsigned long *advertising); +int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising); void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, -- cgit v1.2.3 From 2cf2f4f546f1dea54b63302a7eb28d1fe15f1e28 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:31 +0300 Subject: qed: reformat "qed_chain.h" a bit Reformat structs and macros definitions a bit prior to making functional changes. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 126 ++++++++++++++++++++++-------------------- 1 file changed, 66 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 7071dc92b4e2..087073517c09 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -26,9 +26,9 @@ enum qed_chain_mode { }; enum qed_chain_use_mode { - QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ - QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ - QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ + QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ }; enum qed_chain_cnt_type { @@ -40,84 +40,86 @@ enum qed_chain_cnt_type { }; struct qed_chain_next { - struct regpair next_phys; - void *next_virt; + struct regpair next_phys; + void *next_virt; }; struct qed_chain_pbl_u16 { - u16 prod_page_idx; - u16 cons_page_idx; + u16 prod_page_idx; + u16 cons_page_idx; }; struct qed_chain_pbl_u32 { - u32 prod_page_idx; - u32 cons_page_idx; + u32 prod_page_idx; + u32 cons_page_idx; }; struct qed_chain_ext_pbl { - dma_addr_t p_pbl_phys; - void *p_pbl_virt; + dma_addr_t p_pbl_phys; + void *p_pbl_virt; }; struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ - u16 prod_idx; - u16 cons_idx; + u16 prod_idx; + u16 cons_idx; }; struct qed_chain_u32 { /* Cyclic index of next element to produce/consme */ - u32 prod_idx; - u32 cons_idx; + u32 prod_idx; + u32 cons_idx; }; struct addr_tbl_entry { - void *virt_addr; - dma_addr_t dma_map; + void *virt_addr; + dma_addr_t dma_map; }; struct qed_chain { - /* fastpath portion of the chain - required for commands such + /* Fastpath portion of the chain - required for commands such * as produce / consume. */ + /* Point to next element to produce/consume */ - void *p_prod_elem; - void *p_cons_elem; + void *p_prod_elem; + void *p_cons_elem; /* Fastpath portions of the PBL [if exists] */ + struct { /* Table for keeping the virtual and physical addresses of the * chain pages, respectively to the physical addresses * in the pbl table. */ - struct addr_tbl_entry *pp_addr_tbl; + struct addr_tbl_entry *pp_addr_tbl; union { - struct qed_chain_pbl_u16 u16; - struct qed_chain_pbl_u32 u32; - } c; - } pbl; + struct qed_chain_pbl_u16 u16; + struct qed_chain_pbl_u32 u32; + } c; + } pbl; union { - struct qed_chain_u16 chain16; - struct qed_chain_u32 chain32; - } u; + struct qed_chain_u16 chain16; + struct qed_chain_u32 chain32; + } u; /* Capacity counts only usable elements */ - u32 capacity; - u32 page_cnt; + u32 capacity; + u32 page_cnt; - enum qed_chain_mode mode; + enum qed_chain_mode mode; /* Elements information for fast calculations */ - u16 elem_per_page; - u16 elem_per_page_mask; - u16 elem_size; - u16 next_page_mask; - u16 usable_per_page; - u8 elem_unusable; + u16 elem_per_page; + u16 elem_per_page_mask; + u16 elem_size; + u16 next_page_mask; + u16 usable_per_page; + u8 elem_unusable; - u8 cnt_type; + u8 cnt_type; /* Slowpath of the chain - required for initialization and destruction, * but isn't involved in regular functionality. @@ -125,43 +127,47 @@ struct qed_chain { /* Base address of a pre-allocated buffer for pbl */ struct { - dma_addr_t p_phys_table; - void *p_virt_table; - } pbl_sp; + dma_addr_t p_phys_table; + void *p_virt_table; + } pbl_sp; /* Address of first page of the chain - the address is required * for fastpath operation [consume/produce] but only for the SINGLE * flavour which isn't considered fastpath [== SPQ]. */ - void *p_virt_addr; - dma_addr_t p_phys_addr; + void *p_virt_addr; + dma_addr_t p_phys_addr; /* Total number of elements [for entire chain] */ - u32 size; + u32 size; - u8 intended_use; + u8 intended_use; - bool b_external_pbl; + bool b_external_pbl; }; -#define QED_CHAIN_PBL_ENTRY_SIZE (8) -#define QED_CHAIN_PAGE_SIZE (0x1000) -#define ELEMS_PER_PAGE(elem_size) (QED_CHAIN_PAGE_SIZE / (elem_size)) +#define QED_CHAIN_PBL_ENTRY_SIZE 8 +#define QED_CHAIN_PAGE_SIZE 0x1000 + +#define ELEMS_PER_PAGE(elem_size) \ + (QED_CHAIN_PAGE_SIZE / (elem_size)) -#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ - (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ - (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / \ - (elem_size))) : 0) +#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ + (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ + (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) : \ + 0) -#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ - ((u32)(ELEMS_PER_PAGE(elem_size) - \ - UNUSABLE_ELEMS_PER_PAGE(elem_size, mode))) +#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((u32)(ELEMS_PER_PAGE(elem_size) - \ + UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode)))) -#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ - DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode)) +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ + DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode))) -#define is_chain_u16(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) -#define is_chain_u32(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) +#define is_chain_u16(p) \ + ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) +#define is_chain_u32(p) \ + ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) /* Accessors */ static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) -- cgit v1.2.3 From 9b6ee3cf95d322ab02e9927f5b08ebc870ca9f1f Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:35 +0300 Subject: qed: sanitize PBL chains allocation PBL chain elements are actually DMA addresses stored in __le64, but currently their size is hardcoded to 8, and DMA addresses are assigned via cast to variable-sized dma_addr_t without any bitwise conversions. Change the type of pbl_virt array to match the actual one, add a new field to store the size of allocated DMA memory and sanitize elements assignment. Misc: give more logic names to the members of qed_chain::pbl_sp embedded struct. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 087073517c09..265e0b671a5c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -127,8 +127,9 @@ struct qed_chain { /* Base address of a pre-allocated buffer for pbl */ struct { - dma_addr_t p_phys_table; - void *p_virt_table; + __le64 *table_virt; + dma_addr_t table_phys; + size_t table_size; } pbl_sp; /* Address of first page of the chain - the address is required @@ -146,7 +147,6 @@ struct qed_chain { bool b_external_pbl; }; -#define QED_CHAIN_PBL_ENTRY_SIZE 8 #define QED_CHAIN_PAGE_SIZE 0x1000 #define ELEMS_PER_PAGE(elem_size) \ @@ -236,7 +236,7 @@ static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) { - return p_chain->pbl_sp.p_phys_table; + return p_chain->pbl_sp.table_phys; } /** @@ -527,8 +527,8 @@ static inline void qed_chain_init_params(struct qed_chain *p_chain, p_chain->capacity = p_chain->usable_per_page * page_cnt; p_chain->size = p_chain->elem_per_page * page_cnt; - p_chain->pbl_sp.p_phys_table = 0; - p_chain->pbl_sp.p_virt_table = NULL; + p_chain->pbl_sp.table_phys = 0; + p_chain->pbl_sp.table_virt = NULL; p_chain->pbl.pp_addr_tbl = NULL; } @@ -569,8 +569,8 @@ static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, dma_addr_t p_phys_pbl, struct addr_tbl_entry *pp_addr_tbl) { - p_chain->pbl_sp.p_phys_table = p_phys_pbl; - p_chain->pbl_sp.p_virt_table = p_virt_pbl; + p_chain->pbl_sp.table_phys = p_phys_pbl; + p_chain->pbl_sp.table_virt = p_virt_pbl; p_chain->pbl.pp_addr_tbl = pp_addr_tbl; } -- cgit v1.2.3 From 5e776d8016119e13c27fbb6e87c9e1fd6f8b2a75 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:36 +0300 Subject: qed: move chain initialization inlines next to allocation functions qed_chain_init*() are used in one file/place on "cold" path only, so they can be uninlined and moved next to the call sites. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 112 ------------------------------------------ 1 file changed, 112 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 265e0b671a5c..a0d83095dc73 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -490,118 +490,6 @@ static inline void qed_chain_reset(struct qed_chain *p_chain) } } -/** - * @brief qed_chain_init - Initalizes a basic chain struct - * - * @param p_chain - * @param p_virt_addr - * @param p_phys_addr physical address of allocated buffer's beginning - * @param page_cnt number of pages in the allocated buffer - * @param elem_size size of each element in the chain - * @param intended_use - * @param mode - */ -static inline void qed_chain_init_params(struct qed_chain *p_chain, - u32 page_cnt, - u8 elem_size, - enum qed_chain_use_mode intended_use, - enum qed_chain_mode mode, - enum qed_chain_cnt_type cnt_type) -{ - /* chain fixed parameters */ - p_chain->p_virt_addr = NULL; - p_chain->p_phys_addr = 0; - p_chain->elem_size = elem_size; - p_chain->intended_use = (u8)intended_use; - p_chain->mode = mode; - p_chain->cnt_type = (u8)cnt_type; - - p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); - p_chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; - p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->next_page_mask = (p_chain->usable_per_page & - p_chain->elem_per_page_mask); - - p_chain->page_cnt = page_cnt; - p_chain->capacity = p_chain->usable_per_page * page_cnt; - p_chain->size = p_chain->elem_per_page * page_cnt; - - p_chain->pbl_sp.table_phys = 0; - p_chain->pbl_sp.table_virt = NULL; - p_chain->pbl.pp_addr_tbl = NULL; -} - -/** - * @brief qed_chain_init_mem - - * - * Initalizes a basic chain struct with its chain buffers - * - * @param p_chain - * @param p_virt_addr virtual address of allocated buffer's beginning - * @param p_phys_addr physical address of allocated buffer's beginning - * - */ -static inline void qed_chain_init_mem(struct qed_chain *p_chain, - void *p_virt_addr, dma_addr_t p_phys_addr) -{ - p_chain->p_virt_addr = p_virt_addr; - p_chain->p_phys_addr = p_phys_addr; -} - -/** - * @brief qed_chain_init_pbl_mem - - * - * Initalizes a basic chain struct with its pbl buffers - * - * @param p_chain - * @param p_virt_pbl pointer to a pre allocated side table which will hold - * virtual page addresses. - * @param p_phys_pbl pointer to a pre-allocated side table which will hold - * physical page addresses. - * @param pp_virt_addr_tbl - * pointer to a pre-allocated side table which will hold - * the virtual addresses of the chain pages. - * - */ -static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, - void *p_virt_pbl, - dma_addr_t p_phys_pbl, - struct addr_tbl_entry *pp_addr_tbl) -{ - p_chain->pbl_sp.table_phys = p_phys_pbl; - p_chain->pbl_sp.table_virt = p_virt_pbl; - p_chain->pbl.pp_addr_tbl = pp_addr_tbl; -} - -/** - * @brief qed_chain_init_next_ptr_elem - - * - * Initalizes a next pointer element - * - * @param p_chain - * @param p_virt_curr virtual address of a chain page of which the next - * pointer element is initialized - * @param p_virt_next virtual address of the next chain page - * @param p_phys_next physical address of the next chain page - * - */ -static inline void -qed_chain_init_next_ptr_elem(struct qed_chain *p_chain, - void *p_virt_curr, - void *p_virt_next, dma_addr_t p_phys_next) -{ - struct qed_chain_next *p_next; - u32 size; - - size = p_chain->elem_size * p_chain->usable_per_page; - p_next = (struct qed_chain_next *)((u8 *)p_virt_curr + size); - - DMA_REGPAIR_LE(p_next->next_phys, p_phys_next); - - p_next->next_virt = p_virt_next; -} - /** * @brief qed_chain_get_last_elem - * -- cgit v1.2.3 From b6db3f71c976ea92361dbc7ebfb65db666ac9f02 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:38 +0300 Subject: qed: simplify chain allocation with init params struct To simplify qed_chain_alloc() prototype and call sites, introduce struct qed_chain_init_params to specify chain params, and pass a pointer to filled struct to the actual qed_chain_alloc() instead of a long list of separate arguments. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 21 ++++++++++++++------- include/linux/qed/qed_if.h | 9 ++------- 2 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index a0d83095dc73..f5cfee0934e5 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -54,11 +54,6 @@ struct qed_chain_pbl_u32 { u32 cons_page_idx; }; -struct qed_chain_ext_pbl { - dma_addr_t p_pbl_phys; - void *p_pbl_virt; -}; - struct qed_chain_u16 { /* Cyclic index of next element to produce/consme */ u16 prod_idx; @@ -119,7 +114,7 @@ struct qed_chain { u16 usable_per_page; u8 elem_unusable; - u8 cnt_type; + enum qed_chain_cnt_type cnt_type; /* Slowpath of the chain - required for initialization and destruction, * but isn't involved in regular functionality. @@ -142,11 +137,23 @@ struct qed_chain { /* Total number of elements [for entire chain] */ u32 size; - u8 intended_use; + enum qed_chain_use_mode intended_use; bool b_external_pbl; }; +struct qed_chain_init_params { + enum qed_chain_mode mode; + enum qed_chain_use_mode intended_use; + enum qed_chain_cnt_type cnt_type; + + u32 num_elems; + size_t elem_size; + + void *ext_pbl_virt; + dma_addr_t ext_pbl_phys; +}; + #define QED_CHAIN_PAGE_SIZE 0x1000 #define ELEMS_PER_PAGE(elem_size) \ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index a5c6854343e6..cd6a5c7e56eb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -948,13 +948,8 @@ struct qed_common_ops { u8 dp_level); int (*chain_alloc)(struct qed_dev *cdev, - enum qed_chain_use_mode intended_use, - enum qed_chain_mode mode, - enum qed_chain_cnt_type cnt_type, - u32 num_elems, - size_t elem_size, - struct qed_chain *p_chain, - struct qed_chain_ext_pbl *ext_pbl); + struct qed_chain *chain, + struct qed_chain_init_params *params); void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); -- cgit v1.2.3 From 155065866bc36f20061c55fd2ca287a466911b16 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:39 +0300 Subject: qed: add support for different page sizes for chains Extend current infrastructure to store chain page size in a struct and use it in all functions instead of fixed QED_CHAIN_PAGE_SIZE. Its value remains the default one, but can be overridden in qed_chain_init_params before chain allocation. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index f5cfee0934e5..8a96c361cc19 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -120,6 +121,8 @@ struct qed_chain { * but isn't involved in regular functionality. */ + u32 page_size; + /* Base address of a pre-allocated buffer for pbl */ struct { __le64 *table_virt; @@ -147,6 +150,7 @@ struct qed_chain_init_params { enum qed_chain_use_mode intended_use; enum qed_chain_cnt_type cnt_type; + u32 page_size; u32 num_elems; size_t elem_size; @@ -154,22 +158,23 @@ struct qed_chain_init_params { dma_addr_t ext_pbl_phys; }; -#define QED_CHAIN_PAGE_SIZE 0x1000 +#define QED_CHAIN_PAGE_SIZE SZ_4K -#define ELEMS_PER_PAGE(elem_size) \ - (QED_CHAIN_PAGE_SIZE / (elem_size)) +#define ELEMS_PER_PAGE(elem_size, page_size) \ + ((page_size) / (elem_size)) #define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ (((mode) == QED_CHAIN_MODE_NEXT_PTR) ? \ (u8)(1 + ((sizeof(struct qed_chain_next) - 1) / (elem_size))) : \ 0) -#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ - ((u32)(ELEMS_PER_PAGE(elem_size) - \ +#define USABLE_ELEMS_PER_PAGE(elem_size, page_size, mode) \ + ((u32)(ELEMS_PER_PAGE((elem_size), (page_size)) - \ UNUSABLE_ELEMS_PER_PAGE((elem_size), (mode)))) -#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ - DIV_ROUND_UP((elem_cnt), USABLE_ELEMS_PER_PAGE((elem_size), (mode))) +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, page_size, mode) \ + DIV_ROUND_UP((elem_cnt), \ + USABLE_ELEMS_PER_PAGE((elem_size), (page_size), (mode))) #define is_chain_u16(p) \ ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) @@ -604,7 +609,7 @@ static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain) for (i = 0; i < page_cnt; i++) memset(p_chain->pbl.pp_addr_tbl[i].virt_addr, 0, - QED_CHAIN_PAGE_SIZE); + p_chain->page_size); } #endif -- cgit v1.2.3 From f2aefd20b02d83b8565c867c38eedd88853967e9 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:40 +0300 Subject: qed: optimize common chain accessors Constify chain pointers and refactor qed_chain_get_elem_left{,u32}() a bit. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 60 ++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 8a96c361cc19..434479e2ab65 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -182,73 +182,79 @@ struct qed_chain_init_params { ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) /* Accessors */ -static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) + +static inline u16 qed_chain_get_prod_idx(const struct qed_chain *chain) +{ + return chain->u.chain16.prod_idx; +} + +static inline u16 qed_chain_get_cons_idx(const struct qed_chain *chain) { - return p_chain->u.chain16.prod_idx; + return chain->u.chain16.cons_idx; } -static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain) +static inline u32 qed_chain_get_prod_idx_u32(const struct qed_chain *chain) { - return p_chain->u.chain16.cons_idx; + return chain->u.chain32.prod_idx; } -static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) +static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain) { - return p_chain->u.chain32.cons_idx; + return chain->u.chain32.cons_idx; } -static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) +static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) { - u16 elem_per_page = p_chain->elem_per_page; - u32 prod = p_chain->u.chain16.prod_idx; - u32 cons = p_chain->u.chain16.cons_idx; + u32 prod = qed_chain_get_prod_idx(chain); + u32 cons = qed_chain_get_cons_idx(chain); + u16 elem_per_page = chain->elem_per_page; u16 used; if (prod < cons) prod += (u32)U16_MAX + 1; used = (u16)(prod - cons); - if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= prod / elem_per_page - cons / elem_per_page; + if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) + used -= (u16)(prod / elem_per_page - cons / elem_per_page); - return (u16)(p_chain->capacity - used); + return (u16)(chain->capacity - used); } -static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) +static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) { - u16 elem_per_page = p_chain->elem_per_page; - u64 prod = p_chain->u.chain32.prod_idx; - u64 cons = p_chain->u.chain32.cons_idx; + u64 prod = qed_chain_get_prod_idx_u32(chain); + u64 cons = qed_chain_get_cons_idx_u32(chain); + u16 elem_per_page = chain->elem_per_page; u32 used; if (prod < cons) prod += (u64)U32_MAX + 1; used = (u32)(prod - cons); - if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) + if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u32)(prod / elem_per_page - cons / elem_per_page); - return p_chain->capacity - used; + return chain->capacity - used; } -static inline u16 qed_chain_get_usable_per_page(struct qed_chain *p_chain) +static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain) { - return p_chain->usable_per_page; + return chain->usable_per_page; } -static inline u8 qed_chain_get_unusable_per_page(struct qed_chain *p_chain) +static inline u8 qed_chain_get_unusable_per_page(const struct qed_chain *chain) { - return p_chain->elem_unusable; + return chain->elem_unusable; } -static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) +static inline u32 qed_chain_get_page_cnt(const struct qed_chain *chain) { - return p_chain->page_cnt; + return chain->page_cnt; } -static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) +static inline dma_addr_t qed_chain_get_pbl_phys(const struct qed_chain *chain) { - return p_chain->pbl_sp.table_phys; + return chain->pbl_sp.table_phys; } /** -- cgit v1.2.3 From be0cec6ffd686364bbba2796bbe5eee2fad18181 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Thu, 23 Jul 2020 01:10:41 +0300 Subject: qed: introduce qed_chain_get_elem_used{,u32}() Add reverse-variants of qed_chain_get_elem_left{,u32}() to be able to know current chain occupation. They will be used in the upcoming qede XDP_REDIRECT code. They share most of the logics with the mentioned ones, so were reused to collapse the latters. Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 434479e2ab65..4d58dc8943f0 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -203,7 +203,7 @@ static inline u32 qed_chain_get_cons_idx_u32(const struct qed_chain *chain) return chain->u.chain32.cons_idx; } -static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) +static inline u16 qed_chain_get_elem_used(const struct qed_chain *chain) { u32 prod = qed_chain_get_prod_idx(chain); u32 cons = qed_chain_get_cons_idx(chain); @@ -217,10 +217,15 @@ static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u16)(prod / elem_per_page - cons / elem_per_page); - return (u16)(chain->capacity - used); + return used; } -static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) +static inline u16 qed_chain_get_elem_left(const struct qed_chain *chain) +{ + return (u16)(chain->capacity - qed_chain_get_elem_used(chain)); +} + +static inline u32 qed_chain_get_elem_used_u32(const struct qed_chain *chain) { u64 prod = qed_chain_get_prod_idx_u32(chain); u64 cons = qed_chain_get_cons_idx_u32(chain); @@ -234,7 +239,12 @@ static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) if (chain->mode == QED_CHAIN_MODE_NEXT_PTR) used -= (u32)(prod / elem_per_page - cons / elem_per_page); - return chain->capacity - used; + return used; +} + +static inline u32 qed_chain_get_elem_left_u32(const struct qed_chain *chain) +{ + return chain->capacity - qed_chain_get_elem_used_u32(chain); } static inline u16 qed_chain_get_usable_per_page(const struct qed_chain *chain) -- cgit v1.2.3 From 0cb09aff9d49d92305c3969fc84b785117412968 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Thu, 23 Jul 2020 01:03:00 +0300 Subject: net/flow_dissector: add packet hash dissection Retreive a hash value from the SKB and store it in the dissector key for future matching. Signed-off-by: Ariel Levkovich Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6a82d4a8229e..fa817a105517 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1342,6 +1342,10 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +void skb_flow_dissect_hash(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container); + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) -- cgit v1.2.3 From ba423fdaa589d972473083defedf9e862626d268 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:46 +0200 Subject: net: add a new sockptr_t type Add a uptr_t type that can hold a pointer to either a user or kernel memory region, and simply helpers to copy to and from it. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 include/linux/sockptr.h (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h new file mode 100644 index 000000000000..700856e13ea0 --- /dev/null +++ b/include/linux/sockptr.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 Christoph Hellwig. + * + * Support for "universal" pointers that can point to either kernel or userspace + * memory. + */ +#ifndef _LINUX_SOCKPTR_H +#define _LINUX_SOCKPTR_H + +#include +#include + +typedef struct { + union { + void *kernel; + void __user *user; + }; + bool is_kernel : 1; +} sockptr_t; + +static inline bool sockptr_is_kernel(sockptr_t sockptr) +{ + return sockptr.is_kernel; +} + +static inline sockptr_t KERNEL_SOCKPTR(void *p) +{ + return (sockptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline sockptr_t USER_SOCKPTR(void __user *p) +{ + return (sockptr_t) { .user = p }; +} + +static inline bool sockptr_is_null(sockptr_t sockptr) +{ + return !sockptr.user && !sockptr.kernel; +} + +static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +{ + if (!sockptr_is_kernel(src)) + return copy_from_user(dst, src.user, size); + memcpy(dst, src.kernel, size); + return 0; +} + +static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +{ + if (!sockptr_is_kernel(dst)) + return copy_to_user(dst.user, src, size); + memcpy(dst.kernel, src, size); + return 0; +} + +static inline void *memdup_sockptr(sockptr_t src, size_t len) +{ + void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_sockptr(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + return p; +} + +static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) +{ + char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); + + if (!p) + return ERR_PTR(-ENOMEM); + if (copy_from_sockptr(p, src, len)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + p[len] = '\0'; + return p; +} + +static inline void sockptr_advance(sockptr_t sockptr, size_t len) +{ + if (sockptr_is_kernel(sockptr)) + sockptr.kernel += len; + else + sockptr.user += len; +} + +static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) +{ + if (sockptr_is_kernel(src)) { + size_t len = min(strnlen(src.kernel, count - 1) + 1, count); + + memcpy(dst, src.kernel, len); + return len; + } + return strncpy_from_user(dst, src.user, count); +} + +#endif /* _LINUX_SOCKPTR_H */ -- cgit v1.2.3 From b1ea9ff6aff2deae84eccaf0a07cd14912669680 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:47 +0200 Subject: net: switch copy_bpf_fprog_from_user to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1c6b6d982bf4..d07a6e973a7d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -1276,7 +1277,7 @@ struct bpf_sockopt_kern { s32 retval; }; -int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len); +int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; -- cgit v1.2.3 From ab214d1bf8c7ef1ed7af803a72491cb29edfa8f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:53 +0200 Subject: netfilter: switch xt_copy_counters to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b8b943ee7b8b..5deb099d156d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -301,8 +301,8 @@ int xt_target_to_user(const struct xt_entry_target *t, int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); -void *xt_copy_counters_from_user(const void __user *user, unsigned int len, - struct xt_counters_info *info); +void *xt_copy_counters(sockptr_t arg, unsigned int len, + struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, -- cgit v1.2.3 From c2f12630c60ff33a9cafd221646053fc10ec59b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:54 +0200 Subject: netfilter: switch nf_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 711b4d4486f0..0101747de549 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -13,6 +13,7 @@ #include #include #include +#include #include static inline int NF_DROP_GETERR(int verdict) @@ -163,7 +164,8 @@ struct nf_sockopt_ops { /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; - int (*set)(struct sock *sk, int optval, void __user *user, unsigned int len); + int (*set)(struct sock *sk, int optval, sockptr_t arg, + unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); @@ -338,7 +340,7 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, } /* Call setsockopt() */ -int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, +int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); -- cgit v1.2.3 From b03afaa82ece13b2a008f0e3a7127bead578e3e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:55 +0200 Subject: bpfilter: switch bpfilter_ip_set_sockopt to sockptr_t This is mostly to prepare for cleaning up the callers, as bpfilter by design can't handle kernel pointers. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/bpfilter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 9b114c718a76..2ae3c8e1d83c 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -4,9 +4,10 @@ #include #include +#include struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen); int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen); @@ -16,8 +17,7 @@ struct bpfilter_umh_ops { struct umd_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ struct mutex lock; - int (*sockopt)(struct sock *sk, int optname, - char __user *optval, + int (*sockopt)(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen, bool is_set); int (*start)(void); }; -- cgit v1.2.3 From 01ccb5b48f08f59ca3746d59221f4990aec1b194 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:56 +0200 Subject: net/ipv4: switch ip_mroute_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/mroute.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 9a36fad9e068..6cbbfe94348c 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -8,6 +8,7 @@ #include #include #include +#include #ifdef CONFIG_IP_MROUTE static inline int ip_mroute_opt(int opt) @@ -15,7 +16,7 @@ static inline int ip_mroute_opt(int opt) return opt >= MRT_BASE && opt <= MRT_MAX; } -int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); +int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); @@ -23,7 +24,7 @@ int ip_mr_init(void); bool ipmr_rule_default(const struct fib_rule *rule); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From b43c6153132c92745317f92174af84f57b160b76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:08:59 +0200 Subject: net/ipv6: switch ip6_mroute_setsockopt to sockptr_t Pass a sockptr_t to prepare for set_fs-less handling of the kernel pointer from bpf-cgroup. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/mroute6.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index c4a45859f586..bc351a85ce9b 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #ifdef CONFIG_IPV6_MROUTE @@ -25,7 +26,7 @@ static inline int ip6_mroute_opt(int opt) struct sock; #ifdef CONFIG_IPV6_MROUTE -extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); +extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); @@ -33,9 +34,8 @@ extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *ar extern int ip6_mr_init(void); extern void ip6_mr_cleanup(void); #else -static inline -int ip6_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, unsigned int optlen) +static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, + sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } -- cgit v1.2.3 From a7b75c5a8c41445f33efb663887ff5f5c3b4454b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:09:07 +0200 Subject: net: pass a sockptr_t into ->setsockopt Rework the remaining setsockopt code to pass a sockptr_t instead of a plain user pointer. This removes the last remaining set_fs(KERNEL_DS) outside of architecture specific code. Signed-off-by: Christoph Hellwig Acked-by: Stefan Schmidt [ieee802154] Acked-by: Matthieu Baerts Signed-off-by: David S. Miller --- include/linux/net.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 858ff1d98154..d48ff1180879 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include #include #include +#include #include @@ -162,7 +163,8 @@ struct proto_ops { int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen); + int optname, sockptr_t optval, + unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); void (*show_fdinfo)(struct seq_file *m, struct socket *sock); -- cgit v1.2.3 From 6d04fe15f78acdf8e32329e208552e226f7a8ae6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Jul 2020 08:09:08 +0200 Subject: net: optimize the sockptr_t for unified kernel/user address spaces For architectures like x86 and arm64 we don't need the separate bit to indicate that a pointer is a kernel pointer as the address spaces are unified. That way the sockptr_t can be reduced to a union of two pointers, which leads to nicer calling conventions. The only caveat is that we need to check that users don't pass in kernel address and thus gain access to kernel memory. Thus the USER_SOCKPTR helper is replaced with a init_user_sockptr function that does this check and returns an error if it fails. Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 700856e13ea0..7d5cdb2b30b5 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -8,9 +8,34 @@ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H +#include #include #include +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE +typedef union { + void *kernel; + void __user *user; +} sockptr_t; + +static inline bool sockptr_is_kernel(sockptr_t sockptr) +{ + return (unsigned long)sockptr.kernel >= TASK_SIZE; +} + +static inline sockptr_t KERNEL_SOCKPTR(void *p) +{ + return (sockptr_t) { .kernel = p }; +} + +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) +{ + if ((unsigned long)p >= TASK_SIZE) + return -EFAULT; + sp->user = p; + return 0; +} +#else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { void *kernel; @@ -29,10 +54,13 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) return (sockptr_t) { .kernel = p, .is_kernel = true }; } -static inline sockptr_t USER_SOCKPTR(void __user *p) +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) { - return (sockptr_t) { .user = p }; + sp->user = p; + sp->is_kernel = false; + return 0; } +#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ static inline bool sockptr_is_null(sockptr_t sockptr) { -- cgit v1.2.3 From 178c49d9f9a4b5ade00c93480d714708fe971e24 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 24 Jul 2020 09:03:09 -0400 Subject: icmp: prepare rfc 4884 for ipv6 The RFC 4884 spec is largely the same between IPv4 and IPv6. Factor out the IPv4 specific parts in preparation for IPv6 support: - icmp types supported - icmp header size, and thus offset to original datagram start - datagram length field offset in icmp(6)hdr. - datagram length field word size: 4B for IPv4, 8B for IPv6. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/icmp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 8fc38a34cb20..0af4d210ee31 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -37,6 +37,7 @@ static inline bool icmp_is_err(int type) } void ip_icmp_error_rfc4884(const struct sk_buff *skb, - struct sock_ee_data_rfc4884 *out); + struct sock_ee_data_rfc4884 *out, + int thlen, int off); #endif /* _LINUX_ICMP_H */ -- cgit v1.2.3 From 01370434df85eb76ecb1527a4466013c4aca2436 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 24 Jul 2020 09:03:10 -0400 Subject: icmp6: support rfc 4884 Extend the rfc 4884 read interface introduced for ipv4 in commit eba75c587e81 ("icmp: support rfc 4884") to ipv6. Add socket option SOL_IPV6/IPV6_RECVERR_RFC4884. Changes v1->v2: - make ipv6_icmp_error_rfc4884 static (file scope) Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8d8f877e7f81..a44789d027cc 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -283,6 +283,7 @@ struct ipv6_pinfo { autoflowlabel:1, autoflowlabel_set:1, mc_all:1, + recverr_rfc4884:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From a228a64fc1e4428e2b96dc68e9ad3c447095c9e7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Jul 2020 18:10:18 -0700 Subject: bpf: Add bpf_prog iterator It's mostly a copy paste of commit 6086d29def80 ("bpf: Add bpf_map iterator") that is use to implement bpf_seq_file opreations to traverse all bpf programs. v1->v2: Tweak to use build time btf_id Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: Daniel Borkmann --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bae557ff2da8..72221aea1c60 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1117,6 +1117,7 @@ int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); +struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 14fc6bd6b79c430f615500d0fe6cea4722110db8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:09 -0700 Subject: bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com --- include/linux/bpf.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 72221aea1c60..127067f71fd4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,15 @@ struct seq_operations; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +struct bpf_iter_seq_info { + const struct seq_operations *seq_ops; + bpf_iter_init_seq_priv_t init_seq_private; + bpf_iter_fini_seq_priv_t fini_seq_private; + u32 seq_priv_size; +}; + /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ @@ -1189,18 +1198,12 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); -typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); - #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; - const struct seq_operations *seq_ops; - bpf_iter_init_seq_priv_t init_seq_private; - bpf_iter_fini_seq_priv_t fini_seq_private; - u32 seq_priv_size; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; + const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { -- cgit v1.2.3 From f9c792729581bd8b8473af163e8ab426c2c61d89 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:10 -0700 Subject: bpf: Refactor to provide aux info to bpf_iter_init_seq_priv_t This patch refactored target bpf_iter_init_seq_priv_t callback function to accept additional information. This will be needed in later patches for map element targets since a particular map should be passed to traverse elements for that particular map. In the future, other information may be passed to target as well, e.g., pid, cgroup id, etc. to customize the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com --- include/linux/bpf.h | 7 ++++++- include/linux/proc_fs.h | 3 ++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 127067f71fd4..ef52717336cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -33,11 +33,13 @@ struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; +struct bpf_iter_aux_info; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, + struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; @@ -1198,6 +1200,9 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } +struct bpf_iter_aux_info { +}; + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d1eed1b43651..2df965cd0974 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -133,7 +133,8 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); -extern int bpf_iter_init_seq_net(void *priv_data); +struct bpf_iter_aux_info; +extern int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux); extern void bpf_iter_fini_seq_net(void *priv_data); #ifdef CONFIG_PROC_PID_ARCH_STATUS -- cgit v1.2.3 From afbf21dce668ef59482037596eaffbe5041e094c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:11 -0700 Subject: bpf: Support readonly/readwrite buffers in verifier Readonly and readwrite buffer register states are introduced. Totally four states, PTR_TO_RDONLY_BUF[_OR_NULL] and PTR_TO_RDWR_BUF[_OR_NULL] are supported. As suggested by their respective names, PTR_TO_RDONLY_BUF[_OR_NULL] are for readonly buffers and PTR_TO_RDWR_BUF[_OR_NULL] for read/write buffers. These new register states will be used by later bpf map element iterator. New register states share some similarity to PTR_TO_TP_BUFFER as it will calculate accessed buffer size during verification time. The accessed buffer size will be later compared to other metrics during later attach/link_create time. Similar to reg_state PTR_TO_BTF_ID_OR_NULL in bpf iterator programs, PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL reg_types can be set at prog->aux->bpf_ctx_arg_aux, and bpf verifier will retrieve the values during btf_ctx_access(). Later bpf map element iterator implementation will show how such information will be assigned during target registeration time. The verifier is also enhanced such that PTR_TO_RDONLY_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] helper argument, and PTR_TO_RDWR_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] or ARG_PTR_TO_UNINIT_MEM. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184111.590274-1-yhs@fb.com --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef52717336cf..f9c4bb08f616 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -353,6 +353,10 @@ enum bpf_reg_type { PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ + PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ + PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ + PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ + PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -694,6 +698,8 @@ struct bpf_prog_aux { u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; + u32 max_rdonly_access; + u32 max_rdwr_access; const struct bpf_ctx_arg_aux *ctx_arg_info; struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ -- cgit v1.2.3 From a5cbe05a6673b85bed2a63ffcfea6a96c6410cff Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:12 -0700 Subject: bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f9c4bb08f616..4175cf1f4665 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -107,6 +107,9 @@ struct bpf_map_ops { /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; + + /* bpf_iter info used to open a seq_file */ + const struct bpf_iter_seq_info *iter_seq_info; }; struct bpf_map_memory { @@ -1207,12 +1210,18 @@ int bpf_obj_get_user(const char __user *pathname, int flags); int __init bpf_iter_ ## target(args) { return 0; } struct bpf_iter_aux_info { + struct bpf_map *map; }; +typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog, + struct bpf_iter_aux_info *aux); + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; + bpf_iter_check_target_t check_target; u32 ctx_arg_info_size; + enum bpf_iter_link_info req_linfo; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; @@ -1223,6 +1232,13 @@ struct bpf_iter_meta { u64 seq_num; }; +struct bpf_iter__bpf_map_elem { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(void *, key); + __bpf_md_ptr(void *, value); +}; + int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -- cgit v1.2.3 From 7b04d6d60fcfb5b2200ffebb9cfb90927bdfeec7 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:44 -0700 Subject: bpf: Separate bpf_get_[stack|stackid] for perf events BPF Calling get_perf_callchain() on perf_events from PEBS entries may cause unwinder errors. To fix this issue, the callchain is fetched early. Such perf_events are marked with __PERF_SAMPLE_CALLCHAIN_EARLY. Similarly, calling bpf_get_[stack|stackid] on perf_events from PEBS may also cause unwinder errors. To fix this, add separate version of these two helpers, bpf_get_[stack|stackid]_pe. These two hepers use callchain in bpf_perf_event_data_kern->data->callchain. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723180648.1429892-2-songliubraving@fb.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4175cf1f4665..8357be349133 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1675,6 +1675,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto_pe; +extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; -- cgit v1.2.3 From 5d99cb2c86775b4780c02a339a9578bf9471ead9 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 23 Jul 2020 11:06:45 -0700 Subject: bpf: Fail PERF_EVENT_IOC_SET_BPF when bpf_get_[stack|stackid] cannot work bpf_get_[stack|stackid] on perf_events with precise_ip uses callchain attached to perf_sample_data. If this callchain is not presented, do not allow attaching BPF program that calls bpf_get_[stack|stackid] to this event. In the error case, -EPROTO is returned so that libbpf can identify this error and print proper hint message. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723180648.1429892-3-songliubraving@fb.com --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d07a6e973a7d..0a355b005bf4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -533,7 +533,8 @@ struct bpf_prog { is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ - enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3 From 7d9c3427894fe70d1347b4820476bf37736d2ff0 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 23 Jul 2020 23:47:43 -0500 Subject: bpf: Make cgroup storages shared between programs on the same cgroup This change comes in several parts: One, the restriction that the CGROUP_STORAGE map can only be used by one program is removed. This results in the removal of the field 'aux' in struct bpf_cgroup_storage_map, and removal of relevant code associated with the field, and removal of now-noop functions bpf_free_cgroup_storage and bpf_cgroup_storage_release. Second, we permit a key of type u64 as the key to the map. Providing such a key type indicates that the map should ignore attach type when comparing map keys. However, for simplicity newly linked storage will still have the attach type at link time in its key struct. cgroup_storage_check_btf is adapted to accept u64 as the type of the key. Third, because the storages are now shared, the storages cannot be unconditionally freed on program detach. There could be two ways to solve this issue: * A. Reference count the usage of the storages, and free when the last program is detached. * B. Free only when the storage is impossible to be referred to again, i.e. when either the cgroup_bpf it is attached to, or the map itself, is freed. Option A has the side effect that, when the user detach and reattach a program, whether the program gets a fresh storage depends on whether there is another program attached using that storage. This could trigger races if the user is multi-threaded, and since nondeterminism in data races is evil, go with option B. The both the map and the cgroup_bpf now tracks their associated storages, and the storage unlink and free are removed from cgroup_bpf_detach and added to cgroup_bpf_release and cgroup_storage_map_free. The latter also new holds the cgroup_mutex to prevent any races with the former. Fourth, on attach, we reuse the old storage if the key already exists in the map, via cgroup_storage_lookup. If the storage does not exist yet, we create a new one, and publish it at the last step in the attach process. This does not create a race condition because for the whole attach the cgroup_mutex is held. We keep track of an array of new storages that was allocated and if the process fails only the new storages would get freed. Signed-off-by: YiFei Zhu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/d5401c6106728a00890401190db40020a1f84ff1.1595565795.git.zhuyifei@google.com --- include/linux/bpf-cgroup.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 2c6f26670acc..64f367044e25 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -46,7 +46,8 @@ struct bpf_cgroup_storage { }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; - struct list_head list; + struct list_head list_map; + struct list_head list_cg; struct rb_node node; struct rcu_head rcu; }; @@ -78,6 +79,9 @@ struct cgroup_bpf { struct list_head progs[MAX_BPF_ATTACH_TYPE]; u32 flags[MAX_BPF_ATTACH_TYPE]; + /* list of cgroup shared storages */ + struct list_head storages; + /* temp storage for effective prog array used by prog_attach/detach */ struct bpf_prog_array *inactive; @@ -161,6 +165,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } +struct bpf_cgroup_storage * +cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, + void *key, bool locked); struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); @@ -169,7 +176,6 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -383,8 +389,6 @@ static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, - struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } static inline void bpf_cgroup_storage_free( -- cgit v1.2.3 From 6cc7d1e8e9e06d45f9d1a39a5f465288d7cd8f9a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:54 -0700 Subject: bpf: Make bpf_link API available indepently of CONFIG_BPF_SYSCALL Similarly to bpf_prog, make bpf_link and related generic API available unconditionally to make it easier to have bpf_link support in various parts of the kernel. Stub out init/prime/settle/cleanup and inc/put APIs. Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-2-andriin@fb.com --- include/linux/bpf.h | 81 ++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 55 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8357be349133..40c5e206ecf2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -781,6 +781,32 @@ struct bpf_array_aux { struct work_struct work; }; +struct bpf_link { + atomic64_t refcnt; + u32 id; + enum bpf_link_type type; + const struct bpf_link_ops *ops; + struct bpf_prog *prog; + struct work_struct work; +}; + +struct bpf_link_ops { + void (*release)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); + int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog); + void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); + int (*fill_link_info)(const struct bpf_link *link, + struct bpf_link_info *info); +}; + +struct bpf_link_primer { + struct bpf_link *link; + struct file *file; + int fd; + u32 id; +}; + struct bpf_struct_ops_value; struct btf_type; struct btf_member; @@ -1164,32 +1190,6 @@ static inline bool bpf_bypass_spec_v4(void) int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); -struct bpf_link { - atomic64_t refcnt; - u32 id; - enum bpf_link_type type; - const struct bpf_link_ops *ops; - struct bpf_prog *prog; - struct work_struct work; -}; - -struct bpf_link_primer { - struct bpf_link *link; - struct file *file; - int fd; - u32 id; -}; - -struct bpf_link_ops { - void (*release)(struct bpf_link *link); - void (*dealloc)(struct bpf_link *link); - int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, - struct bpf_prog *old_prog); - void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); - int (*fill_link_info)(const struct bpf_link *link, - struct bpf_link_info *info); -}; - void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); @@ -1401,6 +1401,35 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, + struct bpf_prog *prog) +{ +} + +static inline int bpf_link_prime(struct bpf_link *link, + struct bpf_link_primer *primer) +{ + return -EOPNOTSUPP; +} + +static inline int bpf_link_settle(struct bpf_link_primer *primer) +{ + return -EOPNOTSUPP; +} + +static inline void bpf_link_cleanup(struct bpf_link_primer *primer) +{ +} + +static inline void bpf_link_inc(struct bpf_link *link) +{ +} + +static inline void bpf_link_put(struct bpf_link *link) +{ +} + static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; -- cgit v1.2.3 From 7f0a838254bdd9114b978ef2541a6ce330307e9e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:55 -0700 Subject: bpf, xdp: Maintain info on attached XDP BPF programs in net_device Instead of delegating to drivers, maintain information about which BPF programs are attached in which XDP modes (generic/skb, driver, or hardware) locally in net_device. This effectively obsoletes XDP_QUERY_PROG command. Such re-organization simplifies existing code already. But it also allows to further add bpf_link-based XDP attachments without drivers having to know about any of this at all, which seems like a good setup. XDP_SETUP_PROG/XDP_SETUP_PROG_HW are just low-level commands to driver to install/uninstall active BPF program. All the higher-level concerns about prog/link interaction will be contained within generic driver-agnostic logic. All the XDP_QUERY_PROG calls to driver in dev_xdp_uninstall() were removed. It's not clear for me why dev_xdp_uninstall() were passing previous prog_flags when resetting installed programs. That seems unnecessary, plus most drivers don't populate prog_flags anyways. Having XDP_SETUP_PROG vs XDP_SETUP_PROG_HW should be enough of an indicator of what is required of driver to correctly reset active BPF program. dev_xdp_uninstall() is also generalized as an iteration over all three supported mode. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-3-andriin@fb.com --- include/linux/netdevice.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ac2cd3f49aba..cad44b40c776 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -889,6 +889,17 @@ struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; +enum bpf_xdp_mode { + XDP_MODE_SKB = 0, + XDP_MODE_DRV = 1, + XDP_MODE_HW = 2, + __MAX_XDP_MODE +}; + +struct bpf_xdp_entity { + struct bpf_prog *prog; +}; + struct netdev_bpf { enum bpf_netdev_command command; union { @@ -2142,6 +2153,9 @@ struct net_device { #endif const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; + + /* protected by rtnl_lock */ + struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3817,8 +3831,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); -u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, - enum bpf_netdev_command cmd); +u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From aa8d3a716b59db6c1ad6c68fb8aa05e31980da60 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:45:57 -0700 Subject: bpf, xdp: Add bpf_link-based XDP attachment API Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through BPF_LINK_CREATE command. bpf_xdp_link is mutually exclusive with direct BPF program attachment, previous BPF program should be detached prior to attempting to create a new bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it can't be replaced by other BPF program attachment or link attachment. It will be detached only when the last BPF link FD is closed. bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to how other BPF links behave (cgroup, flow_dissector). At that point bpf_link will become defunct, but won't be destroyed until last FD is closed. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-5-andriin@fb.com --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cad44b40c776..7d3c412fcfe5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -888,6 +888,7 @@ struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; +struct bpf_xdp_link; enum bpf_xdp_mode { XDP_MODE_SKB = 0, @@ -898,6 +899,7 @@ enum bpf_xdp_mode { struct bpf_xdp_entity { struct bpf_prog *prog; + struct bpf_xdp_link *link; }; struct netdev_bpf { @@ -3831,7 +3833,9 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags); +int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); + int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); -- cgit v1.2.3 From e8407fdeb9a6866784e249881f6c786a0835faba Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 21 Jul 2020 23:46:02 -0700 Subject: bpf, xdp: Remove XDP_QUERY_PROG and XDP_QUERY_PROG_HW XDP commands Now that BPF program/link management is centralized in generic net_device code, kernel code never queries program id from drivers, so XDP_QUERY_PROG/XDP_QUERY_PROG_HW commands are unnecessary. This patch removes all the implementations of those commands in kernel, along the xdp_attachment_query(). This patch was compile-tested on allyesconfig. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200722064603.3350758-10-andriin@fb.com --- include/linux/netdevice.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7d3c412fcfe5..1046763cd0dc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -876,8 +876,6 @@ enum bpf_netdev_command { */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, - XDP_QUERY_PROG, - XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, @@ -911,12 +909,6 @@ struct netdev_bpf { struct bpf_prog *prog; struct netlink_ext_ack *extack; }; - /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */ - struct { - u32 prog_id; - /* flags with which program was installed */ - u32 prog_flags; - }; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; -- cgit v1.2.3 From d6945242f45d4745a8169fdab7afeb40f4e36f06 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 18 May 2020 11:13:52 +0300 Subject: net/mlx5: Hold pages RB tree per VF Per page request event, FW request to allocated or release pages for a single function. Driver maintains FW pages object per function, so there is no need to hold one global page data-base. Instead, have a page data-base per function, which will improve performance release flow in all cases, especially for "release all pages". As the range of function IDs is large and not sequential, use xarray to store a per function ID page data-base, where the function ID is the key. Upon first allocation of a page to a function ID, create the page data-base per function. This data-base will be released only at pagealloc mechanism cleanup. NIC: ConnectX-4 Lx CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz Test case: 32 VFs, measure release pages on one VF as part of FLR Before: 0.021 Sec After: 0.014 Sec The improvement depends on amount of VFs and memory utilization by them. Time measurements above were taken from idle system. Signed-off-by: Eran Ben Elisha Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6a97ad601991..a0fcc4d13e93 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -541,7 +541,7 @@ struct mlx5_priv { /* pages stuff */ struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; - struct rb_root page_root; + struct xarray page_root_xa; int fw_pages; atomic_t reg_pages; struct list_head free_list; -- cgit v1.2.3 From 035bfd051eae5b365368be915dfaf916aa501a52 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:34 +0200 Subject: net: make sockptr_is_null strict aliasing safe While the kernel in general is not strict aliasing safe we can trivially do that in sockptr_is_null without affecting code generation, so always check the actually assigned union member. Reported-by: Jan Engelhardt Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 7d5cdb2b30b5..b13ea1422f93 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -64,7 +64,9 @@ static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) static inline bool sockptr_is_null(sockptr_t sockptr) { - return !sockptr.user && !sockptr.kernel; + if (sockptr_is_kernel(sockptr)) + return !sockptr.kernel; + return !sockptr.user; } static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) -- cgit v1.2.3 From d3c48151512922dd35f1f393b30b9138e4441d14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:35 +0200 Subject: net: remove sockptr_advance sockptr_advance never properly worked. Replace it with _offset variants of copy_from_sockptr and copy_to_sockptr. Fixes: ba423fdaa589 ("net: add a new sockptr_t type") Reported-by: Jason A. Donenfeld Reported-by: Ido Schimmel Signed-off-by: Christoph Hellwig Acked-by: Jason A. Donenfeld Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/sockptr.h | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index b13ea1422f93..9e6c81d474cb 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -69,19 +69,26 @@ static inline bool sockptr_is_null(sockptr_t sockptr) return !sockptr.user; } -static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, + size_t offset, size_t size) { if (!sockptr_is_kernel(src)) - return copy_from_user(dst, src.user, size); - memcpy(dst, src.kernel, size); + return copy_from_user(dst, src.user + offset, size); + memcpy(dst, src.kernel + offset, size); return 0; } -static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) +{ + return copy_from_sockptr_offset(dst, src, 0, size); +} + +static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, + const void *src, size_t size) { if (!sockptr_is_kernel(dst)) - return copy_to_user(dst.user, src, size); - memcpy(dst.kernel, src, size); + return copy_to_user(dst.user + offset, src, size); + memcpy(dst.kernel + offset, src, size); return 0; } @@ -112,14 +119,6 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) return p; } -static inline void sockptr_advance(sockptr_t sockptr, size_t len) -{ - if (sockptr_is_kernel(sockptr)) - sockptr.kernel += len; - else - sockptr.user += len; -} - static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { -- cgit v1.2.3 From a31edb2059ed4e498f9aa8230c734b59d0ad797a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 28 Jul 2020 18:38:36 +0200 Subject: net: improve the user pointer check in init_user_sockptr Make sure not just the pointer itself but the whole range lies in the user address space. For that pass the length and then use the access_ok helper to do the check. Fixes: 6d04fe15f78a ("net: optimize the sockptr_t for unified kernel/user address spaces") Reported-by: David Laight Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- include/linux/sockptr.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 9e6c81d474cb..96840def9d69 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -27,14 +27,6 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p }; } - -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) -{ - if ((unsigned long)p >= TASK_SIZE) - return -EFAULT; - sp->user = p; - return 0; -} #else /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ typedef struct { union { @@ -53,14 +45,16 @@ static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } +#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ -static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p) +static inline int __must_check init_user_sockptr(sockptr_t *sp, void __user *p, + size_t size) { - sp->user = p; - sp->is_kernel = false; + if (!access_ok(p, size)) + return -EFAULT; + *sp = (sockptr_t) { .user = p }; return 0; } -#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ static inline bool sockptr_is_null(sockptr_t sockptr) { -- cgit v1.2.3 From b8265621f4888af9494e1d685620871ec81bc33d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 23 Jul 2020 17:21:59 -0700 Subject: Add pldmfw library for PLDM firmware update The pldmfw library is used to implement common logic needed to flash devices based on firmware files using the format described by the PLDM for Firmware Update standard. This library consists of logic to parse the PLDM file format from a firmware file object, as well as common logic for sending the relevant PLDM header data to the device firmware. A simple ops table is provided so that device drivers can implement device specific hardware interactions while keeping the common logic to the pldmfw library. This library will be used by the Intel ice networking driver as part of implementing device flash update via devlink. The library aims to be vendor and device agnostic. For this reason, it has been placed in lib/pldmfw, in the hopes that other devices which use the PLDM firmware file format may benefit from it in the future. However, do note that not all features defined in the PLDM standard have been implemented. Signed-off-by: Jacob Keller Signed-off-by: David S. Miller --- include/linux/pldmfw.h | 165 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) create mode 100644 include/linux/pldmfw.h (limited to 'include/linux') diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h new file mode 100644 index 000000000000..0fc831338226 --- /dev/null +++ b/include/linux/pldmfw.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2018-2019, Intel Corporation. */ + +#ifndef _PLDMFW_H_ +#define _PLDMFW_H_ + +#include +#include + +#define PLDM_DEVICE_UPDATE_CONTINUE_AFTER_FAIL BIT(0) + +#define PLDM_STRING_TYPE_UNKNOWN 0 +#define PLDM_STRING_TYPE_ASCII 1 +#define PLDM_STRING_TYPE_UTF8 2 +#define PLDM_STRING_TYPE_UTF16 3 +#define PLDM_STRING_TYPE_UTF16LE 4 +#define PLDM_STRING_TYPE_UTF16BE 5 + +struct pldmfw_record { + struct list_head entry; + + /* List of descriptor TLVs */ + struct list_head descs; + + /* Component Set version string*/ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* Package Data length */ + u16 package_data_len; + + /* Bitfield of Device Update Flags */ + u32 device_update_flags; + + /* Package Data block */ + const u8 *package_data; + + /* Bitmap of components applicable to this record */ + unsigned long *component_bitmap; + u16 component_bitmap_len; +}; + +/* Standard descriptor TLV identifiers */ +#define PLDM_DESC_ID_PCI_VENDOR_ID 0x0000 +#define PLDM_DESC_ID_IANA_ENTERPRISE_ID 0x0001 +#define PLDM_DESC_ID_UUID 0x0002 +#define PLDM_DESC_ID_PNP_VENDOR_ID 0x0003 +#define PLDM_DESC_ID_ACPI_VENDOR_ID 0x0004 +#define PLDM_DESC_ID_PCI_DEVICE_ID 0x0100 +#define PLDM_DESC_ID_PCI_SUBVENDOR_ID 0x0101 +#define PLDM_DESC_ID_PCI_SUBDEV_ID 0x0102 +#define PLDM_DESC_ID_PCI_REVISION_ID 0x0103 +#define PLDM_DESC_ID_PNP_PRODUCT_ID 0x0104 +#define PLDM_DESC_ID_ACPI_PRODUCT_ID 0x0105 +#define PLDM_DESC_ID_VENDOR_DEFINED 0xFFFF + +struct pldmfw_desc_tlv { + struct list_head entry; + + const u8 *data; + u16 type; + u16 size; +}; + +#define PLDM_CLASSIFICATION_UNKNOWN 0x0000 +#define PLDM_CLASSIFICATION_OTHER 0x0001 +#define PLDM_CLASSIFICATION_DRIVER 0x0002 +#define PLDM_CLASSIFICATION_CONFIG_SW 0x0003 +#define PLDM_CLASSIFICATION_APP_SW 0x0004 +#define PLDM_CLASSIFICATION_INSTRUMENTATION 0x0005 +#define PLDM_CLASSIFICATION_BIOS 0x0006 +#define PLDM_CLASSIFICATION_DIAGNOSTIC_SW 0x0007 +#define PLDM_CLASSIFICATION_OS 0x0008 +#define PLDM_CLASSIFICATION_MIDDLEWARE 0x0009 +#define PLDM_CLASSIFICATION_FIRMWARE 0x000A +#define PLDM_CLASSIFICATION_CODE 0x000B +#define PLDM_CLASSIFICATION_SERVICE_PACK 0x000C +#define PLDM_CLASSIFICATION_SOFTWARE_BUNDLE 0x000D + +#define PLDM_ACTIVATION_METHOD_AUTO BIT(0) +#define PLDM_ACTIVATION_METHOD_SELF_CONTAINED BIT(1) +#define PLDM_ACTIVATION_METHOD_MEDIUM_SPECIFIC BIT(2) +#define PLDM_ACTIVATION_METHOD_REBOOT BIT(3) +#define PLDM_ACTIVATION_METHOD_DC_CYCLE BIT(4) +#define PLDM_ACTIVATION_METHOD_AC_CYCLE BIT(5) + +#define PLDMFW_COMPONENT_OPTION_FORCE_UPDATE BIT(0) +#define PLDMFW_COMPONENT_OPTION_USE_COMPARISON_STAMP BIT(1) + +struct pldmfw_component { + struct list_head entry; + + /* component identifier */ + u16 classification; + u16 identifier; + + u16 options; + u16 activation_method; + + u32 comparison_stamp; + + u32 component_size; + const u8 *component_data; + + /* Component version string */ + const u8 *version_string; + u8 version_type; + u8 version_len; + + /* component index */ + u8 index; + +}; + +/* Transfer flag used for sending components to the firmware */ +#define PLDM_TRANSFER_FLAG_START BIT(0) +#define PLDM_TRANSFER_FLAG_MIDDLE BIT(1) +#define PLDM_TRANSFER_FLAG_END BIT(2) + +struct pldmfw_ops; + +/* Main entry point to the PLDM firmware update engine. Device drivers + * should embed this in a private structure and use container_of to obtain + * a pointer to their own data, used to implement the device specific + * operations. + */ +struct pldmfw { + const struct pldmfw_ops *ops; + struct device *dev; +}; + +bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); + +/* Operations invoked by the generic PLDM firmware update engine. Used to + * implement device specific logic. + * + * @match_record: check if the device matches the given record. For + * convenience, a standard implementation is provided for PCI devices. + * + * @send_package_data: send the package data associated with the matching + * record to firmware. + * + * @send_component_table: send the component data associated with a given + * component to firmware. Called once for each applicable component. + * + * @flash_component: Flash the data for a given component to the device. + * Called once for each applicable component, after all component tables have + * been sent. + * + * @finalize_update: (optional) Finish the update. Called after all components + * have been flashed. + */ +struct pldmfw_ops { + bool (*match_record)(struct pldmfw *context, struct pldmfw_record *record); + int (*send_package_data)(struct pldmfw *context, const u8 *data, u16 length); + int (*send_component_table)(struct pldmfw *context, struct pldmfw_component *component, + u8 transfer_flag); + int (*flash_component)(struct pldmfw *context, struct pldmfw_component *component); + int (*finalize_update)(struct pldmfw *context); +}; + +int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw); + +#endif -- cgit v1.2.3 From 48040793fa6003d211f021c6ad273477bcd90d91 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Thu, 30 Jul 2020 15:44:40 -0700 Subject: tcp: add earliest departure time to SCM_TIMESTAMPING_OPT_STATS This change adds TCP_NLA_EDT to SCM_TIMESTAMPING_OPT_STATS that reports the earliest departure time(EDT) of the timestamped skb. By tracking EDT values of the skb from different timestamps, we can observe when and how much the value changed. This allows to measure the precise delay injected on the sender host e.g. by a bpf-base throttler. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 527d668a5275..14b62d7df942 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -484,7 +484,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp) tp->saved_syn = NULL; } -struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk); +struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, + const struct sk_buff *orig_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { -- cgit v1.2.3 From 829eb208e80d6db95c0201cb8fa00c2f9ad87faf Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 31 Jul 2020 17:34:01 -0700 Subject: rtnetlink: add support for protodown reason netdev protodown is a mechanism that allows protocols to hold an interface down. It was initially introduced in the kernel to hold links down by a multihoming protocol. There was also an attempt to introduce protodown reason at the time but was rejected. protodown and protodown reason is supported by almost every switching and routing platform. It was ok for a while to live without a protodown reason. But, its become more critical now given more than one protocol may need to keep a link down on a system at the same time. eg: vrrp peer node, port security, multihoming protocol. Its common for Network operators and protocol developers to look for such a reason on a networking box (Its also known as errDisable by most networking operators) This patch adds support for link protodown reason attribute. There are two ways to maintain protodown reasons. (a) enumerate every possible reason code in kernel - A protocol developer has to make a request and have that appear in a certain kernel version (b) provide the bits in the kernel, and allow user-space (sysadmin or NOS distributions) to manage the bit-to-reasonname map. - This makes extending reason codes easier (kind of like the iproute2 table to vrf-name map /etc/iproute2/rt_tables.d/) This patch takes approach (b). a few things about the patch: - It treats the protodown reason bits as counter to indicate active protodown users - Since protodown attribute is already an exposed UAPI, the reason is not enforced on a protodown set. Its a no-op if not used. the patch follows the below algorithm: - presence of reason bits set indicates protodown is in use - user can set protodown and protodown reason in a single or multiple setlink operations - setlink operation to clear protodown, will return -EBUSY if there are active protodown reason bits - reason is not included in link dumps if not used example with patched iproute2: $cat /etc/iproute2/protodown_reasons.d/r.conf 0 mlag 1 evpn 2 vrrp 3 psecurity $ip link set dev vxlan0 protodown on protodown_reason vrrp on $ip link set dev vxlan0 protodown_reason mlag on $ip link show 14: vxlan0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether f6:06:be:17:91:e7 brd ff:ff:ff:ff:ff:ff protodown on $ip link set dev vxlan0 protodown_reason mlag off $ip link set dev vxlan0 protodown off protodown_reason vrrp off Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ac2cd3f49aba..ba0fa6b22787 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2058,6 +2058,8 @@ struct net_device { struct timer_list watchdog_timer; int watchdog_timeo; + u32 proto_down_reason; + struct list_head todo_list; int __percpu *pcpu_refcnt; @@ -3810,6 +3812,8 @@ int dev_get_port_parent_id(struct net_device *dev, bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); +void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, + u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From 73b11c2ab072d5b0599d1e12cc126f55ee306daf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 31 Jul 2020 11:28:26 -0700 Subject: bpf: Add support for forced LINK_DETACH command Add LINK_DETACH command to force-detach bpf_link without destroying it. It has the same behavior as auto-detaching of bpf_link due to cgroup dying for bpf_cgroup_link or net_device being destroyed for bpf_xdp_link. In such case, bpf_link is still a valid kernel object, but is defuncts and doesn't hold BPF program attached to corresponding BPF hook. This functionality allows users with enough access rights to manually force-detach attached bpf_link without killing respective owner process. This patch implements LINK_DETACH for cgroup, xdp, and netns links, mostly re-using existing link release handling code. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20200731182830.286260-2-andriin@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 40c5e206ecf2..cef4ef0d2b4e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -793,6 +793,7 @@ struct bpf_link { struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); + int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); -- cgit v1.2.3 From c83e2a6e2fbbb7d47ea46fd7cb1f01292f2d0b6e Mon Sep 17 00:00:00 2001 From: Ajay Singh Date: Fri, 17 Jul 2020 05:11:38 +0000 Subject: wilc1000: Move wilc1000 SDIO ID's from driver source to common header file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Moved macros used for Vendor/Device ID from wilc1000 driver to common header file and changed macro name for consistency with other macros. Signed-off-by: Ajay Singh Acked-by: Ulf Hansson Acked-by: Pali Rohár Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20200717051134.19160-1-ajay.kathat@microchip.com --- include/linux/mmc/sdio_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 15ed8ce9d394..519820d18e62 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -105,6 +105,9 @@ #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 #define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 +#define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 +#define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 + #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 #define SDIO_DEVICE_ID_SIANO_NICE 0x0202 -- cgit v1.2.3 From 4e56cde15f7d68cf86ff8efff8504497de152475 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Fri, 31 Jul 2020 21:38:30 +0300 Subject: mac80211: Handle special status codes in SAE commit SAE authentication has been extended with H2E (IEEE 802.11 REVmd) and PK (WFA) options. Those extensions use special status code values in the SAE commit messages (Authentication frame with transaction sequence number 1) to identify which extension is in use. mac80211 was interpreting those new values as the AP denying authentication and that resulted in failure to complete SAE authentication in some cases. Fix this by adding exceptions for the new status code values 126 and 127. Signed-off-by: Jouni Malinen Link: https://lore.kernel.org/r/20200731183830.18735-1-jouni@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9f732499ea88..c47f43e65a2f 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2561,6 +2561,8 @@ enum ieee80211_statuscode { /* 802.11ai */ WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, + WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, + WLAN_STATUS_SAE_PK = 127, }; -- cgit v1.2.3 From bb3831294cd50750806f2ce8d73317dc8feeda09 Mon Sep 17 00:00:00 2001 From: Bruno Thomsen Date: Thu, 30 Jul 2020 21:57:48 +0200 Subject: net: mdiobus: add reset-post-delay-us handling Load new "reset-post-delay-us" value from MDIO properties, and if configured to a greater then zero delay do a flexible sleeping delay after MDIO bus reset deassert. This allows devices to exit reset state before start bus communication. Signed-off-by: Bruno Thomsen Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0403eb799913..3a09d2bf69ea 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -293,6 +293,8 @@ struct mii_bus { /* GPIO reset pulse width in microseconds */ int reset_delay_us; + /* GPIO reset deassert delay in microseconds */ + int reset_post_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; -- cgit v1.2.3 From 038ebb1a713d114d54dbf14868a73181c0c92758 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 31 Jul 2020 10:45:01 +0800 Subject: net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct When openvswitch conntrack offload with act_ct action. Fragment packets defrag in the ingress tc act_ct action and miss the next chain. Then the packet pass to the openvswitch datapath without the mru. The over mtu packet will be dropped in output action in openvswitch for over mtu. "kernel: net2: dropped over-mtu packet: 1528 > 1500" This patch add mru in the tc_skb_ext for adefrag and miss next chain situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru to the qdisc_skb_cb when the packet defrag. And When the chain miss, The mru is set to tc_skb_ext which can be got by ovs datapath. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: wenxu Reviewed-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa817a105517..3ad65d4ce085 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -283,6 +283,7 @@ struct nf_bridge_info { */ struct tc_skb_ext { __u32 chain; + __u16 mru; }; #endif -- cgit v1.2.3 From 6c84a589972f6458da3168a68e7d65f6ca8687f8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 3 Aug 2020 13:03:52 -0700 Subject: net: dsa: loop: Move data structures to header In preparation for adding support for a mockup data path, move the driver data structures to include/linux/dsa/loop.h such that we can share them between net/dsa/ and drivers/net/dsa/ later on. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/loop.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/linux/dsa/loop.h (limited to 'include/linux') diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h new file mode 100644 index 000000000000..bb39401a8056 --- /dev/null +++ b/include/linux/dsa/loop.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef DSA_LOOP_H +#define DSA_LOOP_H + +#include +#include +#include + +struct dsa_loop_vlan { + u16 members; + u16 untagged; +}; + +struct dsa_loop_mib_entry { + char name[ETH_GSTRING_LEN]; + unsigned long val; +}; + +enum dsa_loop_mib_counters { + DSA_LOOP_PHY_READ_OK, + DSA_LOOP_PHY_READ_ERR, + DSA_LOOP_PHY_WRITE_OK, + DSA_LOOP_PHY_WRITE_ERR, + __DSA_LOOP_CNT_MAX, +}; + +struct dsa_loop_port { + struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; + u16 pvid; +}; + +struct dsa_loop_priv { + struct mii_bus *bus; + unsigned int port_base; + struct dsa_loop_vlan vlans[VLAN_N_VID]; + struct net_device *netdev; + struct dsa_loop_port ports[DSA_MAX_PORTS]; +}; + +#endif /* DSA_LOOP_H */ -- cgit v1.2.3 From c99194eded25deb58f606e59b3101ba05e786021 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 3 Aug 2020 13:03:53 -0700 Subject: net: dsa: loop: Wire-up MTU callbacks For now we simply store the port MTU into a per-port member. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/dsa/loop.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h index bb39401a8056..5a3470bcc8a7 100644 --- a/include/linux/dsa/loop.h +++ b/include/linux/dsa/loop.h @@ -27,6 +27,7 @@ enum dsa_loop_mib_counters { struct dsa_loop_port { struct dsa_loop_mib_entry mib[__DSA_LOOP_CNT_MAX]; u16 pvid; + int mtu; }; struct dsa_loop_priv { -- cgit v1.2.3 From df23bb18b44b9a1f2b54358201730e710a9df57f Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Tue, 4 Aug 2020 07:53:42 +0200 Subject: ipv4: route: Ignore output interface in FIB lookup for PMTU route Currently, processes sending traffic to a local bridge with an encapsulation device as a port don't get ICMP errors if they exceed the PMTU of the encapsulated link. David Ahern suggested this as a hack, but it actually looks like the correct solution: when we update the PMTU for a given destination by means of updating or creating a route exception, the encapsulation might trigger this because of PMTU discovery happening either on the encapsulation device itself, or its lower layer. This happens on bridged encapsulations only. The output interface shouldn't matter, because we already have a valid destination. Drop the output interface restriction from the associated route lookup. For UDP tunnels, we will now have a route exception created for the encapsulation itself, with a MTU value reflecting its headroom, which allows a bridge forwarding IP packets originated locally to deliver errors back to the sending socket. The behaviour is now consistent with IPv6 and verified with selftests pmtu_ipv{4,6}_br_{geneve,vxlan}{4,6}_exception introduced later in this series. v2: - reset output interface only for bridge ports (David Ahern) - add and use netif_is_any_bridge_port() helper (David Ahern) Suggested-by: David Ahern Signed-off-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88d40b9abaa1..90444622b703 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4840,6 +4840,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev) return dev->priv_flags & IFF_OVS_DATAPATH; } +static inline bool netif_is_any_bridge_port(const struct net_device *dev) +{ + return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); +} + static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; -- cgit v1.2.3