diff options
Diffstat (limited to 'include/linux')
40 files changed, 1630 insertions, 265 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9a904f63f8c1..c201017b5730 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -96,6 +96,7 @@ enum bpf_return_type { struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; + bool pkt_access; enum bpf_return_type ret_type; enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; @@ -138,6 +139,13 @@ enum bpf_reg_type { */ PTR_TO_PACKET, PTR_TO_PACKET_END, /* skb->data + headlen */ + + /* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map + * elem value. We only allow this if we can statically verify that + * access from this register are going to fall within the size of the + * map element. + */ + PTR_TO_MAP_VALUE_ADJ, }; struct bpf_prog; @@ -151,7 +159,8 @@ struct bpf_verifier_ops { */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, enum bpf_reg_type *reg_type); - + int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, + const struct bpf_prog *prog); u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn, struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h new file mode 100644 index 000000000000..7035b997aaa5 --- /dev/null +++ b/include/linux/bpf_verifier.h @@ -0,0 +1,102 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _LINUX_BPF_VERIFIER_H +#define _LINUX_BPF_VERIFIER_H 1 + +#include <linux/bpf.h> /* for enum bpf_reg_type */ +#include <linux/filter.h> /* for MAX_BPF_STACK */ + + /* Just some arbitrary values so we can safely do math without overflowing and + * are obviously wrong for any sort of memory access. + */ +#define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) +#define BPF_REGISTER_MIN_RANGE -(1024 * 1024 * 1024) + +struct bpf_reg_state { + enum bpf_reg_type type; + /* + * Used to determine if any memory access using this register will + * result in a bad access. + */ + u64 min_value, max_value; + union { + /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ + s64 imm; + + /* valid when type == PTR_TO_PACKET* */ + struct { + u32 id; + u16 off; + u16 range; + }; + + /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | + * PTR_TO_MAP_VALUE_OR_NULL + */ + struct bpf_map *map_ptr; + }; +}; + +enum bpf_stack_slot_type { + STACK_INVALID, /* nothing was stored in this stack slot */ + STACK_SPILL, /* register spilled into stack */ + STACK_MISC /* BPF program wrote some data into this slot */ +}; + +#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ + +/* state of the program: + * type of all registers and stack info + */ +struct bpf_verifier_state { + struct bpf_reg_state regs[MAX_BPF_REG]; + u8 stack_slot_type[MAX_BPF_STACK]; + struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; +}; + +/* linked list of verifier states used to prune search */ +struct bpf_verifier_state_list { + struct bpf_verifier_state state; + struct bpf_verifier_state_list *next; +}; + +struct bpf_insn_aux_data { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ +}; + +#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ + +struct bpf_verifier_env; +struct bpf_ext_analyzer_ops { + int (*insn_hook)(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx); +}; + +/* single container for all structs + * one verifier_env per bpf_check() call + */ +struct bpf_verifier_env { + struct bpf_prog *prog; /* eBPF program being verified */ + struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ + int stack_size; /* number of states to be processed */ + struct bpf_verifier_state cur_state; /* current verifier state */ + struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ + const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ + void *analyzer_priv; /* pointer to external analyzer's private data */ + struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + u32 used_map_cnt; /* number of used maps */ + u32 id_gen; /* used to generate unique reg IDs */ + bool allow_ptr_leaks; + bool seen_direct_write; + bool varlen_map_value_access; + struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ +}; + +int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, + void *priv); + +#endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5261751f6bd4..5f5270941ba0 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -32,6 +32,7 @@ enum can_mode { * CAN common private data */ struct can_priv { + struct net_device *dev; struct can_device_stats can_stats; struct can_bittiming bittiming, data_bittiming; @@ -47,7 +48,7 @@ struct can_priv { u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; - struct timer_list restart_timer; + struct delayed_work restart_work; int (*do_set_bittiming)(struct net_device *dev); int (*do_set_data_bittiming)(struct net_device *dev); diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 82c3d3b7269d..138bbf721e70 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -162,10 +162,11 @@ static inline void cec_msg_standby(struct cec_msg *msg) /* One Touch Record Feature */ -static inline void cec_msg_record_off(struct cec_msg *msg) +static inline void cec_msg_record_off(struct cec_msg *msg, bool reply) { msg->len = 2; msg->msg[1] = CEC_MSG_RECORD_OFF; + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; } struct cec_op_arib_data { @@ -227,7 +228,7 @@ static inline void cec_set_digital_service_id(__u8 *msg, if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { *msg++ = (digital->channel.channel_number_fmt << 2) | (digital->channel.major >> 8); - *msg++ = digital->channel.major && 0xff; + *msg++ = digital->channel.major & 0xff; *msg++ = digital->channel.minor >> 8; *msg++ = digital->channel.minor & 0xff; *msg++ = 0; @@ -323,6 +324,7 @@ static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, } static inline void cec_msg_record_on(struct cec_msg *msg, + bool reply, const struct cec_op_record_src *rec_src) { switch (rec_src->type) { @@ -346,6 +348,7 @@ static inline void cec_msg_record_on(struct cec_msg *msg, rec_src->ext_phys_addr.phys_addr); break; } + msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0; } static inline void cec_ops_record_on(const struct cec_msg *msg, @@ -1141,6 +1144,75 @@ static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; } +static inline void cec_msg_vendor_command(struct cec_msg *msg, + __u8 size, const __u8 *vendor_cmd) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND; + memcpy(msg->msg + 2, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command(const struct cec_msg *msg, + __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *vendor_cmd = msg->msg + 2; +} + +static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg, + __u32 vendor_id, __u8 size, + const __u8 *vendor_cmd) +{ + if (size > 11) + size = 11; + msg->len = 5 + size; + msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID; + msg->msg[2] = vendor_id >> 16; + msg->msg[3] = (vendor_id >> 8) & 0xff; + msg->msg[4] = vendor_id & 0xff; + memcpy(msg->msg + 5, vendor_cmd, size); +} + +static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg, + __u32 *vendor_id, __u8 *size, + const __u8 **vendor_cmd) +{ + *size = msg->len - 5; + + if (*size > 11) + *size = 11; + *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; + *vendor_cmd = msg->msg + 5; +} + +static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg, + __u8 size, + const __u8 *rc_code) +{ + if (size > 14) + size = 14; + msg->len = 2 + size; + msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN; + memcpy(msg->msg + 2, rc_code, size); +} + +static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg, + __u8 *size, + const __u8 **rc_code) +{ + *size = msg->len - 2; + + if (*size > 14) + *size = 14; + *rc_code = msg->msg + 2; +} + static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) { msg->len = 2; @@ -1277,7 +1349,7 @@ static inline void cec_msg_user_control_pressed(struct cec_msg *msg, msg->len += 4; msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | (ui_cmd->channel_identifier.major >> 8); - msg->msg[4] = ui_cmd->channel_identifier.major && 0xff; + msg->msg[4] = ui_cmd->channel_identifier.major & 0xff; msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; break; diff --git a/include/linux/cec.h b/include/linux/cec.h index b3e22893a002..851968e803fa 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -364,7 +364,7 @@ struct cec_caps { * @num_log_addrs: how many logical addresses should be claimed. Set by the * caller. * @vendor_id: the vendor ID of the device. Set by the caller. - * @flags: set to 0. + * @flags: flags. * @osd_name: the OSD name of the device. Set by the caller. * @primary_device_type: the primary device type for each logical address. * Set by the caller. @@ -389,6 +389,9 @@ struct cec_log_addrs { __u8 features[CEC_MAX_LOG_ADDRS][12]; }; +/* Allow a fallback to unregistered */ +#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0) + /* Events */ /* Event that occurs when the adapter state changes */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 436aa4e42221..668569844d37 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused size_t variable is to validate @p is indeed a pointer - * type by making sure it can be dereferenced. + * The seemingly unused variable ___typecheck_p validates that @p is + * indeed a pointer type by using a pointer to typeof(*p) as the type. + * Taking a pointer to typeof(*p) again is needed in case p is void *. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ + typeof(*(p)) *___typecheck_p __maybe_unused; \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 242bf530edfc..34bd80512a0c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -1,6 +1,8 @@ #ifndef __CPUHOTPLUG_H #define __CPUHOTPLUG_H +#include <linux/types.h> + enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 66533e18276c..dc69df04abc1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -718,7 +718,7 @@ static inline int dma_mmap_wc(struct device *dev, #define dma_mmap_writecombine dma_mmap_wc #endif -#ifdef CONFIG_NEED_DMA_MAP_STATE +#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG) #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME #define DEFINE_DMA_UNMAP_LEN(LEN_NAME) __u32 LEN_NAME #define dma_unmap_addr(PTR, ADDR_NAME) ((PTR)->ADDR_NAME) diff --git a/include/linux/efi.h b/include/linux/efi.h index 7f5a58225385..0148a3046b48 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -118,6 +118,15 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +struct efi_boot_memmap { + efi_memory_desc_t **map; + unsigned long *map_size; + unsigned long *desc_size; + u32 *desc_ver; + unsigned long *key_ptr; + unsigned long *buff_size; +}; + /* * EFI capsule flags */ @@ -946,7 +955,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ - ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ + (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \ (md) = (void *)(md) + (m)->desc_size) /** @@ -1371,11 +1380,7 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, efi_loaded_image_t *image, int *cmd_line_len); efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, - efi_memory_desc_t **map, - unsigned long *map_size, - unsigned long *desc_size, - u32 *desc_ver, - unsigned long *key_ptr); + struct efi_boot_memmap *map); efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, @@ -1457,4 +1462,14 @@ extern void efi_call_virt_check_flags(unsigned long flags, const char *call); arch_efi_call_virt_teardown(); \ }) +typedef efi_status_t (*efi_exit_boot_map_processing)( + efi_system_table_t *sys_table_arg, + struct efi_boot_memmap *map, + void *priv); + +efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, + void *handle, + struct efi_boot_memmap *map, + void *priv, + efi_exit_boot_map_processing priv_func); #endif /* _LINUX_EFI_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 58205f33af02..7268ed076be8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -148,6 +148,7 @@ struct fsnotify_group { #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; + bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -179,7 +180,6 @@ struct fsnotify_group { spinlock_t access_lock; struct list_head access_list; wait_queue_head_t access_waitq; - atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; @@ -292,6 +292,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); +/* group destruction begins, stop queuing new events */ +extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ @@ -304,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); -/* Remove passed event from groups notification queue */ -extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ diff --git a/include/linux/if_link.h b/include/linux/if_link.h index f923d15b432c..0b17c585b5cd 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -25,5 +25,6 @@ struct ifla_vf_info { __u32 max_tx_rate; __u32 rss_query_en; __u32 trusted; + __be16 vlan_proto; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c6dbcd84a2c7..7e9a789be5e0 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -18,6 +18,7 @@ struct ipv6_devconf { __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; + __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; diff --git a/include/linux/irq.h b/include/linux/irq.h index b52424eaa0ed..0ac26c892fe2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -945,6 +945,16 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { } static inline void irq_gc_unlock(struct irq_chip_generic *gc) { } #endif +/* + * The irqsave variants are for usage in non interrupt code. Do not use + * them in irq_chip callbacks. Use irq_gc_lock() instead. + */ +#define irq_gc_lock_irqsave(gc, flags) \ + raw_spin_lock_irqsave(&(gc)->lock, flags) + +#define irq_gc_unlock_irqrestore(gc, flags) \ + raw_spin_unlock_irqrestore(&(gc)->lock, flags) + static inline void irq_reg_writel(struct irq_chip_generic *gc, u32 val, int reg_offset) { diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 2b6a204bd8d4..aa118bad1407 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -231,6 +231,11 @@ static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } +static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) +{ + return ktime_sub_ns(kt, msec * NSEC_PER_MSEC); +} + extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 116b284bc4ce..1f3568694a57 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -309,7 +309,8 @@ int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, struct ifla_vf_stats *vf_stats); u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); -int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); +int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, + u8 qos, __be16 proto); int mlx4_set_vf_rate(struct mlx4_dev *dev, int port, int vf, int min_tx_rate, int max_tx_rate); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 42da3552f7cb..59b50d3eedb4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -221,6 +221,7 @@ enum { MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, + MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, }; enum { @@ -1371,6 +1372,8 @@ int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable); int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val); int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv); +int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port, + bool *vlan_offload_disabled); int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index deaa2217214d..b4ee8f62ce8d 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -160,6 +160,7 @@ struct mlx4_qp_path { enum { /* fl */ MLX4_FL_CV = 1 << 6, + MLX4_FL_SV = 1 << 5, MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2, MLX4_FL_ETH_SRC_CHECK_MC_LB = 1 << 1, MLX4_FL_ETH_SRC_CHECK_UC_LB = 1 << 0, @@ -267,6 +268,7 @@ enum { MLX4_UPD_QP_PATH_MASK_FVL_RX = 16 + 32, MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_UC_LB = 18 + 32, MLX4_UPD_QP_PATH_MASK_ETH_SRC_CHECK_MC_LB = 19 + 32, + MLX4_UPD_QP_PATH_MASK_SV = 22 + 32, }; enum { /* param3 */ diff --git a/include/linux/mroute.h b/include/linux/mroute.h index d351fd3e1049..e5fb81376e92 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -120,5 +120,5 @@ struct mfc_cache { struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, - struct rtmsg *rtm, int nowait); + struct rtmsg *rtm, int nowait, u32 portid); #endif diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 3987b64040c5..19a1c0c2993b 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -116,7 +116,7 @@ struct mfc6_cache { struct rtmsg; extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, - struct rtmsg *rtm, int nowait); + struct rtmsg *rtm, int nowait, u32 portid); #ifdef CONFIG_IPV6_MROUTE extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2095b6ab3661..136ae6bbe81e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -789,6 +789,7 @@ enum { TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_MATCHALL, + TC_SETUP_CLSBPF, }; struct tc_cls_u32_offload; @@ -800,6 +801,7 @@ struct tc_to_netdev { struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; struct tc_cls_matchall_offload *cls_mall; + struct tc_cls_bpf_offload *cls_bpf; }; }; @@ -924,6 +926,14 @@ struct netdev_xdp { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * + * bool (*ndo_has_offload_stats)(int attr_id) + * Return true if this device supports offload stats of this attr_id. + * + * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, + * void *attr_data) + * Get statistics for offload operations by attr_id. Write it into the + * attr_data pointer. + * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is registered. @@ -936,7 +946,8 @@ struct netdev_xdp { * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); - * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); + * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, + * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); @@ -1155,6 +1166,10 @@ struct net_device_ops { struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); + bool (*ndo_has_offload_stats)(int attr_id); + int (*ndo_get_offload_stats)(int attr_id, + const struct net_device *dev, + void *attr_data); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, @@ -1173,7 +1188,8 @@ struct net_device_ops { int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, - int queue, u16 vlan, u8 qos); + int queue, u16 vlan, + u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); @@ -1783,7 +1799,7 @@ struct net_device { #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS - struct list_head nf_hooks_ingress; + struct nf_hook_entry __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 9230f9aee896..abc7fdcb9eb1 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -55,12 +55,34 @@ struct nf_hook_state { struct net_device *out; struct sock *sk; struct net *net; - struct list_head *hook_list; + struct nf_hook_entry __rcu *hook_entries; int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; +typedef unsigned int nf_hookfn(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state); +struct nf_hook_ops { + struct list_head list; + + /* User fills in from here down. */ + nf_hookfn *hook; + struct net_device *dev; + void *priv; + u_int8_t pf; + unsigned int hooknum; + /* Hooks are ordered in ascending priority. */ + int priority; +}; + +struct nf_hook_entry { + struct nf_hook_entry __rcu *next; + struct nf_hook_ops ops; + const struct nf_hook_ops *orig_ops; +}; + static inline void nf_hook_state_init(struct nf_hook_state *p, - struct list_head *hook_list, + struct nf_hook_entry *hook_entry, unsigned int hook, int thresh, u_int8_t pf, struct net_device *indev, @@ -76,26 +98,11 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->out = outdev; p->sk = sk; p->net = net; - p->hook_list = hook_list; + RCU_INIT_POINTER(p->hook_entries, hook_entry); p->okfn = okfn; } -typedef unsigned int nf_hookfn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state); - -struct nf_hook_ops { - struct list_head list; - /* User fills in from here down. */ - nf_hookfn *hook; - struct net_device *dev; - void *priv; - u_int8_t pf; - unsigned int hooknum; - /* Hooks are ordered in ascending priority. */ - int priority; -}; struct nf_sockopt_ops { struct list_head list; @@ -133,6 +140,8 @@ int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); +int _nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); +void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ @@ -161,7 +170,8 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - struct list_head *hook_list; + struct nf_hook_entry *hook_head; + int ret = 1; #ifdef HAVE_JUMP_LABEL if (__builtin_constant_p(pf) && @@ -170,16 +180,19 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, return 1; #endif - hook_list = &net->nf.hooks[pf][hook]; - - if (!list_empty(hook_list)) { + rcu_read_lock(); + hook_head = rcu_dereference(net->nf.hooks[pf][hook]); + if (hook_head) { struct nf_hook_state state; - nf_hook_state_init(&state, hook_list, hook, thresh, + nf_hook_state_init(&state, hook_head, hook, thresh, pf, indev, outdev, sk, net, okfn); - return nf_hook_slow(skb, &state); + + ret = nf_hook_slow(skb, &state); } - return 1; + rcu_read_unlock(); + + return ret; } static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 275505792664..1d1ef4e20512 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -4,13 +4,9 @@ #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { - unsigned int searched; unsigned int found; - unsigned int new; unsigned int invalid; unsigned int ignore; - unsigned int delete; - unsigned int delete_list; unsigned int insert; unsigned int insert_failed; unsigned int drop; diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index df78dc2b5524..dee0acd0dd31 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -1,68 +1,8 @@ #ifndef _CONNTRACK_PROTO_GRE_H #define _CONNTRACK_PROTO_GRE_H #include <asm/byteorder.h> - -/* GRE PROTOCOL HEADER */ - -/* GRE Version field */ -#define GRE_VERSION_1701 0x0 -#define GRE_VERSION_PPTP 0x1 - -/* GRE Protocol field */ -#define GRE_PROTOCOL_PPTP 0x880B - -/* GRE Flags */ -#define GRE_FLAG_C 0x80 -#define GRE_FLAG_R 0x40 -#define GRE_FLAG_K 0x20 -#define GRE_FLAG_S 0x10 -#define GRE_FLAG_A 0x80 - -#define GRE_IS_C(f) ((f)&GRE_FLAG_C) -#define GRE_IS_R(f) ((f)&GRE_FLAG_R) -#define GRE_IS_K(f) ((f)&GRE_FLAG_K) -#define GRE_IS_S(f) ((f)&GRE_FLAG_S) -#define GRE_IS_A(f) ((f)&GRE_FLAG_A) - -/* GRE is a mess: Four different standards */ -struct gre_hdr { -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u16 rec:3, - srr:1, - seq:1, - key:1, - routing:1, - csum:1, - version:3, - reserved:4, - ack:1; -#elif defined(__BIG_ENDIAN_BITFIELD) - __u16 csum:1, - routing:1, - key:1, - seq:1, - srr:1, - rec:3, - ack:1, - reserved:4, - version:3; -#else -#error "Adjust your <asm/byteorder.h> defines" -#endif - __be16 protocol; -}; - -/* modified GRE header for PPTP */ -struct gre_hdr_pptp { - __u8 flags; /* bitfield */ - __u8 version; /* should be GRE_VERSION_PPTP */ - __be16 protocol; /* should be GRE_PROTOCOL_PPTP */ - __be16 payload_len; /* size of ppp payload, not inc. gre header */ - __be16 call_id; /* peer's call_id for this session */ - __be32 seq; /* sequence number. Present if S==1 */ - __be32 ack; /* seq number of highest packet received by */ - /* sender in this session */ -}; +#include <net/gre.h> +#include <net/pptp.h> struct nf_ct_gre { unsigned int stream_timeout; diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 5fcd375ef175..33e37fb41d5d 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -11,22 +11,30 @@ static inline bool nf_hook_ingress_active(const struct sk_buff *skb) if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif - return !list_empty(&skb->dev->nf_hooks_ingress); + return rcu_access_pointer(skb->dev->nf_hooks_ingress); } +/* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { + struct nf_hook_entry *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; - nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, - NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, - skb->dev, NULL, NULL, dev_net(skb->dev), NULL); + /* Must recheck the ingress hook head, in the event it became NULL + * after the check in nf_hook_ingress_active evaluated to true. + */ + if (unlikely(!e)) + return 0; + + nf_hook_state_init(&state, e, NF_NETDEV_INGRESS, INT_MIN, + NFPROTO_NETDEV, skb->dev, NULL, NULL, + dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); } static inline void nf_hook_ingress_init(struct net_device *dev) { - INIT_LIST_HEAD(&dev->nf_hooks_ingress); + RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 66a1260b33de..01e84436cddf 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -571,56 +571,57 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) */ static inline int fault_in_multipages_writeable(char __user *uaddr, int size) { - int ret = 0; char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; + if (unlikely(uaddr > end)) + return -EFAULT; /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. */ - while (uaddr <= end) { - ret = __put_user(0, uaddr); - if (ret != 0) - return ret; + do { + if (unlikely(__put_user(0, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) - ret = __put_user(0, end); + return __put_user(0, end); - return ret; + return 0; } static inline int fault_in_multipages_readable(const char __user *uaddr, int size) { volatile char c; - int ret = 0; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) - return ret; + return 0; - while (uaddr <= end) { - ret = __get_user(c, uaddr); - if (ret != 0) - return ret; + if (unlikely(uaddr > end)) + return -EFAULT; + + do { + if (unlikely(__get_user(c, uaddr) != 0)) + return -EFAULT; uaddr += PAGE_SIZE; - } + } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) { - ret = __get_user(c, end); - (void)c; + return __get_user(c, end); } - return ret; + (void)c; + return 0; } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, diff --git a/include/linux/phy.h b/include/linux/phy.h index 2d24b283aa2d..e25f1830fbcf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -80,6 +80,7 @@ typedef enum { PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, + PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -123,6 +124,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "moca"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; + case PHY_INTERFACE_MODE_TRGMII: + return "trgmii"; default: return "unknown"; } diff --git a/include/linux/property.h b/include/linux/property.h index 3a2f9ae25c86..856e50b2140c 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -190,7 +190,7 @@ struct property_entry { .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ .is_array = true, \ .is_string = false, \ - { .pointer = { _type_##_data = _val_ } }, \ + { .pointer = { ._type_##_data = _val_ } }, \ } #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 6b15e168148a..5ad54fc66cf0 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -127,6 +127,11 @@ struct ptp_clock; * * @info: Structure describing the new clock. * @parent: Pointer to the parent device of the new clock. + * + * Returns a valid pointer on success or PTR_ERR on failure. If PHC + * support is missing at the configuration level, this function + * returns NULL, and drivers are expected to gracefully handle that + * case separately. */ extern struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 19027635df0d..734deb094618 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -674,6 +674,7 @@ union event_ring_data { struct iscsi_eqe_data iscsi_info; struct malicious_vf_eqe_data malicious_vf; struct initial_cleanup_eqe_data vf_init_cleanup; + struct regpair roce_handle; }; /* Event Ring Entry */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e4546abcea08..f9ae903bbb84 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -34,6 +34,8 @@ enum dcbx_protocol_type { DCBX_MAX_PROTOCOL_TYPE }; +#define QED_ROCE_PROTOCOL_INDEX (3) + #ifdef CONFIG_DCB #define QED_LLDP_CHASSIS_ID_STAT_LEN 4 #define QED_LLDP_PORT_ID_STAT_LEN 4 @@ -260,15 +262,15 @@ struct qed_dev_info { /* MFW version */ u32 mfw_rev; - bool rdma_supported; - u32 flash_size; u8 mf_mode; bool tx_switching; + bool rdma_supported; }; enum qed_sb_type { QED_SB_TYPE_L2_QUEUE, + QED_SB_TYPE_CNQ, }; enum qed_protocol { @@ -627,8 +629,9 @@ enum DP_MODULE { QED_MSG_SP = 0x100000, QED_MSG_STORAGE = 0x200000, QED_MSG_CXT = 0x800000, + QED_MSG_LL2 = 0x1000000, QED_MSG_ILT = 0x2000000, - QED_MSG_ROCE = 0x4000000, + QED_MSG_RDMA = 0x4000000, QED_MSG_DEBUG = 0x8000000, /* to be added...up to 0x8000000 */ }; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h new file mode 100644 index 000000000000..fd75c265dba3 --- /dev/null +++ b/include/linux/qed/qed_ll2_if.h @@ -0,0 +1,139 @@ +/* QLogic qed NIC Driver + * + * Copyright (c) 2015 QLogic Corporation + * + * This software is available 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. + */ + +#ifndef _QED_LL2_IF_H +#define _QED_LL2_IF_H + +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/skbuff.h> +#include <linux/version.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/qed/qed_if.h> + +struct qed_ll2_stats { + u64 gsi_invalid_hdr; + u64 gsi_invalid_pkt_length; + u64 gsi_unsupported_pkt_typ; + u64 gsi_crcchksm_error; + + u64 packet_too_big_discard; + u64 no_buff_discard; + + u64 rcv_ucast_bytes; + u64 rcv_mcast_bytes; + u64 rcv_bcast_bytes; + u64 rcv_ucast_pkts; + u64 rcv_mcast_pkts; + u64 rcv_bcast_pkts; + + u64 sent_ucast_bytes; + u64 sent_mcast_bytes; + u64 sent_bcast_bytes; + u64 sent_ucast_pkts; + u64 sent_mcast_pkts; + u64 sent_bcast_pkts; +}; + +#define QED_LL2_UNUSED_HANDLE (0xff) + +struct qed_ll2_cb_ops { + int (*rx_cb)(void *, struct sk_buff *, u32, u32); + int (*tx_cb)(void *, struct sk_buff *, bool); +}; + +struct qed_ll2_params { + u16 mtu; + bool drop_ttl0_packets; + bool rx_vlan_stripping; + u8 tx_tc; + bool frags_mapped; + u8 ll2_mac_address[ETH_ALEN]; +}; + +struct qed_ll2_ops { +/** + * @brief start - initializes ll2 + * + * @param cdev + * @param params - protocol driver configuration for the ll2. + * + * @return 0 on success, otherwise error value. + */ + int (*start)(struct qed_dev *cdev, struct qed_ll2_params *params); + +/** + * @brief stop - stops the ll2 + * + * @param cdev + * + * @return 0 on success, otherwise error value. + */ + int (*stop)(struct qed_dev *cdev); + +/** + * @brief start_xmit - transmits an skb over the ll2 interface + * + * @param cdev + * @param skb + * + * @return 0 on success, otherwise error value. + */ + int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb); + +/** + * @brief register_cb_ops - protocol driver register the callback for Rx/Tx + * packets. Should be called before `start'. + * + * @param cdev + * @param cookie - to be passed to the callback functions. + * @param ops - the callback functions to register for Rx / Tx. + * + * @return 0 on success, otherwise error value. + */ + void (*register_cb_ops)(struct qed_dev *cdev, + const struct qed_ll2_cb_ops *ops, + void *cookie); + +/** + * @brief get LL2 related statistics + * + * @param cdev + * @param stats - pointer to struct that would be filled with stats + * + * @return 0 on success, error otherwise. + */ + int (*get_stats)(struct qed_dev *cdev, struct qed_ll2_stats *stats); +}; + +#ifdef CONFIG_QED_LL2 +int qed_ll2_alloc_if(struct qed_dev *); +void qed_ll2_dealloc_if(struct qed_dev *); +#else +static const struct qed_ll2_ops qed_ll2_ops_pass = { + .start = NULL, + .stop = NULL, + .start_xmit = NULL, + .register_cb_ops = NULL, + .get_stats = NULL, +}; + +static inline int qed_ll2_alloc_if(struct qed_dev *cdev) +{ + return 0; +} + +static inline void qed_ll2_dealloc_if(struct qed_dev *cdev) +{ +} +#endif +#endif diff --git a/include/linux/qed/qed_roce_if.h b/include/linux/qed/qed_roce_if.h new file mode 100644 index 000000000000..53047d3fa678 --- /dev/null +++ b/include/linux/qed/qed_roce_if.h @@ -0,0 +1,604 @@ +/* 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 _QED_ROCE_IF_H +#define _QED_ROCE_IF_H +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/slab.h> +#include <linux/qed/qed_if.h> +#include <linux/qed/qed_ll2_if.h> +#include <linux/qed/rdma_common.h> + +enum qed_roce_ll2_tx_dest { + /* Light L2 TX Destination to the Network */ + QED_ROCE_LL2_TX_DEST_NW, + + /* Light L2 TX Destination to the Loopback */ + QED_ROCE_LL2_TX_DEST_LB, + QED_ROCE_LL2_TX_DEST_MAX +}; + +#define QED_RDMA_MAX_CNQ_SIZE (0xFFFF) + +/* rdma interface */ + +enum qed_roce_qp_state { + QED_ROCE_QP_STATE_RESET, + QED_ROCE_QP_STATE_INIT, + QED_ROCE_QP_STATE_RTR, + QED_ROCE_QP_STATE_RTS, + QED_ROCE_QP_STATE_SQD, + QED_ROCE_QP_STATE_ERR, + QED_ROCE_QP_STATE_SQE +}; + +enum qed_rdma_tid_type { + QED_RDMA_TID_REGISTERED_MR, + QED_RDMA_TID_FMR, + QED_RDMA_TID_MW_TYPE1, + QED_RDMA_TID_MW_TYPE2A +}; + +struct qed_rdma_events { + void *context; + void (*affiliated_event)(void *context, u8 fw_event_code, + void *fw_handle); + void (*unaffiliated_event)(void *context, u8 event_code); +}; + +struct qed_rdma_device { + u32 vendor_id; + u32 vendor_part_id; + u32 hw_ver; + u64 fw_ver; + + u64 node_guid; + u64 sys_image_guid; + + u8 max_cnq; + u8 max_sge; + u8 max_srq_sge; + u16 max_inline; + u32 max_wqe; + u32 max_srq_wqe; + u8 max_qp_resp_rd_atomic_resc; + u8 max_qp_req_rd_atomic_resc; + u64 max_dev_resp_rd_atomic_resc; + u32 max_cq; + u32 max_qp; + u32 max_srq; + u32 max_mr; + u64 max_mr_size; + u32 max_cqe; + u32 max_mw; + u32 max_fmr; + u32 max_mr_mw_fmr_pbl; + u64 max_mr_mw_fmr_size; + u32 max_pd; + u32 max_ah; + u8 max_pkey; + u16 max_srq_wr; + u8 max_stats_queues; + u32 dev_caps; + + /* Abilty to support RNR-NAK generation */ + +#define QED_RDMA_DEV_CAP_RNR_NAK_MASK 0x1 +#define QED_RDMA_DEV_CAP_RNR_NAK_SHIFT 0 + /* Abilty to support shutdown port */ +#define QED_RDMA_DEV_CAP_SHUTDOWN_PORT_MASK 0x1 +#define QED_RDMA_DEV_CAP_SHUTDOWN_PORT_SHIFT 1 + /* Abilty to support port active event */ +#define QED_RDMA_DEV_CAP_PORT_ACTIVE_EVENT_MASK 0x1 +#define QED_RDMA_DEV_CAP_PORT_ACTIVE_EVENT_SHIFT 2 + /* Abilty to support port change event */ +#define QED_RDMA_DEV_CAP_PORT_CHANGE_EVENT_MASK 0x1 +#define QED_RDMA_DEV_CAP_PORT_CHANGE_EVENT_SHIFT 3 + /* Abilty to support system image GUID */ +#define QED_RDMA_DEV_CAP_SYS_IMAGE_MASK 0x1 +#define QED_RDMA_DEV_CAP_SYS_IMAGE_SHIFT 4 + /* Abilty to support bad P_Key counter support */ +#define QED_RDMA_DEV_CAP_BAD_PKEY_CNT_MASK 0x1 +#define QED_RDMA_DEV_CAP_BAD_PKEY_CNT_SHIFT 5 + /* Abilty to support atomic operations */ +#define QED_RDMA_DEV_CAP_ATOMIC_OP_MASK 0x1 +#define QED_RDMA_DEV_CAP_ATOMIC_OP_SHIFT 6 +#define QED_RDMA_DEV_CAP_RESIZE_CQ_MASK 0x1 +#define QED_RDMA_DEV_CAP_RESIZE_CQ_SHIFT 7 + /* Abilty to support modifying the maximum number of + * outstanding work requests per QP + */ +#define QED_RDMA_DEV_CAP_RESIZE_MAX_WR_MASK 0x1 +#define QED_RDMA_DEV_CAP_RESIZE_MAX_WR_SHIFT 8 + /* Abilty to support automatic path migration */ +#define QED_RDMA_DEV_CAP_AUTO_PATH_MIG_MASK 0x1 +#define QED_RDMA_DEV_CAP_AUTO_PATH_MIG_SHIFT 9 + /* Abilty to support the base memory management extensions */ +#define QED_RDMA_DEV_CAP_BASE_MEMORY_EXT_MASK 0x1 +#define QED_RDMA_DEV_CAP_BASE_MEMORY_EXT_SHIFT 10 +#define QED_RDMA_DEV_CAP_BASE_QUEUE_EXT_MASK 0x1 +#define QED_RDMA_DEV_CAP_BASE_QUEUE_EXT_SHIFT 11 + /* Abilty to support multipile page sizes per memory region */ +#define QED_RDMA_DEV_CAP_MULTI_PAGE_PER_MR_EXT_MASK 0x1 +#define QED_RDMA_DEV_CAP_MULTI_PAGE_PER_MR_EXT_SHIFT 12 + /* Abilty to support block list physical buffer list */ +#define QED_RDMA_DEV_CAP_BLOCK_MODE_MASK 0x1 +#define QED_RDMA_DEV_CAP_BLOCK_MODE_SHIFT 13 + /* Abilty to support zero based virtual addresses */ +#define QED_RDMA_DEV_CAP_ZBVA_MASK 0x1 +#define QED_RDMA_DEV_CAP_ZBVA_SHIFT 14 + /* Abilty to support local invalidate fencing */ +#define QED_RDMA_DEV_CAP_LOCAL_INV_FENCE_MASK 0x1 +#define QED_RDMA_DEV_CAP_LOCAL_INV_FENCE_SHIFT 15 + /* Abilty to support Loopback on QP */ +#define QED_RDMA_DEV_CAP_LB_INDICATOR_MASK 0x1 +#define QED_RDMA_DEV_CAP_LB_INDICATOR_SHIFT 16 + u64 page_size_caps; + u8 dev_ack_delay; + u32 reserved_lkey; + u32 bad_pkey_counter; + struct qed_rdma_events events; +}; + +enum qed_port_state { + QED_RDMA_PORT_UP, + QED_RDMA_PORT_DOWN, +}; + +enum qed_roce_capability { + QED_ROCE_V1 = 1 << 0, + QED_ROCE_V2 = 1 << 1, +}; + +struct qed_rdma_port { + enum qed_port_state port_state; + int link_speed; + u64 max_msg_size; + u8 source_gid_table_len; + void *source_gid_table_ptr; + u8 pkey_table_len; + void *pkey_table_ptr; + u32 pkey_bad_counter; + enum qed_roce_capability capability; +}; + +struct qed_rdma_cnq_params { + u8 num_pbl_pages; + u64 pbl_ptr; +}; + +/* The CQ Mode affects the CQ doorbell transaction size. + * 64/32 bit machines should configure to 32/16 bits respectively. + */ +enum qed_rdma_cq_mode { + QED_RDMA_CQ_MODE_16_BITS, + QED_RDMA_CQ_MODE_32_BITS, +}; + +struct qed_roce_dcqcn_params { + u8 notification_point; + u8 reaction_point; + + /* fields for notification point */ + u32 cnp_send_timeout; + + /* fields for reaction point */ + u32 rl_bc_rate; + u16 rl_max_rate; + u16 rl_r_ai; + u16 rl_r_hai; + u16 dcqcn_g; + u32 dcqcn_k_us; + u32 dcqcn_timeout_us; +}; + +struct qed_rdma_start_in_params { + struct qed_rdma_events *events; + struct qed_rdma_cnq_params cnq_pbl_list[128]; + u8 desired_cnq; + enum qed_rdma_cq_mode cq_mode; + struct qed_roce_dcqcn_params dcqcn_params; + u16 max_mtu; + u8 mac_addr[ETH_ALEN]; + u8 iwarp_flags; +}; + +struct qed_rdma_add_user_out_params { + u16 dpi; + u64 dpi_addr; + u64 dpi_phys_addr; + u32 dpi_size; +}; + +enum roce_mode { + ROCE_V1, + ROCE_V2_IPV4, + ROCE_V2_IPV6, + MAX_ROCE_MODE +}; + +union qed_gid { + u8 bytes[16]; + u16 words[8]; + u32 dwords[4]; + u64 qwords[2]; + u32 ipv4_addr; +}; + +struct qed_rdma_register_tid_in_params { + u32 itid; + enum qed_rdma_tid_type tid_type; + u8 key; + u16 pd; + bool local_read; + bool local_write; + bool remote_read; + bool remote_write; + bool remote_atomic; + bool mw_bind; + u64 pbl_ptr; + bool pbl_two_level; + u8 pbl_page_size_log; + u8 page_size_log; + u32 fbo; + u64 length; + u64 vaddr; + bool zbva; + bool phy_mr; + bool dma_mr; + + bool dif_enabled; + u64 dif_error_addr; + u64 dif_runt_addr; +}; + +struct qed_rdma_create_cq_in_params { + u32 cq_handle_lo; + u32 cq_handle_hi; + u32 cq_size; + u16 dpi; + bool pbl_two_level; + u64 pbl_ptr; + u16 pbl_num_pages; + u8 pbl_page_size_log; + u8 cnq_id; + u16 int_timeout; +}; + +struct qed_rdma_create_srq_in_params { + u64 pbl_base_addr; + u64 prod_pair_addr; + u16 num_pages; + u16 pd_id; + u16 page_size; +}; + +struct qed_rdma_destroy_cq_in_params { + u16 icid; +}; + +struct qed_rdma_destroy_cq_out_params { + u16 num_cq_notif; +}; + +struct qed_rdma_create_qp_in_params { + u32 qp_handle_lo; + u32 qp_handle_hi; + u32 qp_handle_async_lo; + u32 qp_handle_async_hi; + bool use_srq; + bool signal_all; + bool fmr_and_reserved_lkey; + u16 pd; + u16 dpi; + u16 sq_cq_id; + u16 sq_num_pages; + u64 sq_pbl_ptr; + u8 max_sq_sges; + u16 rq_cq_id; + u16 rq_num_pages; + u64 rq_pbl_ptr; + u16 srq_id; + u8 stats_queue; +}; + +struct qed_rdma_create_qp_out_params { + u32 qp_id; + u16 icid; + void *rq_pbl_virt; + dma_addr_t rq_pbl_phys; + void *sq_pbl_virt; + dma_addr_t sq_pbl_phys; +}; + +struct qed_rdma_modify_qp_in_params { + u32 modify_flags; +#define QED_RDMA_MODIFY_QP_VALID_NEW_STATE_MASK 0x1 +#define QED_RDMA_MODIFY_QP_VALID_NEW_STATE_SHIFT 0 +#define QED_ROCE_MODIFY_QP_VALID_PKEY_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_PKEY_SHIFT 1 +#define QED_RDMA_MODIFY_QP_VALID_RDMA_OPS_EN_MASK 0x1 +#define QED_RDMA_MODIFY_QP_VALID_RDMA_OPS_EN_SHIFT 2 +#define QED_ROCE_MODIFY_QP_VALID_DEST_QP_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_DEST_QP_SHIFT 3 +#define QED_ROCE_MODIFY_QP_VALID_ADDRESS_VECTOR_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_ADDRESS_VECTOR_SHIFT 4 +#define QED_ROCE_MODIFY_QP_VALID_RQ_PSN_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_RQ_PSN_SHIFT 5 +#define QED_ROCE_MODIFY_QP_VALID_SQ_PSN_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_SQ_PSN_SHIFT 6 +#define QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_REQ_MASK 0x1 +#define QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_REQ_SHIFT 7 +#define QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_RESP_MASK 0x1 +#define QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_RESP_SHIFT 8 +#define QED_ROCE_MODIFY_QP_VALID_ACK_TIMEOUT_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_ACK_TIMEOUT_SHIFT 9 +#define QED_ROCE_MODIFY_QP_VALID_RETRY_CNT_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_RETRY_CNT_SHIFT 10 +#define QED_ROCE_MODIFY_QP_VALID_RNR_RETRY_CNT_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_RNR_RETRY_CNT_SHIFT 11 +#define QED_ROCE_MODIFY_QP_VALID_MIN_RNR_NAK_TIMER_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_MIN_RNR_NAK_TIMER_SHIFT 12 +#define QED_ROCE_MODIFY_QP_VALID_E2E_FLOW_CONTROL_EN_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_E2E_FLOW_CONTROL_EN_SHIFT 13 +#define QED_ROCE_MODIFY_QP_VALID_ROCE_MODE_MASK 0x1 +#define QED_ROCE_MODIFY_QP_VALID_ROCE_MODE_SHIFT 14 + + enum qed_roce_qp_state new_state; + u16 pkey; + bool incoming_rdma_read_en; + bool incoming_rdma_write_en; + bool incoming_atomic_en; + bool e2e_flow_control_en; + u32 dest_qp; + bool lb_indication; + u16 mtu; + u8 traffic_class_tos; + u8 hop_limit_ttl; + u32 flow_label; + union qed_gid sgid; + union qed_gid dgid; + u16 udp_src_port; + + u16 vlan_id; + + u32 rq_psn; + u32 sq_psn; + u8 max_rd_atomic_resp; + u8 max_rd_atomic_req; + u32 ack_timeout; + u8 retry_cnt; + u8 rnr_retry_cnt; + u8 min_rnr_nak_timer; + bool sqd_async; + u8 remote_mac_addr[6]; + u8 local_mac_addr[6]; + bool use_local_mac; + enum roce_mode roce_mode; +}; + +struct qed_rdma_query_qp_out_params { + enum qed_roce_qp_state state; + u32 rq_psn; + u32 sq_psn; + bool draining; + u16 mtu; + u32 dest_qp; + bool incoming_rdma_read_en; + bool incoming_rdma_write_en; + bool incoming_atomic_en; + bool e2e_flow_control_en; + union qed_gid sgid; + union qed_gid dgid; + u32 flow_label; + u8 hop_limit_ttl; + u8 traffic_class_tos; + u32 timeout; + u8 rnr_retry; + u8 retry_cnt; + u8 min_rnr_nak_timer; + u16 pkey_index; + u8 max_rd_atomic; + u8 max_dest_rd_atomic; + bool sqd_async; +}; + +struct qed_rdma_create_srq_out_params { + u16 srq_id; +}; + +struct qed_rdma_destroy_srq_in_params { + u16 srq_id; +}; + +struct qed_rdma_modify_srq_in_params { + u32 wqe_limit; + u16 srq_id; +}; + +struct qed_rdma_stats_out_params { + u64 sent_bytes; + u64 sent_pkts; + u64 rcv_bytes; + u64 rcv_pkts; +}; + +struct qed_rdma_counters_out_params { + u64 pd_count; + u64 max_pd; + u64 dpi_count; + u64 max_dpi; + u64 cq_count; + u64 max_cq; + u64 qp_count; + u64 max_qp; + u64 tid_count; + u64 max_tid; +}; + +#define QED_ROCE_TX_HEAD_FAILURE (1) +#define QED_ROCE_TX_FRAG_FAILURE (2) + +struct qed_roce_ll2_header { + void *vaddr; + dma_addr_t baddr; + size_t len; +}; + +struct qed_roce_ll2_buffer { + dma_addr_t baddr; + size_t len; +}; + +struct qed_roce_ll2_packet { + struct qed_roce_ll2_header header; + int n_seg; + struct qed_roce_ll2_buffer payload[RDMA_MAX_SGE_PER_SQ_WQE]; + int roce_mode; + enum qed_roce_ll2_tx_dest tx_dest; +}; + +struct qed_roce_ll2_tx_params { + int reserved; +}; + +struct qed_roce_ll2_rx_params { + u16 vlan_id; + u8 smac[ETH_ALEN]; + int rc; +}; + +struct qed_roce_ll2_cbs { + void (*tx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt); + + void (*rx_cb)(void *pdev, struct qed_roce_ll2_packet *pkt, + struct qed_roce_ll2_rx_params *params); +}; + +struct qed_roce_ll2_params { + u16 max_rx_buffers; + u16 max_tx_buffers; + u16 mtu; + u8 mac_address[ETH_ALEN]; + struct qed_roce_ll2_cbs cbs; + void *cb_cookie; +}; + +struct qed_roce_ll2_info { + u8 handle; + struct qed_roce_ll2_cbs cbs; + u8 mac_address[ETH_ALEN]; + void *cb_cookie; + + /* Lock to protect ll2 */ + struct mutex lock; +}; + +enum qed_rdma_type { + QED_RDMA_TYPE_ROCE, +}; + +struct qed_dev_rdma_info { + struct qed_dev_info common; + enum qed_rdma_type rdma_type; +}; + +struct qed_rdma_ops { + const struct qed_common_ops *common; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_rdma_info *info); + void *(*rdma_get_rdma_ctx)(struct qed_dev *cdev); + + int (*rdma_init)(struct qed_dev *dev, + struct qed_rdma_start_in_params *iparams); + + int (*rdma_add_user)(void *rdma_cxt, + struct qed_rdma_add_user_out_params *oparams); + + void (*rdma_remove_user)(void *rdma_cxt, u16 dpi); + int (*rdma_stop)(void *rdma_cxt); + struct qed_rdma_device* (*rdma_query_device)(void *rdma_cxt); + struct qed_rdma_port* (*rdma_query_port)(void *rdma_cxt); + int (*rdma_get_start_sb)(struct qed_dev *cdev); + int (*rdma_get_min_cnq_msix)(struct qed_dev *cdev); + void (*rdma_cnq_prod_update)(void *rdma_cxt, u8 cnq_index, u16 prod); + int (*rdma_get_rdma_int)(struct qed_dev *cdev, + struct qed_int_info *info); + int (*rdma_set_rdma_int)(struct qed_dev *cdev, u16 cnt); + int (*rdma_alloc_pd)(void *rdma_cxt, u16 *pd); + void (*rdma_dealloc_pd)(void *rdma_cxt, u16 pd); + int (*rdma_create_cq)(void *rdma_cxt, + struct qed_rdma_create_cq_in_params *params, + u16 *icid); + int (*rdma_destroy_cq)(void *rdma_cxt, + struct qed_rdma_destroy_cq_in_params *iparams, + struct qed_rdma_destroy_cq_out_params *oparams); + struct qed_rdma_qp * + (*rdma_create_qp)(void *rdma_cxt, + struct qed_rdma_create_qp_in_params *iparams, + struct qed_rdma_create_qp_out_params *oparams); + + int (*rdma_modify_qp)(void *roce_cxt, struct qed_rdma_qp *qp, + struct qed_rdma_modify_qp_in_params *iparams); + + int (*rdma_query_qp)(void *rdma_cxt, struct qed_rdma_qp *qp, + struct qed_rdma_query_qp_out_params *oparams); + int (*rdma_destroy_qp)(void *rdma_cxt, struct qed_rdma_qp *qp); + int + (*rdma_register_tid)(void *rdma_cxt, + struct qed_rdma_register_tid_in_params *iparams); + int (*rdma_deregister_tid)(void *rdma_cxt, u32 itid); + int (*rdma_alloc_tid)(void *rdma_cxt, u32 *itid); + void (*rdma_free_tid)(void *rdma_cxt, u32 itid); + int (*roce_ll2_start)(struct qed_dev *cdev, + struct qed_roce_ll2_params *params); + int (*roce_ll2_stop)(struct qed_dev *cdev); + int (*roce_ll2_tx)(struct qed_dev *cdev, + struct qed_roce_ll2_packet *packet, + struct qed_roce_ll2_tx_params *params); + int (*roce_ll2_post_rx_buffer)(struct qed_dev *cdev, + struct qed_roce_ll2_buffer *buf, + u64 cookie, u8 notify_fw); + int (*roce_ll2_set_mac_filter)(struct qed_dev *cdev, + u8 *old_mac_address, + u8 *new_mac_address); + int (*roce_ll2_stats)(struct qed_dev *cdev, + struct qed_ll2_stats *stats); +}; + +const struct qed_rdma_ops *qed_get_rdma_ops(void); + +#endif diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_roce.h new file mode 100644 index 000000000000..99fbe6d55acb --- /dev/null +++ b/include/linux/qed/qede_roce.h @@ -0,0 +1,88 @@ +/* QLogic qedr 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 QEDE_ROCE_H +#define QEDE_ROCE_H + +struct qedr_dev; +struct qed_dev; +struct qede_dev; + +enum qede_roce_event { + QEDE_UP, + QEDE_DOWN, + QEDE_CHANGE_ADDR, + QEDE_CLOSE +}; + +struct qede_roce_event_work { + struct list_head list; + struct work_struct work; + void *ptr; + enum qede_roce_event event; +}; + +struct qedr_driver { + unsigned char name[32]; + + struct qedr_dev* (*add)(struct qed_dev *, struct pci_dev *, + struct net_device *); + + void (*remove)(struct qedr_dev *); + void (*notify)(struct qedr_dev *, enum qede_roce_event); +}; + +/* APIs for RoCE driver to register callback handlers, + * which will be invoked when device is added, removed, ifup, ifdown + */ +int qede_roce_register_driver(struct qedr_driver *drv); +void qede_roce_unregister_driver(struct qedr_driver *drv); + +bool qede_roce_supported(struct qede_dev *dev); + +#if IS_ENABLED(CONFIG_INFINIBAND_QEDR) +int qede_roce_dev_add(struct qede_dev *dev); +void qede_roce_dev_event_open(struct qede_dev *dev); +void qede_roce_dev_event_close(struct qede_dev *dev); +void qede_roce_dev_remove(struct qede_dev *dev); +void qede_roce_event_changeaddr(struct qede_dev *qedr); +#else +static inline int qede_roce_dev_add(struct qede_dev *dev) +{ + return 0; +} + +static inline void qede_roce_dev_event_open(struct qede_dev *dev) {} +static inline void qede_roce_dev_event_close(struct qede_dev *dev) {} +static inline void qede_roce_dev_remove(struct qede_dev *dev) {} +static inline void qede_roce_event_changeaddr(struct qede_dev *qedr) {} +#endif +#endif diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index 187991c1f439..7663725faa94 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -28,6 +28,7 @@ #define RDMA_MAX_PDS (64 * 1024) #define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS +#define RDMA_NUM_STATISTIC_COUNTERS_BB MAX_NUM_VPORTS_BB #define RDMA_TASK_TYPE (PROTOCOLID_ROCE) diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index fd82584acd48..5c132d3188be 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,7 +1,7 @@ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> + * Copyright (c) 2015-2016 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * @@ -53,6 +53,11 @@ struct rhash_head { struct rhash_head __rcu *next; }; +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -137,6 +142,7 @@ struct rhashtable_params { * @key_len: Key length for hashfn * @elasticity: Maximum chain length before rehash * @p: Configuration parameters + * @rhlist: True if this is an rhltable * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping * @lock: Spin lock to protect walker list @@ -147,12 +153,21 @@ struct rhashtable { unsigned int key_len; unsigned int elasticity; struct rhashtable_params p; + bool rhlist; struct work_struct run_work; struct mutex mutex; spinlock_t lock; }; /** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + +/** * struct rhashtable_walker - Hash table walker * @list: List entry on list of walkers * @tbl: The table that we were walking over @@ -163,9 +178,10 @@ struct rhashtable_walker { }; /** - * struct rhashtable_iter - Hash table iterator, fits into netlink cb + * struct rhashtable_iter - Hash table iterator * @ht: Table to iterate through * @p: Current pointer + * @list: Current hash list pointer * @walker: Associated rhashtable walker * @slot: Current slot * @skip: Number of entries to skip in slot @@ -173,6 +189,7 @@ struct rhashtable_walker { struct rhashtable_iter { struct rhashtable *ht; struct rhash_head *p; + struct rhlist_head *list; struct rhashtable_walker walker; unsigned int slot; unsigned int skip; @@ -339,13 +356,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); -struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, - const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl, - void **data); -int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); +void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj); void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter); @@ -507,6 +522,31 @@ void rhashtable_destroy(struct rhashtable *ht); rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ tbl, hash, member) +/** + * rhl_for_each_rcu - iterate over rcu hash table list + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_rcu(pos, list) \ + for (pos = list; pos; pos = rcu_dereference_raw(pos->next)) + +/** + * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * @member: name of the &struct rlist_head within the hashable struct. + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_entry_rcu(tpos, pos, list, member) \ + for (pos = list; pos && rht_entry(tpos, pos, member); \ + pos = rcu_dereference_raw(pos->next)) + static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, const void *obj) { @@ -516,18 +556,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); } -/** - * rhashtable_lookup_fast - search hash table, inlined version - * @ht: hash table - * @key: the pointer to the key - * @params: hash table parameters - * - * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. - * - * Returns the first entry on which the compare function returned true. - */ -static inline void *rhashtable_lookup_fast( +/* Internal function, do not use. */ +static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { @@ -539,8 +569,6 @@ static inline void *rhashtable_lookup_fast( struct rhash_head *he; unsigned int hash; - rcu_read_lock(); - tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); @@ -549,8 +577,7 @@ restart: params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) continue; - rcu_read_unlock(); - return rht_obj(ht, he); + return he; } /* Ensure we see any new tables. */ @@ -559,96 +586,165 @@ restart: tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; - rcu_read_unlock(); return NULL; } +/** + * rhashtable_lookup - search hash table + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * This must only be called under the RCU read lock. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(ht, key, params); + + return he ? rht_obj(ht, he) : NULL; +} + +/** + * rhashtable_lookup_fast - search hash table, without RCU read lock + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Only use this function when you have other mechanisms guaranteeing + * that the object won't go away after the RCU read lock is released. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + void *obj; + + rcu_read_lock(); + obj = rhashtable_lookup(ht, key, params); + rcu_read_unlock(); + + return obj; +} + +/** + * rhltable_lookup - search hash list table + * @hlt: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. All matching entries are returned + * in a list. + * + * This must only be called under the RCU read lock. + * + * Returns the list of entries that match the given key. + */ +static inline struct rhlist_head *rhltable_lookup( + struct rhltable *hlt, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params); + + return he ? container_of(he, struct rhlist_head, rhead) : NULL; +} + /* Internal function, please use rhashtable_insert_fast() instead. This * function returns the existing element already in hashes in there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( struct rhashtable *ht, const void *key, struct rhash_head *obj, - const struct rhashtable_params params) + const struct rhashtable_params params, bool rhlist) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; - struct bucket_table *tbl, *new_tbl; + struct rhash_head __rcu **pprev; + struct bucket_table *tbl; struct rhash_head *head; spinlock_t *lock; - unsigned int elasticity; unsigned int hash; - void *data = NULL; - int err; + int elasticity; + void *data; -restart: rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); + hash = rht_head_hashfn(ht, tbl, obj, params); + lock = rht_bucket_lock(tbl, hash); + spin_lock_bh(lock); - /* All insertions must grab the oldest table containing - * the hashed bucket that is yet to be rehashed. - */ - for (;;) { - hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); - - if (tbl->rehash <= hash) - break; - + if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) { +slow_path: spin_unlock_bh(lock); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); + rcu_read_unlock(); + return rhashtable_insert_slow(ht, key, obj); } - new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); - if (unlikely(new_tbl)) { - tbl = rhashtable_insert_slow(ht, key, obj, new_tbl, &data); - if (!IS_ERR_OR_NULL(tbl)) - goto slow_path; + elasticity = ht->elasticity; + pprev = &tbl->buckets[hash]; + rht_for_each(head, tbl, hash) { + struct rhlist_head *plist; + struct rhlist_head *list; + + elasticity--; + if (!key || + (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head)))) + continue; + + data = rht_obj(ht, head); - err = PTR_ERR(tbl); - if (err == -EEXIST) - err = 0; + if (!rhlist) + goto out; - goto out; - } - err = -E2BIG; - if (unlikely(rht_grow_above_max(ht, tbl))) - goto out; + list = container_of(obj, struct rhlist_head, rhead); + plist = container_of(head, struct rhlist_head, rhead); - if (unlikely(rht_grow_above_100(ht, tbl))) { -slow_path: - spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht, tbl); - rcu_read_unlock(); - if (err) - return ERR_PTR(err); + RCU_INIT_POINTER(list->next, plist); + head = rht_dereference_bucket(head->next, tbl, hash); + RCU_INIT_POINTER(list->rhead.next, head); + rcu_assign_pointer(*pprev, obj); - goto restart; + goto good; } - err = 0; - elasticity = ht->elasticity; - rht_for_each(head, tbl, hash) { - if (key && - unlikely(!(params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head))))) { - data = rht_obj(ht, head); - goto out; - } - if (!--elasticity) - goto slow_path; - } + if (elasticity <= 0) + goto slow_path; + + data = ERR_PTR(-E2BIG); + if (unlikely(rht_grow_above_max(ht, tbl))) + goto out; + + if (unlikely(rht_grow_above_100(ht, tbl))) + goto slow_path; head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); RCU_INIT_POINTER(obj->next, head); + if (rhlist) { + struct rhlist_head *list; + + list = container_of(obj, struct rhlist_head, rhead); + RCU_INIT_POINTER(list->next, NULL); + } rcu_assign_pointer(tbl->buckets[hash], obj); @@ -656,11 +752,14 @@ slow_path: if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); +good: + data = NULL; + out: spin_unlock_bh(lock); rcu_read_unlock(); - return err ? ERR_PTR(err) : data; + return data; } /** @@ -685,7 +784,7 @@ static inline int rhashtable_insert_fast( { void *ret; - ret = __rhashtable_insert_fast(ht, NULL, obj, params); + ret = __rhashtable_insert_fast(ht, NULL, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); @@ -693,6 +792,58 @@ static inline int rhashtable_insert_fast( } /** + * rhltable_insert_key - insert object into hash list table + * @hlt: hash list table + * @key: the pointer to the key + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhltable_insert_key( + struct rhltable *hlt, const void *key, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead, + params, true)); +} + +/** + * rhltable_insert - insert object into hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take a per bucket spinlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket lock. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if the size grows + * beyond the watermark indicated by grow_decision() which can be passed + * to rhashtable_init(). + */ +static inline int rhltable_insert( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + const char *key = rht_obj(&hlt->ht, &list->rhead); + + key += params.key_offset; + + return rhltable_insert_key(hlt, key, list, params); +} + +/** * rhashtable_lookup_insert_fast - lookup and insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object @@ -722,7 +873,8 @@ static inline int rhashtable_lookup_insert_fast( BUG_ON(ht->p.obj_hashfn); - ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params); + ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); if (IS_ERR(ret)) return PTR_ERR(ret); @@ -759,7 +911,7 @@ static inline int rhashtable_lookup_insert_key( BUG_ON(!ht->p.obj_hashfn || !key); - ret = __rhashtable_insert_fast(ht, key, obj, params); + ret = __rhashtable_insert_fast(ht, key, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); @@ -783,13 +935,14 @@ static inline void *rhashtable_lookup_get_insert_key( { BUG_ON(!ht->p.obj_hashfn || !key); - return __rhashtable_insert_fast(ht, key, obj, params); + return __rhashtable_insert_fast(ht, key, obj, params, false); } /* Internal function, please use rhashtable_remove_fast() instead */ -static inline int __rhashtable_remove_fast( +static inline int __rhashtable_remove_fast_one( struct rhashtable *ht, struct bucket_table *tbl, - struct rhash_head *obj, const struct rhashtable_params params) + struct rhash_head *obj, const struct rhashtable_params params, + bool rhlist) { struct rhash_head __rcu **pprev; struct rhash_head *he; @@ -804,39 +957,66 @@ static inline int __rhashtable_remove_fast( pprev = &tbl->buckets[hash]; rht_for_each(he, tbl, hash) { + struct rhlist_head *list; + + list = container_of(he, struct rhlist_head, rhead); + if (he != obj) { + struct rhlist_head __rcu **lpprev; + pprev = &he->next; - continue; + + if (!rhlist) + continue; + + do { + lpprev = &list->next; + list = rht_dereference_bucket(list->next, + tbl, hash); + } while (list && obj != &list->rhead); + + if (!list) + continue; + + list = rht_dereference_bucket(list->next, tbl, hash); + RCU_INIT_POINTER(*lpprev, list); + err = 0; + break; } - rcu_assign_pointer(*pprev, obj->next); - err = 0; + obj = rht_dereference_bucket(obj->next, tbl, hash); + err = 1; + + if (rhlist) { + list = rht_dereference_bucket(list->next, tbl, hash); + if (list) { + RCU_INIT_POINTER(list->rhead.next, obj); + obj = &list->rhead; + err = 0; + } + } + + rcu_assign_pointer(*pprev, obj); break; } spin_unlock_bh(lock); + if (err > 0) { + atomic_dec(&ht->nelems); + if (unlikely(ht->p.automatic_shrinking && + rht_shrink_below_30(ht, tbl))) + schedule_work(&ht->run_work); + err = 0; + } + return err; } -/** - * rhashtable_remove_fast - remove object from hash table - * @ht: hash table - * @obj: pointer to hash head inside object - * @params: hash table parameters - * - * Since the hash chain is single linked, the removal operation needs to - * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. - * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. - * - * Returns zero on success, -ENOENT if the entry could not be found. - */ -static inline int rhashtable_remove_fast( +/* Internal function, please use rhashtable_remove_fast() instead */ +static inline int __rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, - const struct rhashtable_params params) + const struct rhashtable_params params, bool rhlist) { struct bucket_table *tbl; int err; @@ -850,24 +1030,60 @@ static inline int rhashtable_remove_fast( * visible then that guarantees the entry to still be in * the old tbl if it exists. */ - while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) && + while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params, + rhlist)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; - if (err) - goto out; - - atomic_dec(&ht->nelems); - if (unlikely(ht->p.automatic_shrinking && - rht_shrink_below_30(ht, tbl))) - schedule_work(&ht->run_work); - -out: rcu_read_unlock(); return err; } +/** + * rhashtable_remove_fast - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhashtable_remove_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + return __rhashtable_remove_fast(ht, obj, params, false); +} + +/** + * rhltable_remove - remove object from hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the + * shrink_decision function specified at rhashtable_init() returns true. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhltable_remove( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true); +} + /* Internal function, please use rhashtable_replace_fast() instead */ static inline int __rhashtable_replace_fast( struct rhashtable *ht, struct bucket_table *tbl, @@ -958,4 +1174,51 @@ static inline int rhashtable_walk_init(struct rhashtable *ht, return 0; } +/** + * rhltable_walk_enter - Initialise an iterator + * @hlt: Table to walk over + * @iter: Hash table Iterator + * + * This function prepares a hash table walk. + * + * Note that if you restart a walk after rhashtable_walk_stop you + * may see the same object twice. Also, you may miss objects if + * there are removals in between rhashtable_walk_stop and the next + * call to rhashtable_walk_start. + * + * For a completely stable walk you should construct your own data + * structure outside the hash table. + * + * This function may sleep so you must not call it from interrupt + * context or with spin locks held. + * + * You must call rhashtable_walk_exit after this function returns. + */ +static inline void rhltable_walk_enter(struct rhltable *hlt, + struct rhashtable_iter *iter) +{ + return rhashtable_walk_enter(&hlt->ht, iter); +} + +/** + * rhltable_free_and_destroy - free elements and destroy hash list table + * @hlt: the hash list table to destroy + * @free_fn: callback to release resources of element + * @arg: pointer passed to free_fn + * + * See documentation for rhashtable_free_and_destroy. + */ +static inline void rhltable_free_and_destroy(struct rhltable *hlt, + void (*free_fn)(void *ptr, + void *arg), + void *arg) +{ + return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); +} + +static inline void rhltable_destroy(struct rhltable *hlt) +{ + return rhltable_free_and_destroy(hlt, NULL, NULL); +} + #endif /* _LINUX_RHASHTABLE_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4c5662f05bda..9bf60b556bd2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -676,13 +676,23 @@ struct sk_buff { */ kmemcheck_bitfield_begin(flags1); __u16 queue_mapping; + +/* if you move cloned around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define CLONED_MASK (1 << 7) +#else +#define CLONED_MASK 1 +#endif +#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + + __u8 __cloned_offset[0]; __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, - xmit_more:1; - /* one bit hole */ + xmit_more:1, + __unused:1; /* one bit hole */ kmemcheck_bitfield_end(flags1); /* fields enclosed in headers_start/headers_end are copied @@ -3075,6 +3085,7 @@ bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); +int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, diff --git a/include/linux/swap.h b/include/linux/swap.h index b17cc4830fa6..4a529c984a3f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -257,6 +257,7 @@ static inline void workingset_node_pages_inc(struct radix_tree_node *node) static inline void workingset_node_pages_dec(struct radix_tree_node *node) { + VM_BUG_ON(!workingset_node_pages(node)); node->count--; } @@ -272,6 +273,7 @@ static inline void workingset_node_shadows_inc(struct radix_tree_node *node) static inline void workingset_node_shadows_dec(struct radix_tree_node *node) { + VM_BUG_ON(!workingset_node_shadows(node)); node->count -= 1U << RADIX_TREE_COUNT_SHIFT; } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c723a465125d..a17ae7b85218 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -19,6 +19,7 @@ #include <linux/skbuff.h> +#include <linux/win_minmax.h> #include <net/sock.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -212,7 +213,8 @@ struct tcp_sock { u8 reord; /* reordering detected */ } rack; u16 advmss; /* Advertised MSS */ - u8 unused; + u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + unused:7; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ @@ -234,9 +236,7 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ - struct rtt_meas { - u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ - } rtt_min[3]; + struct minmax rtt_min; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ @@ -268,6 +268,12 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 lost; /* Total data packets lost incl. rexmits */ + u32 app_limited; /* limited until "delivered" reaches this val */ + struct skb_mstamp first_tx_mstamp; /* start of window send phase */ + struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 1b5d1cd796e2..75b4aaf31a9d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -76,7 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes); +#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/include/linux/win_minmax.h b/include/linux/win_minmax.h new file mode 100644 index 000000000000..56569604278f --- /dev/null +++ b/include/linux/win_minmax.h @@ -0,0 +1,37 @@ +/** + * lib/minmax.c: windowed min/max tracker by Kathleen Nichols. + * + */ +#ifndef MINMAX_H +#define MINMAX_H + +#include <linux/types.h> + +/* A single data point for our parameterized min-max tracker */ +struct minmax_sample { + u32 t; /* time measurement was taken */ + u32 v; /* value measured */ +}; + +/* State for the parameterized min-max tracker */ +struct minmax { + struct minmax_sample s[3]; +}; + +static inline u32 minmax_get(const struct minmax *m) +{ + return m->s[0].v; +} + +static inline u32 minmax_reset(struct minmax *m, u32 t, u32 meas) +{ + struct minmax_sample val = { .t = t, .v = meas }; + + m->s[2] = m->s[1] = m->s[0] = val; + return m->s[0].v; +} + +u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas); +u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas); + +#endif |