From 540adea3809f61115d2a1ea4ed6e627613452ba1 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 13 Jan 2018 02:55:03 +0900 Subject: error-injection: Separate error-injection from kprobe Since error-injection framework is not limited to be used by kprobes, nor bpf. Other kernel subsystems can use it freely for checking safeness of error-injection, e.g. livepatch, ftrace etc. So this separate error-injection framework from kprobes. Some differences has been made: - "kprobe" word is removed from any APIs/structures. - BPF_ALLOW_ERROR_INJECTION() is renamed to ALLOW_ERROR_INJECTION() since it is not limited for BPF too. - CONFIG_FUNCTION_ERROR_INJECTION is the config item of this feature. It is automatically enabled if the arch supports error injection feature for kprobe or ftrace etc. Signed-off-by: Masami Hiramatsu Reviewed-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 ----------- include/linux/error-injection.h | 21 +++++++++++++++++++++ include/linux/kprobes.h | 1 - include/linux/module.h | 6 +++--- 4 files changed, 24 insertions(+), 15 deletions(-) create mode 100644 include/linux/error-injection.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 44f26f6df8fc..3496977203a3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -613,15 +613,4 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -#define BPF_ALLOW_ERROR_INJECTION(fname) \ -static unsigned long __used \ - __attribute__((__section__("_kprobe_error_inject_list"))) \ - _eil_addr_##fname = (unsigned long)fname; -#else -#define BPF_ALLOW_ERROR_INJECTION(fname) -#endif -#endif - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h new file mode 100644 index 000000000000..130a67c50dac --- /dev/null +++ b/include/linux/error-injection.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ERROR_INJECTION_H +#define _LINUX_ERROR_INJECTION_H + +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + +#include + +extern bool within_error_injection_list(unsigned long addr); + +#else /* !CONFIG_FUNCTION_ERROR_INJECTION */ + +#include +static inline bool within_error_injection_list(unsigned long addr) +{ + return false; +} + +#endif + +#endif /* _LINUX_ERROR_INJECTION_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 963fd364f3d6..9440a2fc8893 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -271,7 +271,6 @@ extern bool arch_kprobe_on_func_entry(unsigned long offset); extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); -extern bool within_kprobe_error_injection_list(unsigned long addr); struct kprobe_insn_cache { struct mutex mutex; diff --git a/include/linux/module.h b/include/linux/module.h index 548fa09fa806..792e51d83bda 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -476,9 +476,9 @@ struct module { unsigned int num_ctors; #endif -#ifdef CONFIG_BPF_KPROBE_OVERRIDE - unsigned int num_kprobe_ei_funcs; - unsigned long *kprobe_ei_funcs; +#ifdef CONFIG_FUNCTION_ERROR_INJECTION + unsigned int num_ei_funcs; + unsigned long *ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT -- cgit v1.2.3 From 663faf9f7beeaca4ad0176bb96c776eed9dad0c5 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 13 Jan 2018 02:55:33 +0900 Subject: error-injection: Add injectable error types Add injectable error types for each error-injectable function. One motivation of error injection test is to find software flaws, mistakes or mis-handlings of expectable errors. If we find such flaws by the test, that is a program bug, so we need to fix it. But if the tester miss input the error (e.g. just return success code without processing anything), it causes unexpected behavior even if the caller is correctly programmed to handle any errors. That is not what we want to test by error injection. To clarify what type of errors the caller must expect for each injectable function, this introduces injectable error types: - EI_ETYPE_NULL : means the function will return NULL if it fails. No ERR_PTR, just a NULL. - EI_ETYPE_ERRNO : means the function will return -ERRNO if it fails. - EI_ETYPE_ERRNO_NULL : means the function will return -ERRNO (ERR_PTR) or NULL. ALLOW_ERROR_INJECTION() macro is expanded to get one of NULL, ERRNO, ERRNO_NULL to record the error type for each function. e.g. ALLOW_ERROR_INJECTION(open_ctree, ERRNO) This error types are shown in debugfs as below. ==== / # cat /sys/kernel/debug/error_injection/list open_ctree [btrfs] ERRNO io_ctl_init [btrfs] ERRNO ==== Signed-off-by: Masami Hiramatsu Reviewed-by: Josef Bacik Signed-off-by: Alexei Starovoitov --- include/linux/error-injection.h | 6 ++++++ include/linux/module.h | 3 ++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/error-injection.h b/include/linux/error-injection.h index 130a67c50dac..280c61ecbf20 100644 --- a/include/linux/error-injection.h +++ b/include/linux/error-injection.h @@ -7,6 +7,7 @@ #include extern bool within_error_injection_list(unsigned long addr); +extern int get_injectable_error_type(unsigned long addr); #else /* !CONFIG_FUNCTION_ERROR_INJECTION */ @@ -16,6 +17,11 @@ static inline bool within_error_injection_list(unsigned long addr) return false; } +static inline int get_injectable_error_type(unsigned long addr) +{ + return EI_ETYPE_NONE; +} + #endif #endif /* _LINUX_ERROR_INJECTION_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 792e51d83bda..9642d3116718 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -477,8 +478,8 @@ struct module { #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION + struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; - unsigned long *ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT -- cgit v1.2.3 From 1110f3a9bcf394c06b81a98206aee9b6860653c8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:03 -0800 Subject: bpf: add map_alloc_check callback .map_alloc callbacks contain a number of checks validating user- -provided map attributes against constraints of a particular map type. For offloaded maps we will need to check map attributes without actually allocating any memory on the host. Add a new callback for validating attributes before any memory is allocated. This callback can be selectively implemented by map types for sharing code with offloads, or simply to separate the logical steps of validation and allocation. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-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 3496977203a3..263598619f90 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -25,6 +25,7 @@ struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ + int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); -- cgit v1.2.3 From bd475643d74e8ed78bfd36d941053b0e45974e8e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:06 -0800 Subject: bpf: add helper for copying attrs to struct bpf_map All map types reimplement the field-by-field copy of union bpf_attr members into struct bpf_map. Add a helper to perform this operation. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-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 263598619f90..c60ddfb34d41 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -378,6 +378,7 @@ void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); +void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From 0a9c1991f285f829fd786fa2a9c824c2a3f87bc6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:07 -0800 Subject: bpf: rename bpf_dev_offload -> bpf_prog_offload With map offload coming, we need to call program offload structure something less ambiguous. Pure rename, no functional changes. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c60ddfb34d41..9fff1ace1d8e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,7 +200,7 @@ struct bpf_prog_offload_ops { int insn_idx, int prev_insn_idx); }; -struct bpf_dev_offload { +struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; void *dev_priv; @@ -230,7 +230,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif - struct bpf_dev_offload *offload; + struct bpf_prog_offload *offload; union { struct work_struct work; struct rcu_head rcu; -- cgit v1.2.3 From a38845729ea3985db5d2544ec3ef3dc8f6313a27 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:09 -0800 Subject: bpf: offload: add map offload infrastructure BPF map offload follow similar path to program offload. At creation time users may specify ifindex of the device on which they want to create the map. Map will be validated by the kernel's .map_alloc_check callback and device driver will be called for the actual allocation. Map will have an empty set of operations associated with it (save for alloc and free callbacks). The real device callbacks are kept in map->offload->dev_ops because they have slightly different signatures. Map operations are called in process context so the driver may communicate with HW freely, msleep(), wait() etc. Map alloc and free callbacks are muxed via existing .ndo_bpf, and are always called with rtnl lock held. Maps and programs are guaranteed to be destroyed before .ndo_uninit (i.e. before unregister_netdev() returns). Map callbacks are invoked with bpf_devs_lock *read* locked, drivers must take care of exclusive locking if necessary. All offload-specific branches are marked with unlikely() (through bpf_map_is_dev_bound()), given that branch penalty will be negligible compared to IO anyway, and we don't want to penalize SW path unnecessarily. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/netdevice.h | 6 +++++ 2 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9fff1ace1d8e..5c2c104dc2c5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -74,6 +74,33 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offloaded_map; + +struct bpf_map_dev_ops { + int (*map_get_next_key)(struct bpf_offloaded_map *map, + void *key, void *next_key); + int (*map_lookup_elem)(struct bpf_offloaded_map *map, + void *key, void *value); + int (*map_update_elem)(struct bpf_offloaded_map *map, + void *key, void *value, u64 flags); + int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); +}; + +struct bpf_offloaded_map { + struct bpf_map map; + struct net_device *netdev; + const struct bpf_map_dev_ops *dev_ops; + void *dev_priv; + struct list_head offloads; +}; + +static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) +{ + return container_of(map, struct bpf_offloaded_map, map); +} + +extern const struct bpf_map_ops bpf_map_offload_ops; + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -369,6 +396,7 @@ int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); +void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -556,6 +584,15 @@ void bpf_prog_offload_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); +int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); +int bpf_map_offload_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags); +int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); +int bpf_map_offload_get_next_key(struct bpf_map *map, + void *key, void *next_key); + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); @@ -563,6 +600,14 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return aux->offload_requested; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return unlikely(map->ops == &bpf_map_offload_ops); +} + +struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); +void bpf_map_offload_map_free(struct bpf_map *map); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -574,6 +619,20 @@ static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { return false; } + +static inline bool bpf_map_is_dev_bound(struct bpf_map *map) +{ + return false; +} + +static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void bpf_map_offload_map_free(struct bpf_map *map) +{ +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef7b348e8498..0b3ab42d50fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -804,6 +804,8 @@ enum bpf_netdev_command { BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, + BPF_OFFLOAD_MAP_ALLOC, + BPF_OFFLOAD_MAP_FREE, }; struct bpf_prog_offload_ops; @@ -834,6 +836,10 @@ struct netdev_bpf { struct { struct bpf_prog *prog; } offload; + /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ + struct { + struct bpf_offloaded_map *offmap; + }; }; }; -- cgit v1.2.3