From 14fc6bd6b79c430f615500d0fe6cea4722110db8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:09 -0700 Subject: bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com --- include/linux/bpf.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 72221aea1c60..127067f71fd4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,15 @@ struct seq_operations; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); +struct bpf_iter_seq_info { + const struct seq_operations *seq_ops; + bpf_iter_init_seq_priv_t init_seq_private; + bpf_iter_fini_seq_priv_t fini_seq_private; + u32 seq_priv_size; +}; + /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ @@ -1189,18 +1198,12 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); -typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); - #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; - const struct seq_operations *seq_ops; - bpf_iter_init_seq_priv_t init_seq_private; - bpf_iter_fini_seq_priv_t fini_seq_private; - u32 seq_priv_size; u32 ctx_arg_info_size; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; + const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { -- cgit v1.2.3 From f9c792729581bd8b8473af163e8ab426c2c61d89 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:10 -0700 Subject: bpf: Refactor to provide aux info to bpf_iter_init_seq_priv_t This patch refactored target bpf_iter_init_seq_priv_t callback function to accept additional information. This will be needed in later patches for map element targets since a particular map should be passed to traverse elements for that particular map. In the future, other information may be passed to target as well, e.g., pid, cgroup id, etc. to customize the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com --- include/linux/bpf.h | 7 ++++++- include/linux/proc_fs.h | 3 ++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 127067f71fd4..ef52717336cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -33,11 +33,13 @@ struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; +struct bpf_iter_aux_info; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; -typedef int (*bpf_iter_init_seq_priv_t)(void *private_data); +typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, + struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; @@ -1198,6 +1200,9 @@ int bpf_obj_get_user(const char __user *pathname, int flags); extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } +struct bpf_iter_aux_info { +}; + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index d1eed1b43651..2df965cd0974 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -133,7 +133,8 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); -extern int bpf_iter_init_seq_net(void *priv_data); +struct bpf_iter_aux_info; +extern int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux); extern void bpf_iter_fini_seq_net(void *priv_data); #ifdef CONFIG_PROC_PID_ARCH_STATUS -- cgit v1.2.3 From afbf21dce668ef59482037596eaffbe5041e094c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:11 -0700 Subject: bpf: Support readonly/readwrite buffers in verifier Readonly and readwrite buffer register states are introduced. Totally four states, PTR_TO_RDONLY_BUF[_OR_NULL] and PTR_TO_RDWR_BUF[_OR_NULL] are supported. As suggested by their respective names, PTR_TO_RDONLY_BUF[_OR_NULL] are for readonly buffers and PTR_TO_RDWR_BUF[_OR_NULL] for read/write buffers. These new register states will be used by later bpf map element iterator. New register states share some similarity to PTR_TO_TP_BUFFER as it will calculate accessed buffer size during verification time. The accessed buffer size will be later compared to other metrics during later attach/link_create time. Similar to reg_state PTR_TO_BTF_ID_OR_NULL in bpf iterator programs, PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL reg_types can be set at prog->aux->bpf_ctx_arg_aux, and bpf verifier will retrieve the values during btf_ctx_access(). Later bpf map element iterator implementation will show how such information will be assigned during target registeration time. The verifier is also enhanced such that PTR_TO_RDONLY_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] helper argument, and PTR_TO_RDWR_BUF can be passed to ARG_PTR_TO_MEM[_OR_NULL] or ARG_PTR_TO_UNINIT_MEM. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184111.590274-1-yhs@fb.com --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef52717336cf..f9c4bb08f616 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -353,6 +353,10 @@ enum bpf_reg_type { PTR_TO_BTF_ID_OR_NULL, /* reg points to kernel struct or NULL */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ + PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ + PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ + PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ + PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -694,6 +698,8 @@ struct bpf_prog_aux { u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; + u32 max_rdonly_access; + u32 max_rdwr_access; const struct bpf_ctx_arg_aux *ctx_arg_info; struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ -- cgit v1.2.3 From a5cbe05a6673b85bed2a63ffcfea6a96c6410cff Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 Jul 2020 11:41:12 -0700 Subject: bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f9c4bb08f616..4175cf1f4665 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -107,6 +107,9 @@ struct bpf_map_ops { /* BTF name and id of struct allocated by map_alloc */ const char * const map_btf_name; int *map_btf_id; + + /* bpf_iter info used to open a seq_file */ + const struct bpf_iter_seq_info *iter_seq_info; }; struct bpf_map_memory { @@ -1207,12 +1210,18 @@ int bpf_obj_get_user(const char __user *pathname, int flags); int __init bpf_iter_ ## target(args) { return 0; } struct bpf_iter_aux_info { + struct bpf_map *map; }; +typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog, + struct bpf_iter_aux_info *aux); + #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; + bpf_iter_check_target_t check_target; u32 ctx_arg_info_size; + enum bpf_iter_link_info req_linfo; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; @@ -1223,6 +1232,13 @@ struct bpf_iter_meta { u64 seq_num; }; +struct bpf_iter__bpf_map_elem { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(void *, key); + __bpf_md_ptr(void *, value); +}; + int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -- cgit v1.2.3