From 15d83c4d7cef5c067a8b075ce59e97df4f60706e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:00 -0700 Subject: bpf: Allow loading of a bpf_iter program A bpf_iter program is a tracing program with attach type BPF_TRACE_ITER. The load attribute attach_btf_id is used by the verifier against a particular kernel function, which represents a target, e.g., __bpf_iter__bpf_map for target bpf_map which is implemented later. The program return value must be 0 or 1 for now. 0 : successful, except potential seq_file buffer overflow which is handled by seq_file reader. 1 : request to restart the same object In the future, other return values may be used for filtering or teminating the iterator. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175900.2474947-1-yhs@fb.com --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6e5e7caa3739..c8a5325cc8d0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -218,6 +218,7 @@ enum bpf_attach_type { BPF_TRACE_FEXIT, BPF_MODIFY_RETURN, BPF_LSM_MAC, + BPF_TRACE_ITER, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From de4e05cac46d206f9090051ef09930514bff73e4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:01 -0700 Subject: bpf: Support bpf tracing/iter programs for BPF_LINK_CREATE Given a bpf program, the step to create an anonymous bpf iterator is: - create a bpf_iter_link, which combines bpf program and the target. In the future, there could be more information recorded in the link. A link_fd will be returned to the user space. - create an anonymous bpf iterator with the given link_fd. The bpf_iter_link can be pinned to bpffs mount file system to create a file based bpf iterator as well. The benefit to use of bpf_iter_link: - using bpf link simplifies design and implementation as bpf link is used for other tracing bpf programs. - for file based bpf iterator, bpf_iter_link provides a standard way to replace underlying bpf programs. - for both anonymous and free based iterators, bpf link query capability can be leveraged. The patch added support of tracing/iter programs for BPF_LINK_CREATE. A new link type BPF_LINK_TYPE_ITER is added to facilitate link querying. Currently, only prog_id is needed, so there is no additional in-kernel show_fdinfo() and fill_link_info() hook is needed for BPF_LINK_TYPE_ITER link. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175901.2475084-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/bpf_iter.c | 62 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 14 ++++++++++ tools/include/uapi/linux/bpf.h | 1 + 6 files changed, 80 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f28bdd714754..e93d2d33c82c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1143,6 +1143,7 @@ struct bpf_iter_reg { int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 8345cdf553b8..29d22752fc87 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) #ifdef CONFIG_CGROUP_BPF BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c8a5325cc8d0..1e8dfff5d5d4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -229,6 +229,7 @@ enum bpf_link_type { BPF_LINK_TYPE_RAW_TRACEPOINT = 1, BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, MAX_BPF_LINK_TYPE, }; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index dec182d8395a..03f5832909db 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -15,6 +15,11 @@ struct bpf_iter_target_info { u32 btf_id; /* cached value */ }; +struct bpf_iter_link { + struct bpf_link link; + struct bpf_iter_target_info *tinfo; +}; + static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); @@ -93,3 +98,60 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog) return supported; } + +static void bpf_iter_link_release(struct bpf_link *link) +{ +} + +static void bpf_iter_link_dealloc(struct bpf_link *link) +{ + struct bpf_iter_link *iter_link = + container_of(link, struct bpf_iter_link, link); + + kfree(iter_link); +} + +static const struct bpf_link_ops bpf_iter_link_lops = { + .release = bpf_iter_link_release, + .dealloc = bpf_iter_link_dealloc, +}; + +int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_iter_target_info *tinfo; + struct bpf_iter_link *link; + bool existed = false; + u32 prog_btf_id; + int err; + + if (attr->link_create.target_fd || attr->link_create.flags) + return -EINVAL; + + prog_btf_id = prog->aux->attach_btf_id; + mutex_lock(&targets_mutex); + list_for_each_entry(tinfo, &targets, list) { + if (tinfo->btf_id == prog_btf_id) { + existed = true; + break; + } + } + mutex_unlock(&targets_mutex); + if (!existed) + return -ENOENT; + + link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); + if (!link) + return -ENOMEM; + + bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); + link->tinfo = tinfo; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + return err; + } + + return bpf_link_settle(&link_primer); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index bb1ab7da6103..6ffe2d8fb6c7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; + case BPF_TRACE_ITER: + return BPF_PROG_TYPE_TRACING; default: return BPF_PROG_TYPE_UNSPEC; } @@ -3729,6 +3731,15 @@ err_put: return err; } +static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + if (attr->link_create.attach_type == BPF_TRACE_ITER && + prog->expected_attach_type == BPF_TRACE_ITER) + return bpf_iter_link_attach(attr, prog); + + return -EINVAL; +} + #define BPF_LINK_CREATE_LAST_FIELD link_create.flags static int link_create(union bpf_attr *attr) { @@ -3765,6 +3776,9 @@ static int link_create(union bpf_attr *attr) case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; + case BPF_PROG_TYPE_TRACING: + ret = tracing_bpf_link_attach(attr, prog); + break; default: ret = -EINVAL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c8a5325cc8d0..1e8dfff5d5d4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -229,6 +229,7 @@ enum bpf_link_type { BPF_LINK_TYPE_RAW_TRACEPOINT = 1, BPF_LINK_TYPE_TRACING = 2, BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, MAX_BPF_LINK_TYPE, }; -- cgit v1.2.3 From ac51d99bf81caac8d8881fe52098948110d0de68 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:05 -0700 Subject: bpf: Create anonymous bpf iterator A new bpf command BPF_ITER_CREATE is added. The anonymous bpf iterator is seq_file based. The seq_file private data are referenced by targets. The bpf_iter infrastructure allocated additional space at seq_file->private before the space used by targets to store some meta data, e.g., prog: prog to run session_id: an unique id for each opened seq_file seq_num: how many times bpf programs are queried in this session done_stop: an internal state to decide whether bpf program should be called in seq_ops->stop() or not The seq_num will start from 0 for valid objects. The bpf program may see the same seq_num more than once if - seq_file buffer overflow happens and the same object is retried by bpf_seq_read(), or - the bpf program explicitly requests a retry of the same object Since module is not supported for bpf_iter, all target registeration happens at __init time, so there is no need to change bpf_iter_unreg_target() as it is used mostly in error path of the init function at which time no bpf iterators have been created yet. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175905.2475770-1-yhs@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++ kernel/bpf/bpf_iter.c | 129 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 26 +++++++++ tools/include/uapi/linux/bpf.h | 6 ++ 5 files changed, 168 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e93d2d33c82c..80b1b9d8a638 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1144,6 +1144,7 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const char *target); bool bpf_iter_prog_supported(struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_new_fd(struct bpf_link *link); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1e8dfff5d5d4..708763f702e1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -116,6 +116,7 @@ enum bpf_cmd { BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, + BPF_ITER_CREATE, }; enum bpf_map_type { @@ -614,6 +615,11 @@ union bpf_attr { __u32 type; } enable_stats; + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 832973ee80fa..e7129b57865f 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include +#include #include #include @@ -20,12 +21,24 @@ struct bpf_iter_link { struct bpf_iter_target_info *tinfo; }; +struct bpf_iter_priv_data { + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u64 session_id; + u64 seq_num; + bool done_stop; + u8 target_private[] __aligned(8); +}; + static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); /* protect bpf_iter_link changes */ static DEFINE_MUTEX(link_mutex); +/* incremented on every opened seq_file */ +static atomic64_t session_id; + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -149,6 +162,33 @@ done: return copied; } +static int iter_release(struct inode *inode, struct file *file) +{ + struct bpf_iter_priv_data *iter_priv; + struct seq_file *seq; + + seq = file->private_data; + if (!seq) + return 0; + + iter_priv = container_of(seq->private, struct bpf_iter_priv_data, + target_private); + + if (iter_priv->tinfo->fini_seq_private) + iter_priv->tinfo->fini_seq_private(seq->private); + + bpf_prog_put(iter_priv->prog); + seq->private = iter_priv; + + return seq_release_private(inode, file); +} + +static const struct file_operations bpf_iter_fops = { + .llseek = no_llseek, + .read = bpf_seq_read, + .release = iter_release, +}; + int bpf_iter_reg_target(struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; @@ -309,3 +349,92 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) return bpf_link_settle(&link_primer); } + +static void init_seq_meta(struct bpf_iter_priv_data *priv_data, + struct bpf_iter_target_info *tinfo, + struct bpf_prog *prog) +{ + priv_data->tinfo = tinfo; + priv_data->prog = prog; + priv_data->session_id = atomic64_inc_return(&session_id); + priv_data->seq_num = 0; + priv_data->done_stop = false; +} + +static int prepare_seq_file(struct file *file, struct bpf_iter_link *link) +{ + struct bpf_iter_priv_data *priv_data; + struct bpf_iter_target_info *tinfo; + struct bpf_prog *prog; + u32 total_priv_dsize; + struct seq_file *seq; + int err = 0; + + mutex_lock(&link_mutex); + prog = link->link.prog; + bpf_prog_inc(prog); + mutex_unlock(&link_mutex); + + tinfo = link->tinfo; + total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + + tinfo->seq_priv_size; + priv_data = __seq_open_private(file, tinfo->seq_ops, total_priv_dsize); + if (!priv_data) { + err = -ENOMEM; + goto release_prog; + } + + if (tinfo->init_seq_private) { + err = tinfo->init_seq_private(priv_data->target_private); + if (err) + goto release_seq_file; + } + + init_seq_meta(priv_data, tinfo, prog); + seq = file->private_data; + seq->private = priv_data->target_private; + + return 0; + +release_seq_file: + seq_release_private(file->f_inode, file); + file->private_data = NULL; +release_prog: + bpf_prog_put(prog); + return err; +} + +int bpf_iter_new_fd(struct bpf_link *link) +{ + struct file *file; + unsigned int flags; + int err, fd; + + if (link->ops != &bpf_iter_link_lops) + return -EINVAL; + + flags = O_RDONLY | O_CLOEXEC; + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto free_fd; + } + + err = prepare_seq_file(file, + container_of(link, struct bpf_iter_link, link)); + if (err) + goto free_file; + + fd_install(fd, file); + return fd; + +free_file: + fput(file); +free_fd: + put_unused_fd(fd); + return err; +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6ffe2d8fb6c7..a293e88ee01a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3941,6 +3941,29 @@ static int bpf_enable_stats(union bpf_attr *attr) return -EINVAL; } +#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags + +static int bpf_iter_create(union bpf_attr *attr) +{ + struct bpf_link *link; + int err; + + if (CHECK_ATTR(BPF_ITER_CREATE)) + return -EINVAL; + + if (attr->iter_create.flags) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->iter_create.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + err = bpf_iter_new_fd(link); + bpf_link_put(link); + + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -4068,6 +4091,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; + case BPF_ITER_CREATE: + err = bpf_iter_create(&attr); + break; default: err = -EINVAL; break; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1e8dfff5d5d4..708763f702e1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -116,6 +116,7 @@ enum bpf_cmd { BPF_LINK_GET_FD_BY_ID, BPF_LINK_GET_NEXT_ID, BPF_ENABLE_STATS, + BPF_ITER_CREATE, }; enum bpf_map_type { @@ -614,6 +615,11 @@ union bpf_attr { __u32 type; } enable_stats; + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From 492e639f0c222784e2e0f121966375f641c61b15 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 9 May 2020 10:59:14 -0700 Subject: bpf: Add bpf_seq_printf and bpf_seq_write helpers Two helpers bpf_seq_printf and bpf_seq_write, are added for writing data to the seq_file buffer. bpf_seq_printf supports common format string flag/width/type fields so at least I can get identical results for netlink and ipv6_route targets. For bpf_seq_printf and bpf_seq_write, return value -EOVERFLOW specifically indicates a write failure due to overflow, which means the object will be repeated in the next bpf invocation if object collection stays the same. Note that if the object collection is changed, depending how collection traversal is done, even if the object still in the collection, it may not be visited. For bpf_seq_printf, format %s, %p{i,I}{4,6} needs to read kernel memory. Reading kernel memory may fail in the following two cases: - invalid kernel address, or - valid kernel address but requiring a major fault If reading kernel memory failed, the %s string will be an empty string and %p{i,I}{4,6} will be all 0. Not returning error to bpf program is consistent with what bpf_trace_printk() does for now. bpf_seq_printf may return -EBUSY meaning that internal percpu buffer for memory copy of strings or other pointees is not available. Bpf program can return 1 to indicate it wants the same object to be repeated. Right now, this should not happen on no-RT kernels since migrate_disable(), which guards bpf prog call, calls preempt_disable(). Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200509175914.2476661-1-yhs@fb.com --- include/uapi/linux/bpf.h | 39 +++++++- kernel/trace/bpf_trace.c | 214 +++++++++++++++++++++++++++++++++++++++++ scripts/bpf_helpers_doc.py | 2 + tools/include/uapi/linux/bpf.h | 39 +++++++- 4 files changed, 292 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 708763f702e1..9d1932e23cec 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3077,6 +3077,41 @@ union bpf_attr { * See: clock_gettime(CLOCK_BOOTTIME) * Return * Current *ktime*. + * + * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * seq_printf uses seq_file seq_printf() to print out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a u64 array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the *data* size in term of bytes. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what bpf_trace_printk() does for now. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EBUSY** Percpu memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * * **-EINVAL** Invalid arguments, or invalid/unsupported formats. + * * **-E2BIG** Too many format specifiers. + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * + * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * seq_write uses seq_file seq_write() to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3204,7 +3239,9 @@ union bpf_attr { FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ FN(sk_assign), \ - FN(ktime_get_boot_ns), + FN(ktime_get_boot_ns), \ + FN(seq_printf), \ + FN(seq_write), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e875c95d3ced..d961428fb5b6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -457,6 +457,212 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } +#define MAX_SEQ_PRINTF_VARARGS 12 +#define MAX_SEQ_PRINTF_MAX_MEMCPY 6 +#define MAX_SEQ_PRINTF_STR_LEN 128 + +struct bpf_seq_printf_buf { + char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN]; +}; +static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf); +static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used); + +BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, + const void *, data, u32, data_len) +{ + int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0; + int i, buf_used, copy_size, num_args; + u64 params[MAX_SEQ_PRINTF_VARARGS]; + struct bpf_seq_printf_buf *bufs; + const u64 *args = data; + + buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used); + if (WARN_ON_ONCE(buf_used > 1)) { + err = -EBUSY; + goto out; + } + + bufs = this_cpu_ptr(&bpf_seq_printf_buf); + + /* + * bpf_check()->check_func_arg()->check_stack_boundary() + * guarantees that fmt points to bpf program stack, + * fmt_size bytes of it were initialized and fmt_size > 0 + */ + if (fmt[--fmt_size] != 0) + goto out; + + if (data_len & 7) + goto out; + + for (i = 0; i < fmt_size; i++) { + if (fmt[i] == '%') { + if (fmt[i + 1] == '%') + i++; + else if (!data || !data_len) + goto out; + } + } + + num_args = data_len / 8; + + /* check format string for allowed specifiers */ + for (i = 0; i < fmt_size; i++) { + /* only printable ascii for now. */ + if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { + err = -EINVAL; + goto out; + } + + if (fmt[i] != '%') + continue; + + if (fmt[i + 1] == '%') { + i++; + continue; + } + + if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) { + err = -E2BIG; + goto out; + } + + if (fmt_cnt >= num_args) { + err = -EINVAL; + goto out; + } + + /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ + i++; + + /* skip optional "[0 +-][num]" width formating field */ + while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || + fmt[i] == ' ') + i++; + if (fmt[i] >= '1' && fmt[i] <= '9') { + i++; + while (fmt[i] >= '0' && fmt[i] <= '9') + i++; + } + + if (fmt[i] == 's') { + /* try our best to copy */ + if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) { + err = -E2BIG; + goto out; + } + + err = strncpy_from_unsafe(bufs->buf[memcpy_cnt], + (void *) (long) args[fmt_cnt], + MAX_SEQ_PRINTF_STR_LEN); + if (err < 0) + bufs->buf[memcpy_cnt][0] = '\0'; + params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt]; + + fmt_cnt++; + memcpy_cnt++; + continue; + } + + if (fmt[i] == 'p') { + if (fmt[i + 1] == 0 || + fmt[i + 1] == 'K' || + fmt[i + 1] == 'x') { + /* just kernel pointers */ + params[fmt_cnt] = args[fmt_cnt]; + fmt_cnt++; + continue; + } + + /* only support "%pI4", "%pi4", "%pI6" and "%pi6". */ + if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') { + err = -EINVAL; + goto out; + } + if (fmt[i + 2] != '4' && fmt[i + 2] != '6') { + err = -EINVAL; + goto out; + } + + if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) { + err = -E2BIG; + goto out; + } + + + copy_size = (fmt[i + 2] == '4') ? 4 : 16; + + err = probe_kernel_read(bufs->buf[memcpy_cnt], + (void *) (long) args[fmt_cnt], + copy_size); + if (err < 0) + memset(bufs->buf[memcpy_cnt], 0, copy_size); + params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt]; + + i += 2; + fmt_cnt++; + memcpy_cnt++; + continue; + } + + if (fmt[i] == 'l') { + i++; + if (fmt[i] == 'l') + i++; + } + + if (fmt[i] != 'i' && fmt[i] != 'd' && + fmt[i] != 'u' && fmt[i] != 'x') { + err = -EINVAL; + goto out; + } + + params[fmt_cnt] = args[fmt_cnt]; + fmt_cnt++; + } + + /* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give + * all of them to seq_printf(). + */ + seq_printf(m, fmt, params[0], params[1], params[2], params[3], + params[4], params[5], params[6], params[7], params[8], + params[9], params[10], params[11]); + + err = seq_has_overflowed(m) ? -EOVERFLOW : 0; +out: + this_cpu_dec(bpf_seq_printf_buf_used); + return err; +} + +static int bpf_seq_printf_btf_ids[5]; +static const struct bpf_func_proto bpf_seq_printf_proto = { + .func = bpf_seq_printf, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_seq_printf_btf_ids, +}; + +BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) +{ + return seq_write(m, data, len) ? -EOVERFLOW : 0; +} + +static int bpf_seq_write_btf_ids[5]; +static const struct bpf_func_proto bpf_seq_write_proto = { + .func = bpf_seq_write, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_seq_write_btf_ids, +}; + static __always_inline int get_map_perf_counter(struct bpf_map *map, u64 flags, u64 *value, u64 *enabled, u64 *running) @@ -1226,6 +1432,14 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_xdp_output: return &bpf_xdp_output_proto; #endif + case BPF_FUNC_seq_printf: + return prog->expected_attach_type == BPF_TRACE_ITER ? + &bpf_seq_printf_proto : + NULL; + case BPF_FUNC_seq_write: + return prog->expected_attach_type == BPF_TRACE_ITER ? + &bpf_seq_write_proto : + NULL; default: return raw_tp_prog_func_proto(func_id, prog); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index f43d193aff3a..ded304c96a05 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -414,6 +414,7 @@ class PrinterHelpers(Printer): 'struct sk_reuseport_md', 'struct sockaddr', 'struct tcphdr', + 'struct seq_file', 'struct __sk_buff', 'struct sk_msg_md', @@ -450,6 +451,7 @@ class PrinterHelpers(Printer): 'struct sk_reuseport_md', 'struct sockaddr', 'struct tcphdr', + 'struct seq_file', } mapped_types = { 'u8': '__u8', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 708763f702e1..9d1932e23cec 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3077,6 +3077,41 @@ union bpf_attr { * See: clock_gettime(CLOCK_BOOTTIME) * Return * Current *ktime*. + * + * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * seq_printf uses seq_file seq_printf() to print out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a u64 array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the *data* size in term of bytes. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what bpf_trace_printk() does for now. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EBUSY** Percpu memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * * **-EINVAL** Invalid arguments, or invalid/unsupported formats. + * * **-E2BIG** Too many format specifiers. + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. + * + * int bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * seq_write uses seq_file seq_write() to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EOVERFLOW** Overflow happens, the same object will be tried again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3204,7 +3239,9 @@ union bpf_attr { FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ FN(sk_assign), \ - FN(ktime_get_boot_ns), + FN(ktime_get_boot_ns), \ + FN(seq_printf), \ + FN(seq_write), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3