aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/include/uapi/linux/bpf.h19
-rw-r--r--tools/lib/bpf/bpf.c10
-rw-r--r--tools/lib/bpf/bpf.h5
-rw-r--r--tools/lib/bpf/libbpf.c649
-rw-r--r--tools/lib/bpf/libbpf.h5
-rw-r--r--tools/lib/bpf/libbpf.map3
-rw-r--r--tools/lib/bpf/libbpf_probes.c2
-rw-r--r--tools/testing/selftests/bpf/bpf_tcp_helpers.h228
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c187
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_dctcp.c210
10 files changed, 1303 insertions, 15 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7df436da542d..2d6a2e572f56 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -136,6 +136,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
+ BPF_MAP_TYPE_STRUCT_OPS,
};
/* Note that tracing related programs such as
@@ -174,6 +175,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_PROG_TYPE_TRACING,
+ BPF_PROG_TYPE_STRUCT_OPS,
};
enum bpf_attach_type {
@@ -397,6 +399,10 @@ union bpf_attr {
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_type_id; /* BTF type_id of the key */
__u32 btf_value_type_id; /* BTF type_id of the value */
+ __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+ * struct stored as the
+ * map value
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -2831,6 +2837,14 @@ union bpf_attr {
* Return
* On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
+ *
+ * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * Description
+ * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * *rcv_nxt* is the ack_seq to be sent out.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2948,7 +2962,8 @@ union bpf_attr {
FN(probe_read_user), \
FN(probe_read_kernel), \
FN(probe_read_user_str), \
- FN(probe_read_kernel_str),
+ FN(probe_read_kernel_str), \
+ FN(tcp_send_ack),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3349,7 +3364,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u32 :32;
+ __u32 btf_vmlinux_value_type_id;
__u64 netns_dev;
__u64 netns_ino;
__u32 btf_id;
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a787d53699c8..b0ecbe9ef2d4 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -95,7 +95,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
attr.btf_key_type_id = create_attr->btf_key_type_id;
attr.btf_value_type_id = create_attr->btf_value_type_id;
attr.map_ifindex = create_attr->map_ifindex;
- attr.inner_map_fd = create_attr->inner_map_fd;
+ if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+ attr.btf_vmlinux_value_type_id =
+ create_attr->btf_vmlinux_value_type_id;
+ else
+ attr.inner_map_fd = create_attr->inner_map_fd;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
@@ -228,7 +232,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
- if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+ if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+ attr.attach_btf_id = load_attr->attach_btf_id;
+ } else if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
attr.attach_btf_id = load_attr->attach_btf_id;
attr.attach_prog_fd = load_attr->attach_prog_fd;
} else {
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index f0ab8519986e..56341d117e5b 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -46,7 +46,10 @@ struct bpf_create_map_attr {
__u32 btf_key_type_id;
__u32 btf_value_type_id;
__u32 map_ifindex;
- __u32 inner_map_fd;
+ union {
+ __u32 inner_map_fd;
+ __u32 btf_vmlinux_value_type_id;
+ };
};
LIBBPF_API int
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7513165b104f..35a4422ef655 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -70,6 +70,13 @@
#define __printf(a, b) __attribute__((format(printf, a, b)))
+static struct btf *bpf_find_kernel_btf(void);
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
+static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj,
+ int idx);
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
static int __base_pr(enum libbpf_print_level level, const char *format,
va_list args)
{
@@ -229,10 +236,32 @@ struct bpf_program {
__u32 prog_flags;
};
+struct bpf_struct_ops {
+ const char *tname;
+ const struct btf_type *type;
+ struct bpf_program **progs;
+ __u32 *kern_func_off;
+ /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
+ void *data;
+ /* e.g. struct bpf_struct_ops_tcp_congestion_ops in
+ * btf_vmlinux's format.
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [... some other kernel fields ...]
+ * struct tcp_congestion_ops data;
+ * }
+ * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops)
+ * bpf_map__init_kern_struct_ops() will populate the "kern_vdata"
+ * from "data".
+ */
+ void *kern_vdata;
+ __u32 type_id;
+};
+
#define DATA_SEC ".data"
#define BSS_SEC ".bss"
#define RODATA_SEC ".rodata"
#define KCONFIG_SEC ".kconfig"
+#define STRUCT_OPS_SEC ".struct_ops"
enum libbpf_map_type {
LIBBPF_MAP_UNSPEC,
@@ -259,10 +288,12 @@ struct bpf_map {
struct bpf_map_def def;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u32 btf_vmlinux_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
enum libbpf_map_type libbpf_type;
void *mmaped;
+ struct bpf_struct_ops *st_ops;
char *pin_path;
bool pinned;
bool reused;
@@ -326,6 +357,7 @@ struct bpf_object {
Elf_Data *data;
Elf_Data *rodata;
Elf_Data *bss;
+ Elf_Data *st_ops_data;
size_t strtabidx;
struct {
GElf_Shdr shdr;
@@ -339,6 +371,7 @@ struct bpf_object {
int data_shndx;
int rodata_shndx;
int bss_shndx;
+ int st_ops_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
@@ -566,6 +599,359 @@ static __u32 get_kernel_version(void)
return KERNEL_VERSION(major, minor, patch);
}
+static const struct btf_member *
+find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (btf_member_bit_offset(t, i) == bit_offset)
+ return m;
+ }
+
+ return NULL;
+}
+
+static const struct btf_member *
+find_member_by_name(const struct btf *btf, const struct btf_type *t,
+ const char *name)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (!strcmp(btf__name_by_offset(btf, m->name_off), name))
+ return m;
+ }
+
+ return NULL;
+}
+
+#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_"
+#define STRUCT_OPS_VALUE_PREFIX_LEN (sizeof(STRUCT_OPS_VALUE_PREFIX) - 1)
+
+static int
+find_struct_ops_kern_types(const struct btf *btf, const char *tname,
+ const struct btf_type **type, __u32 *type_id,
+ const struct btf_type **vtype, __u32 *vtype_id,
+ const struct btf_member **data_member)
+{
+ const struct btf_type *kern_type, *kern_vtype;
+ const struct btf_member *kern_data_member;
+ __s32 kern_vtype_id, kern_type_id;
+ char vtname[128] = STRUCT_OPS_VALUE_PREFIX;
+ __u32 i;
+
+ kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+ if (kern_type_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
+ tname);
+ return kern_type_id;
+ }
+ kern_type = btf__type_by_id(btf, kern_type_id);
+
+ /* Find the corresponding "map_value" type that will be used
+ * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example,
+ * find "struct bpf_struct_ops_tcp_congestion_ops" from the
+ * btf_vmlinux.
+ */
+ strncat(vtname + STRUCT_OPS_VALUE_PREFIX_LEN, tname,
+ sizeof(vtname) - STRUCT_OPS_VALUE_PREFIX_LEN - 1);
+ kern_vtype_id = btf__find_by_name_kind(btf, vtname,
+ BTF_KIND_STRUCT);
+ if (kern_vtype_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
+ vtname);
+ return kern_vtype_id;
+ }
+ kern_vtype = btf__type_by_id(btf, kern_vtype_id);
+
+ /* Find "struct tcp_congestion_ops" from
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [ ... ]
+ * struct tcp_congestion_ops data;
+ * }
+ */
+ kern_data_member = btf_members(kern_vtype);
+ for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) {
+ if (kern_data_member->type == kern_type_id)
+ break;
+ }
+ if (i == btf_vlen(kern_vtype)) {
+ pr_warn("struct_ops init_kern: struct %s data is not found in struct %s\n",
+ tname, vtname);
+ return -EINVAL;
+ }
+
+ *type = kern_type;
+ *type_id = kern_type_id;
+ *vtype = kern_vtype;
+ *vtype_id = kern_vtype_id;
+ *data_member = kern_data_member;
+
+ return 0;
+}
+
+static bool bpf_map__is_struct_ops(const struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_STRUCT_OPS;
+}
+
+/* Init the map's fields that depend on kern_btf */
+static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf *kern_btf)
+{
+ const struct btf_member *member, *kern_member, *kern_data_member;
+ const struct btf_type *type, *kern_type, *kern_vtype;
+ __u32 i, kern_type_id, kern_vtype_id, kern_data_off;
+ struct bpf_struct_ops *st_ops;
+ void *data, *kern_data;
+ const char *tname;
+ int err;
+
+ st_ops = map->st_ops;
+ type = st_ops->type;
+ tname = st_ops->tname;
+ err = find_struct_ops_kern_types(kern_btf, tname,
+ &kern_type, &kern_type_id,
+ &kern_vtype, &kern_vtype_id,
+ &kern_data_member);
+ if (err)
+ return err;
+
+ pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n",
+ map->name, st_ops->type_id, kern_type_id, kern_vtype_id);
+
+ map->def.value_size = kern_vtype->size;
+ map->btf_vmlinux_value_type_id = kern_vtype_id;
+
+ st_ops->kern_vdata = calloc(1, kern_vtype->size);
+ if (!st_ops->kern_vdata)
+ return -ENOMEM;
+
+ data = st_ops->data;
+ kern_data_off = kern_data_member->offset / 8;
+ kern_data = st_ops->kern_vdata + kern_data_off;
+
+ member = btf_members(type);
+ for (i = 0; i < btf_vlen(type); i++, member++) {
+ const struct btf_type *mtype, *kern_mtype;
+ __u32 mtype_id, kern_mtype_id;
+ void *mdata, *kern_mdata;
+ __s64 msize, kern_msize;
+ __u32 moff, kern_moff;
+ __u32 kern_member_idx;
+ const char *mname;
+
+ mname = btf__name_by_offset(btf, member->name_off);
+ kern_member = find_member_by_name(kern_btf, kern_type, mname);
+ if (!kern_member) {
+ pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ kern_member_idx = kern_member - btf_members(kern_type);
+ if (btf_member_bitfield_size(type, i) ||
+ btf_member_bitfield_size(kern_type, kern_member_idx)) {
+ pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ moff = member->offset / 8;
+ kern_moff = kern_member->offset / 8;
+
+ mdata = data + moff;
+ kern_mdata = kern_data + kern_moff;
+
+ mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type,
+ &kern_mtype_id);
+ if (BTF_INFO_KIND(mtype->info) !=
+ BTF_INFO_KIND(kern_mtype->info)) {
+ pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n",
+ map->name, mname, BTF_INFO_KIND(mtype->info),
+ BTF_INFO_KIND(kern_mtype->info));
+ return -ENOTSUP;
+ }
+
+ if (btf_is_ptr(mtype)) {
+ struct bpf_program *prog;
+
+ mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf,
+ kern_mtype->type,
+ &kern_mtype_id);
+ if (!btf_is_func_proto(mtype) ||
+ !btf_is_func_proto(kern_mtype)) {
+ pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ prog = st_ops->progs[i];
+ if (!prog) {
+ pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
+ map->name, mname);
+ continue;
+ }
+
+ prog->attach_btf_id = kern_type_id;
+ prog->expected_attach_type = kern_member_idx;
+
+ st_ops->kern_func_off[i] = kern_data_off + kern_moff;
+
+ pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, prog->name, moff,
+ kern_moff);
+
+ continue;
+ }
+
+ msize = btf__resolve_size(btf, mtype_id);
+ kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
+ if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+ pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
+ map->name, mname, (ssize_t)msize,
+ (ssize_t)kern_msize);
+ return -ENOTSUP;
+ }
+
+ pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, (unsigned int)msize,
+ moff, kern_moff);
+ memcpy(kern_mdata, mdata, msize);
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj)
+{
+ struct btf *kern_btf = NULL;
+ struct bpf_map *map;
+ size_t i;
+ int err;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+
+ if (!kern_btf) {
+ kern_btf = bpf_find_kernel_btf();
+ if (IS_ERR(kern_btf))
+ return PTR_ERR(kern_btf);
+ }
+
+ err = bpf_map__init_kern_struct_ops(map, obj->btf, kern_btf);
+ if (err) {
+ btf__free(kern_btf);
+ return err;
+ }
+ }
+
+ btf__free(kern_btf);
+ return 0;
+}
+
+static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
+{
+ const struct btf_type *type, *datasec;
+ const struct btf_var_secinfo *vsi;
+ struct bpf_struct_ops *st_ops;
+ const char *tname, *var_name;
+ __s32 type_id, datasec_id;
+ const struct btf *btf;
+ struct bpf_map *map;
+ __u32 i;
+
+ if (obj->efile.st_ops_shndx == -1)
+ return 0;
+
+ btf = obj->btf;
+ datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC,
+ BTF_KIND_DATASEC);
+ if (datasec_id < 0) {
+ pr_warn("struct_ops init: DATASEC %s not found\n",
+ STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ datasec = btf__type_by_id(btf, datasec_id);
+ vsi = btf_var_secinfos(datasec);
+ for (i = 0; i < btf_vlen(datasec); i++, vsi++) {
+ type = btf__type_by_id(obj->btf, vsi->type);
+ var_name = btf__name_by_offset(obj->btf, type->name_off);
+
+ type_id = btf__resolve_type(obj->btf, vsi->type);
+ if (type_id < 0) {
+ pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n",
+ vsi->type, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ type = btf__type_by_id(obj->btf, type_id);
+ tname = btf__name_by_offset(obj->btf, type->name_off);
+ if (!tname[0]) {
+ pr_warn("struct_ops init: anonymous type is not supported\n");
+ return -ENOTSUP;
+ }
+ if (!btf_is_struct(type)) {
+ pr_warn("struct_ops init: %s is not a struct\n", tname);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map->sec_idx = obj->efile.st_ops_shndx;
+ map->sec_offset = vsi->offset;
+ map->name = strdup(var_name);
+ if (!map->name)
+ return -ENOMEM;
+
+ map->def.type = BPF_MAP_TYPE_STRUCT_OPS;
+ map->def.key_size = sizeof(int);
+ map->def.value_size = type->size;
+ map->def.max_entries = 1;
+
+ map->st_ops = calloc(1, sizeof(*map->st_ops));
+ if (!map->st_ops)
+ return -ENOMEM;
+ st_ops = map->st_ops;
+ st_ops->data = malloc(type->size);
+ st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs));
+ st_ops->kern_func_off = malloc(btf_vlen(type) *
+ sizeof(*st_ops->kern_func_off));
+ if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
+ return -ENOMEM;
+
+ if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+ pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
+ var_name, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ memcpy(st_ops->data,
+ obj->efile.st_ops_data->d_buf + vsi->offset,
+ type->size);
+ st_ops->tname = tname;
+ st_ops->type = type;
+ st_ops->type_id = type_id;
+
+ pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+ tname, type_id, var_name, vsi->offset);
+ }
+
+ return 0;
+}
+
static struct bpf_object *bpf_object__new(const char *path,
const void *obj_buf,
size_t obj_buf_sz,
@@ -607,6 +993,7 @@ static struct bpf_object *bpf_object__new(const char *path,
obj->efile.data_shndx = -1;
obj->efile.rodata_shndx = -1;
obj->efile.bss_shndx = -1;
+ obj->efile.st_ops_shndx = -1;
obj->kconfig_map_idx = -1;
obj->kern_version = get_kernel_version();
@@ -630,6 +1017,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
obj->efile.data = NULL;
obj->efile.rodata = NULL;
obj->efile.bss = NULL;
+ obj->efile.st_ops_data = NULL;
zfree(&obj->efile.reloc_sects);
obj->efile.nr_reloc_sects = 0;
@@ -815,6 +1203,9 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
} else if (!strcmp(name, RODATA_SEC)) {
if (obj->efile.rodata)
*size = obj->efile.rodata->d_size;
+ } else if (!strcmp(name, STRUCT_OPS_SEC)) {
+ if (obj->efile.st_ops_data)
+ *size = obj->efile.st_ops_data->d_size;
} else {
ret = bpf_object_search_section_size(obj, name, &d_size);
if (!ret)
@@ -1440,6 +1831,20 @@ skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
return t;
}
+static const struct btf_type *
+resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+ const struct btf_type *t;
+
+ t = skip_mods_and_typedefs(btf, id, NULL);
+ if (!btf_is_ptr(t))
+ return NULL;
+
+ t = skip_mods_and_typedefs(btf, t->type, res_id);
+
+ return btf_is_func_proto(t) ? t : NULL;
+}
+
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
@@ -1787,6 +2192,7 @@ static int bpf_object__init_maps(struct bpf_object *obj,
err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
err = err ?: bpf_object__init_global_data_maps(obj);
err = err ?: bpf_object__init_kconfig_map(obj);
+ err = err ?: bpf_object__init_struct_ops_maps(obj);
if (err)
return err;
@@ -1889,7 +2295,8 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
{
return obj->efile.btf_maps_shndx >= 0 ||
- obj->nr_extern > 0;
+ obj->efile.st_ops_shndx >= 0 ||
+ obj->nr_extern > 0;
}
static int bpf_object__init_btf(struct bpf_object *obj,
@@ -2088,6 +2495,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
} else if (strcmp(name, RODATA_SEC) == 0) {
obj->efile.rodata = data;
obj->efile.rodata_shndx = idx;
+ } else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
+ obj->efile.st_ops_data = data;
+ obj->efile.st_ops_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
@@ -2097,7 +2507,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
- if (!section_have_execinstr(obj, sec)) {
+ if (!section_have_execinstr(obj, sec) &&
+ strcmp(name, ".rel" STRUCT_OPS_SEC)) {
pr_debug("skip relo %s(%d) for section(%d)\n",
name, idx, sec);
continue;
@@ -2599,8 +3010,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
__u32 key_type_id = 0, value_type_id = 0;
int ret;
- /* if it's BTF-defined map, we don't need to search for type IDs */
- if (map->sec_idx == obj->efile.btf_maps_shndx)
+ /* if it's BTF-defined map, we don't need to search for type IDs.
+ * For struct_ops map, it does not need btf_key_type_id and
+ * btf_value_type_id.
+ */
+ if (map->sec_idx == obj->efile.btf_maps_shndx ||
+ bpf_map__is_struct_ops(map))
return 0;
if (!bpf_map__is_internal(map)) {
@@ -3025,6 +3440,9 @@ bpf_object__create_maps(struct bpf_object *obj)
if (bpf_map_type__is_map_in_map(def->type) &&
map->inner_map_fd >= 0)
create_attr.inner_map_fd = map->inner_map_fd;
+ if (bpf_map__is_struct_ops(map))
+ create_attr.btf_vmlinux_value_type_id =
+ map->btf_vmlinux_value_type_id;
if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
create_attr.btf_fd = btf__fd(obj->btf);
@@ -3899,7 +4317,7 @@ cleanup:
* Probe few well-known locations for vmlinux kernel image and try to load BTF
* data out of it to use for target BTF.
*/
-static struct btf *bpf_core_find_kernel_btf(void)
+static struct btf *bpf_find_kernel_btf(void)
{
struct {
const char *path_fmt;
@@ -4180,7 +4598,7 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path)
if (targ_btf_path)
targ_btf = btf__parse_elf(targ_btf_path, NULL);
else
- targ_btf = bpf_core_find_kernel_btf();
+ targ_btf = bpf_find_kernel_btf();
if (IS_ERR(targ_btf)) {
pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
return PTR_ERR(targ_btf);
@@ -4379,6 +4797,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
return 0;
}
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data);
+
static int bpf_object__collect_reloc(struct bpf_object *obj)
{
int i, err;
@@ -4399,6 +4821,15 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
return -LIBBPF_ERRNO__INTERNAL;
}
+ if (idx == obj->efile.st_ops_shndx) {
+ err = bpf_object__collect_struct_ops_map_reloc(obj,
+ shdr,
+ data);
+ if (err)
+ return err;
+ continue;
+ }
+
prog = bpf_object__find_prog_by_idx(obj, idx);
if (!prog) {
pr_warn("relocation failed: no section(%d)\n", idx);
@@ -4433,7 +4864,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
- if (prog->type == BPF_PROG_TYPE_TRACING) {
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+ load_attr.attach_btf_id = prog->attach_btf_id;
+ } else if (prog->type == BPF_PROG_TYPE_TRACING) {
load_attr.attach_prog_fd = prog->attach_prog_fd;
load_attr.attach_btf_id = prog->attach_btf_id;
} else {
@@ -4679,6 +5112,9 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
enum bpf_prog_type prog_type;
enum bpf_attach_type attach_type;
+ if (prog->type != BPF_PROG_TYPE_UNSPEC)
+ continue;
+
err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
&attach_type);
if (err == -ESRCH)
@@ -4774,8 +5210,11 @@ int bpf_object__unload(struct bpf_object *obj)
if (!obj)
return -EINVAL;
- for (i = 0; i < obj->nr_maps; i++)
+ for (i = 0; i < obj->nr_maps; i++) {
zclose(obj->maps[i].fd);
+ if (obj->maps[i].st_ops)
+ zfree(&obj->maps[i].st_ops->kern_vdata);
+ }
for (i = 0; i < obj->nr_programs; i++)
bpf_program__unload(&obj->programs[i]);
@@ -4891,6 +5330,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
err = err ? : bpf_object__sanitize_maps(obj);
+ err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
err = err ? : bpf_object__create_maps(obj);
err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
err = err ? : bpf_object__load_progs(obj, attr->log_level);
@@ -5478,6 +5918,13 @@ void bpf_object__close(struct bpf_object *obj)
map->mmaped = NULL;
}
+ if (map->st_ops) {
+ zfree(&map->st_ops->data);
+ zfree(&map->st_ops->progs);
+ zfree(&map->st_ops->kern_func_off);
+ zfree(&map->st_ops);
+ }
+
zfree(&map->name);
zfree(&map->pin_path);
}
@@ -5746,6 +6193,7 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
+BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS);
enum bpf_attach_type
bpf_program__get_expected_attach_type(struct bpf_program *prog)
@@ -5899,6 +6347,7 @@ static const struct bpf_sec_def section_defs[] = {
BPF_CGROUP_GETSOCKOPT),
BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_CGROUP_SETSOCKOPT),
+ BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS),
};
#undef BPF_PROG_SEC_IMPL
@@ -5975,11 +6424,141 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
return -ESRCH;
}
+static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+ size_t offset)
+{
+ struct bpf_map *map;
+ size_t i;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+ if (map->sec_offset <= offset &&
+ offset - map->sec_offset < map->def.value_size)
+ return map;
+ }
+
+ return NULL;
+}
+
+/* Collect the reloc from ELF and populate the st_ops->progs[] */
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data)
+{
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_program *prog;
+ unsigned int shdr_idx;
+ const struct btf *btf;
+ struct bpf_map *map;
+ Elf_Data *symbols;
+ unsigned int moff;
+ const char *name;
+ u32 member_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
+ int i, nrels;
+
+ symbols = obj->efile.symbols;
+ btf = obj->btf;
+ nrels = shdr->sh_size / shdr->sh_entsize;
+ for (i = 0; i < nrels; i++) {
+ if (!gelf_getrel(data, i, &rel)) {
+ pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+ pr_warn("struct_ops reloc: symbol %zx not found\n",
+ (size_t)GELF_R_SYM(rel.r_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+ map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+ if (!map) {
+ pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
+ (size_t)rel.r_offset);
+ return -EINVAL;
+ }
+
+ moff = rel.r_offset - map->sec_offset;
+ shdr_idx = sym.st_shndx;
+ st_ops = map->st_ops;
+ pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+ map->name,
+ (long long)(rel.r_info >> 32),
+ (long long)sym.st_value,
+ shdr_idx, (size_t)rel.r_offset,
+ map->sec_offset, sym.st_name, name);
+
+ if (shdr_idx >= SHN_LORESERVE) {
+ pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
+ map->name, (size_t)rel.r_offset, shdr_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+
+ member = find_member_by_offset(st_ops->type, moff * 8);
+ if (!member) {
+ pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
+ map->name, moff);
+ return -EINVAL;
+ }
+ member_idx = member - btf_members(st_ops->type);
+ name = btf__name_by_offset(btf, member->name_off);
+
+ if (!resolve_func_ptr(btf, member->type, NULL)) {
+ pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n",
+ map->name, name);
+ return -EINVAL;
+ }
+
+ prog = bpf_object__find_prog_by_idx(obj, shdr_idx);
+ if (!prog) {
+ pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n",
+ map->name, shdr_idx, name);
+ return -EINVAL;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+ const struct bpf_sec_def *sec_def;
+
+ sec_def = find_sec_def(prog->section_name);
+ if (sec_def &&
+ sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
+ /* for pr_warn */
+ prog->type = sec_def->prog_type;
+ goto invalid_prog;
+ }
+
+ prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+ prog->attach_btf_id = st_ops->type_id;
+ prog->expected_attach_type = member_idx;
+ } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->attach_btf_id != st_ops->type_id ||
+ prog->expected_attach_type != member_idx) {
+ goto invalid_prog;
+ }
+ st_ops->progs[member_idx] = prog;
+ }
+
+ return 0;
+
+invalid_prog:
+ pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+ map->name, prog->name, prog->section_name, prog->type,
+ prog->attach_btf_id, prog->expected_attach_type, name);
+ return -EINVAL;
+}
+
#define BTF_PREFIX "btf_trace_"
int libbpf_find_vmlinux_btf_id(const char *name,
enum bpf_attach_type attach_type)
{
- struct btf *btf = bpf_core_find_kernel_btf();
+ struct btf *btf = bpf_find_kernel_btf();
char raw_tp_btf[128] = BTF_PREFIX;
char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
const char *btf_name;
@@ -6805,6 +7384,58 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
return sec_def->attach_fn(sec_def, prog);
}
+static int bpf_link__detach_struct_ops(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ __u32 zero = 0;
+
+ if (bpf_map_delete_elem(l->fd, &zero))
+ return -errno;
+
+ return 0;
+}
+
+struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+{
+ struct bpf_struct_ops *st_ops;
+ struct bpf_link_fd *link;
+ __u32 i, zero = 0;
+ int err;
+
+ if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+ return ERR_PTR(-EINVAL);
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-EINVAL);
+
+ st_ops = map->st_ops;
+ for (i = 0; i < btf_vlen(st_ops->type); i++) {
+ struct bpf_program *prog = st_ops->progs[i];
+ void *kern_data;
+ int prog_fd;
+
+ if (!prog)
+ continue;
+
+ prog_fd = bpf_program__fd(prog);
+ kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+ *(unsigned long *)kern_data = prog_fd;
+ }
+
+ err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
+ if (err) {
+ err = -errno;
+ free(link);
+ return ERR_PTR(err);
+ }
+
+ link->link.detach = bpf_link__detach_struct_ops;
+ link->fd = map->fd;
+
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 26bf539f1b3c..01639f9a1062 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -239,6 +239,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
LIBBPF_API struct bpf_link *
bpf_program__attach_trace(struct bpf_program *prog);
+struct bpf_map;
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
struct bpf_insn;
/*
@@ -315,6 +317,7 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
@@ -335,6 +338,7 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -354,7 +358,6 @@ struct bpf_map_def {
* The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
* so no need to worry about a name clash.
*/
-struct bpf_map;
LIBBPF_API struct bpf_map *
bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b300d74c921a..a19f04e6e3d9 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -213,6 +213,7 @@ LIBBPF_0.0.7 {
global:
btf_dump__emit_type_decl;
bpf_link__disconnect;
+ bpf_map__attach_struct_ops;
bpf_object__find_program_by_name;
bpf_object__attach_skeleton;
bpf_object__destroy_skeleton;
@@ -223,5 +224,7 @@ LIBBPF_0.0.7 {
bpf_prog_attach_xattr;
bpf_program__attach;
bpf_program__name;
+ bpf_program__is_struct_ops;
+ bpf_program__set_struct_ops;
btf__align_of;
} LIBBPF_0.0.6;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 221e6ad97012..320697f8e4c7 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -103,6 +103,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_STRUCT_OPS:
default:
break;
}
@@ -251,6 +252,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
case BPF_MAP_TYPE_XSKMAP:
case BPF_MAP_TYPE_SOCKHASH:
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ case BPF_MAP_TYPE_STRUCT_OPS:
default:
break;
}
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
new file mode 100644
index 000000000000..7da3e8db3adf
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TCP_HELPERS_H
+#define __BPF_TCP_HELPERS_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <bpf_helpers.h>
+#include <bpf_core_read.h>
+#include "bpf_trace_helpers.h"
+
+/* "struct_ops/" is only a convention. not a requirement. */
+#define BPF_TCP_OPS_0(fname, ret_type, ...) BPF_TRACE_x(0, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+#define BPF_TCP_OPS_1(fname, ret_type, ...) BPF_TRACE_x(1, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+#define BPF_TCP_OPS_2(fname, ret_type, ...) BPF_TRACE_x(2, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+#define BPF_TCP_OPS_3(fname, ret_type, ...) BPF_TRACE_x(3, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+#define BPF_TCP_OPS_4(fname, ret_type, ...) BPF_TRACE_x(4, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+#define BPF_TCP_OPS_5(fname, ret_type, ...) BPF_TRACE_x(5, "struct_ops/"#fname, fname, ret_type, __VA_ARGS__)
+
+struct sock_common {
+ unsigned char skc_state;
+} __attribute__((preserve_access_index));
+
+struct sock {
+ struct sock_common __sk_common;
+} __attribute__((preserve_access_index));
+
+struct inet_sock {
+ struct sock sk;
+} __attribute__((preserve_access_index));
+
+struct inet_connection_sock {
+ struct inet_sock icsk_inet;
+ __u8 icsk_ca_state:6,
+ icsk_ca_setsockopt:1,
+ icsk_ca_dst_locked:1;
+ struct {
+ __u8 pending;
+ } icsk_ack;
+ __u64 icsk_ca_priv[104 / sizeof(__u64)];
+} __attribute__((preserve_access_index));
+
+struct tcp_sock {
+ struct inet_connection_sock inet_conn;
+
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u8 ecn_flags;
+ __u32 delivered;
+ __u32 delivered_ce;
+ __u32 snd_cwnd;
+ __u32 snd_cwnd_cnt;
+ __u32 snd_cwnd_clamp;
+ __u32 snd_ssthresh;
+ __u8 syn_data:1, /* SYN includes data */
+ syn_fastopen:1, /* SYN includes Fast Open option */
+ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
+ syn_fastopen_ch:1, /* Active TFO re-enabling probe */
+ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+ save_syn:1, /* Save headers of SYN packet */
+ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+ syn_smc:1; /* SYN includes SMC */
+ __u32 max_packets_out;
+ __u32 lsndtime;
+ __u32 prior_cwnd;
+} __attribute__((preserve_access_index));
+
+static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+ return (struct inet_connection_sock *)sk;
+}
+
+static __always_inline void *inet_csk_ca(const struct sock *sk)
+{
+ return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk)
+{
+ return (struct tcp_sock *)sk;
+}
+
+static __always_inline bool before(__u32 seq1, __u32 seq2)
+{
+ return (__s32)(seq1-seq2) < 0;
+}
+#define after(seq2, seq1) before(seq1, seq2)
+
+#define TCP_ECN_OK 1
+#define TCP_ECN_QUEUE_CWR 2
+#define TCP_ECN_DEMAND_CWR 4
+#define TCP_ECN_SEEN 8
+
+enum inet_csk_ack_state_t {
+ ICSK_ACK_SCHED = 1,
+ ICSK_ACK_TIMER = 2,
+ ICSK_ACK_PUSHED = 4,
+ ICSK_ACK_PUSHED2 = 8,
+ ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
+};
+
+enum tcp_ca_event {
+ CA_EVENT_TX_START = 0,
+ CA_EVENT_CWND_RESTART = 1,
+ CA_EVENT_COMPLETE_CWR = 2,
+ CA_EVENT_LOSS = 3,
+ CA_EVENT_ECN_NO_CE = 4,
+ CA_EVENT_ECN_IS_CE = 5,
+};
+
+enum tcp_ca_state {
+ TCP_CA_Open = 0,
+ TCP_CA_Disorder = 1,
+ TCP_CA_CWR = 2,
+ TCP_CA_Recovery = 3,
+ TCP_CA_Loss = 4
+};
+
+struct ack_sample {
+ __u32 pkts_acked;
+ __s32 rtt_us;
+ __u32 in_flight;
+} __attribute__((preserve_access_index));
+
+struct rate_sample {
+ __u64 prior_mstamp; /* starting timestamp for interval */
+ __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */
+ __s32 delivered; /* number of packets delivered over interval */
+ long interval_us; /* time for tp->delivered to incr "delivered" */
+ __u32 snd_interval_us; /* snd interval for delivered packets */
+ __u32 rcv_interval_us; /* rcv interval for delivered packets */
+ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */
+ int losses; /* number of packets marked lost upon ACK */
+ __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
+ __u32 prior_in_flight; /* in flight before this ACK */
+ bool is_app_limited; /* is sample from packet with bubble in pipe? */
+ bool is_retrans; /* is sample from retransmission? */
+ bool is_ack_delayed; /* is this (likely) a delayed ACK? */
+} __attribute__((preserve_access_index));
+
+#define TCP_CA_NAME_MAX 16
+#define TCP_CONG_NEEDS_ECN 0x2
+
+struct tcp_congestion_ops {
+ char name[TCP_CA_NAME_MAX];
+ __u32 flags;
+
+ /* initialize private data (optional) */
+ void (*init)(struct sock *sk);
+ /* cleanup private data (optional) */
+ void (*release)(struct sock *sk);
+
+ /* return slow start threshold (required) */
+ __u32 (*ssthresh)(struct sock *sk);
+ /* do new cwnd calculation (required) */
+ void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked);
+ /* call before changing ca_state (optional) */
+ void (*set_state)(struct sock *sk, __u8 new_state);
+ /* call when cwnd event occurs (optional) */
+ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+ /* call when ack arrives (optional) */
+ void (*in_ack_event)(struct sock *sk, __u32 flags);
+ /* new value of cwnd after loss (required) */
+ __u32 (*undo_cwnd)(struct sock *sk);
+ /* hook for packet ack accounting (optional) */
+ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
+ /* override sysctl_tcp_min_tso_segs */
+ __u32 (*min_tso_segs)(struct sock *sk);
+ /* returns the multiplier used in tcp_sndbuf_expand (optional) */
+ __u32 (*sndbuf_expand)(struct sock *sk);
+ /* call when packets are delivered to update cwnd and pacing rate,
+ * after all the ca_state processing. (optional)
+ */
+ void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
+};
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min_not_zero(x, y) ({ \
+ typeof(x) __x = (x); \
+ typeof(y) __y = (y); \
+ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
+{
+ __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
+
+ acked -= cwnd - tp->snd_cwnd;
+ tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+ return acked;
+}
+
+static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
+static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ /* If in slow start, ensure cwnd grows to twice what was ACKed. */
+ if (tcp_in_slow_start(tp))
+ return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+ return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
+}
+
+static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
+{
+ /* If credits accumulated at a higher w, apply them gently now. */
+ if (tp->snd_cwnd_cnt >= w) {
+ tp->snd_cwnd_cnt = 0;
+ tp->snd_cwnd++;
+ }
+
+ tp->snd_cwnd_cnt += acked;
+ if (tp->snd_cwnd_cnt >= w) {
+ __u32 delta = tp->snd_cwnd_cnt / w;
+
+ tp->snd_cwnd_cnt -= delta * w;
+ tp->snd_cwnd += delta;
+ }
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
new file mode 100644
index 000000000000..517318f05b1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/err.h>
+#include <test_progs.h>
+#include "bpf_dctcp.skel.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static const struct timeval timeo_sec = { .tv_sec = 10 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static int settimeo(int fd)
+{
+ int err;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static int settcpca(int fd, const char *tcp_ca)
+{
+ int err;
+
+ err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
+ if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static void *server(void *arg)
+{
+ int lfd = (int)(long)arg, err = 0, fd;
+ ssize_t nr_sent = 0, bytes = 0;
+ char batch[1500];
+
+ fd = accept(lfd, NULL, NULL);
+ while (fd == -1) {
+ if (errno == EINTR)
+ continue;
+ err = -errno;
+ goto done;
+ }
+
+ if (settimeo(fd)) {
+ err = -errno;
+ goto done;
+ }
+
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_sent = send(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_sent == -1 && errno == EINTR)
+ continue;
+ if (nr_sent == -1) {
+ err = -errno;
+ break;
+ }
+ bytes += nr_sent;
+ }
+
+ CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+ bytes, total_bytes, nr_sent, errno);
+
+done:
+ if (fd != -1)
+ close(fd);
+ if (err) {
+ WRITE_ONCE(stop, 1);
+ return ERR_PTR(err);
+ }
+ return NULL;
+}
+
+static void do_test(const char *tcp_ca)
+{
+ struct sockaddr_in6 sa6 = {};
+ ssize_t nr_recv = 0, bytes = 0;
+ int lfd = -1, fd = -1;
+ pthread_t srv_thread;
+ socklen_t addrlen = sizeof(sa6);
+ void *thread_ret;
+ char batch[1500];
+ int err;
+
+ WRITE_ONCE(stop, 0);
+
+ lfd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+ return;
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+ close(lfd);
+ return;
+ }
+
+ if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+ settimeo(lfd) || settimeo(fd))
+ goto done;
+
+ /* bind, listen and start server thread to accept */
+ sa6.sin6_family = AF_INET6;
+ sa6.sin6_addr = in6addr_loopback;
+ err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+ goto done;
+ err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
+ if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+ goto done;
+ err = listen(lfd, 1);
+ if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+ goto done;
+ err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+ if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
+ goto done;
+
+ /* connect to server */
+ err = connect(fd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+ goto wait_thread;
+
+ /* recv total_bytes */
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_recv = recv(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_recv == -1 && errno == EINTR)
+ continue;
+ if (nr_recv == -1)
+ break;
+ bytes += nr_recv;
+ }
+
+ CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+ bytes, total_bytes, nr_recv, errno);
+
+wait_thread:
+ WRITE_ONCE(stop, 1);
+ pthread_join(srv_thread, &thread_ret);
+ CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+ PTR_ERR(thread_ret));
+done:
+ close(lfd);
+ close(fd);
+}
+
+static void test_dctcp(void)
+{
+ struct bpf_dctcp *dctcp_skel;
+ struct bpf_link *link;
+
+ dctcp_skel = bpf_dctcp__open_and_load();
+ if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+ return;
+
+ link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+ if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+ PTR_ERR(link))) {
+ bpf_dctcp__destroy(dctcp_skel);
+ return;
+ }
+
+ do_test("bpf_dctcp");
+
+ bpf_link__destroy(link);
+ bpf_dctcp__destroy(dctcp_skel);
+}
+
+void test_bpf_tcp_ca(void)
+{
+ if (test__start_subtest("dctcp"))
+ test_dctcp();
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
new file mode 100644
index 000000000000..5f9b613663e5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_dctcp.c. The purpose is mainly for testing
+ * the kernel BPF logic.
+ */
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define DCTCP_MAX_ALPHA 1024U
+
+struct dctcp {
+ __u32 old_delivered;
+ __u32 old_delivered_ce;
+ __u32 prior_rcv_nxt;
+ __u32 dctcp_alpha;
+ __u32 next_seq;
+ __u32 ce_state;
+ __u32 loss_cwnd;
+};
+
+static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */
+static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA;
+
+static __always_inline void dctcp_reset(const struct tcp_sock *tp,
+ struct dctcp *ca)
+{
+ ca->next_seq = tp->snd_nxt;
+
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
+}
+
+BPF_TCP_OPS_1(dctcp_init, void, struct sock *, sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+ ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+ ca->loss_cwnd = 0;
+ ca->ce_state = 0;
+
+ dctcp_reset(tp, ca);
+}
+
+BPF_TCP_OPS_1(dctcp_ssthresh, __u32, struct sock *, sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+BPF_TCP_OPS_2(dctcp_update_alpha, void,
+ struct sock *, sk, __u32, flags)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ /* Expired RTT */
+ if (!before(tp->snd_una, ca->next_seq)) {
+ __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
+ __u32 alpha = ca->dctcp_alpha;
+
+ /* alpha = (1 - g) * alpha + g * F */
+
+ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
+ if (delivered_ce) {
+ __u32 delivered = tp->delivered - ca->old_delivered;
+
+ /* If dctcp_shift_g == 1, a 32bit value would overflow
+ * after 8 M packets.
+ */
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
+
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
+ }
+ ca->dctcp_alpha = alpha;
+ dctcp_reset(tp, ca);
+ }
+}
+
+static __always_inline void dctcp_react_to_loss(struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+BPF_TCP_OPS_2(dctcp_state, void, struct sock *, sk, __u8, new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
+}
+
+static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (ce_state == 1)
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ else
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S: 0 <- last pkt was non-CE
+ * 1 <- last pkt was CE
+ */
+static __always_inline
+void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+ __u32 *prior_rcv_nxt, __u32 *ce_state)
+{
+ __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
+
+ if (*ce_state != new_ce_state) {
+ /* CE state has changed, force an immediate ACK to
+ * reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+ dctcp_ece_ack_cwr(sk, *ce_state);
+ bpf_tcp_send_ack(sk, *prior_rcv_nxt);
+ }
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+ }
+ *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt;
+ *ce_state = new_ce_state;
+ dctcp_ece_ack_cwr(sk, new_ce_state);
+}
+
+BPF_TCP_OPS_2(dctcp_cwnd_event, void,
+ struct sock *, sk, enum tcp_ca_event, ev)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ switch (ev) {
+ case CA_EVENT_ECN_IS_CE:
+ case CA_EVENT_ECN_NO_CE:
+ dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
+ break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
+ default:
+ /* Don't care for the rest. */
+ break;
+ }
+}
+
+BPF_TCP_OPS_1(dctcp_cwnd_undo, __u32, struct sock *, sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+BPF_TCP_OPS_3(tcp_reno_cong_avoid, void,
+ struct sock *, sk, __u32, ack, __u32, acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tcp_is_cwnd_limited(sk))
+ return;
+
+ /* In "safe" area, increase. */
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ /* In dangerous area, increase slowly. */
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_nouse = {
+ .init = (void *)dctcp_init,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp_nouse",
+};
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp = {
+ .init = (void *)dctcp_init,
+ .in_ack_event = (void *)dctcp_update_alpha,
+ .cwnd_event = (void *)dctcp_cwnd_event,
+ .ssthresh = (void *)dctcp_ssthresh,
+ .cong_avoid = (void *)tcp_reno_cong_avoid,
+ .undo_cwnd = (void *)dctcp_cwnd_undo,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp",
+};
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.