diff options
Diffstat (limited to 'tools')
77 files changed, 5061 insertions, 1084 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 6965c94dfdaf..09e4f2ff5658 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -20,7 +20,7 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + *OBJECT* := { **map** | **prog** | **link** | **cgroup** | **perf** | **net** | **feature** | **btf** | **gen** | **struct_ops** | **iter** } *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0f6cdf52b1da..7a5498242eaa 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1200,6 +1200,9 @@ enum bpf_perf_event_type { */ #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_REG_INVARIANTS (1U << 7) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ @@ -4517,6 +4520,8 @@ union bpf_attr { * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) * Description * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. * To achieve this, the helper needs *task*, which is a valid * pointer to **struct task_struct**. To store the stacktrace, the * bpf program provides *buf* with a nonnegative *size*. @@ -4528,6 +4533,7 @@ union bpf_attr { * * **BPF_F_USER_STACK** * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. * **BPF_F_USER_BUILD_ID** * Collect buildid+offset instead of ips for user stack, * only valid if **BPF_F_USER_STACK** is also specified. @@ -7151,40 +7157,31 @@ struct bpf_spin_lock { }; struct bpf_timer { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_dynptr { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_head { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_node { - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[3]; } __attribute__((aligned(8))); struct bpf_rb_root { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_rb_node { - __u64 :64; - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[4]; } __attribute__((aligned(8))); struct bpf_refcount { - __u32 :32; + __u32 __opaque[1]; } __attribute__((aligned(4))); struct bpf_sysctl { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 2943a151d4f1..2b37233e00c0 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -65,15 +65,51 @@ enum { }; enum { + NETDEV_A_PAGE_POOL_ID = 1, + NETDEV_A_PAGE_POOL_IFINDEX, + NETDEV_A_PAGE_POOL_NAPI_ID, + NETDEV_A_PAGE_POOL_INFLIGHT, + NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + NETDEV_A_PAGE_POOL_DETACH_TIME, + + __NETDEV_A_PAGE_POOL_MAX, + NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) +}; + +enum { + NETDEV_A_PAGE_POOL_STATS_INFO = 1, + NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + + __NETDEV_A_PAGE_POOL_STATS_MAX, + NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, NETDEV_CMD_DEV_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_GET, + NETDEV_CMD_PAGE_POOL_ADD_NTF, + NETDEV_CMD_PAGE_POOL_DEL_NTF, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_STATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) }; #define NETDEV_MCGRP_MGMT "mgmt" +#define NETDEV_MCGRP_PAGE_POOL "page-pool" #endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index b7060f254486..8fe248e14eb6 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -79,11 +79,14 @@ */ #define LIBBPF_OPTS_RESET(NAME, ...) \ do { \ - memset(&NAME, 0, sizeof(NAME)); \ - NAME = (typeof(NAME)) { \ - .sz = sizeof(NAME), \ - __VA_ARGS__ \ - }; \ + typeof(NAME) ___##NAME = ({ \ + memset(&___##NAME, 0, sizeof(NAME)); \ + (typeof(NAME)) { \ + .sz = sizeof(NAME), \ + __VA_ARGS__ \ + }; \ + }); \ + memcpy(&NAME, &___##NAME, sizeof(NAME)); \ } while (0) #endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index d664b36deb5b..da1aa10bbcc3 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -4,6 +4,8 @@ SUBDIRS = lib generated samples all: $(SUBDIRS) +samples: | lib generated + $(SUBDIRS): @if [ -f "$@/Makefile" ] ; then \ $(MAKE) -C $@ ; \ diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index b5ffe8cd1144..a7b7019d00f1 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -18,6 +18,11 @@ static const char * const netdev_op_strmap[] = { [NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf", [NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf", [NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf", + [NETDEV_CMD_PAGE_POOL_GET] = "page-pool-get", + [NETDEV_CMD_PAGE_POOL_ADD_NTF] = "page-pool-add-ntf", + [NETDEV_CMD_PAGE_POOL_DEL_NTF] = "page-pool-del-ntf", + [NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = "page-pool-change-ntf", + [NETDEV_CMD_PAGE_POOL_STATS_GET] = "page-pool-stats-get", }; const char *netdev_op_str(int op) @@ -59,6 +64,16 @@ const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value) } /* Policies */ +struct ynl_policy_attr netdev_page_pool_info_policy[NETDEV_A_PAGE_POOL_MAX + 1] = { + [NETDEV_A_PAGE_POOL_ID] = { .name = "id", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest netdev_page_pool_info_nest = { + .max_attr = NETDEV_A_PAGE_POOL_MAX, + .table = netdev_page_pool_info_policy, +}; + struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, @@ -72,7 +87,85 @@ struct ynl_policy_nest netdev_dev_nest = { .table = netdev_dev_policy, }; +struct ynl_policy_attr netdev_page_pool_policy[NETDEV_A_PAGE_POOL_MAX + 1] = { + [NETDEV_A_PAGE_POOL_ID] = { .name = "id", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_PAGE_POOL_NAPI_ID] = { .name = "napi-id", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_INFLIGHT] = { .name = "inflight", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_INFLIGHT_MEM] = { .name = "inflight-mem", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_DETACH_TIME] = { .name = "detach-time", .type = YNL_PT_UINT, }, +}; + +struct ynl_policy_nest netdev_page_pool_nest = { + .max_attr = NETDEV_A_PAGE_POOL_MAX, + .table = netdev_page_pool_policy, +}; + +struct ynl_policy_attr netdev_page_pool_stats_policy[NETDEV_A_PAGE_POOL_STATS_MAX + 1] = { + [NETDEV_A_PAGE_POOL_STATS_INFO] = { .name = "info", .type = YNL_PT_NEST, .nest = &netdev_page_pool_info_nest, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST] = { .name = "alloc-fast", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW] = { .name = "alloc-slow", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER] = { .name = "alloc-slow-high-order", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY] = { .name = "alloc-empty", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL] = { .name = "alloc-refill", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE] = { .name = "alloc-waive", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED] = { .name = "recycle-cached", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL] = { .name = "recycle-cache-full", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING] = { .name = "recycle-ring", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL] = { .name = "recycle-ring-full", .type = YNL_PT_UINT, }, + [NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT] = { .name = "recycle-released-refcnt", .type = YNL_PT_UINT, }, +}; + +struct ynl_policy_nest netdev_page_pool_stats_nest = { + .max_attr = NETDEV_A_PAGE_POOL_STATS_MAX, + .table = netdev_page_pool_stats_policy, +}; + /* Common nested types */ +void netdev_page_pool_info_free(struct netdev_page_pool_info *obj) +{ +} + +int netdev_page_pool_info_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct netdev_page_pool_info *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.id) + mnl_attr_put_uint(nlh, NETDEV_A_PAGE_POOL_ID, obj->id); + if (obj->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_PAGE_POOL_IFINDEX, obj->ifindex); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +int netdev_page_pool_info_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct netdev_page_pool_info *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_PAGE_POOL_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.id = 1; + dst->id = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return 0; +} + /* ============== NETDEV_CMD_DEV_GET ============== */ /* NETDEV_CMD_DEV_GET - do */ void netdev_dev_get_req_free(struct netdev_dev_get_req *req) @@ -197,6 +290,314 @@ void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp) free(rsp); } +/* ============== NETDEV_CMD_PAGE_POOL_GET ============== */ +/* NETDEV_CMD_PAGE_POOL_GET - do */ +void netdev_page_pool_get_req_free(struct netdev_page_pool_get_req *req) +{ + free(req); +} + +void netdev_page_pool_get_rsp_free(struct netdev_page_pool_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_page_pool_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct netdev_page_pool_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_PAGE_POOL_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.id = 1; + dst->id = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_PAGE_POOL_NAPI_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.napi_id = 1; + dst->napi_id = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_INFLIGHT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.inflight = 1; + dst->inflight = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_INFLIGHT_MEM) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.inflight_mem = 1; + dst->inflight_mem = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_DETACH_TIME) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.detach_time = 1; + dst->detach_time = mnl_attr_get_uint(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_page_pool_get_rsp * +netdev_page_pool_get(struct ynl_sock *ys, struct netdev_page_pool_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_page_pool_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_PAGE_POOL_GET, 1); + ys->req_policy = &netdev_page_pool_nest; + yrs.yarg.rsp_policy = &netdev_page_pool_nest; + + if (req->_present.id) + mnl_attr_put_uint(nlh, NETDEV_A_PAGE_POOL_ID, req->id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_page_pool_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_PAGE_POOL_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_page_pool_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_PAGE_POOL_GET - dump */ +void netdev_page_pool_get_list_free(struct netdev_page_pool_get_list *rsp) +{ + struct netdev_page_pool_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_page_pool_get_list * +netdev_page_pool_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_page_pool_get_list); + yds.cb = netdev_page_pool_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_PAGE_POOL_GET; + yds.rsp_policy = &netdev_page_pool_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_PAGE_POOL_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_page_pool_get_list_free(yds.first); + return NULL; +} + +/* NETDEV_CMD_PAGE_POOL_GET - notify */ +void netdev_page_pool_get_ntf_free(struct netdev_page_pool_get_ntf *rsp) +{ + free(rsp); +} + +/* ============== NETDEV_CMD_PAGE_POOL_STATS_GET ============== */ +/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */ +void +netdev_page_pool_stats_get_req_free(struct netdev_page_pool_stats_get_req *req) +{ + netdev_page_pool_info_free(&req->info); + free(req); +} + +void +netdev_page_pool_stats_get_rsp_free(struct netdev_page_pool_stats_get_rsp *rsp) +{ + netdev_page_pool_info_free(&rsp->info); + free(rsp); +} + +int netdev_page_pool_stats_get_rsp_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct netdev_page_pool_stats_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_PAGE_POOL_STATS_INFO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.info = 1; + + parg.rsp_policy = &netdev_page_pool_info_nest; + parg.data = &dst->info; + if (netdev_page_pool_info_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_fast = 1; + dst->alloc_fast = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_slow = 1; + dst->alloc_slow = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_slow_high_order = 1; + dst->alloc_slow_high_order = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_empty = 1; + dst->alloc_empty = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_refill = 1; + dst->alloc_refill = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.alloc_waive = 1; + dst->alloc_waive = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.recycle_cached = 1; + dst->recycle_cached = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.recycle_cache_full = 1; + dst->recycle_cache_full = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.recycle_ring = 1; + dst->recycle_ring = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.recycle_ring_full = 1; + dst->recycle_ring_full = mnl_attr_get_uint(attr); + } else if (type == NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.recycle_released_refcnt = 1; + dst->recycle_released_refcnt = mnl_attr_get_uint(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_page_pool_stats_get_rsp * +netdev_page_pool_stats_get(struct ynl_sock *ys, + struct netdev_page_pool_stats_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_page_pool_stats_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_PAGE_POOL_STATS_GET, 1); + ys->req_policy = &netdev_page_pool_stats_nest; + yrs.yarg.rsp_policy = &netdev_page_pool_stats_nest; + + if (req->_present.info) + netdev_page_pool_info_put(nlh, NETDEV_A_PAGE_POOL_STATS_INFO, &req->info); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_page_pool_stats_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_PAGE_POOL_STATS_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_page_pool_stats_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_PAGE_POOL_STATS_GET - dump */ +void +netdev_page_pool_stats_get_list_free(struct netdev_page_pool_stats_get_list *rsp) +{ + struct netdev_page_pool_stats_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + netdev_page_pool_info_free(&rsp->obj.info); + free(rsp); + } +} + +struct netdev_page_pool_stats_get_list * +netdev_page_pool_stats_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_page_pool_stats_get_list); + yds.cb = netdev_page_pool_stats_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_PAGE_POOL_STATS_GET; + yds.rsp_policy = &netdev_page_pool_stats_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_PAGE_POOL_STATS_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_page_pool_stats_get_list_free(yds.first); + return NULL; +} + static const struct ynl_ntf_info netdev_ntf_info[] = { [NETDEV_CMD_DEV_ADD_NTF] = { .alloc_sz = sizeof(struct netdev_dev_get_ntf), @@ -216,6 +617,24 @@ static const struct ynl_ntf_info netdev_ntf_info[] = { .policy = &netdev_dev_nest, .free = (void *)netdev_dev_get_ntf_free, }, + [NETDEV_CMD_PAGE_POOL_ADD_NTF] = { + .alloc_sz = sizeof(struct netdev_page_pool_get_ntf), + .cb = netdev_page_pool_get_rsp_parse, + .policy = &netdev_page_pool_nest, + .free = (void *)netdev_page_pool_get_ntf_free, + }, + [NETDEV_CMD_PAGE_POOL_DEL_NTF] = { + .alloc_sz = sizeof(struct netdev_page_pool_get_ntf), + .cb = netdev_page_pool_get_rsp_parse, + .policy = &netdev_page_pool_nest, + .free = (void *)netdev_page_pool_get_ntf_free, + }, + [NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = { + .alloc_sz = sizeof(struct netdev_page_pool_get_ntf), + .cb = netdev_page_pool_get_rsp_parse, + .policy = &netdev_page_pool_nest, + .free = (void *)netdev_page_pool_get_ntf_free, + }, }; const struct ynl_family ynl_netdev_family = { diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 4fafac879df3..4093602c9b6c 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -21,6 +21,16 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value); const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value); /* Common nested types */ +struct netdev_page_pool_info { + struct { + __u32 id:1; + __u32 ifindex:1; + } _present; + + __u64 id; + __u32 ifindex; +}; + /* ============== NETDEV_CMD_DEV_GET ============== */ /* NETDEV_CMD_DEV_GET - do */ struct netdev_dev_get_req { @@ -87,4 +97,165 @@ struct netdev_dev_get_ntf { void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp); +/* ============== NETDEV_CMD_PAGE_POOL_GET ============== */ +/* NETDEV_CMD_PAGE_POOL_GET - do */ +struct netdev_page_pool_get_req { + struct { + __u32 id:1; + } _present; + + __u64 id; +}; + +static inline struct netdev_page_pool_get_req * +netdev_page_pool_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_page_pool_get_req)); +} +void netdev_page_pool_get_req_free(struct netdev_page_pool_get_req *req); + +static inline void +netdev_page_pool_get_req_set_id(struct netdev_page_pool_get_req *req, __u64 id) +{ + req->_present.id = 1; + req->id = id; +} + +struct netdev_page_pool_get_rsp { + struct { + __u32 id:1; + __u32 ifindex:1; + __u32 napi_id:1; + __u32 inflight:1; + __u32 inflight_mem:1; + __u32 detach_time:1; + } _present; + + __u64 id; + __u32 ifindex; + __u64 napi_id; + __u64 inflight; + __u64 inflight_mem; + __u64 detach_time; +}; + +void netdev_page_pool_get_rsp_free(struct netdev_page_pool_get_rsp *rsp); + +/* + * Get / dump information about Page Pools. +(Only Page Pools associated with a net_device can be listed.) + + */ +struct netdev_page_pool_get_rsp * +netdev_page_pool_get(struct ynl_sock *ys, struct netdev_page_pool_get_req *req); + +/* NETDEV_CMD_PAGE_POOL_GET - dump */ +struct netdev_page_pool_get_list { + struct netdev_page_pool_get_list *next; + struct netdev_page_pool_get_rsp obj __attribute__((aligned(8))); +}; + +void netdev_page_pool_get_list_free(struct netdev_page_pool_get_list *rsp); + +struct netdev_page_pool_get_list * +netdev_page_pool_get_dump(struct ynl_sock *ys); + +/* NETDEV_CMD_PAGE_POOL_GET - notify */ +struct netdev_page_pool_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct netdev_page_pool_get_ntf *ntf); + struct netdev_page_pool_get_rsp obj __attribute__((aligned(8))); +}; + +void netdev_page_pool_get_ntf_free(struct netdev_page_pool_get_ntf *rsp); + +/* ============== NETDEV_CMD_PAGE_POOL_STATS_GET ============== */ +/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */ +struct netdev_page_pool_stats_get_req { + struct { + __u32 info:1; + } _present; + + struct netdev_page_pool_info info; +}; + +static inline struct netdev_page_pool_stats_get_req * +netdev_page_pool_stats_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_page_pool_stats_get_req)); +} +void +netdev_page_pool_stats_get_req_free(struct netdev_page_pool_stats_get_req *req); + +static inline void +netdev_page_pool_stats_get_req_set_info_id(struct netdev_page_pool_stats_get_req *req, + __u64 id) +{ + req->_present.info = 1; + req->info._present.id = 1; + req->info.id = id; +} +static inline void +netdev_page_pool_stats_get_req_set_info_ifindex(struct netdev_page_pool_stats_get_req *req, + __u32 ifindex) +{ + req->_present.info = 1; + req->info._present.ifindex = 1; + req->info.ifindex = ifindex; +} + +struct netdev_page_pool_stats_get_rsp { + struct { + __u32 info:1; + __u32 alloc_fast:1; + __u32 alloc_slow:1; + __u32 alloc_slow_high_order:1; + __u32 alloc_empty:1; + __u32 alloc_refill:1; + __u32 alloc_waive:1; + __u32 recycle_cached:1; + __u32 recycle_cache_full:1; + __u32 recycle_ring:1; + __u32 recycle_ring_full:1; + __u32 recycle_released_refcnt:1; + } _present; + + struct netdev_page_pool_info info; + __u64 alloc_fast; + __u64 alloc_slow; + __u64 alloc_slow_high_order; + __u64 alloc_empty; + __u64 alloc_refill; + __u64 alloc_waive; + __u64 recycle_cached; + __u64 recycle_cache_full; + __u64 recycle_ring; + __u64 recycle_ring_full; + __u64 recycle_released_refcnt; +}; + +void +netdev_page_pool_stats_get_rsp_free(struct netdev_page_pool_stats_get_rsp *rsp); + +/* + * Get page pool statistics. + */ +struct netdev_page_pool_stats_get_rsp * +netdev_page_pool_stats_get(struct ynl_sock *ys, + struct netdev_page_pool_stats_get_req *req); + +/* NETDEV_CMD_PAGE_POOL_STATS_GET - dump */ +struct netdev_page_pool_stats_get_list { + struct netdev_page_pool_stats_get_list *next; + struct netdev_page_pool_stats_get_rsp obj __attribute__((aligned(8))); +}; + +void +netdev_page_pool_stats_get_list_free(struct netdev_page_pool_stats_get_list *rsp); + +struct netdev_page_pool_stats_get_list * +netdev_page_pool_stats_get_dump(struct ynl_sock *ys); + #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h index e974378e3b8c..075d868f3b57 100644 --- a/tools/net/ynl/lib/ynl.h +++ b/tools/net/ynl/lib/ynl.h @@ -239,7 +239,7 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); #ifndef MNL_HAS_AUTO_SCALARS static inline uint64_t mnl_attr_get_uint(const struct nlattr *attr) { - if (mnl_attr_get_len(attr) == 4) + if (mnl_attr_get_payload_len(attr) == 4) return mnl_attr_get_u32(attr); return mnl_attr_get_u64(attr); } diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore index 2aae60c4829f..49637b26c482 100644 --- a/tools/net/ynl/samples/.gitignore +++ b/tools/net/ynl/samples/.gitignore @@ -1,3 +1,4 @@ ethtool devlink netdev +page-pool
\ No newline at end of file diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile index 3dbb106e87d9..28bdb1557a54 100644 --- a/tools/net/ynl/samples/Makefile +++ b/tools/net/ynl/samples/Makefile @@ -18,7 +18,9 @@ include $(wildcard *.d) all: $(BINS) -$(BINS): ../lib/ynl.a ../generated/protos.a +CFLAGS_page-pool=$(CFLAGS_netdev) + +$(BINS): ../lib/ynl.a ../generated/protos.a $(SRCS) @echo -e '\tCC sample $@' @$(COMPILE.c) $(CFLAGS_$@) $@.c -o $@.o @$(LINK.c) $@.o -o $@ $(LDLIBS) diff --git a/tools/net/ynl/samples/page-pool.c b/tools/net/ynl/samples/page-pool.c new file mode 100644 index 000000000000..098b5190d0e5 --- /dev/null +++ b/tools/net/ynl/samples/page-pool.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include <net/if.h> + +#include "netdev-user.h" + +struct stat { + unsigned int ifc; + + struct { + unsigned int cnt; + size_t refs, bytes; + } live[2]; + + size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache; +}; + +struct stats_array { + unsigned int i, max; + struct stat *s; +}; + +static struct stat *find_ifc(struct stats_array *a, unsigned int ifindex) +{ + unsigned int i; + + for (i = 0; i < a->i; i++) { + if (a->s[i].ifc == ifindex) + return &a->s[i]; + } + + a->i++; + if (a->i == a->max) { + a->max *= 2; + a->s = reallocarray(a->s, a->max, sizeof(*a->s)); + } + a->s[i].ifc = ifindex; + return &a->s[i]; +} + +static void count(struct stat *s, unsigned int l, + struct netdev_page_pool_get_rsp *pp) +{ + s->live[l].cnt++; + if (pp->_present.inflight) + s->live[l].refs += pp->inflight; + if (pp->_present.inflight_mem) + s->live[l].bytes += pp->inflight_mem; +} + +int main(int argc, char **argv) +{ + struct netdev_page_pool_stats_get_list *pp_stats; + struct netdev_page_pool_get_list *pools; + struct stats_array a = {}; + struct ynl_error yerr; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + a.max = 128; + a.s = calloc(a.max, sizeof(*a.s)); + if (!a.s) + goto err_close; + + pools = netdev_page_pool_get_dump(ys); + if (!pools) + goto err_free; + + ynl_dump_foreach(pools, pp) { + struct stat *s = find_ifc(&a, pp->ifindex); + + count(s, 1, pp); + if (pp->_present.detach_time) + count(s, 0, pp); + } + netdev_page_pool_get_list_free(pools); + + pp_stats = netdev_page_pool_stats_get_dump(ys); + if (!pp_stats) + goto err_free; + + ynl_dump_foreach(pp_stats, pp) { + struct stat *s = find_ifc(&a, pp->info.ifindex); + + if (pp->_present.alloc_fast) + s->alloc_fast += pp->alloc_fast; + if (pp->_present.alloc_slow) + s->alloc_slow += pp->alloc_slow; + if (pp->_present.recycle_ring) + s->recycle_ring += pp->recycle_ring; + if (pp->_present.recycle_cached) + s->recycle_cache += pp->recycle_cached; + } + netdev_page_pool_stats_get_list_free(pp_stats); + + for (unsigned int i = 0; i < a.i; i++) { + char ifname[IF_NAMESIZE]; + struct stat *s = &a.s[i]; + const char *name; + double recycle; + + if (!s->ifc) { + name = "<orphan>\t"; + } else { + name = if_indextoname(s->ifc, ifname); + if (name) + printf("%8s", name); + printf("[%d]\t", s->ifc); + } + + printf("page pools: %u (zombies: %u)\n", + s->live[1].cnt, s->live[0].cnt); + printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n", + s->live[1].refs, s->live[1].bytes, + s->live[0].refs, s->live[0].bytes); + + /* We don't know how many pages are sitting in cache and ring + * so we will under-count the recycling rate a bit. + */ + recycle = (double)(s->recycle_ring + s->recycle_cache) / + (s->alloc_fast + s->alloc_slow) * 100; + printf("\t\trecycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)\n", + recycle, s->alloc_slow, s->alloc_fast, + s->recycle_ring, s->recycle_cache); + } + + ynl_sock_destroy(ys); + return 0; + +err_free: + free(a.s); +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 8337aa6de25e..266bc1629e58 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -67,9 +67,9 @@ class Type(SpecAttr): if 'nested-attributes' in attr: self.nested_attrs = attr['nested-attributes'] if self.nested_attrs == family.name: - self.nested_render_name = f"{family.name}" + self.nested_render_name = c_lower(f"{family.name}") else: - self.nested_render_name = f"{family.name}_{c_lower(self.nested_attrs)}" + self.nested_render_name = c_lower(f"{family.name}_{self.nested_attrs}") if self.nested_attrs in self.family.consts: self.nested_struct_type = 'struct ' + self.nested_render_name + '_' @@ -335,7 +335,7 @@ class TypeScalar(Type): maybe_enum = not self.is_bitfield and 'enum' in self.attr if maybe_enum and self.family.consts[self.attr['enum']].enum_name: - self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}" + self.type_name = c_lower(f"enum {self.family.name}_{self.attr['enum']}") elif self.is_auto_scalar: self.type_name = '__' + self.type[0] + '64' else: @@ -685,9 +685,9 @@ class Struct: self.nested = type_list is None if family.name == c_lower(space_name): - self.render_name = f"{family.name}" + self.render_name = c_lower(family.name) else: - self.render_name = f"{family.name}_{c_lower(space_name)}" + self.render_name = c_lower(family.name + '-' + space_name) self.struct_name = 'struct ' + self.render_name if self.nested and space_name in family.consts: self.struct_name += '_' @@ -755,11 +755,17 @@ class EnumSet(SpecEnumSet): if 'enum-name' in yaml: if yaml['enum-name']: self.enum_name = 'enum ' + c_lower(yaml['enum-name']) + self.user_type = self.enum_name else: self.enum_name = None else: self.enum_name = 'enum ' + self.render_name + if self.enum_name: + self.user_type = self.enum_name + else: + self.user_type = 'int' + self.value_pfx = yaml.get('name-prefix', f"{family.name}-{yaml['name']}-") super().__init__(family, yaml) @@ -841,7 +847,7 @@ class Operation(SpecOperation): def __init__(self, family, yaml, req_value, rsp_value): super().__init__(family, yaml, req_value, rsp_value) - self.render_name = family.name + '_' + c_lower(self.name) + self.render_name = c_lower(family.name + '_' + self.name) self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \ ('dump' in yaml and 'request' in yaml['dump']) @@ -1158,8 +1164,9 @@ class RenderInfo: class CodeWriter: - def __init__(self, nlib, out_file=None): + def __init__(self, nlib, out_file=None, overwrite=True): self.nlib = nlib + self._overwrite = overwrite self._nl = False self._block_end = False @@ -1180,8 +1187,9 @@ class CodeWriter: return # Avoid modifying the file if contents didn't change self._out.flush() - if os.path.isfile(self._out_file) and filecmp.cmp(self._out.name, self._out_file, shallow=False): - return + if not self._overwrite and os.path.isfile(self._out_file): + if filecmp.cmp(self._out.name, self._out_file, shallow=False): + return with open(self._out_file, 'w+') as out_file: self._out.seek(0) shutil.copyfileobj(self._out, out_file) @@ -1431,7 +1439,7 @@ def op_prefix(ri, direction, deref=False): suffix += '_rsp' suffix += '_dump' if deref else '_list' - return f"{ri.family['name']}{suffix}" + return f"{ri.family.c_name}{suffix}" def type_name(ri, direction, deref=False): @@ -1483,8 +1491,8 @@ def put_typol(cw, struct): def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None): args = [f'int {arg_name}'] - if enum and not ('enum-name' in enum and not enum['enum-name']): - args = [f'enum {render_name} {arg_name}'] + if enum: + args = [enum.user_type + ' ' + arg_name] cw.write_func_prot('const char *', f'{render_name}_str', args) cw.block_start() if enum and enum.type == 'flags': @@ -1497,11 +1505,11 @@ def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None): def put_op_name_fwd(family, cw): - cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op'], suffix=';') + cw.write_func_prot('const char *', f'{family.c_name}_op_str', ['int op'], suffix=';') def put_op_name(family, cw): - map_name = f'{family.name}_op_strmap' + map_name = f'{family.c_name}_op_strmap' cw.block_start(line=f"static const char * const {map_name}[] =") for op_name, op in family.msgs.items(): if op.rsp_value: @@ -1518,13 +1526,11 @@ def put_op_name(family, cw): cw.block_end(line=';') cw.nl() - _put_enum_to_str_helper(cw, family.name + '_op', map_name, 'op') + _put_enum_to_str_helper(cw, family.c_name + '_op', map_name, 'op') def put_enum_to_str_fwd(family, cw, enum): - args = [f'enum {enum.render_name} value'] - if 'enum-name' in enum and not enum['enum-name']: - args = ['int value'] + args = [enum.user_type + ' value'] cw.write_func_prot('const char *', f'{enum.render_name}_str', args, suffix=';') @@ -1838,7 +1844,7 @@ def _print_type(ri, direction, struct): if ri.op_mode == 'dump': suffix += '_dump' - ri.cw.block_start(line=f"struct {ri.family['name']}{suffix}") + ri.cw.block_start(line=f"struct {ri.family.c_name}{suffix}") meta_started = False for _, attr in struct.member_list(): @@ -2068,12 +2074,13 @@ def print_kernel_policy_ranges(family, cw): first = False sign = '' if attr.type[0] == 'u' else '_signed' + suffix = 'ULL' if attr.type[0] == 'u' else 'LL' cw.block_start(line=f'static const struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =') members = [] if 'min' in attr.checks: - members.append(('min', attr.get_limit('min'))) + members.append(('min', str(attr.get_limit('min')) + suffix)) if 'max' in attr.checks: - members.append(('max', attr.get_limit('max'))) + members.append(('max', str(attr.get_limit('max')) + suffix)) cw.write_struct_init(members) cw.block_end(line=';') cw.nl() @@ -2103,7 +2110,7 @@ def print_kernel_op_table_fwd(family, cw, terminate): cnt = len(family.ops) qual = 'static const' if not exported else 'const' - line = f"{qual} struct {struct_type} {family.name}_nl_ops[{cnt}]" + line = f"{qual} struct {struct_type} {family.c_name}_nl_ops[{cnt}]" if terminate: cw.p(f"extern {line};") else: @@ -2246,7 +2253,7 @@ def print_kernel_mcgrp_src(family, cw): if not family.mcgrps['list']: return - cw.block_start('static const struct genl_multicast_group ' + family.name + '_nl_mcgrps[] =') + cw.block_start('static const struct genl_multicast_group ' + family.c_name + '_nl_mcgrps[] =') for grp in family.mcgrps['list']: name = grp['name'] grp_id = c_upper(f"{family.name}-nlgrp-{name}") @@ -2259,7 +2266,7 @@ def print_kernel_family_struct_hdr(family, cw): if not kernel_can_gen_family_struct(family): return - cw.p(f"extern struct genl_family {family.name}_nl_family;") + cw.p(f"extern struct genl_family {family.c_name}_nl_family;") cw.nl() @@ -2274,14 +2281,14 @@ def print_kernel_family_struct_src(family, cw): cw.p('.parallel_ops\t= true,') cw.p('.module\t\t= THIS_MODULE,') if family.kernel_policy == 'per-op': - cw.p(f'.ops\t\t= {family.name}_nl_ops,') - cw.p(f'.n_ops\t\t= ARRAY_SIZE({family.name}_nl_ops),') + cw.p(f'.ops\t\t= {family.c_name}_nl_ops,') + cw.p(f'.n_ops\t\t= ARRAY_SIZE({family.c_name}_nl_ops),') elif family.kernel_policy == 'split': - cw.p(f'.split_ops\t= {family.name}_nl_ops,') - cw.p(f'.n_split_ops\t= ARRAY_SIZE({family.name}_nl_ops),') + cw.p(f'.split_ops\t= {family.c_name}_nl_ops,') + cw.p(f'.n_split_ops\t= ARRAY_SIZE({family.c_name}_nl_ops),') if family.mcgrps['list']: - cw.p(f'.mcgrps\t\t= {family.name}_nl_mcgrps,') - cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.name}_nl_mcgrps),') + cw.p(f'.mcgrps\t\t= {family.c_name}_nl_mcgrps,') + cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),') cw.block_end(';') @@ -2291,7 +2298,7 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'): if obj[enum_name]: start_line = 'enum ' + c_lower(obj[enum_name]) elif ckey and ckey in obj: - start_line = 'enum ' + family.name + '_' + c_lower(obj[ckey]) + start_line = 'enum ' + family.c_name + '_' + c_lower(obj[ckey]) cw.block_start(line=start_line) @@ -2475,7 +2482,7 @@ def render_user_family(family, cw, prototype): cw.nl() cw.block_start(f'{symbol} = ') - cw.p(f'.name\t\t= "{family.name}",') + cw.p(f'.name\t\t= "{family.c_name}",') if family.ntfs: cw.p(f".ntf_info\t= {family['name']}_ntf_info,") cw.p(f".ntf_info_size\t= MNL_ARRAY_SIZE({family['name']}_ntf_info),") @@ -2509,6 +2516,8 @@ def main(): parser.add_argument('--header', dest='header', action='store_true', default=None) parser.add_argument('--source', dest='header', action='store_false') parser.add_argument('--user-header', nargs='+', default=[]) + parser.add_argument('--cmp-out', action='store_true', default=None, + help='Do not overwrite the output file if the new output is identical to the old') parser.add_argument('--exclude-op', action='append', default=[]) parser.add_argument('-o', dest='out_file', type=str, default=None) args = parser.parse_args() @@ -2536,7 +2545,7 @@ def main(): print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') os.sys.exit(1) - cw = CodeWriter(BaseNlLib(), args.out_file) + cw = CodeWriter(BaseNlLib(), args.out_file, overwrite=(not args.cmp_out)) _, spec_kernel = find_kernel_root(args.spec) if args.mode == 'uapi' or args.header: @@ -2557,7 +2566,7 @@ def main(): render_uapi(parsed, cw) return - hdr_prot = f"_LINUX_{parsed.name.upper()}_GEN_H" + hdr_prot = f"_LINUX_{parsed.c_name.upper()}_GEN_H" if args.header: cw.p('#ifndef ' + hdr_prot) cw.p('#define ' + hdr_prot) diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py new file mode 100755 index 000000000000..b6292109e236 --- /dev/null +++ b/tools/net/ynl/ynl-gen-rst.py @@ -0,0 +1,388 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# -*- coding: utf-8; mode: python -*- + +""" + Script to auto generate the documentation for Netlink specifications. + + :copyright: Copyright (C) 2023 Breno Leitao <leitao@debian.org> + :license: GPL Version 2, June 1991 see linux/COPYING for details. + + This script performs extensive parsing to the Linux kernel's netlink YAML + spec files, in an effort to avoid needing to heavily mark up the original + YAML file. + + This code is split in three big parts: + 1) RST formatters: Use to convert a string to a RST output + 2) Parser helpers: Functions to parse the YAML data structure + 3) Main function and small helpers +""" + +from typing import Any, Dict, List +import os.path +import sys +import argparse +import logging +import yaml + + +SPACE_PER_LEVEL = 4 + + +# RST Formatters +# ============== +def headroom(level: int) -> str: + """Return space to format""" + return " " * (level * SPACE_PER_LEVEL) + + +def bold(text: str) -> str: + """Format bold text""" + return f"**{text}**" + + +def inline(text: str) -> str: + """Format inline text""" + return f"``{text}``" + + +def sanitize(text: str) -> str: + """Remove newlines and multiple spaces""" + # This is useful for some fields that are spread across multiple lines + return str(text).replace("\n", "").strip() + + +def rst_fields(key: str, value: str, level: int = 0) -> str: + """Return a RST formatted field""" + return headroom(level) + f":{key}: {value}" + + +def rst_definition(key: str, value: Any, level: int = 0) -> str: + """Format a single rst definition""" + return headroom(level) + key + "\n" + headroom(level + 1) + str(value) + + +def rst_paragraph(paragraph: str, level: int = 0) -> str: + """Return a formatted paragraph""" + return headroom(level) + paragraph + + +def rst_bullet(item: str, level: int = 0) -> str: + """Return a formatted a bullet""" + return headroom(level) + f" - {item}" + + +def rst_subsection(title: str) -> str: + """Add a sub-section to the document""" + return f"{title}\n" + "-" * len(title) + + +def rst_subsubsection(title: str) -> str: + """Add a sub-sub-section to the document""" + return f"{title}\n" + "~" * len(title) + + +def rst_section(title: str) -> str: + """Add a section to the document""" + return f"\n{title}\n" + "=" * len(title) + + +def rst_subtitle(title: str) -> str: + """Add a subtitle to the document""" + return "\n" + "-" * len(title) + f"\n{title}\n" + "-" * len(title) + "\n\n" + + +def rst_title(title: str) -> str: + """Add a title to the document""" + return "=" * len(title) + f"\n{title}\n" + "=" * len(title) + "\n\n" + + +def rst_list_inline(list_: List[str], level: int = 0) -> str: + """Format a list using inlines""" + return headroom(level) + "[" + ", ".join(inline(i) for i in list_) + "]" + + +def rst_header() -> str: + """The headers for all the auto generated RST files""" + lines = [] + + lines.append(rst_paragraph(".. SPDX-License-Identifier: GPL-2.0")) + lines.append(rst_paragraph(".. NOTE: This document was auto-generated.\n\n")) + + return "\n".join(lines) + + +def rst_toctree(maxdepth: int = 2) -> str: + """Generate a toctree RST primitive""" + lines = [] + + lines.append(".. toctree::") + lines.append(f" :maxdepth: {maxdepth}\n\n") + + return "\n".join(lines) + + +# Parsers +# ======= + + +def parse_mcast_group(mcast_group: List[Dict[str, Any]]) -> str: + """Parse 'multicast' group list and return a formatted string""" + lines = [] + for group in mcast_group: + lines.append(rst_bullet(group["name"])) + + return "\n".join(lines) + + +def parse_do(do_dict: Dict[str, Any], level: int = 0) -> str: + """Parse 'do' section and return a formatted string""" + lines = [] + for key in do_dict.keys(): + lines.append(rst_paragraph(bold(key), level + 1)) + lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n") + + return "\n".join(lines) + + +def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str: + """Parse 'attributes' section""" + if "attributes" not in attrs: + return "" + lines = [rst_fields("attributes", rst_list_inline(attrs["attributes"]), level + 1)] + + return "\n".join(lines) + + +def parse_operations(operations: List[Dict[str, Any]]) -> str: + """Parse operations block""" + preprocessed = ["name", "doc", "title", "do", "dump"] + lines = [] + + for operation in operations: + lines.append(rst_section(operation["name"])) + lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n") + + for key in operation.keys(): + if key in preprocessed: + # Skip the special fields + continue + lines.append(rst_fields(key, operation[key], 0)) + + if "do" in operation: + lines.append(rst_paragraph(":do:", 0)) + lines.append(parse_do(operation["do"], 0)) + if "dump" in operation: + lines.append(rst_paragraph(":dump:", 0)) + lines.append(parse_do(operation["dump"], 0)) + + # New line after fields + lines.append("\n") + + return "\n".join(lines) + + +def parse_entries(entries: List[Dict[str, Any]], level: int) -> str: + """Parse a list of entries""" + lines = [] + for entry in entries: + if isinstance(entry, dict): + # entries could be a list or a dictionary + lines.append( + rst_fields(entry.get("name", ""), sanitize(entry.get("doc", "")), level) + ) + elif isinstance(entry, list): + lines.append(rst_list_inline(entry, level)) + else: + lines.append(rst_bullet(inline(sanitize(entry)), level)) + + lines.append("\n") + return "\n".join(lines) + + +def parse_definitions(defs: Dict[str, Any]) -> str: + """Parse definitions section""" + preprocessed = ["name", "entries", "members"] + ignored = ["render-max"] # This is not printed + lines = [] + + for definition in defs: + lines.append(rst_section(definition["name"])) + for k in definition.keys(): + if k in preprocessed + ignored: + continue + lines.append(rst_fields(k, sanitize(definition[k]), 0)) + + # Field list needs to finish with a new line + lines.append("\n") + if "entries" in definition: + lines.append(rst_paragraph(":entries:", 0)) + lines.append(parse_entries(definition["entries"], 1)) + if "members" in definition: + lines.append(rst_paragraph(":members:", 0)) + lines.append(parse_entries(definition["members"], 1)) + + return "\n".join(lines) + + +def parse_attr_sets(entries: List[Dict[str, Any]]) -> str: + """Parse attribute from attribute-set""" + preprocessed = ["name", "type"] + ignored = ["checks"] + lines = [] + + for entry in entries: + lines.append(rst_section(entry["name"])) + for attr in entry["attributes"]: + type_ = attr.get("type") + attr_line = bold(attr["name"]) + if type_: + # Add the attribute type in the same line + attr_line += f" ({inline(type_)})" + + lines.append(rst_subsubsection(attr_line)) + + for k in attr.keys(): + if k in preprocessed + ignored: + continue + lines.append(rst_fields(k, sanitize(attr[k]), 2)) + lines.append("\n") + + return "\n".join(lines) + + +def parse_yaml(obj: Dict[str, Any]) -> str: + """Format the whole YAML into a RST string""" + lines = [] + + # Main header + + lines.append(rst_header()) + + title = f"Family ``{obj['name']}`` netlink specification" + lines.append(rst_title(title)) + lines.append(rst_paragraph(".. contents::\n")) + + if "doc" in obj: + lines.append(rst_subtitle("Summary")) + lines.append(rst_paragraph(obj["doc"], 0)) + + # Operations + if "operations" in obj: + lines.append(rst_subtitle("Operations")) + lines.append(parse_operations(obj["operations"]["list"])) + + # Multicast groups + if "mcast-groups" in obj: + lines.append(rst_subtitle("Multicast groups")) + lines.append(parse_mcast_group(obj["mcast-groups"]["list"])) + + # Definitions + if "definitions" in obj: + lines.append(rst_subtitle("Definitions")) + lines.append(parse_definitions(obj["definitions"])) + + # Attributes set + if "attribute-sets" in obj: + lines.append(rst_subtitle("Attribute sets")) + lines.append(parse_attr_sets(obj["attribute-sets"])) + + return "\n".join(lines) + + +# Main functions +# ============== + + +def parse_arguments() -> argparse.Namespace: + """Parse arguments from user""" + parser = argparse.ArgumentParser(description="Netlink RST generator") + + parser.add_argument("-v", "--verbose", action="store_true") + parser.add_argument("-o", "--output", help="Output file name") + + # Index and input are mutually exclusive + group = parser.add_mutually_exclusive_group() + group.add_argument( + "-x", "--index", action="store_true", help="Generate the index page" + ) + group.add_argument("-i", "--input", help="YAML file name") + + args = parser.parse_args() + + if args.verbose: + logging.basicConfig(level=logging.DEBUG) + + if args.input and not os.path.isfile(args.input): + logging.warning("%s is not a valid file.", args.input) + sys.exit(-1) + + if not args.output: + logging.error("No output file specified.") + sys.exit(-1) + + if os.path.isfile(args.output): + logging.debug("%s already exists. Overwriting it.", args.output) + + return args + + +def parse_yaml_file(filename: str) -> str: + """Transform the YAML specified by filename into a rst-formmated string""" + with open(filename, "r", encoding="utf-8") as spec_file: + yaml_data = yaml.safe_load(spec_file) + content = parse_yaml(yaml_data) + + return content + + +def write_to_rstfile(content: str, filename: str) -> None: + """Write the generated content into an RST file""" + logging.debug("Saving RST file to %s", filename) + + with open(filename, "w", encoding="utf-8") as rst_file: + rst_file.write(content) + + +def generate_main_index_rst(output: str) -> None: + """Generate the `networking_spec/index` content and write to the file""" + lines = [] + + lines.append(rst_header()) + lines.append(rst_title("Netlink Specification")) + lines.append(rst_toctree(1)) + + index_dir = os.path.dirname(output) + logging.debug("Looking for .rst files in %s", index_dir) + for filename in os.listdir(index_dir): + if not filename.endswith(".rst") or filename == "index.rst": + continue + lines.append(f" {filename.replace('.rst', '')}\n") + + logging.debug("Writing an index file at %s", output) + write_to_rstfile("".join(lines), output) + + +def main() -> None: + """Main function that reads the YAML files and generates the RST files""" + + args = parse_arguments() + + if args.input: + logging.debug("Parsing %s", args.input) + try: + content = parse_yaml_file(os.path.join(args.input)) + except Exception as exception: + logging.warning("Failed to parse %s.", args.input) + logging.warning(exception) + sys.exit(-1) + + write_to_rstfile(content, args.output) + + if args.index: + # Generate the index RST file + generate_main_index_rst(args.output) + + +if __name__ == "__main__": + main() diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index bdba24066cf1..a37304dcc88e 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -30,8 +30,8 @@ for f in $files; do fi echo -e "\tGEN ${params[2]}\t$f" - $TOOL --mode ${params[2]} --${params[3]} --spec $KDIR/${params[0]} \ - $args -o $f + $TOOL --cmp-out --mode ${params[2]} --${params[3]} \ + --spec $KDIR/${params[0]} $args -o $f done popd >>/dev/null diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 5b1da2a32ea7..5aa133bf3688 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -45,9 +45,12 @@ #define format_parent_cgroup_path(buf, path) \ format_cgroup_path_pid(buf, path, getppid()) -#define format_classid_path(buf) \ - snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ - CGROUP_WORK_DIR) +#define format_classid_path_pid(buf, pid) \ + snprintf(buf, sizeof(buf), "%s%s%d", NETCLS_MOUNT_PATH, \ + CGROUP_WORK_DIR, pid) + +#define format_classid_path(buf) \ + format_classid_path_pid(buf, getpid()) static __thread bool cgroup_workdir_mounted; @@ -419,26 +422,23 @@ int create_and_get_cgroup(const char *relative_path) } /** - * get_cgroup_id() - Get cgroup id for a particular cgroup path - * @relative_path: The cgroup path, relative to the workdir, to join + * get_cgroup_id_from_path - Get cgroup id for a particular cgroup path + * @cgroup_workdir: The absolute cgroup path * * On success, it returns the cgroup id. On failure it returns 0, * which is an invalid cgroup id. * If there is a failure, it prints the error to stderr. */ -unsigned long long get_cgroup_id(const char *relative_path) +unsigned long long get_cgroup_id_from_path(const char *cgroup_workdir) { int dirfd, err, flags, mount_id, fhsize; union { unsigned long long cgid; unsigned char raw_bytes[8]; } id; - char cgroup_workdir[PATH_MAX + 1]; struct file_handle *fhp, *fhp2; unsigned long long ret = 0; - format_cgroup_path(cgroup_workdir, relative_path); - dirfd = AT_FDCWD; flags = 0; fhsize = sizeof(*fhp); @@ -474,6 +474,14 @@ free_mem: return ret; } +unsigned long long get_cgroup_id(const char *relative_path) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_cgroup_path(cgroup_workdir, relative_path); + return get_cgroup_id_from_path(cgroup_workdir); +} + int cgroup_setup_and_join(const char *path) { int cg_fd; @@ -523,10 +531,20 @@ int setup_classid_environment(void) return 1; } - if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && - errno != EBUSY) { - log_err("mount cgroup net_cls"); - return 1; + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls")) { + if (errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + if (rmdir(NETCLS_MOUNT_PATH)) { + log_err("rmdir cgroup net_cls"); + return 1; + } + if (umount(CGROUP_MOUNT_DFLT)) { + log_err("umount cgroup base"); + return 1; + } } cleanup_classid_environment(); @@ -541,15 +559,16 @@ int setup_classid_environment(void) /** * set_classid() - Set a cgroupv1 net_cls classid - * @id: the numeric classid * - * Writes the passed classid into the cgroup work dir's net_cls.classid + * Writes the classid into the cgroup work dir's net_cls.classid * file in order to later on trigger socket tagging. * + * We leverage the current pid as the classid, ensuring unique identification. + * * On success, it returns 0, otherwise on failure it returns 1. If there * is a failure, it prints the error to stderr. */ -int set_classid(unsigned int id) +int set_classid(void) { char cgroup_workdir[PATH_MAX - 42]; char cgroup_classid_path[PATH_MAX + 1]; @@ -565,7 +584,7 @@ int set_classid(unsigned int id) return 1; } - if (dprintf(fd, "%u\n", id) < 0) { + if (dprintf(fd, "%u\n", getpid()) < 0) { log_err("Setting cgroup classid"); rc = 1; } @@ -607,3 +626,66 @@ void cleanup_classid_environment(void) join_cgroup_from_top(NETCLS_MOUNT_PATH); nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT); } + +/** + * get_classid_cgroup_id - Get the cgroup id of a net_cls cgroup + */ +unsigned long long get_classid_cgroup_id(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return get_cgroup_id_from_path(cgroup_workdir); +} + +/** + * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name. + * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be + * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-contollers like + * "net_cls,net_prio". + */ +int get_cgroup1_hierarchy_id(const char *subsys_name) +{ + char *c, *c2, *c3, *c4; + bool found = false; + char line[1024]; + FILE *file; + int i, id; + + if (!subsys_name) + return -1; + + file = fopen("/proc/self/cgroup", "r"); + if (!file) { + log_err("fopen /proc/self/cgroup"); + return -1; + } + + while (fgets(line, 1024, file)) { + i = 0; + for (c = strtok_r(line, ":", &c2); c && i < 2; c = strtok_r(NULL, ":", &c2)) { + if (i == 0) { + id = strtol(c, NULL, 10); + } else if (i == 1) { + if (!strcmp(c, subsys_name)) { + found = true; + break; + } + + /* Multiple subsystems may share one single mount point */ + for (c3 = strtok_r(c, ",", &c4); c3; + c3 = strtok_r(NULL, ",", &c4)) { + if (!strcmp(c, subsys_name)) { + found = true; + break; + } + } + } + i++; + } + if (found) + break; + } + fclose(file); + return found ? id : -1; +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 5c2cb9c8b546..ee053641c026 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -20,6 +20,7 @@ int get_root_cgroup(void); int create_and_get_cgroup(const char *relative_path); void remove_cgroup(const char *relative_path); unsigned long long get_cgroup_id(const char *relative_path); +int get_cgroup1_hierarchy_id(const char *subsys_name); int join_cgroup(const char *relative_path); int join_root_cgroup(void); @@ -29,8 +30,9 @@ int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); /* cgroupv1 related */ -int set_classid(unsigned int id); +int set_classid(void); int join_classid(void); +unsigned long long get_classid_cgroup_id(void); int setup_classid_environment(void); void cleanup_classid_environment(void); diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64 index 253821494884..29c8635c5722 100644 --- a/tools/testing/selftests/bpf/config.aarch64 +++ b/tools/testing/selftests/bpf/config.aarch64 @@ -1,4 +1,3 @@ -CONFIG_9P_FS=y CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y CONFIG_ARM_SMMU_V3=y @@ -37,6 +36,7 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_REDUCED=n CONFIG_DEBUG_LIST=y CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_NOTIFIERS=y @@ -46,7 +46,6 @@ CONFIG_DEBUG_SG=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_DEVTMPFS=y -CONFIG_DRM_VIRTIO_GPU=y CONFIG_DRM=y CONFIG_DUMMY=y CONFIG_EXPERT=y @@ -67,7 +66,6 @@ CONFIG_HAVE_KRETPROBES=y CONFIG_HEADERS_INSTALL=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HUGETLBFS=y -CONFIG_HW_RANDOM_VIRTIO=y CONFIG_HW_RANDOM=y CONFIG_HZ_100=y CONFIG_IDLE_PAGE_TRACKING=y @@ -99,8 +97,6 @@ CONFIG_MEMCG=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_NAMESPACES=y -CONFIG_NET_9P_VIRTIO=y -CONFIG_NET_9P=y CONFIG_NET_ACT_BPF=y CONFIG_NET_ACT_GACT=y CONFIG_NETDEVICES=y @@ -140,7 +136,6 @@ CONFIG_SCHED_TRACER=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SCAN_ASYNC=y -CONFIG_SCSI_VIRTIO=y CONFIG_SCSI=y CONFIG_SECURITY_NETWORK=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y @@ -167,16 +162,6 @@ CONFIG_UPROBES=y CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y -CONFIG_VIRTIO_BALLOON=y -CONFIG_VIRTIO_BLK=y -CONFIG_VIRTIO_CONSOLE=y -CONFIG_VIRTIO_FS=y -CONFIG_VIRTIO_INPUT=y -CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_VIRTIO_MMIO=y -CONFIG_VIRTIO_NET=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_VSOCKETS_COMMON=y CONFIG_VLAN_8021Q=y CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x index 2ba92167be35..e93330382849 100644 --- a/tools/testing/selftests/bpf/config.s390x +++ b/tools/testing/selftests/bpf/config.s390x @@ -1,4 +1,3 @@ -CONFIG_9P_FS=y CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y CONFIG_AUDIT=y CONFIG_BLK_CGROUP=y @@ -84,8 +83,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_NAMESPACES=y CONFIG_NET=y -CONFIG_NET_9P=y -CONFIG_NET_9P_VIRTIO=y CONFIG_NET_ACT_BPF=y CONFIG_NET_ACT_GACT=y CONFIG_NET_KEY=y @@ -114,7 +111,6 @@ CONFIG_SAMPLE_SECCOMP=y CONFIG_SAMPLES=y CONFIG_SCHED_TRACER=y CONFIG_SCSI=y -CONFIG_SCSI_VIRTIO=y CONFIG_SECURITY_NETWORK=y CONFIG_STACK_TRACER=y CONFIG_STATIC_KEYS_SELFTEST=y @@ -136,11 +132,6 @@ CONFIG_UPROBES=y CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y -CONFIG_VIRTIO_BALLOON=y -CONFIG_VIRTIO_BLK=y -CONFIG_VIRTIO_NET=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_VSOCKETS_COMMON=y CONFIG_VLAN_8021Q=y CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y diff --git a/tools/testing/selftests/bpf/config.vm b/tools/testing/selftests/bpf/config.vm new file mode 100644 index 000000000000..a9746ca78777 --- /dev/null +++ b/tools/testing/selftests/bpf/config.vm @@ -0,0 +1,12 @@ +CONFIG_9P_FS=y +CONFIG_9P_FS_POSIX_ACL=y +CONFIG_9P_FS_SECURITY=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_NET=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_VSOCKETS_COMMON=y diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index 2e70a6048278..f7bfb2b09c82 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -1,6 +1,3 @@ -CONFIG_9P_FS=y -CONFIG_9P_FS_POSIX_ACL=y -CONFIG_9P_FS_SECURITY=y CONFIG_AGP=y CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y @@ -45,7 +42,6 @@ CONFIG_CPU_IDLE_GOV_LADDER=y CONFIG_CPUSETS=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_BLAKE2B=y -CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y @@ -145,8 +141,6 @@ CONFIG_MEMORY_FAILURE=y CONFIG_MINIX_SUBPARTITION=y CONFIG_NAMESPACES=y CONFIG_NET=y -CONFIG_NET_9P=y -CONFIG_NET_9P_VIRTIO=y CONFIG_NET_ACT_BPF=y CONFIG_NET_CLS_CGROUP=y CONFIG_NET_EMATCH=y @@ -228,12 +222,6 @@ CONFIG_USER_NS=y CONFIG_VALIDATE_FS_PARSER=y CONFIG_VETH=y CONFIG_VIRT_DRIVERS=y -CONFIG_VIRTIO_BALLOON=y -CONFIG_VIRTIO_BLK=y -CONFIG_VIRTIO_CONSOLE=y -CONFIG_VIRTIO_NET=y -CONFIG_VIRTIO_PCI=y -CONFIG_VIRTIO_VSOCKETS_COMMON=y CONFIG_VLAN_8021Q=y CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c index 8bf497a9843e..2ea36408816b 100644 --- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c +++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c @@ -131,10 +131,17 @@ static bool is_lru(__u32 map_type) map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } +static bool is_percpu(__u32 map_type) +{ + return map_type == BPF_MAP_TYPE_PERCPU_HASH || + map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; +} + struct upsert_opts { __u32 map_type; int map_fd; __u32 n; + bool retry_for_nomem; }; static int create_small_hash(void) @@ -148,19 +155,38 @@ static int create_small_hash(void) return map_fd; } +static bool retry_for_nomem_fn(int err) +{ + return err == ENOMEM; +} + static void *patch_map_thread(void *arg) { + /* 8KB is enough for 1024 CPUs. And it is shared between N_THREADS. */ + static __u8 blob[8 << 10]; struct upsert_opts *opts = arg; + void *val_ptr; int val; int ret; int i; for (i = 0; i < opts->n; i++) { - if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) + if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { val = create_small_hash(); - else + val_ptr = &val; + } else if (is_percpu(opts->map_type)) { + val_ptr = blob; + } else { val = rand(); - ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0); + val_ptr = &val; + } + + /* 2 seconds may be enough ? */ + if (opts->retry_for_nomem) + ret = map_update_retriable(opts->map_fd, &i, val_ptr, 0, + 40, retry_for_nomem_fn); + else + ret = bpf_map_update_elem(opts->map_fd, &i, val_ptr, 0); CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno)); if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) @@ -281,6 +307,13 @@ static void __test(int map_fd) else opts.n /= 2; + /* per-cpu bpf memory allocator may not be able to allocate per-cpu + * pointer successfully and it can not refill free llist timely, and + * bpf_map_update_elem() will return -ENOMEM. so just retry to mitigate + * the problem temporarily. + */ + opts.retry_for_nomem = is_percpu(opts.map_type) && (info.map_flags & BPF_F_NO_PREALLOC); + /* * Upsert keys [0, n) under some competition: with random values from * N_THREADS threads. Check values, then delete all elements and check diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 465c1c3a3d3c..4ebd0da898f5 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -40,7 +40,7 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1", "ctx(off=0,imm=0)"}, + {0, "R1", "ctx()"}, {0, "R10", "fp0"}, {0, "R3_w", "2"}, {1, "R3_w", "4"}, @@ -68,7 +68,7 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1", "ctx(off=0,imm=0)"}, + {0, "R1", "ctx()"}, {0, "R10", "fp0"}, {0, "R3_w", "1"}, {1, "R3_w", "2"}, @@ -97,7 +97,7 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1", "ctx(off=0,imm=0)"}, + {0, "R1", "ctx()"}, {0, "R10", "fp0"}, {0, "R3_w", "4"}, {1, "R3_w", "8"}, @@ -119,7 +119,7 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1", "ctx(off=0,imm=0)"}, + {0, "R1", "ctx()"}, {0, "R10", "fp0"}, {0, "R3_w", "7"}, {1, "R3_w", "7"}, @@ -162,13 +162,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R0_w", "pkt(off=8,r=8,imm=0)"}, + {6, "R0_w", "pkt(off=8,r=8)"}, {6, "R3_w", "var_off=(0x0; 0xff)"}, {7, "R3_w", "var_off=(0x0; 0x1fe)"}, {8, "R3_w", "var_off=(0x0; 0x3fc)"}, {9, "R3_w", "var_off=(0x0; 0x7f8)"}, {10, "R3_w", "var_off=(0x0; 0xff0)"}, - {12, "R3_w", "pkt_end(off=0,imm=0)"}, + {12, "R3_w", "pkt_end()"}, {17, "R4_w", "var_off=(0x0; 0xff)"}, {18, "R4_w", "var_off=(0x0; 0x1fe0)"}, {19, "R4_w", "var_off=(0x0; 0xff0)"}, @@ -235,11 +235,11 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {2, "R5_w", "pkt(off=0,r=0,imm=0)"}, - {4, "R5_w", "pkt(off=14,r=0,imm=0)"}, - {5, "R4_w", "pkt(off=14,r=0,imm=0)"}, - {9, "R2", "pkt(off=0,r=18,imm=0)"}, - {10, "R5", "pkt(off=14,r=18,imm=0)"}, + {2, "R5_w", "pkt(r=0)"}, + {4, "R5_w", "pkt(off=14,r=0)"}, + {5, "R4_w", "pkt(off=14,r=0)"}, + {9, "R2", "pkt(r=18)"}, + {10, "R5", "pkt(off=14,r=18)"}, {10, "R4_w", "var_off=(0x0; 0xff)"}, {13, "R4_w", "var_off=(0x0; 0xffff)"}, {14, "R4_w", "var_off=(0x0; 0xffff)"}, @@ -299,7 +299,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(off=0,r=8,imm=0)"}, + {6, "R2_w", "pkt(r=8)"}, {7, "R6_w", "var_off=(0x0; 0x3fc)"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. @@ -337,7 +337,7 @@ static struct bpf_align_test tests[] = { /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {26, "R5_w", "pkt(off=14,r=8,"}, + {26, "R5_w", "pkt(off=14,r=8)"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). See comment for insn #18 * for R4 = R5 trick. @@ -397,7 +397,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(off=0,r=8,imm=0)"}, + {6, "R2_w", "pkt(r=8)"}, {7, "R6_w", "var_off=(0x0; 0x3fc)"}, /* Adding 14 makes R6 be (4n+2) */ {8, "R6_w", "var_off=(0x2; 0x7fc)"}, @@ -459,7 +459,7 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {3, "R5_w", "pkt_end(off=0,imm=0)"}, + {3, "R5_w", "pkt_end()"}, /* (ptr - ptr) << 2 == unknown, (4n) */ {5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because @@ -513,7 +513,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(off=0,r=8,imm=0)"}, + {6, "R2_w", "pkt(r=8)"}, {8, "R6_w", "var_off=(0x0; 0x3fc)"}, /* Adding 14 makes R6 be (4n+2) */ {9, "R6_w", "var_off=(0x2; 0x7fc)"}, @@ -566,7 +566,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(off=0,r=8,imm=0)"}, + {6, "R2_w", "pkt(r=8)"}, {9, "R6_w", "var_off=(0x0; 0x3c)"}, /* Adding 14 makes R6 be (4n+2) */ {10, "R6_w", "var_off=(0x2; 0x7c)"}, @@ -659,14 +659,14 @@ static int do_test_single(struct bpf_align_test *test) /* Check the next line as well in case the previous line * did not have a corresponding bpf insn. Example: * func#0 @0 - * 0: R1=ctx(off=0,imm=0) R10=fp0 + * 0: R1=ctx() R10=fp0 * 0: (b7) r3 = 2 ; R3_w=2 * * Sometimes it's actually two lines below, e.g. when * searching for "6: R3_w=scalar(umax=255,var_off=(0x0; 0xff))": - * from 4 to 6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0 - * 6: R0_w=pkt(off=8,r=8,imm=0) R1=ctx(off=0,imm=0) R2_w=pkt(off=0,r=8,imm=0) R3_w=pkt_end(off=0,imm=0) R10=fp0 - * 6: (71) r3 = *(u8 *)(r2 +0) ; R2_w=pkt(off=0,r=8,imm=0) R3_w=scalar(umax=255,var_off=(0x0; 0xff)) + * from 4 to 6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0 + * 6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0 + * 6: (71) r3 = *(u8 *)(r2 +0) ; R2_w=pkt(r=8) R3_w=scalar(umax=255,var_off=(0x0; 0xff)) */ while (!(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) { cur_line = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index a1766a298bb7..f7cd129cb82b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -9,8 +9,6 @@ #include "cap_helpers.h" #include "bind_perm.skel.h" -static int duration; - static int create_netns(void) { if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) @@ -27,7 +25,7 @@ void try_bind(int family, int port, int expected_errno) int fd = -1; fd = socket(family, SOCK_STREAM, 0); - if (CHECK(fd < 0, "fd", "errno %d", errno)) + if (!ASSERT_GE(fd, 0, "socket")) goto close_socket; if (family == AF_INET) { @@ -60,7 +58,7 @@ void test_bind_perm(void) return; cgroup_fd = test__join_cgroup("/bind_perm"); - if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) + if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; skel = bind_perm__open_and_load(); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index e3498f607b49..618af9dfae9b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -34,8 +34,6 @@ #include "bpf_iter_ksym.skel.h" #include "bpf_iter_sockmap.skel.h" -static int duration; - static void test_btf_id_or_null(void) { struct bpf_iter_test_kern3 *skel; @@ -64,7 +62,7 @@ static void do_dummy_read_opts(struct bpf_program *prog, struct bpf_iter_attach_ /* not check contents, but ensure read() ends without error */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)); + ASSERT_GE(len, 0, "read"); close(iter_fd); @@ -334,6 +332,8 @@ static void test_task_stack(void) do_dummy_read(skel->progs.dump_task_stack); do_dummy_read(skel->progs.get_task_user_stacks); + ASSERT_EQ(skel->bss->num_user_stacks, 1, "num_user_stacks"); + bpf_iter_task_stack__destroy(skel); } @@ -413,7 +413,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel) goto free_link; } - if (CHECK(err < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(err, 0, "read")) goto free_link; ASSERT_HAS_SUBSTR(taskbuf, "(struct task_struct)", @@ -526,11 +526,11 @@ static int do_read_with_fd(int iter_fd, const char *expected, start = 0; while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) { start += len; - if (CHECK(start >= 16, "read", "read len %d\n", len)) + if (!ASSERT_LT(start, 16, "read")) return -1; read_buf_len = read_one_char ? 1 : 16 - start; } - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) return -1; if (!ASSERT_STREQ(buf, expected, "read")) @@ -571,8 +571,7 @@ static int do_read(const char *path, const char *expected) int err, iter_fd; iter_fd = open(path, O_RDONLY); - if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n", - path, strerror(errno))) + if (!ASSERT_GE(iter_fd, 0, "open")) return -1; err = do_read_with_fd(iter_fd, expected, false); @@ -600,7 +599,7 @@ static void test_file_iter(void) unlink(path); err = bpf_link__pin(link, path); - if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err)) + if (!ASSERT_OK(err, "pin_iter")) goto free_link; err = do_read(path, "abcd"); @@ -651,12 +650,10 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) * overflow and needs restart. */ map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); - if (CHECK(map1_fd < 0, "bpf_map_create", - "map_creation failed: %s\n", strerror(errno))) + if (!ASSERT_GE(map1_fd, 0, "bpf_map_create")) goto out; map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); - if (CHECK(map2_fd < 0, "bpf_map_create", - "map_creation failed: %s\n", strerror(errno))) + if (!ASSERT_GE(map2_fd, 0, "bpf_map_create")) goto free_map1; /* bpf_seq_printf kernel buffer is 8 pages, so one map @@ -685,14 +682,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) /* setup filtering map_id in bpf program */ map_info_len = sizeof(map_info); err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len); - if (CHECK(err, "get_map_info", "get map info failed: %s\n", - strerror(errno))) + if (!ASSERT_OK(err, "get_map_info")) goto free_map2; skel->bss->map1_id = map_info.id; err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len); - if (CHECK(err, "get_map_info", "get map info failed: %s\n", - strerror(errno))) + if (!ASSERT_OK(err, "get_map_info")) goto free_map2; skel->bss->map2_id = map_info.id; @@ -705,7 +700,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) goto free_link; buf = malloc(expected_read_len); - if (!buf) + if (!ASSERT_OK_PTR(buf, "malloc")) goto close_iter; /* do read */ @@ -714,16 +709,14 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) while ((len = read(iter_fd, buf, expected_read_len)) > 0) total_read_len += len; - CHECK(len != -1 || errno != E2BIG, "read", - "expected ret -1, errno E2BIG, but get ret %d, error %s\n", - len, strerror(errno)); + ASSERT_EQ(len, -1, "read"); + ASSERT_EQ(errno, E2BIG, "read"); goto free_buf; } else if (!ret1) { while ((len = read(iter_fd, buf, expected_read_len)) > 0) total_read_len += len; - if (CHECK(len < 0, "read", "read failed: %s\n", - strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto free_buf; } else { do { @@ -732,8 +725,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) total_read_len += len; } while (len > 0 || len == -EAGAIN); - if (CHECK(len < 0, "read", "read failed: %s\n", - strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto free_buf; } @@ -836,7 +828,7 @@ static void test_bpf_hash_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -878,6 +870,8 @@ static void test_bpf_percpu_hash_map(void) skel->rodata->num_cpus = bpf_num_possible_cpus(); val = malloc(8 * bpf_num_possible_cpus()); + if (!ASSERT_OK_PTR(val, "malloc")) + goto out; err = bpf_iter_bpf_percpu_hash_map__load(skel); if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_hash_map__load")) @@ -917,7 +911,7 @@ static void test_bpf_percpu_hash_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -983,17 +977,14 @@ static void test_bpf_array_map(void) start = 0; while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0) start += len; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ res_first_key = *(__u32 *)buf; res_first_val = *(__u64 *)(buf + sizeof(__u32)); - if (CHECK(res_first_key != 0 || res_first_val != first_val, - "bpf_seq_write", - "seq_write failure: first key %u vs expected 0, " - " first value %llu vs expected %llu\n", - res_first_key, res_first_val, first_val)) + if (!ASSERT_EQ(res_first_key, 0, "bpf_seq_write") || + !ASSERT_EQ(res_first_val, first_val, "bpf_seq_write")) goto close_iter; if (!ASSERT_EQ(skel->bss->key_sum, expected_key, "key_sum")) @@ -1057,6 +1048,8 @@ static void test_bpf_percpu_array_map(void) skel->rodata->num_cpus = bpf_num_possible_cpus(); val = malloc(8 * bpf_num_possible_cpus()); + if (!ASSERT_OK_PTR(val, "malloc")) + goto out; err = bpf_iter_bpf_percpu_array_map__load(skel); if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_array_map__load")) @@ -1092,7 +1085,7 @@ static void test_bpf_percpu_array_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -1131,6 +1124,7 @@ static void test_bpf_sk_storage_delete(void) sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) goto out; + err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST); if (!ASSERT_OK(err, "map_update")) goto out; @@ -1151,14 +1145,19 @@ static void test_bpf_sk_storage_delete(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem", - "map value wasn't deleted (err=%d, errno=%d)\n", err, errno)) - goto close_iter; + + /* Note: The following assertions serve to ensure + * the value was deleted. It does so by asserting + * that bpf_map_lookup_elem has failed. This might + * seem counterintuitive at first. + */ + ASSERT_ERR(err, "bpf_map_lookup_elem"); + ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem"); close_iter: close(iter_fd); @@ -1203,17 +1202,15 @@ static void test_bpf_sk_storage_get(void) do_dummy_read(skel->progs.fill_socket_owner); err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - if (CHECK(err || val != getpid(), "bpf_map_lookup_elem", - "map value wasn't set correctly (expected %d, got %d, err=%d)\n", - getpid(), val, err)) + if (!ASSERT_OK(err, "bpf_map_lookup_elem") || + !ASSERT_EQ(val, getpid(), "bpf_map_lookup_elem")) goto close_socket; do_dummy_read(skel->progs.negate_socket_local_storage); err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - CHECK(err || val != -getpid(), "bpf_map_lookup_elem", - "map value wasn't set correctly (expected %d, got %d, err=%d)\n", - -getpid(), val, err); + ASSERT_OK(err, "bpf_map_lookup_elem"); + ASSERT_EQ(val, -getpid(), "bpf_map_lookup_elem"); close_socket: close(sock_fd); @@ -1290,7 +1287,7 @@ static void test_bpf_sk_storage_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index 675b90b15280..f09d6ac2ef09 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -25,7 +25,7 @@ void serial_test_bpf_obj_id(void) */ __u32 map_ids[nr_iters + 1]; char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128]; - __u32 i, next_id, info_len, nr_id_found, duration = 0; + __u32 i, next_id, info_len, nr_id_found; struct timespec real_time_ts, boot_time_ts; int err = 0; __u64 array_value; @@ -33,16 +33,16 @@ void serial_test_bpf_obj_id(void) time_t now, load_time; err = bpf_prog_get_fd_by_id(0); - CHECK(err >= 0 || errno != ENOENT, - "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); + ASSERT_LT(err, 0, "bpf_prog_get_fd_by_id"); + ASSERT_EQ(errno, ENOENT, "bpf_prog_get_fd_by_id"); err = bpf_map_get_fd_by_id(0); - CHECK(err >= 0 || errno != ENOENT, - "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno); + ASSERT_LT(err, 0, "bpf_map_get_fd_by_id"); + ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id"); err = bpf_link_get_fd_by_id(0); - CHECK(err >= 0 || errno != ENOENT, - "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno); + ASSERT_LT(err, 0, "bpf_map_get_fd_by_id"); + ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id"); /* Check bpf_map_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); @@ -53,25 +53,26 @@ void serial_test_bpf_obj_id(void) /* test_obj_id.o is a dumb prog. It should never fail * to load. */ - if (CHECK_FAIL(err)) + if (!ASSERT_OK(err, "bpf_prog_test_load")) continue; /* Insert a magic value to the map */ map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); - if (CHECK_FAIL(map_fds[i] < 0)) + if (!ASSERT_GE(map_fds[i], 0, "bpf_find_map")) goto done; + err = bpf_map_update_elem(map_fds[i], &array_key, &array_magic_value, 0); - if (CHECK_FAIL(err)) + if (!ASSERT_OK(err, "bpf_map_update_elem")) goto done; - prog = bpf_object__find_program_by_name(objs[i], - "test_obj_id"); - if (CHECK_FAIL(!prog)) + prog = bpf_object__find_program_by_name(objs[i], "test_obj_id"); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) goto done; + links[i] = bpf_program__attach(prog); err = libbpf_get_error(links[i]); - if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) { + if (!ASSERT_OK(err, "bpf_program__attach")) { links[i] = NULL; goto done; } @@ -81,24 +82,14 @@ void serial_test_bpf_obj_id(void) bzero(&map_infos[i], info_len); err = bpf_map_get_info_by_fd(map_fds[i], &map_infos[i], &info_len); - if (CHECK(err || - map_infos[i].type != BPF_MAP_TYPE_ARRAY || - map_infos[i].key_size != sizeof(__u32) || - map_infos[i].value_size != sizeof(__u64) || - map_infos[i].max_entries != 1 || - map_infos[i].map_flags != 0 || - info_len != sizeof(struct bpf_map_info) || - strcmp((char *)map_infos[i].name, expected_map_name), - "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", - err, errno, - map_infos[i].type, BPF_MAP_TYPE_ARRAY, - info_len, sizeof(struct bpf_map_info), - map_infos[i].key_size, - map_infos[i].value_size, - map_infos[i].max_entries, - map_infos[i].map_flags, - map_infos[i].name, expected_map_name)) + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd") || + !ASSERT_EQ(map_infos[i].type, BPF_MAP_TYPE_ARRAY, "map_type") || + !ASSERT_EQ(map_infos[i].key_size, sizeof(__u32), "key_size") || + !ASSERT_EQ(map_infos[i].value_size, sizeof(__u64), "value_size") || + !ASSERT_EQ(map_infos[i].max_entries, 1, "max_entries") || + !ASSERT_EQ(map_infos[i].map_flags, 0, "map_flags") || + !ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "map_info_len") || + !ASSERT_STREQ((char *)map_infos[i].name, expected_map_name, "map_name")) goto done; /* Check getting prog info */ @@ -112,48 +103,34 @@ void serial_test_bpf_obj_id(void) prog_infos[i].xlated_prog_len = sizeof(xlated_insns); prog_infos[i].map_ids = ptr_to_u64(map_ids + i); prog_infos[i].nr_map_ids = 2; + err = clock_gettime(CLOCK_REALTIME, &real_time_ts); - if (CHECK_FAIL(err)) + if (!ASSERT_OK(err, "clock_gettime")) goto done; + err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts); - if (CHECK_FAIL(err)) + if (!ASSERT_OK(err, "clock_gettime")) goto done; + err = bpf_prog_get_info_by_fd(prog_fds[i], &prog_infos[i], &info_len); load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + (prog_infos[i].load_time / nsec_per_sec); - if (CHECK(err || - prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT || - info_len != sizeof(struct bpf_prog_info) || - (env.jit_enabled && !prog_infos[i].jited_prog_len) || - (env.jit_enabled && - !memcmp(jited_insns, zeros, sizeof(zeros))) || - !prog_infos[i].xlated_prog_len || - !memcmp(xlated_insns, zeros, sizeof(zeros)) || - load_time < now - 60 || load_time > now + 60 || - prog_infos[i].created_by_uid != my_uid || - prog_infos[i].nr_map_ids != 1 || - *(int *)(long)prog_infos[i].map_ids != map_infos[i].id || - strcmp((char *)prog_infos[i].name, expected_prog_name), - "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%zu) " - "jit_enabled %d jited_prog_len %u xlated_prog_len %u " - "jited_prog %d xlated_prog %d load_time %lu(%lu) " - "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) " - "name %s(%s)\n", - err, errno, i, - prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, - info_len, sizeof(struct bpf_prog_info), - env.jit_enabled, - prog_infos[i].jited_prog_len, - prog_infos[i].xlated_prog_len, - !!memcmp(jited_insns, zeros, sizeof(zeros)), - !!memcmp(xlated_insns, zeros, sizeof(zeros)), - load_time, now, - prog_infos[i].created_by_uid, my_uid, - prog_infos[i].nr_map_ids, 1, - *(int *)(long)prog_infos[i].map_ids, map_infos[i].id, - prog_infos[i].name, expected_prog_name)) + + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") || + !ASSERT_EQ(prog_infos[i].type, BPF_PROG_TYPE_RAW_TRACEPOINT, "prog_type") || + !ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len") || + !ASSERT_FALSE((env.jit_enabled && !prog_infos[i].jited_prog_len), "jited_prog_len") || + !ASSERT_FALSE((env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))), + "jited_insns") || + !ASSERT_NEQ(prog_infos[i].xlated_prog_len, 0, "xlated_prog_len") || + !ASSERT_NEQ(memcmp(xlated_insns, zeros, sizeof(zeros)), 0, "xlated_insns") || + !ASSERT_GE(load_time, (now - 60), "load_time") || + !ASSERT_LE(load_time, (now + 60), "load_time") || + !ASSERT_EQ(prog_infos[i].created_by_uid, my_uid, "created_by_uid") || + !ASSERT_EQ(prog_infos[i].nr_map_ids, 1, "nr_map_ids") || + !ASSERT_EQ(*(int *)(long)prog_infos[i].map_ids, map_infos[i].id, "map_ids") || + !ASSERT_STREQ((char *)prog_infos[i].name, expected_prog_name, "prog_name")) goto done; /* Check getting link info */ @@ -163,25 +140,12 @@ void serial_test_bpf_obj_id(void) link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); err = bpf_link_get_info_by_fd(bpf_link__fd(links[i]), &link_infos[i], &info_len); - if (CHECK(err || - link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || - link_infos[i].prog_id != prog_infos[i].id || - link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) || - strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), - "sys_enter") || - info_len != sizeof(struct bpf_link_info), - "get-link-info(fd)", - "err %d errno %d info_len %u(%zu) type %d(%d) id %d " - "prog_id %d (%d) tp_name %s(%s)\n", - err, errno, - info_len, sizeof(struct bpf_link_info), - link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, - link_infos[i].id, - link_infos[i].prog_id, prog_infos[i].id, - (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), - "sys_enter")) + if (!ASSERT_OK(err, "bpf_link_get_info_by_fd") || + !ASSERT_EQ(link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type") || + !ASSERT_EQ(link_infos[i].prog_id, prog_infos[i].id, "prog_id") || + !ASSERT_EQ(link_infos[i].raw_tracepoint.tp_name, ptr_to_u64(&tp_name), "&tp_name") || + !ASSERT_STREQ(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter", "tp_name")) goto done; - } /* Check bpf_prog_get_next_id() */ @@ -190,7 +154,7 @@ void serial_test_bpf_obj_id(void) while (!bpf_prog_get_next_id(next_id, &next_id)) { struct bpf_prog_info prog_info = {}; __u32 saved_map_id; - int prog_fd; + int prog_fd, cmp_res; info_len = sizeof(prog_info); @@ -198,9 +162,7 @@ void serial_test_bpf_obj_id(void) if (prog_fd < 0 && errno == ENOENT) /* The bpf_prog is in the dead row */ continue; - if (CHECK(prog_fd < 0, "get-prog-fd(next_id)", - "prog_fd %d next_id %d errno %d\n", - prog_fd, next_id, errno)) + if (!ASSERT_GE(prog_fd, 0, "bpf_prog_get_fd_by_id")) break; for (i = 0; i < nr_iters; i++) @@ -218,9 +180,8 @@ void serial_test_bpf_obj_id(void) */ prog_info.nr_map_ids = 1; err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len); - if (CHECK(!err || errno != EFAULT, - "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)", - err, errno, EFAULT)) + if (!ASSERT_ERR(err, "bpf_prog_get_info_by_fd") || + !ASSERT_EQ(errno, EFAULT, "bpf_prog_get_info_by_fd")) break; bzero(&prog_info, sizeof(prog_info)); info_len = sizeof(prog_info); @@ -231,27 +192,22 @@ void serial_test_bpf_obj_id(void) err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len); prog_infos[i].jited_prog_insns = 0; prog_infos[i].xlated_prog_insns = 0; - CHECK(err || info_len != sizeof(struct bpf_prog_info) || - memcmp(&prog_info, &prog_infos[i], info_len) || - *(int *)(long)prog_info.map_ids != saved_map_id, - "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n", - err, errno, info_len, sizeof(struct bpf_prog_info), - memcmp(&prog_info, &prog_infos[i], info_len), - *(int *)(long)prog_info.map_ids, saved_map_id); + cmp_res = memcmp(&prog_info, &prog_infos[i], info_len); + + ASSERT_OK(err, "bpf_prog_get_info_by_fd"); + ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len"); + ASSERT_OK(cmp_res, "memcmp"); + ASSERT_EQ(*(int *)(long)prog_info.map_ids, saved_map_id, "map_id"); close(prog_fd); } - CHECK(nr_id_found != nr_iters, - "check total prog id found by get_next_id", - "nr_id_found %u(%u)\n", - nr_id_found, nr_iters); + ASSERT_EQ(nr_id_found, nr_iters, "prog_nr_id_found"); /* Check bpf_map_get_next_id() */ nr_id_found = 0; next_id = 0; while (!bpf_map_get_next_id(next_id, &next_id)) { struct bpf_map_info map_info = {}; - int map_fd; + int map_fd, cmp_res; info_len = sizeof(map_info); @@ -259,9 +215,7 @@ void serial_test_bpf_obj_id(void) if (map_fd < 0 && errno == ENOENT) /* The bpf_map is in the dead row */ continue; - if (CHECK(map_fd < 0, "get-map-fd(next_id)", - "map_fd %d next_id %u errno %d\n", - map_fd, next_id, errno)) + if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id")) break; for (i = 0; i < nr_iters; i++) @@ -274,25 +228,19 @@ void serial_test_bpf_obj_id(void) nr_id_found++; err = bpf_map_lookup_elem(map_fd, &array_key, &array_value); - if (CHECK_FAIL(err)) + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) goto done; err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len); - CHECK(err || info_len != sizeof(struct bpf_map_info) || - memcmp(&map_info, &map_infos[i], info_len) || - array_value != array_magic_value, - "check get-map-info(next_id->fd)", - "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n", - err, errno, info_len, sizeof(struct bpf_map_info), - memcmp(&map_info, &map_infos[i], info_len), - array_value, array_magic_value); + cmp_res = memcmp(&map_info, &map_infos[i], info_len); + ASSERT_OK(err, "bpf_map_get_info_by_fd"); + ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "info_len"); + ASSERT_OK(cmp_res, "memcmp"); + ASSERT_EQ(array_value, array_magic_value, "array_value"); close(map_fd); } - CHECK(nr_id_found != nr_iters, - "check total map id found by get_next_id", - "nr_id_found %u(%u)\n", - nr_id_found, nr_iters); + ASSERT_EQ(nr_id_found, nr_iters, "map_nr_id_found"); /* Check bpf_link_get_next_id() */ nr_id_found = 0; @@ -308,9 +256,7 @@ void serial_test_bpf_obj_id(void) if (link_fd < 0 && errno == ENOENT) /* The bpf_link is in the dead row */ continue; - if (CHECK(link_fd < 0, "get-link-fd(next_id)", - "link_fd %d next_id %u errno %d\n", - link_fd, next_id, errno)) + if (!ASSERT_GE(link_fd, 0, "bpf_link_get_fd_by_id")) break; for (i = 0; i < nr_iters; i++) @@ -325,17 +271,13 @@ void serial_test_bpf_obj_id(void) err = bpf_link_get_info_by_fd(link_fd, &link_info, &info_len); cmp_res = memcmp(&link_info, &link_infos[i], offsetof(struct bpf_link_info, raw_tracepoint)); - CHECK(err || info_len != sizeof(link_info) || cmp_res, - "check get-link-info(next_id->fd)", - "err %d errno %d info_len %u(%zu) memcmp %d\n", - err, errno, info_len, sizeof(struct bpf_link_info), - cmp_res); + ASSERT_OK(err, "bpf_link_get_info_by_fd"); + ASSERT_EQ(info_len, sizeof(link_info), "info_len"); + ASSERT_OK(cmp_res, "memcmp"); close(link_fd); } - CHECK(nr_id_found != nr_iters, - "check total link id found by get_next_id", - "nr_id_found %u(%u)\n", nr_id_found, nr_iters); + ASSERT_EQ(nr_id_found, nr_iters, "link_nr_id_found"); done: for (i = 0; i < nr_iters; i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 4aabeaa525d4..a88e6e07e4f5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -20,15 +20,14 @@ static const unsigned int total_bytes = 10 * 1024 * 1024; static int expected_stg = 0xeB9F; -static int stop, duration; +static int stop; 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)) + if (!ASSERT_NEQ(err, -1, "setsockopt")) return -1; return 0; @@ -65,8 +64,7 @@ static void *server(void *arg) bytes += nr_sent; } - CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n", - bytes, total_bytes, nr_sent, errno); + ASSERT_EQ(bytes, total_bytes, "send"); done: if (fd >= 0) @@ -92,10 +90,11 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) WRITE_ONCE(stop, 0); lfd = socket(AF_INET6, SOCK_STREAM, 0); - if (CHECK(lfd == -1, "socket", "errno:%d\n", errno)) + if (!ASSERT_NEQ(lfd, -1, "socket")) return; + fd = socket(AF_INET6, SOCK_STREAM, 0); - if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) { + if (!ASSERT_NEQ(fd, -1, "socket")) { close(lfd); return; } @@ -108,26 +107,27 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) 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)) + if (!ASSERT_NEQ(err, -1, "bind")) goto done; + err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen); - if (CHECK(err == -1, "getsockname", "errno:%d\n", errno)) + if (!ASSERT_NEQ(err, -1, "getsockname")) goto done; + err = listen(lfd, 1); - if (CHECK(err == -1, "listen", "errno:%d\n", errno)) + if (!ASSERT_NEQ(err, -1, "listen")) goto done; if (sk_stg_map) { err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd, &expected_stg, BPF_NOEXIST); - if (CHECK(err, "bpf_map_update_elem(sk_stg_map)", - "err:%d errno:%d\n", err, errno)) + if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)")) goto done; } /* connect to server */ err = connect(fd, (struct sockaddr *)&sa6, addrlen); - if (CHECK(err == -1, "connect", "errno:%d\n", errno)) + if (!ASSERT_NEQ(err, -1, "connect")) goto done; if (sk_stg_map) { @@ -135,14 +135,13 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd, &tmp_stg); - if (CHECK(!err || errno != ENOENT, - "bpf_map_lookup_elem(sk_stg_map)", - "err:%d errno:%d\n", err, errno)) + if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") || + !ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)")) goto done; } err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); - if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno)) + if (!ASSERT_OK(err, "pthread_create")) goto done; /* recv total_bytes */ @@ -156,13 +155,12 @@ static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map) bytes += nr_recv; } - CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n", - bytes, total_bytes, nr_recv, errno); + ASSERT_EQ(bytes, total_bytes, "recv"); WRITE_ONCE(stop, 1); pthread_join(srv_thread, &thread_ret); - CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld", - PTR_ERR(thread_ret)); + ASSERT_OK(IS_ERR(thread_ret), "thread_ret"); + done: close(lfd); close(fd); @@ -174,7 +172,7 @@ static void test_cubic(void) struct bpf_link *link; cubic_skel = bpf_cubic__open_and_load(); - if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(cubic_skel, "bpf_cubic__open_and_load")) return; link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic); @@ -197,7 +195,7 @@ static void test_dctcp(void) struct bpf_link *link; dctcp_skel = bpf_dctcp__open_and_load(); - if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(dctcp_skel, "bpf_dctcp__open_and_load")) return; link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp); @@ -207,9 +205,7 @@ static void test_dctcp(void) } do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map); - CHECK(dctcp_skel->bss->stg_result != expected_stg, - "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n", - dctcp_skel->bss->stg_result, expected_stg); + ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result"); bpf_link__destroy(link); bpf_dctcp__destroy(dctcp_skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 731c343897d8..e770912fc1d2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type) } bpf_program__set_type(prog, type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags); err = bpf_object__load(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 92d51f377fe5..8fb4a04fbbc0 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -5265,6 +5265,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind) #endif assert(0); + return 0; } static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c new file mode 100644 index 000000000000..74d6d7546f40 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include <sys/types.h> +#include <unistd.h> +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "test_cgroup1_hierarchy.skel.h" + +static void bpf_cgroup1(struct test_cgroup1_hierarchy *skel) +{ + struct bpf_link *lsm_link, *fentry_link; + int err; + + /* Attach LSM prog first */ + lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run); + if (!ASSERT_OK_PTR(lsm_link, "lsm_attach")) + return; + + /* LSM prog will be triggered when attaching fentry */ + fentry_link = bpf_program__attach_trace(skel->progs.fentry_run); + ASSERT_NULL(fentry_link, "fentry_attach_fail"); + + err = bpf_link__destroy(lsm_link); + ASSERT_OK(err, "destroy_lsm"); +} + +static void bpf_cgroup1_sleepable(struct test_cgroup1_hierarchy *skel) +{ + struct bpf_link *lsm_link, *fentry_link; + int err; + + /* Attach LSM prog first */ + lsm_link = bpf_program__attach_lsm(skel->progs.lsm_s_run); + if (!ASSERT_OK_PTR(lsm_link, "lsm_attach")) + return; + + /* LSM prog will be triggered when attaching fentry */ + fentry_link = bpf_program__attach_trace(skel->progs.fentry_run); + ASSERT_NULL(fentry_link, "fentry_attach_fail"); + + err = bpf_link__destroy(lsm_link); + ASSERT_OK(err, "destroy_lsm"); +} + +static void bpf_cgroup1_invalid_id(struct test_cgroup1_hierarchy *skel) +{ + struct bpf_link *lsm_link, *fentry_link; + int err; + + /* Attach LSM prog first */ + lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run); + if (!ASSERT_OK_PTR(lsm_link, "lsm_attach")) + return; + + /* LSM prog will be triggered when attaching fentry */ + fentry_link = bpf_program__attach_trace(skel->progs.fentry_run); + if (!ASSERT_OK_PTR(fentry_link, "fentry_attach_success")) + goto cleanup; + + err = bpf_link__destroy(fentry_link); + ASSERT_OK(err, "destroy_lsm"); + +cleanup: + err = bpf_link__destroy(lsm_link); + ASSERT_OK(err, "destroy_fentry"); +} + +void test_cgroup1_hierarchy(void) +{ + struct test_cgroup1_hierarchy *skel; + __u64 current_cgid; + int hid, err; + + skel = test_cgroup1_hierarchy__open(); + if (!ASSERT_OK_PTR(skel, "open")) + return; + + skel->bss->target_pid = getpid(); + + err = bpf_program__set_attach_target(skel->progs.fentry_run, 0, "bpf_fentry_test1"); + if (!ASSERT_OK(err, "fentry_set_target")) + goto destroy; + + err = test_cgroup1_hierarchy__load(skel); + if (!ASSERT_OK(err, "load")) + goto destroy; + + /* Setup cgroup1 hierarchy */ + err = setup_classid_environment(); + if (!ASSERT_OK(err, "setup_classid_environment")) + goto destroy; + + err = join_classid(); + if (!ASSERT_OK(err, "join_cgroup1")) + goto cleanup; + + current_cgid = get_classid_cgroup_id(); + if (!ASSERT_GE(current_cgid, 0, "cgroup1 id")) + goto cleanup; + + hid = get_cgroup1_hierarchy_id("net_cls"); + if (!ASSERT_GE(hid, 0, "cgroup1 id")) + goto cleanup; + skel->bss->target_hid = hid; + + if (test__start_subtest("test_cgroup1_hierarchy")) { + skel->bss->target_ancestor_cgid = current_cgid; + bpf_cgroup1(skel); + } + + if (test__start_subtest("test_root_cgid")) { + skel->bss->target_ancestor_cgid = 1; + skel->bss->target_ancestor_level = 0; + bpf_cgroup1(skel); + } + + if (test__start_subtest("test_invalid_level")) { + skel->bss->target_ancestor_cgid = 1; + skel->bss->target_ancestor_level = 1; + bpf_cgroup1_invalid_id(skel); + } + + if (test__start_subtest("test_invalid_cgid")) { + skel->bss->target_ancestor_cgid = 0; + bpf_cgroup1_invalid_id(skel); + } + + if (test__start_subtest("test_invalid_hid")) { + skel->bss->target_ancestor_cgid = 1; + skel->bss->target_ancestor_level = 0; + skel->bss->target_hid = -1; + bpf_cgroup1_invalid_id(skel); + } + + if (test__start_subtest("test_invalid_cgrp_name")) { + skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cl"); + skel->bss->target_ancestor_cgid = current_cgid; + bpf_cgroup1_invalid_id(skel); + } + + if (test__start_subtest("test_invalid_cgrp_name2")) { + skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cls,"); + skel->bss->target_ancestor_cgid = current_cgid; + bpf_cgroup1_invalid_id(skel); + } + + if (test__start_subtest("test_sleepable_prog")) { + skel->bss->target_hid = hid; + skel->bss->target_ancestor_cgid = current_cgid; + bpf_cgroup1_sleepable(skel); + } + +cleanup: + cleanup_classid_environment(); +destroy: + test_cgroup1_hierarchy__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c index 9026b42914d3..addf720428f7 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -71,7 +71,7 @@ void test_cgroup_v1v2(void) } ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only"); setup_classid_environment(); - set_classid(42); + set_classid(); ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2"); cleanup_classid_environment(); close(server_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c index b25b870f87ba..e6e50a394472 100644 --- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c @@ -73,6 +73,37 @@ static void test_local_kptr_stash_unstash(void) local_kptr_stash__destroy(skel); } +static void test_refcount_acquire_without_unstash(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct local_kptr_stash *skel; + int ret; + + skel = local_kptr_stash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash), + &opts); + ASSERT_OK(ret, "refcount_acquire_without_unstash run"); + ASSERT_EQ(opts.retval, 2, "refcount_acquire_without_unstash retval"); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_refcounted_node), &opts); + ASSERT_OK(ret, "stash_refcounted_node run"); + ASSERT_OK(opts.retval, "stash_refcounted_node retval"); + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash), + &opts); + ASSERT_OK(ret, "refcount_acquire_without_unstash (2) run"); + ASSERT_EQ(opts.retval, 42, "refcount_acquire_without_unstash (2) retval"); + + local_kptr_stash__destroy(skel); +} + static void test_local_kptr_stash_fail(void) { RUN_TESTS(local_kptr_stash_fail); @@ -86,6 +117,8 @@ void test_local_kptr_stash(void) test_local_kptr_stash_plain(); if (test__start_subtest("local_kptr_stash_unstash")) test_local_kptr_stash_unstash(); + if (test__start_subtest("refcount_acquire_without_unstash")) + test_refcount_acquire_without_unstash(); if (test__start_subtest("local_kptr_stash_fail")) test_local_kptr_stash_fail(); } diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index fe9a23e65ef4..0f7ea4d7d9f6 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -78,7 +78,7 @@ static void obj_load_log_buf(void) ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"), "libbpf_log_not_empty"); ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty"); - ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), + ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx() R10=fp0"), "good_log_verbose"); ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"), "bad_log_not_empty"); @@ -175,7 +175,7 @@ static void bpf_prog_load_log_buf(void) opts.log_level = 2; fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL", good_prog_insns, good_prog_insn_cnt, &opts); - ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2"); + ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx() R10=fp0"), "good_log_2"); ASSERT_GE(fd, 0, "good_fd2"); if (fd >= 0) close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c new file mode 100644 index 000000000000..0c9abd279e18 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -0,0 +1,2124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#define _GNU_SOURCE +#include <limits.h> +#include <test_progs.h> +#include <linux/filter.h> +#include <linux/bpf.h> + +/* ================================= + * SHORT AND CONSISTENT NUMBER TYPES + * ================================= + */ +#define U64_MAX ((u64)UINT64_MAX) +#define U32_MAX ((u32)UINT_MAX) +#define U16_MAX ((u32)UINT_MAX) +#define S64_MIN ((s64)INT64_MIN) +#define S64_MAX ((s64)INT64_MAX) +#define S32_MIN ((s32)INT_MIN) +#define S32_MAX ((s32)INT_MAX) +#define S16_MIN ((s16)0x80000000) +#define S16_MAX ((s16)0x7fffffff) + +typedef unsigned long long ___u64; +typedef unsigned int ___u32; +typedef long long ___s64; +typedef int ___s32; + +/* avoid conflicts with already defined types in kernel headers */ +#define u64 ___u64 +#define u32 ___u32 +#define s64 ___s64 +#define s32 ___s32 + +/* ================================== + * STRING BUF ABSTRACTION AND HELPERS + * ================================== + */ +struct strbuf { + size_t buf_sz; + int pos; + char buf[0]; +}; + +#define DEFINE_STRBUF(name, N) \ + struct { struct strbuf buf; char data[(N)]; } ___##name; \ + struct strbuf *name = (___##name.buf.buf_sz = (N), ___##name.buf.pos = 0, &___##name.buf) + +__printf(2, 3) +static inline void snappendf(struct strbuf *s, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + s->pos += vsnprintf(s->buf + s->pos, + s->pos < s->buf_sz ? s->buf_sz - s->pos : 0, + fmt, args); + va_end(args); +} + +/* ================================== + * GENERIC NUMBER TYPE AND OPERATIONS + * ================================== + */ +enum num_t { U64, first_t = U64, U32, S64, S32, last_t = S32 }; + +static __always_inline u64 min_t(enum num_t t, u64 x, u64 y) +{ + switch (t) { + case U64: return (u64)x < (u64)y ? (u64)x : (u64)y; + case U32: return (u32)x < (u32)y ? (u32)x : (u32)y; + case S64: return (s64)x < (s64)y ? (s64)x : (s64)y; + case S32: return (s32)x < (s32)y ? (s32)x : (s32)y; + default: printf("min_t!\n"); exit(1); + } +} + +static __always_inline u64 max_t(enum num_t t, u64 x, u64 y) +{ + switch (t) { + case U64: return (u64)x > (u64)y ? (u64)x : (u64)y; + case U32: return (u32)x > (u32)y ? (u32)x : (u32)y; + case S64: return (s64)x > (s64)y ? (s64)x : (s64)y; + case S32: return (s32)x > (s32)y ? (u32)(s32)x : (u32)(s32)y; + default: printf("max_t!\n"); exit(1); + } +} + +static __always_inline u64 cast_t(enum num_t t, u64 x) +{ + switch (t) { + case U64: return (u64)x; + case U32: return (u32)x; + case S64: return (s64)x; + case S32: return (u32)(s32)x; + default: printf("cast_t!\n"); exit(1); + } +} + +static const char *t_str(enum num_t t) +{ + switch (t) { + case U64: return "u64"; + case U32: return "u32"; + case S64: return "s64"; + case S32: return "s32"; + default: printf("t_str!\n"); exit(1); + } +} + +static enum num_t t_is_32(enum num_t t) +{ + switch (t) { + case U64: return false; + case U32: return true; + case S64: return false; + case S32: return true; + default: printf("t_is_32!\n"); exit(1); + } +} + +static enum num_t t_signed(enum num_t t) +{ + switch (t) { + case U64: return S64; + case U32: return S32; + case S64: return S64; + case S32: return S32; + default: printf("t_signed!\n"); exit(1); + } +} + +static enum num_t t_unsigned(enum num_t t) +{ + switch (t) { + case U64: return U64; + case U32: return U32; + case S64: return U64; + case S32: return U32; + default: printf("t_unsigned!\n"); exit(1); + } +} + +#define UNUM_MAX_DECIMAL U16_MAX +#define SNUM_MAX_DECIMAL S16_MAX +#define SNUM_MIN_DECIMAL S16_MIN + +static bool num_is_small(enum num_t t, u64 x) +{ + switch (t) { + case U64: return (u64)x <= UNUM_MAX_DECIMAL; + case U32: return (u32)x <= UNUM_MAX_DECIMAL; + case S64: return (s64)x >= SNUM_MIN_DECIMAL && (s64)x <= SNUM_MAX_DECIMAL; + case S32: return (s32)x >= SNUM_MIN_DECIMAL && (s32)x <= SNUM_MAX_DECIMAL; + default: printf("num_is_small!\n"); exit(1); + } +} + +static void snprintf_num(enum num_t t, struct strbuf *sb, u64 x) +{ + bool is_small = num_is_small(t, x); + + if (is_small) { + switch (t) { + case U64: return snappendf(sb, "%llu", (u64)x); + case U32: return snappendf(sb, "%u", (u32)x); + case S64: return snappendf(sb, "%lld", (s64)x); + case S32: return snappendf(sb, "%d", (s32)x); + default: printf("snprintf_num!\n"); exit(1); + } + } else { + switch (t) { + case U64: + if (x == U64_MAX) + return snappendf(sb, "U64_MAX"); + else if (x >= U64_MAX - 256) + return snappendf(sb, "U64_MAX-%llu", U64_MAX - x); + else + return snappendf(sb, "%#llx", (u64)x); + case U32: + if ((u32)x == U32_MAX) + return snappendf(sb, "U32_MAX"); + else if ((u32)x >= U32_MAX - 256) + return snappendf(sb, "U32_MAX-%u", U32_MAX - (u32)x); + else + return snappendf(sb, "%#x", (u32)x); + case S64: + if ((s64)x == S64_MAX) + return snappendf(sb, "S64_MAX"); + else if ((s64)x >= S64_MAX - 256) + return snappendf(sb, "S64_MAX-%lld", S64_MAX - (s64)x); + else if ((s64)x == S64_MIN) + return snappendf(sb, "S64_MIN"); + else if ((s64)x <= S64_MIN + 256) + return snappendf(sb, "S64_MIN+%lld", (s64)x - S64_MIN); + else + return snappendf(sb, "%#llx", (s64)x); + case S32: + if ((s32)x == S32_MAX) + return snappendf(sb, "S32_MAX"); + else if ((s32)x >= S32_MAX - 256) + return snappendf(sb, "S32_MAX-%d", S32_MAX - (s32)x); + else if ((s32)x == S32_MIN) + return snappendf(sb, "S32_MIN"); + else if ((s32)x <= S32_MIN + 256) + return snappendf(sb, "S32_MIN+%d", (s32)x - S32_MIN); + else + return snappendf(sb, "%#x", (s32)x); + default: printf("snprintf_num!\n"); exit(1); + } + } +} + +/* =================================== + * GENERIC RANGE STRUCT AND OPERATIONS + * =================================== + */ +struct range { + u64 a, b; +}; + +static void snprintf_range(enum num_t t, struct strbuf *sb, struct range x) +{ + if (x.a == x.b) + return snprintf_num(t, sb, x.a); + + snappendf(sb, "["); + snprintf_num(t, sb, x.a); + snappendf(sb, "; "); + snprintf_num(t, sb, x.b); + snappendf(sb, "]"); +} + +static void print_range(enum num_t t, struct range x, const char *sfx) +{ + DEFINE_STRBUF(sb, 128); + + snprintf_range(t, sb, x); + printf("%s%s", sb->buf, sfx); +} + +static const struct range unkn[] = { + [U64] = { 0, U64_MAX }, + [U32] = { 0, U32_MAX }, + [S64] = { (u64)S64_MIN, (u64)S64_MAX }, + [S32] = { (u64)(u32)S32_MIN, (u64)(u32)S32_MAX }, +}; + +static struct range unkn_subreg(enum num_t t) +{ + switch (t) { + case U64: return unkn[U32]; + case U32: return unkn[U32]; + case S64: return unkn[U32]; + case S32: return unkn[S32]; + default: printf("unkn_subreg!\n"); exit(1); + } +} + +static struct range range(enum num_t t, u64 a, u64 b) +{ + switch (t) { + case U64: return (struct range){ (u64)a, (u64)b }; + case U32: return (struct range){ (u32)a, (u32)b }; + case S64: return (struct range){ (s64)a, (s64)b }; + case S32: return (struct range){ (u32)(s32)a, (u32)(s32)b }; + default: printf("range!\n"); exit(1); + } +} + +static __always_inline u32 sign64(u64 x) { return (x >> 63) & 1; } +static __always_inline u32 sign32(u64 x) { return ((u32)x >> 31) & 1; } +static __always_inline u32 upper32(u64 x) { return (u32)(x >> 32); } +static __always_inline u64 swap_low32(u64 x, u32 y) { return (x & 0xffffffff00000000ULL) | y; } + +static bool range_eq(struct range x, struct range y) +{ + return x.a == y.a && x.b == y.b; +} + +static struct range range_cast_to_s32(struct range x) +{ + u64 a = x.a, b = x.b; + + /* if upper 32 bits are constant, lower 32 bits should form a proper + * s32 range to be correct + */ + if (upper32(a) == upper32(b) && (s32)a <= (s32)b) + return range(S32, a, b); + + /* Special case where upper bits form a small sequence of two + * sequential numbers (in 32-bit unsigned space, so 0xffffffff to + * 0x00000000 is also valid), while lower bits form a proper s32 range + * going from negative numbers to positive numbers. + * + * E.g.: [0xfffffff0ffffff00; 0xfffffff100000010]. Iterating + * over full 64-bit numbers range will form a proper [-16, 16] + * ([0xffffff00; 0x00000010]) range in its lower 32 bits. + */ + if (upper32(a) + 1 == upper32(b) && (s32)a < 0 && (s32)b >= 0) + return range(S32, a, b); + + /* otherwise we can't derive much meaningful information */ + return unkn[S32]; +} + +static struct range range_cast_u64(enum num_t to_t, struct range x) +{ + u64 a = (u64)x.a, b = (u64)x.b; + + switch (to_t) { + case U64: + return x; + case U32: + if (upper32(a) != upper32(b)) + return unkn[U32]; + return range(U32, a, b); + case S64: + if (sign64(a) != sign64(b)) + return unkn[S64]; + return range(S64, a, b); + case S32: + return range_cast_to_s32(x); + default: printf("range_cast_u64!\n"); exit(1); + } +} + +static struct range range_cast_s64(enum num_t to_t, struct range x) +{ + s64 a = (s64)x.a, b = (s64)x.b; + + switch (to_t) { + case U64: + /* equivalent to (s64)a <= (s64)b check */ + if (sign64(a) != sign64(b)) + return unkn[U64]; + return range(U64, a, b); + case U32: + if (upper32(a) != upper32(b) || sign32(a) != sign32(b)) + return unkn[U32]; + return range(U32, a, b); + case S64: + return x; + case S32: + return range_cast_to_s32(x); + default: printf("range_cast_s64!\n"); exit(1); + } +} + +static struct range range_cast_u32(enum num_t to_t, struct range x) +{ + u32 a = (u32)x.a, b = (u32)x.b; + + switch (to_t) { + case U64: + case S64: + /* u32 is always a valid zero-extended u64/s64 */ + return range(to_t, a, b); + case U32: + return x; + case S32: + return range_cast_to_s32(range(U32, a, b)); + default: printf("range_cast_u32!\n"); exit(1); + } +} + +static struct range range_cast_s32(enum num_t to_t, struct range x) +{ + s32 a = (s32)x.a, b = (s32)x.b; + + switch (to_t) { + case U64: + case U32: + case S64: + if (sign32(a) != sign32(b)) + return unkn[to_t]; + return range(to_t, a, b); + case S32: + return x; + default: printf("range_cast_s32!\n"); exit(1); + } +} + +/* Reinterpret range in *from_t* domain as a range in *to_t* domain preserving + * all possible information. Worst case, it will be unknown range within + * *to_t* domain, if nothing more specific can be guaranteed during the + * conversion + */ +static struct range range_cast(enum num_t from_t, enum num_t to_t, struct range from) +{ + switch (from_t) { + case U64: return range_cast_u64(to_t, from); + case U32: return range_cast_u32(to_t, from); + case S64: return range_cast_s64(to_t, from); + case S32: return range_cast_s32(to_t, from); + default: printf("range_cast!\n"); exit(1); + } +} + +static bool is_valid_num(enum num_t t, u64 x) +{ + switch (t) { + case U64: return true; + case U32: return upper32(x) == 0; + case S64: return true; + case S32: return upper32(x) == 0; + default: printf("is_valid_num!\n"); exit(1); + } +} + +static bool is_valid_range(enum num_t t, struct range x) +{ + if (!is_valid_num(t, x.a) || !is_valid_num(t, x.b)) + return false; + + switch (t) { + case U64: return (u64)x.a <= (u64)x.b; + case U32: return (u32)x.a <= (u32)x.b; + case S64: return (s64)x.a <= (s64)x.b; + case S32: return (s32)x.a <= (s32)x.b; + default: printf("is_valid_range!\n"); exit(1); + } +} + +static struct range range_improve(enum num_t t, struct range old, struct range new) +{ + return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b)); +} + +static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y) +{ + struct range y_cast; + + y_cast = range_cast(y_t, x_t, y); + + /* the case when new range knowledge, *y*, is a 32-bit subregister + * range, while previous range knowledge, *x*, is a full register + * 64-bit range, needs special treatment to take into account upper 32 + * bits of full register range + */ + if (t_is_32(y_t) && !t_is_32(x_t)) { + struct range x_swap; + + /* some combinations of upper 32 bits and sign bit can lead to + * invalid ranges, in such cases it's easier to detect them + * after cast/swap than try to enumerate all the conditions + * under which transformation and knowledge transfer is valid + */ + x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b)); + if (!is_valid_range(x_t, x_swap)) + return x; + return range_improve(x_t, x, x_swap); + } + + /* otherwise, plain range cast and intersection works */ + return range_improve(x_t, x, y_cast); +} + +/* ======================= + * GENERIC CONDITIONAL OPS + * ======================= + */ +enum op { OP_LT, OP_LE, OP_GT, OP_GE, OP_EQ, OP_NE, first_op = OP_LT, last_op = OP_NE }; + +static enum op complement_op(enum op op) +{ + switch (op) { + case OP_LT: return OP_GE; + case OP_LE: return OP_GT; + case OP_GT: return OP_LE; + case OP_GE: return OP_LT; + case OP_EQ: return OP_NE; + case OP_NE: return OP_EQ; + default: printf("complement_op!\n"); exit(1); + } +} + +static const char *op_str(enum op op) +{ + switch (op) { + case OP_LT: return "<"; + case OP_LE: return "<="; + case OP_GT: return ">"; + case OP_GE: return ">="; + case OP_EQ: return "=="; + case OP_NE: return "!="; + default: printf("op_str!\n"); exit(1); + } +} + +/* Can register with range [x.a, x.b] *EVER* satisfy + * OP (<, <=, >, >=, ==, !=) relation to + * a regsiter with range [y.a, y.b] + * _in *num_t* domain_ + */ +static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op op) +{ +#define range_canbe(T) do { \ + switch (op) { \ + case OP_LT: return (T)x.a < (T)y.b; \ + case OP_LE: return (T)x.a <= (T)y.b; \ + case OP_GT: return (T)x.b > (T)y.a; \ + case OP_GE: return (T)x.b >= (T)y.a; \ + case OP_EQ: return (T)max_t(t, x.a, y.a) <= (T)min_t(t, x.b, y.b); \ + case OP_NE: return !((T)x.a == (T)x.b && (T)y.a == (T)y.b && (T)x.a == (T)y.a); \ + default: printf("range_canbe op %d\n", op); exit(1); \ + } \ +} while (0) + + switch (t) { + case U64: { range_canbe(u64); } + case U32: { range_canbe(u32); } + case S64: { range_canbe(s64); } + case S32: { range_canbe(s32); } + default: printf("range_canbe!\n"); exit(1); + } +#undef range_canbe +} + +/* Does register with range [x.a, x.b] *ALWAYS* satisfy + * OP (<, <=, >, >=, ==, !=) relation to + * a regsiter with range [y.a, y.b] + * _in *num_t* domain_ + */ +static bool range_always_op(enum num_t t, struct range x, struct range y, enum op op) +{ + /* always op <=> ! canbe complement(op) */ + return !range_canbe_op(t, x, y, complement_op(op)); +} + +/* Does register with range [x.a, x.b] *NEVER* satisfy + * OP (<, <=, >, >=, ==, !=) relation to + * a regsiter with range [y.a, y.b] + * _in *num_t* domain_ + */ +static bool range_never_op(enum num_t t, struct range x, struct range y, enum op op) +{ + return !range_canbe_op(t, x, y, op); +} + +/* similar to verifier's is_branch_taken(): + * 1 - always taken; + * 0 - never taken, + * -1 - unsure. + */ +static int range_branch_taken_op(enum num_t t, struct range x, struct range y, enum op op) +{ + if (range_always_op(t, x, y, op)) + return 1; + if (range_never_op(t, x, y, op)) + return 0; + return -1; +} + +/* What would be the new estimates for register x and y ranges assuming truthful + * OP comparison between them. I.e., (x OP y == true) => x <- newx, y <- newy. + * + * We assume "interesting" cases where ranges overlap. Cases where it's + * obvious that (x OP y) is either always true or false should be filtered with + * range_never and range_always checks. + */ +static void range_cond(enum num_t t, struct range x, struct range y, + enum op op, struct range *newx, struct range *newy) +{ + if (!range_canbe_op(t, x, y, op)) { + /* nothing to adjust, can't happen, return original values */ + *newx = x; + *newy = y; + return; + } + switch (op) { + case OP_LT: + *newx = range(t, x.a, min_t(t, x.b, y.b - 1)); + *newy = range(t, max_t(t, x.a + 1, y.a), y.b); + break; + case OP_LE: + *newx = range(t, x.a, min_t(t, x.b, y.b)); + *newy = range(t, max_t(t, x.a, y.a), y.b); + break; + case OP_GT: + *newx = range(t, max_t(t, x.a, y.a + 1), x.b); + *newy = range(t, y.a, min_t(t, x.b - 1, y.b)); + break; + case OP_GE: + *newx = range(t, max_t(t, x.a, y.a), x.b); + *newy = range(t, y.a, min_t(t, x.b, y.b)); + break; + case OP_EQ: + *newx = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b)); + *newy = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b)); + break; + case OP_NE: + /* generic case, can't derive more information */ + *newx = range(t, x.a, x.b); + *newy = range(t, y.a, y.b); + break; + + /* below extended logic is not supported by verifier just yet */ + if (x.a == x.b && x.a == y.a) { + /* X is a constant matching left side of Y */ + *newx = range(t, x.a, x.b); + *newy = range(t, y.a + 1, y.b); + } else if (x.a == x.b && x.b == y.b) { + /* X is a constant matching rigth side of Y */ + *newx = range(t, x.a, x.b); + *newy = range(t, y.a, y.b - 1); + } else if (y.a == y.b && x.a == y.a) { + /* Y is a constant matching left side of X */ + *newx = range(t, x.a + 1, x.b); + *newy = range(t, y.a, y.b); + } else if (y.a == y.b && x.b == y.b) { + /* Y is a constant matching rigth side of X */ + *newx = range(t, x.a, x.b - 1); + *newy = range(t, y.a, y.b); + } else { + /* generic case, can't derive more information */ + *newx = range(t, x.a, x.b); + *newy = range(t, y.a, y.b); + } + + break; + default: + break; + } +} + +/* ======================= + * REGISTER STATE HANDLING + * ======================= + */ +struct reg_state { + struct range r[4]; /* indexed by enum num_t: U64, U32, S64, S32 */ + bool valid; +}; + +static void print_reg_state(struct reg_state *r, const char *sfx) +{ + DEFINE_STRBUF(sb, 512); + enum num_t t; + int cnt = 0; + + if (!r->valid) { + printf("<not found>%s", sfx); + return; + } + + snappendf(sb, "scalar("); + for (t = first_t; t <= last_t; t++) { + snappendf(sb, "%s%s=", cnt++ ? "," : "", t_str(t)); + snprintf_range(t, sb, r->r[t]); + } + snappendf(sb, ")"); + + printf("%s%s", sb->buf, sfx); +} + +static void print_refinement(enum num_t s_t, struct range src, + enum num_t d_t, struct range old, struct range new, + const char *ctx) +{ + printf("REFINING (%s) (%s)SRC=", ctx, t_str(s_t)); + print_range(s_t, src, ""); + printf(" (%s)DST_OLD=", t_str(d_t)); + print_range(d_t, old, ""); + printf(" (%s)DST_NEW=", t_str(d_t)); + print_range(d_t, new, "\n"); +} + +static void reg_state_refine(struct reg_state *r, enum num_t t, struct range x, const char *ctx) +{ + enum num_t d_t, s_t; + struct range old; + bool keep_going = false; + +again: + /* try to derive new knowledge from just learned range x of type t */ + for (d_t = first_t; d_t <= last_t; d_t++) { + old = r->r[d_t]; + r->r[d_t] = range_refine(d_t, r->r[d_t], t, x); + if (!range_eq(r->r[d_t], old)) { + keep_going = true; + if (env.verbosity >= VERBOSE_VERY) + print_refinement(t, x, d_t, old, r->r[d_t], ctx); + } + } + + /* now see if we can derive anything new from updated reg_state's ranges */ + for (s_t = first_t; s_t <= last_t; s_t++) { + for (d_t = first_t; d_t <= last_t; d_t++) { + old = r->r[d_t]; + r->r[d_t] = range_refine(d_t, r->r[d_t], s_t, r->r[s_t]); + if (!range_eq(r->r[d_t], old)) { + keep_going = true; + if (env.verbosity >= VERBOSE_VERY) + print_refinement(s_t, r->r[s_t], d_t, old, r->r[d_t], ctx); + } + } + } + + /* keep refining until we converge */ + if (keep_going) { + keep_going = false; + goto again; + } +} + +static void reg_state_set_const(struct reg_state *rs, enum num_t t, u64 val) +{ + enum num_t tt; + + rs->valid = true; + for (tt = first_t; tt <= last_t; tt++) + rs->r[tt] = tt == t ? range(t, val, val) : unkn[tt]; + + reg_state_refine(rs, t, rs->r[t], "CONST"); +} + +static void reg_state_cond(enum num_t t, struct reg_state *x, struct reg_state *y, enum op op, + struct reg_state *newx, struct reg_state *newy, const char *ctx) +{ + char buf[32]; + enum num_t ts[2]; + struct reg_state xx = *x, yy = *y; + int i, t_cnt; + struct range z1, z2; + + if (op == OP_EQ || op == OP_NE) { + /* OP_EQ and OP_NE are sign-agnostic, so we need to process + * both signed and unsigned domains at the same time + */ + ts[0] = t_unsigned(t); + ts[1] = t_signed(t); + t_cnt = 2; + } else { + ts[0] = t; + t_cnt = 1; + } + + for (i = 0; i < t_cnt; i++) { + t = ts[i]; + z1 = x->r[t]; + z2 = y->r[t]; + + range_cond(t, z1, z2, op, &z1, &z2); + + if (newx) { + snprintf(buf, sizeof(buf), "%s R1", ctx); + reg_state_refine(&xx, t, z1, buf); + } + if (newy) { + snprintf(buf, sizeof(buf), "%s R2", ctx); + reg_state_refine(&yy, t, z2, buf); + } + } + + if (newx) + *newx = xx; + if (newy) + *newy = yy; +} + +static int reg_state_branch_taken_op(enum num_t t, struct reg_state *x, struct reg_state *y, + enum op op) +{ + if (op == OP_EQ || op == OP_NE) { + /* OP_EQ and OP_NE are sign-agnostic */ + enum num_t tu = t_unsigned(t); + enum num_t ts = t_signed(t); + int br_u, br_s, br; + + br_u = range_branch_taken_op(tu, x->r[tu], y->r[tu], op); + br_s = range_branch_taken_op(ts, x->r[ts], y->r[ts], op); + + if (br_u >= 0 && br_s >= 0 && br_u != br_s) + ASSERT_FALSE(true, "branch taken inconsistency!\n"); + + /* if 64-bit ranges are indecisive, use 32-bit subranges to + * eliminate always/never taken branches, if possible + */ + if (br_u == -1 && (t == U64 || t == S64)) { + br = range_branch_taken_op(U32, x->r[U32], y->r[U32], op); + /* we can only reject for OP_EQ, never take branch + * based on lower 32 bits + */ + if (op == OP_EQ && br == 0) + return 0; + /* for OP_NEQ we can be conclusive only if lower 32 bits + * differ and thus inequality branch is always taken + */ + if (op == OP_NE && br == 1) + return 1; + + br = range_branch_taken_op(S32, x->r[S32], y->r[S32], op); + if (op == OP_EQ && br == 0) + return 0; + if (op == OP_NE && br == 1) + return 1; + } + + return br_u >= 0 ? br_u : br_s; + } + return range_branch_taken_op(t, x->r[t], y->r[t], op); +} + +/* ===================================== + * BPF PROGS GENERATION AND VERIFICATION + * ===================================== + */ +struct case_spec { + /* whether to init full register (r1) or sub-register (w1) */ + bool init_subregs; + /* whether to establish initial value range on full register (r1) or + * sub-register (w1) + */ + bool setup_subregs; + /* whether to establish initial value range using signed or unsigned + * comparisons (i.e., initialize umin/umax or smin/smax directly) + */ + bool setup_signed; + /* whether to perform comparison on full registers or sub-registers */ + bool compare_subregs; + /* whether to perform comparison using signed or unsigned operations */ + bool compare_signed; +}; + +/* Generate test BPF program based on provided test ranges, operation, and + * specifications about register bitness and signedness. + */ +static int load_range_cmp_prog(struct range x, struct range y, enum op op, + int branch_taken, struct case_spec spec, + char *log_buf, size_t log_sz, + int *false_pos, int *true_pos) +{ +#define emit(insn) ({ \ + struct bpf_insn __insns[] = { insn }; \ + int __i; \ + for (__i = 0; __i < ARRAY_SIZE(__insns); __i++) \ + insns[cur_pos + __i] = __insns[__i]; \ + cur_pos += __i; \ +}) +#define JMP_TO(target) (target - cur_pos - 1) + int cur_pos = 0, exit_pos, fd, op_code; + struct bpf_insn insns[64]; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_level = 2, + .log_buf = log_buf, + .log_size = log_sz, + .prog_flags = BPF_F_TEST_REG_INVARIANTS, + ); + + /* ; skip exit block below + * goto +2; + */ + emit(BPF_JMP_A(2)); + exit_pos = cur_pos; + /* ; exit block for all the preparatory conditionals + * out: + * r0 = 0; + * exit; + */ + emit(BPF_MOV64_IMM(BPF_REG_0, 0)); + emit(BPF_EXIT_INSN()); + /* + * ; assign r6/w6 and r7/w7 unpredictable u64/u32 value + * call bpf_get_current_pid_tgid; + * r6 = r0; | w6 = w0; + * call bpf_get_current_pid_tgid; + * r7 = r0; | w7 = w0; + */ + emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid)); + if (spec.init_subregs) + emit(BPF_MOV32_REG(BPF_REG_6, BPF_REG_0)); + else + emit(BPF_MOV64_REG(BPF_REG_6, BPF_REG_0)); + emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid)); + if (spec.init_subregs) + emit(BPF_MOV32_REG(BPF_REG_7, BPF_REG_0)); + else + emit(BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + /* ; setup initial r6/w6 possible value range ([x.a, x.b]) + * r1 = %[x.a] ll; | w1 = %[x.a]; + * r2 = %[x.b] ll; | w2 = %[x.b]; + * if r6 < r1 goto out; | if w6 < w1 goto out; + * if r6 > r2 goto out; | if w6 > w2 goto out; + */ + if (spec.setup_subregs) { + emit(BPF_MOV32_IMM(BPF_REG_1, (s32)x.a)); + emit(BPF_MOV32_IMM(BPF_REG_2, (s32)x.b)); + emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT, + BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos))); + emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT, + BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos))); + } else { + emit(BPF_LD_IMM64(BPF_REG_1, x.a)); + emit(BPF_LD_IMM64(BPF_REG_2, x.b)); + emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT, + BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos))); + emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT, + BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos))); + } + /* ; setup initial r7/w7 possible value range ([y.a, y.b]) + * r1 = %[y.a] ll; | w1 = %[y.a]; + * r2 = %[y.b] ll; | w2 = %[y.b]; + * if r7 < r1 goto out; | if w7 < w1 goto out; + * if r7 > r2 goto out; | if w7 > w2 goto out; + */ + if (spec.setup_subregs) { + emit(BPF_MOV32_IMM(BPF_REG_1, (s32)y.a)); + emit(BPF_MOV32_IMM(BPF_REG_2, (s32)y.b)); + emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT, + BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos))); + emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT, + BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos))); + } else { + emit(BPF_LD_IMM64(BPF_REG_1, y.a)); + emit(BPF_LD_IMM64(BPF_REG_2, y.b)); + emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT, + BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos))); + emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT, + BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos))); + } + /* ; range test instruction + * if r6 <op> r7 goto +3; | if w6 <op> w7 goto +3; + */ + switch (op) { + case OP_LT: op_code = spec.compare_signed ? BPF_JSLT : BPF_JLT; break; + case OP_LE: op_code = spec.compare_signed ? BPF_JSLE : BPF_JLE; break; + case OP_GT: op_code = spec.compare_signed ? BPF_JSGT : BPF_JGT; break; + case OP_GE: op_code = spec.compare_signed ? BPF_JSGE : BPF_JGE; break; + case OP_EQ: op_code = BPF_JEQ; break; + case OP_NE: op_code = BPF_JNE; break; + default: + printf("unrecognized op %d\n", op); + return -ENOTSUP; + } + /* ; BEFORE conditional, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably + * ; this is used for debugging, as verifier doesn't always print + * ; registers states as of condition jump instruction (e.g., when + * ; precision marking happens) + * r0 = r6; | w0 = w6; + * r0 = r7; | w0 = w7; + */ + if (spec.compare_subregs) { + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7)); + } else { + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + } + if (spec.compare_subregs) + emit(BPF_JMP32_REG(op_code, BPF_REG_6, BPF_REG_7, 3)); + else + emit(BPF_JMP_REG(op_code, BPF_REG_6, BPF_REG_7, 3)); + /* ; FALSE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably + * r0 = r6; | w0 = w6; + * r0 = r7; | w0 = w7; + * exit; + */ + *false_pos = cur_pos; + if (spec.compare_subregs) { + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7)); + } else { + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + } + if (branch_taken == 1) /* false branch is never taken */ + emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */ + else + emit(BPF_EXIT_INSN()); + /* ; TRUE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably + * r0 = r6; | w0 = w6; + * r0 = r7; | w0 = w7; + * exit; + */ + *true_pos = cur_pos; + if (spec.compare_subregs) { + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7)); + } else { + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6)); + emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + } + if (branch_taken == 0) /* true branch is never taken */ + emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */ + emit(BPF_EXIT_INSN()); /* last instruction has to be exit */ + + fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "reg_bounds_test", + "GPL", insns, cur_pos, &opts); + if (fd < 0) + return fd; + + close(fd); + return 0; +#undef emit +#undef JMP_TO +} + +#define str_has_pfx(str, pfx) (strncmp(str, pfx, strlen(pfx)) == 0) + +/* Parse register state from verifier log. + * `s` should point to the start of "Rx = ..." substring in the verifier log. + */ +static int parse_reg_state(const char *s, struct reg_state *reg) +{ + /* There are two generic forms for SCALAR register: + * - known constant: R6_rwD=P%lld + * - range: R6_rwD=scalar(id=1,...), where "..." is a comma-separated + * list of optional range specifiers: + * - umin=%llu, if missing, assumed 0; + * - umax=%llu, if missing, assumed U64_MAX; + * - smin=%lld, if missing, assumed S64_MIN; + * - smax=%lld, if missing, assummed S64_MAX; + * - umin32=%d, if missing, assumed 0; + * - umax32=%d, if missing, assumed U32_MAX; + * - smin32=%d, if missing, assumed S32_MIN; + * - smax32=%d, if missing, assummed S32_MAX; + * - var_off=(%#llx; %#llx), tnum part, we don't care about it. + * + * If some of the values are equal, they will be grouped (but min/max + * are not mixed together, and similarly negative values are not + * grouped with non-negative ones). E.g.: + * + * R6_w=Pscalar(smin=smin32=0, smax=umax=umax32=1000) + * + * _rwD part is optional (and any of the letters can be missing). + * P (precision mark) is optional as well. + * + * Anything inside scalar() is optional, including id, of course. + */ + struct { + const char *pfx; + u64 *dst, def; + bool is_32, is_set; + } *f, fields[8] = { + {"smin=", ®->r[S64].a, S64_MIN}, + {"smax=", ®->r[S64].b, S64_MAX}, + {"umin=", ®->r[U64].a, 0}, + {"umax=", ®->r[U64].b, U64_MAX}, + {"smin32=", ®->r[S32].a, (u32)S32_MIN, true}, + {"smax32=", ®->r[S32].b, (u32)S32_MAX, true}, + {"umin32=", ®->r[U32].a, 0, true}, + {"umax32=", ®->r[U32].b, U32_MAX, true}, + }; + const char *p; + int i; + + p = strchr(s, '='); + if (!p) + return -EINVAL; + p++; + if (*p == 'P') + p++; + + if (!str_has_pfx(p, "scalar(")) { + long long sval; + enum num_t t; + + if (p[0] == '0' && p[1] == 'x') { + if (sscanf(p, "%llx", &sval) != 1) + return -EINVAL; + } else { + if (sscanf(p, "%lld", &sval) != 1) + return -EINVAL; + } + + reg->valid = true; + for (t = first_t; t <= last_t; t++) { + reg->r[t] = range(t, sval, sval); + } + return 0; + } + + p += sizeof("scalar"); + while (p) { + int midxs[ARRAY_SIZE(fields)], mcnt = 0; + u64 val; + + for (i = 0; i < ARRAY_SIZE(fields); i++) { + f = &fields[i]; + if (!str_has_pfx(p, f->pfx)) + continue; + midxs[mcnt++] = i; + p += strlen(f->pfx); + } + + if (mcnt) { + /* populate all matched fields */ + if (p[0] == '0' && p[1] == 'x') { + if (sscanf(p, "%llx", &val) != 1) + return -EINVAL; + } else { + if (sscanf(p, "%lld", &val) != 1) + return -EINVAL; + } + + for (i = 0; i < mcnt; i++) { + f = &fields[midxs[i]]; + f->is_set = true; + *f->dst = f->is_32 ? (u64)(u32)val : val; + } + } else if (str_has_pfx(p, "var_off")) { + /* skip "var_off=(0x0; 0x3f)" part completely */ + p = strchr(p, ')'); + if (!p) + return -EINVAL; + p++; + } + + p = strpbrk(p, ",)"); + if (*p == ')') + break; + if (p) + p++; + } + + reg->valid = true; + + for (i = 0; i < ARRAY_SIZE(fields); i++) { + f = &fields[i]; + if (!f->is_set) + *f->dst = f->def; + } + + return 0; +} + + +/* Parse all register states (TRUE/FALSE branches and DST/SRC registers) + * out of the verifier log for a corresponding test case BPF program. + */ +static int parse_range_cmp_log(const char *log_buf, struct case_spec spec, + int false_pos, int true_pos, + struct reg_state *false1_reg, struct reg_state *false2_reg, + struct reg_state *true1_reg, struct reg_state *true2_reg) +{ + struct { + int insn_idx; + int reg_idx; + const char *reg_upper; + struct reg_state *state; + } specs[] = { + {false_pos, 6, "R6=", false1_reg}, + {false_pos + 1, 7, "R7=", false2_reg}, + {true_pos, 6, "R6=", true1_reg}, + {true_pos + 1, 7, "R7=", true2_reg}, + }; + char buf[32]; + const char *p = log_buf, *q; + int i, err; + + for (i = 0; i < 4; i++) { + sprintf(buf, "%d: (%s) %s = %s%d", specs[i].insn_idx, + spec.compare_subregs ? "bc" : "bf", + spec.compare_subregs ? "w0" : "r0", + spec.compare_subregs ? "w" : "r", specs[i].reg_idx); + + q = strstr(p, buf); + if (!q) { + *specs[i].state = (struct reg_state){.valid = false}; + continue; + } + p = strstr(q, specs[i].reg_upper); + if (!p) + return -EINVAL; + err = parse_reg_state(p, specs[i].state); + if (err) + return -EINVAL; + } + return 0; +} + +/* Validate ranges match, and print details if they don't */ +static bool assert_range_eq(enum num_t t, struct range x, struct range y, + const char *ctx1, const char *ctx2) +{ + DEFINE_STRBUF(sb, 512); + + if (range_eq(x, y)) + return true; + + snappendf(sb, "MISMATCH %s.%s: ", ctx1, ctx2); + snprintf_range(t, sb, x); + snappendf(sb, " != "); + snprintf_range(t, sb, y); + + printf("%s\n", sb->buf); + + return false; +} + +/* Validate that register states match, and print details if they don't */ +static bool assert_reg_state_eq(struct reg_state *r, struct reg_state *e, const char *ctx) +{ + bool ok = true; + enum num_t t; + + if (r->valid != e->valid) { + printf("MISMATCH %s: actual %s != expected %s\n", ctx, + r->valid ? "<valid>" : "<invalid>", + e->valid ? "<valid>" : "<invalid>"); + return false; + } + + if (!r->valid) + return true; + + for (t = first_t; t <= last_t; t++) { + if (!assert_range_eq(t, r->r[t], e->r[t], ctx, t_str(t))) + ok = false; + } + + return ok; +} + +/* Printf verifier log, filtering out irrelevant noise */ +static void print_verifier_log(const char *buf) +{ + const char *p; + + while (buf[0]) { + p = strchrnul(buf, '\n'); + + /* filter out irrelevant precision backtracking logs */ + if (str_has_pfx(buf, "mark_precise: ")) + goto skip_line; + + printf("%.*s\n", (int)(p - buf), buf); + +skip_line: + buf = *p == '\0' ? p : p + 1; + } +} + +/* Simulate provided test case purely with our own range-based logic. + * This is done to set up expectations for verifier's branch_taken logic and + * verifier's register states in the verifier log. + */ +static void sim_case(enum num_t init_t, enum num_t cond_t, + struct range x, struct range y, enum op op, + struct reg_state *fr1, struct reg_state *fr2, + struct reg_state *tr1, struct reg_state *tr2, + int *branch_taken) +{ + const u64 A = x.a; + const u64 B = x.b; + const u64 C = y.a; + const u64 D = y.b; + struct reg_state rc; + enum op rev_op = complement_op(op); + enum num_t t; + + fr1->valid = fr2->valid = true; + tr1->valid = tr2->valid = true; + for (t = first_t; t <= last_t; t++) { + /* if we are initializing using 32-bit subregisters, + * full registers get upper 32 bits zeroed automatically + */ + struct range z = t_is_32(init_t) ? unkn_subreg(t) : unkn[t]; + + fr1->r[t] = fr2->r[t] = tr1->r[t] = tr2->r[t] = z; + } + + /* step 1: r1 >= A, r2 >= C */ + reg_state_set_const(&rc, init_t, A); + reg_state_cond(init_t, fr1, &rc, OP_GE, fr1, NULL, "r1>=A"); + reg_state_set_const(&rc, init_t, C); + reg_state_cond(init_t, fr2, &rc, OP_GE, fr2, NULL, "r2>=C"); + *tr1 = *fr1; + *tr2 = *fr2; + if (env.verbosity >= VERBOSE_VERY) { + printf("STEP1 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n"); + printf("STEP1 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n"); + } + + /* step 2: r1 <= B, r2 <= D */ + reg_state_set_const(&rc, init_t, B); + reg_state_cond(init_t, fr1, &rc, OP_LE, fr1, NULL, "r1<=B"); + reg_state_set_const(&rc, init_t, D); + reg_state_cond(init_t, fr2, &rc, OP_LE, fr2, NULL, "r2<=D"); + *tr1 = *fr1; + *tr2 = *fr2; + if (env.verbosity >= VERBOSE_VERY) { + printf("STEP2 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n"); + printf("STEP2 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n"); + } + + /* step 3: r1 <op> r2 */ + *branch_taken = reg_state_branch_taken_op(cond_t, fr1, fr2, op); + fr1->valid = fr2->valid = false; + tr1->valid = tr2->valid = false; + if (*branch_taken != 1) { /* FALSE is possible */ + fr1->valid = fr2->valid = true; + reg_state_cond(cond_t, fr1, fr2, rev_op, fr1, fr2, "FALSE"); + } + if (*branch_taken != 0) { /* TRUE is possible */ + tr1->valid = tr2->valid = true; + reg_state_cond(cond_t, tr1, tr2, op, tr1, tr2, "TRUE"); + } + if (env.verbosity >= VERBOSE_VERY) { + printf("STEP3 (%s) FALSE R1:", t_str(cond_t)); print_reg_state(fr1, "\n"); + printf("STEP3 (%s) FALSE R2:", t_str(cond_t)); print_reg_state(fr2, "\n"); + printf("STEP3 (%s) TRUE R1:", t_str(cond_t)); print_reg_state(tr1, "\n"); + printf("STEP3 (%s) TRUE R2:", t_str(cond_t)); print_reg_state(tr2, "\n"); + } +} + +/* =============================== + * HIGH-LEVEL TEST CASE VALIDATION + * =============================== + */ +static u32 upper_seeds[] = { + 0, + 1, + U32_MAX, + U32_MAX - 1, + S32_MAX, + (u32)S32_MIN, +}; + +static u32 lower_seeds[] = { + 0, + 1, + 2, (u32)-2, + 255, (u32)-255, + UINT_MAX, + UINT_MAX - 1, + INT_MAX, + (u32)INT_MIN, +}; + +struct ctx { + int val_cnt, subval_cnt, range_cnt, subrange_cnt; + u64 uvals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)]; + s64 svals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)]; + u32 usubvals[ARRAY_SIZE(lower_seeds)]; + s32 ssubvals[ARRAY_SIZE(lower_seeds)]; + struct range *uranges, *sranges; + struct range *usubranges, *ssubranges; + int max_failure_cnt, cur_failure_cnt; + int total_case_cnt, case_cnt; + int rand_case_cnt; + unsigned rand_seed; + __u64 start_ns; + char progress_ctx[64]; +}; + +static void cleanup_ctx(struct ctx *ctx) +{ + free(ctx->uranges); + free(ctx->sranges); + free(ctx->usubranges); + free(ctx->ssubranges); +} + +struct subtest_case { + enum num_t init_t; + enum num_t cond_t; + struct range x; + struct range y; + enum op op; +}; + +static void subtest_case_str(struct strbuf *sb, struct subtest_case *t, bool use_op) +{ + snappendf(sb, "(%s)", t_str(t->init_t)); + snprintf_range(t->init_t, sb, t->x); + snappendf(sb, " (%s)%s ", t_str(t->cond_t), use_op ? op_str(t->op) : "<op>"); + snprintf_range(t->init_t, sb, t->y); +} + +/* Generate and validate test case based on specific combination of setup + * register ranges (including their expected num_t domain), and conditional + * operation to perform (including num_t domain in which it has to be + * performed) + */ +static int verify_case_op(enum num_t init_t, enum num_t cond_t, + struct range x, struct range y, enum op op) +{ + char log_buf[256 * 1024]; + size_t log_sz = sizeof(log_buf); + int err, false_pos = 0, true_pos = 0, branch_taken; + struct reg_state fr1, fr2, tr1, tr2; + struct reg_state fe1, fe2, te1, te2; + bool failed = false; + struct case_spec spec = { + .init_subregs = (init_t == U32 || init_t == S32), + .setup_subregs = (init_t == U32 || init_t == S32), + .setup_signed = (init_t == S64 || init_t == S32), + .compare_subregs = (cond_t == U32 || cond_t == S32), + .compare_signed = (cond_t == S64 || cond_t == S32), + }; + + log_buf[0] = '\0'; + + sim_case(init_t, cond_t, x, y, op, &fe1, &fe2, &te1, &te2, &branch_taken); + + err = load_range_cmp_prog(x, y, op, branch_taken, spec, + log_buf, log_sz, &false_pos, &true_pos); + if (err) { + ASSERT_OK(err, "load_range_cmp_prog"); + failed = true; + } + + err = parse_range_cmp_log(log_buf, spec, false_pos, true_pos, + &fr1, &fr2, &tr1, &tr2); + if (err) { + ASSERT_OK(err, "parse_range_cmp_log"); + failed = true; + } + + if (!assert_reg_state_eq(&fr1, &fe1, "false_reg1") || + !assert_reg_state_eq(&fr2, &fe2, "false_reg2") || + !assert_reg_state_eq(&tr1, &te1, "true_reg1") || + !assert_reg_state_eq(&tr2, &te2, "true_reg2")) { + failed = true; + } + + if (failed || env.verbosity >= VERBOSE_NORMAL) { + if (failed || env.verbosity >= VERBOSE_VERY) { + printf("VERIFIER LOG:\n========================\n"); + print_verifier_log(log_buf); + printf("=====================\n"); + } + printf("ACTUAL FALSE1: "); print_reg_state(&fr1, "\n"); + printf("EXPECTED FALSE1: "); print_reg_state(&fe1, "\n"); + printf("ACTUAL FALSE2: "); print_reg_state(&fr2, "\n"); + printf("EXPECTED FALSE2: "); print_reg_state(&fe2, "\n"); + printf("ACTUAL TRUE1: "); print_reg_state(&tr1, "\n"); + printf("EXPECTED TRUE1: "); print_reg_state(&te1, "\n"); + printf("ACTUAL TRUE2: "); print_reg_state(&tr2, "\n"); + printf("EXPECTED TRUE2: "); print_reg_state(&te2, "\n"); + + return failed ? -EINVAL : 0; + } + + return 0; +} + +/* Given setup ranges and number types, go over all supported operations, + * generating individual subtest for each allowed combination + */ +static int verify_case_opt(struct ctx *ctx, enum num_t init_t, enum num_t cond_t, + struct range x, struct range y, bool is_subtest) +{ + DEFINE_STRBUF(sb, 256); + int err; + struct subtest_case sub = { + .init_t = init_t, + .cond_t = cond_t, + .x = x, + .y = y, + }; + + sb->pos = 0; /* reset position in strbuf */ + subtest_case_str(sb, &sub, false /* ignore op */); + if (is_subtest && !test__start_subtest(sb->buf)) + return 0; + + for (sub.op = first_op; sub.op <= last_op; sub.op++) { + sb->pos = 0; /* reset position in strbuf */ + subtest_case_str(sb, &sub, true /* print op */); + + if (env.verbosity >= VERBOSE_NORMAL) /* this speeds up debugging */ + printf("TEST CASE: %s\n", sb->buf); + + err = verify_case_op(init_t, cond_t, x, y, sub.op); + if (err || env.verbosity >= VERBOSE_NORMAL) + ASSERT_OK(err, sb->buf); + if (err) { + ctx->cur_failure_cnt++; + if (ctx->cur_failure_cnt > ctx->max_failure_cnt) + return err; + return 0; /* keep testing other cases */ + } + ctx->case_cnt++; + if ((ctx->case_cnt % 10000) == 0) { + double progress = (ctx->case_cnt + 0.0) / ctx->total_case_cnt; + u64 elapsed_ns = get_time_ns() - ctx->start_ns; + double remain_ns = elapsed_ns / progress * (1 - progress); + + fprintf(env.stderr, "PROGRESS (%s): %d/%d (%.2lf%%), " + "elapsed %llu mins (%.2lf hrs), " + "ETA %.0lf mins (%.2lf hrs)\n", + ctx->progress_ctx, + ctx->case_cnt, ctx->total_case_cnt, 100.0 * progress, + elapsed_ns / 1000000000 / 60, + elapsed_ns / 1000000000.0 / 3600, + remain_ns / 1000000000.0 / 60, + remain_ns / 1000000000.0 / 3600); + } + } + + return 0; +} + +static int verify_case(struct ctx *ctx, enum num_t init_t, enum num_t cond_t, + struct range x, struct range y) +{ + return verify_case_opt(ctx, init_t, cond_t, x, y, true /* is_subtest */); +} + +/* ================================ + * GENERATED CASES FROM SEED VALUES + * ================================ + */ +static int u64_cmp(const void *p1, const void *p2) +{ + u64 x1 = *(const u64 *)p1, x2 = *(const u64 *)p2; + + return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0; +} + +static int u32_cmp(const void *p1, const void *p2) +{ + u32 x1 = *(const u32 *)p1, x2 = *(const u32 *)p2; + + return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0; +} + +static int s64_cmp(const void *p1, const void *p2) +{ + s64 x1 = *(const s64 *)p1, x2 = *(const s64 *)p2; + + return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0; +} + +static int s32_cmp(const void *p1, const void *p2) +{ + s32 x1 = *(const s32 *)p1, x2 = *(const s32 *)p2; + + return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0; +} + +/* Generate valid unique constants from seeds, both signed and unsigned */ +static void gen_vals(struct ctx *ctx) +{ + int i, j, cnt = 0; + + for (i = 0; i < ARRAY_SIZE(upper_seeds); i++) { + for (j = 0; j < ARRAY_SIZE(lower_seeds); j++) { + ctx->uvals[cnt++] = (((u64)upper_seeds[i]) << 32) | lower_seeds[j]; + } + } + + /* sort and compact uvals (i.e., it's `sort | uniq`) */ + qsort(ctx->uvals, cnt, sizeof(*ctx->uvals), u64_cmp); + for (i = 1, j = 0; i < cnt; i++) { + if (ctx->uvals[j] == ctx->uvals[i]) + continue; + j++; + ctx->uvals[j] = ctx->uvals[i]; + } + ctx->val_cnt = j + 1; + + /* we have exactly the same number of s64 values, they are just in + * a different order than u64s, so just sort them differently + */ + for (i = 0; i < ctx->val_cnt; i++) + ctx->svals[i] = ctx->uvals[i]; + qsort(ctx->svals, ctx->val_cnt, sizeof(*ctx->svals), s64_cmp); + + if (env.verbosity >= VERBOSE_SUPER) { + DEFINE_STRBUF(sb1, 256); + DEFINE_STRBUF(sb2, 256); + + for (i = 0; i < ctx->val_cnt; i++) { + sb1->pos = sb2->pos = 0; + snprintf_num(U64, sb1, ctx->uvals[i]); + snprintf_num(S64, sb2, ctx->svals[i]); + printf("SEED #%d: u64=%-20s s64=%-20s\n", i, sb1->buf, sb2->buf); + } + } + + /* 32-bit values are generated separately */ + cnt = 0; + for (i = 0; i < ARRAY_SIZE(lower_seeds); i++) { + ctx->usubvals[cnt++] = lower_seeds[i]; + } + + /* sort and compact usubvals (i.e., it's `sort | uniq`) */ + qsort(ctx->usubvals, cnt, sizeof(*ctx->usubvals), u32_cmp); + for (i = 1, j = 0; i < cnt; i++) { + if (ctx->usubvals[j] == ctx->usubvals[i]) + continue; + j++; + ctx->usubvals[j] = ctx->usubvals[i]; + } + ctx->subval_cnt = j + 1; + + for (i = 0; i < ctx->subval_cnt; i++) + ctx->ssubvals[i] = ctx->usubvals[i]; + qsort(ctx->ssubvals, ctx->subval_cnt, sizeof(*ctx->ssubvals), s32_cmp); + + if (env.verbosity >= VERBOSE_SUPER) { + DEFINE_STRBUF(sb1, 256); + DEFINE_STRBUF(sb2, 256); + + for (i = 0; i < ctx->subval_cnt; i++) { + sb1->pos = sb2->pos = 0; + snprintf_num(U32, sb1, ctx->usubvals[i]); + snprintf_num(S32, sb2, ctx->ssubvals[i]); + printf("SUBSEED #%d: u32=%-10s s32=%-10s\n", i, sb1->buf, sb2->buf); + } + } +} + +/* Generate valid ranges from upper/lower seeds */ +static int gen_ranges(struct ctx *ctx) +{ + int i, j, cnt = 0; + + for (i = 0; i < ctx->val_cnt; i++) { + for (j = i; j < ctx->val_cnt; j++) { + if (env.verbosity >= VERBOSE_SUPER) { + DEFINE_STRBUF(sb1, 256); + DEFINE_STRBUF(sb2, 256); + + sb1->pos = sb2->pos = 0; + snprintf_range(U64, sb1, range(U64, ctx->uvals[i], ctx->uvals[j])); + snprintf_range(S64, sb2, range(S64, ctx->svals[i], ctx->svals[j])); + printf("RANGE #%d: u64=%-40s s64=%-40s\n", cnt, sb1->buf, sb2->buf); + } + cnt++; + } + } + ctx->range_cnt = cnt; + + ctx->uranges = calloc(ctx->range_cnt, sizeof(*ctx->uranges)); + if (!ASSERT_OK_PTR(ctx->uranges, "uranges_calloc")) + return -EINVAL; + ctx->sranges = calloc(ctx->range_cnt, sizeof(*ctx->sranges)); + if (!ASSERT_OK_PTR(ctx->sranges, "sranges_calloc")) + return -EINVAL; + + cnt = 0; + for (i = 0; i < ctx->val_cnt; i++) { + for (j = i; j < ctx->val_cnt; j++) { + ctx->uranges[cnt] = range(U64, ctx->uvals[i], ctx->uvals[j]); + ctx->sranges[cnt] = range(S64, ctx->svals[i], ctx->svals[j]); + cnt++; + } + } + + cnt = 0; + for (i = 0; i < ctx->subval_cnt; i++) { + for (j = i; j < ctx->subval_cnt; j++) { + if (env.verbosity >= VERBOSE_SUPER) { + DEFINE_STRBUF(sb1, 256); + DEFINE_STRBUF(sb2, 256); + + sb1->pos = sb2->pos = 0; + snprintf_range(U32, sb1, range(U32, ctx->usubvals[i], ctx->usubvals[j])); + snprintf_range(S32, sb2, range(S32, ctx->ssubvals[i], ctx->ssubvals[j])); + printf("SUBRANGE #%d: u32=%-20s s32=%-20s\n", cnt, sb1->buf, sb2->buf); + } + cnt++; + } + } + ctx->subrange_cnt = cnt; + + ctx->usubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->usubranges)); + if (!ASSERT_OK_PTR(ctx->usubranges, "usubranges_calloc")) + return -EINVAL; + ctx->ssubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->ssubranges)); + if (!ASSERT_OK_PTR(ctx->ssubranges, "ssubranges_calloc")) + return -EINVAL; + + cnt = 0; + for (i = 0; i < ctx->subval_cnt; i++) { + for (j = i; j < ctx->subval_cnt; j++) { + ctx->usubranges[cnt] = range(U32, ctx->usubvals[i], ctx->usubvals[j]); + ctx->ssubranges[cnt] = range(S32, ctx->ssubvals[i], ctx->ssubvals[j]); + cnt++; + } + } + + return 0; +} + +static int parse_env_vars(struct ctx *ctx) +{ + const char *s; + + if ((s = getenv("REG_BOUNDS_MAX_FAILURE_CNT"))) { + errno = 0; + ctx->max_failure_cnt = strtol(s, NULL, 10); + if (errno || ctx->max_failure_cnt < 0) { + ASSERT_OK(-errno, "REG_BOUNDS_MAX_FAILURE_CNT"); + return -EINVAL; + } + } + + if ((s = getenv("REG_BOUNDS_RAND_CASE_CNT"))) { + errno = 0; + ctx->rand_case_cnt = strtol(s, NULL, 10); + if (errno || ctx->rand_case_cnt < 0) { + ASSERT_OK(-errno, "REG_BOUNDS_RAND_CASE_CNT"); + return -EINVAL; + } + } + + if ((s = getenv("REG_BOUNDS_RAND_SEED"))) { + errno = 0; + ctx->rand_seed = strtoul(s, NULL, 10); + if (errno) { + ASSERT_OK(-errno, "REG_BOUNDS_RAND_SEED"); + return -EINVAL; + } + } + + return 0; +} + +static int prepare_gen_tests(struct ctx *ctx) +{ + const char *s; + int err; + + if (!(s = getenv("SLOW_TESTS")) || strcmp(s, "1") != 0) { + test__skip(); + return -ENOTSUP; + } + + err = parse_env_vars(ctx); + if (err) + return err; + + gen_vals(ctx); + err = gen_ranges(ctx); + if (err) { + ASSERT_OK(err, "gen_ranges"); + return err; + } + + return 0; +} + +/* Go over generated constants and ranges and validate various supported + * combinations of them + */ +static void validate_gen_range_vs_const_64(enum num_t init_t, enum num_t cond_t) +{ + struct ctx ctx; + struct range rconst; + const struct range *ranges; + const u64 *vals; + int i, j; + + memset(&ctx, 0, sizeof(ctx)); + + if (prepare_gen_tests(&ctx)) + goto cleanup; + + ranges = init_t == U64 ? ctx.uranges : ctx.sranges; + vals = init_t == U64 ? ctx.uvals : (const u64 *)ctx.svals; + + ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.range_cnt * ctx.val_cnt); + ctx.start_ns = get_time_ns(); + snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx), + "RANGE x CONST, %s -> %s", + t_str(init_t), t_str(cond_t)); + + for (i = 0; i < ctx.val_cnt; i++) { + for (j = 0; j < ctx.range_cnt; j++) { + rconst = range(init_t, vals[i], vals[i]); + + /* (u64|s64)(<range> x <const>) */ + if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst)) + goto cleanup; + /* (u64|s64)(<const> x <range>) */ + if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j])) + goto cleanup; + } + } + +cleanup: + cleanup_ctx(&ctx); +} + +static void validate_gen_range_vs_const_32(enum num_t init_t, enum num_t cond_t) +{ + struct ctx ctx; + struct range rconst; + const struct range *ranges; + const u32 *vals; + int i, j; + + memset(&ctx, 0, sizeof(ctx)); + + if (prepare_gen_tests(&ctx)) + goto cleanup; + + ranges = init_t == U32 ? ctx.usubranges : ctx.ssubranges; + vals = init_t == U32 ? ctx.usubvals : (const u32 *)ctx.ssubvals; + + ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.subrange_cnt * ctx.subval_cnt); + ctx.start_ns = get_time_ns(); + snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx), + "RANGE x CONST, %s -> %s", + t_str(init_t), t_str(cond_t)); + + for (i = 0; i < ctx.subval_cnt; i++) { + for (j = 0; j < ctx.subrange_cnt; j++) { + rconst = range(init_t, vals[i], vals[i]); + + /* (u32|s32)(<range> x <const>) */ + if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst)) + goto cleanup; + /* (u32|s32)(<const> x <range>) */ + if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j])) + goto cleanup; + } + } + +cleanup: + cleanup_ctx(&ctx); +} + +static void validate_gen_range_vs_range(enum num_t init_t, enum num_t cond_t) +{ + struct ctx ctx; + const struct range *ranges; + int i, j, rcnt; + + memset(&ctx, 0, sizeof(ctx)); + + if (prepare_gen_tests(&ctx)) + goto cleanup; + + switch (init_t) + { + case U64: + ranges = ctx.uranges; + rcnt = ctx.range_cnt; + break; + case U32: + ranges = ctx.usubranges; + rcnt = ctx.subrange_cnt; + break; + case S64: + ranges = ctx.sranges; + rcnt = ctx.range_cnt; + break; + case S32: + ranges = ctx.ssubranges; + rcnt = ctx.subrange_cnt; + break; + default: + printf("validate_gen_range_vs_range!\n"); + exit(1); + } + + ctx.total_case_cnt = (last_op - first_op + 1) * (2 * rcnt * (rcnt + 1) / 2); + ctx.start_ns = get_time_ns(); + snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx), + "RANGE x RANGE, %s -> %s", + t_str(init_t), t_str(cond_t)); + + for (i = 0; i < rcnt; i++) { + for (j = i; j < rcnt; j++) { + /* (<range> x <range>) */ + if (verify_case(&ctx, init_t, cond_t, ranges[i], ranges[j])) + goto cleanup; + if (verify_case(&ctx, init_t, cond_t, ranges[j], ranges[i])) + goto cleanup; + } + } + +cleanup: + cleanup_ctx(&ctx); +} + +/* Go over thousands of test cases generated from initial seed values. + * Given this take a long time, guard this begind SLOW_TESTS=1 envvar. If + * envvar is not set, this test is skipped during test_progs testing. + * + * We split this up into smaller subsets based on initialization and + * conditiona numeric domains to get an easy parallelization with test_progs' + * -j argument. + */ + +/* RANGE x CONST, U64 initial range */ +void test_reg_bounds_gen_consts_u64_u64(void) { validate_gen_range_vs_const_64(U64, U64); } +void test_reg_bounds_gen_consts_u64_s64(void) { validate_gen_range_vs_const_64(U64, S64); } +void test_reg_bounds_gen_consts_u64_u32(void) { validate_gen_range_vs_const_64(U64, U32); } +void test_reg_bounds_gen_consts_u64_s32(void) { validate_gen_range_vs_const_64(U64, S32); } +/* RANGE x CONST, S64 initial range */ +void test_reg_bounds_gen_consts_s64_u64(void) { validate_gen_range_vs_const_64(S64, U64); } +void test_reg_bounds_gen_consts_s64_s64(void) { validate_gen_range_vs_const_64(S64, S64); } +void test_reg_bounds_gen_consts_s64_u32(void) { validate_gen_range_vs_const_64(S64, U32); } +void test_reg_bounds_gen_consts_s64_s32(void) { validate_gen_range_vs_const_64(S64, S32); } +/* RANGE x CONST, U32 initial range */ +void test_reg_bounds_gen_consts_u32_u64(void) { validate_gen_range_vs_const_32(U32, U64); } +void test_reg_bounds_gen_consts_u32_s64(void) { validate_gen_range_vs_const_32(U32, S64); } +void test_reg_bounds_gen_consts_u32_u32(void) { validate_gen_range_vs_const_32(U32, U32); } +void test_reg_bounds_gen_consts_u32_s32(void) { validate_gen_range_vs_const_32(U32, S32); } +/* RANGE x CONST, S32 initial range */ +void test_reg_bounds_gen_consts_s32_u64(void) { validate_gen_range_vs_const_32(S32, U64); } +void test_reg_bounds_gen_consts_s32_s64(void) { validate_gen_range_vs_const_32(S32, S64); } +void test_reg_bounds_gen_consts_s32_u32(void) { validate_gen_range_vs_const_32(S32, U32); } +void test_reg_bounds_gen_consts_s32_s32(void) { validate_gen_range_vs_const_32(S32, S32); } + +/* RANGE x RANGE, U64 initial range */ +void test_reg_bounds_gen_ranges_u64_u64(void) { validate_gen_range_vs_range(U64, U64); } +void test_reg_bounds_gen_ranges_u64_s64(void) { validate_gen_range_vs_range(U64, S64); } +void test_reg_bounds_gen_ranges_u64_u32(void) { validate_gen_range_vs_range(U64, U32); } +void test_reg_bounds_gen_ranges_u64_s32(void) { validate_gen_range_vs_range(U64, S32); } +/* RANGE x RANGE, S64 initial range */ +void test_reg_bounds_gen_ranges_s64_u64(void) { validate_gen_range_vs_range(S64, U64); } +void test_reg_bounds_gen_ranges_s64_s64(void) { validate_gen_range_vs_range(S64, S64); } +void test_reg_bounds_gen_ranges_s64_u32(void) { validate_gen_range_vs_range(S64, U32); } +void test_reg_bounds_gen_ranges_s64_s32(void) { validate_gen_range_vs_range(S64, S32); } +/* RANGE x RANGE, U32 initial range */ +void test_reg_bounds_gen_ranges_u32_u64(void) { validate_gen_range_vs_range(U32, U64); } +void test_reg_bounds_gen_ranges_u32_s64(void) { validate_gen_range_vs_range(U32, S64); } +void test_reg_bounds_gen_ranges_u32_u32(void) { validate_gen_range_vs_range(U32, U32); } +void test_reg_bounds_gen_ranges_u32_s32(void) { validate_gen_range_vs_range(U32, S32); } +/* RANGE x RANGE, S32 initial range */ +void test_reg_bounds_gen_ranges_s32_u64(void) { validate_gen_range_vs_range(S32, U64); } +void test_reg_bounds_gen_ranges_s32_s64(void) { validate_gen_range_vs_range(S32, S64); } +void test_reg_bounds_gen_ranges_s32_u32(void) { validate_gen_range_vs_range(S32, U32); } +void test_reg_bounds_gen_ranges_s32_s32(void) { validate_gen_range_vs_range(S32, S32); } + +#define DEFAULT_RAND_CASE_CNT 100 + +#define RAND_21BIT_MASK ((1 << 22) - 1) + +static u64 rand_u64() +{ + /* RAND_MAX is guaranteed to be at least 1<<15, but in practice it + * seems to be 1<<31, so we need to call it thrice to get full u64; + * we'll use rougly equal split: 22 + 21 + 21 bits + */ + return ((u64)random() << 42) | + (((u64)random() & RAND_21BIT_MASK) << 21) | + (random() & RAND_21BIT_MASK); +} + +static u64 rand_const(enum num_t t) +{ + return cast_t(t, rand_u64()); +} + +static struct range rand_range(enum num_t t) +{ + u64 x = rand_const(t), y = rand_const(t); + + return range(t, min_t(t, x, y), max_t(t, x, y)); +} + +static void validate_rand_ranges(enum num_t init_t, enum num_t cond_t, bool const_range) +{ + struct ctx ctx; + struct range range1, range2; + int err, i; + u64 t; + + memset(&ctx, 0, sizeof(ctx)); + + err = parse_env_vars(&ctx); + if (err) { + ASSERT_OK(err, "parse_env_vars"); + return; + } + + if (ctx.rand_case_cnt == 0) + ctx.rand_case_cnt = DEFAULT_RAND_CASE_CNT; + if (ctx.rand_seed == 0) + ctx.rand_seed = (unsigned)get_time_ns(); + + srandom(ctx.rand_seed); + + ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.rand_case_cnt); + ctx.start_ns = get_time_ns(); + snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx), + "[RANDOM SEED %u] RANGE x %s, %s -> %s", + ctx.rand_seed, const_range ? "CONST" : "RANGE", + t_str(init_t), t_str(cond_t)); + + for (i = 0; i < ctx.rand_case_cnt; i++) { + range1 = rand_range(init_t); + if (const_range) { + t = rand_const(init_t); + range2 = range(init_t, t, t); + } else { + range2 = rand_range(init_t); + } + + /* <range1> x <range2> */ + if (verify_case_opt(&ctx, init_t, cond_t, range1, range2, false /* !is_subtest */)) + goto cleanup; + /* <range2> x <range1> */ + if (verify_case_opt(&ctx, init_t, cond_t, range2, range1, false /* !is_subtest */)) + goto cleanup; + } + +cleanup: + /* make sure we report random seed for reproducing */ + ASSERT_TRUE(true, ctx.progress_ctx); + cleanup_ctx(&ctx); +} + +/* [RANDOM] RANGE x CONST, U64 initial range */ +void test_reg_bounds_rand_consts_u64_u64(void) { validate_rand_ranges(U64, U64, true /* const */); } +void test_reg_bounds_rand_consts_u64_s64(void) { validate_rand_ranges(U64, S64, true /* const */); } +void test_reg_bounds_rand_consts_u64_u32(void) { validate_rand_ranges(U64, U32, true /* const */); } +void test_reg_bounds_rand_consts_u64_s32(void) { validate_rand_ranges(U64, S32, true /* const */); } +/* [RANDOM] RANGE x CONST, S64 initial range */ +void test_reg_bounds_rand_consts_s64_u64(void) { validate_rand_ranges(S64, U64, true /* const */); } +void test_reg_bounds_rand_consts_s64_s64(void) { validate_rand_ranges(S64, S64, true /* const */); } +void test_reg_bounds_rand_consts_s64_u32(void) { validate_rand_ranges(S64, U32, true /* const */); } +void test_reg_bounds_rand_consts_s64_s32(void) { validate_rand_ranges(S64, S32, true /* const */); } +/* [RANDOM] RANGE x CONST, U32 initial range */ +void test_reg_bounds_rand_consts_u32_u64(void) { validate_rand_ranges(U32, U64, true /* const */); } +void test_reg_bounds_rand_consts_u32_s64(void) { validate_rand_ranges(U32, S64, true /* const */); } +void test_reg_bounds_rand_consts_u32_u32(void) { validate_rand_ranges(U32, U32, true /* const */); } +void test_reg_bounds_rand_consts_u32_s32(void) { validate_rand_ranges(U32, S32, true /* const */); } +/* [RANDOM] RANGE x CONST, S32 initial range */ +void test_reg_bounds_rand_consts_s32_u64(void) { validate_rand_ranges(S32, U64, true /* const */); } +void test_reg_bounds_rand_consts_s32_s64(void) { validate_rand_ranges(S32, S64, true /* const */); } +void test_reg_bounds_rand_consts_s32_u32(void) { validate_rand_ranges(S32, U32, true /* const */); } +void test_reg_bounds_rand_consts_s32_s32(void) { validate_rand_ranges(S32, S32, true /* const */); } + +/* [RANDOM] RANGE x RANGE, U64 initial range */ +void test_reg_bounds_rand_ranges_u64_u64(void) { validate_rand_ranges(U64, U64, false /* range */); } +void test_reg_bounds_rand_ranges_u64_s64(void) { validate_rand_ranges(U64, S64, false /* range */); } +void test_reg_bounds_rand_ranges_u64_u32(void) { validate_rand_ranges(U64, U32, false /* range */); } +void test_reg_bounds_rand_ranges_u64_s32(void) { validate_rand_ranges(U64, S32, false /* range */); } +/* [RANDOM] RANGE x RANGE, S64 initial range */ +void test_reg_bounds_rand_ranges_s64_u64(void) { validate_rand_ranges(S64, U64, false /* range */); } +void test_reg_bounds_rand_ranges_s64_s64(void) { validate_rand_ranges(S64, S64, false /* range */); } +void test_reg_bounds_rand_ranges_s64_u32(void) { validate_rand_ranges(S64, U32, false /* range */); } +void test_reg_bounds_rand_ranges_s64_s32(void) { validate_rand_ranges(S64, S32, false /* range */); } +/* [RANDOM] RANGE x RANGE, U32 initial range */ +void test_reg_bounds_rand_ranges_u32_u64(void) { validate_rand_ranges(U32, U64, false /* range */); } +void test_reg_bounds_rand_ranges_u32_s64(void) { validate_rand_ranges(U32, S64, false /* range */); } +void test_reg_bounds_rand_ranges_u32_u32(void) { validate_rand_ranges(U32, U32, false /* range */); } +void test_reg_bounds_rand_ranges_u32_s32(void) { validate_rand_ranges(U32, S32, false /* range */); } +/* [RANDOM] RANGE x RANGE, S32 initial range */ +void test_reg_bounds_rand_ranges_s32_u64(void) { validate_rand_ranges(S32, U64, false /* range */); } +void test_reg_bounds_rand_ranges_s32_s64(void) { validate_rand_ranges(S32, S64, false /* range */); } +void test_reg_bounds_rand_ranges_s32_u32(void) { validate_rand_ranges(S32, U32, false /* range */); } +void test_reg_bounds_rand_ranges_s32_s32(void) { validate_rand_ranges(S32, S32, false /* range */); } + +/* A set of hard-coded "interesting" cases to validate as part of normal + * test_progs test runs + */ +static struct subtest_case crafted_cases[] = { + {U64, U64, {0, 0xffffffff}, {0, 0}}, + {U64, U64, {0, 0x80000000}, {0, 0}}, + {U64, U64, {0x100000000ULL, 0x100000100ULL}, {0, 0}}, + {U64, U64, {0x100000000ULL, 0x180000000ULL}, {0, 0}}, + {U64, U64, {0x100000000ULL, 0x1ffffff00ULL}, {0, 0}}, + {U64, U64, {0x100000000ULL, 0x1ffffff01ULL}, {0, 0}}, + {U64, U64, {0x100000000ULL, 0x1fffffffeULL}, {0, 0}}, + {U64, U64, {0x100000001ULL, 0x1000000ffULL}, {0, 0}}, + + /* single point overlap, interesting BPF_EQ and BPF_NE interactions */ + {U64, U64, {0, 1}, {1, 0x80000000}}, + {U64, S64, {0, 1}, {1, 0x80000000}}, + {U64, U32, {0, 1}, {1, 0x80000000}}, + {U64, S32, {0, 1}, {1, 0x80000000}}, + + {U64, S64, {0, 0xffffffff00000000ULL}, {0, 0}}, + {U64, S64, {0x7fffffffffffffffULL, 0xffffffff00000000ULL}, {0, 0}}, + {U64, S64, {0x7fffffff00000001ULL, 0xffffffff00000000ULL}, {0, 0}}, + {U64, S64, {0, 0xffffffffULL}, {1, 1}}, + {U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}}, + + {U64, U32, {0, 0x100000000}, {0, 0}}, + {U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}}, + + {U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}}, + /* these are tricky cases where lower 32 bits allow to tighten 64 + * bit boundaries based on tightened lower 32 bit boundaries + */ + {U64, S32, {0, 0x0ffffffffULL}, {0, 0}}, + {U64, S32, {0, 0x100000000ULL}, {0, 0}}, + {U64, S32, {0, 0x100000001ULL}, {0, 0}}, + {U64, S32, {0, 0x180000000ULL}, {0, 0}}, + {U64, S32, {0, 0x17fffffffULL}, {0, 0}}, + {U64, S32, {0, 0x180000001ULL}, {0, 0}}, + + /* verifier knows about [-1, 0] range for s32 for this case already */ + {S64, S64, {0xffffffffffffffffULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}}, + /* but didn't know about these cases initially */ + {U64, U64, {0xffffffff, 0x100000000ULL}, {0, 0}}, /* s32: [-1, 0] */ + {U64, U64, {0xffffffff, 0x100000001ULL}, {0, 0}}, /* s32: [-1, 1] */ + + /* longer convergence case: learning from u64 -> s64 -> u64 -> u32, + * arriving at u32: [1, U32_MAX] (instead of more pessimistic [0, U32_MAX]) + */ + {S64, U64, {0xffffffff00000001ULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}}, + + {U32, U32, {1, U32_MAX}, {0, 0}}, + + {U32, S32, {0, U32_MAX}, {U32_MAX, U32_MAX}}, + + {S32, U64, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}, {(u32)(s32)-255, 0}}, + {S32, S64, {(u32)(s32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}}, + {S32, S64, {0, 1}, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}}, + {S32, U32, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}, {(u32)(s32)S32_MIN, (u32)(s32)S32_MIN}}, +}; + +/* Go over crafted hard-coded cases. This is fast, so we do it as part of + * normal test_progs run. + */ +void test_reg_bounds_crafted(void) +{ + struct ctx ctx; + int i; + + memset(&ctx, 0, sizeof(ctx)); + + for (i = 0; i < ARRAY_SIZE(crafted_cases); i++) { + struct subtest_case *c = &crafted_cases[i]; + + verify_case(&ctx, c->init_t, c->cond_t, c->x, c->y); + verify_case(&ctx, c->init_t, c->cond_t, c->y, c->x); + } + + cleanup_ctx(&ctx); +} diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c index f29c08d93beb..18d451be57c8 100644 --- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -13,22 +13,22 @@ static struct { const char *err_msg; } spin_lock_fail_tests[] = { { "lock_id_kptr_preserve", - "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) " - "R1_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n" + "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2) " + "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n" "R1 type=ptr_ expected=percpu_ptr_" }, { "lock_id_global_zero", - "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n" + "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mapval_preserve", "[0-9]\\+: (bf) r1 = r0 ;" - " R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)" - " R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n" + " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)" + " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n" "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_innermapval_preserve", "[0-9]\\+: (bf) r1 = r0 ;" - " R0=map_value(id=2,off=0,ks=4,vs=8,imm=0)" - " R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n" + " R0=map_value(id=2,ks=4,vs=8)" + " R1_w=map_value(id=2,ks=4,vs=8)\n" "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" }, diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index 51883ccb8020..196abf223465 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2387,12 +2387,9 @@ static int generate_dummy_prog(void) const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); LIBBPF_OPTS(bpf_prog_load_opts, opts); const size_t log_buf_sz = 256; - char *log_buf; + char log_buf[log_buf_sz]; int fd = -1; - log_buf = malloc(log_buf_sz); - if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc")) - return fd; opts.log_buf = log_buf; opts.log_size = log_buf_sz; @@ -2402,7 +2399,6 @@ static int generate_dummy_prog(void) prog_insns, prog_insn_cnt, &opts); ASSERT_STREQ(log_buf, "", "log_0"); ASSERT_GE(fd, 0, "prog_fd"); - free(log_buf); return fd; } diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c index 72310cfc6474..6fb2217d940b 100644 --- a/tools/testing/selftests/bpf/prog_tests/vmlinux.c +++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c @@ -16,27 +16,27 @@ static void nsleep() void test_vmlinux(void) { - int duration = 0, err; + int err; struct test_vmlinux* skel; struct test_vmlinux__bss *bss; skel = test_vmlinux__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "test_vmlinux__open_and_load")) return; bss = skel->bss; err = test_vmlinux__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_vmlinux__attach")) goto cleanup; /* trigger everything */ nsleep(); - CHECK(!bss->tp_called, "tp", "not called\n"); - CHECK(!bss->raw_tp_called, "raw_tp", "not called\n"); - CHECK(!bss->tp_btf_called, "tp_btf", "not called\n"); - CHECK(!bss->kprobe_called, "kprobe", "not called\n"); - CHECK(!bss->fentry_called, "fentry", "not called\n"); + ASSERT_TRUE(bss->tp_called, "tp"); + ASSERT_TRUE(bss->raw_tp_called, "raw_tp"); + ASSERT_TRUE(bss->tp_btf_called, "tp_btf"); + ASSERT_TRUE(bss->kprobe_called, "kprobe"); + ASSERT_TRUE(bss->fentry_called, "fentry"); cleanup: test_vmlinux__destroy(skel); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index f2b8167b72a8..442f4ca39fd7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -35,6 +35,8 @@ int dump_task_stack(struct bpf_iter__task *ctx) return 0; } +int num_user_stacks = 0; + SEC("iter/task") int get_task_user_stacks(struct bpf_iter__task *ctx) { @@ -51,6 +53,9 @@ int get_task_user_stacks(struct bpf_iter__task *ctx) if (res <= 0) return 0; + /* Only one task, the current one, should succeed */ + ++num_user_stacks; + buf_sz += res; /* If the verifier doesn't refine bpf_get_task_stack res, and instead diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index e1e5c54a6a11..49efaed143fc 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -18,48 +18,48 @@ return *(u64 *)num; \ } -__msg(": R0_w=-2147483648 R10=fp0") +__msg(": R0_w=0xffffffff80000000 R10=fp0") check_assert(s64, eq, int_min, INT_MIN); -__msg(": R0_w=2147483647 R10=fp0") +__msg(": R0_w=0x7fffffff R10=fp0") check_assert(s64, eq, int_max, INT_MAX); __msg(": R0_w=0 R10=fp0") check_assert(s64, eq, zero, 0); -__msg(": R0_w=-9223372036854775808 R1_w=-9223372036854775808 R10=fp0") +__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000 R10=fp0") check_assert(s64, eq, llong_min, LLONG_MIN); -__msg(": R0_w=9223372036854775807 R1_w=9223372036854775807 R10=fp0") +__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff R10=fp0") check_assert(s64, eq, llong_max, LLONG_MAX); -__msg(": R0_w=scalar(smax=2147483646) R10=fp0") +__msg(": R0_w=scalar(smax=0x7ffffffe) R10=fp0") check_assert(s64, lt, pos, INT_MAX); -__msg(": R0_w=scalar(smax=-1,umin=9223372036854775808,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, lt, zero, 0); -__msg(": R0_w=scalar(smax=-2147483649,umin=9223372036854775808,umax=18446744071562067967,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=0xffffffff7fffffff,umin=0x8000000000000000,umax=0xffffffff7fffffff,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, lt, neg, INT_MIN); -__msg(": R0_w=scalar(smax=2147483647) R10=fp0") +__msg(": R0_w=scalar(smax=0x7fffffff) R10=fp0") check_assert(s64, le, pos, INT_MAX); __msg(": R0_w=scalar(smax=0) R10=fp0") check_assert(s64, le, zero, 0); -__msg(": R0_w=scalar(smax=-2147483648,umin=9223372036854775808,umax=18446744071562067968,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smax=0xffffffff80000000,umin=0x8000000000000000,umax=0xffffffff80000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, le, neg, INT_MIN); -__msg(": R0_w=scalar(smin=umin=2147483648,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, gt, pos, INT_MAX); -__msg(": R0_w=scalar(smin=umin=1,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, gt, zero, 0); -__msg(": R0_w=scalar(smin=-2147483647) R10=fp0") +__msg(": R0_w=scalar(smin=0xffffffff80000001) R10=fp0") check_assert(s64, gt, neg, INT_MIN); -__msg(": R0_w=scalar(smin=umin=2147483647,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0_w=scalar(smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, ge, pos, INT_MAX); -__msg(": R0_w=scalar(smin=0,umax=9223372036854775807,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0") +__msg(": R0_w=scalar(smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0") check_assert(s64, ge, zero, 0); -__msg(": R0_w=scalar(smin=-2147483648) R10=fp0") +__msg(": R0_w=scalar(smin=0xffffffff80000000) R10=fp0") check_assert(s64, ge, neg, INT_MIN); SEC("?tc") __log_level(2) __failure -__msg(": R0=0 R1=ctx(off=0,imm=0) R2=scalar(smin=smin32=-2147483646,smax=smax32=2147483645) R10=fp0") +__msg(": R0=0 R1=ctx() R2=scalar(smin=0xffffffff80000002,smax=smax32=0x7ffffffd,smin32=0x80000002) R10=fp0") int check_assert_range_s64(struct __sk_buff *ctx) { struct bpf_sock *sk = ctx->sk; @@ -75,7 +75,7 @@ int check_assert_range_s64(struct __sk_buff *ctx) SEC("?tc") __log_level(2) __failure -__msg(": R1=ctx(off=0,imm=0) R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))") +__msg(": R1=ctx() R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))") int check_assert_range_u64(struct __sk_buff *ctx) { u64 num = ctx->len; @@ -86,7 +86,7 @@ int check_assert_range_u64(struct __sk_buff *ctx) SEC("?tc") __log_level(2) __failure -__msg(": R0=0 R1=ctx(off=0,imm=0) R2=4096 R10=fp0") +__msg(": R0=0 R1=ctx() R2=4096 R10=fp0") int check_assert_single_range_s64(struct __sk_buff *ctx) { struct bpf_sock *sk = ctx->sk; @@ -103,7 +103,7 @@ int check_assert_single_range_s64(struct __sk_buff *ctx) SEC("?tc") __log_level(2) __failure -__msg(": R1=ctx(off=0,imm=0) R2=4096 R10=fp0") +__msg(": R1=ctx() R2=4096 R10=fp0") int check_assert_single_range_u64(struct __sk_buff *ctx) { u64 num = ctx->len; @@ -114,7 +114,7 @@ int check_assert_single_range_u64(struct __sk_buff *ctx) SEC("?tc") __log_level(2) __failure -__msg(": R1=pkt(off=64,r=64,imm=0) R2=pkt_end(off=0,imm=0) R6=pkt(off=0,r=64,imm=0) R10=fp0") +__msg(": R1=pkt(off=64,r=64) R2=pkt_end() R6=pkt(r=64) R10=fp0") int check_assert_generic(struct __sk_buff *ctx) { u8 *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index c20c4e38b71c..b2181f850d3e 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1411,4 +1411,26 @@ __naked int checkpoint_states_deletion(void) ); } +struct { + int data[32]; + int n; +} loop_data; + +SEC("raw_tp") +__success +int iter_arr_with_actual_elem_count(const void *ctx) +{ + int i, n = loop_data.n, sum = 0; + + if (n > ARRAY_SIZE(loop_data.data)) + return 0; + + bpf_for(i, 0, n) { + /* no rechecking of i against ARRAY_SIZE(loop_data.n) */ + sum += loop_data.data[i]; + } + + return sum; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index b567a666d2b8..1769fdff6aea 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -14,6 +14,24 @@ struct node_data { struct bpf_rb_node node; }; +struct refcounted_node { + long data; + struct bpf_rb_node rb_node; + struct bpf_refcount refcount; +}; + +struct stash { + struct bpf_spin_lock l; + struct refcounted_node __kptr *stashed; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct stash); + __uint(max_entries, 10); +} refcounted_node_stash SEC(".maps"); + struct plain_local { long key; long data; @@ -38,6 +56,7 @@ struct map_value { * Had to do the same w/ bpf_kfunc_call_test_release below */ struct node_data *just_here_because_btf_bug; +struct refcounted_node *just_here_because_btf_bug2; struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -132,4 +151,56 @@ long stash_test_ref_kfunc(void *ctx) return 0; } +SEC("tc") +long refcount_acquire_without_unstash(void *ctx) +{ + struct refcounted_node *p; + struct stash *s; + int ret = 0; + + s = bpf_map_lookup_elem(&refcounted_node_stash, &ret); + if (!s) + return 1; + + if (!s->stashed) + /* refcount_acquire failure is expected when no refcounted_node + * has been stashed before this program executes + */ + return 2; + + p = bpf_refcount_acquire(s->stashed); + if (!p) + return 3; + + ret = s->stashed ? s->stashed->data : -1; + bpf_obj_drop(p); + return ret; +} + +/* Helper for refcount_acquire_without_unstash test */ +SEC("tc") +long stash_refcounted_node(void *ctx) +{ + struct refcounted_node *p; + struct stash *s; + int key = 0; + + s = bpf_map_lookup_elem(&refcounted_node_stash, &key); + if (!s) + return 1; + + p = bpf_obj_new(typeof(*p)); + if (!p) + return 2; + p->data = 42; + + p = bpf_kptr_xchg(&s->stashed, p); + if (p) { + bpf_obj_drop(p); + return 3; + } + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c index c39f559d3100..42c4a8b62e36 100644 --- a/tools/testing/selftests/bpf/progs/pyperf180.c +++ b/tools/testing/selftests/bpf/progs/pyperf180.c @@ -1,4 +1,26 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #define STACK_MAX_LEN 180 + +/* llvm upstream commit at clang18 + * https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e + * changed inlining behavior and caused compilation failure as some branch + * target distance exceeded 16bit representation which is the maximum for + * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18 + * to specify which cpu version is used for compilation. So a smaller + * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which + * reduced some branch target distances and resolved the compilation failure. + * + * To capture the case where a developer/ci uses clang18 but the corresponding + * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count + * will be set as well to prevent potential compilation failures. + */ +#ifdef __BPF_CPU_VERSION__ +#if __BPF_CPU_VERSION__ < 4 +#define UNROLL_COUNT 90 +#endif +#elif __clang_major__ == 18 +#define UNROLL_COUNT 90 +#endif + #include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c index 1ef07f6ee580..1553b9c16aa7 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c @@ -54,6 +54,25 @@ long rbtree_refcounted_node_ref_escapes(void *ctx) } SEC("?tc") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +long refcount_acquire_maybe_null(void *ctx) +{ + struct node_acquire *n, *m; + + n = bpf_obj_new(typeof(*n)); + /* Intentionally not testing !n + * it's MAYBE_NULL for refcount_acquire + */ + m = bpf_refcount_acquire(n); + if (m) + bpf_obj_drop(m); + if (n) + bpf_obj_drop(n); + + return 0; +} + +SEC("?tc") __failure __msg("Unreleased reference id=3 alloc_insn=9") long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c new file mode 100644 index 000000000000..44628865fe1d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +__u32 target_ancestor_level; +__u64 target_ancestor_cgid; +int target_pid, target_hid; + +struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym; +struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; + +static int bpf_link_create_verify(int cmd) +{ + struct cgroup *cgrp, *ancestor; + struct task_struct *task; + int ret = 0; + + if (cmd != BPF_LINK_CREATE) + return 0; + + task = bpf_get_current_task_btf(); + + /* Then it can run in parallel with others */ + if (task->pid != target_pid) + return 0; + + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + /* Refuse it if its cgid or its ancestor's cgid is the target cgid */ + if (cgrp->kn->id == target_ancestor_cgid) + ret = -1; + + ancestor = bpf_cgroup_ancestor(cgrp, target_ancestor_level); + if (!ancestor) + goto out; + + if (ancestor->kn->id == target_ancestor_cgid) + ret = -1; + bpf_cgroup_release(ancestor); + +out: + bpf_cgroup_release(cgrp); + return ret; +} + +SEC("lsm/bpf") +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + return bpf_link_create_verify(cmd); +} + +SEC("lsm.s/bpf") +int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + return bpf_link_create_verify(cmd); +} + +SEC("fentry") +int BPF_PROG(fentry_run) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index c5588a14fe2e..ec430b71730b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -965,6 +965,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP_JSLT for crossing 64-bit signed boundary") __success __retval(0) +__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ __naked void crossing_64_bit_signed_boundary_2(void) { asm volatile (" \ @@ -1046,6 +1047,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary") __success __retval(0) +__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ __naked void crossing_32_bit_signed_boundary_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 37ffa57f28a1..a350ecdfba4a 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -153,6 +153,14 @@ static int parse_retval(const char *str, int *val, const char *name) return parse_int(str, val, name); } +static void update_flags(int *flags, int flag, bool clear) +{ + if (clear) + *flags &= ~flag; + else + *flags |= flag; +} + /* Uses btf_decl_tag attributes to describe the expected test * behavior, see bpf_misc.h for detailed description of each attribute * and attribute combinations. @@ -171,6 +179,7 @@ static int parse_test_spec(struct test_loader *tester, memset(spec, 0, sizeof(*spec)); spec->prog_name = bpf_program__name(prog); + spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */ btf = bpf_object__btf(obj); if (!btf) { @@ -187,7 +196,8 @@ static int parse_test_spec(struct test_loader *tester, for (i = 1; i < btf__type_cnt(btf); i++) { const char *s, *val, *msg; const struct btf_type *t; - int tmp; + bool clear; + int flags; t = btf__type_by_id(btf, i); if (!btf_is_decl_tag(t)) @@ -253,23 +263,30 @@ static int parse_test_spec(struct test_loader *tester, goto cleanup; } else if (str_has_pfx(s, TEST_TAG_PROG_FLAGS_PFX)) { val = s + sizeof(TEST_TAG_PROG_FLAGS_PFX) - 1; + + clear = val[0] == '!'; + if (clear) + val++; + if (strcmp(val, "BPF_F_STRICT_ALIGNMENT") == 0) { - spec->prog_flags |= BPF_F_STRICT_ALIGNMENT; + update_flags(&spec->prog_flags, BPF_F_STRICT_ALIGNMENT, clear); } else if (strcmp(val, "BPF_F_ANY_ALIGNMENT") == 0) { - spec->prog_flags |= BPF_F_ANY_ALIGNMENT; + update_flags(&spec->prog_flags, BPF_F_ANY_ALIGNMENT, clear); } else if (strcmp(val, "BPF_F_TEST_RND_HI32") == 0) { - spec->prog_flags |= BPF_F_TEST_RND_HI32; + update_flags(&spec->prog_flags, BPF_F_TEST_RND_HI32, clear); } else if (strcmp(val, "BPF_F_TEST_STATE_FREQ") == 0) { - spec->prog_flags |= BPF_F_TEST_STATE_FREQ; + update_flags(&spec->prog_flags, BPF_F_TEST_STATE_FREQ, clear); } else if (strcmp(val, "BPF_F_SLEEPABLE") == 0) { - spec->prog_flags |= BPF_F_SLEEPABLE; + update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear); } else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) { - spec->prog_flags |= BPF_F_XDP_HAS_FRAGS; + update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear); + } else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) { + update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear); } else /* assume numeric value */ { - err = parse_int(val, &tmp, "test prog flags"); + err = parse_int(val, &flags, "test prog flags"); if (err) goto cleanup; - spec->prog_flags |= tmp; + update_flags(&spec->prog_flags, flags, clear); } } } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 7fc00e423e4d..767e0693df10 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1396,13 +1396,18 @@ static void test_map_stress(void) #define MAX_DELAY_US 50000 #define MIN_DELAY_RANGE_US 5000 -static int map_update_retriable(int map_fd, const void *key, const void *value, - int flags, int attempts) +static bool retry_for_again_or_busy(int err) +{ + return (err == EAGAIN || err == EBUSY); +} + +int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, + retry_for_error_fn need_retry) { int delay = rand() % MIN_DELAY_RANGE_US; while (bpf_map_update_elem(map_fd, key, value, flags)) { - if (!attempts || (errno != EAGAIN && errno != EBUSY)) + if (!attempts || !need_retry(errno)) return -errno; if (delay <= MAX_DELAY_US / 2) @@ -1445,11 +1450,13 @@ static void test_update_delete(unsigned int fn, void *data) key = value = i; if (do_update) { - err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES); + err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES, + retry_for_again_or_busy); if (err) printf("error %d %d\n", err, errno); assert(err == 0); - err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES); + err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES, + retry_for_again_or_busy); if (err) printf("error %d %d\n", err, errno); assert(err == 0); diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h index f6fbca761732..e4ac704a536c 100644 --- a/tools/testing/selftests/bpf/test_maps.h +++ b/tools/testing/selftests/bpf/test_maps.h @@ -4,6 +4,7 @@ #include <stdio.h> #include <stdlib.h> +#include <stdbool.h> #define CHECK(condition, tag, format...) ({ \ int __ret = !!(condition); \ @@ -16,4 +17,8 @@ extern int skips; +typedef bool (*retry_for_error_fn)(int err); +int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, + retry_for_error_fn need_retry); + #endif diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 2c89674fc62c..b0068a9d2cfe 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -679,7 +679,7 @@ static int load_path(const struct sock_addr_test *test, const char *path) bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); bpf_program__set_expected_attach_type(prog, test->expected_attach_type); - bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS); err = bpf_object__load(obj); if (err) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 98107e0452d3..f36e41435be7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1588,7 +1588,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (fixup_skips != skips) return; - pflags = BPF_F_TEST_RND_HI32; + pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT) pflags |= BPF_F_STRICT_ALIGNMENT; if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 8d994884c7b4..d2458c1b1671 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -276,7 +276,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type, if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type) bpf_program__set_type(prog, type); - flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32; + flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS; bpf_program__set_flags(prog, flags); err = bpf_object__load(obj); @@ -299,7 +299,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, { LIBBPF_OPTS(bpf_prog_load_opts, opts, .kern_version = kern_version, - .prog_flags = BPF_F_TEST_RND_HI32, + .prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS, .log_level = extra_prog_load_log_flags, .log_buf = log_buf, .log_size = log_buf_sz, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 655095810d4a..1d418d66e375 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -18,6 +18,7 @@ #include <libelf.h> #include <gelf.h> #include <float.h> +#include <math.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) @@ -99,6 +100,7 @@ struct stat_specs { enum stat_id ids[ALL_STATS_CNT]; enum stat_variant variants[ALL_STATS_CNT]; bool asc[ALL_STATS_CNT]; + bool abs[ALL_STATS_CNT]; int lens[ALL_STATS_CNT * 3]; /* 3x for comparison mode */ }; @@ -133,6 +135,7 @@ struct filter { int stat_id; enum stat_variant stat_var; long value; + bool abs; }; static struct env { @@ -142,10 +145,12 @@ static struct env { bool debug; bool quiet; bool force_checkpoints; + bool force_reg_invariants; enum resfmt out_fmt; bool show_version; bool comparison_mode; bool replay_mode; + int top_n; int log_level; int log_size; @@ -210,8 +215,7 @@ static const struct argp_option opts[] = { { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, - { "test-states", 't', NULL, 0, - "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, + { "top-n", 'n', "N", 0, "Emit only up to first N results." }, { "quiet", 'q', NULL, 0, "Quiet mode" }, { "emit", 'e', "SPEC", 0, "Specify stats to be emitted" }, { "sort", 's', "SPEC", 0, "Specify sort order" }, @@ -219,6 +223,10 @@ static const struct argp_option opts[] = { { "compare", 'C', NULL, 0, "Comparison mode" }, { "replay", 'R', NULL, 0, "Replay mode" }, { "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." }, + { "test-states", 't', NULL, 0, + "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, + { "test-reg-invariants", 'r', NULL, 0, + "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" }, {}, }; @@ -290,6 +298,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) case 't': env.force_checkpoints = true; break; + case 'r': + env.force_reg_invariants = true; + break; + case 'n': + errno = 0; + env.top_n = strtol(arg, NULL, 10); + if (errno) { + fprintf(stderr, "invalid top N specifier: %s\n", arg); + argp_usage(state); + } case 'C': env.comparison_mode = true; break; @@ -455,7 +473,8 @@ static struct { { OP_EQ, "=" }, }; -static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var); +static bool parse_stat_id_var(const char *name, size_t len, int *id, + enum stat_variant *var, bool *is_abs); static int append_filter(struct filter **filters, int *cnt, const char *str) { @@ -488,13 +507,14 @@ static int append_filter(struct filter **filters, int *cnt, const char *str) long val; const char *end = str; const char *op_str; + bool is_abs; op_str = operators[i].op_str; p = strstr(str, op_str); if (!p) continue; - if (!parse_stat_id_var(str, p - str, &id, &var)) { + if (!parse_stat_id_var(str, p - str, &id, &var, &is_abs)) { fprintf(stderr, "Unrecognized stat name in '%s'!\n", str); return -EINVAL; } @@ -533,6 +553,7 @@ static int append_filter(struct filter **filters, int *cnt, const char *str) f->stat_id = id; f->stat_var = var; f->op = operators[i].op_kind; + f->abs = true; f->value = val; *cnt += 1; @@ -657,7 +678,8 @@ static struct stat_def { [MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, }, }; -static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var) +static bool parse_stat_id_var(const char *name, size_t len, int *id, + enum stat_variant *var, bool *is_abs) { static const char *var_sfxs[] = { [VARIANT_A] = "_a", @@ -667,6 +689,14 @@ static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_v }; int i, j, k; + /* |<stat>| means we take absolute value of given stat */ + *is_abs = false; + if (len > 2 && name[0] == '|' && name[len - 1] == '|') { + *is_abs = true; + name += 1; + len -= 2; + } + for (i = 0; i < ARRAY_SIZE(stat_defs); i++) { struct stat_def *def = &stat_defs[i]; size_t alias_len, sfx_len; @@ -722,7 +752,7 @@ static bool is_desc_sym(char c) static int parse_stat(const char *stat_name, struct stat_specs *specs) { int id; - bool has_order = false, is_asc = false; + bool has_order = false, is_asc = false, is_abs = false; size_t len = strlen(stat_name); enum stat_variant var; @@ -737,7 +767,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs) len -= 1; } - if (!parse_stat_id_var(stat_name, len, &id, &var)) { + if (!parse_stat_id_var(stat_name, len, &id, &var, &is_abs)) { fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name); return -ESRCH; } @@ -745,6 +775,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs) specs->ids[specs->spec_cnt] = id; specs->variants[specs->spec_cnt] = var; specs->asc[specs->spec_cnt] = has_order ? is_asc : stat_defs[id].asc_by_default; + specs->abs[specs->spec_cnt] = is_abs; specs->spec_cnt++; return 0; @@ -997,6 +1028,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf if (env.force_checkpoints) bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); + if (env.force_reg_invariants) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS); err = bpf_object__load(obj); env.progs_processed++; @@ -1103,7 +1136,7 @@ cleanup: } static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2, - enum stat_id id, bool asc) + enum stat_id id, bool asc, bool abs) { int cmp = 0; @@ -1124,6 +1157,11 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2, long v1 = s1->stats[id]; long v2 = s2->stats[id]; + if (abs) { + v1 = v1 < 0 ? -v1 : v1; + v2 = v2 < 0 ? -v2 : v2; + } + if (v1 != v2) cmp = v1 < v2 ? -1 : 1; break; @@ -1142,7 +1180,8 @@ static int cmp_prog_stats(const void *v1, const void *v2) int i, cmp; for (i = 0; i < env.sort_spec.spec_cnt; i++) { - cmp = cmp_stat(s1, s2, env.sort_spec.ids[i], env.sort_spec.asc[i]); + cmp = cmp_stat(s1, s2, env.sort_spec.ids[i], + env.sort_spec.asc[i], env.sort_spec.abs[i]); if (cmp != 0) return cmp; } @@ -1211,7 +1250,8 @@ static void fetch_join_stat_value(const struct verif_stats_join *s, static int cmp_join_stat(const struct verif_stats_join *s1, const struct verif_stats_join *s2, - enum stat_id id, enum stat_variant var, bool asc) + enum stat_id id, enum stat_variant var, + bool asc, bool abs) { const char *str1 = NULL, *str2 = NULL; double v1, v2; @@ -1220,6 +1260,11 @@ static int cmp_join_stat(const struct verif_stats_join *s1, fetch_join_stat_value(s1, id, var, &str1, &v1); fetch_join_stat_value(s2, id, var, &str2, &v2); + if (abs) { + v1 = fabs(v1); + v2 = fabs(v2); + } + if (str1) cmp = strcmp(str1, str2); else if (v1 != v2) @@ -1237,7 +1282,8 @@ static int cmp_join_stats(const void *v1, const void *v2) cmp = cmp_join_stat(s1, s2, env.sort_spec.ids[i], env.sort_spec.variants[i], - env.sort_spec.asc[i]); + env.sort_spec.asc[i], + env.sort_spec.abs[i]); if (cmp != 0) return cmp; } @@ -1720,6 +1766,9 @@ static bool is_join_stat_filter_matched(struct filter *f, const struct verif_sta fetch_join_stat_value(stats, f->stat_id, f->stat_var, &str, &value); + if (f->abs) + value = fabs(value); + switch (f->op) { case OP_EQ: return value > f->value - eps && value < f->value + eps; case OP_NEQ: return value < f->value - eps || value > f->value + eps; @@ -1766,7 +1815,7 @@ static int handle_comparison_mode(void) struct stat_specs base_specs = {}, comp_specs = {}; struct stat_specs tmp_sort_spec; enum resfmt cur_fmt; - int err, i, j, last_idx; + int err, i, j, last_idx, cnt; if (env.filename_cnt != 2) { fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n\n"); @@ -1879,7 +1928,7 @@ static int handle_comparison_mode(void) env.join_stat_cnt += 1; } - /* now sort joined results accorsing to sort spec */ + /* now sort joined results according to sort spec */ qsort(env.join_stats, env.join_stat_cnt, sizeof(*env.join_stats), cmp_join_stats); /* for human-readable table output we need to do extra pass to @@ -1896,16 +1945,22 @@ one_more_time: output_comp_headers(cur_fmt); last_idx = -1; + cnt = 0; for (i = 0; i < env.join_stat_cnt; i++) { const struct verif_stats_join *join = &env.join_stats[i]; if (!should_output_join_stats(join)) continue; + if (env.top_n && cnt >= env.top_n) + break; + if (cur_fmt == RESFMT_TABLE_CALCLEN) last_idx = i; output_comp_stats(join, cur_fmt, i == last_idx); + + cnt++; } if (cur_fmt == RESFMT_TABLE_CALCLEN) { @@ -1920,6 +1975,9 @@ static bool is_stat_filter_matched(struct filter *f, const struct verif_stats *s { long value = stats->stats[f->stat_id]; + if (f->abs) + value = value < 0 ? -value : value; + switch (f->op) { case OP_EQ: return value == f->value; case OP_NEQ: return value != f->value; @@ -1964,7 +2022,7 @@ static bool should_output_stats(const struct verif_stats *stats) static void output_prog_stats(void) { const struct verif_stats *stats; - int i, last_stat_idx = 0; + int i, last_stat_idx = 0, cnt = 0; if (env.out_fmt == RESFMT_TABLE) { /* calculate column widths */ @@ -1984,7 +2042,10 @@ static void output_prog_stats(void) stats = &env.prog_stats[i]; if (!should_output_stats(stats)) continue; + if (env.top_n && cnt >= env.top_n) + break; output_stats(stats, env.out_fmt, i == last_stat_idx); + cnt++; } } diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 685034528018..65d14f3bbe30 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -36,7 +36,9 @@ DEFAULT_COMMAND="./test_progs" MOUNT_DIR="mnt" ROOTFS_IMAGE="root.img" OUTPUT_DIR="$HOME/.bpf_selftests" -KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config" "tools/testing/selftests/bpf/config.${ARCH}") +KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config" + "tools/testing/selftests/bpf/config.vm" + "tools/testing/selftests/bpf/config.${ARCH}") INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX" NUM_COMPILE_JOBS="$(nproc)" LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")" diff --git a/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh new file mode 100755 index 000000000000..fe0343b95e6c --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh @@ -0,0 +1,58 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that PCI reset works correctly by verifying that only the expected reset +# methods are supported and that after issuing the reset the ifindex of the +# port changes. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + pci_reset_test +" +NUM_NETIFS=1 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +pci_reset_test() +{ + RET=0 + + local bus=$(echo $DEVLINK_DEV | cut -d '/' -f 1) + local bdf=$(echo $DEVLINK_DEV | cut -d '/' -f 2) + + if [ $bus != "pci" ]; then + check_err 1 "devlink device is not a PCI device" + log_test "pci reset" + return + fi + + if [ ! -f /sys/bus/pci/devices/$bdf/reset_method ]; then + check_err 1 "reset is not supported" + log_test "pci reset" + return + fi + + [[ $(cat /sys/bus/pci/devices/$bdf/reset_method) == "bus" ]] + check_err $? "only \"bus\" reset method should be supported" + + local ifindex_pre=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]') + + echo 1 > /sys/bus/pci/devices/$bdf/reset + check_err $? "reset failed" + + # Wait for udev to rename newly created netdev. + udevadm settle + + local ifindex_post=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]') + + [[ $ifindex_pre != $ifindex_post ]] + check_err $? "reset not performed" + + log_test "pci reset" +} + +swp1=${NETIFS[p1]} +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5b2aca4c5f10..9274edfb76ff 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -91,6 +91,7 @@ TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh +TEST_PROGS += fq_band_pktlimit.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 6ff3e732f449..c79e65581dc3 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -45,11 +45,13 @@ struct options { const char *host; const char *service; unsigned int size; + unsigned int num_pkt; struct { unsigned int mark; unsigned int dontfrag; unsigned int tclass; unsigned int hlimit; + unsigned int priority; } sockopt; struct { unsigned int family; @@ -72,6 +74,7 @@ struct options { } v6; } opt = { .size = 13, + .num_pkt = 1, .sock = { .family = AF_UNSPEC, .type = SOCK_DGRAM, @@ -112,7 +115,7 @@ static void cs_parse_args(int argc, char *argv[]) { int o; - while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) { + while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) { switch (o) { case 's': opt.silent_send = true; @@ -138,7 +141,9 @@ static void cs_parse_args(int argc, char *argv[]) cs_usage(argv[0]); } break; - + case 'P': + opt.sockopt.priority = atoi(optarg); + break; case 'm': opt.mark.ena = true; opt.mark.val = atoi(optarg); @@ -146,6 +151,9 @@ static void cs_parse_args(int argc, char *argv[]) case 'M': opt.sockopt.mark = atoi(optarg); break; + case 'n': + opt.num_pkt = atoi(optarg); + break; case 'd': opt.txtime.ena = true; opt.txtime.delay = atoi(optarg); @@ -410,6 +418,10 @@ static void ca_set_sockopts(int fd) setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); + if (opt.sockopt.priority && + setsockopt(fd, SOL_SOCKET, SO_PRIORITY, + &opt.sockopt.priority, sizeof(opt.sockopt.priority))) + error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY"); } int main(int argc, char *argv[]) @@ -421,6 +433,7 @@ int main(int argc, char *argv[]) char cbuf[1024]; int err; int fd; + int i; cs_parse_args(argc, argv); @@ -480,24 +493,27 @@ int main(int argc, char *argv[]) cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); - err = sendmsg(fd, &msg, 0); - if (err < 0) { - if (!opt.silent_send) - fprintf(stderr, "send failed: %s\n", strerror(errno)); - err = ERN_SEND; - goto err_out; - } else if (err != (int)opt.size) { - fprintf(stderr, "short send\n"); - err = ERN_SEND_SHORT; - goto err_out; - } else { - err = ERN_SUCCESS; + for (i = 0; i < opt.num_pkt; i++) { + err = sendmsg(fd, &msg, 0); + if (err < 0) { + if (!opt.silent_send) + fprintf(stderr, "send failed: %s\n", strerror(errno)); + err = ERN_SEND; + goto err_out; + } else if (err != (int)opt.size) { + fprintf(stderr, "short send\n"); + err = ERN_SEND_SHORT; + goto err_out; + } } + err = ERN_SUCCESS; - /* Make sure all timestamps have time to loop back */ - usleep(opt.txtime.delay); + if (opt.ts.ena) { + /* Make sure all timestamps have time to loop back */ + usleep(opt.txtime.delay); - cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + } err_out: close(fd); diff --git a/tools/testing/selftests/net/fq_band_pktlimit.sh b/tools/testing/selftests/net/fq_band_pktlimit.sh new file mode 100755 index 000000000000..24b77bdf41ff --- /dev/null +++ b/tools/testing/selftests/net/fq_band_pktlimit.sh @@ -0,0 +1,57 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Verify that FQ has a packet limit per band: +# +# 1. set the limit to 10 per band +# 2. send 20 pkts on band A: verify that 10 are queued, 10 dropped +# 3. send 20 pkts on band A: verify that 0 are queued, 20 dropped +# 4. send 20 pkts on band B: verify that 10 are queued, 10 dropped +# +# Send packets with a 100ms delay to ensure that previously sent +# packets are still queued when later ones are sent. +# Use SO_TXTIME for this. + +die() { + echo "$1" + exit 1 +} + +# run inside private netns +if [[ $# -eq 0 ]]; then + ./in_netns.sh "$0" __subprocess + exit +fi + +ip link add type dummy +ip link set dev dummy0 up +ip -6 addr add fdaa::1/128 dev dummy0 +ip -6 route add fdaa::/64 dev dummy0 +tc qdisc replace dev dummy0 root handle 1: fq quantum 1514 initial_quantum 1514 limit 10 + +./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +OUT1="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +./cmsg_sender -6 -p u -d 100000 -n 20 fdaa::2 8000 +OUT2="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +./cmsg_sender -6 -p u -d 100000 -n 20 -P 7 fdaa::2 8000 +OUT3="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +# Initial stats will report zero sent, as all packets are still +# queued in FQ. Sleep for the delay period (100ms) and see that +# twenty are now sent. +sleep 0.1 +OUT4="$(tc -s qdisc show dev dummy0 | grep '^\ Sent')" + +# Log the output after the test +echo "${OUT1}" +echo "${OUT2}" +echo "${OUT3}" +echo "${OUT4}" + +# Test the output for expected values +echo "${OUT1}" | grep -q '0\ pkt\ (dropped\ 10' || die "unexpected drop count at 1" +echo "${OUT2}" | grep -q '0\ pkt\ (dropped\ 30' || die "unexpected drop count at 2" +echo "${OUT3}" | grep -q '0\ pkt\ (dropped\ 40' || die "unexpected drop count at 3" +echo "${OUT4}" | grep -q '20\ pkt\ (dropped\ 40' || die "unexpected accept count at 4" diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 85a8ee9395b3..95b498efacd1 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -182,23 +182,6 @@ chk_msk_inuse() __chk_nr get_msk_inuse $expected "$msg" 0 } -# $1: ns, $2: port -wait_local_port_listen() -{ - local listener_ns="${1}" - local port="${2}" - - local port_hex i - - port_hex="$(printf "%04X" "${port}")" - for i in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done -} - wait_connected() { local listener_ns="${1}" @@ -222,7 +205,7 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \ 0.0.0.0 >/dev/null & -wait_local_port_listen $ns 10000 +mptcp_lib_wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation" chk_msk_listen 10000 @@ -245,7 +228,7 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \ 0.0.0.0 >/dev/null & -wait_local_port_listen $ns 10001 +mptcp_lib_wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ @@ -266,7 +249,7 @@ for I in `seq 1 $NR_CLIENTS`; do ./mptcp_connect -p $((I+10001)) -l -w 20 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done -wait_local_port_listen $ns $((NR_CLIENTS + 10001)) +mptcp_lib_wait_local_port_listen $ns $((NR_CLIENTS + 10001)) for I in `seq 1 $NR_CLIENTS`; do echo "b" | \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index b1fc8afd072d..7898d62fce0b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -254,31 +254,6 @@ else set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args" fi -print_file_err() -{ - ls -l "$1" 1>&2 - echo "Trailing bytes are: " - tail -c 27 "$1" -} - -check_transfer() -{ - local in=$1 - local out=$2 - local what=$3 - - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then - echo "[ FAIL ] $what does not match (in, out):" - print_file_err "$in" - print_file_err "$out" - - return 1 - fi - - return 0 -} - check_mptcp_disabled() { local disabled_ns="ns_disabled-$rndh" @@ -310,12 +285,6 @@ check_mptcp_disabled() return 0 } -# $1: IP address -is_v6() -{ - [ -z "${1##*:*}" ] -} - do_ping() { local listener_ns="$1" @@ -324,7 +293,7 @@ do_ping() local ping_args="-q -c 1" local rc=0 - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then $ipv6 || return 0 ping_args="${ping_args} -6" fi @@ -341,38 +310,6 @@ do_ping() return 0 } -# $1: ns, $2: MIB counter -get_mib_counter() -{ - local listener_ns="${1}" - local mib="${2}" - - # strip the header - ip netns exec "${listener_ns}" \ - nstat -z -a "${mib}" | \ - tail -n+2 | \ - while read a count c rest; do - echo $count - done -} - -# $1: ns, $2: port -wait_local_port_listen() -{ - local listener_ns="${1}" - local port="${2}" - - local port_hex i - - port_hex="$(printf "%04X" "${port}")" - for i in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done -} - do_transfer() { local listener_ns="$1" @@ -441,12 +378,12 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -454,7 +391,7 @@ do_transfer() $extra_args $local_addr < "$sin" > "$sout" & local spid=$! - wait_local_port_listen "${listener_ns}" "${port}" + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start start=$(date +%s%3N) @@ -504,16 +441,16 @@ do_transfer() return 1 fi - check_transfer $sin $cout "file received by client" + mptcp_lib_check_transfer $sin $cout "file received by client" retc=$? - check_transfer $cin $sout "file received by server" + mptcp_lib_check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -542,8 +479,8 @@ do_transfer() fi if $checksum; then - local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) if [ $csum_err_s_nr -gt 0 ]; then @@ -613,9 +550,8 @@ make_file() ksize=$((SIZE / 1024)) rem=$((SIZE - (ksize * 1024))) - dd if=/dev/urandom of="$name" bs=1024 count=$ksize 2> /dev/null - dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$rem 2> /dev/null - echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + mptcp_lib_make_file $name 1024 $ksize + dd if=/dev/urandom conv=notrunc of="$name" oflag=append bs=1 count=$rem 2> /dev/null echo "Created $name (size $(du -b "$name")) containing data sent by $who" } @@ -635,12 +571,12 @@ run_tests_lo() fi # skip if we don't want v6 - if ! $ipv6 && is_v6 "${connect_addr}"; then + if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then return 0 fi local local_addr - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then local_addr="::" else local_addr="0.0.0.0" @@ -708,7 +644,7 @@ run_test_transparent() TEST_GROUP="${msg}" # skip if we don't want v6 - if ! $ipv6 && is_v6 "${connect_addr}"; then + if ! $ipv6 && mptcp_lib_is_v6 "${connect_addr}"; then return 0 fi @@ -741,7 +677,7 @@ EOF fi local local_addr - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then local_addr="::" r6flag="-6" else diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c94f2f194d6..8362ea454af3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -511,13 +511,6 @@ get_failed_tests_ids() done | sort -n } -print_file_err() -{ - ls -l "$1" 1>&2 - echo -n "Trailing bytes are: " - tail -c 27 "$1" -} - check_transfer() { local in=$1 @@ -548,8 +541,8 @@ check_transfer() local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then fail_test "$what does not match (in, out):" - print_file_err "$in" - print_file_err "$out" + mptcp_lib_print_file_err "$in" + mptcp_lib_print_file_err "$out" return 1 else @@ -587,49 +580,9 @@ link_failure() done } -# $1: IP address -is_v6() -{ - [ -z "${1##*:*}" ] -} - -# $1: ns, $2: port -wait_local_port_listen() -{ - local listener_ns="${1}" - local port="${2}" - - local port_hex - port_hex="$(printf "%04X" "${port}")" - - local i - for i in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done -} - -# $1: ns ; $2: counter -get_counter() -{ - local ns="${1}" - local counter="${2}" - local count - - count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') - if [ -z "${count}" ]; then - mptcp_lib_fail_if_expected_feature "${counter} counter" - return 1 - fi - - echo "${count}" -} - rm_addr_count() { - get_counter "${1}" "MPTcpExtRmAddr" + mptcp_lib_get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -649,7 +602,7 @@ wait_rm_addr() rm_sf_count() { - get_counter "${1}" "MPTcpExtRmSubflow" + mptcp_lib_get_counter "${1}" "MPTcpExtRmSubflow" } # $1: ns, $2: old rm_sf counter in $ns @@ -672,26 +625,20 @@ wait_mpj() local ns="${1}" local cnt old_cnt - old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + old_cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") + cnt=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done } -kill_wait() -{ - kill $1 > /dev/null 2>&1 - wait $1 2>/dev/null -} - kill_events_pids() { - kill_wait $evts_ns1_pid - kill_wait $evts_ns2_pid + mptcp_lib_kill_wait $evts_ns1_pid + mptcp_lib_kill_wait $evts_ns2_pid } kill_tests_wait() @@ -901,7 +848,7 @@ pm_nl_set_endpoint() local id=10 while [ $add_nr_ns1 -gt 0 ]; do local addr - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then addr="dead:beef:$counter::1" else addr="10.0.$counter.1" @@ -953,7 +900,7 @@ pm_nl_set_endpoint() local id=20 while [ $add_nr_ns2 -gt 0 ]; do local addr - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then addr="dead:beef:$counter::2" else addr="10.0.$counter.2" @@ -995,7 +942,7 @@ pm_nl_set_endpoint() pm_nl_flush_endpoint ${connector_ns} elif [ $rm_nr_ns2 -eq 9 ]; then local addr - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then addr="dead:beef:1::2" else addr="10.0.1.2" @@ -1117,7 +1064,7 @@ do_transfer() fi local spid=$! - wait_local_port_listen "${listener_ns}" "${port}" + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" extra_cl_args="$extra_args $extra_cl_args" if [ "$test_linkfail" -eq 0 ];then @@ -1199,8 +1146,7 @@ make_file() local who=$2 local size=$3 - dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null - echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + mptcp_lib_make_file $name 1024 $size print_info "Test file (size $size KB) for $who" } @@ -1284,7 +1230,7 @@ chk_csum_nr() fi print_check "sum" - count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi @@ -1297,7 +1243,7 @@ chk_csum_nr() print_ok fi print_check "csum" - count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi @@ -1341,7 +1287,7 @@ chk_fail_nr() fi print_check "ftx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi @@ -1355,7 +1301,7 @@ chk_fail_nr() fi print_check "failrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi @@ -1388,7 +1334,7 @@ chk_fclose_nr() fi print_check "ctx" - count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_tx" ]; then @@ -1399,7 +1345,7 @@ chk_fclose_nr() fi print_check "fclzrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_rx" ]; then @@ -1429,7 +1375,7 @@ chk_rst_nr() fi print_check "rtx" - count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1441,7 +1387,7 @@ chk_rst_nr() fi print_check "rstrx" - count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx") if [ -z "$count" ]; then print_skip # accept more rst than expected except if we don't expect any @@ -1462,7 +1408,7 @@ chk_infi_nr() local count print_check "itx" - count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_tx" ]; then @@ -1472,7 +1418,7 @@ chk_infi_nr() fi print_check "infirx" - count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$infi_rx" ]; then @@ -1501,7 +1447,7 @@ chk_join_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1512,7 +1458,7 @@ chk_join_nr() print_check "synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1529,7 +1475,7 @@ chk_join_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1562,8 +1508,8 @@ chk_stale_nr() print_check "stale" - stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") - recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + stale_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(mptcp_lib_get_counter ${ns} "MPTcpExtSubflowRecover") if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then print_skip elif [ $stale_nr -lt $stale_min ] || @@ -1600,7 +1546,7 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add" - count=$(get_counter ${ns2} "MPTcpExtAddAddr") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1612,7 +1558,7 @@ chk_add_nr() fi print_check "echo" - count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_nr" ]; then @@ -1623,7 +1569,7 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then print_check "pt" - count=$(get_counter ${ns2} "MPTcpExtPortAdd") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$port_nr" ]; then @@ -1633,7 +1579,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1644,7 +1590,7 @@ chk_add_nr() fi print_check "synack" - count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1655,7 +1601,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1666,7 +1612,7 @@ chk_add_nr() fi print_check "syn" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_syn_nr" ]; then @@ -1677,7 +1623,7 @@ chk_add_nr() fi print_check "ack" - count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_ack_nr" ]; then @@ -1699,7 +1645,7 @@ chk_add_tx_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) print_check "add TX" - count=$(get_counter ${ns1} "MPTcpExtAddAddrTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1711,7 +1657,7 @@ chk_add_tx_nr() fi print_check "echo TX" - count=$(get_counter ${ns2} "MPTcpExtEchoAddTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtEchoAddTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_tx_nr" ]; then @@ -1749,7 +1695,7 @@ chk_rm_nr() fi print_check "rm" - count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_nr" ]; then @@ -1759,13 +1705,13 @@ chk_rm_nr() fi print_check "rmsf" - count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow") if [ -z "$count" ]; then print_skip elif [ -n "$simult" ]; then local cnt suffix - cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") + cnt=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable @@ -1794,7 +1740,7 @@ chk_rm_tx_nr() local rm_addr_tx_nr=$1 print_check "rm TX" - count=$(get_counter ${ns2} "MPTcpExtRmAddrTx") + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$rm_addr_tx_nr" ]; then @@ -1811,7 +1757,7 @@ chk_prio_nr() local count print_check "ptx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_tx" ]; then @@ -1821,7 +1767,7 @@ chk_prio_nr() fi print_check "prx" - count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mp_prio_nr_rx" ]; then @@ -1867,12 +1813,10 @@ chk_mptcp_info() local cnt2 local dump_stats - print_check "mptcp_info ${info1:0:8}=$exp1:$exp2" + print_check "mptcp_info ${info1:0:15}=$exp1:$exp2" - cnt1=$(ss -N $ns1 -inmHM | grep "$info1:" | - sed -n 's/.*\('"$info1"':\)\([[:digit:]]*\).*$/\2/p;q') - cnt2=$(ss -N $ns2 -inmHM | grep "$info2:" | - sed -n 's/.*\('"$info2"':\)\([[:digit:]]*\).*$/\2/p;q') + cnt1=$(ss -N $ns1 -inmHM | mptcp_lib_get_info_value "$info1" "$info1") + cnt2=$(ss -N $ns2 -inmHM | mptcp_lib_get_info_value "$info2" "$info2") # 'ss' only display active connections and counters that are not 0. [ -z "$cnt1" ] && cnt1=0 [ -z "$cnt2" ] && cnt2=0 @@ -1890,6 +1834,42 @@ chk_mptcp_info() fi } +# $1: subflows in ns1 ; $2: subflows in ns2 +# number of all subflows, including the initial subflow. +chk_subflows_total() +{ + local cnt1 + local cnt2 + local info="subflows_total" + local dump_stats + + # if subflows_total counter is supported, use it: + if [ -n "$(ss -N $ns1 -inmHM | mptcp_lib_get_info_value $info $info)" ]; then + chk_mptcp_info $info $1 $info $2 + return + fi + + print_check "$info $1:$2" + + # if not, count the TCP connections that are in fact MPTCP subflows + cnt1=$(ss -N $ns1 -ti state established state syn-sent state syn-recv | + grep -c tcp-ulp-mptcp) + cnt2=$(ss -N $ns2 -ti state established state syn-sent state syn-recv | + grep -c tcp-ulp-mptcp) + + if [ "$1" != "$cnt1" ] || [ "$2" != "$cnt2" ]; then + fail_test "got subflows $cnt1:$cnt2 expected $1:$2" + dump_stats=1 + else + print_ok + fi + + if [ "$dump_stats" = 1 ]; then + ss -N $ns1 -ti + ss -N $ns2 -ti + fi +} + chk_link_usage() { local ns=$1 @@ -1921,7 +1901,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(get_counter ${ns} "TcpAttemptFails") + cnt=$(mptcp_lib_get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -2814,6 +2794,7 @@ backup_tests() fi } +SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED LISTENER_CREATED=15 #MPTCP_EVENT_LISTENER_CREATED LISTENER_CLOSED=16 #MPTCP_EVENT_LISTENER_CLOSED @@ -2848,13 +2829,13 @@ verify_listener_events() return fi - type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + type=$(mptcp_lib_evts_get_info type "$evt" "$e_type") + family=$(mptcp_lib_evts_get_info family "$evt" "$e_type") + sport=$(mptcp_lib_evts_get_info sport "$evt" "$e_type") if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" "$e_type") else - saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" "$e_type") fi if [ $type ] && [ $type = $e_type ] && @@ -3249,8 +3230,7 @@ fastclose_tests() pedit_action_pkts() { tc -n $ns2 -j -s action show action pedit index 100 | \ - grep "packets" | \ - sed 's/.*"packets":\([0-9]\+\),.*/\1/' + mptcp_lib_get_info_value \"packets\" packets } fail_tests() @@ -3275,75 +3255,70 @@ fail_tests() fi } +# $1: ns ; $2: addr ; $3: id userspace_pm_add_addr() { - local addr=$1 - local id=$2 + local evts=$evts_ns1 local tk - tk=$(grep "type:1," "$evts_ns1" | - sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') - ip netns exec $ns1 ./pm_nl_ctl ann $addr token $tk id $id + [ "$1" == "$ns2" ] && evts=$evts_ns2 + tk=$(mptcp_lib_evts_get_info token "$evts") + + ip netns exec $1 ./pm_nl_ctl ann $2 token $tk id $3 sleep 1 } -userspace_pm_rm_sf_addr_ns1() +# $1: ns ; $2: id +userspace_pm_rm_addr() { - local addr=$1 - local id=$2 - local tk sp da dp - local cnt_addr cnt_sf - - tk=$(grep "type:1," "$evts_ns1" | - sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') - sp=$(grep "type:10" "$evts_ns1" | - sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') - da=$(grep "type:10" "$evts_ns1" | - sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') - dp=$(grep "type:10" "$evts_ns1" | - sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') - cnt_addr=$(rm_addr_count ${ns1}) - cnt_sf=$(rm_sf_count ${ns1}) - ip netns exec $ns1 ./pm_nl_ctl rem token $tk id $id - ip netns exec $ns1 ./pm_nl_ctl dsf lip "::ffff:$addr" \ - lport $sp rip $da rport $dp token $tk - wait_rm_addr $ns1 "${cnt_addr}" - wait_rm_sf $ns1 "${cnt_sf}" + local evts=$evts_ns1 + local tk + local cnt + + [ "$1" == "$ns2" ] && evts=$evts_ns2 + tk=$(mptcp_lib_evts_get_info token "$evts") + + cnt=$(rm_addr_count ${1}) + ip netns exec $1 ./pm_nl_ctl rem token $tk id $2 + wait_rm_addr $1 "${cnt}" } +# $1: ns ; $2: addr ; $3: id userspace_pm_add_sf() { - local addr=$1 - local id=$2 + local evts=$evts_ns1 local tk da dp - tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") - dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - ip netns exec $ns2 ./pm_nl_ctl csf lip $addr lid $id \ + [ "$1" == "$ns2" ] && evts=$evts_ns2 + tk=$(mptcp_lib_evts_get_info token "$evts") + da=$(mptcp_lib_evts_get_info daddr4 "$evts") + dp=$(mptcp_lib_evts_get_info dport "$evts") + + ip netns exec $1 ./pm_nl_ctl csf lip $2 lid $3 \ rip $da rport $dp token $tk sleep 1 } -userspace_pm_rm_sf_addr_ns2() +# $1: ns ; $2: addr $3: event type +userspace_pm_rm_sf() { - local addr=$1 - local id=$2 + local evts=$evts_ns1 + local t=${3:-1} + local ip=4 local tk da dp sp - local cnt_addr cnt_sf - - tk=$(sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - da=$(sed -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evts_ns2") - dp=$(sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evts_ns2") - sp=$(grep "type:10" "$evts_ns2" | - sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') - cnt_addr=$(rm_addr_count ${ns2}) - cnt_sf=$(rm_sf_count ${ns2}) - ip netns exec $ns2 ./pm_nl_ctl rem token $tk id $id - ip netns exec $ns2 ./pm_nl_ctl dsf lip $addr lport $sp \ + local cnt + + [ "$1" == "$ns2" ] && evts=$evts_ns2 + if mptcp_lib_is_v6 $2; then ip=6; fi + tk=$(mptcp_lib_evts_get_info token "$evts") + da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t) + dp=$(mptcp_lib_evts_get_info dport "$evts" $t) + sp=$(mptcp_lib_evts_get_info sport "$evts" $t) + + cnt=$(rm_sf_count ${1}) + ip netns exec $1 ./pm_nl_ctl dsf lip $2 lport $sp \ rip $da rport $dp token $tk - wait_rm_addr $ns2 "${cnt_addr}" - wait_rm_sf $ns2 "${cnt_sf}" + wait_rm_sf $1 "${cnt}" } userspace_tests() @@ -3430,14 +3405,17 @@ userspace_tests() run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! wait_mpj $ns1 - userspace_pm_add_addr 10.0.2.1 10 + userspace_pm_add_addr $ns1 10.0.2.1 10 chk_join_nr 1 1 1 chk_add_nr 1 1 chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 - userspace_pm_rm_sf_addr_ns1 10.0.2.1 10 + userspace_pm_rm_addr $ns1 10 + userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED chk_rm_nr 1 1 invert chk_mptcp_info subflows 0 subflows 0 + chk_subflows_total 1 1 kill_events_pids wait $tests_pid fi @@ -3451,12 +3429,84 @@ userspace_tests() run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! wait_mpj $ns2 - userspace_pm_add_sf 10.0.3.2 20 + userspace_pm_add_sf $ns2 10.0.3.2 20 chk_join_nr 1 1 1 chk_mptcp_info subflows 1 subflows 1 - userspace_pm_rm_sf_addr_ns2 10.0.3.2 20 + chk_subflows_total 2 2 + userspace_pm_rm_addr $ns2 20 + userspace_pm_rm_sf $ns2 10.0.3.2 $SUB_ESTABLISHED chk_rm_nr 1 1 chk_mptcp_info subflows 0 subflows 0 + chk_subflows_total 1 1 + kill_events_pids + wait $tests_pid + fi + + # userspace pm create id 0 subflow + if reset_with_events "userspace pm create id 0 subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 1 + speed=5 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + wait_mpj $ns2 + chk_mptcp_info subflows 0 subflows 0 + chk_subflows_total 1 1 + userspace_pm_add_sf $ns2 10.0.3.2 0 + chk_join_nr 1 1 1 + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 + kill_events_pids + wait $tests_pid + fi + + # userspace pm remove initial subflow + if reset_with_events "userspace pm remove initial subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 1 + speed=5 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + wait_mpj $ns2 + userspace_pm_add_sf $ns2 10.0.3.2 20 + chk_join_nr 1 1 1 + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 + userspace_pm_rm_sf $ns2 10.0.1.2 + # we don't look at the counter linked to the RM_ADDR but + # to the one linked to the subflows that have been removed + chk_rm_nr 0 1 + chk_rst_nr 0 0 invert + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 1 1 + kill_events_pids + wait $tests_pid + fi + + # userspace pm send RM_ADDR for ID 0 + if reset_with_events "userspace pm send RM_ADDR for ID 0" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns2 1 1 + speed=5 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + wait_mpj $ns1 + userspace_pm_add_addr $ns1 10.0.2.1 10 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 2 2 + chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 + userspace_pm_rm_addr $ns1 0 + # we don't look at the counter linked to the subflows that + # have been removed but to the one linked to the RM_ADDR + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 invert + chk_mptcp_info subflows 1 subflows 1 + chk_subflows_total 1 1 kill_events_pids wait $tests_pid fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 92a5befe8039..022262a2cfe0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -207,3 +207,94 @@ mptcp_lib_result_print_all_tap() { printf "%s\n" "${subtest}" done } + +# get the value of keyword $1 in the line marked by keyword $2 +mptcp_lib_get_info_value() { + grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q' +} + +# $1: info name ; $2: evts_ns ; $3: event type +mptcp_lib_evts_get_info() { + mptcp_lib_get_info_value "${1}" "^type:${3:-1}," < "${2}" +} + +# $1: PID +mptcp_lib_kill_wait() { + [ "${1}" -eq 0 ] && return 0 + + kill -SIGUSR1 "${1}" > /dev/null 2>&1 + kill "${1}" > /dev/null 2>&1 + wait "${1}" 2>/dev/null +} + +# $1: IP address +mptcp_lib_is_v6() { + [ -z "${1##*:*}" ] +} + +# $1: ns, $2: MIB counter +mptcp_lib_get_counter() { + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +mptcp_lib_make_file() { + local name="${1}" + local bs="${2}" + local size="${3}" + + dd if=/dev/urandom of="${name}" bs="${bs}" count="${size}" 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "${name}" +} + +# $1: file +mptcp_lib_print_file_err() { + ls -l "${1}" 1>&2 + echo "Trailing bytes are: " + tail -c 27 "${1}" +} + +# $1: input file ; $2: output file ; $3: what kind of file +mptcp_lib_check_transfer() { + local in="${1}" + local out="${2}" + local what="${3}" + + if ! cmp "$in" "$out" > /dev/null 2>&1; then + echo "[ FAIL ] $what does not match (in, out):" + mptcp_lib_print_file_err "$in" + mptcp_lib_print_file_err "$out" + + return 1 + fi + + return 0 +} + +# $1: ns, $2: port +mptcp_lib_wait_local_port_listen() { + local listener_ns="${1}" + local port="${2}" + + local port_hex + port_hex="$(printf "%04X" "${port}")" + + local _ + for _ in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) \ + {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index a817af6616ec..c643872ddf47 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -135,38 +135,6 @@ check_mark() return 0 } -print_file_err() -{ - ls -l "$1" 1>&2 - echo "Trailing bytes are: " - tail -c 27 "$1" -} - -check_transfer() -{ - local in=$1 - local out=$2 - local what=$3 - - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then - echo "[ FAIL ] $what does not match (in, out):" - print_file_err "$in" - print_file_err "$out" - ret=1 - - return 1 - fi - - return 0 -} - -# $1: IP address -is_v6() -{ - [ -z "${1##*:*}" ] -} - do_transfer() { local listener_ns="$1" @@ -183,7 +151,7 @@ do_transfer() local mptcp_connect="./mptcp_connect -r 20" local local_addr ip - if is_v6 "${connect_addr}"; then + if mptcp_lib_is_v6 "${connect_addr}"; then local_addr="::" ip=ipv6 else @@ -238,7 +206,7 @@ do_transfer() check_mark $connector_ns 4 || retc=1 fi - check_transfer $cin $sout "file received by server" + mptcp_lib_check_transfer $cin $sout "file received by server" rets=$? mptcp_lib_result_code "${retc}" "mark ${ip}" @@ -257,8 +225,7 @@ make_file() local who=$2 local size=$3 - dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null - echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + mptcp_lib_make_file $name 1024 $size echo "Created $name (size $size KB) containing data sent by $who" } diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ce9203b817f8..ae8ad5d6fb9d 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -123,23 +123,6 @@ setup() grep -q ' kmemleak_init$\| lockdep_init$\| kasan_init$\| prove_locking$' /proc/kallsyms && slack=$((slack+550)) } -# $1: ns, $2: port -wait_local_port_listen() -{ - local listener_ns="${1}" - local port="${2}" - - local port_hex i - - port_hex="$(printf "%04X" "${port}")" - for i in $(seq 10); do - ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ - awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && - break - sleep 0.1 - done -} - do_transfer() { local cin=$1 @@ -179,7 +162,7 @@ do_transfer() 0.0.0.0 < "$sin" > "$sout" & local spid=$! - wait_local_port_listen "${ns3}" "${port}" + mptcp_lib_wait_local_port_listen "${ns3}" "${port}" timeout ${timeout_test} \ ip netns exec ${ns1} \ diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b25a3e33eb25..6167837f48e1 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -108,15 +108,6 @@ test_fail() mptcp_lib_result_fail "${test_name}" } -kill_wait() -{ - [ $1 -eq 0 ] && return 0 - - kill -SIGUSR1 $1 > /dev/null 2>&1 - kill $1 > /dev/null 2>&1 - wait $1 2>/dev/null -} - # This function is used in the cleanup trap #shellcheck disable=SC2317 cleanup() @@ -128,7 +119,7 @@ cleanup() for pid in $client4_pid $server4_pid $client6_pid $server6_pid\ $server_evts_pid $client_evts_pid do - kill_wait $pid + mptcp_lib_kill_wait $pid done local netns @@ -173,22 +164,12 @@ print_title "Init" print_test "Created network namespaces ns1, ns2" test_pass -make_file() -{ - # Store a chunk of data in a file to transmit over an MPTCP connection - local name=$1 - local ksize=1 - - dd if=/dev/urandom of="$name" bs=2 count=$ksize 2> /dev/null - echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" -} - make_connection() { if [ -z "$file" ]; then file=$(mktemp) fi - make_file "$file" "client" + mptcp_lib_make_file "$file" 2 1 local is_v6=$1 local app_port=$app4_port @@ -210,7 +191,7 @@ make_connection() fi :>"$client_evts" if [ $client_evts_pid -ne 0 ]; then - kill_wait $client_evts_pid + mptcp_lib_kill_wait $client_evts_pid fi ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & client_evts_pid=$! @@ -219,7 +200,7 @@ make_connection() fi :>"$server_evts" if [ $server_evts_pid -ne 0 ]; then - kill_wait $server_evts_pid + mptcp_lib_kill_wait $server_evts_pid fi ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 & server_evts_pid=$! @@ -247,14 +228,11 @@ make_connection() local server_token local server_serverside - client_token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") - client_port=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") - client_serverside=$(sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q'\ - "$client_evts") - server_token=$(grep "type:1," "$server_evts" | - sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') - server_serverside=$(grep "type:1," "$server_evts" | - sed --unbuffered -n 's/.*\(server_side:\)\([[:digit:]]*\).*$/\2/p;q') + client_token=$(mptcp_lib_evts_get_info token "$client_evts") + client_port=$(mptcp_lib_evts_get_info sport "$client_evts") + client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts") + server_token=$(mptcp_lib_evts_get_info token "$server_evts") + server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts") print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && @@ -340,16 +318,16 @@ verify_announce_event() local dport local id - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + type=$(mptcp_lib_evts_get_info type "$evt" $e_type) + token=$(mptcp_lib_evts_get_info token "$evt" $e_type) if [ "$e_af" = "v6" ] then - addr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") + addr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type) else - addr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") + addr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type) fi - dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type) + id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type) check_expected "type" "token" "addr" "dport" "id" } @@ -367,7 +345,7 @@ test_announce() $client_addr_id dev ns2eth1 > /dev/null 2>&1 local type - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + type=$(mptcp_lib_evts_get_info type "$server_evts") print_test "ADD_ADDR 10.0.2.2 (ns2) => ns1, invalid token" if [ "$type" = "" ] then @@ -446,9 +424,9 @@ verify_remove_event() local token local id - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - id=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + type=$(mptcp_lib_evts_get_info type "$evt" $e_type) + token=$(mptcp_lib_evts_get_info token "$evt" $e_type) + id=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type) check_expected "type" "token" "id" } @@ -466,7 +444,7 @@ test_remove() $client_addr_id > /dev/null 2>&1 print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token" local type - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] then test_pass @@ -479,7 +457,7 @@ test_remove() ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $invalid_id > /dev/null 2>&1 print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id" - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] then test_pass @@ -583,19 +561,19 @@ verify_subflow_events() fi fi - type=$(sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - token=$(sed --unbuffered -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - family=$(sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - dport=$(sed --unbuffered -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - locid=$(sed --unbuffered -n 's/.*\(loc_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") - remid=$(sed --unbuffered -n 's/.*\(rem_id:\)\([[:digit:]]*\).*$/\2/p;q' "$evt") + type=$(mptcp_lib_evts_get_info type "$evt" $e_type) + token=$(mptcp_lib_evts_get_info token "$evt" $e_type) + family=$(mptcp_lib_evts_get_info family "$evt" $e_type) + dport=$(mptcp_lib_evts_get_info dport "$evt" $e_type) + locid=$(mptcp_lib_evts_get_info loc_id "$evt" $e_type) + remid=$(mptcp_lib_evts_get_info rem_id "$evt" $e_type) if [ "$family" = "$AF_INET6" ] then - saddr=$(sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") - daddr=$(sed --unbuffered -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q' "$evt") + saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" $e_type) + daddr=$(mptcp_lib_evts_get_info daddr6 "$evt" $e_type) else - saddr=$(sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") - daddr=$(sed --unbuffered -n 's/.*\(daddr4:\)\([0-9.]*\).*$/\2/p;q' "$evt") + saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" $e_type) + daddr=$(mptcp_lib_evts_get_info daddr4 "$evt" $e_type) fi check_expected "type" "token" "daddr" "dport" "family" "saddr" "locid" "remid" @@ -627,10 +605,10 @@ test_subflows() "10.0.2.2" "$client4_port" "23" "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid local sport - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW from server to client machine :>"$server_evts" @@ -666,9 +644,9 @@ test_subflows() "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW6 from server to client machine :>"$server_evts" @@ -705,9 +683,9 @@ test_subflows() "$client_addr_id" "ns1" "ns2" # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$server_evts") + sport=$(mptcp_lib_evts_get_info sport "$server_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW from server to client machine :>"$server_evts" @@ -743,9 +721,9 @@ test_subflows() "10.0.2.1" "$app4_port" "23" "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW from client to server machine :>"$client_evts" @@ -782,9 +760,9 @@ test_subflows() "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW6 from client to server machine :>"$client_evts" @@ -819,9 +797,9 @@ test_subflows() "10.0.2.2" "10.0.2.1" "$new4_port" "23" "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW from client to server machine :>"$client_evts" @@ -865,9 +843,9 @@ test_subflows_v4_v6_mix() "$server_addr_id" "ns2" "ns1" # Delete the listener from the server ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid - sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + sport=$(mptcp_lib_evts_get_info sport "$client_evts" $SUB_ESTABLISHED) # DESTROY_SUBFLOW from client to server machine :>"$client_evts" @@ -896,9 +874,10 @@ test_prio() # Check TX print_test "MP_PRIO TX" - count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns2" "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass @@ -906,9 +885,10 @@ test_prio() # Check RX print_test "MP_PRIO RX" - count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count != 1 ]; then + count=$(mptcp_lib_get_counter "$ns1" "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + test_skip + elif [ $count != 1 ]; then test_fail "Count != 1: ${count}" else test_pass @@ -933,18 +913,13 @@ verify_listener_events() print_test "CLOSE_LISTENER $e_saddr:$e_sport" fi - type=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + type=$(mptcp_lib_evts_get_info type $evt $e_type) + family=$(mptcp_lib_evts_get_info family $evt $e_type) + sport=$(mptcp_lib_evts_get_info sport $evt $e_type) if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(mptcp_lib_evts_get_info saddr6 $evt $e_type) else - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(mptcp_lib_evts_get_info saddr4 $evt $e_type) fi check_expected "type" "family" "saddr" "sport" @@ -982,7 +957,7 @@ test_listener() sleep 0.5 # Delete the listener from the client ns, if one was created - kill_wait $listener_pid + mptcp_lib_kill_wait $listener_pid sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh new file mode 100755 index 000000000000..4fe0befa13fb --- /dev/null +++ b/tools/testing/selftests/net/net_helper.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Helper functions + +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + local protocol="${3}" + local port_hex + local i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \ + grep -q "${port_hex}"; then + break + fi + sleep 0.1 + done +} diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 0c743752669a..af5dc57c8ce9 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro functional tests. +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -51,8 +53,7 @@ run_one() { echo "ok" || \ echo "failed" & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen ${PEER_NS} 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) @@ -97,7 +98,7 @@ run_one_nat() { echo "ok" || \ echo "failed"& - sleep 0.1 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? kill -INT $pid @@ -118,11 +119,9 @@ run_one_2sock() { echo "ok" || \ echo "failed" & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 12345 udp ./udpgso_bench_tx ${tx_args} -p 12345 - sleep 0.1 - # first UDP GSO socket should be closed at this point + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index 894972877e8b..cb664679b434 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro benchmarks +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -40,8 +42,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} } diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 0a6359bed0b9..dd47fa96f6b3 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -3,6 +3,8 @@ # # Run a series of udpgro benchmarks +source net_helper.sh + readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" BPF_FILE="../bpf/xdp_dummy.bpf.o" @@ -45,8 +47,7 @@ run_one() { echo ${rx_args} ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & - # Hack: let bg programs complete the startup - sleep 0.2 + wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} } diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile index b1fa2e177e2f..e8b3dde4fa16 100644 --- a/tools/testing/selftests/tc-testing/Makefile +++ b/tools/testing/selftests/tc-testing/Makefile @@ -1,31 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -include ../../../scripts/Makefile.include -top_srcdir = $(abspath ../../../..) -APIDIR := $(top_scrdir)/include/uapi -TEST_GEN_FILES = action.o +TEST_PROGS += ./tdc.sh +TEST_FILES := action-ebpf tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts include ../lib.mk - -PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) - -ifeq ($(PROBE),) - CPU ?= probe -else - CPU ?= generic -endif - -CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') - -CLANG_FLAGS = -I. -I$(APIDIR) \ - $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types - -$(OUTPUT)/%.o: %.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 --target=bpf -emit-llvm -c $< -o - | \ - $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ - -TEST_PROGS += ./tdc.sh -TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index be7b00799b3e..fc8e858ff119 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -195,8 +195,6 @@ directory: and the other is a test whether the command leaked memory or not. (This one is a preliminary version, it may not work quite right yet, but the overall template is there and it should only need tweaks.) - - buildebpfPlugin.py: - builds all programs in $EBPFDIR. ACKNOWLEDGEMENTS diff --git a/tools/testing/selftests/tc-testing/action-ebpf b/tools/testing/selftests/tc-testing/action-ebpf Binary files differnew file mode 100644 index 000000000000..4879479b2ee5 --- /dev/null +++ b/tools/testing/selftests/tc-testing/action-ebpf diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py deleted file mode 100644 index d34fe06268d2..000000000000 --- a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py +++ /dev/null @@ -1,67 +0,0 @@ -''' -build ebpf program -''' - -import os -import signal -from string import Template -import subprocess -import time -from TdcPlugin import TdcPlugin -from tdc_config import * - -class SubPlugin(TdcPlugin): - def __init__(self): - self.sub_class = 'buildebpf/SubPlugin' - self.tap = '' - super().__init__() - - def pre_suite(self, testcount, testidlist): - super().pre_suite(testcount, testidlist) - - if self.args.buildebpf: - self._ebpf_makeall() - - def post_suite(self, index): - super().post_suite(index) - - self._ebpf_makeclean() - - def add_args(self, parser): - super().add_args(parser) - - self.argparser_group = self.argparser.add_argument_group( - 'buildebpf', - 'options for buildebpfPlugin') - self.argparser_group.add_argument( - '--nobuildebpf', action='store_false', default=True, - dest='buildebpf', - help='Don\'t build eBPF programs') - - return self.argparser - - def _ebpf_makeall(self): - if self.args.buildebpf: - self._make('all') - - def _ebpf_makeclean(self): - if self.args.buildebpf: - self._make('clean') - - def _make(self, target): - command = 'make -C {} {}'.format(self.args.NAMES['EBPFDIR'], target) - proc = subprocess.Popen(command, - shell=True, - stdout=subprocess.PIPE, - stderr=subprocess.PIPE, - env=os.environ.copy()) - (rawout, serr) = proc.communicate() - - if proc.returncode != 0 and len(serr) > 0: - foutput = serr.decode("utf-8") - else: - foutput = rawout.decode("utf-8") - - proc.stdout.close() - proc.stderr.close() - return proc, foutput diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py index b62429b0fcdb..bb19b8b76d3b 100644 --- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py +++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py @@ -9,43 +9,13 @@ from TdcPlugin import TdcPlugin from tdc_config import * -def prepare_suite(obj, test): - original = obj.args.NAMES - - if 'skip' in test and test['skip'] == 'yes': - return - - if 'nsPlugin' not in test['plugins']: - return - - shadow = {} - shadow['IP'] = original['IP'] - shadow['TC'] = original['TC'] - shadow['NS'] = '{}-{}'.format(original['NS'], test['random']) - shadow['DEV0'] = '{}id{}'.format(original['DEV0'], test['id']) - shadow['DEV1'] = '{}id{}'.format(original['DEV1'], test['id']) - shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], test['id']) - shadow['DEV2'] = original['DEV2'] - obj.args.NAMES = shadow - - if obj.args.namespace: - obj._ns_create() - else: - obj._ports_create() - - # Make sure the netns is visible in the fs - while True: - obj._proc_check() - try: - ns = obj.args.NAMES['NS'] - f = open('/run/netns/{}'.format(ns)) - f.close() - break - except: - time.sleep(0.1) - continue - - obj.args.NAMES = original +try: + from pyroute2 import netns + from pyroute2 import IPRoute + netlink = True +except ImportError: + netlink = False + print("!!! Consider installing pyroute2 !!!") class SubPlugin(TdcPlugin): def __init__(self): @@ -53,64 +23,71 @@ class SubPlugin(TdcPlugin): super().__init__() def pre_suite(self, testcount, testlist): - from itertools import cycle - super().pre_suite(testcount, testlist) - print("Setting up namespaces and devices...") + def prepare_test(self, test): + if 'skip' in test and test['skip'] == 'yes': + return - with Pool(self.args.mp) as p: - it = zip(cycle([self]), testlist) - p.starmap(prepare_suite, it) + if 'nsPlugin' not in test['plugins']: + return - def pre_case(self, caseinfo, test_skip): + if netlink == True: + self._nl_ns_create() + else: + self._ipr2_ns_create() + + # Make sure the netns is visible in the fs + ticks = 20 + while True: + if ticks == 0: + raise TimeoutError + self._proc_check() + try: + ns = self.args.NAMES['NS'] + f = open('/run/netns/{}'.format(ns)) + f.close() + break + except: + time.sleep(0.1) + ticks -= 1 + continue + + def pre_case(self, test, test_skip): if self.args.verbose: print('{}.pre_case'.format(self.sub_class)) if test_skip: return + self.prepare_test(test) def post_case(self): if self.args.verbose: print('{}.post_case'.format(self.sub_class)) - if self.args.namespace: - self._ns_destroy() + if netlink == True: + self._nl_ns_destroy() else: - self._ports_destroy() + self._ipr2_ns_destroy() def post_suite(self, index): if self.args.verbose: print('{}.post_suite'.format(self.sub_class)) # Make sure we don't leak resources - for f in os.listdir('/run/netns/'): - cmd = self._replace_keywords("$IP netns del {}".format(f)) + cmd = self._replace_keywords("$IP -a netns del") - if self.args.verbose > 3: - print('_exec_cmd: command "{}"'.format(cmd)) - - subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) + if self.args.verbose > 3: + print('_exec_cmd: command "{}"'.format(cmd)) - def add_args(self, parser): - super().add_args(parser) - self.argparser_group = self.argparser.add_argument_group( - 'netns', - 'options for nsPlugin(run commands in net namespace)') - self.argparser_group.add_argument( - '-N', '--no-namespace', action='store_false', default=True, - dest='namespace', help='Don\'t run commands in namespace') - return self.argparser + subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) def adjust_command(self, stage, command): super().adjust_command(stage, command) cmdform = 'list' cmdlist = list() - if not self.args.namespace: - return command - if self.args.verbose: print('{}.adjust_command'.format(self.sub_class)) @@ -138,63 +115,90 @@ class SubPlugin(TdcPlugin): print('adjust_command: return command [{}]'.format(command)) return command - def _ports_create_cmds(self): - cmds = [] - - cmds.append(self._replace_keywords('link add $DEV0 type veth peer name $DEV1')) - cmds.append(self._replace_keywords('link set $DEV0 up')) - cmds.append(self._replace_keywords('link add $DUMMY type dummy')) - if not self.args.namespace: - cmds.append(self._replace_keywords('link set $DEV1 up')) - - return cmds - - def _ports_create(self): - self._exec_cmd_batched('pre', self._ports_create_cmds()) + def _nl_ns_create(self): + ns = self.args.NAMES["NS"]; + dev0 = self.args.NAMES["DEV0"]; + dev1 = self.args.NAMES["DEV1"]; + dummy = self.args.NAMES["DUMMY"]; - def _ports_destroy_cmd(self): - return self._replace_keywords('link del $DEV0') - - def _ports_destroy(self): - self._exec_cmd('post', self._ports_destroy_cmd()) - - def _ns_create_cmds(self): + if self.args.verbose: + print('{}._nl_ns_create'.format(self.sub_class)) + + netns.create(ns) + netns.pushns(newns=ns) + with IPRoute() as ip: + ip.link('add', ifname=dev1, kind='veth', peer={'ifname': dev0, 'net_ns_fd':'/proc/1/ns/net'}) + ip.link('add', ifname=dummy, kind='dummy') + ticks = 20 + while True: + if ticks == 0: + raise TimeoutError + try: + dev1_idx = ip.link_lookup(ifname=dev1)[0] + dummy_idx = ip.link_lookup(ifname=dummy)[0] + ip.link('set', index=dev1_idx, state='up') + ip.link('set', index=dummy_idx, state='up') + break + except: + time.sleep(0.1) + ticks -= 1 + continue + netns.popns() + + with IPRoute() as ip: + ticks = 20 + while True: + if ticks == 0: + raise TimeoutError + try: + dev0_idx = ip.link_lookup(ifname=dev0)[0] + ip.link('set', index=dev0_idx, state='up') + break + except: + time.sleep(0.1) + ticks -= 1 + continue + + def _ipr2_ns_create_cmds(self): cmds = [] - if self.args.namespace: - ns = self.args.NAMES['NS'] + ns = self.args.NAMES['NS'] - cmds.append(self._replace_keywords('netns add {}'.format(ns))) - cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns))) - cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns))) - cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns))) - cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns))) + cmds.append(self._replace_keywords('netns add {}'.format(ns))) + cmds.append(self._replace_keywords('link add $DEV1 type veth peer name $DEV0')) + cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns))) + cmds.append(self._replace_keywords('link add $DUMMY type dummy'.format(ns))) + cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns))) + cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns))) + cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns))) + cmds.append(self._replace_keywords('link set $DEV0 up'.format(ns))) - if self.args.device: - cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns))) - cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns))) + if self.args.device: + cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns))) + cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns))) return cmds - def _ns_create(self): + def _ipr2_ns_create(self): ''' Create the network namespace in which the tests will be run and set up the required network devices for it. ''' - self._ports_create() - self._exec_cmd_batched('pre', self._ns_create_cmds()) + self._exec_cmd_batched('pre', self._ipr2_ns_create_cmds()) + + def _nl_ns_destroy(self): + ns = self.args.NAMES['NS'] + netns.remove(ns) - def _ns_destroy_cmd(self): + def _ipr2_ns_destroy_cmd(self): return self._replace_keywords('netns delete {}'.format(self.args.NAMES['NS'])) - def _ns_destroy(self): + def _ipr2_ns_destroy(self): ''' Destroy the network namespace for testing (and any associated network devices as well) ''' - if self.args.namespace: - self._exec_cmd('post', self._ns_destroy_cmd()) - self._ports_destroy() + self._exec_cmd('post', self._ipr2_ns_destroy_cmd()) @cached_property def _proc(self): diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 91832400ddbd..6e00bf32ef9a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -54,9 +54,6 @@ "actions", "bpf" ], - "plugins": { - "requires": "buildebpfPlugin" - }, "setup": [ [ "$TC action flush action bpf", @@ -65,10 +62,10 @@ 255 ] ], - "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", + "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action-ebpf section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action-ebpf:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" @@ -81,9 +78,6 @@ "actions", "bpf" ], - "plugins": { - "requires": "buildebpfPlugin" - }, "setup": [ [ "$TC action flush action bpf", @@ -92,10 +86,10 @@ 255 ] ], - "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667", + "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action-ebpf section action-ko index 667", "expExitCode": "255", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action-ebpf:\\[action-ko\\] id [0-9].*index 667 ref", "matchCount": "0", "teardown": [ [ diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json index 013fb983bc3f..725d406a30ac 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/bpf.json @@ -52,17 +52,16 @@ ], "plugins": { "requires": [ - "buildebpfPlugin", "nsPlugin" ] }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action.o section action-ok", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action-ebpf section action-ok", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf", - "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action.o:\\[action-ok\\].*tag [0-9a-f]{16}( jited)?", + "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action-ebpf:\\[action-ok\\].*tag [0-9a-f]{16}( jited)?", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" @@ -77,17 +76,16 @@ ], "plugins": { "requires": [ - "buildebpfPlugin", "nsPlugin" ] }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action.o section action-ko", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf object-file $EBPFDIR/action-ebpf section action-ko", "expExitCode": "1", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 100 bpf", - "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action.o:\\[action-ko\\].*tag [0-9a-f]{16}( jited)?", + "matchPattern": "filter parent ffff: protocol ip pref 100 bpf chain [0-9]+ handle 0x1 action-ebpf:\\[action-ko\\].*tag [0-9a-f]{16}( jited)?", "matchCount": "0", "teardown": [ "$TC qdisc del dev $DEV1 ingress" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index ddc7c355be0a..24bd0c2a3014 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -272,5 +272,62 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "bd32", + "name": "Try to delete hashtable referenced by another u32 filter", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 parent root handle 10: drr", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 1: u32 divisor 1", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 1:" + ], + "cmdUnderTest": "$TC filter delete dev $DEV1 parent 10: prio 2 handle 1: u32", + "expExitCode": "2", + "verifyCmd": "$TC filter show dev $DEV1", + "matchPattern": "protocol ip pref 2 u32 chain 0 fh 1:", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 parent root drr" + ] + }, + { + "id": "4585", + "name": "Delete small tree of u32 hashtables and filters", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 parent root handle 10: drr", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 1: u32 divisor 1", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 2: u32 divisor 1", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 3: u32 divisor 2", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 handle 4: u32 divisor 1", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 1: match ip src any action drop", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 2: match ip src any action drop", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 3: match ip src any link 2:", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 3: match ip src any link 1:", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 4: match ip src any action drop", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 3:", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 ht 800: match ip src any link 4:" + ], + "cmdUnderTest": "$TC filter delete dev $DEV1 parent 10:", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1", + "matchPattern": "protocol ip pref 2 u32", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 parent root drr" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index a6718192aff3..caeacc691587 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -497,11 +497,6 @@ def prepare_run(pm, args, testlist): pm.call_post_suite(1) return emergency_exit_message - if args.verbose: - print('give test rig 2 seconds to stabilize') - - time.sleep(2) - def purge_run(pm, index): pm.call_post_suite(index) @@ -616,7 +611,7 @@ def test_runner_mp(pm, args, alltests): batches.insert(0, serial) print("Executing {} tests in parallel and {} in serial".format(len(parallel), len(serial))) - print("Using {} batches".format(len(batches))) + print("Using {} batches and {} workers".format(len(batches), args.mp)) # We can't pickle these objects so workaround them global mp_pm @@ -1017,12 +1012,17 @@ def main(): parser = pm.call_add_args(parser) (args, remaining) = parser.parse_known_args() args.NAMES = NAMES + args.mp = min(args.mp, 4) pm.set_args(args) check_default_settings(args, remaining, pm) if args.verbose > 2: print('args is {}'.format(args)) - set_operation_mode(pm, parser, args, remaining) + try: + set_operation_mode(pm, parser, args, remaining) + except KeyboardInterrupt: + # Cleanup on Ctrl-C + pm.call_post_suite(None) if __name__ == "__main__": main() diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index eb357bd7923c..407fa53822a0 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -1,7 +1,68 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -modprobe netdevsim -modprobe sch_teql -./tdc.py -c actions --nobuildebpf -./tdc.py -c qdisc +# If a module is required and was not compiled +# the test that requires it will fail anyways +try_modprobe() { + modprobe -q -R "$1" + if [ $? -ne 0 ]; then + echo "Module $1 not found... skipping." + else + modprobe "$1" + fi +} + +try_modprobe netdevsim +try_modprobe act_bpf +try_modprobe act_connmark +try_modprobe act_csum +try_modprobe act_ct +try_modprobe act_ctinfo +try_modprobe act_gact +try_modprobe act_gate +try_modprobe act_ipt +try_modprobe act_mirred +try_modprobe act_mpls +try_modprobe act_nat +try_modprobe act_pedit +try_modprobe act_police +try_modprobe act_sample +try_modprobe act_simple +try_modprobe act_skbedit +try_modprobe act_skbmod +try_modprobe act_tunnel_key +try_modprobe act_vlan +try_modprobe cls_basic +try_modprobe cls_bpf +try_modprobe cls_cgroup +try_modprobe cls_flow +try_modprobe cls_flower +try_modprobe cls_fw +try_modprobe cls_matchall +try_modprobe cls_route +try_modprobe cls_u32 +try_modprobe em_canid +try_modprobe em_cmp +try_modprobe em_ipset +try_modprobe em_ipt +try_modprobe em_meta +try_modprobe em_nbyte +try_modprobe em_text +try_modprobe em_u32 +try_modprobe sch_cake +try_modprobe sch_cbs +try_modprobe sch_choke +try_modprobe sch_codel +try_modprobe sch_drr +try_modprobe sch_etf +try_modprobe sch_ets +try_modprobe sch_fq +try_modprobe sch_fq_codel +try_modprobe sch_fq_pie +try_modprobe sch_gred +try_modprobe sch_hfsc +try_modprobe sch_hhf +try_modprobe sch_htb +try_modprobe sch_teql +./tdc.py -J`nproc` -c actions +./tdc.py -J`nproc` -c qdisc |