- Linux-kselftest-mirror - lists.linaro.org

[PATCH bpf-next v3 1/2] bpftool: Use appropriate permissions for map access

by Slava Imameev

Modify several functions in tools/bpf/bpftool/common.c to allow specification of requested access for file descriptors, such as read-only access. Update bpftool to request only read access for maps when write access is not required. This fixes errors when reading from maps that are protected from modification via security_bpf_map. Signed-off-by: Slava Imameev <slava.imameev(a)crowdstrike.com> --- Changes in v2: - fix for a test compilation error: "conflicting types for 'bpf_fentry_test1'" Changes in v3: - Addressed review feedback - Converted the check for flags to an assert in map_parse_fds - Modified map_fd_by_name to keep an existing fd where possible - Fixed requested access for map delete command in do_delete - Changed requested access to RDONLY for inner map fd in do_create - Changed requested access to RDONLY for iterator fd in do_pin --- --- tools/bpf/bpftool/btf.c | 3 +- tools/bpf/bpftool/common.c | 58 ++++++++++++++++++++++--------- tools/bpf/bpftool/iter.c | 2 +- tools/bpf/bpftool/link.c | 2 +- tools/bpf/bpftool/main.h | 13 ++++--- tools/bpf/bpftool/map.c | 56 +++++++++++++++++------------ tools/bpf/bpftool/map_perf_ring.c | 3 +- tools/bpf/bpftool/prog.c | 4 +-- 8 files changed, 91 insertions(+), 50 deletions(-) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 6b14cbfa58aa..1ba27cb03348 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -905,7 +905,8 @@ static int do_dump(int argc, char **argv) return -1; } - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, + BPF_F_RDONLY); if (fd < 0) return -1; diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index ecfa790adc13..3bdc65112c0d 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -193,7 +193,8 @@ int mount_tracefs(const char *target) return err; } -int open_obj_pinned(const char *path, bool quiet) +int open_obj_pinned(const char *path, bool quiet, + const struct bpf_obj_get_opts *opts) { char *pname; int fd = -1; @@ -205,7 +206,7 @@ int open_obj_pinned(const char *path, bool quiet) goto out_ret; } - fd = bpf_obj_get(pname); + fd = bpf_obj_get_opts(pname, opts); if (fd < 0) { if (!quiet) p_err("bpf obj get (%s): %s", pname, @@ -221,12 +222,13 @@ int open_obj_pinned(const char *path, bool quiet) return fd; } -int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type, + const struct bpf_obj_get_opts *opts) { enum bpf_obj_type type; int fd; - fd = open_obj_pinned(path, false); + fd = open_obj_pinned(path, false, opts); if (fd < 0) return -1; @@ -555,7 +557,7 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb, if (typeflag != FTW_F) goto out_ret; - fd = open_obj_pinned(fpath, true); + fd = open_obj_pinned(fpath, true, NULL); if (fd < 0) goto out_ret; @@ -928,7 +930,7 @@ int prog_parse_fds(int *argc, char ***argv, int **fds) path = **argv; NEXT_ARGP(); - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG, NULL); if ((*fds)[0] < 0) return -1; return 1; @@ -965,7 +967,8 @@ int prog_parse_fd(int *argc, char ***argv) return fd; } -static int map_fd_by_name(char *name, int **fds) +static int map_fd_by_name(char *name, int **fds, + const struct bpf_get_fd_by_id_opts *opts) { unsigned int id = 0; int fd, nb_fds = 0; @@ -973,6 +976,7 @@ static int map_fd_by_name(char *name, int **fds) int err; while (true) { + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts_ro); struct bpf_map_info info = {}; __u32 len = sizeof(info); @@ -985,7 +989,9 @@ static int map_fd_by_name(char *name, int **fds) return nb_fds; } - fd = bpf_map_get_fd_by_id(id); + /* Request a read-only fd to query the map info */ + opts_ro.open_flags = BPF_F_RDONLY; + fd = bpf_map_get_fd_by_id_opts(id, &opts_ro); if (fd < 0) { p_err("can't get map by id (%u): %s", id, strerror(errno)); @@ -1004,6 +1010,19 @@ static int map_fd_by_name(char *name, int **fds) continue; } + /* Get an fd with the requested options, if they differ + * from the read-only options used to get the fd above. + */ + if (memcmp(opts, &opts_ro, sizeof(opts_ro))) { + close(fd); + fd = bpf_map_get_fd_by_id_opts(id, opts); + if (fd < 0) { + p_err("can't get map by id (%u): %s", id, + strerror(errno)); + goto err_close_fds; + } + } + if (nb_fds > 0) { tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); if (!tmp) { @@ -1023,8 +1042,13 @@ static int map_fd_by_name(char *name, int **fds) return -1; } -int map_parse_fds(int *argc, char ***argv, int **fds) +int map_parse_fds(int *argc, char ***argv, int **fds, __u32 open_flags) { + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); + + assert((open_flags & ~BPF_F_RDONLY) == 0); + opts.open_flags = open_flags; + if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -1038,7 +1062,7 @@ int map_parse_fds(int *argc, char ***argv, int **fds) } NEXT_ARGP(); - (*fds)[0] = bpf_map_get_fd_by_id(id); + (*fds)[0] = bpf_map_get_fd_by_id_opts(id, &opts); if ((*fds)[0] < 0) { p_err("get map by id (%u): %s", id, strerror(errno)); return -1; @@ -1056,16 +1080,18 @@ int map_parse_fds(int *argc, char ***argv, int **fds) } NEXT_ARGP(); - return map_fd_by_name(name, fds); + return map_fd_by_name(name, fds, &opts); } else if (is_prefix(**argv, "pinned")) { char *path; + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + get_opts.file_flags = open_flags; NEXT_ARGP(); path = **argv; NEXT_ARGP(); - (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP, &get_opts); if ((*fds)[0] < 0) return -1; return 1; @@ -1075,7 +1101,7 @@ int map_parse_fds(int *argc, char ***argv, int **fds) return -1; } -int map_parse_fd(int *argc, char ***argv) +int map_parse_fd(int *argc, char ***argv, __u32 open_flags) { int *fds = NULL; int nb_fds, fd; @@ -1085,7 +1111,7 @@ int map_parse_fd(int *argc, char ***argv) p_err("mem alloc failed"); return -1; } - nb_fds = map_parse_fds(argc, argv, &fds); + nb_fds = map_parse_fds(argc, argv, &fds, open_flags); if (nb_fds != 1) { if (nb_fds > 1) { p_err("several maps match this handle"); @@ -1103,12 +1129,12 @@ int map_parse_fd(int *argc, char ***argv) } int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, - __u32 *info_len) + __u32 *info_len, __u32 open_flags) { int err; int fd; - fd = map_parse_fd(argc, argv); + fd = map_parse_fd(argc, argv, open_flags); if (fd < 0) return -1; diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 5c39c2ed36a2..df5f0d1e07e8 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -37,7 +37,7 @@ static int do_pin(int argc, char **argv) return -1; } - map_fd = map_parse_fd(&argc, &argv); + map_fd = map_parse_fd(&argc, &argv, BPF_F_RDONLY); if (map_fd < 0) return -1; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 03513ffffb79..a773e05d5ade 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -117,7 +117,7 @@ static int link_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_LINK); + return open_obj_pinned_any(path, BPF_OBJ_LINK, NULL); } p_err("expected 'id' or 'pinned', got: '%s'?", **argv); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 9eb764fe4cc8..6db704fda5c0 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -15,6 +15,7 @@ #include <bpf/hashmap.h> #include <bpf/libbpf.h> +#include <bpf/bpf.h> #include "json_writer.h" @@ -140,8 +141,10 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); -int open_obj_pinned(const char *path, bool quiet); -int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); +int open_obj_pinned(const char *path, bool quiet, + const struct bpf_obj_get_opts *opts); +int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type, + const struct bpf_obj_get_opts *opts); int mount_bpffs_for_file(const char *file_name); int create_and_mount_bpffs_dir(const char *dir_name); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); @@ -167,10 +170,10 @@ int do_iter(int argc, char **argv) __weak; int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); int prog_parse_fds(int *argc, char ***argv, int **fds); -int map_parse_fd(int *argc, char ***argv); -int map_parse_fds(int *argc, char ***argv, int **fds); +int map_parse_fd(int *argc, char ***argv, __u32 open_flags); +int map_parse_fds(int *argc, char ***argv, int **fds, __u32 open_flags); int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info, - __u32 *info_len); + __u32 *info_len, __u32 open_flags); struct bpf_prog_linfo; #if defined(HAVE_LLVM_SUPPORT) || defined(HAVE_LIBBFD_SUPPORT) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 81cc668b4b05..c9de44a45778 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -337,9 +337,9 @@ static void fill_per_cpu_value(struct bpf_map_info *info, void *value) memcpy(value + i * step, value, info->value_size); } -static int parse_elem(char **argv, struct bpf_map_info *info, - void *key, void *value, __u32 key_size, __u32 value_size, - __u32 *flags, __u32 **value_fd) +static int parse_elem(char **argv, struct bpf_map_info *info, void *key, + void *value, __u32 key_size, __u32 value_size, + __u32 *flags, __u32 **value_fd, __u32 open_flags) { if (!*argv) { if (!key && !value) @@ -362,7 +362,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; return parse_elem(argv, info, NULL, value, key_size, value_size, - flags, value_fd); + flags, value_fd, open_flags); } else if (is_prefix(*argv, "value")) { int fd; @@ -388,7 +388,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; } - fd = map_parse_fd(&argc, &argv); + fd = map_parse_fd(&argc, &argv, open_flags); if (fd < 0) return -1; @@ -424,7 +424,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info, } return parse_elem(argv, info, key, NULL, key_size, value_size, - flags, NULL); + flags, NULL, open_flags); } else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") || is_prefix(*argv, "exist")) { if (!flags) { @@ -440,7 +440,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info, *flags = BPF_EXIST; return parse_elem(argv + 1, info, key, value, key_size, - value_size, NULL, value_fd); + value_size, NULL, value_fd, open_flags); } p_err("expected key or value, got: %s", *argv); @@ -639,7 +639,7 @@ static int do_show_subset(int argc, char **argv) p_err("mem alloc failed"); return -1; } - nb_fds = map_parse_fds(&argc, &argv, &fds); + nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY); if (nb_fds < 1) goto exit_free; @@ -672,12 +672,15 @@ static int do_show_subset(int argc, char **argv) static int do_show(int argc, char **argv) { + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); struct bpf_map_info info = {}; __u32 len = sizeof(info); __u32 id = 0; int err; int fd; + opts.open_flags = BPF_F_RDONLY; + if (show_pinned) { map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); @@ -707,7 +710,7 @@ static int do_show(int argc, char **argv) break; } - fd = bpf_map_get_fd_by_id(id); + fd = bpf_map_get_fd_by_id_opts(id, &opts); if (fd < 0) { if (errno == ENOENT) continue; @@ -909,7 +912,7 @@ static int do_dump(int argc, char **argv) p_err("mem alloc failed"); return -1; } - nb_fds = map_parse_fds(&argc, &argv, &fds); + nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY); if (nb_fds < 1) goto exit_free; @@ -997,7 +1000,7 @@ static int do_update(int argc, char **argv) if (argc < 2) usage(); - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); if (fd < 0) return -1; @@ -1006,7 +1009,7 @@ static int do_update(int argc, char **argv) goto exit_free; err = parse_elem(argv, &info, key, value, info.key_size, - info.value_size, &flags, &value_fd); + info.value_size, &flags, &value_fd, 0); if (err) goto exit_free; @@ -1076,7 +1079,7 @@ static int do_lookup(int argc, char **argv) if (argc < 2) usage(); - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY); if (fd < 0) return -1; @@ -1084,7 +1087,8 @@ static int do_lookup(int argc, char **argv) if (err) goto exit_free; - err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL, + BPF_F_RDONLY); if (err) goto exit_free; @@ -1127,7 +1131,7 @@ static int do_getnext(int argc, char **argv) if (argc < 2) usage(); - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY); if (fd < 0) return -1; @@ -1140,8 +1144,8 @@ static int do_getnext(int argc, char **argv) } if (argc) { - err = parse_elem(argv, &info, key, NULL, info.key_size, 0, - NULL, NULL); + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, + NULL, BPF_F_RDONLY); if (err) goto exit_free; } else { @@ -1198,7 +1202,7 @@ static int do_delete(int argc, char **argv) if (argc < 2) usage(); - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); if (fd < 0) return -1; @@ -1209,7 +1213,8 @@ static int do_delete(int argc, char **argv) goto exit_free; } - err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL, + 0); if (err) goto exit_free; @@ -1226,11 +1231,16 @@ static int do_delete(int argc, char **argv) return err; } +static int map_parse_read_only_fd(int *argc, char ***argv) +{ + return map_parse_fd(argc, argv, BPF_F_RDONLY); +} + static int do_pin(int argc, char **argv) { int err; - err = do_pin_any(argc, argv, map_parse_fd); + err = do_pin_any(argc, argv, map_parse_read_only_fd); if (!err && json_output) jsonw_null(json_wtr); return err; @@ -1319,7 +1329,7 @@ static int do_create(int argc, char **argv) if (!REQ_ARGS(2)) usage(); inner_map_fd = map_parse_fd_and_info(&argc, &argv, - &info, &len); + &info, &len, BPF_F_RDONLY); if (inner_map_fd < 0) return -1; attr.inner_map_fd = inner_map_fd; @@ -1368,7 +1378,7 @@ static int do_pop_dequeue(int argc, char **argv) if (argc < 2) usage(); - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0); if (fd < 0) return -1; @@ -1407,7 +1417,7 @@ static int do_freeze(int argc, char **argv) if (!REQ_ARGS(2)) return -1; - fd = map_parse_fd(&argc, &argv); + fd = map_parse_fd(&argc, &argv, 0); if (fd < 0) return -1; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 552b4ca40c27..bcb767e2d673 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -128,7 +128,8 @@ int do_event_pipe(int argc, char **argv) int err, map_fd; map_info_len = sizeof(map_info); - map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len, + 0); if (map_fd < 0) return -1; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 96eea8a67225..deeaa5c1ed7d 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1062,7 +1062,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, if (!REQ_ARGS(2)) return -EINVAL; - *mapfd = map_parse_fd(&argc, &argv); + *mapfd = map_parse_fd(&argc, &argv, 0); if (*mapfd < 0) return *mapfd; @@ -1608,7 +1608,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) } NEXT_ARG(); - fd = map_parse_fd(&argc, &argv); + fd = map_parse_fd(&argc, &argv, 0); if (fd < 0) goto err_free_reuse_maps; -- 2.34.1

1 week, 3 days

2
3
0 0

[PATCH v19 net-next 0/5] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v18. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v19 (14-Jun-2025) - Fix one typo in the comment of #1 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update commit message of #4 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Wrap long lines of Documentation/netlink/specs/tc.yaml to within 80 characters (Jakub Kicinski <kuba(a)kernel.org>) v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (4): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 166 +++ include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 70 +- net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1146 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 1 + 9 files changed, 1656 insertions(+), 1 deletion(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

1 week, 3 days

2
6
0 0

[RFC PATCH v1 0/2] kselftest/resctrl: CAT functional tests

by Ilpo Järvinen

Hi all, In the last Fall Reinette mentioned functional tests of resctrl would be preferred over selftests that are based on performance measurement. This series tries to address that shortcoming by adding some functional tests for resctrl FS interface and another that checks MSRs match to what is written through resctrl FS. The MSR test is only available for Intel CPUs at the moment. Why RFC? The new functional selftest itself works, AFAIK. However, calling ksft_test_result_skip() in cat.c if MSR reading is found to be unavailable is problematic because of how kselftest harness is architected. The kselftest.h header itself defines some variables, so including it into different .c files results in duplicating the test framework related variables (duplication of ksft_count matters in this case). The duplication problem could be worked around by creating a resctrl selftest specific wrapper for ksft_test_result_skip() into resctrl_tests.c so the accounting would occur in the "correct" .c file, but perhaps that is considered hacky and the selftest framework/build systems should be reworked to avoid duplicating variables? Ilpo Järvinen (2): kselftest/resctrl: CAT L3 resctrl FS function tests kselftest/resctrl: Add CAT L3 CBM functional test for Intel RDT tools/testing/selftests/resctrl/cat_test.c | 210 ++++++++++++++++++ tools/testing/selftests/resctrl/msr.c | 55 +++++ tools/testing/selftests/resctrl/resctrl.h | 6 + .../testing/selftests/resctrl/resctrl_tests.c | 2 + tools/testing/selftests/resctrl/resctrlfs.c | 48 ++++ 5 files changed, 321 insertions(+) create mode 100644 tools/testing/selftests/resctrl/msr.c base-commit: c1d7e19c70cbb8a19f63c190cf53e71b5f970514 -- 2.39.5

1 week, 3 days

1
2
0 0

[PATCH 0/1] selftests/memfd: skip hugetlbfs test if not supported

by Po-Hsu Lin

Check hugetlbfs support before starting tests in run_hugetlbfs_test.sh. Otherwise on a system that does not support hugetlbfs the free huge pages availability check will fail with: ./run_hugetlbfs_test.sh: line 47: [: -lt: unary operator expected ./run_hugetlbfs_test.sh: line 60: 12577 Aborted (core dumped) ./memfd_test hugetlbfs Aborted (core dumped) And it will left a fuse_mnt process behind, which may cause some unexpected issues. Patch tested with a kernel that does not have hugetlbfs support enabled and the test was skipped as expected. Po-Hsu Lin (1): selftests/memfd: skip hugetlbfs test if not supported tools/testing/selftests/memfd/run_hugetlbfs_test.sh | 5 +++++ 1 file changed, 5 insertions(+) -- 2.34.1

1 week, 3 days

1
1
0 0

[PATCH v11 0/6] rust: reduce `as` casts, enable related lints

by Tamir Duberstein

This started with a patch that enabled `clippy::ptr_as_ptr`. Benno Lossin suggested I also look into `clippy::ptr_cast_constness` and I discovered `clippy::as_ptr_cast_mut`. This series now enables all 3 lints. It also enables `clippy::as_underscore` which ensures other pointer casts weren't missed. As a later addition, `clippy::cast_lossless` and `clippy::ref_as_ptr` are also enabled. This series depends on "rust: retain pointer mut-ness in `container_of!`"[1]. Link: https://lore.kernel.org/all/20250409-container-of-mutness-v1-1-64f472b94534… [1] Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v11: - Rebase on v6.16-rc1. - Replace some `as <integer>` with `as bindings::T` and others with `as ffi::T`. (Miguel Ojeda) - Revert explicit `ffi::c_void` import which is in the prelude. (Miguel Ojeda) - Link to v10: https://lore.kernel.org/r/20250418-ptr-as-ptr-v10-0-3d63d27907aa@gmail.com Changes in v10: - Move fragment from "rust: enable `clippy::ptr_cast_constness` lint" to "rust: enable `clippy::ptr_as_ptr` lint". (Boqun Feng) - Replace `(...).into()` with `T::from(...)` where the destination type isn't obvious in "rust: enable `clippy::cast_lossless` lint". (Boqun Feng) - Link to v9: https://lore.kernel.org/r/20250416-ptr-as-ptr-v9-0-18ec29b1b1f3@gmail.com Changes in v9: - Replace ref-to-ptr coercion using `let` bindings with `core::ptr::from_{ref,mut}`. (Boqun Feng). - Link to v8: https://lore.kernel.org/r/20250409-ptr-as-ptr-v8-0-3738061534ef@gmail.com Changes in v8: - Use coercion to go ref -> ptr. - rustfmt. - Rebase on v6.15-rc1. - Extract first commit to its own series as it is shared with other series. - Link to v7: https://lore.kernel.org/r/20250325-ptr-as-ptr-v7-0-87ab452147b9@gmail.com Changes in v7: - Add patch to enable `clippy::ref_as_ptr`. - Link to v6: https://lore.kernel.org/r/20250324-ptr-as-ptr-v6-0-49d1b7fd4290@gmail.com Changes in v6: - Drop strict provenance patch. - Fix URLs in doc comments. - Add patch to enable `clippy::cast_lossless`. - Rebase on rust-next. - Link to v5: https://lore.kernel.org/r/20250317-ptr-as-ptr-v5-0-5b5f21fa230a@gmail.com Changes in v5: - Use `pointer::addr` in OF. (Boqun Feng) - Add documentation on stubs. (Benno Lossin) - Mark stubs `#[inline]`. - Pick up Alice's RB on a shared commit from https://lore.kernel.org/all/Z9f-3Aj3_FWBZRrm@google.com/. - Link to v4: https://lore.kernel.org/r/20250315-ptr-as-ptr-v4-0-b2d72c14dc26@gmail.com Changes in v4: - Add missing SoB. (Benno Lossin) - Use `without_provenance_mut` in alloc. (Boqun Feng) - Limit strict provenance lints to the `kernel` crate to avoid complex logic in the build system. This can be revisited on MSRV >= 1.84.0. - Rebase on rust-next. - Link to v3: https://lore.kernel.org/r/20250314-ptr-as-ptr-v3-0-e7ba61048f4a@gmail.com Changes in v3: - Fixed clippy warning in rust/kernel/firmware.rs. (kernel test robot) Link: https://lore.kernel.org/all/202503120332.YTCpFEvv-lkp@intel.com/ - s/as u64/as bindings::phys_addr_t/g. (Benno Lossin) - Use strict provenance APIs and enable lints. (Benno Lossin) - Link to v2: https://lore.kernel.org/r/20250309-ptr-as-ptr-v2-0-25d60ad922b7@gmail.com Changes in v2: - Fixed typo in first commit message. - Added additional patches, converted to series. - Link to v1: https://lore.kernel.org/r/20250307-ptr-as-ptr-v1-1-582d06514c98@gmail.com --- Tamir Duberstein (6): rust: enable `clippy::ptr_as_ptr` lint rust: enable `clippy::ptr_cast_constness` lint rust: enable `clippy::as_ptr_cast_mut` lint rust: enable `clippy::as_underscore` lint rust: enable `clippy::cast_lossless` lint rust: enable `clippy::ref_as_ptr` lint Makefile | 6 ++++ drivers/gpu/drm/drm_panic_qr.rs | 4 +-- rust/bindings/lib.rs | 3 ++ rust/kernel/alloc/allocator_test.rs | 2 +- rust/kernel/alloc/kvec.rs | 4 +-- rust/kernel/block/mq/operations.rs | 2 +- rust/kernel/block/mq/request.rs | 11 +++++-- rust/kernel/device.rs | 4 +-- rust/kernel/device_id.rs | 4 +-- rust/kernel/devres.rs | 17 +++++------ rust/kernel/dma.rs | 6 ++-- rust/kernel/drm/device.rs | 6 ++-- rust/kernel/error.rs | 2 +- rust/kernel/firmware.rs | 3 +- rust/kernel/fs/file.rs | 2 +- rust/kernel/io.rs | 18 ++++++------ rust/kernel/kunit.rs | 11 ++++--- rust/kernel/list/impl_list_item_mod.rs | 2 +- rust/kernel/miscdevice.rs | 2 +- rust/kernel/mm/virt.rs | 52 +++++++++++++++++----------------- rust/kernel/net/phy.rs | 4 +-- rust/kernel/of.rs | 6 ++-- rust/kernel/pci.rs | 11 ++++--- rust/kernel/platform.rs | 4 ++- rust/kernel/print.rs | 6 ++-- rust/kernel/seq_file.rs | 2 +- rust/kernel/str.rs | 14 ++++----- rust/kernel/sync/poll.rs | 2 +- rust/kernel/time/hrtimer/pin.rs | 2 +- rust/kernel/time/hrtimer/pin_mut.rs | 2 +- rust/kernel/uaccess.rs | 4 +-- rust/kernel/workqueue.rs | 8 +++--- rust/uapi/lib.rs | 3 ++ 33 files changed, 128 insertions(+), 101 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250307-ptr-as-ptr-21b1867fc4d4 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

1 week, 4 days

2
8
0 0

[PATCH bpf 0/7] bpf: deny trampoline attachment if args can not be located exactly on stack

by Alexis Lothoré (eBPF Foundation)

Hello, this series follows some discussions started in [1] around bpf trampolines limitations on specific cases. When a trampoline is generated for a target function involving many arguments, it has to properly find and save the arguments that has been passed through stack. While this is doable with basic types (eg: scalars), it brings more uncertainty when dealing with specific types like structs (many ABIs allow to pass structures by value if they fit in a register or a pair of registers). The issue is that those structures layout and location on the stack can be altered (ie with attributes, like packed or aligned(x)), and this kind of alteration is not encoded in dwarf or BTF, making the trampolines clueless about the needed adjustments. Rather than trying to support this specific case, as agreed in [2], this series aims to properly deny it. It targets all the architectures currently implementing arch_prepare_bpf_trampoline (except aarch64, since it has been handled while adding the support for many args): - x86 - s390 - riscv - powerpc A small validation function is added in the JIT compiler for each of those architectures, ensuring that no argument passed on stack is a struct. If so, the trampoline creation is cancelled. Any check on args already implemented in a JIT comp has been moved in this new function. On top of that, it updates the tracing_struct_many_args test, which now merely checks that this case is indeed denied. [1] https://lore.kernel.org/bpf/20250411-many_args_arm64-v1-0-0a32fe72339e@boot… [2] https://lore.kernel.org/bpf/CAADnVQKr3ftNt1uQVrXBE0a2o37ZYRo2PHqCoHUnw6PE5T… Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- Alexis Lothoré (eBPF Foundation) (7): bpf/x86: use define for max regs count used for arguments bpf/x86: prevent trampoline attachment when args location on stack is uncertain bpf/riscv: prevent trampoline attachment when args location on stack is uncertain bpf/s390: prevent trampoline attachment when args location on stack is uncertain bpf/powerpc64: use define for max regs count used for arguments bpf/powerpc64: prevent trampoline attachment when args location on stack is uncertain selftests/bpf: ensure that functions passing structs on stack can not be hooked arch/powerpc/net/bpf_jit_comp.c | 38 ++++++++++-- arch/riscv/net/bpf_jit_comp64.c | 26 +++++++- arch/s390/net/bpf_jit_comp.c | 33 ++++++++-- arch/x86/net/bpf_jit_comp.c | 50 ++++++++++++---- .../selftests/bpf/prog_tests/tracing_struct.c | 37 +----------- .../selftests/bpf/progs/tracing_struct_many_args.c | 70 ---------------------- .../testing/selftests/bpf/test_kmods/bpf_testmod.c | 43 ++----------- 7 files changed, 129 insertions(+), 168 deletions(-) --- base-commit: c4f4f8da70044d8b28fccf73016b4119f3e2fd50 change-id: 20250609-deny_trampoline_structs_on_stack-5bbc7bc20dd1 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

1 week, 4 days

4
14
0 0

[PATCH net-next v1 1/4] net: netmem: fix skb_ensure_writable with unreadable skbs

by Mina Almasry

skb_ensure_writable actually makes sure that the header of the skb is writable, and doesn't touch the payload. It doesn't need an skb_frags_readable check. Removing this check restores DSCP functionality with unreadable skbs as it's called from dscp_tg. Fixes: 65249feb6b3d ("net: add support for skbs with unreadable frags") Signed-off-by: Mina Almasry <almasrymina(a)google.com> --- net/core/skbuff.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 85fc82f72d26..d6420b74ea9c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6261,9 +6261,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM; - if (!skb_frags_readable(skb)) - return -EFAULT; - if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; base-commit: 6d4e01d29d87356924f1521ca6df7a364e948f13 -- 2.50.0.rc1.591.g9c95f17f64-goog

1 week, 5 days

2
5
0 0

[PATCH net-next v3] page_pool: import Jesper's page_pool benchmark

by Mina Almasry

From: Jesper Dangaard Brouer <hawk(a)kernel.org> We frequently consult with Jesper's out-of-tree page_pool benchmark to evaluate page_pool changes. Import the benchmark into the upstream linux kernel tree so that (a) we're all running the same version, (b) pave the way for shared improvements, and (c) maybe one day integrate it with nipa, if possible. Import bench_page_pool_simple from commit 35b1716d0c30 ("Add page_bench06_walk_all"), from this repository: https://github.com/netoptimizer/prototype-kernel.git Changes done during upstreaming: - Fix checkpatch issues. - Remove the tasklet logic not needed. - Move under tools/testing - Create ksft for the benchmark. - Changed slightly how the benchmark gets build. Out of tree, time_bench is built as an independent .ko. Here it is included in bench_page_pool.ko Steps to run: ``` mkdir -p /tmp/run-pp-bench make -C ./tools/testing/selftests/net/bench make -C ./tools/testing/selftests/net/bench install INSTALL_PATH=/tmp/run-pp-bench rsync --delete -avz --progress /tmp/run-pp-bench mina@$SERVER:~/ ssh mina@$SERVER << EOF cd ~/run-pp-bench && sudo ./test_bench_page_pool.sh EOF ``` Output: ``` (benchmrk dmesg logs) Fast path results: no-softirq-page_pool01 Per elem: 11 cycles(tsc) 4.368 ns ptr_ring results: no-softirq-page_pool02 Per elem: 527 cycles(tsc) 195.187 ns slow path results: no-softirq-page_pool03 Per elem: 549 cycles(tsc) 203.466 ns ``` Cc: Jesper Dangaard Brouer <hawk(a)kernel.org> Cc: Ilias Apalodimas <ilias.apalodimas(a)linaro.org> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Toke Høiland-Jørgensen <toke(a)toke.dk> Signed-off-by: Mina Almasry <almasrymina(a)google.com> Acked-by: Ilias Apalodimas <ilias.apalodimas(a)linaro.org> Signed-off-by: Jesper Dangaard Brouer <hawk(a)kernel.org> --- v3: - Non RFC - Collect Signed-off-by from Jesper and Acked-by Ilias. - Move test_bench_page_pool.sh to address nipa complaint. - Remove `static inline` in .c files to address nipa complaint. v2: - Move under tools/selftests (Jakub) - Create ksft for it. - Remove the tasklet logic no longer needed (Jesper + Toke) RFC discussion points: - Desirable to import it? - Can the benchmark be imported as-is for an initial version? Or needs lots of modifications? - Code location. I retained the location in Jesper's tree, but a path like net/core/bench/ may make more sense. --- tools/testing/selftests/net/bench/Makefile | 7 + .../selftests/net/bench/page_pool/Makefile | 17 + .../bench/page_pool/bench_page_pool_simple.c | 274 ++++++++++++ .../net/bench/page_pool/time_bench.c | 406 ++++++++++++++++++ .../net/bench/page_pool/time_bench.h | 259 +++++++++++ .../net/bench/test_bench_page_pool.sh | 32 ++ 6 files changed, 995 insertions(+) create mode 100644 tools/testing/selftests/net/bench/Makefile create mode 100644 tools/testing/selftests/net/bench/page_pool/Makefile create mode 100644 tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c create mode 100644 tools/testing/selftests/net/bench/page_pool/time_bench.c create mode 100644 tools/testing/selftests/net/bench/page_pool/time_bench.h create mode 100755 tools/testing/selftests/net/bench/test_bench_page_pool.sh diff --git a/tools/testing/selftests/net/bench/Makefile b/tools/testing/selftests/net/bench/Makefile new file mode 100644 index 000000000000..2546c45e42f7 --- /dev/null +++ b/tools/testing/selftests/net/bench/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_MODS_DIR := page_pool + +TEST_PROGS += test_bench_page_pool.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile new file mode 100644 index 000000000000..0549a16ba275 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/Makefile @@ -0,0 +1,17 @@ +BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +obj-m += bench_page_pool.o +bench_page_pool-y += bench_page_pool_simple.o time_bench.o + +all: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c new file mode 100644 index 000000000000..44355043b632 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -0,0 +1,274 @@ +/* + * Benchmark module for page_pool. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/mutex.h> + +#include <linux/version.h> +#include <net/page_pool/helpers.h> + +#include <linux/interrupt.h> +#include <linux/limits.h> + +#include "time_bench.h" + +static int verbose = 1; +#define MY_POOL_SIZE 1024 + +static void _page_pool_put_page(struct page_pool *pool, struct page *page, + bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + +/* Makes tests selectable. Useful for perf-record to analyze a single test. + * Hint: Bash shells support writing binary number like: $((2#101010) + * + * # modprobe bench_page_pool_simple run_flags=$((2#100)) + */ +static unsigned long run_flags = 0xFFFFFFFF; +module_param(run_flags, ulong, 0); +MODULE_PARM_DESC(run_flags, "Limit which bench test that runs"); +/* Count the bit number from the enum */ +enum benchmark_bit { + bit_run_bench_baseline, + bit_run_bench_no_softirq01, + bit_run_bench_no_softirq02, + bit_run_bench_no_softirq03, +}; +#define bit(b) (1 << (b)) +#define enabled(b) ((run_flags & (bit(b)))) + +/* notice time_bench is limited to U32_MAX nr loops */ +static unsigned long loops = 10000000; +module_param(loops, ulong, 0); +MODULE_PARM_DESC(loops, "Specify loops bench will run"); + +/* Timing at the nanosec level, we need to know the overhead + * introduced by the for loop itself */ +static int time_bench_for_loop(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + int i; + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +static int time_bench_atomic_inc(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + atomic_t cnt; + int i; + + atomic_set(&cnt, 0); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + atomic_inc(&cnt); + barrier(); /* avoid compiler to optimize this loop */ + } + loops_cnt = atomic_read(&cnt); + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum + * overhead of taking+releasing a spinlock, to know the cycles that can be saved + * by e.g. amortizing this via bulking. + */ +static int time_bench_lock(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + spinlock_t lock; + int i; + + spin_lock_init(&lock); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + spin_lock(&lock); + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + spin_unlock(&lock); + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* Helper for filling some page's into ptr_ring */ +static void pp_fill_ptr_ring(struct page_pool *pp, int elems) +{ + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC needed when under run softirq */ + struct page **array; + int i; + + array = kzalloc(sizeof(struct page *) * elems, gfp_mask); + + for (i = 0; i < elems; i++) { + array[i] = page_pool_alloc_pages(pp, gfp_mask); + } + for (i = 0; i < elems; i++) { + _page_pool_put_page(pp, array[i], false); + } + + kfree(array); +} + +enum test_type { type_fast_path, type_ptr_ring, type_page_allocator }; + +/* Depends on compile optimizing this function */ +static int time_bench_page_pool(struct time_bench_record *rec, void *data, + enum test_type type, const char *func) +{ + uint64_t loops_cnt = 0; + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */ + int i, err; + + struct page_pool *pp; + struct page *page; + + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = MY_POOL_SIZE, + .nid = NUMA_NO_NODE, + .dev = NULL, /* Only use for DMA mapping */ + .dma_dir = DMA_BIDIRECTIONAL, + }; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + pr_warn("%s: Error(%d) creating page_pool\n", func, err); + goto out; + } + pp_fill_ptr_ring(pp, 64); + + if (in_serving_softirq()) + pr_warn("%s(): in_serving_softirq fast-path\n", func); + else + pr_warn("%s(): Cannot use page_pool fast-path\n", func); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + /* Common fast-path alloc, that depend on in_serving_softirq() */ + page = page_pool_alloc_pages(pp, gfp_mask); + if (!page) + break; + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + + /* The benchmarks purpose it to test different return paths. + * Compiler should inline optimize other function calls out + */ + if (type == type_fast_path) { + /* Fast-path recycling e.g. XDP_DROP use-case */ + page_pool_recycle_direct(pp, page); + + } else if (type == type_ptr_ring) { + /* Normal return path */ + _page_pool_put_page(pp, page, false); + + } else if (type == type_page_allocator) { + /* Test if not pages are recycled, but instead + * returned back into systems page allocator + */ + get_page(page); /* cause no-recycling */ + _page_pool_put_page(pp, page, false); + put_page(page); + } else { + BUILD_BUG(); + } + } + time_bench_stop(rec, loops_cnt); +out: + page_pool_destroy(pp); + return loops_cnt; +} + +static int time_bench_page_pool01_fast_path(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_fast_path, __func__); +} + +static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_ptr_ring, __func__); +} + +static int time_bench_page_pool03_slow(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_page_allocator, __func__); +} + +static int run_benchmark_tests(void) +{ + uint32_t nr_loops = loops; + int passed_count = 0; + + /* Baseline tests */ + if (enabled(bit_run_bench_baseline)) { + time_bench_loop(nr_loops * 10, 0, "for_loop", NULL, + time_bench_for_loop); + time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL, + time_bench_atomic_inc); + time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock); + } + + /* This test cannot activate correct code path, due to no-softirq ctx */ + if (enabled(bit_run_bench_no_softirq01)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL, + time_bench_page_pool01_fast_path); + if (enabled(bit_run_bench_no_softirq02)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL, + time_bench_page_pool02_ptr_ring); + if (enabled(bit_run_bench_no_softirq03)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL, + time_bench_page_pool03_slow); + + return passed_count; +} + +static int __init bench_page_pool_simple_module_init(void) +{ + if (verbose) + pr_info("Loaded\n"); + + if (loops > U32_MAX) { + pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops, + U32_MAX); + return -ECHRNG; + } + + run_benchmark_tests(); + + return 0; +} +module_init(bench_page_pool_simple_module_init); + +static void __exit bench_page_pool_simple_module_exit(void) +{ + if (verbose) + pr_info("Unloaded\n"); +} +module_exit(bench_page_pool_simple_module_exit); + +MODULE_DESCRIPTION("Benchmark of page_pool simple cases"); +MODULE_AUTHOR("Jesper Dangaard Brouer <netoptimizer(a)brouer.com>"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c new file mode 100644 index 000000000000..257b1515c64e --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c @@ -0,0 +1,406 @@ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/time.h> + +#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */ + +/* For concurrency testing */ +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> + +#include "time_bench.h" + +static int verbose = 1; + +/** TSC (Time-Stamp Counter) based ** + * See: linux/time_bench.h + * tsc_start_clock() and tsc_stop_clock() + */ + +/** Wall-clock based ** + */ + +/** PMU (Performance Monitor Unit) based ** + */ +#define PERF_FORMAT \ + (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +struct raw_perf_event { + uint64_t config; /* event */ + uint64_t config1; /* umask */ + struct perf_event *save; + char *desc; +}; + +/* if HT is enable a maximum of 4 events (5 if one is instructions + * retired can be specified, if HT is disabled a maximum of 8 (9 if + * one is instructions retired) can be specified. + * + * From Table 19-1. Architectural Performance Events + * Architectures Software Developer’s Manual Volume 3: System Programming Guide + */ +struct raw_perf_event perf_events[] = { + { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" }, + { 0xc0, 0x00, NULL, "Instruction Retired" } +}; + +#define NUM_EVTS (sizeof(perf_events) / sizeof(struct raw_perf_event)) + +/* WARNING: PMU config is currently broken! + */ +bool time_bench_PMU_config(bool enable) +{ + int i; + struct perf_event_attr perf_conf; + struct perf_event *perf_event; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + pr_info("DEBUG: cpu:%d\n", cpu); + preempt_enable(); + + memset(&perf_conf, 0, sizeof(struct perf_event_attr)); + perf_conf.type = PERF_TYPE_RAW; + perf_conf.size = sizeof(struct perf_event_attr); + perf_conf.read_format = PERF_FORMAT; + perf_conf.pinned = 1; + perf_conf.exclude_user = 1; /* No userspace events */ + perf_conf.exclude_kernel = 0; /* Only kernel events */ + + for (i = 0; i < NUM_EVTS; i++) { + perf_conf.disabled = enable; + //perf_conf.disabled = (i == 0) ? 1 : 0; + perf_conf.config = perf_events[i].config; + perf_conf.config1 = perf_events[i].config1; + if (verbose) + pr_info("%s() enable PMU counter: %s\n", + __func__, perf_events[i].desc); + perf_event = perf_event_create_kernel_counter(&perf_conf, cpu, + NULL /* task */, + NULL /* overflow_handler*/, + NULL /* context */); + if (perf_event) { + perf_events[i].save = perf_event; + pr_info("%s():DEBUG perf_event success\n", __func__); + + perf_event_enable(perf_event); + } else { + pr_info("%s():DEBUG perf_event is NULL\n", __func__); + } + } + + return true; +} + +/** Generic functions ** + */ + +/* Calculate stats, store results in record */ +bool time_bench_calc_stats(struct time_bench_record *rec) +{ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ + uint64_t ns_per_call_tmp_rem = 0; + uint32_t ns_per_call_remainder = 0; + uint64_t pmc_ipc_tmp_rem = 0; + uint32_t pmc_ipc_remainder = 0; + uint32_t pmc_ipc_div = 0; + uint32_t invoked_cnt_precision = 0; + uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */ + + if (rec->flags & TIME_BENCH_LOOP) { + if (rec->invoked_cnt < 1000) { + pr_err("ERR: need more(>1000) loops(%llu) for timing\n", + rec->invoked_cnt); + return false; + } + if (rec->invoked_cnt > ((1ULL << 32) - 1)) { + /* div_u64_rem() can only support div with 32bit*/ + pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n", + rec->invoked_cnt); + return false; + } + invoked_cnt = (uint32_t)rec->invoked_cnt; + } + + /* TSC (Time-Stamp Counter) records */ + if (rec->flags & TIME_BENCH_TSC) { + rec->tsc_interval = rec->tsc_stop - rec->tsc_start; + if (rec->tsc_interval == 0) { + pr_err("ABORT: timing took ZERO TSC time\n"); + return false; + } + /* Calculate stats */ + if (rec->flags & TIME_BENCH_LOOP) + rec->tsc_cycles = rec->tsc_interval / invoked_cnt; + else + rec->tsc_cycles = rec->tsc_interval; + } + + /* Wall-clock time calc */ + if (rec->flags & TIME_BENCH_WALLCLOCK) { + rec->time_start = rec->ts_start.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_start.tv_sec); + rec->time_stop = rec->ts_stop.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_stop.tv_sec); + rec->time_interval = rec->time_stop - rec->time_start; + if (rec->time_interval == 0) { + pr_err("ABORT: timing took ZERO wallclock time\n"); + return false; + } + /* Calculate stats */ + /*** Division in kernel it tricky ***/ + /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */ + /* remainder only correct because NANOSEC_PER_SEC is 10^9 */ + rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC, + &rec->time_sec_remainder); + //TODO: use existing struct timespec records instead of div? + + if (rec->flags & TIME_BENCH_LOOP) { + /*** Division in kernel it tricky ***/ + /* Orig: ns = ((double)time_interval / invoked_cnt); */ + /* First get quotient */ + rec->ns_per_call_quotient = + div_u64_rem(rec->time_interval, invoked_cnt, + &ns_per_call_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + ns_per_call_tmp_rem = ns_per_call_remainder; + invoked_cnt_precision = invoked_cnt / 1000; + if (invoked_cnt_precision > 0) { + rec->ns_per_call_decimal = + div_u64_rem(ns_per_call_tmp_rem, + invoked_cnt_precision, + &ns_per_call_remainder); + } + } + } + + /* Performance Monitor Unit (PMU) counters */ + if (rec->flags & TIME_BENCH_PMU) { + //FIXME: Overflow handling??? + rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start; + rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start; + + /* Calc Instruction Per Cycle (IPC) */ + /* First get quotient */ + rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk, + &pmc_ipc_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + pmc_ipc_tmp_rem = pmc_ipc_remainder; + pmc_ipc_div = rec->pmc_clk / 1000; + if (pmc_ipc_div > 0) { + rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem, + pmc_ipc_div, + &pmc_ipc_remainder); + } + } + + return true; +} + +/* Generic function for invoking a loop function and calculating + * execution time stats. The function being called/timed is assumed + * to perform a tight loop, and update the timing record struct. + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *record, void *data)) +{ + struct time_bench_record rec; + + /* Setup record */ + memset(&rec, 0, sizeof(rec)); /* zero func might not update all */ + rec.version_abi = 1; + rec.loops = loops; + rec.step = step; + rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC|TIME_BENCH_WALLCLOCK); +// rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC| +// TIME_BENCH_WALLCLOCK|TIME_BENCH_PMU); + //TODO: Add/copy txt to rec + + /*** Loop function being timed ***/ + if (!func(&rec, data)) { + pr_err("ABORT: function being timed failed\n"); + return false; + } + + if (rec.invoked_cnt < loops) + pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n", + rec.invoked_cnt, loops); + + /* Calculate stats */ + time_bench_calc_stats(&rec); + + pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d)" + " - (measurement period time:%llu.%09u sec time_interval:%llu)" + " - (invoke count:%llu tsc_interval:%llu)\n", + txt, rec.tsc_cycles, + rec.ns_per_call_quotient, rec.ns_per_call_decimal, rec.step, + rec.time_sec, rec.time_sec_remainder, rec.time_interval, + rec.invoked_cnt, rec.tsc_interval); +/* pr_info("DEBUG check is %llu/%llu == %llu.%03llu ?\n", + rec.time_interval, rec.invoked_cnt, + rec.ns_per_call_quotient, rec.ns_per_call_decimal); +*/ + if (rec.flags & TIME_BENCH_PMU) { + pr_info("Type:%s PMU inst/clock" + "%llu/%llu = %llu.%03llu IPC (inst per cycle)\n", + txt, rec.pmc_inst, rec.pmc_clk, + rec.pmc_ipc_quotient, rec.pmc_ipc_decimal); + } + return true; +} + +/* Function getting invoked by kthread */ +static int invoke_test_on_cpu_func(void *private) +{ + struct time_bench_cpu *cpu = private; + struct time_bench_sync *sync = cpu->sync; + cpumask_t newmask = CPU_MASK_NONE; + void *data = cpu->data; + + /* Restrict CPU */ + cpumask_set_cpu(cpu->rec.cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + /* Synchronize start of concurrency test */ + atomic_inc(&sync->nr_tests_running); + wait_for_completion(&sync->start_event); + + /* Start benchmark function */ + if (!cpu->bench_func(&cpu->rec, data)) { + pr_err("ERROR: function being timed failed on CPU:%d(%d)\n", + cpu->rec.cpu, smp_processor_id()); + } else { + if (verbose) + pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu, + smp_processor_id()); + } + cpu->did_bench_run = true; + + /* End test */ + atomic_dec(&sync->nr_tests_running); + /* Wait for kthread_stop() telling us to stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask) +{ + uint64_t average = 0; + int cpu; + int step = 0; + struct sum { + uint64_t tsc_cycles; + int records; + } sum = { 0 }; + + /* Get stats */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + struct time_bench_record *rec = &c->rec; + + /* Calculate stats */ + time_bench_calc_stats(rec); + + pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns" + " (step:%d)" + " - (measurement period time:%llu.%09u sec time_interval:%llu)" + " - (invoke count:%llu tsc_interval:%llu)\n", + desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient, + rec->ns_per_call_decimal, rec->step, rec->time_sec, + rec->time_sec_remainder, rec->time_interval, + rec->invoked_cnt, rec->tsc_interval); + + /* Collect average */ + sum.records++; + sum.tsc_cycles += rec->tsc_cycles; + step = rec->step; + } + + if (sum.records) /* avoid div-by-zero */ + average = sum.tsc_cycles / sum.records; + pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc, + average, sum.records, step); +} + +void time_bench_run_concurrent( + uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)) +{ + int cpu, running = 0; + + if (verbose) // DEBUG + pr_warn("%s() Started on CPU:%d\n", __func__, + smp_processor_id()); + + /* Reset sync conditions */ + atomic_set(&sync->nr_tests_running, 0); + init_completion(&sync->start_event); + + /* Spawn off jobs on all CPUs */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + running++; + c->sync = sync; /* Send sync variable along */ + c->data = data; /* Send opaque along */ + + /* Init benchmark record */ + memset(&c->rec, 0, sizeof(struct time_bench_record)); + c->rec.version_abi = 1; + c->rec.loops = loops; + c->rec.step = step; + c->rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC| + TIME_BENCH_WALLCLOCK); + c->rec.cpu = cpu; + c->bench_func = func; + c->task = kthread_run(invoke_test_on_cpu_func, c, + "time_bench%d", cpu); + if (IS_ERR(c->task)) { + pr_err("%s(): Failed to start test func\n", __func__); + return; /* Argh, what about cleanup?! */ + } + } + + /* Wait until all processes are running */ + while (atomic_read(&sync->nr_tests_running) < running) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + /* Kick off all CPU concurrently on completion event */ + complete_all(&sync->start_event); + + /* Wait for CPUs to finish */ + while (atomic_read(&sync->nr_tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + /* Stop the kthreads */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + kthread_stop(c->task); + } + + if (verbose) // DEBUG - happens often, finish on another CPU + pr_warn("%s() Finished on CPU:%d\n", __func__, + smp_processor_id()); +} diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h new file mode 100644 index 000000000000..b0e7139179e5 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h @@ -0,0 +1,259 @@ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#ifndef _LINUX_TIME_BENCH_H +#define _LINUX_TIME_BENCH_H + +/* Main structure used for recording a benchmark run */ +struct time_bench_record { + uint32_t version_abi; + uint32_t loops; /* Requested loop invocations */ + uint32_t step; /* option for e.g. bulk invocations */ + + uint32_t flags; /* Measurements types enabled */ +#define TIME_BENCH_LOOP (1<<0) +#define TIME_BENCH_TSC (1<<1) +#define TIME_BENCH_WALLCLOCK (1<<2) +#define TIME_BENCH_PMU (1<<3) + + uint32_t cpu; /* Used when embedded in time_bench_cpu */ + + /* Records */ + uint64_t invoked_cnt; /* Returned actual invocations */ + uint64_t tsc_start; + uint64_t tsc_stop; + struct timespec64 ts_start; + struct timespec64 ts_stop; + /** PMU counters for instruction and cycles + * instructions counter including pipelined instructions */ + uint64_t pmc_inst_start; + uint64_t pmc_inst_stop; + /* CPU unhalted clock counter */ + uint64_t pmc_clk_start; + uint64_t pmc_clk_stop; + + /* Result records */ + uint64_t tsc_interval; + uint64_t time_start, time_stop, time_interval; /* in nanosec */ + uint64_t pmc_inst, pmc_clk; + + /* Derived result records */ + uint64_t tsc_cycles; // +decimal? + uint64_t ns_per_call_quotient, ns_per_call_decimal; + uint64_t time_sec; + uint32_t time_sec_remainder; + uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */ +}; + +/* For synchronizing parallel CPUs to run concurrently */ +struct time_bench_sync { + atomic_t nr_tests_running; + struct completion start_event; +}; + +/* Keep track of CPUs executing our bench function. + * + * Embed a time_bench_record for storing info per cpu + */ +struct time_bench_cpu { + struct time_bench_record rec; + struct time_bench_sync *sync; /* back ptr */ + struct task_struct *task; + /* "data" opaque could have been placed in time_bench_sync, + * but to avoid any false sharing, place it per CPU + */ + void *data; + /* Support masking outsome CPUs, mark if it ran */ + bool did_bench_run; + /* int cpu; // note CPU stored in time_bench_record */ + int (*bench_func)(struct time_bench_record *record, void *data); +}; + +/* + * Below TSC assembler code is not compatible with other archs, and + * can also fail on guests if cpu-flags are not correct. + * + * The way TSC reading is used, many iterations, does not require as + * high accuracy as described below (in Intel Doc #324264). + * + * Considering changing to use get_cycles() (#include <asm/timex.h>). + */ + +/** TSC (Time-Stamp Counter) based ** + * Recommend reading, to understand details of reading TSC accurately: + * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel" + * + * Consider getting exclusive ownership of CPU by using: + * unsigned long flags; + * preempt_disable(); + * raw_local_irq_save(flags); + * _your_code_ + * raw_local_irq_restore(flags); + * preempt_enable(); + * + * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx" + * RDTSC only change "%rax" and "%rdx" but + * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx) + */ +static __always_inline uint64_t tsc_start_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned hi, lo; + asm volatile("CPUID\n\t" + "RDTSC\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + //FIXME: on 32bit use clobbered %eax + %edx + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +static __always_inline uint64_t tsc_stop_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned hi, lo; + asm volatile("RDTSCP\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + "CPUID\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +/* Notes for RDTSC and RDTSCP + * + * Hannes found out that __builtin_ia32_rdtsc and + * __builtin_ia32_rdtscp are undocumented available in gcc, so there + * is no need to write inline assembler functions for them any more. + * + * unsigned long long __builtin_ia32_rdtscp(unsigned int *foo); + * (where foo is set to: numa_node << 12 | cpu) + * and + * unsigned long long __builtin_ia32_rdtsc(void); + * + * Above we combine the calls with CPUID, thus I don't see how this is + * directly appreciable. + */ + +/* +inline uint64_t rdtsc(void) +{ + uint32_t low, high; + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + return low | (((uint64_t )high ) << 32); +} +*/ + +/** Wall-clock based ** + * + * use: getnstimeofday() + * getnstimeofday(&rec->ts_start); + * getnstimeofday(&rec->ts_stop); + * + * API changed see: Documentation/core-api/timekeeping.rst + * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstim… + * + * We should instead use: ktime_get_real_ts64() is a direct + * replacement, but consider using monotonic time (ktime_get_ts64()) + * and/or a ktime_t based interface (ktime_get()/ktime_get_real()). + */ + +/** PMU (Performance Monitor Unit) based ** + * + * Needed for calculating: Instructions Per Cycle (IPC) + * - The IPC number tell how efficient the CPU pipelining were + */ +//lookup: perf_event_create_kernel_counter() + +bool time_bench_PMU_config(bool enable); + +/* Raw reading via rdpmc() using fixed counters + * + * From: https://github.com/andikleen/simple-pmu + */ +enum { + FIXED_SELECT = (1U << 30), /* == 0x40000000 */ + FIXED_INST_RETIRED_ANY = 0, + FIXED_CPU_CLK_UNHALTED_CORE = 1, + FIXED_CPU_CLK_UNHALTED_REF = 2, +}; + +static __always_inline unsigned long long p_rdpmc(unsigned in) +{ + unsigned d, a; + + asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory"); + return ((unsigned long long)d << 32) | a; +} + +/* These PMU counter needs to be enabled, but I don't have the + * configure code implemented. My current hack is running: + * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko + */ +/* Reading all pipelined instruction */ +static __always_inline unsigned long long pmc_inst(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY); +} + +/* Reading CPU clock cycles */ +static __always_inline unsigned long long pmc_clk(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE); +} + +/* Raw reading via MSR rdmsr() is likely wrong + * FIXME: How can I know which raw MSR registers are conf for what? + */ +#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */ +#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */ +#define MSR_IA32_PCM2 0x400000C3 +static inline uint64_t msr_inst(unsigned long long *msr_result) +{ + return rdmsrq_safe(MSR_IA32_PCM0, msr_result); +} + +/** Generic functions ** + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *rec, void *data)); +bool time_bench_calc_stats(struct time_bench_record *rec); + +void time_bench_run_concurrent( + uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)); +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask); + +//FIXME: use rec->flags to select measurement, should be MACRO +static __always_inline void time_bench_start(struct time_bench_record *rec) +{ + //getnstimeofday(&rec->ts_start); + ktime_get_real_ts64(&rec->ts_start); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_start = pmc_inst(); + rec->pmc_clk_start = pmc_clk(); + } + rec->tsc_start = tsc_start_clock(); +} + +static __always_inline void time_bench_stop(struct time_bench_record *rec, + uint64_t invoked_cnt) +{ + rec->tsc_stop = tsc_stop_clock(); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_stop = pmc_inst(); + rec->pmc_clk_stop = pmc_clk(); + } + //getnstimeofday(&rec->ts_stop); + ktime_get_real_ts64(&rec->ts_stop); + rec->invoked_cnt = invoked_cnt; +} + +#endif /* _LINUX_TIME_BENCH_H */ diff --git a/tools/testing/selftests/net/bench/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/test_bench_page_pool.sh new file mode 100755 index 000000000000..5eb48f28b659 --- /dev/null +++ b/tools/testing/selftests/net/bench/test_bench_page_pool.sh @@ -0,0 +1,32 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +set -e + +DRIVER="./page_pool/bench_page_pool.ko" +result="" + +function run_test() +{ + rmmod "bench_page_pool.ko" || true + insmod $DRIVER > /dev/null 2>&1 + result=$(dmesg | tail -10) + echo "$result" + + echo + echo "Fast path results:" + echo ${result} | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" + + echo + echo "ptr_ring results:" + echo ${result} | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" + + echo + echo "slow path results:" + echo ${result} | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" +} + +run_test + +exit 0 base-commit: 08207f42d3ffee43c97f16baf03d7426a3c353ca -- 2.50.0.rc1.591.g9c95f17f64-goog

1 week, 5 days

2
1
0 0

[PATCH v18 net-next 0/5] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v18. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (4): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 161 +++ include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 70 +- net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1146 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 1 + 9 files changed, 1651 insertions(+), 1 deletion(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

1 week, 5 days

4
9
0 0

[PATCH v18 net-next 0/5] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v18. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (4): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 161 +++ include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 70 +- net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1146 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 1 + 9 files changed, 1651 insertions(+), 1 deletion(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

1 week, 5 days

1
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror