diff options
author | David S. Miller <davem@davemloft.net> | 2018-05-24 22:20:51 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-05-24 22:20:51 -0400 |
commit | 90fed9c94625718a3a10db7d1e8e4efe093bbf5f (patch) | |
tree | 09b3bc9ea679316372b139338179a230105306dc /kernel/bpf | |
parent | 49a473f5b5f54f33e0bd8618158d33f83153c921 (diff) | |
parent | 10f678683e4026e43524b0492068a371d00fdeed (diff) | |
download | linux-90fed9c94625718a3a10db7d1e8e4efe093bbf5f.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2018-05-24
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Björn Töpel cleans up AF_XDP (removes rebind, explicit cache alignment from uapi, etc).
2) David Ahern adds mtu checks to bpf_ipv{4,6}_fib_lookup() helpers.
3) Jesper Dangaard Brouer adds bulking support to ndo_xdp_xmit.
4) Jiong Wang adds support for indirect and arithmetic shifts to NFP
5) Martin KaFai Lau cleans up BTF uapi and makes the btf_header extensible.
6) Mathieu Xhonneux adds an End.BPF action to seg6local with BPF helpers allowing
to edit/grow/shrink a SRH and apply on a packet generic SRv6 actions.
7) Sandipan Das adds support for bpf2bpf function calls in ppc64 JIT.
8) Yonghong Song adds BPF_TASK_FD_QUERY command for introspection of tracing events.
9) other misc fixes from Gustavo A. R. Silva, Sirio Balmelli, John Fastabend, and Magnus Karlsson
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/arraymap.c | 2 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 334 | ||||
-rw-r--r-- | kernel/bpf/cpumap.c | 2 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 131 | ||||
-rw-r--r-- | kernel/bpf/sockmap.c | 4 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 245 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 23 | ||||
-rw-r--r-- | kernel/bpf/xskmap.c | 9 |
8 files changed, 614 insertions, 136 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0fd8d8f1a398..544e58f5f642 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -352,7 +352,7 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, } seq_printf(m, "%u: ", *(u32 *)key); - btf_type_seq_show(map->btf, map->btf_value_id, value, m); + btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_puts(m, "\n"); rcu_read_unlock(); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ded10ab47b8a..7e90fd13b5b5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -12,6 +12,7 @@ #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/idr.h> +#include <linux/sort.h> #include <linux/bpf_verifier.h> #include <linux/btf.h> @@ -162,13 +163,16 @@ #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) +#define BTF_INFO_MASK 0x0f00ffff +#define BTF_INT_MASK 0x0fffffff +#define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) +#define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) + /* 16MB for 64k structs and each has 16 members and * a few MB spaces for the string section. * The hard limit is S32_MAX. */ #define BTF_MAX_SIZE (16 * 1024 * 1024) -/* 64k. We can raise it later. The hard limit is S32_MAX. */ -#define BTF_MAX_NR_TYPES 65535 #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ @@ -184,15 +188,13 @@ static DEFINE_IDR(btf_idr); static DEFINE_SPINLOCK(btf_idr_lock); struct btf { - union { - struct btf_header *hdr; - void *data; - }; + void *data; struct btf_type **types; u32 *resolved_ids; u32 *resolved_sizes; const char *strings; void *nohdr_data; + struct btf_header hdr; u32 nr_types; u32 types_size; u32 data_size; @@ -228,6 +230,11 @@ enum resolve_mode { #define MAX_RESOLVE_DEPTH 32 +struct btf_sec_info { + u32 off; + u32 len; +}; + struct btf_verifier_env { struct btf *btf; u8 *visit_states; @@ -379,8 +386,6 @@ static const char *btf_int_encoding_str(u8 encoding) return "CHAR"; else if (encoding == BTF_INT_BOOL) return "BOOL"; - else if (encoding == BTF_INT_VARARGS) - return "VARARGS"; else return "UNKN"; } @@ -417,16 +422,16 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) static bool btf_name_offset_valid(const struct btf *btf, u32 offset) { - return !BTF_STR_TBL_ELF_ID(offset) && - BTF_STR_OFFSET(offset) < btf->hdr->str_len; + return BTF_STR_OFFSET_VALID(offset) && + offset < btf->hdr.str_len; } static const char *btf_name_by_offset(const struct btf *btf, u32 offset) { - if (!BTF_STR_OFFSET(offset)) + if (!offset) return "(anon)"; - else if (BTF_STR_OFFSET(offset) < btf->hdr->str_len) - return &btf->strings[BTF_STR_OFFSET(offset)]; + else if (offset < btf->hdr.str_len) + return &btf->strings[offset]; else return "(invalid-name-offset)"; } @@ -439,6 +444,28 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) return btf->types[type_id]; } +/* + * Regular int is not a bit field and it must be either + * u8/u16/u32/u64. + */ +static bool btf_type_int_is_regular(const struct btf_type *t) +{ + u16 nr_bits, nr_bytes; + u32 int_data; + + int_data = btf_type_int(t); + nr_bits = BTF_INT_BITS(int_data); + nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); + if (BITS_PER_BYTE_MASKED(nr_bits) || + BTF_INT_OFFSET(int_data) || + (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && + nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) { + return false; + } + + return true; +} + __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, const char *fmt, ...) { @@ -536,7 +563,8 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, __btf_verifier_log(log, "\n"); } -static void btf_verifier_log_hdr(struct btf_verifier_env *env) +static void btf_verifier_log_hdr(struct btf_verifier_env *env, + u32 btf_data_size) { struct bpf_verifier_log *log = &env->log; const struct btf *btf = env->btf; @@ -545,19 +573,16 @@ static void btf_verifier_log_hdr(struct btf_verifier_env *env) if (!bpf_verifier_log_needed(log)) return; - hdr = btf->hdr; + hdr = &btf->hdr; __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); __btf_verifier_log(log, "version: %u\n", hdr->version); __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); - __btf_verifier_log(log, "parent_label: %u\n", hdr->parent_label); - __btf_verifier_log(log, "parent_name: %u\n", hdr->parent_name); - __btf_verifier_log(log, "label_off: %u\n", hdr->label_off); - __btf_verifier_log(log, "object_off: %u\n", hdr->object_off); - __btf_verifier_log(log, "func_off: %u\n", hdr->func_off); + __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len); __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); + __btf_verifier_log(log, "type_len: %u\n", hdr->type_len); __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); - __btf_verifier_log(log, "btf_total_size: %u\n", btf->data_size); + __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size); } static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) @@ -574,13 +599,13 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) struct btf_type **new_types; u32 expand_by, new_size; - if (btf->types_size == BTF_MAX_NR_TYPES) { + if (btf->types_size == BTF_MAX_TYPE) { btf_verifier_log(env, "Exceeded max num of types"); return -E2BIG; } expand_by = max_t(u32, btf->types_size >> 2, 16); - new_size = min_t(u32, BTF_MAX_NR_TYPES, + new_size = min_t(u32, BTF_MAX_TYPE, btf->types_size + expand_by); new_types = kvzalloc(new_size * sizeof(*new_types), @@ -910,6 +935,12 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env, } int_data = btf_type_int(t); + if (int_data & ~BTF_INT_MASK) { + btf_verifier_log_basic(env, t, "Invalid int_data:%x", + int_data); + return -EINVAL; + } + nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); if (nr_bits > BITS_PER_U64) { @@ -923,12 +954,17 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* + * Only one of the encoding bits is allowed and it + * should be sufficient for the pretty print purpose (i.e. decoding). + * Multiple bits can be allowed later if it is found + * to be insufficient. + */ encoding = BTF_INT_ENCODING(int_data); if (encoding && encoding != BTF_INT_SIGNED && encoding != BTF_INT_CHAR && - encoding != BTF_INT_BOOL && - encoding != BTF_INT_VARARGS) { + encoding != BTF_INT_BOOL) { btf_verifier_log_type(env, t, "Unsupported encoding"); return -ENOTSUPP; } @@ -1102,7 +1138,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (BTF_TYPE_PARENT(t->type)) { + if (!BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } @@ -1306,14 +1342,16 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env, return -EINVAL; } - /* We are a little forgiving on array->index_type since - * the kernel is not using it. - */ - /* Array elem cannot be in type void, - * so !array->type is not allowed. + /* Array elem type and index type cannot be in type void, + * so !array->type and !array->index_type are not allowed. */ - if (!array->type || BTF_TYPE_PARENT(array->type)) { - btf_verifier_log_type(env, t, "Invalid type_id"); + if (!array->type || !BTF_TYPE_ID_VALID(array->type)) { + btf_verifier_log_type(env, t, "Invalid elem"); + return -EINVAL; + } + + if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) { + btf_verifier_log_type(env, t, "Invalid index"); return -EINVAL; } @@ -1326,11 +1364,32 @@ static int btf_array_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_array *array = btf_type_array(v->t); - const struct btf_type *elem_type; - u32 elem_type_id = array->type; + const struct btf_type *elem_type, *index_type; + u32 elem_type_id, index_type_id; struct btf *btf = env->btf; u32 elem_size; + /* Check array->index_type */ + index_type_id = array->index_type; + index_type = btf_type_by_id(btf, index_type_id); + if (btf_type_is_void_or_null(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, index_type) && + !env_type_is_resolved(env, index_type_id)) + return env_stack_push(env, index_type, index_type_id); + + index_type = btf_type_id_size(btf, &index_type_id, NULL); + if (!index_type || !btf_type_is_int(index_type) || + !btf_type_int_is_regular(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + /* Check array->type */ + elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); if (btf_type_is_void_or_null(elem_type)) { btf_verifier_log_type(env, v->t, @@ -1348,22 +1407,9 @@ static int btf_array_resolve(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_is_int(elem_type)) { - int int_type_data = btf_type_int(elem_type); - u16 nr_bits = BTF_INT_BITS(int_type_data); - u16 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); - - /* Put more restriction on array of int. The int cannot - * be a bit field and it must be either u8/u16/u32/u64. - */ - if (BITS_PER_BYTE_MASKED(nr_bits) || - BTF_INT_OFFSET(int_type_data) || - (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && - nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) { - btf_verifier_log_type(env, v->t, - "Invalid array of int"); - return -EINVAL; - } + if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) { + btf_verifier_log_type(env, v->t, "Invalid array of int"); + return -EINVAL; } if (array->nelems && elem_size > U32_MAX / array->nelems) { @@ -1473,7 +1519,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, } /* A member cannot be in type void */ - if (!member->type || BTF_TYPE_PARENT(member->type)) { + if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { btf_verifier_log_member(env, t, member, "Invalid type_id"); return -EINVAL; @@ -1726,6 +1772,12 @@ static s32 btf_check_meta(struct btf_verifier_env *env, } meta_left -= sizeof(*t); + if (t->info & ~BTF_INFO_MASK) { + btf_verifier_log(env, "[%u] Invalid btf_info:%x", + env->log_type_id, t->info); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { btf_verifier_log(env, "[%u] Invalid kind:%u", @@ -1754,9 +1806,9 @@ static int btf_check_all_metas(struct btf_verifier_env *env) struct btf_header *hdr; void *cur, *end; - hdr = btf->hdr; + hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; - end = btf->nohdr_data + hdr->str_off; + end = btf->nohdr_data + hdr->type_len; env->log_type_id = 1; while (cur < end) { @@ -1866,8 +1918,20 @@ static int btf_check_all_types(struct btf_verifier_env *env) static int btf_parse_type_sec(struct btf_verifier_env *env) { + const struct btf_header *hdr = &env->btf->hdr; int err; + /* Type section must align to 4 bytes */ + if (hdr->type_off & (sizeof(u32) - 1)) { + btf_verifier_log(env, "Unaligned type_off"); + return -EINVAL; + } + + if (!hdr->type_len) { + btf_verifier_log(env, "No type found"); + return -EINVAL; + } + err = btf_check_all_metas(env); if (err) return err; @@ -1881,10 +1945,15 @@ static int btf_parse_str_sec(struct btf_verifier_env *env) struct btf *btf = env->btf; const char *start, *end; - hdr = btf->hdr; + hdr = &btf->hdr; start = btf->nohdr_data + hdr->str_off; end = start + hdr->str_len; + if (end != btf->data + btf->data_size) { + btf_verifier_log(env, "String section is not at the end"); + return -EINVAL; + } + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || start[0] || end[-1]) { btf_verifier_log(env, "Invalid string section"); @@ -1896,20 +1965,121 @@ static int btf_parse_str_sec(struct btf_verifier_env *env) return 0; } -static int btf_parse_hdr(struct btf_verifier_env *env) +static const size_t btf_sec_info_offset[] = { + offsetof(struct btf_header, type_off), + offsetof(struct btf_header, str_off), +}; + +static int btf_sec_info_cmp(const void *a, const void *b) +{ + const struct btf_sec_info *x = a; + const struct btf_sec_info *y = b; + + return (int)(x->off - y->off) ? : (int)(x->len - y->len); +} + +static int btf_check_sec_info(struct btf_verifier_env *env, + u32 btf_data_size) { + struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)]; + u32 total, expected_total, i; const struct btf_header *hdr; - struct btf *btf = env->btf; - u32 meta_left; + const struct btf *btf; + + btf = env->btf; + hdr = &btf->hdr; - if (btf->data_size < sizeof(*hdr)) { + /* Populate the secs from hdr */ + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) + secs[i] = *(struct btf_sec_info *)((void *)hdr + + btf_sec_info_offset[i]); + + sort(secs, ARRAY_SIZE(btf_sec_info_offset), + sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL); + + /* Check for gaps and overlap among sections */ + total = 0; + expected_total = btf_data_size - hdr->hdr_len; + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) { + if (expected_total < secs[i].off) { + btf_verifier_log(env, "Invalid section offset"); + return -EINVAL; + } + if (total < secs[i].off) { + /* gap */ + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + if (total > secs[i].off) { + btf_verifier_log(env, "Section overlap found"); + return -EINVAL; + } + if (expected_total - total < secs[i].len) { + btf_verifier_log(env, + "Total section length too long"); + return -EINVAL; + } + total += secs[i].len; + } + + /* There is data other than hdr and known sections */ + if (expected_total != total) { + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + + return 0; +} + +static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, + u32 btf_data_size) +{ + const struct btf_header *hdr; + u32 hdr_len, hdr_copy; + /* + * Minimal part of the "struct btf_header" that + * contains the hdr_len. + */ + struct btf_min_header { + u16 magic; + u8 version; + u8 flags; + u32 hdr_len; + } __user *min_hdr; + struct btf *btf; + int err; + + btf = env->btf; + min_hdr = btf_data; + + if (btf_data_size < sizeof(*min_hdr)) { + btf_verifier_log(env, "hdr_len not found"); + return -EINVAL; + } + + if (get_user(hdr_len, &min_hdr->hdr_len)) + return -EFAULT; + + if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } - btf_verifier_log_hdr(env); + err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); + if (err) { + if (err == -E2BIG) + btf_verifier_log(env, "Unsupported btf_header"); + return err; + } + + hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); + if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) + return -EFAULT; + + hdr = &btf->hdr; + + btf_verifier_log_hdr(env, btf_data_size); - hdr = btf->hdr; if (hdr->magic != BTF_MAGIC) { btf_verifier_log(env, "Invalid magic"); return -EINVAL; @@ -1925,26 +2095,14 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return -ENOTSUPP; } - meta_left = btf->data_size - sizeof(*hdr); - if (!meta_left) { + if (btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } - if (meta_left < hdr->type_off || hdr->str_off <= hdr->type_off || - /* Type section must align to 4 bytes */ - hdr->type_off & (sizeof(u32) - 1)) { - btf_verifier_log(env, "Invalid type_off"); - return -EINVAL; - } - - if (meta_left < hdr->str_off || - meta_left - hdr->str_off < hdr->str_len) { - btf_verifier_log(env, "Invalid str_off or str_len"); - return -EINVAL; - } - - btf->nohdr_data = btf->hdr + 1; + err = btf_check_sec_info(env, btf_data_size); + if (err) + return err; return 0; } @@ -1987,6 +2145,11 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, err = -ENOMEM; goto errout; } + env->btf = btf; + + err = btf_parse_hdr(env, btf_data, btf_data_size); + if (err) + goto errout; data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { @@ -1996,18 +2159,13 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; + btf->nohdr_data = btf->data + btf->hdr.hdr_len; if (copy_from_user(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } - env->btf = btf; - - err = btf_parse_hdr(env); - if (err) - goto errout; - err = btf_parse_str_sec(env); if (err) goto errout; @@ -2016,16 +2174,14 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, if (err) goto errout; - if (!err && log->level && bpf_verifier_log_full(log)) { + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; goto errout; } - if (!err) { - btf_verifier_env_free(env); - refcount_set(&btf->refcnt, 1); - return btf; - } + btf_verifier_env_free(env); + refcount_set(&btf->refcnt, 1); + return btf; errout: btf_verifier_env_free(env); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index c95b04ec103e..e0918d180f08 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -578,7 +578,7 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - xdp_return_frame(xdpf); + xdp_return_frame_rx_napi(xdpf); } processed++; } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 565f9ece9115..ae16d0c373ef 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -48,15 +48,25 @@ * calls will fail at this point. */ #include <linux/bpf.h> +#include <net/xdp.h> #include <linux/filter.h> +#include <trace/events/xdp.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +#define DEV_MAP_BULK_SIZE 16 +struct xdp_bulk_queue { + struct xdp_frame *q[DEV_MAP_BULK_SIZE]; + struct net_device *dev_rx; + unsigned int count; +}; + struct bpf_dtab_netdev { - struct net_device *dev; + struct net_device *dev; /* must be first member, due to tracepoint */ struct bpf_dtab *dtab; unsigned int bit; + struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; }; @@ -206,6 +216,50 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) __set_bit(bit, bitmap); } +static int bq_xmit_all(struct bpf_dtab_netdev *obj, + struct xdp_bulk_queue *bq) +{ + struct net_device *dev = obj->dev; + int sent = 0, drops = 0, err = 0; + int i; + + if (unlikely(!bq->count)) + return 0; + + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + prefetch(xdpf); + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q); + if (sent < 0) { + err = sent; + sent = 0; + goto error; + } + drops = bq->count - sent; +out: + bq->count = 0; + + trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + sent, drops, bq->dev_rx, dev, err); + bq->dev_rx = NULL; + return 0; +error: + /* If ndo_xdp_xmit fails with an errno, no frames have been + * xmit'ed and it's our responsibility to them free all. + */ + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + /* RX path under NAPI protection, can return frames faster */ + xdp_return_frame_rx_napi(xdpf); + drops++; + } + goto out; +} + /* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled @@ -221,6 +275,7 @@ void __dev_map_flush(struct bpf_map *map) for_each_set_bit(bit, bitmap, map->max_entries) { struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); + struct xdp_bulk_queue *bq; struct net_device *netdev; /* This is possible if the dev entry is removed by user space @@ -230,6 +285,9 @@ void __dev_map_flush(struct bpf_map *map) continue; __clear_bit(bit, bitmap); + + bq = this_cpu_ptr(dev->bulkq); + bq_xmit_all(dev, bq); netdev = dev->dev; if (likely(netdev->netdev_ops->ndo_xdp_flush)) netdev->netdev_ops->ndo_xdp_flush(netdev); @@ -240,21 +298,61 @@ void __dev_map_flush(struct bpf_map *map) * update happens in parallel here a dev_put wont happen until after reading the * ifindex. */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct bpf_dtab_netdev *dev; + struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; - dev = READ_ONCE(dtab->netdev_map[key]); - return dev ? dev->dev : NULL; + obj = READ_ONCE(dtab->netdev_map[key]); + return obj; +} + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, + struct net_device *dev_rx) + +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + + if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) + bq_xmit_all(obj, bq); + + /* Ingress dev_rx will be the same for all xdp_frame's in + * bulk_queue, because bq stored per-CPU and must be flushed + * from net_device drivers NAPI func end. + */ + if (!bq->dev_rx) + bq->dev_rx = dev_rx; + + bq->q[bq->count++] = xdpf; + return 0; +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + struct xdp_frame *xdpf; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + return bq_enqueue(dst, xdpf, dev_rx); } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { - struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key); + struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); + struct net_device *dev = dev = obj ? obj->dev : NULL; return dev ? &dev->ifindex : NULL; } @@ -263,13 +361,18 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_flush) { struct net_device *fl = dev->dev; + struct xdp_bulk_queue *bq; unsigned long *bitmap; + int cpu; for_each_online_cpu(cpu) { bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); __clear_bit(dev->bit, bitmap); + bq = per_cpu_ptr(dev->bulkq, cpu); + bq_xmit_all(dev, bq); + fl->netdev_ops->ndo_xdp_flush(dev->dev); } } @@ -281,6 +384,7 @@ static void __dev_map_entry_free(struct rcu_head *rcu) dev = container_of(rcu, struct bpf_dtab_netdev, rcu); dev_map_flush_old(dev); + free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -313,6 +417,7 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct net *net = current->nsproxy->net_ns; + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; u32 i = *(u32 *)key; u32 ifindex = *(u32 *)value; @@ -327,13 +432,20 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); if (!dev) return -ENOMEM; + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return -ENOMEM; + } + dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { + free_percpu(dev->bulkq); kfree(dev); return -EINVAL; } @@ -405,6 +517,9 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { + /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ + BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != + offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cd832250a478..52a91d816c0e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -523,6 +523,7 @@ static unsigned int smap_do_tx_msg(struct sock *sk, } bpf_compute_data_pointers_sg(md); + md->sk = sk; rc = (*prog->bpf_func)(md, prog->insnsi); psock->apply_bytes = md->apply_bytes; @@ -1713,7 +1714,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, struct smap_psock_map_entry *e = NULL; struct smap_psock *psock; bool new = false; - int err; + int err = 0; /* 1. If sock map has BPF programs those will be inherited by the * sock being added. If the sock is already attached to BPF programs @@ -1823,7 +1824,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, write_unlock_bh(&sock->sk_callback_lock); return err; out_free: - kfree(e); smap_release_sock(psock, sock); out_progs: if (parse && verdict) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index bfcde949c7f8..388d4feda348 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -18,7 +18,9 @@ #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> +#include <linux/fdtable.h> #include <linux/file.h> +#include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/version.h> @@ -65,9 +67,9 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -static int check_uarg_tail_zero(void __user *uaddr, - size_t expected_size, - size_t actual_size) +int bpf_check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) { unsigned char __user *addr; unsigned char __user *end; @@ -422,7 +424,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD btf_value_id +#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -457,10 +459,10 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->usercnt, 1); if (bpf_map_support_seq_show(map) && - (attr->btf_key_id || attr->btf_value_id)) { + (attr->btf_key_type_id || attr->btf_value_type_id)) { struct btf *btf; - if (!attr->btf_key_id || !attr->btf_value_id) { + if (!attr->btf_key_type_id || !attr->btf_value_type_id) { err = -EINVAL; goto free_map_nouncharge; } @@ -471,16 +473,16 @@ static int map_create(union bpf_attr *attr) goto free_map_nouncharge; } - err = map->ops->map_check_btf(map, btf, attr->btf_key_id, - attr->btf_value_id); + err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); if (err) { btf_put(btf); goto free_map_nouncharge; } map->btf = btf; - map->btf_key_id = attr->btf_key_id; - map->btf_value_id = attr->btf_value_id; + map->btf_key_type_id = attr->btf_key_type_id; + map->btf_value_type_id = attr->btf_value_type_id; } err = security_bpf_map_alloc(map); @@ -1899,7 +1901,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, u32 ulen; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -1933,6 +1935,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; info.xlated_prog_len = 0; + info.nr_jited_ksyms = 0; goto done; } @@ -1969,18 +1972,93 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, * for offload. */ ulen = info.jited_prog_len; - info.jited_prog_len = prog->jited_len; + if (prog->aux->func_cnt) { + u32 i; + + info.jited_prog_len = 0; + for (i = 0; i < prog->aux->func_cnt; i++) + info.jited_prog_len += prog->aux->func[i]->jited_len; + } else { + info.jited_prog_len = prog->jited_len; + } + if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok()) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); - if (copy_to_user(uinsns, prog->bpf_func, ulen)) - return -EFAULT; + + /* for multi-function programs, copy the JITed + * instructions for all the functions + */ + if (prog->aux->func_cnt) { + u32 len, free, i; + u8 *img; + + free = ulen; + for (i = 0; i < prog->aux->func_cnt; i++) { + len = prog->aux->func[i]->jited_len; + len = min_t(u32, len, free); + img = (u8 *) prog->aux->func[i]->bpf_func; + if (copy_to_user(uinsns, img, len)) + return -EFAULT; + uinsns += len; + free -= len; + if (!free) + break; + } + } else { + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } } else { info.jited_prog_insns = 0; } } + ulen = info.nr_jited_ksyms; + info.nr_jited_ksyms = prog->aux->func_cnt; + if (info.nr_jited_ksyms && ulen) { + if (bpf_dump_raw_ok()) { + u64 __user *user_ksyms; + ulong ksym_addr; + u32 i; + + /* copy the address of the kernel symbol + * corresponding to each function + */ + ulen = min_t(u32, info.nr_jited_ksyms, ulen); + user_ksyms = u64_to_user_ptr(info.jited_ksyms); + for (i = 0; i < ulen; i++) { + ksym_addr = (ulong) prog->aux->func[i]->bpf_func; + ksym_addr &= PAGE_MASK; + if (put_user((u64) ksym_addr, &user_ksyms[i])) + return -EFAULT; + } + } else { + info.jited_ksyms = 0; + } + } + + ulen = info.nr_jited_func_lens; + info.nr_jited_func_lens = prog->aux->func_cnt; + if (info.nr_jited_func_lens && ulen) { + if (bpf_dump_raw_ok()) { + u32 __user *user_lens; + u32 func_len, i; + + /* copy the JITed image lengths for each function */ + ulen = min_t(u32, info.nr_jited_func_lens, ulen); + user_lens = u64_to_user_ptr(info.jited_func_lens); + for (i = 0; i < ulen; i++) { + func_len = prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + info.jited_func_lens = 0; + } + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -1998,7 +2076,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, u32 info_len = attr->info.info_len; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -2013,8 +2091,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, if (map->btf) { info.btf_id = btf_id(map->btf); - info.btf_key_id = map->btf_key_id; - info.btf_value_id = map->btf_value_id; + info.btf_key_type_id = map->btf_key_type_id; + info.btf_value_type_id = map->btf_value_type_id; } if (bpf_map_is_dev_bound(map)) { @@ -2038,7 +2116,7 @@ static int bpf_btf_get_info_by_fd(struct btf *btf, u32 info_len = attr->info.info_len; int err; - err = check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); if (err) return err; @@ -2102,6 +2180,132 @@ static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) return btf_get_fd_by_id(attr->btf_id); } +static int bpf_task_fd_query_copy(const union bpf_attr *attr, + union bpf_attr __user *uattr, + u32 prog_id, u32 fd_type, + const char *buf, u64 probe_offset, + u64 probe_addr) +{ + char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); + u32 len = buf ? strlen(buf) : 0, input_len; + int err = 0; + + if (put_user(len, &uattr->task_fd_query.buf_len)) + return -EFAULT; + input_len = attr->task_fd_query.buf_len; + if (input_len && ubuf) { + if (!len) { + /* nothing to copy, just make ubuf NULL terminated */ + char zero = '\0'; + + if (put_user(zero, ubuf)) + return -EFAULT; + } else if (input_len >= len + 1) { + /* ubuf can hold the string with NULL terminator */ + if (copy_to_user(ubuf, buf, len + 1)) + return -EFAULT; + } else { + /* ubuf cannot hold the string with NULL terminator, + * do a partial copy with NULL terminator. + */ + char zero = '\0'; + + err = -ENOSPC; + if (copy_to_user(ubuf, buf, input_len - 1)) + return -EFAULT; + if (put_user(zero, ubuf + input_len - 1)) + return -EFAULT; + } + } + + if (put_user(prog_id, &uattr->task_fd_query.prog_id) || + put_user(fd_type, &uattr->task_fd_query.fd_type) || + put_user(probe_offset, &uattr->task_fd_query.probe_offset) || + put_user(probe_addr, &uattr->task_fd_query.probe_addr)) + return -EFAULT; + + return err; +} + +#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr + +static int bpf_task_fd_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + pid_t pid = attr->task_fd_query.pid; + u32 fd = attr->task_fd_query.fd; + const struct perf_event *event; + struct files_struct *files; + struct task_struct *task; + struct file *file; + int err; + + if (CHECK_ATTR(BPF_TASK_FD_QUERY)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->task_fd_query.flags != 0) + return -EINVAL; + + task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + if (!task) + return -ENOENT; + + files = get_files_struct(task); + put_task_struct(task); + if (!files) + return -ENOENT; + + err = 0; + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (!file) + err = -EBADF; + else + get_file(file); + spin_unlock(&files->file_lock); + put_files_struct(files); + + if (err) + goto out; + + if (file->f_op == &bpf_raw_tp_fops) { + struct bpf_raw_tracepoint *raw_tp = file->private_data; + struct bpf_raw_event_map *btp = raw_tp->btp; + + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + + event = perf_get_event(file); + if (!IS_ERR(event)) { + u64 probe_offset, probe_addr; + u32 prog_id, fd_type; + const char *buf; + + err = bpf_get_perf_event_info(event, &prog_id, &fd_type, + &buf, &probe_offset, + &probe_addr); + if (!err) + err = bpf_task_fd_query_copy(attr, uattr, prog_id, + fd_type, buf, + probe_offset, + probe_addr); + goto put_file; + } + + err = -ENOTSUPP; +put_file: + fput(file); +out: + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2110,7 +2314,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; - err = check_uarg_tail_zero(uattr, sizeof(attr), size); + err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); @@ -2188,6 +2392,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; + case BPF_TASK_FD_QUERY: + err = bpf_task_fd_query(&attr, uattr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a9e4b1372da6..967cacf286ea 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1262,6 +1262,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, switch (env->prog->type) { case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: /* dst_input() and dst_output() can't write for now */ if (t == BPF_WRITE) return false; @@ -5383,11 +5384,24 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->src_reg != BPF_PSEUDO_CALL) continue; subprog = insn->off; - insn->off = 0; insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) func[subprog]->bpf_func - __bpf_call_base; } + + /* we use the aux data to keep a list of the start addresses + * of the JITed images for each function in the program + * + * for some architectures, such as powerpc64, the imm field + * might not be large enough to hold the offset of the start + * address of the callee's JITed image from __bpf_call_base + * + * in such cases, we can lookup the start address of a callee + * by using its subprog id, available from the off field of + * the call instruction, as an index for this list + */ + func[i]->aux->func = func; + func[i]->aux->func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; @@ -5413,17 +5427,12 @@ static int jit_subprogs(struct bpf_verifier_env *env) * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - unsigned long addr; - if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); - addr = (unsigned long)func[subprog]->bpf_func; - addr &= PAGE_MASK; - insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) - addr - __bpf_call_base; + insn->imm = subprog; } prog->jited = 1; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index cb3a12137404..b3c557476a8d 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -1,15 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* XSKMAP used for AF_XDP sockets * Copyright(c) 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/bpf.h> |