aboutsummaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
authorThomas Gleixner <[email protected]>2018-09-15 20:50:42 +0200
committerThomas Gleixner <[email protected]>2018-09-15 20:50:42 +0200
commit9ac669fc01dbfef707ecaa6b618c0d03294cca16 (patch)
tree3207995766ab5664c60026daae5da268806a3262 /kernel/bpf
parentfbfa9260085b5b578a049a90135e5c51928c5f7f (diff)
parent67314ec7b0250290cc85eaa7a2f88a8ddb9e8547 (diff)
Merge tag 'y2038' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/playground into timers/core
Pull more y2038 work from Arnd Bergman: y2038: convert more syscalls Here is another set of system call changes to prepare the change over to 64-bit time_t. As before, the strategy is to change system calls that take a 'struct timespec' argument over to 'struct __kernel_timespec', which for now is defined to be the same but will get redefined to use a 64-bit time_t argument once we are ready to modify the system call tables. The major change from previous patches is that the plan is no longer to directly use the 'compat' system calls for providing compatibility with the existing 32-bit time_t based entry points. Instead, we rename the compat code to something that makes more sense on 32-bit architectures, e.g. compat_timespec becomes old_timespec32. With the renamed types in place, change over the 'stat' and 'utimes' families of system calls, sched_rr_get_interval, recvmmsg and rt_sigtimedwait. Another series for poll, select and io_pgetevents is currently being tested.
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/Makefile4
-rw-r--r--kernel/bpf/arraymap.c28
-rw-r--r--kernel/bpf/btf.c60
-rw-r--r--kernel/bpf/cgroup.c216
-rw-r--r--kernel/bpf/core.c109
-rw-r--r--kernel/bpf/cpumap.c18
-rw-r--r--kernel/bpf/devmap.c23
-rw-r--r--kernel/bpf/hashtab.c42
-rw-r--r--kernel/bpf/helpers.c20
-rw-r--r--kernel/bpf/inode.c11
-rw-r--r--kernel/bpf/local_storage.c379
-rw-r--r--kernel/bpf/lpm_trie.c12
-rw-r--r--kernel/bpf/map_in_map.c3
-rw-r--r--kernel/bpf/offload.c223
-rw-r--r--kernel/bpf/reuseport_array.c363
-rw-r--r--kernel/bpf/sockmap.c409
-rw-r--r--kernel/bpf/stackmap.c1
-rw-r--r--kernel/bpf/syscall.c210
-rw-r--r--kernel/bpf/verifier.c87
-rw-r--r--kernel/bpf/xskmap.c4
20 files changed, 1712 insertions, 510 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f27f5496d6fe..0488b8258321 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -3,6 +3,7 @@ obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
ifeq ($(CONFIG_NET),y)
@@ -22,3 +23,6 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
obj-$(CONFIG_CGROUP_BPF) += cgroup.o
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
+endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 544e58f5f642..0c17aab3ce5f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -54,7 +54,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
}
/* Called from syscall */
-static int array_map_alloc_check(union bpf_attr *attr)
+int array_map_alloc_check(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int numa_node = bpf_map_attr_numa_node(attr);
@@ -358,27 +358,20 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
rcu_read_unlock();
}
-static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
- u32 btf_key_id, u32 btf_value_id)
+static int array_map_check_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
{
- const struct btf_type *key_type, *value_type;
- u32 key_size, value_size;
u32 int_data;
- key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
- if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
int_data = *(u32 *)(key_type + 1);
- /* bpf array can only take a u32 key. This check makes
- * sure that the btf matches the attr used during map_create.
+ /* bpf array can only take a u32 key. This check makes sure
+ * that the btf matches the attr used during map_create.
*/
- if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
- BTF_INT_OFFSET(int_data))
- return -EINVAL;
-
- value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
- if (!value_type || value_size > map->value_size)
+ if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
return -EINVAL;
return 0;
@@ -405,6 +398,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
.map_lookup_elem = percpu_array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
+ .map_check_btf = array_map_check_btf,
};
static int fd_array_map_alloc_check(union bpf_attr *attr)
@@ -546,6 +540,7 @@ const struct bpf_map_ops prog_array_map_ops = {
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
.map_release_uref = bpf_fd_array_map_clear,
+ .map_check_btf = map_check_no_btf,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
@@ -634,6 +629,7 @@ const struct bpf_map_ops perf_event_array_map_ops = {
.map_fd_get_ptr = perf_event_fd_array_get_ptr,
.map_fd_put_ptr = perf_event_fd_array_put_ptr,
.map_release = perf_event_fd_array_release,
+ .map_check_btf = map_check_no_btf,
};
#ifdef CONFIG_CGROUPS
@@ -665,6 +661,7 @@ const struct bpf_map_ops cgroup_array_map_ops = {
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = cgroup_fd_array_get_ptr,
.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+ .map_check_btf = map_check_no_btf,
};
#endif
@@ -749,4 +746,5 @@ const struct bpf_map_ops array_of_maps_map_ops = {
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = array_of_map_gen_lookup,
+ .map_check_btf = map_check_no_btf,
};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..2590700237c1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
-
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u64_num >>= bits_offset;
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
@@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
+ u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
- u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
+ last_offset = 0;
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
@@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
@@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
}
btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
}
return meta_needed;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..6a7d931bbc55 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -34,6 +34,8 @@ void cgroup_bpf_put(struct cgroup *cgrp)
list_for_each_entry_safe(pl, tmp, progs, node) {
list_del(&pl->node);
bpf_prog_put(pl->prog);
+ bpf_cgroup_storage_unlink(pl->storage);
+ bpf_cgroup_storage_free(pl->storage);
kfree(pl);
static_branch_dec(&cgroup_bpf_enabled_key);
}
@@ -95,7 +97,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
enum bpf_attach_type type,
struct bpf_prog_array __rcu **array)
{
- struct bpf_prog_array __rcu *progs;
+ struct bpf_prog_array *progs;
struct bpf_prog_list *pl;
struct cgroup *p = cgrp;
int cnt = 0;
@@ -115,18 +117,20 @@ static int compute_effective_progs(struct cgroup *cgrp,
cnt = 0;
p = cgrp;
do {
- if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
- list_for_each_entry(pl,
- &p->bpf.progs[type], node) {
- if (!pl->prog)
- continue;
- rcu_dereference_protected(progs, 1)->
- progs[cnt++] = pl->prog;
- }
- p = cgroup_parent(p);
- } while (p);
+ if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ continue;
+
+ list_for_each_entry(pl, &p->bpf.progs[type], node) {
+ if (!pl->prog)
+ continue;
+
+ progs->items[cnt].prog = pl->prog;
+ progs->items[cnt].cgroup_storage = pl->storage;
+ cnt++;
+ }
+ } while ((p = cgroup_parent(p)));
- *array = progs;
+ rcu_assign_pointer(*array, progs);
return 0;
}
@@ -173,6 +177,45 @@ cleanup:
return -ENOMEM;
}
+static int update_effective_progs(struct cgroup *cgrp,
+ enum bpf_attach_type type)
+{
+ struct cgroup_subsys_state *css;
+ int err;
+
+ /* allocate and recompute effective prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+ if (err)
+ goto cleanup;
+ }
+
+ /* all allocations were successful. Activate all prog arrays */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ activate_effective_progs(desc, type, desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ return 0;
+
+cleanup:
+ /* oom while computing effective. Free all computed effective arrays
+ * since they were not activated
+ */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ bpf_prog_array_free(desc->bpf.inactive);
+ desc->bpf.inactive = NULL;
+ }
+
+ return err;
+}
+
#define BPF_CGROUP_MAX_PROGS 64
/**
@@ -189,7 +232,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
{
struct list_head *progs = &cgrp->bpf.progs[type];
struct bpf_prog *old_prog = NULL;
- struct cgroup_subsys_state *css;
+ struct bpf_cgroup_storage *storage, *old_storage = NULL;
struct bpf_prog_list *pl;
bool pl_was_allocated;
int err;
@@ -211,72 +254,71 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
return -E2BIG;
+ storage = bpf_cgroup_storage_alloc(prog);
+ if (IS_ERR(storage))
+ return -ENOMEM;
+
if (flags & BPF_F_ALLOW_MULTI) {
- list_for_each_entry(pl, progs, node)
- if (pl->prog == prog)
+ list_for_each_entry(pl, progs, node) {
+ if (pl->prog == prog) {
/* disallow attaching the same prog twice */
+ bpf_cgroup_storage_free(storage);
return -EINVAL;
+ }
+ }
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
- if (!pl)
+ if (!pl) {
+ bpf_cgroup_storage_free(storage);
return -ENOMEM;
+ }
+
pl_was_allocated = true;
pl->prog = prog;
+ pl->storage = storage;
list_add_tail(&pl->node, progs);
} else {
if (list_empty(progs)) {
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
- if (!pl)
+ if (!pl) {
+ bpf_cgroup_storage_free(storage);
return -ENOMEM;
+ }
pl_was_allocated = true;
list_add_tail(&pl->node, progs);
} else {
pl = list_first_entry(progs, typeof(*pl), node);
old_prog = pl->prog;
+ old_storage = pl->storage;
+ bpf_cgroup_storage_unlink(old_storage);
pl_was_allocated = false;
}
pl->prog = prog;
+ pl->storage = storage;
}
cgrp->bpf.flags[type] = flags;
- /* allocate and recompute effective prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- err = compute_effective_progs(desc, type, &desc->bpf.inactive);
- if (err)
- goto cleanup;
- }
-
- /* all allocations were successful. Activate all prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- activate_effective_progs(desc, type, desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
+ err = update_effective_progs(cgrp, type);
+ if (err)
+ goto cleanup;
static_branch_inc(&cgroup_bpf_enabled_key);
+ if (old_storage)
+ bpf_cgroup_storage_free(old_storage);
if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
+ bpf_cgroup_storage_link(storage, cgrp, type);
return 0;
cleanup:
- /* oom while computing effective. Free all computed effective arrays
- * since they were not activated
- */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- bpf_prog_array_free(desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
-
/* and cleanup the prog list */
pl->prog = old_prog;
+ bpf_cgroup_storage_free(pl->storage);
+ pl->storage = old_storage;
+ bpf_cgroup_storage_link(old_storage, cgrp, type);
if (pl_was_allocated) {
list_del(&pl->node);
kfree(pl);
@@ -299,7 +341,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
struct list_head *progs = &cgrp->bpf.progs[type];
u32 flags = cgrp->bpf.flags[type];
struct bpf_prog *old_prog = NULL;
- struct cgroup_subsys_state *css;
struct bpf_prog_list *pl;
int err;
@@ -338,25 +379,14 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
pl->prog = NULL;
}
- /* allocate and recompute effective prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- err = compute_effective_progs(desc, type, &desc->bpf.inactive);
- if (err)
- goto cleanup;
- }
-
- /* all allocations were successful. Activate all prog arrays */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- activate_effective_progs(desc, type, desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
+ err = update_effective_progs(cgrp, type);
+ if (err)
+ goto cleanup;
/* now can actually delete it from this cgroup list */
list_del(&pl->node);
+ bpf_cgroup_storage_unlink(pl->storage);
+ bpf_cgroup_storage_free(pl->storage);
kfree(pl);
if (list_empty(progs))
/* last program was detached, reset flags to zero */
@@ -367,16 +397,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
return 0;
cleanup:
- /* oom while computing effective. Free all computed effective arrays
- * since they were not activated
- */
- css_for_each_descendant_pre(css, &cgrp->self) {
- struct cgroup *desc = container_of(css, struct cgroup, self);
-
- bpf_prog_array_free(desc->bpf.inactive);
- desc->bpf.inactive = NULL;
- }
-
/* and restore back old_prog */
pl->prog = old_prog;
return err;
@@ -428,6 +448,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
@@ -601,6 +675,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_delete_elem_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a9e6c04d0f4a..3f5bf1af0826 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
- hdr->locked = 0;
-
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
return 0;
}
-static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
-{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- int i, err;
-
- for (i = 0; i < fp->aux->func_cnt; i++) {
- err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
- if (err)
- return err;
- }
-
- return bpf_prog_check_pages_ro_single(fp);
-#endif
- return 0;
-}
-
static void bpf_prog_select_func(struct bpf_prog *fp)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
@@ -1524,17 +1506,7 @@ finalize:
* all eBPF JITs might immediately support all features.
*/
*err = bpf_check_tail_call(fp);
- if (*err)
- return fp;
-
- /* Checkpoint: at this point onwards any cBPF -> eBPF or
- * native eBPF program is read-only. If we failed to change
- * the page attributes (e.g. allocation failure from
- * splitting large pages), then reject the whole program
- * in order to guarantee not ending up with any W+X pages
- * from BPF side in kernel.
- */
- *err = bpf_prog_check_pages_ro_locked(fp);
+
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
@@ -1566,11 +1538,12 @@ static struct {
.null_prog = NULL,
};
-struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
{
if (prog_cnt)
return kzalloc(sizeof(struct bpf_prog_array) +
- sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ sizeof(struct bpf_prog_array_item) *
+ (prog_cnt + 1),
flags);
return &empty_prog_array.hdr;
@@ -1584,43 +1557,45 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
kfree_rcu(progs, rcu);
}
-int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
{
- struct bpf_prog **prog;
+ struct bpf_prog_array_item *item;
u32 cnt = 0;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++)
- if (*prog != &dummy_bpf_prog.prog)
+ item = rcu_dereference(array)->items;
+ for (; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
cnt++;
rcu_read_unlock();
return cnt;
}
-static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
u32 *prog_ids,
u32 request_cnt)
{
+ struct bpf_prog_array_item *item;
int i = 0;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
+ item = rcu_dereference_check(array, 1)->items;
+ for (; item->prog; item++) {
+ if (item->prog == &dummy_bpf_prog.prog)
continue;
- prog_ids[i] = (*prog)->aux->id;
+ prog_ids[i] = item->prog->aux->id;
if (++i == request_cnt) {
- prog++;
+ item++;
break;
}
}
- return !!(*prog);
+ return !!(item->prog);
}
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
__u32 __user *prog_ids, u32 cnt)
{
- struct bpf_prog **prog;
unsigned long err = 0;
bool nospc;
u32 *ids;
@@ -1639,8 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
if (!ids)
return -ENOMEM;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- nospc = bpf_prog_array_copy_core(prog, ids, cnt);
+ nospc = bpf_prog_array_copy_core(array, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
@@ -1651,14 +1625,14 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
return 0;
}
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
struct bpf_prog *old_prog)
{
- struct bpf_prog **prog = progs->progs;
+ struct bpf_prog_array_item *item = array->items;
- for (; *prog; prog++)
- if (*prog == old_prog) {
- WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ for (; item->prog; item++)
+ if (item->prog == old_prog) {
+ WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
break;
}
}
@@ -1669,7 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog_array **new_array)
{
int new_prog_cnt, carry_prog_cnt = 0;
- struct bpf_prog **existing_prog;
+ struct bpf_prog_array_item *existing;
struct bpf_prog_array *array;
bool found_exclude = false;
int new_prog_idx = 0;
@@ -1678,15 +1652,15 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
* the new array.
*/
if (old_array) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++) {
- if (*existing_prog == exclude_prog) {
+ existing = old_array->items;
+ for (; existing->prog; existing++) {
+ if (existing->prog == exclude_prog) {
found_exclude = true;
continue;
}
- if (*existing_prog != &dummy_bpf_prog.prog)
+ if (existing->prog != &dummy_bpf_prog.prog)
carry_prog_cnt++;
- if (*existing_prog == include_prog)
+ if (existing->prog == include_prog)
return -EEXIST;
}
}
@@ -1712,15 +1686,17 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
/* Fill in the new prog array */
if (carry_prog_cnt) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++)
- if (*existing_prog != exclude_prog &&
- *existing_prog != &dummy_bpf_prog.prog)
- array->progs[new_prog_idx++] = *existing_prog;
+ existing = old_array->items;
+ for (; existing->prog; existing++)
+ if (existing->prog != exclude_prog &&
+ existing->prog != &dummy_bpf_prog.prog) {
+ array->items[new_prog_idx++].prog =
+ existing->prog;
+ }
}
if (include_prog)
- array->progs[new_prog_idx++] = include_prog;
- array->progs[new_prog_idx] = NULL;
+ array->items[new_prog_idx++].prog = include_prog;
+ array->items[new_prog_idx].prog = NULL;
*new_array = array;
return 0;
}
@@ -1729,7 +1705,6 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
- struct bpf_prog **prog;
u32 cnt = 0;
if (array)
@@ -1742,8 +1717,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
return 0;
/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
- prog = rcu_dereference_check(array, 1)->progs;
- return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
: 0;
}
@@ -1821,6 +1795,7 @@ const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto bpf_sock_map_update_proto __weak;
const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_local_storage_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..24aac0d0f412 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq);
+ struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
/* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, false);
}
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -479,6 +479,8 @@ static void cpu_map_free(struct bpf_map *map)
* It does __not__ ensure pending flush operations (if any) are
* complete.
*/
+
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* To ensure all pending flush operations have completed wait for flush
@@ -555,10 +557,11 @@ const struct bpf_map_ops cpu_map_ops = {
.map_update_elem = cpu_map_update_elem,
.map_lookup_elem = cpu_map_lookup_elem,
.map_get_next_key = cpu_map_get_next_key,
+ .map_check_btf = map_check_no_btf,
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq)
+ struct xdp_bulk_queue *bq, bool in_napi_ctx)
{
unsigned int processed = 0, drops = 0;
const int to_cpu = rcpu->cpu;
@@ -578,7 +581,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
}
processed++;
}
@@ -598,7 +604,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
@@ -661,7 +667,7 @@ void __cpu_map_flush(struct bpf_map *map)
/* Flush all frames in bulkq to real queue */
bq = this_cpu_ptr(rcpu->bulkq);
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642c97f6d1b8..141710b82a6c 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -161,6 +161,7 @@ static void dev_map_free(struct bpf_map *map)
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
+ bpf_clear_redirect_map(map);
synchronize_rcu();
/* To ensure all pending flush operations have completed wait for flush
@@ -217,7 +218,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
}
static int bq_xmit_all(struct bpf_dtab_netdev *obj,
- struct xdp_bulk_queue *bq, u32 flags)
+ struct xdp_bulk_queue *bq, u32 flags,
+ bool in_napi_ctx)
{
struct net_device *dev = obj->dev;
int sent = 0, drops = 0, err = 0;
@@ -254,7 +256,10 @@ error:
struct xdp_frame *xdpf = bq->q[i];
/* RX path under NAPI protection, can return frames faster */
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
drops++;
}
goto out;
@@ -286,7 +291,7 @@ void __dev_map_flush(struct bpf_map *map)
__clear_bit(bit, bitmap);
bq = this_cpu_ptr(dev->bulkq);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
}
}
@@ -316,7 +321,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
- bq_xmit_all(obj, bq, 0);
+ bq_xmit_all(obj, bq, 0, true);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
@@ -334,10 +339,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
+ int err;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -350,7 +360,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
{
int err;
- err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+ err = xdp_ok_fwd_dev(dst->dev, skb->len);
if (unlikely(err))
return err;
skb->dev = dst->dev;
@@ -380,7 +390,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
__clear_bit(dev->bit, bitmap);
bq = per_cpu_ptr(dev->bulkq, cpu);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
}
}
}
@@ -479,6 +489,7 @@ const struct bpf_map_ops dev_map_ops = {
.map_lookup_elem = dev_map_lookup_elem,
.map_update_elem = dev_map_update_elem,
.map_delete_elem = dev_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
static int dev_map_notification(struct notifier_block *notifier,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..04b8eda94e7d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -11,9 +11,11 @@
* General Public License for more details.
*/
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
+#include <uapi/linux/btf.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
#include "map_in_map.h"
@@ -747,13 +749,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
* old element will be freed immediately.
* Otherwise return an error
*/
- atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
}
l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
htab->map.numa_node);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
}
memcpy(l_new->key, key, key_size);
@@ -766,7 +770,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
- return ERR_PTR(-ENOMEM);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
}
}
@@ -780,6 +785,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new->hash = hash;
return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
}
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
@@ -1156,6 +1164,27 @@ static void htab_map_free(struct bpf_map *map)
kfree(htab);
}
+static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
+ struct seq_file *m)
+{
+ void *value;
+
+ rcu_read_lock();
+
+ value = htab_map_lookup_elem(map, key);
+ if (!value) {
+ rcu_read_unlock();
+ return;
+ }
+
+ btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+ seq_puts(m, ": ");
+ btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
+ seq_puts(m, "\n");
+
+ rcu_read_unlock();
+}
+
const struct bpf_map_ops htab_map_ops = {
.map_alloc_check = htab_map_alloc_check,
.map_alloc = htab_map_alloc,
@@ -1165,6 +1194,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_update_elem = htab_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_gen_lookup = htab_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
};
const struct bpf_map_ops htab_lru_map_ops = {
@@ -1176,6 +1206,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_update_elem = htab_lru_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
.map_gen_lookup = htab_lru_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
};
/* Called from eBPF program */
@@ -1402,4 +1433,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = htab_of_map_gen_lookup,
+ .map_check_btf = map_check_no_btf,
};
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73065e2d23c2..1991466b8327 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -193,4 +193,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
};
+
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+ /* map and flags arguments are not used now,
+ * but provide an ability to extend the API
+ * for other types of local storages.
+ * verifier checks that their values are correct.
+ */
+ return (unsigned long) this_cpu_read(bpf_cgroup_storage);
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+ .func = bpf_get_local_storage,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_ANYTHING,
+};
#endif
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 76efe9a183f5..2ada5e21dfa6 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -196,19 +196,21 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
+ void *prev_key;
if (map_iter(m)->done)
return NULL;
if (unlikely(v == SEQ_START_TOKEN))
- goto done;
+ prev_key = NULL;
+ else
+ prev_key = key;
- if (map->ops->map_get_next_key(map, key, key)) {
+ if (map->ops->map_get_next_key(map, prev_key, key)) {
map_iter(m)->done = true;
return NULL;
}
-done:
++(*pos);
return key;
}
@@ -332,7 +334,8 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
struct bpf_map *map = arg;
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
- map->btf ? &bpffs_map_fops : &bpffs_obj_fops);
+ bpf_map_support_seq_show(map) ?
+ &bpffs_map_fops : &bpffs_obj_fops);
}
static struct dentry *
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
new file mode 100644
index 000000000000..22ad967d1e5f
--- /dev/null
+++ b/kernel/bpf/local_storage.c
@@ -0,0 +1,379 @@
+//SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf-cgroup.h>
+#include <linux/bpf.h>
+#include <linux/bug.h>
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+DEFINE_PER_CPU(void*, bpf_cgroup_storage);
+
+#ifdef CONFIG_CGROUP_BPF
+
+#define LOCAL_STORAGE_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bpf_cgroup_storage_map {
+ struct bpf_map map;
+
+ spinlock_t lock;
+ struct bpf_prog *prog;
+ struct rb_root root;
+ struct list_head list;
+};
+
+static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
+{
+ return container_of(map, struct bpf_cgroup_storage_map, map);
+}
+
+static int bpf_cgroup_storage_key_cmp(
+ const struct bpf_cgroup_storage_key *key1,
+ const struct bpf_cgroup_storage_key *key2)
+{
+ if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+ return -1;
+ else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+ return 1;
+ else if (key1->attach_type < key2->attach_type)
+ return -1;
+ else if (key1->attach_type > key2->attach_type)
+ return 1;
+ return 0;
+}
+
+static struct bpf_cgroup_storage *cgroup_storage_lookup(
+ struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
+ bool locked)
+{
+ struct rb_root *root = &map->root;
+ struct rb_node *node;
+
+ if (!locked)
+ spin_lock_bh(&map->lock);
+
+ node = root->rb_node;
+ while (node) {
+ struct bpf_cgroup_storage *storage;
+
+ storage = container_of(node, struct bpf_cgroup_storage, node);
+
+ switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+ case -1:
+ node = node->rb_left;
+ break;
+ case 1:
+ node = node->rb_right;
+ break;
+ default:
+ if (!locked)
+ spin_unlock_bh(&map->lock);
+ return storage;
+ }
+ }
+
+ if (!locked)
+ spin_unlock_bh(&map->lock);
+
+ return NULL;
+}
+
+static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
+ struct bpf_cgroup_storage *storage)
+{
+ struct rb_root *root = &map->root;
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ while (*new) {
+ struct bpf_cgroup_storage *this;
+
+ this = container_of(*new, struct bpf_cgroup_storage, node);
+
+ parent = *new;
+ switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+ case -1:
+ new = &((*new)->rb_left);
+ break;
+ case 1:
+ new = &((*new)->rb_right);
+ break;
+ default:
+ return -EEXIST;
+ }
+ }
+
+ rb_link_node(&storage->node, parent, new);
+ rb_insert_color(&storage->node, root);
+
+ return 0;
+}
+
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage)
+ return NULL;
+
+ return &READ_ONCE(storage->buf)->data[0];
+}
+
+static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+ void *value, u64 flags)
+{
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ struct bpf_storage_buffer *new;
+
+ if (flags & BPF_NOEXIST)
+ return -EINVAL;
+
+ storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
+ key, false);
+ if (!storage)
+ return -ENOENT;
+
+ new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+ map->value_size, __GFP_ZERO | GFP_USER,
+ map->numa_node);
+ if (!new)
+ return -ENOMEM;
+
+ memcpy(&new->data[0], value, map->value_size);
+
+ new = xchg(&storage->buf, new);
+ kfree_rcu(new, rcu);
+
+ return 0;
+}
+
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+ void *_next_key)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage_key *next = _next_key;
+ struct bpf_cgroup_storage *storage;
+
+ spin_lock_bh(&map->lock);
+
+ if (list_empty(&map->list))
+ goto enoent;
+
+ if (key) {
+ storage = cgroup_storage_lookup(map, key, true);
+ if (!storage)
+ goto enoent;
+
+ storage = list_next_entry(storage, list);
+ if (!storage)
+ goto enoent;
+ } else {
+ storage = list_first_entry(&map->list,
+ struct bpf_cgroup_storage, list);
+ }
+
+ spin_unlock_bh(&map->lock);
+ next->attach_type = storage->key.attach_type;
+ next->cgroup_inode_id = storage->key.cgroup_inode_id;
+ return 0;
+
+enoent:
+ spin_unlock_bh(&map->lock);
+ return -ENOENT;
+}
+
+static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
+{
+ int numa_node = bpf_map_attr_numa_node(attr);
+ struct bpf_cgroup_storage_map *map;
+
+ if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+ return ERR_PTR(-EINVAL);
+
+ if (attr->value_size > PAGE_SIZE)
+ return ERR_PTR(-E2BIG);
+
+ if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
+ /* reserved bits should not be used */
+ return ERR_PTR(-EINVAL);
+
+ if (attr->max_entries)
+ /* max_entries is not used and enforced to be 0 */
+ return ERR_PTR(-EINVAL);
+
+ map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
+ __GFP_ZERO | GFP_USER, numa_node);
+ if (!map)
+ return ERR_PTR(-ENOMEM);
+
+ map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map),
+ PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* copy mandatory map attributes */
+ bpf_map_init_from_attr(&map->map, attr);
+
+ spin_lock_init(&map->lock);
+ map->root = RB_ROOT;
+ INIT_LIST_HEAD(&map->list);
+
+ return &map->map;
+}
+
+static void cgroup_storage_map_free(struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+ WARN_ON(!RB_EMPTY_ROOT(&map->root));
+ WARN_ON(!list_empty(&map->list));
+
+ kfree(map);
+}
+
+static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
+{
+ return -EINVAL;
+}
+
+const struct bpf_map_ops cgroup_storage_map_ops = {
+ .map_alloc = cgroup_storage_map_alloc,
+ .map_free = cgroup_storage_map_free,
+ .map_get_next_key = cgroup_storage_get_next_key,
+ .map_lookup_elem = cgroup_storage_lookup_elem,
+ .map_update_elem = cgroup_storage_update_elem,
+ .map_delete_elem = cgroup_storage_delete_elem,
+ .map_check_btf = map_check_no_btf,
+};
+
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ int ret = -EBUSY;
+
+ spin_lock_bh(&map->lock);
+
+ if (map->prog && map->prog != prog)
+ goto unlock;
+ if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map)
+ goto unlock;
+
+ map->prog = prog;
+ prog->aux->cgroup_storage = _map;
+ ret = 0;
+unlock:
+ spin_unlock_bh(&map->lock);
+
+ return ret;
+}
+
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+ spin_lock_bh(&map->lock);
+ if (map->prog == prog) {
+ WARN_ON(prog->aux->cgroup_storage != _map);
+ map->prog = NULL;
+ prog->aux->cgroup_storage = NULL;
+ }
+ spin_unlock_bh(&map->lock);
+}
+
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog)
+{
+ struct bpf_cgroup_storage *storage;
+ struct bpf_map *map;
+ u32 pages;
+
+ map = prog->aux->cgroup_storage;
+ if (!map)
+ return NULL;
+
+ pages = round_up(sizeof(struct bpf_cgroup_storage) +
+ sizeof(struct bpf_storage_buffer) +
+ map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ if (bpf_map_charge_memlock(map, pages))
+ return ERR_PTR(-EPERM);
+
+ storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
+ __GFP_ZERO | GFP_USER, map->numa_node);
+ if (!storage) {
+ bpf_map_uncharge_memlock(map, pages);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+ map->value_size, __GFP_ZERO | GFP_USER,
+ map->numa_node);
+ if (!storage->buf) {
+ bpf_map_uncharge_memlock(map, pages);
+ kfree(storage);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ storage->map = (struct bpf_cgroup_storage_map *)map;
+
+ return storage;
+}
+
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
+{
+ u32 pages;
+ struct bpf_map *map;
+
+ if (!storage)
+ return;
+
+ map = &storage->map->map;
+ pages = round_up(sizeof(struct bpf_cgroup_storage) +
+ sizeof(struct bpf_storage_buffer) +
+ map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ bpf_map_uncharge_memlock(map, pages);
+
+ kfree_rcu(storage->buf, rcu);
+ kfree_rcu(storage, rcu);
+}
+
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+ struct cgroup *cgroup,
+ enum bpf_attach_type type)
+{
+ struct bpf_cgroup_storage_map *map;
+
+ if (!storage)
+ return;
+
+ storage->key.attach_type = type;
+ storage->key.cgroup_inode_id = cgroup->kn->id.id;
+
+ map = storage->map;
+
+ spin_lock_bh(&map->lock);
+ WARN_ON(cgroup_storage_insert(map, storage));
+ list_add(&storage->list, &map->list);
+ spin_unlock_bh(&map->lock);
+}
+
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
+{
+ struct bpf_cgroup_storage_map *map;
+ struct rb_root *root;
+
+ if (!storage)
+ return;
+
+ map = storage->map;
+
+ spin_lock_bh(&map->lock);
+ root = &map->root;
+ rb_erase(&storage->node, root);
+
+ list_del(&storage->list);
+ spin_unlock_bh(&map->lock);
+}
+
+#endif
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1603492c9cc7..9058317ba9de 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -10,11 +10,13 @@
*/
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <net/ipv6.h>
+#include <uapi/linux/btf.h>
/* Intermediate node */
#define LPM_TREE_NODE_FLAG_IM BIT(0)
@@ -686,6 +688,15 @@ free_stack:
return err;
}
+static int trie_check_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ /* Keys must have struct bpf_lpm_trie_key embedded. */
+ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ?
+ -EINVAL : 0;
+}
+
const struct bpf_map_ops trie_map_ops = {
.map_alloc = trie_alloc,
.map_free = trie_free,
@@ -693,4 +704,5 @@ const struct bpf_map_ops trie_map_ops = {
.map_lookup_elem = trie_lookup_elem,
.map_update_elem = trie_update_elem,
.map_delete_elem = trie_delete_elem,
+ .map_check_btf = trie_check_btf,
};
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 1da574612bea..3bfbf4464416 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -23,7 +23,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
* is a runtime binding. Doing static check alone
* in the verifier is not enough.
*/
- if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+ inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ac747d5cf7c6..177a52436394 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -18,19 +18,43 @@
#include <linux/bug.h>
#include <linux/kdev_t.h>
#include <linux/list.h>
+#include <linux/lockdep.h>
#include <linux/netdevice.h>
#include <linux/printk.h>
#include <linux/proc_ns.h>
+#include <linux/rhashtable.h>
#include <linux/rtnetlink.h>
#include <linux/rwsem.h>
-/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members
+/* Protects offdevs, members of bpf_offload_netdev and offload members
* of all progs.
* RTNL lock cannot be taken when holding this lock.
*/
static DECLARE_RWSEM(bpf_devs_lock);
-static LIST_HEAD(bpf_prog_offload_devs);
-static LIST_HEAD(bpf_map_offload_devs);
+
+struct bpf_offload_dev {
+ struct list_head netdevs;
+};
+
+struct bpf_offload_netdev {
+ struct rhash_head l;
+ struct net_device *netdev;
+ struct bpf_offload_dev *offdev;
+ struct list_head progs;
+ struct list_head maps;
+ struct list_head offdev_netdevs;
+};
+
+static const struct rhashtable_params offdevs_params = {
+ .nelem_hint = 4,
+ .key_len = sizeof(struct net_device *),
+ .key_offset = offsetof(struct bpf_offload_netdev, netdev),
+ .head_offset = offsetof(struct bpf_offload_netdev, l),
+ .automatic_shrinking = true,
+};
+
+static struct rhashtable offdevs;
+static bool offdevs_inited;
static int bpf_dev_offload_check(struct net_device *netdev)
{
@@ -41,8 +65,19 @@ static int bpf_dev_offload_check(struct net_device *netdev)
return 0;
}
+static struct bpf_offload_netdev *
+bpf_offload_find_netdev(struct net_device *netdev)
+{
+ lockdep_assert_held(&bpf_devs_lock);
+
+ if (!offdevs_inited)
+ return NULL;
+ return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+}
+
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
{
+ struct bpf_offload_netdev *ondev;
struct bpf_prog_offload *offload;
int err;
@@ -66,12 +101,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
goto err_maybe_put;
down_write(&bpf_devs_lock);
- if (offload->netdev->reg_state != NETREG_REGISTERED) {
+ ondev = bpf_offload_find_netdev(offload->netdev);
+ if (!ondev) {
err = -EINVAL;
goto err_unlock;
}
prog->aux->offload = offload;
- list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+ list_add_tail(&offload->offloads, &ondev->progs);
dev_put(offload->netdev);
up_write(&bpf_devs_lock);
@@ -294,6 +330,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
struct net *net = current->nsproxy->net_ns;
+ struct bpf_offload_netdev *ondev;
struct bpf_offloaded_map *offmap;
int err;
@@ -316,11 +353,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
if (err)
goto err_unlock;
+ ondev = bpf_offload_find_netdev(offmap->netdev);
+ if (!ondev) {
+ err = -EINVAL;
+ goto err_unlock;
+ }
+
err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
if (err)
goto err_unlock;
- list_add_tail(&offmap->offloads, &bpf_map_offload_devs);
+ list_add_tail(&offmap->offloads, &ondev->maps);
up_write(&bpf_devs_lock);
rtnl_unlock();
@@ -468,77 +511,159 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
return 0;
}
-bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
+static bool __bpf_offload_dev_match(struct bpf_prog *prog,
+ struct net_device *netdev)
{
- struct bpf_offloaded_map *offmap;
+ struct bpf_offload_netdev *ondev1, *ondev2;
struct bpf_prog_offload *offload;
- bool ret;
if (!bpf_prog_is_dev_bound(prog->aux))
return false;
- if (!bpf_map_is_dev_bound(map))
- return bpf_map_offload_neutral(map);
- down_read(&bpf_devs_lock);
offload = prog->aux->offload;
- offmap = map_to_offmap(map);
+ if (!offload)
+ return false;
+ if (offload->netdev == netdev)
+ return true;
- ret = offload && offload->netdev == offmap->netdev;
+ ondev1 = bpf_offload_find_netdev(offload->netdev);
+ ondev2 = bpf_offload_find_netdev(netdev);
+
+ return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
+{
+ bool ret;
+
+ down_read(&bpf_devs_lock);
+ ret = __bpf_offload_dev_match(prog, netdev);
up_read(&bpf_devs_lock);
return ret;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
-static void bpf_offload_orphan_all_progs(struct net_device *netdev)
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
{
- struct bpf_prog_offload *offload, *tmp;
+ struct bpf_offloaded_map *offmap;
+ bool ret;
- list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads)
- if (offload->netdev == netdev)
- __bpf_prog_offload_destroy(offload->prog);
+ if (!bpf_map_is_dev_bound(map))
+ return bpf_map_offload_neutral(map);
+ offmap = map_to_offmap(map);
+
+ down_read(&bpf_devs_lock);
+ ret = __bpf_offload_dev_match(prog, offmap->netdev);
+ up_read(&bpf_devs_lock);
+
+ return ret;
}
-static void bpf_offload_orphan_all_maps(struct net_device *netdev)
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+ struct net_device *netdev)
{
- struct bpf_offloaded_map *offmap, *tmp;
+ struct bpf_offload_netdev *ondev;
+ int err;
- list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads)
- if (offmap->netdev == netdev)
- __bpf_map_offload_destroy(offmap);
+ ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+ if (!ondev)
+ return -ENOMEM;
+
+ ondev->netdev = netdev;
+ ondev->offdev = offdev;
+ INIT_LIST_HEAD(&ondev->progs);
+ INIT_LIST_HEAD(&ondev->maps);
+
+ down_write(&bpf_devs_lock);
+ err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+ if (err) {
+ netdev_warn(netdev, "failed to register for BPF offload\n");
+ goto err_unlock_free;
+ }
+
+ list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+ up_write(&bpf_devs_lock);
+ return 0;
+
+err_unlock_free:
+ up_write(&bpf_devs_lock);
+ kfree(ondev);
+ return err;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
-static int bpf_offload_notification(struct notifier_block *notifier,
- ulong event, void *ptr)
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+ struct net_device *netdev)
{
- struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+ struct bpf_offload_netdev *ondev, *altdev;
+ struct bpf_offloaded_map *offmap, *mtmp;
+ struct bpf_prog_offload *offload, *ptmp;
ASSERT_RTNL();
- switch (event) {
- case NETDEV_UNREGISTER:
- /* ignore namespace changes */
- if (netdev->reg_state != NETREG_UNREGISTERING)
- break;
-
- down_write(&bpf_devs_lock);
- bpf_offload_orphan_all_progs(netdev);
- bpf_offload_orphan_all_maps(netdev);
- up_write(&bpf_devs_lock);
- break;
- default:
- break;
+ down_write(&bpf_devs_lock);
+ ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+ if (WARN_ON(!ondev))
+ goto unlock;
+
+ WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+ list_del(&ondev->offdev_netdevs);
+
+ /* Try to move the objects to another netdev of the device */
+ altdev = list_first_entry_or_null(&offdev->netdevs,
+ struct bpf_offload_netdev,
+ offdev_netdevs);
+ if (altdev) {
+ list_for_each_entry(offload, &ondev->progs, offloads)
+ offload->netdev = altdev->netdev;
+ list_splice_init(&ondev->progs, &altdev->progs);
+
+ list_for_each_entry(offmap, &ondev->maps, offloads)
+ offmap->netdev = altdev->netdev;
+ list_splice_init(&ondev->maps, &altdev->maps);
+ } else {
+ list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+ __bpf_prog_offload_destroy(offload->prog);
+ list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+ __bpf_map_offload_destroy(offmap);
}
- return NOTIFY_OK;
-}
-static struct notifier_block bpf_offload_notifier = {
- .notifier_call = bpf_offload_notification,
-};
+ WARN_ON(!list_empty(&ondev->progs));
+ WARN_ON(!list_empty(&ondev->maps));
+ kfree(ondev);
+unlock:
+ up_write(&bpf_devs_lock);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
-static int __init bpf_offload_init(void)
+struct bpf_offload_dev *bpf_offload_dev_create(void)
{
- register_netdevice_notifier(&bpf_offload_notifier);
- return 0;
+ struct bpf_offload_dev *offdev;
+ int err;
+
+ down_write(&bpf_devs_lock);
+ if (!offdevs_inited) {
+ err = rhashtable_init(&offdevs, &offdevs_params);
+ if (err)
+ return ERR_PTR(err);
+ offdevs_inited = true;
+ }
+ up_write(&bpf_devs_lock);
+
+ offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
+ if (!offdev)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&offdev->netdevs);
+
+ return offdev;
}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_create);
-subsys_initcall(bpf_offload_init);
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
+{
+ WARN_ON(!list_empty(&offdev->netdevs));
+ kfree(offdev);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
new file mode 100644
index 000000000000..18e225de80ff
--- /dev/null
+++ b/kernel/bpf/reuseport_array.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/sock_diag.h>
+#include <net/sock_reuseport.h>
+
+struct reuseport_array {
+ struct bpf_map map;
+ struct sock __rcu *ptrs[];
+};
+
+static struct reuseport_array *reuseport_array(struct bpf_map *map)
+{
+ return (struct reuseport_array *)map;
+}
+
+/* The caller must hold the reuseport_lock */
+void bpf_sk_reuseport_detach(struct sock *sk)
+{
+ struct sock __rcu **socks;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ socks = sk->sk_user_data;
+ if (socks) {
+ WRITE_ONCE(sk->sk_user_data, NULL);
+ /*
+ * Do not move this NULL assignment outside of
+ * sk->sk_callback_lock because there is
+ * a race with reuseport_array_free()
+ * which does not hold the reuseport_lock.
+ */
+ RCU_INIT_POINTER(*socks, NULL);
+ }
+ write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int reuseport_array_alloc_check(union bpf_attr *attr)
+{
+ if (attr->value_size != sizeof(u32) &&
+ attr->value_size != sizeof(u64))
+ return -EINVAL;
+
+ return array_map_alloc_check(attr);
+}
+
+static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = *(u32 *)key;
+
+ if (unlikely(index >= array->map.max_entries))
+ return NULL;
+
+ return rcu_dereference(array->ptrs[index]);
+}
+
+/* Called from syscall only */
+static int reuseport_array_delete_elem(struct bpf_map *map, void *key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = *(u32 *)key;
+ struct sock *sk;
+ int err;
+
+ if (index >= map->max_entries)
+ return -E2BIG;
+
+ if (!rcu_access_pointer(array->ptrs[index]))
+ return -ENOENT;
+
+ spin_lock_bh(&reuseport_lock);
+
+ sk = rcu_dereference_protected(array->ptrs[index],
+ lockdep_is_held(&reuseport_lock));
+ if (sk) {
+ write_lock_bh(&sk->sk_callback_lock);
+ WRITE_ONCE(sk->sk_user_data, NULL);
+ RCU_INIT_POINTER(array->ptrs[index], NULL);
+ write_unlock_bh(&sk->sk_callback_lock);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+
+ spin_unlock_bh(&reuseport_lock);
+
+ return err;
+}
+
+static void reuseport_array_free(struct bpf_map *map)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ struct sock *sk;
+ u32 i;
+
+ synchronize_rcu();
+
+ /*
+ * ops->map_*_elem() will not be able to access this
+ * array now. Hence, this function only races with
+ * bpf_sk_reuseport_detach() which was triggerred by
+ * close() or disconnect().
+ *
+ * This function and bpf_sk_reuseport_detach() are
+ * both removing sk from "array". Who removes it
+ * first does not matter.
+ *
+ * The only concern here is bpf_sk_reuseport_detach()
+ * may access "array" which is being freed here.
+ * bpf_sk_reuseport_detach() access this "array"
+ * through sk->sk_user_data _and_ with sk->sk_callback_lock
+ * held which is enough because this "array" is not freed
+ * until all sk->sk_user_data has stopped referencing this "array".
+ *
+ * Hence, due to the above, taking "reuseport_lock" is not
+ * needed here.
+ */
+
+ /*
+ * Since reuseport_lock is not taken, sk is accessed under
+ * rcu_read_lock()
+ */
+ rcu_read_lock();
+ for (i = 0; i < map->max_entries; i++) {
+ sk = rcu_dereference(array->ptrs[i]);
+ if (sk) {
+ write_lock_bh(&sk->sk_callback_lock);
+ /*
+ * No need for WRITE_ONCE(). At this point,
+ * no one is reading it without taking the
+ * sk->sk_callback_lock.
+ */
+ sk->sk_user_data = NULL;
+ write_unlock_bh(&sk->sk_callback_lock);
+ RCU_INIT_POINTER(array->ptrs[i], NULL);
+ }
+ }
+ rcu_read_unlock();
+
+ /*
+ * Once reaching here, all sk->sk_user_data is not
+ * referenceing this "array". "array" can be freed now.
+ */
+ bpf_map_area_free(array);
+}
+
+static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
+{
+ int err, numa_node = bpf_map_attr_numa_node(attr);
+ struct reuseport_array *array;
+ u64 cost, array_size;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ array_size = sizeof(*array);
+ array_size += (u64)attr->max_entries * sizeof(struct sock *);
+
+ /* make sure there is no u32 overflow later in round_up() */
+ cost = array_size;
+ if (cost >= U32_MAX - PAGE_SIZE)
+ return ERR_PTR(-ENOMEM);
+ cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ err = bpf_map_precharge_memlock(cost);
+ if (err)
+ return ERR_PTR(err);
+
+ /* allocate all map elements and zero-initialize them */
+ array = bpf_map_area_alloc(array_size, numa_node);
+ if (!array)
+ return ERR_PTR(-ENOMEM);
+
+ /* copy mandatory map attributes */
+ bpf_map_init_from_attr(&array->map, attr);
+ array->map.pages = cost;
+
+ return &array->map;
+}
+
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+ void *value)
+{
+ struct sock *sk;
+ int err;
+
+ if (map->value_size != sizeof(u64))
+ return -ENOSPC;
+
+ rcu_read_lock();
+ sk = reuseport_array_lookup_elem(map, key);
+ if (sk) {
+ *(u64 *)value = sock_gen_cookie(sk);
+ err = 0;
+ } else {
+ err = -ENOENT;
+ }
+ rcu_read_unlock();
+
+ return err;
+}
+
+static int
+reuseport_array_update_check(const struct reuseport_array *array,
+ const struct sock *nsk,
+ const struct sock *osk,
+ const struct sock_reuseport *nsk_reuse,
+ u32 map_flags)
+{
+ if (osk && map_flags == BPF_NOEXIST)
+ return -EEXIST;
+
+ if (!osk && map_flags == BPF_EXIST)
+ return -ENOENT;
+
+ if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP)
+ return -ENOTSUPP;
+
+ if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6)
+ return -ENOTSUPP;
+
+ if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM)
+ return -ENOTSUPP;
+
+ /*
+ * sk must be hashed (i.e. listening in the TCP case or binded
+ * in the UDP case) and
+ * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL).
+ *
+ * Also, sk will be used in bpf helper that is protected by
+ * rcu_read_lock().
+ */
+ if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse)
+ return -EINVAL;
+
+ /* READ_ONCE because the sk->sk_callback_lock may not be held here */
+ if (READ_ONCE(nsk->sk_user_data))
+ return -EBUSY;
+
+ return 0;
+}
+
+/*
+ * Called from syscall only.
+ * The "nsk" in the fd refcnt.
+ * The "osk" and "reuse" are protected by reuseport_lock.
+ */
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ struct sock *free_osk = NULL, *osk, *nsk;
+ struct sock_reuseport *reuse;
+ u32 index = *(u32 *)key;
+ struct socket *socket;
+ int err, fd;
+
+ if (map_flags > BPF_EXIST)
+ return -EINVAL;
+
+ if (index >= map->max_entries)
+ return -E2BIG;
+
+ if (map->value_size == sizeof(u64)) {
+ u64 fd64 = *(u64 *)value;
+
+ if (fd64 > S32_MAX)
+ return -EINVAL;
+ fd = fd64;
+ } else {
+ fd = *(int *)value;
+ }
+
+ socket = sockfd_lookup(fd, &err);
+ if (!socket)
+ return err;
+
+ nsk = socket->sk;
+ if (!nsk) {
+ err = -EINVAL;
+ goto put_file;
+ }
+
+ /* Quick checks before taking reuseport_lock */
+ err = reuseport_array_update_check(array, nsk,
+ rcu_access_pointer(array->ptrs[index]),
+ rcu_access_pointer(nsk->sk_reuseport_cb),
+ map_flags);
+ if (err)
+ goto put_file;
+
+ spin_lock_bh(&reuseport_lock);
+ /*
+ * Some of the checks only need reuseport_lock
+ * but it is done under sk_callback_lock also
+ * for simplicity reason.
+ */
+ write_lock_bh(&nsk->sk_callback_lock);
+
+ osk = rcu_dereference_protected(array->ptrs[index],
+ lockdep_is_held(&reuseport_lock));
+ reuse = rcu_dereference_protected(nsk->sk_reuseport_cb,
+ lockdep_is_held(&reuseport_lock));
+ err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags);
+ if (err)
+ goto put_file_unlock;
+
+ /* Ensure reuse->reuseport_id is set */
+ err = reuseport_get_id(reuse);
+ if (err < 0)
+ goto put_file_unlock;
+
+ WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+ rcu_assign_pointer(array->ptrs[index], nsk);
+ free_osk = osk;
+ err = 0;
+
+put_file_unlock:
+ write_unlock_bh(&nsk->sk_callback_lock);
+
+ if (free_osk) {
+ write_lock_bh(&free_osk->sk_callback_lock);
+ WRITE_ONCE(free_osk->sk_user_data, NULL);
+ write_unlock_bh(&free_osk->sk_callback_lock);
+ }
+
+ spin_unlock_bh(&reuseport_lock);
+put_file:
+ fput(socket->file);
+ return err;
+}
+
+/* Called from syscall */
+static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
+ void *next_key)
+{
+ struct reuseport_array *array = reuseport_array(map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = (u32 *)next_key;
+
+ if (index >= array->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == array->map.max_entries - 1)
+ return -ENOENT;
+
+ *next = index + 1;
+ return 0;
+}
+
+const struct bpf_map_ops reuseport_array_ops = {
+ .map_alloc_check = reuseport_array_alloc_check,
+ .map_alloc = reuseport_array_alloc,
+ .map_free = reuseport_array_free,
+ .map_lookup_elem = reuseport_array_lookup_elem,
+ .map_get_next_key = reuseport_array_get_next_key,
+ .map_delete_elem = reuseport_array_delete_elem,
+};
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..98e621a29e8e 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -58,6 +58,7 @@ struct bpf_stab {
struct bpf_map map;
struct sock **sock_map;
struct bpf_sock_progs progs;
+ raw_spinlock_t lock;
};
struct bucket {
@@ -72,6 +73,7 @@ struct bpf_htab {
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
@@ -88,9 +90,9 @@ enum smap_psock_state {
struct smap_psock_map_entry {
struct list_head list;
+ struct bpf_map *map;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
};
struct smap_psock {
@@ -120,6 +122,7 @@ struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
@@ -140,6 +143,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
@@ -161,7 +165,42 @@ out:
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
@@ -181,14 +220,17 @@ static int bpf_tcp_init(struct sock *sk)
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
@@ -219,24 +261,64 @@ out:
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
+ lock_sock(sk);
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
+ release_sock(sk);
return sk->sk_prot->close(sk, timeout);
}
@@ -247,7 +329,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
@@ -260,21 +341,46 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
- osk = cmpxchg(e->entry, sk, NULL);
+ struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map);
+
+ raw_spin_lock_bh(&stab->lock);
+ osk = *e->entry;
if (osk == sk) {
- list_del(&e->list);
+ *e->entry = NULL;
smap_release_sock(psock, sk);
}
+ raw_spin_unlock_bh(&stab->lock);
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ kfree(e);
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
+ release_sock(sk);
close_fun(sk, timeout);
}
@@ -472,7 +578,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
while (sg[i].length) {
free += sg[i].length;
sk_mem_uncharge(sk, sg[i].length);
- put_page(sg_page(&sg[i]));
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
sg[i].length = 0;
sg[i].page_link = 0;
sg[i].offset = 0;
@@ -481,6 +588,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ if (md->skb)
+ consume_skb(md->skb);
return free;
}
@@ -623,11 +732,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
{
bool ingress = !!(md->flags & BPF_F_INGRESS);
struct smap_psock *psock;
- struct scatterlist *sg;
int err = 0;
- sg = md->sg_data;
-
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock))
@@ -946,12 +1052,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
while (msg_data_left(msg)) {
- struct sk_msg_buff *m;
+ struct sk_msg_buff *m = NULL;
bool enospc = false;
int copy;
if (sk->sk_err) {
- err = sk->sk_err;
+ err = -sk->sk_err;
goto out_err;
}
@@ -1014,8 +1120,11 @@ wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
err = sk_stream_wait_memory(sk, &timeo);
- if (err)
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m);
goto out_err;
+ }
}
out_err:
if (err < 0)
@@ -1111,8 +1220,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
@@ -1135,7 +1243,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
@@ -1357,7 +1465,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1388,7 +1498,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -1508,6 +1618,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
@@ -1537,6 +1648,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&stab->map, attr);
+ raw_spin_lock_init(&stab->lock);
/* make sure page count doesn't overflow */
cost = (u64) stab->map.max_entries * sizeof(struct sock *);
@@ -1564,18 +1676,36 @@ free_stab:
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry) {
list_del(&e->list);
- break;
+ kfree(e);
}
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link) {
+ list_del(&e->list);
+ kfree(e);
+ }
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
@@ -1593,15 +1723,15 @@ static void sock_map_free(struct bpf_map *map)
* and a grace period expire to ensure psock is really safe to remove.
*/
rcu_read_lock();
+ raw_spin_lock_bh(&stab->lock);
for (i = 0; i < stab->map.max_entries; i++) {
struct smap_psock *psock;
struct sock *sock;
- sock = xchg(&stab->sock_map[i], NULL);
+ sock = stab->sock_map[i];
if (!sock)
continue;
-
- write_lock_bh(&sock->sk_callback_lock);
+ stab->sock_map[i] = NULL;
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -1609,11 +1739,11 @@ static void sock_map_free(struct bpf_map *map)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
+ raw_spin_unlock_bh(&stab->lock);
rcu_read_unlock();
sock_map_remove_complete(stab);
@@ -1657,21 +1787,23 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
if (k >= map->max_entries)
return -EINVAL;
- sock = xchg(&stab->sock_map[k], NULL);
+ raw_spin_lock_bh(&stab->lock);
+ sock = stab->sock_map[k];
+ stab->sock_map[k] = NULL;
+ raw_spin_unlock_bh(&stab->lock);
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
- goto out;
-
- if (psock->bpf_parse)
+ return 0;
+ if (psock->bpf_parse) {
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ write_unlock_bh(&sock->sk_callback_lock);
+ }
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
-out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
@@ -1707,11 +1839,9 @@ out:
static int __sock_map_ctx_update_elem(struct bpf_map *map,
struct bpf_sock_progs *progs,
struct sock *sock,
- struct sock **map_link,
void *key)
{
struct bpf_prog *verdict, *parse, *tx_msg;
- struct smap_psock_map_entry *e = NULL;
struct smap_psock *psock;
bool new = false;
int err = 0;
@@ -1752,7 +1882,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
@@ -1785,14 +1914,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
new = true;
}
- if (map_link) {
- e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
- if (!e) {
- err = -ENOMEM;
- goto out_progs;
- }
- }
-
/* 3. At this point we have a reference to a valid psock that is
* running. Attach any BPF programs needed.
*/
@@ -1809,19 +1930,11 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
- /* 4. Place psock in sockmap for use and stop any programs on
- * the old sock assuming its not the same sock we are replacing
- * it with. Because we can only have a single set of programs if
- * old_sock has a strp we can stop it.
- */
- if (map_link) {
- e->entry = map_link;
- list_add_tail(&e->list, &psock->maps);
- }
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
@@ -1832,8 +1945,6 @@ out_progs:
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(e);
return err;
}
@@ -1843,38 +1954,57 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
struct bpf_sock_progs *progs = &stab->progs;
- struct sock *osock, *sock;
+ struct sock *osock, *sock = skops->sk;
+ struct smap_psock_map_entry *e;
+ struct smap_psock *psock;
u32 i = *(u32 *)key;
int err;
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
-
if (unlikely(i >= stab->map.max_entries))
return -E2BIG;
- sock = READ_ONCE(stab->sock_map[i]);
- if (flags == BPF_EXIST && !sock)
- return -ENOENT;
- else if (flags == BPF_NOEXIST && sock)
- return -EEXIST;
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e)
+ return -ENOMEM;
- sock = skops->sk;
- err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i],
- key);
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
if (err)
goto out;
- osock = xchg(&stab->sock_map[i], sock);
- if (osock) {
- struct smap_psock *opsock = smap_psock_sk(osock);
+ /* psock guaranteed to be present. */
+ psock = smap_psock_sk(sock);
+ raw_spin_lock_bh(&stab->lock);
+ osock = stab->sock_map[i];
+ if (osock && flags == BPF_NOEXIST) {
+ err = -EEXIST;
+ goto out_unlock;
+ }
+ if (!osock && flags == BPF_EXIST) {
+ err = -ENOENT;
+ goto out_unlock;
+ }
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
- smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
+ e->entry = &stab->sock_map[i];
+ e->map = map;
+ spin_lock_bh(&psock->maps_lock);
+ list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
+
+ stab->sock_map[i] = sock;
+ if (osock) {
+ psock = smap_psock_sk(osock);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
+ smap_release_sock(psock, osock);
}
+ raw_spin_unlock_bh(&stab->lock);
+ return 0;
+out_unlock:
+ smap_release_sock(psock, sock);
+ raw_spin_unlock_bh(&stab->lock);
out:
+ kfree(e);
return err;
}
@@ -1915,6 +2045,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
@@ -1944,7 +2092,13 @@ static int sock_map_update_elem(struct bpf_map *map,
return -EOPNOTSUPP;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2043,14 +2197,13 @@ free_htab:
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2222,18 @@ static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
@@ -2086,16 +2241,15 @@ static void sock_hash_free(struct bpf_map *map)
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2276,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
@@ -2226,11 +2367,14 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
b = __select_bucket(htab, hash);
head = &b->head;
- err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key);
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
if (err)
goto err;
- /* bpf_map_update_elem() can be called in_irq() */
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
raw_spin_lock_bh(&b->lock);
l_old = lookup_elem_raw(head, hash, key, key_size);
if (l_old && map_flags == BPF_NOEXIST) {
@@ -2248,15 +2392,11 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto bucket_err;
}
- psock = smap_psock_sk(sock);
- if (unlikely(!psock)) {
- err = -EINVAL;
- goto bucket_err;
- }
-
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ e->map = map;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
@@ -2266,19 +2406,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
raw_spin_unlock_bh(&b->lock);
return 0;
bucket_err:
+ smap_release_sock(psock, sock);
raw_spin_unlock_bh(&b->lock);
err:
kfree(e);
- psock = smap_psock_sk(sock);
- if (psock)
- smap_release_sock(psock, sock);
return err;
}
@@ -2300,7 +2438,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
return -EINVAL;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2326,7 +2470,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2477,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
@@ -2359,10 +2501,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- raw_spin_lock_bh(&b->lock);
l = lookup_elem_raw(head, hash, key, key_size);
sk = l ? l->sk : NULL;
- raw_spin_unlock_bh(&b->lock);
return sk;
}
@@ -2374,6 +2514,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
.map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
};
const struct bpf_map_ops sock_hash_ops = {
@@ -2383,6 +2524,8 @@ const struct bpf_map_ops sock_hash_ops = {
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index b675a3f3d141..8061a439ef18 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -607,6 +607,7 @@ const struct bpf_map_ops stack_map_ops = {
.map_lookup_elem = stack_map_lookup_elem,
.map_update_elem = stack_map_update_elem,
.map_delete_elem = stack_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
static int __init stack_map_init(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35dc466641f2..8339d81cba1d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -103,6 +103,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
const struct bpf_map_ops bpf_map_offload_ops = {
.map_alloc = bpf_map_offload_map_alloc,
.map_free = bpf_map_offload_map_free,
+ .map_check_btf = map_check_no_btf,
};
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
@@ -181,32 +182,60 @@ int bpf_map_precharge_memlock(u32 pages)
return 0;
}
-static int bpf_map_charge_memlock(struct bpf_map *map)
+static int bpf_charge_memlock(struct user_struct *user, u32 pages)
{
- struct user_struct *user = get_current_user();
- unsigned long memlock_limit;
+ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
+ atomic_long_sub(pages, &user->locked_vm);
+ return -EPERM;
+ }
+ return 0;
+}
- atomic_long_add(map->pages, &user->locked_vm);
+static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
+{
+ atomic_long_sub(pages, &user->locked_vm);
+}
- if (atomic_long_read(&user->locked_vm) > memlock_limit) {
- atomic_long_sub(map->pages, &user->locked_vm);
+static int bpf_map_init_memlock(struct bpf_map *map)
+{
+ struct user_struct *user = get_current_user();
+ int ret;
+
+ ret = bpf_charge_memlock(user, map->pages);
+ if (ret) {
free_uid(user);
- return -EPERM;
+ return ret;
}
map->user = user;
- return 0;
+ return ret;
}
-static void bpf_map_uncharge_memlock(struct bpf_map *map)
+static void bpf_map_release_memlock(struct bpf_map *map)
{
struct user_struct *user = map->user;
-
- atomic_long_sub(map->pages, &user->locked_vm);
+ bpf_uncharge_memlock(user, map->pages);
free_uid(user);
}
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
+{
+ int ret;
+
+ ret = bpf_charge_memlock(map->user, pages);
+ if (ret)
+ return ret;
+ map->pages += pages;
+ return ret;
+}
+
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
+{
+ bpf_uncharge_memlock(map->user, pages);
+ map->pages -= pages;
+}
+
static int bpf_map_alloc_id(struct bpf_map *map)
{
int id;
@@ -256,7 +285,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
- bpf_map_uncharge_memlock(map);
+ bpf_map_release_memlock(map);
security_bpf_map_free(map);
/* implementation dependent freeing */
map->ops->map_free(map);
@@ -427,6 +456,34 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
return 0;
}
+int map_check_no_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ return -ENOTSUPP;
+}
+
+static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+ u32 btf_key_id, u32 btf_value_id)
+{
+ const struct btf_type *key_type, *value_type;
+ u32 key_size, value_size;
+ int ret = 0;
+
+ key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+ if (!key_type || key_size != map->key_size)
+ return -EINVAL;
+
+ value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+ if (!value_type || value_size != map->value_size)
+ return -EINVAL;
+
+ if (map->ops->map_check_btf)
+ ret = map->ops->map_check_btf(map, key_type, value_type);
+
+ return ret;
+}
+
#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
/* called via syscall */
static int map_create(union bpf_attr *attr)
@@ -461,8 +518,7 @@ static int map_create(union bpf_attr *attr)
atomic_set(&map->refcnt, 1);
atomic_set(&map->usercnt, 1);
- if (bpf_map_support_seq_show(map) &&
- (attr->btf_key_type_id || attr->btf_value_type_id)) {
+ if (attr->btf_key_type_id || attr->btf_value_type_id) {
struct btf *btf;
if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
@@ -476,8 +532,8 @@ static int map_create(union bpf_attr *attr)
goto free_map_nouncharge;
}
- err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id,
- attr->btf_value_type_id);
+ err = map_check_btf(map, btf, attr->btf_key_type_id,
+ attr->btf_value_type_id);
if (err) {
btf_put(btf);
goto free_map_nouncharge;
@@ -492,7 +548,7 @@ static int map_create(union bpf_attr *attr)
if (err)
goto free_map_nouncharge;
- err = bpf_map_charge_memlock(map);
+ err = bpf_map_init_memlock(map);
if (err)
goto free_map_sec;
@@ -515,7 +571,7 @@ static int map_create(union bpf_attr *attr)
return err;
free_map:
- bpf_map_uncharge_memlock(map);
+ bpf_map_release_memlock(map);
free_map_sec:
security_bpf_map_free(map);
free_map_nouncharge:
@@ -575,7 +631,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
{
int refold;
- refold = __atomic_add_unless(&map->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
@@ -656,6 +712,8 @@ static int map_lookup_elem(union bpf_attr *attr)
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
err = bpf_fd_htab_map_lookup_elem(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else {
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
@@ -735,7 +793,9 @@ static int map_update_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
@@ -760,6 +820,10 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ /* rcu_read_lock() is not needed */
+ err = bpf_fd_reuseport_array_update_elem(map, key, value,
+ attr->flags);
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
@@ -927,6 +991,9 @@ static void free_used_maps(struct bpf_prog_aux *aux)
{
int i;
+ if (aux->cgroup_storage)
+ bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage);
+
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);
@@ -1142,7 +1209,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
int refold;
- refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
@@ -1483,8 +1550,6 @@ out_free_tp:
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
@@ -1499,40 +1564,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
@@ -1540,7 +1571,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
@@ -1577,12 +1607,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
@@ -1596,18 +1629,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
@@ -1616,9 +1651,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -1651,29 +1683,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1681,9 +1701,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1711,14 +1728,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -2365,7 +2377,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
@@ -2375,7 +2386,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..92246117d2b0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1310,6 +1310,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+ case BPF_PROG_TYPE_SK_REUSEPORT:
/* dst_input() and dst_output() can't write for now */
if (t == BPF_WRITE)
return false;
@@ -2127,6 +2128,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
+ case BPF_MAP_TYPE_CGROUP_STORAGE:
+ if (func_id != BPF_FUNC_get_local_storage)
+ goto error;
+ break;
/* devmap returns a pointer to a live net_device ifindex that we cannot
* allow to be modified from bpf side. So do not allow lookup elements
* for now.
@@ -2162,6 +2167,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_msg_redirect_hash)
goto error;
break;
+ case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ if (func_id != BPF_FUNC_sk_select_reuseport)
+ goto error;
+ break;
default:
break;
}
@@ -2209,6 +2218,14 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
+ case BPF_FUNC_get_local_storage:
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ goto error;
+ break;
+ case BPF_FUNC_sk_select_reuseport:
+ if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+ goto error;
+ break;
default:
break;
}
@@ -2533,6 +2550,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
regs = cur_regs(env);
+
+ /* check that flags argument in get_local_storage(map, flags) is 0,
+ * this is required because get_local_storage() can't return an error.
+ */
+ if (func_id == BPF_FUNC_get_local_storage &&
+ !register_is_null(&regs[BPF_REG_2])) {
+ verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+ return -EINVAL;
+ }
+
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
@@ -2545,8 +2572,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
- } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ else
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].off = 0;
@@ -3238,8 +3269,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
}
- /* check dest operand */
- err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ /* check dest operand, mark as required later */
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
if (err)
return err;
@@ -3265,6 +3296,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
/* case: R = imm
* remember the value we stored into this reg
*/
+ /* clear any state __mark_reg_known doesn't set */
+ mark_reg_unknown(env, regs, insn->dst_reg);
regs[insn->dst_reg].type = SCALAR_VALUE;
if (BPF_CLASS(insn->code) == BPF_ALU64) {
__mark_reg_known(regs + insn->dst_reg,
@@ -5054,7 +5087,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
- !bpf_offload_dev_match(prog, map)) {
+ !bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
return -EINVAL;
}
@@ -5152,6 +5185,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
}
env->used_maps[env->used_map_cnt++] = map;
+ if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+ bpf_cgroup_storage_assign(env->prog, map)) {
+ verbose(env,
+ "only one cgroup storage is allowed\n");
+ fdput(f);
+ return -EBUSY;
+ }
+
fdput(f);
next_insn:
insn++;
@@ -5178,6 +5219,10 @@ static void release_maps(struct bpf_verifier_env *env)
{
int i;
+ if (env->prog->aux->cgroup_storage)
+ bpf_cgroup_storage_release(env->prog,
+ env->prog->aux->cgroup_storage);
+
for (i = 0; i < env->used_map_cnt; i++)
bpf_map_put(env->used_maps[i]);
}
@@ -5430,6 +5475,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5499,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
- return -ENOMEM;
+ goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
@@ -5515,7 +5564,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
- err = -EFAULT;
+ err = -ENOTSUPP;
goto out_free;
}
cond_resched();
@@ -5552,6 +5601,7 @@ out_free:
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
+out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5628,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
err = jit_subprogs(env);
if (err == 0)
return 0;
+ if (err == -EFAULT)
+ return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
@@ -5792,27 +5844,6 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
goto patch_call_imm;
}
- if (insn->imm == BPF_FUNC_redirect_map) {
- /* Note, we cannot use prog directly as imm as subsequent
- * rewrites would still change the prog pointer. The only
- * stable address we can use is aux, which also works with
- * prog clones during blinding.
- */
- u64 addr = (unsigned long)prog->aux;
- struct bpf_insn r4_ld[] = {
- BPF_LD_IMM64(BPF_REG_4, addr),
- *insn,
- };
- cnt = ARRAY_SIZE(r4_ld);
-
- new_prog = bpf_patch_insn_data(env, i + delta, r4_ld, cnt);
- if (!new_prog)
- return -ENOMEM;
-
- delta += cnt - 1;
- env->prog = prog = new_prog;
- insn = new_prog->insnsi + i + delta;
- }
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index b3c557476a8d..9f8463afda9c 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -75,6 +75,7 @@ static void xsk_map_free(struct bpf_map *map)
struct xsk_map *m = container_of(map, struct xsk_map, map);
int i;
+ bpf_clear_redirect_map(map);
synchronize_net();
for (i = 0; i < map->max_entries; i++) {
@@ -227,6 +228,5 @@ const struct bpf_map_ops xsk_map_ops = {
.map_lookup_elem = xsk_map_lookup_elem,
.map_update_elem = xsk_map_update_elem,
.map_delete_elem = xsk_map_delete_elem,
+ .map_check_btf = map_check_no_btf,
};
-
-
Powered by cgit, Gruvboxed by Blaster4385.