summaryrefslogtreecommitdiff
path: root/kernel/bpf/arraymap.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/arraymap.c')
-rw-r--r--kernel/bpf/arraymap.c86
1 files changed, 72 insertions, 14 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index d771a3872500..aaa319848e7d 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -19,6 +19,9 @@
#include "map_in_map.h"
+#define ARRAY_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
@@ -49,13 +52,17 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
+ int numa_node = bpf_map_attr_numa_node(attr);
+ u32 elem_size, index_mask, max_entries;
+ bool unpriv = !capable(CAP_SYS_ADMIN);
struct bpf_array *array;
u64 array_size;
- u32 elem_size;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
- attr->value_size == 0 || attr->map_flags)
+ attr->value_size == 0 ||
+ attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+ (percpu && numa_node != NUMA_NO_NODE))
return ERR_PTR(-EINVAL);
if (attr->value_size > KMALLOC_MAX_SIZE)
@@ -66,20 +73,31 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
elem_size = round_up(attr->value_size, 8);
+ max_entries = attr->max_entries;
+ index_mask = roundup_pow_of_two(max_entries) - 1;
+
+ if (unpriv)
+ /* round up array size to nearest power of 2,
+ * since cpu will speculate within index_mask limits
+ */
+ max_entries = index_mask + 1;
+
array_size = sizeof(*array);
if (percpu)
- array_size += (u64) attr->max_entries * sizeof(void *);
+ array_size += (u64) max_entries * sizeof(void *);
else
- array_size += (u64) attr->max_entries * elem_size;
+ array_size += (u64) max_entries * elem_size;
/* make sure there is no u32 overflow later in round_up() */
if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
/* allocate all map elements and zero-initialize them */
- array = bpf_map_area_alloc(array_size);
+ array = bpf_map_area_alloc(array_size, numa_node);
if (!array)
return ERR_PTR(-ENOMEM);
+ array->index_mask = index_mask;
+ array->map.unpriv_array = unpriv;
/* copy mandatory map attributes */
array->map.map_type = attr->map_type;
@@ -87,6 +105,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
array->map.map_flags = attr->map_flags;
+ array->map.numa_node = numa_node;
array->elem_size = elem_size;
if (!percpu)
@@ -95,7 +114,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
if (array_size >= U32_MAX - PAGE_SIZE ||
- elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+ bpf_array_alloc_percpu(array)) {
bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
@@ -114,12 +133,13 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
if (unlikely(index >= array->map.max_entries))
return NULL;
- return array->value + array->elem_size * index;
+ return array->value + array->elem_size * (index & array->index_mask);
}
/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_insn *insn = insn_buf;
u32 elem_size = round_up(map->value_size, 8);
const int ret = BPF_REG_0;
@@ -128,7 +148,12 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
- *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+ if (map->unpriv_array) {
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
+ *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+ } else {
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+ }
if (is_power_of_2(elem_size)) {
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
@@ -150,7 +175,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
if (unlikely(index >= array->map.max_entries))
return NULL;
- return this_cpu_ptr(array->pptrs[index]);
+ return this_cpu_ptr(array->pptrs[index & array->index_mask]);
}
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
@@ -170,7 +195,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
- pptr = array->pptrs[index];
+ pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
off += size;
@@ -218,10 +243,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
return -EEXIST;
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
- memcpy(this_cpu_ptr(array->pptrs[index]),
+ memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
else
- memcpy(array->value + array->elem_size * index,
+ memcpy(array->value +
+ array->elem_size * (index & array->index_mask),
value, map->value_size);
return 0;
}
@@ -255,7 +281,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
- pptr = array->pptrs[index];
+ pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
off += size;
@@ -489,7 +515,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
ee = ERR_PTR(-EOPNOTSUPP);
event = perf_file->private_data;
- if (perf_event_read_local(event, &value) == -EOPNOTSUPP)
+ if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
goto err_out;
ee = bpf_event_entry_gen(perf_file, map_file);
@@ -603,6 +629,37 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
return READ_ONCE(*inner_map);
}
+static u32 array_of_map_gen_lookup(struct bpf_map *map,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 elem_size = round_up(map->value_size, 8);
+ struct bpf_insn *insn = insn_buf;
+ const int ret = BPF_REG_0;
+ const int map_ptr = BPF_REG_1;
+ const int index = BPF_REG_2;
+
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+ *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+ if (map->unpriv_array) {
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
+ *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+ } else {
+ *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+ }
+ if (is_power_of_2(elem_size))
+ *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+ else
+ *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+ *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+ *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+ *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+ *insn++ = BPF_MOV64_IMM(ret, 0);
+
+ return insn - insn_buf;
+}
+
const struct bpf_map_ops array_of_maps_map_ops = {
.map_alloc = array_of_map_alloc,
.map_free = array_of_map_free,
@@ -612,4 +669,5 @@ const struct bpf_map_ops array_of_maps_map_ops = {
.map_fd_get_ptr = bpf_map_fd_get_ptr,
.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,
};
generated by cgit (git 2.34.1) at 2025-06-09 19:18:28 +0000