summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf.h42
-rw-r--r--include/linux/bpf_verifier.h20
-rw-r--r--include/uapi/linux/bpf.h83
3 files changed, 145 insertions, 0 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9b1875212f6..a7080c86fa76 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -392,10 +392,18 @@ enum bpf_type_flag {
MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS),
+ /* DYNPTR points to memory local to the bpf program. */
+ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS),
+
+ /* DYNPTR points to a ringbuf record. */
+ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS),
+
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
+#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
+
/* Max number of base types. */
#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
@@ -438,6 +446,7 @@ enum bpf_arg_type {
ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */
ARG_PTR_TO_TIMER, /* pointer to bpf_timer */
ARG_PTR_TO_KPTR, /* pointer to referenced kptr */
+ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
__BPF_ARG_TYPE_MAX,
/* Extended arg_types. */
@@ -479,6 +488,7 @@ enum bpf_return_type {
RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
+ RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
/* This must be the last entry. Its purpose is to ensure the enum is
@@ -2225,6 +2235,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
@@ -2376,4 +2389,33 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
u32 **bin_buf, u32 num_args);
void bpf_bprintf_cleanup(void);
+/* the implementation of the opaque uapi struct bpf_dynptr */
+struct bpf_dynptr_kern {
+ void *data;
+ /* Size represents the number of usable bytes of dynptr data.
+ * If for example the offset is at 4 for a local dynptr whose data is
+ * of type u64, the number of usable bytes is 4.
+ *
+ * The upper 8 bits are reserved. It is as follows:
+ * Bits 0 - 23 = size
+ * Bits 24 - 30 = dynptr type
+ * Bit 31 = whether dynptr is read-only
+ */
+ u32 size;
+ u32 offset;
+} __aligned(8);
+
+enum bpf_dynptr_type {
+ BPF_DYNPTR_TYPE_INVALID,
+ /* Points to memory that is local to the bpf program */
+ BPF_DYNPTR_TYPE_LOCAL,
+ /* Underlying data is a ringbuf record */
+ BPF_DYNPTR_TYPE_RINGBUF,
+};
+
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+ enum bpf_dynptr_type type, u32 offset, u32 size);
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_check_size(u32 size);
+
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 1f1e7f2ea967..e8439f6cbe57 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -72,6 +72,18 @@ struct bpf_reg_state {
u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
+ /* For dynptr stack slots */
+ struct {
+ enum bpf_dynptr_type type;
+ /* A dynptr is 16 bytes so it takes up 2 stack slots.
+ * We need to track which slot is the first slot
+ * to protect against cases where the user may try to
+ * pass in an address starting at the second slot of the
+ * dynptr.
+ */
+ bool first_slot;
+ } dynptr;
+
/* Max size from any of the above. */
struct {
unsigned long raw1;
@@ -88,6 +100,8 @@ struct bpf_reg_state {
* for the purpose of tracking that it's freed.
* For PTR_TO_SOCKET this is used to share which pointers retain the
* same reference to the socket, to determine proper reference freeing.
+ * For stack slots that are dynptrs, this is used to track references to
+ * the dynptr to determine proper reference freeing.
*/
u32 id;
/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
@@ -174,9 +188,15 @@ enum bpf_stack_slot_type {
STACK_SPILL, /* register spilled into stack */
STACK_MISC, /* BPF program wrote some data into this slot */
STACK_ZERO, /* BPF program wrote constant zero */
+ /* A dynptr is stored in this stack slot. The type of dynptr
+ * is stored in bpf_stack_state->spilled_ptr.dynptr.type
+ */
+ STACK_DYNPTR,
};
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
+#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern)
+#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE)
struct bpf_stack_state {
struct bpf_reg_state spilled_ptr;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 56688bee20d9..f4009dbdf62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5178,6 +5178,77 @@ union bpf_attr {
* Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
* Return
* *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Get a dynptr to local memory *data*.
+ *
+ * *data* must be a ptr to a map value.
+ * The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * -EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * through the dynptr interface. *flags* must be 0.
+ *
+ * Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * reservation fails. This is enforced by the verifier.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*,
+ * through the dynptr interface. This is a no-op if the dynptr is
+ * invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_submit'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample through the dynptr
+ * interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_discard'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset)
+ * Description
+ * Read *len* bytes from *src* into *dst*, starting from *offset*
+ * into *src*.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *src*'s data, -EINVAL if *src* is an invalid dynptr.
+ *
+ * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len)
+ * Description
+ * Write *len* bytes from *src* into *dst*, starting from *offset*
+ * into *dst*.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * Description
+ * Get a pointer to the underlying dynptr data.
+ *
+ * *len* must be a statically known value. The returned data slice
+ * is invalidated whenever the dynptr is invalidated.
+ * Return
+ * Pointer to the underlying dynptr data, NULL if the dynptr is
+ * read-only, if the dynptr is invalid, or if the offset and length
+ * is out of bounds.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5377,6 +5448,13 @@ union bpf_attr {
FN(kptr_xchg), \
FN(map_lookup_percpu_elem), \
FN(skc_to_mptcp_sock), \
+ FN(dynptr_from_mem), \
+ FN(ringbuf_reserve_dynptr), \
+ FN(ringbuf_submit_dynptr), \
+ FN(ringbuf_discard_dynptr), \
+ FN(dynptr_read), \
+ FN(dynptr_write), \
+ FN(dynptr_data), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -6528,6 +6606,11 @@ struct bpf_timer {
__u64 :64;
} __attribute__((aligned(8)));
+struct bpf_dynptr {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
struct bpf_sysctl {
__u32 write; /* Sysctl is being read (= 0) or written (= 1).
* Allows 1,2,4-byte read, but no write.