Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Daniel Borkmann says:
====================
pull-request: bpf 2019-03-16
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) Fix a umem memory leak on cleanup in AF_XDP, from Björn.
2) Fix BTF to properly resolve forward-declared enums into their corresponding
full enum definition types during deduplication, from Andrii.
3) Fix libbpf to reject invalid flags in xsk_socket__create(), from Magnus.
4) Fix accessing invalid pointer returned from bpf_tcp_sock() and
bpf_sk_fullsock() after bpf_sk_release() was called, from Martin.
5) Fix generation of load/store DW instructions in PPC JIT, from Naveen.
6) Various fixes in BPF helper function documentation in bpf.h UAPI header
used to bpf-helpers(7) man page, from Quentin.
7) Fix segfault in BPF test_progs when prog loading failed, from Yonghong.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index c5698a5..23f7ed7 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -302,6 +302,7 @@
/* Misc instructions for BPF compiler */
#define PPC_INST_LBZ 0x88000000
#define PPC_INST_LD 0xe8000000
+#define PPC_INST_LDX 0x7c00002a
#define PPC_INST_LHZ 0xa0000000
#define PPC_INST_LWZ 0x80000000
#define PPC_INST_LHBRX 0x7c00062c
@@ -309,6 +310,7 @@
#define PPC_INST_STB 0x98000000
#define PPC_INST_STH 0xb0000000
#define PPC_INST_STD 0xf8000000
+#define PPC_INST_STDX 0x7c00012a
#define PPC_INST_STDU 0xf8000001
#define PPC_INST_STW 0x90000000
#define PPC_INST_STWU 0x94000000
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 549e949..dcac377 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -51,6 +51,8 @@
#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i)
#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \
___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \
+ ___PPC_RA(base) | ___PPC_RB(b))
#define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \
___PPC_RA(base) | ((i) & 0xfffc))
#define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \
@@ -65,7 +67,9 @@
#define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \
___PPC_RA(base) | IMM_L(i))
#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \
- ___PPC_RA(base) | IMM_L(i))
+ ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \
+ ___PPC_RA(base) | ___PPC_RB(b))
#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \
___PPC_RA(base) | IMM_L(i))
#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \
@@ -85,17 +89,6 @@
___PPC_RA(a) | ___PPC_RB(b))
#define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \
___PPC_RA(a) | ___PPC_RB(b))
-
-#ifdef CONFIG_PPC64
-#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
-#else
-#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
-#endif
-
#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
#define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index dc50a8d..21744d8 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -122,6 +122,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
#define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i)
#endif
+#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
+#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
+
#define SEEN_DATAREF 0x10000 /* might call external helpers */
#define SEEN_XREG 0x20000 /* X reg is used */
#define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 3609be4..47f441f 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -68,6 +68,26 @@ static const int b2p[] = {
/* PPC NVR range -- update this if we ever use NVRs below r27 */
#define BPF_PPC_NVR_MIN 27
+/*
+ * WARNING: These can use TMP_REG_2 if the offset is not at word boundary,
+ * so ensure that it isn't in use already.
+ */
+#define PPC_BPF_LL(r, base, i) do { \
+ if ((i) % 4) { \
+ PPC_LI(b2p[TMP_REG_2], (i)); \
+ PPC_LDX(r, base, b2p[TMP_REG_2]); \
+ } else \
+ PPC_LD(r, base, i); \
+ } while(0)
+#define PPC_BPF_STL(r, base, i) do { \
+ if ((i) % 4) { \
+ PPC_LI(b2p[TMP_REG_2], (i)); \
+ PPC_STDX(r, base, b2p[TMP_REG_2]); \
+ } else \
+ PPC_STD(r, base, i); \
+ } while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
+
#define SEEN_FUNC 0x1000 /* might call external helpers */
#define SEEN_STACK 0x2000 /* uses BPF stack */
#define SEEN_TAILCALL 0x4000 /* uses tail calls */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 4194d3c..21a1dcd 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -252,7 +252,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
* goto out;
*/
- PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
+ PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT);
PPC_BCC(COND_GT, out);
@@ -265,7 +265,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
/* prog = array->ptrs[index]; */
PPC_MULI(b2p[TMP_REG_1], b2p_index, 8);
PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array);
- PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
+ PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
/*
* if (prog == NULL)
@@ -275,7 +275,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
PPC_BCC(COND_EQ, out);
/* goto *(prog->bpf_func + prologue_size); */
- PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
+ PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
#ifdef PPC64_ELF_ABI_v1
/* skip past the function descriptor */
PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
@@ -606,7 +606,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
* the instructions generated will remain the
* same across all passes
*/
- PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx));
+ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
break;
@@ -662,7 +662,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
PPC_LI32(b2p[TMP_REG_1], imm);
src_reg = b2p[TMP_REG_1];
}
- PPC_STD(src_reg, dst_reg, off);
+ PPC_BPF_STL(src_reg, dst_reg, off);
break;
/*
@@ -709,7 +709,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
break;
/* dst = *(u64 *)(ul) (src + off) */
case BPF_LDX | BPF_MEM | BPF_DW:
- PPC_LD(dst_reg, src_reg, off);
+ PPC_BPF_LL(dst_reg, src_reg, off);
break;
/*
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a2132e0..f02367f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -193,7 +193,6 @@ enum bpf_arg_type {
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
- ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */
ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
};
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 69f7a34..7d8228d 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -66,6 +66,46 @@ struct bpf_reg_state {
* same reference to the socket, to determine proper reference freeing.
*/
u32 id;
+ /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
+ * from a pointer-cast helper, bpf_sk_fullsock() and
+ * bpf_tcp_sock().
+ *
+ * Consider the following where "sk" is a reference counted
+ * pointer returned from "sk = bpf_sk_lookup_tcp();":
+ *
+ * 1: sk = bpf_sk_lookup_tcp();
+ * 2: if (!sk) { return 0; }
+ * 3: fullsock = bpf_sk_fullsock(sk);
+ * 4: if (!fullsock) { bpf_sk_release(sk); return 0; }
+ * 5: tp = bpf_tcp_sock(fullsock);
+ * 6: if (!tp) { bpf_sk_release(sk); return 0; }
+ * 7: bpf_sk_release(sk);
+ * 8: snd_cwnd = tp->snd_cwnd; // verifier will complain
+ *
+ * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and
+ * "tp" ptr should be invalidated also. In order to do that,
+ * the reg holding "fullsock" and "sk" need to remember
+ * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id
+ * such that the verifier can reset all regs which have
+ * ref_obj_id matching the sk_reg->id.
+ *
+ * sk_reg->ref_obj_id is set to sk_reg->id at line 1.
+ * sk_reg->id will stay as NULL-marking purpose only.
+ * After NULL-marking is done, sk_reg->id can be reset to 0.
+ *
+ * After "fullsock = bpf_sk_fullsock(sk);" at line 3,
+ * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id.
+ *
+ * After "tp = bpf_tcp_sock(fullsock);" at line 5,
+ * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id
+ * which is the same as sk_reg->ref_obj_id.
+ *
+ * From the verifier perspective, if sk, fullsock and tp
+ * are not NULL, they are the same ptr with different
+ * reg->type. In particular, bpf_sk_release(tp) is also
+ * allowed and has the same effect as bpf_sk_release(sk).
+ */
+ u32 ref_obj_id;
/* For scalar types (SCALAR_VALUE), this represents our knowledge of
* the actual value.
* For pointer types, this represents the variable part of the offset
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 61cf7db..d074b6d 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -36,7 +36,6 @@ struct xdp_umem {
u32 headroom;
u32 chunk_size_nohr;
struct user_struct *user;
- struct pid *pid;
unsigned long address;
refcount_t users;
struct work_struct work;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3c38ac9..929c8e5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -502,16 +502,6 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * Description
- * Push an element *value* in *map*. *flags* is one of:
- *
- * **BPF_EXIST**
- * If the queue/stack is full, the oldest element is removed to
- * make room for this.
- * Return
- * 0 on success, or a negative error in case of failure.
- *
* int bpf_probe_read(void *dst, u32 size, const void *src)
* Description
* For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1425,14 @@ union bpf_attr {
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * *skb*, but gets socket from **struct bpf_sock_addr** context.
* Return
* A 8-byte long non-decreasing number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
*
@@ -2098,6 +2088,25 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * int bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
* int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
* Description
* This helper is used in programs implementing IR decoding, to
@@ -2124,26 +2133,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_rc_repeat(void *ctx)
- * Description
- * This helper is used in programs implementing IR decoding, to
- * report a successfully decoded repeat key message. This delays
- * the generation of a key up event for previously generated
- * key down event.
- *
- * Some IR protocols like NEC have a special IR message for
- * repeating last button, for when a button is held down.
- *
- * The *ctx* should point to the lirc sample as passed into
- * the program.
- *
- * This helper is only available is the kernel was compiled with
- * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
- * "**y**".
- * Return
- * 0
- *
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
* Description
* Return the cgroup v2 id of the socket associated with the *skb*.
* This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2149,12 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- * Description
- * Return id of cgroup v2 that is ancestor of cgroup associated
- * with the *skb* at the *ancestor_level*. The root cgroup is at
- * *ancestor_level* zero and each step down the hierarchy
- * increments the level. If *ancestor_level* == level of cgroup
- * associated with *skb*, then return value will be same as that
- * of **bpf_skb_cgroup_id**\ ().
- *
- * The helper is useful to implement policies based on cgroups
- * that are upper in hierarchy than immediate cgroup associated
- * with *skb*.
- *
- * The format of returned id and helper limitations are same as in
- * **bpf_skb_cgroup_id**\ ().
- * Return
- * The id is returned or 0 in case the id could not be retrieved.
- *
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
* Description
* Get the pointer to the local storage area.
* The type and the size of the local storage is defined
@@ -2209,6 +2181,24 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
* struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
* Description
* Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2279,16 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
* int bpf_map_pop_elem(struct bpf_map *map, void *value)
* Description
* Pop an element from *map*.
@@ -2343,29 +2343,94 @@ union bpf_attr {
* Return
* 0
*
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
* struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_sock** pointer such
- * that all the fields in bpf_sock can be accessed.
+ * that all the fields in this **bpf_sock** can be accessed.
* Return
- * A **struct bpf_sock** pointer on success, or NULL in
+ * A **struct bpf_sock** pointer on success, or **NULL** in
* case of failure.
*
* struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_tcp_sock** pointer from a
* **struct bpf_sock** pointer.
- *
* Return
- * A **struct bpf_tcp_sock** pointer on success, or NULL in
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
* case of failure.
*
* int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- * Description
- * Sets ECN of IP header to ce (congestion encountered) if
- * current value is ect (ECN capable). Works with IPv6 and IPv4.
- * Return
- * 1 if set, 0 if not set.
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2465,7 +2530,8 @@ union bpf_attr {
FN(spin_unlock), \
FN(sk_fullsock), \
FN(tcp_sock), \
- FN(skb_ecn_set_ce),
+ FN(skb_ecn_set_ce), \
+ FN(get_listener_sock),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ce166a0..86f9cd5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -212,7 +212,7 @@ struct bpf_call_arg_meta {
int access_size;
s64 msize_smax_value;
u64 msize_umax_value;
- int ptr_id;
+ int ref_obj_id;
int func_id;
};
@@ -346,35 +346,15 @@ static bool reg_type_may_be_null(enum bpf_reg_type type)
type == PTR_TO_TCP_SOCK_OR_NULL;
}
-static bool type_is_refcounted(enum bpf_reg_type type)
-{
- return type == PTR_TO_SOCKET;
-}
-
-static bool type_is_refcounted_or_null(enum bpf_reg_type type)
-{
- return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL;
-}
-
-static bool reg_is_refcounted(const struct bpf_reg_state *reg)
-{
- return type_is_refcounted(reg->type);
-}
-
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return reg->type == PTR_TO_MAP_VALUE &&
map_value_has_spin_lock(reg->map_ptr);
}
-static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg)
+static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
{
- return type_is_refcounted_or_null(reg->type);
-}
-
-static bool arg_type_is_refcounted(enum bpf_arg_type type)
-{
- return type == ARG_PTR_TO_SOCKET;
+ return type == ARG_PTR_TO_SOCK_COMMON;
}
/* Determine whether the function releases some resources allocated by another
@@ -392,6 +372,12 @@ static bool is_acquire_function(enum bpf_func_id func_id)
func_id == BPF_FUNC_sk_lookup_udp;
}
+static bool is_ptr_cast_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_tcp_sock ||
+ func_id == BPF_FUNC_sk_fullsock;
+}
+
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
@@ -465,7 +451,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (t == PTR_TO_STACK)
verbose(env, ",call_%d", func(env, reg)->callsite);
} else {
- verbose(env, "(id=%d", reg->id);
+ verbose(env, "(id=%d ref_obj_id=%d", reg->id,
+ reg->ref_obj_id);
if (t != SCALAR_VALUE)
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
@@ -2414,16 +2401,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
if (!type_is_sk_pointer(type))
goto err_type;
- } else if (arg_type == ARG_PTR_TO_SOCKET) {
- expected_type = PTR_TO_SOCKET;
- if (type != expected_type)
- goto err_type;
- if (meta->ptr_id || !reg->id) {
- verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n",
- meta->ptr_id, reg->id);
- return -EFAULT;
+ if (reg->ref_obj_id) {
+ if (meta->ref_obj_id) {
+ verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+ regno, reg->ref_obj_id,
+ meta->ref_obj_id);
+ return -EFAULT;
+ }
+ meta->ref_obj_id = reg->ref_obj_id;
}
- meta->ptr_id = reg->id;
} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
if (meta->func_id == BPF_FUNC_spin_lock) {
if (process_spin_lock(env, regno, true))
@@ -2740,32 +2726,38 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
return true;
}
-static bool check_refcount_ok(const struct bpf_func_proto *fn)
+static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
{
int count = 0;
- if (arg_type_is_refcounted(fn->arg1_type))
+ if (arg_type_may_be_refcounted(fn->arg1_type))
count++;
- if (arg_type_is_refcounted(fn->arg2_type))
+ if (arg_type_may_be_refcounted(fn->arg2_type))
count++;
- if (arg_type_is_refcounted(fn->arg3_type))
+ if (arg_type_may_be_refcounted(fn->arg3_type))
count++;
- if (arg_type_is_refcounted(fn->arg4_type))
+ if (arg_type_may_be_refcounted(fn->arg4_type))
count++;
- if (arg_type_is_refcounted(fn->arg5_type))
+ if (arg_type_may_be_refcounted(fn->arg5_type))
count++;
+ /* A reference acquiring function cannot acquire
+ * another refcounted ptr.
+ */
+ if (is_acquire_function(func_id) && count)
+ return false;
+
/* We only support one arg being unreferenced at the moment,
* which is sufficient for the helper functions we have right now.
*/
return count <= 1;
}
-static int check_func_proto(const struct bpf_func_proto *fn)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
{
return check_raw_mode_ok(fn) &&
check_arg_pair_ok(fn) &&
- check_refcount_ok(fn) ? 0 : -EINVAL;
+ check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
}
/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
@@ -2799,19 +2791,20 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
}
static void release_reg_references(struct bpf_verifier_env *env,
- struct bpf_func_state *state, int id)
+ struct bpf_func_state *state,
+ int ref_obj_id)
{
struct bpf_reg_state *regs = state->regs, *reg;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
- if (regs[i].id == id)
+ if (regs[i].ref_obj_id == ref_obj_id)
mark_reg_unknown(env, regs, i);
bpf_for_each_spilled_reg(i, state, reg) {
if (!reg)
continue;
- if (reg_is_refcounted(reg) && reg->id == id)
+ if (reg->ref_obj_id == ref_obj_id)
__mark_reg_unknown(reg);
}
}
@@ -2820,15 +2813,20 @@ static void release_reg_references(struct bpf_verifier_env *env,
* resources. Identify all copies of the same pointer and clear the reference.
*/
static int release_reference(struct bpf_verifier_env *env,
- struct bpf_call_arg_meta *meta)
+ int ref_obj_id)
{
struct bpf_verifier_state *vstate = env->cur_state;
+ int err;
int i;
- for (i = 0; i <= vstate->curframe; i++)
- release_reg_references(env, vstate->frame[i], meta->ptr_id);
+ err = release_reference_state(cur_func(env), ref_obj_id);
+ if (err)
+ return err;
- return release_reference_state(cur_func(env), meta->ptr_id);
+ for (i = 0; i <= vstate->curframe; i++)
+ release_reg_references(env, vstate->frame[i], ref_obj_id);
+
+ return 0;
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
@@ -3047,7 +3045,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
memset(&meta, 0, sizeof(meta));
meta.pkt_access = fn->pkt_access;
- err = check_func_proto(fn);
+ err = check_func_proto(fn, func_id);
if (err) {
verbose(env, "kernel subsystem misconfigured func %s#%d\n",
func_id_name(func_id), func_id);
@@ -3093,7 +3091,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return err;
}
} else if (is_release_function(func_id)) {
- err = release_reference(env, &meta);
+ err = release_reference(env, meta.ref_obj_id);
if (err) {
verbose(env, "func %s#%d reference has not been acquired before\n",
func_id_name(func_id), func_id);
@@ -3154,8 +3152,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
if (id < 0)
return id;
- /* For release_reference() */
+ /* For mark_ptr_or_null_reg() */
regs[BPF_REG_0].id = id;
+ /* For release_reference() */
+ regs[BPF_REG_0].ref_obj_id = id;
} else {
/* For mark_ptr_or_null_reg() */
regs[BPF_REG_0].id = ++env->id_gen;
@@ -3170,6 +3170,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
+ if (is_ptr_cast_function(func_id))
+ /* For release_reference() */
+ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+
do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
@@ -4665,11 +4669,19 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
} else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
reg->type = PTR_TO_TCP_SOCK;
}
- if (is_null || !(reg_is_refcounted(reg) ||
- reg_may_point_to_spin_lock(reg))) {
- /* We don't need id from this point onwards anymore,
- * thus we should better reset it, so that state
- * pruning has chances to take effect.
+ if (is_null) {
+ /* We don't need id and ref_obj_id from this point
+ * onwards anymore, thus we should better reset it,
+ * so that state pruning has chances to take effect.
+ */
+ reg->id = 0;
+ reg->ref_obj_id = 0;
+ } else if (!reg_may_point_to_spin_lock(reg)) {
+ /* For not-NULL ptr, reg->ref_obj_id will be reset
+ * in release_reg_references().
+ *
+ * reg->id is still used by spin_lock ptr. Other
+ * than spin_lock ptr type, reg->id can be reset.
*/
reg->id = 0;
}
@@ -4684,11 +4696,16 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg, *regs = state->regs;
+ u32 ref_obj_id = regs[regno].ref_obj_id;
u32 id = regs[regno].id;
int i, j;
- if (reg_is_refcounted_or_null(®s[regno]) && is_null)
- release_reference_state(state, id);
+ if (ref_obj_id && ref_obj_id == id && is_null)
+ /* regs[regno] is in the " == NULL" branch.
+ * No one could have freed the reference state before
+ * doing the NULL check.
+ */
+ WARN_ON_ONCE(release_reference_state(state, id));
for (i = 0; i < MAX_BPF_REG; i++)
mark_ptr_or_null_reg(state, ®s[i], id, is_null);
diff --git a/net/core/filter.c b/net/core/filter.c
index f274620..647c63a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1796,8 +1796,6 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk)
{
- sk = sk_to_full_sk(sk);
-
return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL;
}
@@ -5266,7 +5264,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
.func = bpf_sk_release,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_SOCKET,
+ .arg1_type = ARG_PTR_TO_SOCK_COMMON,
};
BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
@@ -5407,8 +5405,6 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
{
- sk = sk_to_full_sk(sk);
-
if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
return (unsigned long)sk;
@@ -5422,6 +5418,23 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
.arg1_type = ARG_PTR_TO_SOCK_COMMON,
};
+BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk)
+{
+ sk = sk_to_full_sk(sk);
+
+ if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE))
+ return (unsigned long)sk;
+
+ return (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_get_listener_sock_proto = {
+ .func = bpf_get_listener_sock,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_SOCK_COMMON,
+};
+
BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
{
unsigned int iphdr_len;
@@ -5607,6 +5620,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#ifdef CONFIG_INET
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
+ case BPF_FUNC_get_listener_sock:
+ return &bpf_get_listener_sock_proto;
case BPF_FUNC_skb_ecn_set_ce:
return &bpf_skb_ecn_set_ce_proto;
#endif
@@ -5702,6 +5717,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_release_proto;
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
+ case BPF_FUNC_get_listener_sock:
+ return &bpf_get_listener_sock_proto;
#endif
default:
return bpf_base_func_proto(func_id);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 77520ea..989e523 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -193,9 +193,6 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
static void xdp_umem_release(struct xdp_umem *umem)
{
- struct task_struct *task;
- struct mm_struct *mm;
-
xdp_umem_clear_dev(umem);
ida_simple_remove(&umem_ida, umem->id);
@@ -214,21 +211,10 @@ static void xdp_umem_release(struct xdp_umem *umem)
xdp_umem_unpin_pages(umem);
- task = get_pid_task(umem->pid, PIDTYPE_PID);
- put_pid(umem->pid);
- if (!task)
- goto out;
- mm = get_task_mm(task);
- put_task_struct(task);
- if (!mm)
- goto out;
-
- mmput(mm);
kfree(umem->pages);
umem->pages = NULL;
xdp_umem_unaccount_pages(umem);
-out:
kfree(umem);
}
@@ -357,7 +343,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (size_chk < 0)
return -EINVAL;
- umem->pid = get_task_pid(current, PIDTYPE_PID);
umem->address = (unsigned long)addr;
umem->chunk_mask = ~((u64)chunk_size - 1);
umem->size = size;
@@ -373,7 +358,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
err = xdp_umem_account_pages(umem);
if (err)
- goto out;
+ return err;
err = xdp_umem_pin_pages(umem);
if (err)
@@ -392,8 +377,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
out_account:
xdp_umem_unaccount_pages(umem);
-out:
- put_pid(umem->pid);
return err;
}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c38ac9..929c8e5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -502,16 +502,6 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * Description
- * Push an element *value* in *map*. *flags* is one of:
- *
- * **BPF_EXIST**
- * If the queue/stack is full, the oldest element is removed to
- * make room for this.
- * Return
- * 0 on success, or a negative error in case of failure.
- *
* int bpf_probe_read(void *dst, u32 size, const void *src)
* Description
* For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1425,14 @@ union bpf_attr {
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * *skb*, but gets socket from **struct bpf_sock_addr** context.
* Return
* A 8-byte long non-decreasing number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
*
@@ -2098,6 +2088,25 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * int bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
* int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
* Description
* This helper is used in programs implementing IR decoding, to
@@ -2124,26 +2133,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_rc_repeat(void *ctx)
- * Description
- * This helper is used in programs implementing IR decoding, to
- * report a successfully decoded repeat key message. This delays
- * the generation of a key up event for previously generated
- * key down event.
- *
- * Some IR protocols like NEC have a special IR message for
- * repeating last button, for when a button is held down.
- *
- * The *ctx* should point to the lirc sample as passed into
- * the program.
- *
- * This helper is only available is the kernel was compiled with
- * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
- * "**y**".
- * Return
- * 0
- *
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
* Description
* Return the cgroup v2 id of the socket associated with the *skb*.
* This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2149,12 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- * Description
- * Return id of cgroup v2 that is ancestor of cgroup associated
- * with the *skb* at the *ancestor_level*. The root cgroup is at
- * *ancestor_level* zero and each step down the hierarchy
- * increments the level. If *ancestor_level* == level of cgroup
- * associated with *skb*, then return value will be same as that
- * of **bpf_skb_cgroup_id**\ ().
- *
- * The helper is useful to implement policies based on cgroups
- * that are upper in hierarchy than immediate cgroup associated
- * with *skb*.
- *
- * The format of returned id and helper limitations are same as in
- * **bpf_skb_cgroup_id**\ ().
- * Return
- * The id is returned or 0 in case the id could not be retrieved.
- *
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
* Description
* Get the pointer to the local storage area.
* The type and the size of the local storage is defined
@@ -2209,6 +2181,24 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
* struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
* Description
* Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2279,16 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
* int bpf_map_pop_elem(struct bpf_map *map, void *value)
* Description
* Pop an element from *map*.
@@ -2343,29 +2343,94 @@ union bpf_attr {
* Return
* 0
*
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
* struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_sock** pointer such
- * that all the fields in bpf_sock can be accessed.
+ * that all the fields in this **bpf_sock** can be accessed.
* Return
- * A **struct bpf_sock** pointer on success, or NULL in
+ * A **struct bpf_sock** pointer on success, or **NULL** in
* case of failure.
*
* struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
* Description
* This helper gets a **struct bpf_tcp_sock** pointer from a
* **struct bpf_sock** pointer.
- *
* Return
- * A **struct bpf_tcp_sock** pointer on success, or NULL in
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
* case of failure.
*
* int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- * Description
- * Sets ECN of IP header to ce (congestion encountered) if
- * current value is ect (ECN capable). Works with IPv6 and IPv4.
- * Return
- * 1 if set, 0 if not set.
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2465,7 +2530,8 @@ union bpf_attr {
FN(spin_unlock), \
FN(sk_fullsock), \
FN(tcp_sock), \
- FN(skb_ecn_set_ce),
+ FN(skb_ecn_set_ce), \
+ FN(get_listener_sock),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1b8d8cd..87e3020 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
/* Calculate type signature hash of ENUM. */
static __u32 btf_hash_enum(struct btf_type *t)
{
- struct btf_enum *member = (struct btf_enum *)(t + 1);
- __u32 vlen = BTF_INFO_VLEN(t->info);
- __u32 h = btf_hash_common(t);
- int i;
+ __u32 h;
- for (i = 0; i < vlen; i++) {
- h = hash_combine(h, member->name_off);
- h = hash_combine(h, member->val);
- member++;
- }
+ /* don't hash vlen and enum members to support enum fwd resolving */
+ h = hash_combine(0, t->name_off);
+ h = hash_combine(h, t->info & ~0xffff);
+ h = hash_combine(h, t->size);
return h;
}
@@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
return true;
}
+static inline bool btf_is_enum_fwd(struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
+ BTF_INFO_VLEN(t->info) == 0;
+}
+
+static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
+{
+ if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
+ return btf_equal_enum(t1, t2);
+ /* ignore vlen when comparing */
+ return t1->name_off == t2->name_off &&
+ (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
+ t1->size == t2->size;
+}
+
/*
* Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
* as referenced type IDs equivalence is established separately during type
@@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
new_id = cand_node->type_id;
break;
}
+ if (d->opts.dont_resolve_fwds)
+ continue;
+ if (btf_compat_enum(t, cand)) {
+ if (btf_is_enum_fwd(t)) {
+ /* resolve fwd to full enum */
+ new_id = cand_node->type_id;
+ break;
+ }
+ /* resolve canonical enum fwd to full enum */
+ d->map[cand_node->type_id] = type_id;
+ }
}
break;
@@ -2084,15 +2107,15 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
return fwd_kind == real_kind;
}
- if (cand_type->info != canon_type->info)
- return 0;
-
switch (cand_kind) {
case BTF_KIND_INT:
return btf_equal_int(cand_type, canon_type);
case BTF_KIND_ENUM:
- return btf_equal_enum(cand_type, canon_type);
+ if (d->opts.dont_resolve_fwds)
+ return btf_equal_enum(cand_type, canon_type);
+ else
+ return btf_compat_enum(cand_type, canon_type);
case BTF_KIND_FWD:
return btf_equal_common(cand_type, canon_type);
@@ -2103,6 +2126,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
case BTF_KIND_PTR:
case BTF_KIND_TYPEDEF:
case BTF_KIND_FUNC:
+ if (cand_type->info != canon_type->info)
+ return 0;
return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d5b830d..5e977d2 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -835,12 +835,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
obj->efile.maps_shndx = idx;
else if (strcmp(name, BTF_ELF_SEC) == 0) {
obj->btf = btf__new(data->d_buf, data->d_size);
- if (IS_ERR(obj->btf) || btf__load(obj->btf)) {
+ if (IS_ERR(obj->btf)) {
pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
BTF_ELF_SEC, PTR_ERR(obj->btf));
- if (!IS_ERR(obj->btf))
- btf__free(obj->btf);
obj->btf = NULL;
+ continue;
+ }
+ err = btf__load(obj->btf);
+ if (err) {
+ pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n",
+ BTF_ELF_SEC, err);
+ btf__free(obj->btf);
+ obj->btf = NULL;
+ err = 0;
}
} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
btf_ext_data = data;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index f98ac82..8d0078b 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
cfg->frame_headroom = usr_cfg->frame_headroom;
}
-static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
- const struct xsk_socket_config *usr_cfg)
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+ const struct xsk_socket_config *usr_cfg)
{
if (!usr_cfg) {
cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
cfg->libbpf_flags = 0;
cfg->xdp_flags = 0;
cfg->bind_flags = 0;
- return;
+ return 0;
}
+ if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
+ return -EINVAL;
+
cfg->rx_size = usr_cfg->rx_size;
cfg->tx_size = usr_cfg->tx_size;
cfg->libbpf_flags = usr_cfg->libbpf_flags;
cfg->xdp_flags = usr_cfg->xdp_flags;
cfg->bind_flags = usr_cfg->bind_flags;
+
+ return 0;
}
int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
@@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
strncpy(xsk->ifname, ifname, IFNAMSIZ);
- xsk_set_xdp_socket_config(&xsk->config, usr_config);
+ err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+ if (err)
+ goto out_socket;
if (rx) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index c9433a4..c81fc35 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) =
(void *) BPF_FUNC_sk_fullsock;
static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) =
(void *) BPF_FUNC_tcp_sock;
+static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) =
+ (void *) BPF_FUNC_get_listener_sock;
static int (*bpf_skb_ecn_set_ce)(void *ctx) =
(void *) BPF_FUNC_skb_ecn_set_ce;
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
index 90f8a206..ee99368 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -37,7 +37,7 @@ void test_map_lock(void)
const char *file = "./test_map_lock.o";
int prog_fd, map_fd[2], vars[17] = {};
pthread_t thread_id[6];
- struct bpf_object *obj;
+ struct bpf_object *obj = NULL;
int err = 0, key = 0, i;
void *ret;
diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c
index 9a573a9..114ebe6 100644
--- a/tools/testing/selftests/bpf/prog_tests/spinlock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c
@@ -5,7 +5,7 @@ void test_spinlock(void)
{
const char *file = "./test_spin_lock.o";
pthread_t thread_id[4];
- struct bpf_object *obj;
+ struct bpf_object *obj = NULL;
int prog_fd;
int err = 0, i;
void *ret;
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index de1a43e..37328f1 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -8,38 +8,51 @@
#include "bpf_helpers.h"
#include "bpf_endian.h"
-enum bpf_array_idx {
- SRV_IDX,
- CLI_IDX,
- __NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+ ADDR_SRV_IDX,
+ ADDR_CLI_IDX,
+ __NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+ EGRESS_SRV_IDX,
+ EGRESS_CLI_IDX,
+ INGRESS_LISTEN_IDX,
+ __NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+ EGRESS_LINUM_IDX,
+ INGRESS_LINUM_IDX,
+ __NR_BPF_LINUM_ARRAY_IDX,
};
struct bpf_map_def SEC("maps") addr_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct sockaddr_in6),
- .max_entries = __NR_BPF_ARRAY_IDX,
+ .max_entries = __NR_BPF_ADDR_ARRAY_IDX,
};
struct bpf_map_def SEC("maps") sock_result_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct bpf_sock),
- .max_entries = __NR_BPF_ARRAY_IDX,
+ .max_entries = __NR_BPF_RESULT_ARRAY_IDX,
};
struct bpf_map_def SEC("maps") tcp_sock_result_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct bpf_tcp_sock),
- .max_entries = __NR_BPF_ARRAY_IDX,
+ .max_entries = __NR_BPF_RESULT_ARRAY_IDX,
};
struct bpf_map_def SEC("maps") linum_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
- .max_entries = 1,
+ .max_entries = __NR_BPF_LINUM_ARRAY_IDX,
};
static bool is_loopback6(__u32 *a6)
@@ -100,18 +113,20 @@ static void tpcpy(struct bpf_tcp_sock *dst,
#define RETURN { \
linum = __LINE__; \
- bpf_map_update_elem(&linum_map, &idx0, &linum, 0); \
+ bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0); \
return 1; \
}
SEC("cgroup_skb/egress")
-int read_sock_fields(struct __sk_buff *skb)
+int egress_read_sock_fields(struct __sk_buff *skb)
{
- __u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx;
+ __u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx;
struct sockaddr_in6 *srv_sa6, *cli_sa6;
struct bpf_tcp_sock *tp, *tp_ret;
struct bpf_sock *sk, *sk_ret;
- __u32 linum, idx0 = 0;
+ __u32 linum, linum_idx;
+
+ linum_idx = EGRESS_LINUM_IDX;
sk = skb->sk;
if (!sk || sk->state == 10)
@@ -132,14 +147,55 @@ int read_sock_fields(struct __sk_buff *skb)
RETURN;
if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port))
- idx = srv_idx;
+ result_idx = EGRESS_SRV_IDX;
else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port))
- idx = cli_idx;
+ result_idx = EGRESS_CLI_IDX;
else
RETURN;
- sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx);
- tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx);
+ sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+ tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
+ if (!sk_ret || !tp_ret)
+ RETURN;
+
+ skcpy(sk_ret, sk);
+ tpcpy(tp_ret, tp);
+
+ RETURN;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_read_sock_fields(struct __sk_buff *skb)
+{
+ __u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX;
+ struct bpf_tcp_sock *tp, *tp_ret;
+ struct bpf_sock *sk, *sk_ret;
+ struct sockaddr_in6 *srv_sa6;
+ __u32 linum, linum_idx;
+
+ linum_idx = INGRESS_LINUM_IDX;
+
+ sk = skb->sk;
+ if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6))
+ RETURN;
+
+ srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
+ if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port))
+ RETURN;
+
+ if (sk->state != 10 && sk->state != 12)
+ RETURN;
+
+ sk = bpf_get_listener_sock(sk);
+ if (!sk)
+ RETURN;
+
+ tp = bpf_tcp_sock(sk);
+ if (!tp)
+ RETURN;
+
+ sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+ tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
if (!sk_ret || !tp_ret)
RETURN;
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 38797aa..23e3b31 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5874,6 +5874,50 @@ const struct btf_dedup_test dedup_tests[] = {
.dont_resolve_fwds = false,
},
},
+{
+ .descr = "dedup: enum fwd resolution",
+ .input = {
+ .raw_types = {
+ /* [1] fwd enum 'e1' before full enum */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+ /* [2] full enum 'e1' after fwd */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 123),
+ /* [3] full enum 'e2' before fwd */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(4), 456),
+ /* [4] fwd enum 'e2' after full enum */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+ /* [5] incompatible fwd enum with different size */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+ /* [6] incompatible full enum with different value */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 321),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+ },
+ .expect = {
+ .raw_types = {
+ /* [1] full enum 'e1' */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 123),
+ /* [2] full enum 'e2' */
+ BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(4), 456),
+ /* [3] incompatible fwd enum with different size */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+ /* [4] incompatible full enum with different value */
+ BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+ BTF_ENUM_ENC(NAME_NTH(2), 321),
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+ },
+ .opts = {
+ .dont_resolve_fwds = false,
+ },
+},
};
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
index bc89439..dcae7f6 100644
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -16,10 +16,23 @@
#include "cgroup_helpers.h"
#include "bpf_rlimit.h"
-enum bpf_array_idx {
- SRV_IDX,
- CLI_IDX,
- __NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+ ADDR_SRV_IDX,
+ ADDR_CLI_IDX,
+ __NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+ EGRESS_SRV_IDX,
+ EGRESS_CLI_IDX,
+ INGRESS_LISTEN_IDX,
+ __NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+ EGRESS_LINUM_IDX,
+ INGRESS_LINUM_IDX,
+ __NR_BPF_LINUM_ARRAY_IDX,
};
#define CHECK(condition, tag, format...) ({ \
@@ -41,8 +54,16 @@ static int linum_map_fd;
static int addr_map_fd;
static int tp_map_fd;
static int sk_map_fd;
-static __u32 srv_idx = SRV_IDX;
-static __u32 cli_idx = CLI_IDX;
+
+static __u32 addr_srv_idx = ADDR_SRV_IDX;
+static __u32 addr_cli_idx = ADDR_CLI_IDX;
+
+static __u32 egress_srv_idx = EGRESS_SRV_IDX;
+static __u32 egress_cli_idx = EGRESS_CLI_IDX;
+static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX;
+
+static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
+static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
static void init_loopback6(struct sockaddr_in6 *sa6)
{
@@ -93,29 +114,46 @@ static void print_tp(const struct bpf_tcp_sock *tp)
static void check_result(void)
{
- struct bpf_tcp_sock srv_tp, cli_tp;
- struct bpf_sock srv_sk, cli_sk;
- __u32 linum, idx0 = 0;
+ struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
+ struct bpf_sock srv_sk, cli_sk, listen_sk;
+ __u32 ingress_linum, egress_linum;
int err;
- err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum);
+ err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
+ &egress_linum);
CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
"err:%d errno:%d", err, errno);
- err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk);
- CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)",
- "err:%d errno:%d", err, errno);
- err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp);
- CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)",
+ err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
+ &ingress_linum);
+ CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
"err:%d errno:%d", err, errno);
- err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk);
- CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)",
+ err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk);
+ CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)",
"err:%d errno:%d", err, errno);
- err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp);
- CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)",
+ err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp);
+ CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)",
"err:%d errno:%d", err, errno);
+ err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk);
+ CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)",
+ "err:%d errno:%d", err, errno);
+ err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp);
+ CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)",
+ "err:%d errno:%d", err, errno);
+
+ err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk);
+ CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)",
+ "err:%d errno:%d", err, errno);
+ err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp);
+ CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)",
+ "err:%d errno:%d", err, errno);
+
+ printf("listen_sk: ");
+ print_sk(&listen_sk);
+ printf("\n");
+
printf("srv_sk: ");
print_sk(&srv_sk);
printf("\n");
@@ -124,6 +162,10 @@ static void check_result(void)
print_sk(&cli_sk);
printf("\n");
+ printf("listen_tp: ");
+ print_tp(&listen_tp);
+ printf("\n");
+
printf("srv_tp: ");
print_tp(&srv_tp);
printf("\n");
@@ -132,6 +174,19 @@ static void check_result(void)
print_tp(&cli_tp);
printf("\n");
+ CHECK(listen_sk.state != 10 ||
+ listen_sk.family != AF_INET6 ||
+ listen_sk.protocol != IPPROTO_TCP ||
+ memcmp(listen_sk.src_ip6, &in6addr_loopback,
+ sizeof(listen_sk.src_ip6)) ||
+ listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] ||
+ listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] ||
+ listen_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+ listen_sk.dst_port,
+ "Unexpected listen_sk",
+ "Check listen_sk output. ingress_linum:%u",
+ ingress_linum);
+
CHECK(srv_sk.state == 10 ||
!srv_sk.state ||
srv_sk.family != AF_INET6 ||
@@ -142,7 +197,8 @@ static void check_result(void)
sizeof(srv_sk.dst_ip6)) ||
srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
srv_sk.dst_port != cli_sa6.sin6_port,
- "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum);
+ "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u",
+ egress_linum);
CHECK(cli_sk.state == 10 ||
!cli_sk.state ||
@@ -154,21 +210,31 @@ static void check_result(void)
sizeof(cli_sk.dst_ip6)) ||
cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
cli_sk.dst_port != srv_sa6.sin6_port,
- "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum);
+ "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u",
+ egress_linum);
+
+ CHECK(listen_tp.data_segs_out ||
+ listen_tp.data_segs_in ||
+ listen_tp.total_retrans ||
+ listen_tp.bytes_acked,
+ "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u",
+ ingress_linum);
CHECK(srv_tp.data_segs_out != 1 ||
srv_tp.data_segs_in ||
srv_tp.snd_cwnd != 10 ||
srv_tp.total_retrans ||
srv_tp.bytes_acked != DATA_LEN,
- "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum);
+ "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u",
+ egress_linum);
CHECK(cli_tp.data_segs_out ||
cli_tp.data_segs_in != 1 ||
cli_tp.snd_cwnd != 10 ||
cli_tp.total_retrans ||
cli_tp.bytes_received != DATA_LEN,
- "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum);
+ "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u",
+ egress_linum);
}
static void test(void)
@@ -211,10 +277,10 @@ static void test(void)
err, errno);
/* Update addr_map with srv_sa6 and cli_sa6 */
- err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0);
+ err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0);
CHECK(err, "map_update", "err:%d errno:%d", err, errno);
- err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0);
+ err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0);
CHECK(err, "map_update", "err:%d errno:%d", err, errno);
/* Connect from cli_sa6 to srv_sa6 */
@@ -273,9 +339,9 @@ int main(int argc, char **argv)
struct bpf_prog_load_attr attr = {
.file = "test_sock_fields_kern.o",
.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
- .expected_attach_type = BPF_CGROUP_INET_EGRESS,
};
- int cgroup_fd, prog_fd, err;
+ int cgroup_fd, egress_fd, ingress_fd, err;
+ struct bpf_program *ingress_prog;
struct bpf_object *obj;
struct bpf_map *map;
@@ -293,12 +359,24 @@ int main(int argc, char **argv)
err = join_cgroup(TEST_CGROUP);
CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno);
- err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+ err = bpf_prog_load_xattr(&attr, &obj, &egress_fd);
CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
- err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
+ ingress_prog = bpf_object__find_program_by_title(obj,
+ "cgroup_skb/ingress");
+ CHECK(!ingress_prog,
+ "bpf_object__find_program_by_title(cgroup_skb/ingress)",
+ "not found");
+ ingress_fd = bpf_program__fd(ingress_prog);
+
+ err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)",
"err:%d errno%d", err, errno);
+
+ err = bpf_prog_attach(ingress_fd, cgroup_fd,
+ BPF_CGROUP_INET_INGRESS, 0);
+ CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)",
+ "err:%d errno%d", err, errno);
close(cgroup_fd);
map = bpf_object__find_map_by_name(obj, "addr_map");
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 3ed3593..923f211 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -605,3 +605,171 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
},
+{
+ "reference tracking: use ptr from bpf_tcp_sock() after release",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "invalid mem access",
+},
+{
+ "reference tracking: use ptr from bpf_sk_fullsock() after release",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "invalid mem access",
+},
+{
+ "reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "invalid mem access",
+},
+{
+ "reference tracking: use sk after bpf_sk_release(tp)",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "invalid mem access",
+},
+{
+ "reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+},
+{
+ "reference tracking: bpf_sk_release(listen_sk)",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "reference has not been acquired before",
+},
+{
+ /* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
+ "reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)",
+ .insns = {
+ BPF_SK_LOOKUP,
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_EMIT_CALL(BPF_FUNC_sk_release),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "invalid mem access",
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 0ddfdf7..4164362 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -342,7 +342,7 @@
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
- .errstr = "type=sock_common expected=sock",
+ .errstr = "reference has not been acquired before",
},
{
"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
@@ -380,5 +380,5 @@
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
- .errstr = "type=tcp_sock expected=sock",
+ .errstr = "reference has not been acquired before",
},
