bpf/verifier: rework value tracking

Unifies adjusted and unadjusted register value types (e.g. FRAME_POINTER is
 now just a PTR_TO_STACK with zero offset).
Tracks value alignment by means of tracking known & unknown bits.  This
 also replaces the 'reg->imm' (leading zero bits) calculations for (what
 were) UNKNOWN_VALUEs.
If pointer leaks are allowed, and adjust_ptr_min_max_vals returns -EACCES,
 treat the pointer as an unknown scalar and try again, because we might be
 able to conclude something about the result (e.g. pointer & 0x40 is either
 0 or 0x40).
Verifier hooks in the netronome/nfp driver were changed to match the new
 data structures.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/bpf/verifier.c

@@ -79,28 +79,32 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog,
 		   const struct bpf_verifier_env *env)
 {
 	const struct bpf_reg_state *reg0 = &env->cur_state.regs[0];
+	u64 imm;
 
 	if (nfp_prog->act == NN_ACT_XDP)
 		return 0;
 
-	if (reg0->type != CONST_IMM) {
-		pr_info("unsupported exit state: %d, imm: %llx\n",
-			reg0->type, reg0->imm);
+	if (!(reg0->type == SCALAR_VALUE && tnum_is_const(reg0->var_off))) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg0->var_off);
+		pr_info("unsupported exit state: %d, var_off: %s\n",
+			reg0->type, tn_buf);
 		return -EINVAL;
 	}
 
-	if (nfp_prog->act != NN_ACT_DIRECT &&
-	    reg0->imm != 0 && (reg0->imm & ~0U) != ~0U) {
+	imm = reg0->var_off.value;
+	if (nfp_prog->act != NN_ACT_DIRECT && imm != 0 && (imm & ~0U) != ~0U) {
 		pr_info("unsupported exit state: %d, imm: %llx\n",
-			reg0->type, reg0->imm);
+			reg0->type, imm);
 		return -EINVAL;
 	}
 
-	if (nfp_prog->act == NN_ACT_DIRECT && reg0->imm <= TC_ACT_REDIRECT &&
-	    reg0->imm != TC_ACT_SHOT && reg0->imm != TC_ACT_STOLEN &&
-	    reg0->imm != TC_ACT_QUEUED) {
+	if (nfp_prog->act == NN_ACT_DIRECT && imm <= TC_ACT_REDIRECT &&
+	    imm != TC_ACT_SHOT && imm != TC_ACT_STOLEN &&
+	    imm != TC_ACT_QUEUED) {
 		pr_info("unsupported exit state: %d, imm: %llx\n",
-			reg0->type, reg0->imm);
+			reg0->type, imm);
 		return -EINVAL;
 	}
 

include/linux/bpf.h

@@ -117,35 +117,25 @@ enum bpf_access_type {
 };
 
 /* types of values stored in eBPF registers */
+/* Pointer types represent:
+ * pointer
+ * pointer + imm
+ * pointer + (u16) var
+ * pointer + (u16) var + imm
+ * if (range > 0) then [ptr, ptr + range - off) is safe to access
+ * if (id > 0) means that some 'var' was added
+ * if (off > 0) means that 'imm' was added
+ */
 enum bpf_reg_type {
 	NOT_INIT = 0,		 /* nothing was written into register */
-	UNKNOWN_VALUE,		 /* reg doesn't contain a valid pointer */
+	SCALAR_VALUE,		 /* reg doesn't contain a valid pointer */
 	PTR_TO_CTX,		 /* reg points to bpf_context */
 	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
 	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
 	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
-	FRAME_PTR,		 /* reg == frame_pointer */
-	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
-	CONST_IMM,		 /* constant integer value */
-
-	/* PTR_TO_PACKET represents:
-	 * skb->data
-	 * skb->data + imm
-	 * skb->data + (u16) var
-	 * skb->data + (u16) var + imm
-	 * if (range > 0) then [ptr, ptr + range - off) is safe to access
-	 * if (id > 0) means that some 'var' was added
-	 * if (off > 0) menas that 'imm' was added
-	 */
-	PTR_TO_PACKET,
+	PTR_TO_STACK,		 /* reg == frame_pointer + offset */
+	PTR_TO_PACKET,		 /* reg points to skb->data */
 	PTR_TO_PACKET_END,	 /* skb->data + headlen */
-
-	/* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map
-	 * elem value.  We only allow this if we can statically verify that
-	 * access from this register are going to fall within the size of the
-	 * map element.
-	 */
-	PTR_TO_MAP_VALUE_ADJ,
 };
 
 struct bpf_prog;

include/linux/bpf_verifier.h

@@ -9,6 +9,7 @@
 
 #include <linux/bpf.h> /* for enum bpf_reg_type */
 #include <linux/filter.h> /* for MAX_BPF_STACK */
+#include <linux/tnum.h>
 
  /* Just some arbitrary values so we can safely do math without overflowing and
   * are obviously wrong for any sort of memory access.
@@ -19,30 +20,37 @@
 struct bpf_reg_state {
 	enum bpf_reg_type type;
 	union {
-		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
-		s64 imm;
-
-		/* valid when type == PTR_TO_PACKET* */
-		struct {
-			u16 off;
-			u16 range;
-		};
+		/* valid when type == PTR_TO_PACKET */
+		u16 range;
 
 		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
 		 *   PTR_TO_MAP_VALUE_OR_NULL
 		 */
 		struct bpf_map *map_ptr;
 	};
+	/* Fixed part of pointer offset, pointer types only */
+	s32 off;
+	/* For PTR_TO_PACKET, used to find other pointers with the same variable
+	 * offset, so they can share range knowledge.
+	 * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
+	 * came from, when one is tested for != NULL.
+	 */
 	u32 id;
+	/* These three fields must be last.  See states_equal() */
+	/* For scalar types (SCALAR_VALUE), this represents our knowledge of
+	 * the actual value.
+	 * For pointer types, this represents the variable part of the offset
+	 * from the pointed-to object, and is shared with all bpf_reg_states
+	 * with the same id as us.
+	 */
+	struct tnum var_off;
 	/* Used to determine if any memory access using this register will
-	 * result in a bad access. These two fields must be last.
-	 * See states_equal()
+	 * result in a bad access.
+	 * These refer to the same value as var_off, not necessarily the actual
+	 * contents of the register.
 	 */
 	s64 min_value;
 	u64 max_value;
-	u32 min_align;
-	u32 aux_off;
-	u32 aux_off_align;
 	bool value_from_signed;
 };
 

include/linux/tnum.h

@@ -0,0 +1,79 @@
+/* tnum: tracked (or tristate) numbers
+ *
+ * A tnum tracks knowledge about the bits of a value.  Each bit can be either
+ * known (0 or 1), or unknown (x).  Arithmetic operations on tnums will
+ * propagate the unknown bits such that the tnum result represents all the
+ * possible results for possible values of the operands.
+ */
+#include <linux/types.h>
+
+struct tnum {
+	u64 value;
+	u64 mask;
+};
+
+/* Constructors */
+/* Represent a known constant as a tnum. */
+struct tnum tnum_const(u64 value);
+/* A completely unknown value */
+extern const struct tnum tnum_unknown;
+
+/* Arithmetic and logical ops */
+/* Shift a tnum left (by a fixed shift) */
+struct tnum tnum_lshift(struct tnum a, u8 shift);
+/* Shift a tnum right (by a fixed shift) */
+struct tnum tnum_rshift(struct tnum a, u8 shift);
+/* Add two tnums, return @a + @b */
+struct tnum tnum_add(struct tnum a, struct tnum b);
+/* Subtract two tnums, return @a - @b */
+struct tnum tnum_sub(struct tnum a, struct tnum b);
+/* Bitwise-AND, return @a & @b */
+struct tnum tnum_and(struct tnum a, struct tnum b);
+/* Bitwise-OR, return @a | @b */
+struct tnum tnum_or(struct tnum a, struct tnum b);
+/* Bitwise-XOR, return @a ^ @b */
+struct tnum tnum_xor(struct tnum a, struct tnum b);
+/* Multiply two tnums, return @a * @b */
+struct tnum tnum_mul(struct tnum a, struct tnum b);
+
+/* Return a tnum representing numbers satisfying both @a and @b */
+struct tnum tnum_intersect(struct tnum a, struct tnum b);
+
+/* Return @a with all but the lowest @size bytes cleared */
+struct tnum tnum_cast(struct tnum a, u8 size);
+
+/* Returns true if @a is a known constant */
+static inline bool tnum_is_const(struct tnum a)
+{
+	return !a.mask;
+}
+
+/* Returns true if @a == tnum_const(@b) */
+static inline bool tnum_equals_const(struct tnum a, u64 b)
+{
+	return tnum_is_const(a) && a.value == b;
+}
+
+/* Returns true if @a is completely unknown */
+static inline bool tnum_is_unknown(struct tnum a)
+{
+	return !~a.mask;
+}
+
+/* Returns true if @a is known to be a multiple of @size.
+ * @size must be a power of two.
+ */
+bool tnum_is_aligned(struct tnum a, u64 size);
+
+/* Returns true if @b represents a subset of @a. */
+bool tnum_in(struct tnum a, struct tnum b);
+
+/* Formatting functions.  These have snprintf-like semantics: they will write
+ * up to @size bytes (including the terminating NUL byte), and return the number
+ * of bytes (excluding the terminating NUL) which would have been written had
+ * sufficient space been available.  (Thus tnum_sbin always returns 64.)
+ */
+/* Format a tnum as a pair of hex numbers (value; mask) */
+int tnum_strn(char *str, size_t size, struct tnum a);
+/* Format a tnum as tristate binary expansion */
+int tnum_sbin(char *str, size_t size, struct tnum a);

kernel/bpf/Makefile

@@ -1,6 +1,6 @@
 obj-y := core.o
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o