bpf: simplify narrower ctx access

This work tries to make the semantics and code around the
narrower ctx access a bit easier to follow. Right now
everything is done inside the .is_valid_access(). Offset
matching is done differently for read/write types, meaning
writes don't support narrower access and thus matching only
on offsetof(struct foo, bar) is enough whereas for read
case that supports narrower access we must check for
offsetof(struct foo, bar) + offsetof(struct foo, bar) +
sizeof(<bar>) - 1 for each of the cases. For read cases of
individual members that don't support narrower access (like
packet pointers or skb->cb[] case which has its own narrow
access logic), we check as usual only offsetof(struct foo,
bar) like in write case. Then, for the case where narrower
access is allowed, we also need to set the aux info for the
access. Meaning, ctx_field_size and converted_op_size have
to be set. First is the original field size e.g. sizeof(<bar>)
as in above example from the user facing ctx, and latter
one is the target size after actual rewrite happened, thus
for the kernel facing ctx. Also here we need the range match
and we need to keep track changing convert_ctx_access() and
converted_op_size from is_valid_access() as both are not at
the same location.

We can simplify the code a bit: check_ctx_access() becomes
simpler in that we only store ctx_field_size as a meta data
and later in convert_ctx_accesses() we fetch the target_size
right from the location where we do convert. Should the verifier
be misconfigured we do reject for BPF_WRITE cases or target_size
that are not provided. For the subsystems, we always work on
ranges in is_valid_access() and add small helpers for ranges
and narrow access, convert_ctx_accesses() sets target_size
for the relevant instruction.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Cc: Yonghong Song <yhs@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 19 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 97c46b440cd6..5c6d538dbf43 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -583,7 +583,8 @@ const struct bpf_verifier_ops tracepoint_prog_ops = {
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
-	int sample_period_off;
+	const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data,
+					 sample_period);
 
 	if (off < 0 || off >= sizeof(struct bpf_perf_event_data))
 		return false;
@@ -592,43 +593,35 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	if (off % size != 0)
 		return false;
 
-	/* permit 1, 2, 4 byte narrower and 8 normal read access to sample_period */
-	sample_period_off = offsetof(struct bpf_perf_event_data, sample_period);
-	if (off >= sample_period_off && off < sample_period_off + sizeof(__u64)) {
-		int allowed;
-
-#ifdef __LITTLE_ENDIAN
-		allowed = (off & 0x7) == 0 && size <= 8 && (size & (size - 1)) == 0;
-#else
-		allowed = ((off & 0x7) + size) == 8 && size <= 8 && (size & (size - 1)) == 0;
-#endif
-		if (!allowed)
+	switch (off) {
+	case bpf_ctx_range(struct bpf_perf_event_data, sample_period):
+		bpf_ctx_record_field_size(info, size_sp);
+		if (!bpf_ctx_narrow_access_ok(off, size, size_sp))
 			return false;
-		info->ctx_field_size = 8;
-		info->converted_op_size = 8;
-	} else {
+		break;
+	default:
 		if (size != sizeof(long))
 			return false;
 	}
+
 	return true;
 }
 
 static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 				      const struct bpf_insn *si,
 				      struct bpf_insn *insn_buf,
-				      struct bpf_prog *prog)
+				      struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
 
 	switch (si->off) {
 	case offsetof(struct bpf_perf_event_data, sample_period):
-		BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64));
-
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,
 						       data), si->dst_reg, si->src_reg,
 				      offsetof(struct bpf_perf_event_data_kern, data));
 		*insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
-				      offsetof(struct perf_sample_data, period));
+				      bpf_target_off(struct perf_sample_data, period, 8,
+						     target_size));
 		break;
 	default:
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern,