bpf: fix context access in tracing progs on 32 bit archs

Wang reported that all the testcases for BPF_PROG_TYPE_PERF_EVENT
program type in test_verifier report the following errors on x86_32:

  172/p unpriv: spill/fill of different pointers ldx FAIL
  Unexpected error message!
  0: (bf) r6 = r10
  1: (07) r6 += -8
  2: (15) if r1 == 0x0 goto pc+3
  R1=ctx(id=0,off=0,imm=0) R6=fp-8,call_-1 R10=fp0,call_-1
  3: (bf) r2 = r10
  4: (07) r2 += -76
  5: (7b) *(u64 *)(r6 +0) = r2
  6: (55) if r1 != 0x0 goto pc+1
  R1=ctx(id=0,off=0,imm=0) R2=fp-76,call_-1 R6=fp-8,call_-1 R10=fp0,call_-1 fp-8=fp
  7: (7b) *(u64 *)(r6 +0) = r1
  8: (79) r1 = *(u64 *)(r6 +0)
  9: (79) r1 = *(u64 *)(r1 +68)
  invalid bpf_context access off=68 size=8

  378/p check bpf_perf_event_data->sample_period byte load permitted FAIL
  Failed to load prog 'Permission denied'!
  0: (b7) r0 = 0
  1: (71) r0 = *(u8 *)(r1 +68)
  invalid bpf_context access off=68 size=1

  379/p check bpf_perf_event_data->sample_period half load permitted FAIL
  Failed to load prog 'Permission denied'!
  0: (b7) r0 = 0
  1: (69) r0 = *(u16 *)(r1 +68)
  invalid bpf_context access off=68 size=2

  380/p check bpf_perf_event_data->sample_period word load permitted FAIL
  Failed to load prog 'Permission denied'!
  0: (b7) r0 = 0
  1: (61) r0 = *(u32 *)(r1 +68)
  invalid bpf_context access off=68 size=4

  381/p check bpf_perf_event_data->sample_period dword load permitted FAIL
  Failed to load prog 'Permission denied'!
  0: (b7) r0 = 0
  1: (79) r0 = *(u64 *)(r1 +68)
  invalid bpf_context access off=68 size=8

Reason is that struct pt_regs on x86_32 doesn't fully align to 8 byte
boundary due to its size of 68 bytes. Therefore, bpf_ctx_narrow_access_ok()
will then bail out saying that off & (size_default - 1) which is 68 & 7
doesn't cleanly align in the case of sample_period access from struct
bpf_perf_event_data, hence verifier wrongly thinks we might be doing an
unaligned access here though underlying arch can handle it just fine.
Therefore adjust this down to machine size and check and rewrite the
offset for narrow access on that basis. We also need to fix corresponding
pe_prog_is_valid_access(), since we hit the check for off % size != 0
(e.g. 68 % 8 -> 4) in the first and last test. With that in place, progs
for tracing work on x86_32.

Reported-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 10 insertions, 3 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1dd6d5a7aa5bf..d6403b5166f49 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5349,6 +5349,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		 */
 		is_narrower_load = size < ctx_field_size;
 		if (is_narrower_load) {
+			u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
 			u32 off = insn->off;
 			u8 size_code;
 
@@ -5363,7 +5364,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			else if (ctx_field_size == 8)
 				size_code = BPF_DW;
 
-			insn->off = off & ~(ctx_field_size - 1);
+			insn->off = off & ~(size_default - 1);
 			insn->code = BPF_LDX | BPF_MEM | size_code;
 		}
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index af1486d9a0ed6..752992ce35131 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -880,8 +880,14 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type
 		return false;
 	if (type != BPF_READ)
 		return false;
-	if (off % size != 0)
-		return false;
+	if (off % size != 0) {
+		if (sizeof(unsigned long) != 4)
+			return false;
+		if (size != 8)
+			return false;
+		if (off % size != 4)
+			return false;
+	}
 
 	switch (off) {
 	case bpf_ctx_range(struct bpf_perf_event_data, sample_period):