Re: [PATCH ipsec-next v1 6/7] bpf: selftests: test_tunnel: Disable CO-RE relocations

[Eduard Zingerman <eddyz87@gmail.com>]

On Sun, 2023-11-26 at 18:04 -0600, Daniel Xu wrote:
[...]
> > Tbh I'm not sure. This test passes with preserve_static_offset
> > because it suppresses preserve_access_index. In general clang
> > translates bitfield access to a set of IR statements like:
> > 
> >   C:
> >     struct foo {
> >       unsigned _;
> >       unsigned a:1;
> >       ...
> >     };
> >     ... foo->a ...
> > 
> >   IR:
> >     %a = getelementptr inbounds %struct.foo, ptr %0, i32 0, i32 1
> >     %bf.load = load i8, ptr %a, align 4
> >     %bf.clear = and i8 %bf.load, 1
> >     %bf.cast = zext i8 %bf.clear to i32
> > 
> > With preserve_static_offset the getelementptr+load are replaced by a
> > single statement which is preserved as-is till code generation,
> > thus load with align 4 is preserved.
> > 
> > On the other hand, I'm not sure that clang guarantees that load or
> > stores used for bitfield access would be always aligned according to
> > verifier expectations.
> > 
> > I think we should check if there are some clang knobs that prevent
> > generation of unaligned memory access. I'll take a look.
> 
> Is there a reason to prefer fixing in compiler? I'm not opposed to it,
> but the downside to compiler fix is it takes years to propagate and
> sprinkles ifdefs into the code.
>
> Would it be possible to have an analogue of BPF_CORE_READ_BITFIELD()?

Well, the contraption below passes verification, tunnel selftest
appears to work. I might have messed up some shifts in the macro, though.

Still, if clang would peek unlucky BYTE_{OFFSET,SIZE} for a particular
field access might be unaligned.

---

diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 3065a716544d..41cd913ac7ff 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -9,6 +9,7 @@
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
 #include "bpf_kfuncs.h"
 #include "bpf_tracing_net.h"
 
@@ -144,6 +145,38 @@ int ip6gretap_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({			\
+	void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET);	\
+	unsigned byte_size = __CORE_RELO(s, field, BYTE_SIZE);		\
+	unsigned lshift = __CORE_RELO(s, field, LSHIFT_U64);		\
+	unsigned rshift = __CORE_RELO(s, field, RSHIFT_U64);		\
+	unsigned bit_size = (rshift - lshift);				\
+	unsigned long long nval, val, hi, lo;				\
+									\
+	asm volatile("" : "=r"(p) : "0"(p));				\
+									\
+	switch (byte_size) {						\
+	case 1: val = *(unsigned char *)p; break;			\
+	case 2: val = *(unsigned short *)p; break;			\
+	case 4: val = *(unsigned int *)p; break;			\
+	case 8: val = *(unsigned long long *)p; break;			\
+	}								\
+	hi = val >> (bit_size + rshift);				\
+	hi <<= bit_size + rshift;					\
+	lo = val << (bit_size + lshift);				\
+	lo >>= bit_size + lshift;					\
+	nval = new_val;							\
+	nval <<= lshift;						\
+	nval >>= rshift;						\
+	val = hi | nval | lo;						\
+	switch (byte_size) {						\
+	case 1: *(unsigned char *)p      = val; break;			\
+	case 2: *(unsigned short *)p     = val; break;			\
+	case 4: *(unsigned int *)p       = val; break;			\
+	case 8: *(unsigned long long *)p = val; break;			\
+	}								\
+})
+
 SEC("tc")
 int erspan_set_tunnel(struct __sk_buff *skb)
 {
@@ -173,9 +206,9 @@ int erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 7;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -214,8 +247,9 @@ int erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -252,9 +286,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 17;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -294,8 +328,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif