Re: [PATCH v4 5/8] bpf ppc64: Add BPF_PROBE_MEM support for JIT

On Wed, Sep 29, 2021 at 9:50 PM Christophe Leroy
[off-list ref] wrote:

Le 29/09/2021 à 13:18, Hari Bathini a écrit :

quoted

From: Ravi Bangoria <redacted>

BPF load instruction with BPF_PROBE_MEM mode can cause a fault
inside kernel. Append exception table for such instructions
within BPF program.

Unlike other archs which uses extable 'fixup' field to pass dest_reg
and nip, BPF exception table on PowerPC follows the generic PowerPC

For my curiosity, can you explain why we don't want and can't do the
same on powerpc as on other archs ?

The main thing is on x86, the extable has another field , handler:
struct exception_table_entry { int insn, fixup, handler; };
handler can be used to perform other things before continuing on to fixup.
So for bpf the handler is used to clear the dest register (which is
encoded in the low byte of fixup).
More detail in 3dec541b2e63 ("bpf: Add support for BTF pointers to x86 JIT").

arm64 is an example of an arch that doesn't have a handler field in the extable.
They did something along the lines of this rather than adding a
handler field to the extable.
See 800834285361 ("bpf, arm64: Add BPF exception tables")

quoted

exception table design, where it populates both fixup and extable
sections within BPF program. fixup section contains two instructions,
first instruction clears dest_reg and 2nd jumps to next instruction
in the BPF code. extable 'insn' field contains relative offset of
the instruction and 'fixup' field contains relative offset of the
fixup entry. Example layout of BPF program with extable present:

              +------------------+
              |                  |
              |                  |
    0x4020 -->| ld   r27,4(r3)   |
              |                  |
              |                  |
    0x40ac -->| lwz  r3,0(r4)    |
              |                  |
              |                  |
              |------------------|
    0x4280 -->| li  r27,0        |  \ fixup entry
              | b   0x4024       |  /
    0x4288 -->| li  r3,0         |
              | b   0x40b0       |
              |------------------|
    0x4290 -->| insn=0xfffffd90  |  \ extable entry
              | fixup=0xffffffec |  /
    0x4298 -->| insn=0xfffffe14  |
              | fixup=0xffffffec |
              +------------------+

    (Addresses shown here are chosen random, not real)