Received-SPF: pass (google.com: domain of linux-kernel+bounces-125454-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Precedence: bulk
MIME-Version: 1.0
References: <20240329094906.18147-1-ubizjak@gmail.com> <20240329094906.18147-3-ubizjak@gmail.com>
In-Reply-To: <20240329094906.18147-3-ubizjak@gmail.com>
From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Date: Fri, 29 Mar 2024 14:53:03 -0700
Message-ID: <CAADnVQ+6D++hCXaP=aK+Q5wienMzhHo3h9YCvpA_7sHjMt+q6A@mail.gmail.com>
Subject: Re: [PATCH RESEND bpf 2/2] x86/bpf: Fix IP for relocating call depth accounting
To: Uros Bizjak <ubizjak@gmail.com>
Cc: X86 ML <x86@kernel.org>, bpf <bpf@vger.kernel.org>, 
	Network Development <netdev@vger.kernel.org>, LKML <linux-kernel@vger.kernel.org>, 
	=?UTF-8?Q?Joan_Bruguera_Mic=C3=B3?= <joanbrugueram@gmail.com>, 
	Ingo Molnar <mingo@kernel.org>, Alexei Starovoitov <ast@kernel.org>, 
	Daniel Borkmann <daniel@iogearbox.net>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, Mar 29, 2024 at 2:49=E2=80=AFAM Uros Bizjak <ubizjak@gmail.com> wro=
te:
>
> From: Joan Bruguera Mic=C3=B3 <joanbrugueram@gmail.com>
>
> The recently introduced support for %rip-relative relocations in the
> call thunk template assumes that the code is being patched in-place,
> so the destination of the relocation matches the address of the code.
> This is not true for the call depth accounting emitted by the BPF JIT,
> so the calculated address is wrong and usually causes a page fault.

Could you share the link to what this 'rip-relative' relocation is ?

> Pass the destination IP when the BPF JIT emits call depth accounting.
>
> Fixes: 17bce3b2ae2d ("x86/callthunks: Handle %rip-relative relocations in=
 call thunk template")

Ohh. It's buried inside that patch.
Pls make commit log a bit more clear that that commit 17bce3b2ae2d
broke x86_call_depth_emit_accounting logic.

> Signed-off-by: Joan Bruguera Mic=C3=B3 <joanbrugueram@gmail.com>
> Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
> Acked-by: Ingo Molnar <mingo@kernel.org>
> Cc: Alexei Starovoitov <ast@kernel.org>
> Cc: Daniel Borkmann <daniel@iogearbox.net>
> ---
>  arch/x86/include/asm/alternative.h |  4 ++--
>  arch/x86/kernel/callthunks.c       |  4 ++--
>  arch/x86/net/bpf_jit_comp.c        | 19 ++++++++-----------
>  3 files changed, 12 insertions(+), 15 deletions(-)
>
> diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/al=
ternative.h
> index fcd20c6dc7f9..67b68d0d17d1 100644
> --- a/arch/x86/include/asm/alternative.h
> +++ b/arch/x86/include/asm/alternative.h
> @@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
>  extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
>                                           struct module *mod);
>  extern void *callthunks_translate_call_dest(void *dest);
> -extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
> +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *=
ip);
>  #else
>  static __always_inline void callthunks_patch_builtin_calls(void) {}
>  static __always_inline void
> @@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_cal=
l_dest(void *dest)
>         return dest;
>  }
>  static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
> -                                                         void *func)
> +                                                         void *func, voi=
d *ip)
>  {
>         return 0;
>  }
> diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
> index 30335182b6b0..e92ff0c11db8 100644
> --- a/arch/x86/kernel/callthunks.c
> +++ b/arch/x86/kernel/callthunks.c
> @@ -314,7 +314,7 @@ static bool is_callthunk(void *addr)
>         return !bcmp(pad, insn_buff, tmpl_size);
>  }
>
> -int x86_call_depth_emit_accounting(u8 **pprog, void *func)
> +int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
>  {
>         unsigned int tmpl_size =3D SKL_TMPL_SIZE;
>         u8 insn_buff[MAX_PATCH_LEN];
> @@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *=
func)
>                 return 0;
>
>         memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
> -       apply_relocation(insn_buff, tmpl_size, *pprog,
> +       apply_relocation(insn_buff, tmpl_size, ip,

Did the logic inside apply_relocation() change to have
a new meaning for 'dest' and 'src'?
Answering to myself... yes. in that commit.
Better commit log would have made the code review so much easier.

>                          skl_call_thunk_template, tmpl_size);
>
>         memcpy(*pprog, insn_buff, tmpl_size);
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index 09f7dc9d4d65..f2e8769f5eee 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
> @@ -481,7 +481,7 @@ static int emit_rsb_call(u8 **pprog, void *func, void=
 *ip)
>  {
>         void *adjusted_ip;
>         OPTIMIZER_HIDE_VAR(func);
> -       adjusted_ip =3D ip + x86_call_depth_emit_accounting(pprog, func);
> +       adjusted_ip =3D ip + x86_call_depth_emit_accounting(pprog, func, =
ip);

Now I see why you added extra var in the previous patch.
Should have mentioned it in the commit log.

>         return emit_patch(pprog, func, adjusted_ip, 0xE8);
>  }
>
> @@ -1973,20 +1973,17 @@ st:                     if (is_imm8(insn->off))
>
>                         /* call */
>                 case BPF_JMP | BPF_CALL: {
> -                       int offs;
> +                       u8 *ip =3D image + addrs[i - 1];
>
>                         func =3D (u8 *) __bpf_call_base + imm32;
>                         if (tail_call_reachable) {
>                                 RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stac=
k_depth);
> -                               if (!imm32)
> -                                       return -EINVAL;
> -                               offs =3D 7 + x86_call_depth_emit_accounti=
ng(&prog, func);
> -                       } else {
> -                               if (!imm32)
> -                                       return -EINVAL;
> -                               offs =3D x86_call_depth_emit_accounting(&=
prog, func);
> +                               ip +=3D 7;
>                         }
> -                       if (emit_call(&prog, func, image + addrs[i - 1] +=
 offs))
> +                       if (!imm32)
> +                               return -EINVAL;
> +                       ip +=3D x86_call_depth_emit_accounting(&prog, fun=
c, ip);
> +                       if (emit_call(&prog, func, ip))
>                                 return -EINVAL;
>                         break;
>                 }
> @@ -2836,7 +2833,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf=
_tramp_image *im, void *rw_im
>                  * Direct-call fentry stub, as such it needs accounting f=
or the
>                  * __fentry__ call.
>                  */
> -               x86_call_depth_emit_accounting(&prog, NULL);
> +               x86_call_depth_emit_accounting(&prog, NULL, image);

Overall it all makes sense.
Pls respin with more precise commit logs.