All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michael Ellerman <mpe@ellerman.id.au>
To: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	netdev@vger.kernel.org, Matt Evans <matt@ozlabs.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Alexei Starovoitov <ast@fb.com>,
	Denis Kirjanov <kda@linux-powerpc.org>,
	Paul Mackerras <paulus@samba.org>,
	"David S. Miller" <davem@davemloft.net>,
	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Subject: Re: [PATCH] ppc: Fix BPF JIT for ABIv2
Date: Wed, 22 Jun 2016 15:18:10 +1000	[thread overview]
Message-ID: <1466572690.19785.4.camel@ellerman.id.au> (raw)
In-Reply-To: <20160617130042.GO3516@indiana.gru.redhat.com>

On Fri, 2016-06-17 at 10:00 -0300, Thadeu Lima de Souza Cascardo wrote:
> From a984dc02b6317a1d3a3c2302385adba5227be5bd Mon Sep 17 00:00:00 2001
> From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
> Date: Wed, 15 Jun 2016 13:22:12 -0300
> Subject: [PATCH] ppc: Fix BPF JIT for ABIv2
> 
> ABIv2 used for ppc64le does not use function descriptors. Without this patch,
> whenever BPF JIT is enabled, we get a crash as below.
> 
...

> diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
> index 889fd19..28b89ed 100644
> --- a/arch/powerpc/net/bpf_jit.h
> +++ b/arch/powerpc/net/bpf_jit.h
> @@ -70,7 +70,7 @@ DECLARE_LOAD_FUNC(sk_load_half);
>  DECLARE_LOAD_FUNC(sk_load_byte);
>  DECLARE_LOAD_FUNC(sk_load_byte_msh);
>  
> -#ifdef CONFIG_PPC64
> +#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2)
>  #define FUNCTION_DESCR_SIZE	24
>  #else
>  #define FUNCTION_DESCR_SIZE	0
> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> index 2d66a84..035b887 100644
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c
> @@ -664,7 +664,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
>  
>  	if (image) {
>  		bpf_flush_icache(code_base, code_base + (proglen/4));
> -#ifdef CONFIG_PPC64
> +#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2)
>  		/* Function descriptor nastiness: Address + TOC */
>  		((u64 *)image)[0] = (u64)code_base;
>  		((u64 *)image)[1] = local_paca->kernel_toc;


Confirmed that even with this patch we still crash:

  # echo 1 > /proc/sys/net/core/bpf_jit_enable
  # modprobe test_bpf
  BPF filter opcode 0020 (@3) unsupported
  BPF filter opcode 0020 (@2) unsupported
  BPF filter opcode 0020 (@0) unsupported
  Unable to handle kernel paging request for data at address 0xd0000000054f65e8
  Faulting instruction address: 0xc0000000008765f8
  cpu 0x0: Vector: 300 (Data Access) at [c0000000034f3480]
      pc: c0000000008765f8: skb_copy_bits+0x158/0x330
      lr: c00000000008fb7c: bpf_slow_path_byte+0x28/0x54
      sp: c0000000034f3700
     msr: 800000010280b033
     dar: d0000000054f65e8
   dsisr: 40000000
    current = 0xc0000001f857d8d0
    paca    = 0xc000000007b80000	 softe: 0	 irq_happened: 0x01
      pid   = 2993, comm = modprobe
  Linux version 4.7.0-rc3-00055-g9497a1c1c5b4-dirty (michael@ka3.ozlabs.ibm.com) () #30 SMP Wed Jun 22 15:06:58 AEST 2016
  enter ? for help
  [c0000000034f3770] c00000000008fb7c bpf_slow_path_byte+0x28/0x54
  [c0000000034f37e0] d000000007bb004c
  [c0000000034f3900] d000000005331668 test_bpf_init+0x5fc/0x7f8 [test_bpf]
  [c0000000034f3a30] c00000000000b628 do_one_initcall+0x68/0x1d0
  [c0000000034f3af0] c0000000009beb24 do_init_module+0x90/0x240
  [c0000000034f3b80] c0000000001642bc load_module+0x206c/0x22f0
  [c0000000034f3d30] c0000000001648b0 SyS_finit_module+0x120/0x180
  [c0000000034f3e30] c000000000009260 system_call+0x38/0x108
  --- Exception: c01 (System Call) at 00003fff7ffa2db4


cheers

WARNING: multiple messages have this Message-ID (diff)
From: Michael Ellerman <mpe@ellerman.id.au>
To: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Cc: Matt Evans <matt@ozlabs.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Alexei Starovoitov <ast@fb.com>,
	netdev@vger.kernel.org, Denis Kirjanov <kda@linux-powerpc.org>,
	linux-kernel@vger.kernel.org, Paul Mackerras <paulus@samba.org>,
	"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>,
	linuxppc-dev@lists.ozlabs.org,
	"David S. Miller" <davem@davemloft.net>,
	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Subject: Re: [PATCH] ppc: Fix BPF JIT for ABIv2
Date: Wed, 22 Jun 2016 15:18:10 +1000	[thread overview]
Message-ID: <1466572690.19785.4.camel@ellerman.id.au> (raw)
In-Reply-To: <20160617130042.GO3516@indiana.gru.redhat.com>

On Fri, 2016-06-17 at 10:00 -0300, Thadeu Lima de Souza Cascardo wrote:
> From a984dc02b6317a1d3a3c2302385adba5227be5bd Mon Sep 17 00:00:00 2001
> From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
> Date: Wed, 15 Jun 2016 13:22:12 -0300
> Subject: [PATCH] ppc: Fix BPF JIT for ABIv2
> 
> ABIv2 used for ppc64le does not use function descriptors. Without this patch,
> whenever BPF JIT is enabled, we get a crash as below.
> 
...

> diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
> index 889fd19..28b89ed 100644
> --- a/arch/powerpc/net/bpf_jit.h
> +++ b/arch/powerpc/net/bpf_jit.h
> @@ -70,7 +70,7 @@ DECLARE_LOAD_FUNC(sk_load_half);
>  DECLARE_LOAD_FUNC(sk_load_byte);
>  DECLARE_LOAD_FUNC(sk_load_byte_msh);
>  
> -#ifdef CONFIG_PPC64
> +#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2)
>  #define FUNCTION_DESCR_SIZE	24
>  #else
>  #define FUNCTION_DESCR_SIZE	0
> diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
> index 2d66a84..035b887 100644
> --- a/arch/powerpc/net/bpf_jit_comp.c
> +++ b/arch/powerpc/net/bpf_jit_comp.c
> @@ -664,7 +664,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
>  
>  	if (image) {
>  		bpf_flush_icache(code_base, code_base + (proglen/4));
> -#ifdef CONFIG_PPC64
> +#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2)
>  		/* Function descriptor nastiness: Address + TOC */
>  		((u64 *)image)[0] = (u64)code_base;
>  		((u64 *)image)[1] = local_paca->kernel_toc;


Confirmed that even with this patch we still crash:

  # echo 1 > /proc/sys/net/core/bpf_jit_enable
  # modprobe test_bpf
  BPF filter opcode 0020 (@3) unsupported
  BPF filter opcode 0020 (@2) unsupported
  BPF filter opcode 0020 (@0) unsupported
  Unable to handle kernel paging request for data at address 0xd0000000054f65e8
  Faulting instruction address: 0xc0000000008765f8
  cpu 0x0: Vector: 300 (Data Access) at [c0000000034f3480]
      pc: c0000000008765f8: skb_copy_bits+0x158/0x330
      lr: c00000000008fb7c: bpf_slow_path_byte+0x28/0x54
      sp: c0000000034f3700
     msr: 800000010280b033
     dar: d0000000054f65e8
   dsisr: 40000000
    current = 0xc0000001f857d8d0
    paca    = 0xc000000007b80000	 softe: 0	 irq_happened: 0x01
      pid   = 2993, comm = modprobe
  Linux version 4.7.0-rc3-00055-g9497a1c1c5b4-dirty (michael@ka3.ozlabs.ibm.com) () #30 SMP Wed Jun 22 15:06:58 AEST 2016
  enter ? for help
  [c0000000034f3770] c00000000008fb7c bpf_slow_path_byte+0x28/0x54
  [c0000000034f37e0] d000000007bb004c
  [c0000000034f3900] d000000005331668 test_bpf_init+0x5fc/0x7f8 [test_bpf]
  [c0000000034f3a30] c00000000000b628 do_one_initcall+0x68/0x1d0
  [c0000000034f3af0] c0000000009beb24 do_init_module+0x90/0x240
  [c0000000034f3b80] c0000000001642bc load_module+0x206c/0x22f0
  [c0000000034f3d30] c0000000001648b0 SyS_finit_module+0x120/0x180
  [c0000000034f3e30] c000000000009260 system_call+0x38/0x108
  --- Exception: c01 (System Call) at 00003fff7ffa2db4


cheers

_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev

  parent reply	other threads:[~2016-06-22  5:18 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-07 13:32 [PATCH 0/6] eBPF JIT for PPC64 Naveen N. Rao
2016-06-07 13:32 ` [PATCH 1/6] ppc: bpf/jit: Fix/enhance 32-bit Load Immediate implementation Naveen N. Rao
2016-06-07 13:32 ` [PATCH 2/6] ppc: bpf/jit: Optimize 64-bit Immediate loads Naveen N. Rao
2016-06-07 13:32 ` [PATCH 3/6] ppc: bpf/jit: Introduce rotate immediate instructions Naveen N. Rao
2016-06-07 13:32 ` [PATCH 4/6] ppc: bpf/jit: A few cleanups Naveen N. Rao
2016-06-07 13:32 ` [PATCH 5/6] ppc: bpf/jit: Isolate classic BPF JIT specifics into a separate header Naveen N. Rao
2016-06-07 13:32 ` [PATCH 6/6] ppc: ebpf/jit: Implement JIT compiler for extended BPF Naveen N. Rao
2016-06-07 22:56   ` Alexei Starovoitov
2016-06-08 17:17     ` Naveen N. Rao
2016-06-09  3:19   ` Nilay Vaish
2016-06-09  6:07     ` Naveen N. Rao
2016-06-17 12:53   ` [6/6] " Michael Ellerman
2016-06-17 13:00     ` [PATCH] ppc: Fix BPF JIT for ABIv2 Thadeu Lima de Souza Cascardo
2016-06-19 17:49       ` Naveen N. Rao
2016-06-20 18:56         ` Thadeu Lima de Souza Cascardo
2016-06-20 18:56           ` Thadeu Lima de Souza Cascardo
2016-06-21  8:58           ` Naveen N. Rao
2016-06-21  8:58             ` Naveen N. Rao
2016-06-21 11:15             ` Michael Ellerman
2016-06-21 11:15               ` Michael Ellerman
2016-06-21 14:47               ` Thadeu Lima de Souza Cascardo
2016-06-21 14:47                 ` Thadeu Lima de Souza Cascardo
2016-06-21 15:45                 ` Alexei Starovoitov
2016-06-22  4:06                   ` Michael Ellerman
2016-06-22  7:12                 ` Naveen N. Rao
2016-06-22 14:57                   ` Naveen N. Rao
2016-06-22  5:20             ` Michael Ellerman
2016-06-22  5:20               ` Michael Ellerman
2016-06-22  5:18       ` Michael Ellerman [this message]
2016-06-22  5:18         ` Michael Ellerman
2016-06-19 17:36     ` [6/6] ppc: ebpf/jit: Implement JIT compiler for extended BPF Naveen N. Rao
2016-06-20 23:38       ` Michael Ellerman
2016-06-20 23:38         ` Michael Ellerman
2016-06-21  6:58         ` Naveen N. Rao
2016-06-21 11:04           ` Michael Ellerman
2016-06-21 11:04             ` Michael Ellerman
2016-06-22  7:06             ` Naveen N. Rao
2016-06-22 10:37   ` [PATCH 6/6] " Michael Ellerman
2016-06-22 12:32     ` Naveen N. Rao
2016-06-11  5:47 ` [PATCH 0/6] eBPF JIT for PPC64 David Miller
2016-06-13  5:40   ` Naveen N. Rao
2016-06-18  4:57     ` mpe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1466572690.19785.4.camel@ellerman.id.au \
    --to=mpe@ellerman.id.au \
    --cc=ananth@in.ibm.com \
    --cc=ast@fb.com \
    --cc=cascardo@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=kda@linux-powerpc.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=matt@ozlabs.org \
    --cc=naveen.n.rao@linux.vnet.ibm.com \
    --cc=netdev@vger.kernel.org \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.