All of lore.kernel.org
 help / color / mirror / Atom feed
From: Josh Poimboeuf <jpoimboe@redhat.com>
To: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>,
	Ingo Molnar <mingo@kernel.org>, X86 ML <x86@kernel.org>,
	Daniel Xu <dxu@dxuuu.xyz>,
	linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
	kuba@kernel.org, mingo@redhat.com, ast@kernel.org,
	tglx@linutronix.de, kernel-team@fb.com, yhs@fb.com,
	linux-ia64@vger.kernel.org,
	Abhishek Sagar <sagar.abhishek@gmail.com>,
	Andrii Nakryiko <andrii.nakryiko@gmail.com>
Subject: Re: [PATCH -tip v7 11/13] x86/unwind: Recover kretprobe trampoline entry
Date: Wed, 16 Jun 2021 23:41:24 -0500	[thread overview]
Message-ID: <20210617044124.pv4xm47cum4faaeo@treble> (raw)
In-Reply-To: <162209764814.436794.15907711942126944591.stgit@devnote2>

On Thu, May 27, 2021 at 03:40:48PM +0900, Masami Hiramatsu wrote:
> Since the kretprobe replaces the function return address with
> the kretprobe_trampoline on the stack, x86 unwinders can not
> continue the stack unwinding at that point, or record
> kretprobe_trampoline instead of correct return address.
> 
> To fix this issue, find the correct return address from task's
> kretprobe_instances as like as function-graph tracer does.
> 
> With this fix, the unwinder can correctly unwind the stack
> from kretprobe event on x86, as below.
> 
>            <...>-135     [003] ...1     6.722338: r_full_proxy_read_0: (vfs_read+0xab/0x1a0 <- full_proxy_read)
>            <...>-135     [003] ...1     6.722377: <stack trace>
>  => kretprobe_trace_func+0x209/0x2f0
>  => kretprobe_dispatcher+0x4a/0x70
>  => __kretprobe_trampoline_handler+0xca/0x150
>  => trampoline_handler+0x44/0x70
>  => kretprobe_trampoline+0x2a/0x50
>  => vfs_read+0xab/0x1a0
>  => ksys_read+0x5f/0xe0
>  => do_syscall_64+0x33/0x40
>  => entry_SYSCALL_64_after_hwframe+0x44/0xae
> 
> 
> Reported-by: Daniel Xu <dxu@dxuuu.xyz>
> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Tested-by: Andrii Nakryik <andrii@kernel.org>

Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>

-- 
Josh


WARNING: multiple messages have this Message-ID (diff)
From: Josh Poimboeuf <jpoimboe@redhat.com>
To: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>,
	Ingo Molnar <mingo@kernel.org>, X86 ML <x86@kernel.org>,
	Daniel Xu <dxu@dxuuu.xyz>,
	linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
	kuba@kernel.org, mingo@redhat.com, ast@kernel.org,
	tglx@linutronix.de, kernel-team@fb.com, yhs@fb.com,
	linux-ia64@vger.kernel.org,
	Abhishek Sagar <sagar.abhishek@gmail.com>,
	Andrii Nakryiko <andrii.nakryiko@gmail.com>
Subject: Re: [PATCH -tip v7 11/13] x86/unwind: Recover kretprobe trampoline entry
Date: Thu, 17 Jun 2021 04:41:24 +0000	[thread overview]
Message-ID: <20210617044124.pv4xm47cum4faaeo@treble> (raw)
In-Reply-To: <162209764814.436794.15907711942126944591.stgit@devnote2>

On Thu, May 27, 2021 at 03:40:48PM +0900, Masami Hiramatsu wrote:
> Since the kretprobe replaces the function return address with
> the kretprobe_trampoline on the stack, x86 unwinders can not
> continue the stack unwinding at that point, or record
> kretprobe_trampoline instead of correct return address.
> 
> To fix this issue, find the correct return address from task's
> kretprobe_instances as like as function-graph tracer does.
> 
> With this fix, the unwinder can correctly unwind the stack
> from kretprobe event on x86, as below.
> 
>            <...>-135     [003] ...1     6.722338: r_full_proxy_read_0: (vfs_read+0xab/0x1a0 <- full_proxy_read)
>            <...>-135     [003] ...1     6.722377: <stack trace>
>  => kretprobe_trace_func+0x209/0x2f0
>  => kretprobe_dispatcher+0x4a/0x70
>  => __kretprobe_trampoline_handler+0xca/0x150
>  => trampoline_handler+0x44/0x70
>  => kretprobe_trampoline+0x2a/0x50
>  => vfs_read+0xab/0x1a0
>  => ksys_read+0x5f/0xe0
>  => do_syscall_64+0x33/0x40
>  => entry_SYSCALL_64_after_hwframe+0x44/0xae
> 
> 
> Reported-by: Daniel Xu <dxu@dxuuu.xyz>
> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
> Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Tested-by: Andrii Nakryik <andrii@kernel.org>

Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>

-- 
Josh

  reply	other threads:[~2021-06-17  4:41 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-27  6:39 [PATCH -tip v7 00/13] kprobes: Fix stacktrace with kretprobes on x86 Masami Hiramatsu
2021-05-27  6:39 ` Masami Hiramatsu
2021-05-27  6:39 ` [PATCH -tip v7 01/13] ia64: kprobes: Fix to pass correct trampoline address to the handler Masami Hiramatsu
2021-05-27  6:39   ` Masami Hiramatsu
2021-05-27  6:39 ` [PATCH -tip v7 02/13] kprobes: treewide: Replace arch_deref_entry_point() with dereference_symbol_descriptor() Masami Hiramatsu
2021-05-27  6:39   ` [PATCH -tip v7 02/13] kprobes: treewide: Replace arch_deref_entry_point() with dereference_symbol_de Masami Hiramatsu
2021-05-27  6:39 ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_handler() Masami Hiramatsu
2021-05-27  6:39   ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_handler Masami Hiramatsu
2021-06-14 15:46   ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_handler() Naveen N. Rao
2021-06-14 15:58     ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_han Naveen N. Rao
2021-06-15  0:06     ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_handler() Masami Hiramatsu
2021-06-15  0:06       ` [PATCH -tip v7 03/13] kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_han Masami Hiramatsu
2021-05-27  6:39 ` [PATCH -tip v7 04/13] kprobes: Add kretprobe_find_ret_addr() for searching return address Masami Hiramatsu
2021-05-27  6:39   ` Masami Hiramatsu
2021-05-27  6:39 ` [PATCH -tip v7 05/13] x86/kprobes: Add UNWIND_HINT_FUNC on kretprobe_trampoline code Masami Hiramatsu
2021-05-27  6:39   ` Masami Hiramatsu
2021-05-27  6:40 ` [PATCH -tip v7 06/13] ARC: Add instruction_pointer_set() API Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-05-27  6:40 ` [PATCH -tip v7 07/13] ia64: " Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-05-27  6:40 ` [PATCH -tip v7 08/13] arm: kprobes: Make a space for regs->ARM_pc at kretprobe_trampoline Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-05-27  6:40 ` [PATCH -tip v7 09/13] kprobes: Setup instruction pointer in __kretprobe_trampoline_handler Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-06-17  4:39   ` Josh Poimboeuf
2021-06-17  4:39     ` Josh Poimboeuf
2021-06-17  4:40     ` Josh Poimboeuf
2021-06-17  4:40       ` Josh Poimboeuf
2021-06-17 14:40       ` Masami Hiramatsu
2021-06-17 14:40         ` Masami Hiramatsu
2021-06-17 15:02         ` Masami Hiramatsu
2021-06-17 15:02           ` Masami Hiramatsu
2021-06-17 17:45           ` Andrii Nakryiko
2021-06-17 17:45             ` Andrii Nakryiko
2021-06-17 18:21             ` Josh Poimboeuf
2021-06-17 18:21               ` Josh Poimboeuf
2021-06-17 18:31               ` Andrii Nakryiko
2021-06-17 18:31                 ` Andrii Nakryiko
2021-06-17 19:26                 ` Josh Poimboeuf
2021-06-17 19:26                   ` Josh Poimboeuf
2021-06-17 19:46                   ` Andrii Nakryiko
2021-06-17 19:46                     ` Andrii Nakryiko
2021-06-18  0:33                     ` Masami Hiramatsu
2021-06-18  0:33                       ` Masami Hiramatsu
2021-06-18  1:03                       ` Josh Poimboeuf
2021-06-18  1:03                         ` Josh Poimboeuf
2021-06-17 23:58               ` Masami Hiramatsu
2021-06-17 23:58                 ` Masami Hiramatsu
2021-06-18  0:58                 ` Josh Poimboeuf
2021-06-18  0:58                   ` Josh Poimboeuf
2021-05-27  6:40 ` [PATCH -tip v7 10/13] x86/kprobes: Push a fake return address at kretprobe_trampoline Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-06-17  4:41   ` Josh Poimboeuf
2021-06-17  4:41     ` Josh Poimboeuf
2021-05-27  6:40 ` [PATCH -tip v7 11/13] x86/unwind: Recover kretprobe trampoline entry Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-06-17  4:41   ` Josh Poimboeuf [this message]
2021-06-17  4:41     ` Josh Poimboeuf
2021-05-27  6:40 ` [PATCH -tip v7 12/13] tracing: Show kretprobe unknown indicator only for kretprobe_trampoline Masami Hiramatsu
2021-05-27  6:40   ` Masami Hiramatsu
2021-05-27  6:41 ` [PATCH -tip v7 13/13] x86/kprobes: Fixup return address in generic trampoline handler Masami Hiramatsu
2021-05-27  6:41   ` Masami Hiramatsu
2021-05-27 16:41 ` [PATCH -tip v7 00/13] kprobes: Fix stacktrace with kretprobes on x86 Andrii Nakryiko
2021-05-27 16:41   ` Andrii Nakryiko
2021-06-10  3:40 ` Masami Hiramatsu
2021-06-10  3:40   ` Masami Hiramatsu

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=20210617044124.pv4xm47cum4faaeo@treble \
    --to=jpoimboe@redhat.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=dxu@dxuuu.xyz \
    --cc=kernel-team@fb.com \
    --cc=kuba@kernel.org \
    --cc=linux-ia64@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@kernel.org \
    --cc=mingo@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=sagar.abhishek@gmail.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --cc=yhs@fb.com \
    /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.