Re: [PATCH RFC 02/10] perf: Remove get_perf_callchain() 'crosstask' argument

[Namhyung Kim <namhyung@kernel.org>]

On Wed, Nov 8, 2023 at 4:44 PM Josh Poimboeuf <jpoimboe@kernel.org> wrote:
>
> get_perf_callchain() doesn't support cross-task unwinding, so it doesn't

For only user stacks, but it seems there's no place to get cross-task kernel
stacks too.

> make much sense to have 'crosstask' as an argument.  Instead, have
> perf_callchain() adjust 'user' accordingly.
>
> Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>

Acked-by: Namhyung Kim <namhyung@kernel.org>

Thanks,
Namhyung

> ---
>  include/linux/perf_event.h | 2 +-
>  kernel/bpf/stackmap.c      | 5 ++---
>  kernel/events/callchain.c  | 6 +-----
>  kernel/events/core.c       | 8 ++++----
>  4 files changed, 8 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index f4b05954076c..2d8fa253b9df 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1534,7 +1534,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p
>  extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
>  extern struct perf_callchain_entry *
>  get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
> -                  u32 max_stack, bool crosstask, bool add_mark);
> +                  u32 max_stack, bool add_mark);
>  extern int get_callchain_buffers(int max_stack);
>  extern void put_callchain_buffers(void);
>  extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
> diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
> index b0b0fbff7c18..e4827ca5378d 100644
> --- a/kernel/bpf/stackmap.c
> +++ b/kernel/bpf/stackmap.c
> @@ -294,8 +294,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
>         if (max_depth > sysctl_perf_event_max_stack)
>                 max_depth = sysctl_perf_event_max_stack;
>
> -       trace = get_perf_callchain(regs, kernel, user, max_depth,
> -                                  false, false);
> +       trace = get_perf_callchain(regs, kernel, user, max_depth, false);
>
>         if (unlikely(!trace))
>                 /* couldn't fetch the stack trace */
> @@ -421,7 +420,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
>                 trace = get_callchain_entry_for_task(task, max_depth);
>         else
>                 trace = get_perf_callchain(regs, kernel, user, max_depth,
> -                                          false, false);
> +                                          false);
>         if (unlikely(!trace))
>                 goto err_fault;
>
> diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
> index 1e135195250c..aa5f9d11c28d 100644
> --- a/kernel/events/callchain.c
> +++ b/kernel/events/callchain.c
> @@ -178,7 +178,7 @@ put_callchain_entry(int rctx)
>
>  struct perf_callchain_entry *
>  get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
> -                  u32 max_stack, bool crosstask, bool add_mark)
> +                  u32 max_stack, bool add_mark)
>  {
>         struct perf_callchain_entry *entry;
>         struct perf_callchain_entry_ctx ctx;
> @@ -209,9 +209,6 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
>                 }
>
>                 if (regs) {
> -                       if (crosstask)
> -                               goto exit_put;
> -
>                         if (add_mark)
>                                 perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
>
> @@ -219,7 +216,6 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
>                 }
>         }
>
> -exit_put:
>         put_callchain_entry(rctx);
>
>         return entry;
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index b0d62df7df4e..5e41a3b70bcd 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -7592,16 +7592,16 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
>  {
>         bool kernel = !event->attr.exclude_callchain_kernel;
>         bool user   = !event->attr.exclude_callchain_user;
> -       /* Disallow cross-task user callchains. */
> -       bool crosstask = event->ctx->task && event->ctx->task != current;
>         const u32 max_stack = event->attr.sample_max_stack;
>         struct perf_callchain_entry *callchain;
>
> +       /* Disallow cross-task user callchains. */
> +       user &= !event->ctx->task || event->ctx->task == current;
> +
>         if (!kernel && !user)
>                 return &__empty_callchain;
>
> -       callchain = get_perf_callchain(regs, kernel, user,
> -                                      max_stack, crosstask, true);
> +       callchain = get_perf_callchain(regs, kernel, user, max_stack, true);
>         return callchain ?: &__empty_callchain;
>  }
>
> --
> 2.41.0
>