All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dmitry Vyukov <dvyukov@google.com>
To: Marco Elver <elver@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Frederic Weisbecker <frederic@kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	linux-perf-users@vger.kernel.org, x86@kernel.org,
	linux-sh@vger.kernel.org, kasan-dev@googlegroups.com,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/8] perf/hw_breakpoint: Optimize constant number of breakpoint slots
Date: Thu, 9 Jun 2022 13:55:57 +0200	[thread overview]
Message-ID: <CACT4Y+YhFT3wwtbjdjmBs5wKYjF3DOmH=AoP0Qq5bb6DAGHZxA@mail.gmail.com> (raw)
In-Reply-To: <20220609113046.780504-4-elver@google.com>

On Thu, 9 Jun 2022 at 13:31, Marco Elver <elver@google.com> wrote:
>
> Optimize internal hw_breakpoint state if the architecture's number of
> breakpoint slots is constant. This avoids several kmalloc() calls and
> potentially unnecessary failures if the allocations fail, as well as
> subtly improves code generation and cache locality.
>
> The protocol is that if an architecture defines hw_breakpoint_slots via
> the preprocessor, it must be constant and the same for all types.
>
> Signed-off-by: Marco Elver <elver@google.com>

Acked-by: Dmitry Vyukov <dvyukov@google.com>

> ---
>  arch/sh/include/asm/hw_breakpoint.h  |  5 +-
>  arch/x86/include/asm/hw_breakpoint.h |  5 +-
>  kernel/events/hw_breakpoint.c        | 92 ++++++++++++++++++----------
>  3 files changed, 62 insertions(+), 40 deletions(-)
>
> diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
> index 199d17b765f2..361a0f57bdeb 100644
> --- a/arch/sh/include/asm/hw_breakpoint.h
> +++ b/arch/sh/include/asm/hw_breakpoint.h
> @@ -48,10 +48,7 @@ struct pmu;
>  /* Maximum number of UBC channels */
>  #define HBP_NUM                2
>
> -static inline int hw_breakpoint_slots(int type)
> -{
> -       return HBP_NUM;
> -}
> +#define hw_breakpoint_slots(type) (HBP_NUM)
>
>  /* arch/sh/kernel/hw_breakpoint.c */
>  extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
> diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
> index a1f0e90d0818..0bc931cd0698 100644
> --- a/arch/x86/include/asm/hw_breakpoint.h
> +++ b/arch/x86/include/asm/hw_breakpoint.h
> @@ -44,10 +44,7 @@ struct arch_hw_breakpoint {
>  /* Total number of available HW breakpoint registers */
>  #define HBP_NUM 4
>
> -static inline int hw_breakpoint_slots(int type)
> -{
> -       return HBP_NUM;
> -}
> +#define hw_breakpoint_slots(type) (HBP_NUM)
>
>  struct perf_event_attr;
>  struct perf_event;
> diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
> index 1f718745d569..8e939723f27d 100644
> --- a/kernel/events/hw_breakpoint.c
> +++ b/kernel/events/hw_breakpoint.c
> @@ -41,13 +41,16 @@ struct bp_cpuinfo {
>         /* Number of pinned cpu breakpoints in a cpu */
>         unsigned int    cpu_pinned;
>         /* tsk_pinned[n] is the number of tasks having n+1 breakpoints */
> +#ifdef hw_breakpoint_slots
> +       unsigned int    tsk_pinned[hw_breakpoint_slots(0)];
> +#else
>         unsigned int    *tsk_pinned;
> +#endif
>         /* Number of non-pinned cpu/task breakpoints in a cpu */
>         unsigned int    flexible; /* XXX: placeholder, see fetch_this_slot() */
>  };
>
>  static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
> -static int nr_slots[TYPE_MAX] __ro_after_init;
>
>  static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
>  {
> @@ -74,6 +77,54 @@ struct bp_busy_slots {
>  /* Serialize accesses to the above constraints */
>  static DEFINE_MUTEX(nr_bp_mutex);
>
> +#ifdef hw_breakpoint_slots
> +/*
> + * Number of breakpoint slots is constant, and the same for all types.
> + */
> +static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA));
> +static inline int hw_breakpoint_slots_cached(int type) { return hw_breakpoint_slots(type); }
> +static inline int init_breakpoint_slots(void)          { return 0; }
> +#else
> +/*
> + * Dynamic number of breakpoint slots.
> + */
> +static int __nr_bp_slots[TYPE_MAX] __ro_after_init;
> +
> +static inline int hw_breakpoint_slots_cached(int type)
> +{
> +       return __nr_bp_slots[type];
> +}
> +
> +static __init int init_breakpoint_slots(void)
> +{
> +       int i, cpu, err_cpu;
> +
> +       for (i = 0; i < TYPE_MAX; i++)
> +               __nr_bp_slots[i] = hw_breakpoint_slots(i);
> +
> +       for_each_possible_cpu(cpu) {
> +               for (i = 0; i < TYPE_MAX; i++) {
> +                       struct bp_cpuinfo *info = get_bp_info(cpu, i);
> +
> +                       info->tsk_pinned = kcalloc(__nr_bp_slots[i], sizeof(int), GFP_KERNEL);
> +                       if (!info->tsk_pinned)
> +                               goto err;
> +               }
> +       }
> +
> +       return 0;
> +err:
> +       for_each_possible_cpu(err_cpu) {
> +               for (i = 0; i < TYPE_MAX; i++)
> +                       kfree(get_bp_info(err_cpu, i)->tsk_pinned);
> +               if (err_cpu == cpu)
> +                       break;
> +       }
> +
> +       return -ENOMEM;
> +}
> +#endif
> +
>  __weak int hw_breakpoint_weight(struct perf_event *bp)
>  {
>         return 1;
> @@ -96,7 +147,7 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
>         unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
>         int i;
>
> -       for (i = nr_slots[type] - 1; i >= 0; i--) {
> +       for (i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
>                 if (tsk_pinned[i] > 0)
>                         return i + 1;
>         }
> @@ -313,7 +364,7 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
>         fetch_this_slot(&slots, weight);
>
>         /* Flexible counters need to keep at least one slot */
> -       if (slots.pinned + (!!slots.flexible) > nr_slots[type])
> +       if (slots.pinned + (!!slots.flexible) > hw_breakpoint_slots_cached(type))
>                 return -ENOSPC;
>
>         ret = arch_reserve_bp_slot(bp);
> @@ -688,42 +739,19 @@ static struct pmu perf_breakpoint = {
>
>  int __init init_hw_breakpoint(void)
>  {
> -       int cpu, err_cpu;
> -       int i, ret;
> -
> -       for (i = 0; i < TYPE_MAX; i++)
> -               nr_slots[i] = hw_breakpoint_slots(i);
> -
> -       for_each_possible_cpu(cpu) {
> -               for (i = 0; i < TYPE_MAX; i++) {
> -                       struct bp_cpuinfo *info = get_bp_info(cpu, i);
> -
> -                       info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
> -                                                       GFP_KERNEL);
> -                       if (!info->tsk_pinned) {
> -                               ret = -ENOMEM;
> -                               goto err;
> -                       }
> -               }
> -       }
> +       int ret;
>
>         ret = rhltable_init(&task_bps_ht, &task_bps_ht_params);
>         if (ret)
> -               goto err;
> +               return ret;
> +
> +       ret = init_breakpoint_slots();
> +       if (ret)
> +               return ret;
>
>         constraints_initialized = true;
>
>         perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
>
>         return register_die_notifier(&hw_breakpoint_exceptions_nb);
> -
> -err:
> -       for_each_possible_cpu(err_cpu) {
> -               for (i = 0; i < TYPE_MAX; i++)
> -                       kfree(get_bp_info(err_cpu, i)->tsk_pinned);
> -               if (err_cpu == cpu)
> -                       break;
> -       }
> -
> -       return ret;
>  }
> --
> 2.36.1.255.ge46751e96f-goog
>

  reply	other threads:[~2022-06-09 11:56 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-09 11:30 [PATCH 0/8] perf/hw_breakpoint: Optimize for thousands of tasks Marco Elver
2022-06-09 11:30 ` [PATCH 1/8] perf/hw_breakpoint: Optimize list of per-task breakpoints Marco Elver
2022-06-09 12:30   ` Dmitry Vyukov
2022-06-09 12:53     ` Marco Elver
2022-06-09 13:05       ` Dmitry Vyukov
2022-06-09 14:29   ` Dmitry Vyukov
2022-06-09 14:55     ` Marco Elver
2022-06-09 16:53       ` Dmitry Vyukov
2022-06-09 18:37         ` Marco Elver
2022-06-10  9:04           ` Dmitry Vyukov
2022-06-10  9:36             ` Marco Elver
2022-06-09 11:30 ` [PATCH 2/8] perf/hw_breakpoint: Mark data __ro_after_init Marco Elver
2022-06-09 11:45   ` Dmitry Vyukov
2022-06-09 11:30 ` [PATCH 3/8] perf/hw_breakpoint: Optimize constant number of breakpoint slots Marco Elver
2022-06-09 11:55   ` Dmitry Vyukov [this message]
2022-06-09 11:30 ` [PATCH 4/8] perf/hw_breakpoint: Make hw_breakpoint_weight() inlinable Marco Elver
2022-06-09 12:03   ` Dmitry Vyukov
2022-06-09 12:08     ` Marco Elver
2022-06-09 12:23       ` Dmitry Vyukov
2022-06-09 13:25     ` Peter Zijlstra
2022-06-09 11:30 ` [PATCH 5/8] perf/hw_breakpoint: Remove useless code related to flexible breakpoints Marco Elver
2022-06-09 12:04   ` Dmitry Vyukov
2022-06-09 13:41     ` Dmitry Vyukov
2022-06-09 14:00       ` Marco Elver
2022-06-09 11:30 ` [PATCH 6/8] perf/hw_breakpoint: Reduce contention with large number of tasks Marco Elver
2022-06-09 13:03   ` Dmitry Vyukov
2022-06-09 13:29     ` Marco Elver
2022-06-09 11:30 ` [PATCH 7/8] perf/hw_breakpoint: Optimize task_bp_pinned() if CPU-independent Marco Elver
2022-06-09 15:00   ` Dmitry Vyukov
2022-06-10  8:25     ` Marco Elver
2022-06-10  9:13       ` Dmitry Vyukov
2022-06-09 11:30 ` [PATCH 8/8] perf/hw_breakpoint: Clean up headers Marco Elver
2022-06-09 12:11   ` Dmitry Vyukov
2022-06-09 12:28 ` [PATCH 0/8] perf/hw_breakpoint: Optimize for thousands of tasks Dmitry Vyukov

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='CACT4Y+YhFT3wwtbjdjmBs5wKYjF3DOmH=AoP0Qq5bb6DAGHZxA@mail.gmail.com' \
    --to=dvyukov@google.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=elver@google.com \
    --cc=frederic@kernel.org \
    --cc=jolsa@redhat.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux-sh@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.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.