Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190812221154.46875-1-yabinc@google.com>
In-Reply-To: <20190812221154.46875-1-yabinc@google.com>
From:   Mathieu Poirier <mathieu.poirier@linaro.org>
Date:   Wed, 14 Aug 2019 14:38:18 -0600
Message-ID: <CANLsYkzxLi36JNsOCaEE-Dsm3f4k6RXkkKrdkdeJDivdeu6axQ@mail.gmail.com>
Subject: Re: [PATCH v2] coresight: tmc-etr: Fix updating buffer in
 not-snapshot mode.
To:     Yabin Cui <yabinc@google.com>
Cc:     Suzuki K Poulose <suzuki.poulose@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, 12 Aug 2019 at 16:11, Yabin Cui <yabinc@google.com> wrote:
>
> TMC etr always copies all available data to perf aux buffer, which
> may exceed the available space in perf aux buffer. It isn't suitable
> for not-snapshot mode, because:
> 1) It may overwrite previously written data.
> 2) It may make the perf_event_mmap_page->aux_head report having more
> or less data than the reality.
>
> So change to only copy the latest data fitting the available space in
> perf aux buffer.
>
> Signed-off-by: Yabin Cui <yabinc@google.com>
> ---
>
> v1 -> v2: copy the latest data instead of the earliest data.
>
> ---
>  .../hwtracing/coresight/coresight-tmc-etr.c    | 18 +++++++++++-------
>  1 file changed, 11 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
> index 17006705287a..676dcb4cf0e2 100644
> --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
> +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
> @@ -1410,9 +1410,10 @@ static void tmc_free_etr_buffer(void *config)
>   * tmc_etr_sync_perf_buffer: Copy the actual trace data from the hardware
>   * buffer to the perf ring buffer.
>   */
> -static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf)
> +static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf,
> +                                    unsigned long to_copy)
>  {
> -       long bytes, to_copy;
> +       long bytes;
>         long pg_idx, pg_offset, src_offset;
>         unsigned long head = etr_perf->head;
>         char **dst_pages, *src_buf;
> @@ -1422,8 +1423,7 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf)
>         pg_idx = head >> PAGE_SHIFT;
>         pg_offset = head & (PAGE_SIZE - 1);
>         dst_pages = (char **)etr_perf->pages;
> -       src_offset = etr_buf->offset;
> -       to_copy = etr_buf->len;
> +       src_offset = etr_buf->offset + etr_buf->len - to_copy;
>
>         while (to_copy > 0) {
>                 /*
> @@ -1434,6 +1434,8 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf)
>                  *  3) what is available in the destination page.
>                  * in one iteration.
>                  */
> +               if (src_offset >= etr_buf->size)
> +                       src_offset -= etr_buf->size;
>                 bytes = tmc_etr_buf_get_data(etr_buf, src_offset, to_copy,
>                                              &src_buf);
>                 if (WARN_ON_ONCE(bytes <= 0))
> @@ -1454,8 +1456,6 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf)
>
>                 /* Move source pointers */
>                 src_offset += bytes;
> -               if (src_offset >= etr_buf->size)
> -                       src_offset -= etr_buf->size;
>         }
>  }

Yes, much better now.  I have applied your work.

Thanks,
Mathieu

>
> @@ -1501,7 +1501,11 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
>         spin_unlock_irqrestore(&drvdata->spinlock, flags);
>
>         size = etr_buf->len;
> -       tmc_etr_sync_perf_buffer(etr_perf);
> +       if (!etr_perf->snapshot && size > handle->size) {
> +               size = handle->size;
> +               lost = true;
> +       }
> +       tmc_etr_sync_perf_buffer(etr_perf, size);
>
>         /*
>          * In snapshot mode we simply increment the head by the number of byte
> --
> 2.23.0.rc1.153.gdeed80330f-goog
>