From: Shashank Sharma <shashank.sharma@amd.com>
To: "André Almeida" <andrealmeid@igalia.com>,
dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org,
linux-kernel@vger.kernel.org
Cc: kernel-dev@igalia.com, alexander.deucher@amd.com,
christian.koenig@amd.com, pierre-eric.pelloux-prayer@amd.com,
"'Marek Olšák'" <maraeo@gmail.com>,
"Samuel Pitoiset" <samuel.pitoiset@gmail.com>,
"Bas Nieuwenhuizen" <bas@basnieuwenhuizen.nl>,
"Timur Kristóf" <timur.kristof@gmail.com>
Subject: Re: [PATCH v5 4/5] drm/amdgpu: Move coredump code to amdgpu_reset file
Date: Mon, 21 Aug 2023 16:22:55 +0200 [thread overview]
Message-ID: <7e785b0a-aa1e-b733-2521-694941b7593f@amd.com> (raw)
In-Reply-To: <20230817182050.205925-5-andrealmeid@igalia.com>
On 17/08/2023 20:20, André Almeida wrote:
> Giving that we use codedump just for device resets, move it's functions
> and structs to a more semantic file, the amdgpu_reset.{c, h}.
>
> Signed-off-by: André Almeida <andrealmeid@igalia.com>
> ---
> v5: no change
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 9 ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 78 ----------------------
> drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 76 +++++++++++++++++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h | 10 +++
> 4 files changed, 86 insertions(+), 87 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 56d78ca6e917..b11187d153ef 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -781,15 +781,6 @@ struct amdgpu_mqd {
> #define AMDGPU_PRODUCT_NAME_LEN 64
> struct amdgpu_reset_domain;
>
> -#ifdef CONFIG_DEV_COREDUMP
> -struct amdgpu_coredump_info {
> - struct amdgpu_device *adev;
> - struct amdgpu_task_info reset_task_info;
> - struct timespec64 reset_time;
> - bool reset_vram_lost;
> -};
> -#endif
> -
> struct amdgpu_reset_info {
> /* reset dump register */
> u32 *reset_dump_reg_list;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 96975591841d..883953f2ae53 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -32,8 +32,6 @@
> #include <linux/slab.h>
> #include <linux/iommu.h>
> #include <linux/pci.h>
> -#include <linux/devcoredump.h>
> -#include <generated/utsrelease.h>
> #include <linux/pci-p2pdma.h>
> #include <linux/apple-gmux.h>
>
> @@ -4799,82 +4797,6 @@ static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
> return 0;
> }
>
> -#ifndef CONFIG_DEV_COREDUMP
> -static void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
> - struct amdgpu_reset_context *reset_context)
> -{
> -}
> -#else
> -static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
> - size_t count, void *data, size_t datalen)
> -{
> - struct drm_printer p;
> - struct amdgpu_coredump_info *coredump = data;
> - struct drm_print_iterator iter;
> - int i;
> -
> - iter.data = buffer;
> - iter.offset = 0;
> - iter.start = offset;
> - iter.remain = count;
> -
> - p = drm_coredump_printer(&iter);
> -
> - drm_printf(&p, "**** AMDGPU Device Coredump ****\n");
> - drm_printf(&p, "kernel: " UTS_RELEASE "\n");
> - drm_printf(&p, "module: " KBUILD_MODNAME "\n");
> - drm_printf(&p, "time: %lld.%09ld\n", coredump->reset_time.tv_sec, coredump->reset_time.tv_nsec);
> - if (coredump->reset_task_info.pid)
> - drm_printf(&p, "process_name: %s PID: %d\n",
> - coredump->reset_task_info.process_name,
> - coredump->reset_task_info.pid);
> -
> - if (coredump->reset_vram_lost)
> - drm_printf(&p, "VRAM is lost due to GPU reset!\n");
> - if (coredump->adev->reset_info.num_regs) {
> - drm_printf(&p, "AMDGPU register dumps:\nOffset: Value:\n");
> -
> - for (i = 0; i < coredump->adev->reset_info.num_regs; i++)
> - drm_printf(&p, "0x%08x: 0x%08x\n",
> - coredump->adev->reset_info.reset_dump_reg_list[i],
> - coredump->adev->reset_info.reset_dump_reg_value[i]);
> - }
> -
> - return count - iter.remain;
> -}
> -
> -static void amdgpu_devcoredump_free(void *data)
> -{
> - kfree(data);
> -}
> -
> -static void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
> - struct amdgpu_reset_context *reset_context)
> -{
> - struct amdgpu_coredump_info *coredump;
> - struct drm_device *dev = adev_to_drm(adev);
> -
> - coredump = kzalloc(sizeof(*coredump), GFP_NOWAIT);
> -
> - if (!coredump) {
> - DRM_ERROR("%s: failed to allocate memory for coredump\n", __func__);
> - return;
> - }
> -
> - coredump->reset_vram_lost = vram_lost;
> -
> - if (reset_context->job && reset_context->job->vm)
> - coredump->reset_task_info = reset_context->job->vm->task_info;
> -
> - coredump->adev = adev;
> -
> - ktime_get_ts64(&coredump->reset_time);
> -
> - dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT,
> - amdgpu_devcoredump_read, amdgpu_devcoredump_free);
> -}
> -#endif
> -
> int amdgpu_do_asic_reset(struct list_head *device_list_handle,
> struct amdgpu_reset_context *reset_context)
> {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> index 5fed06ffcc6b..579b70a3cdab 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> @@ -21,6 +21,9 @@
> *
> */
>
> +#include <linux/devcoredump.h>
> +#include <generated/utsrelease.h>
> +
> #include "amdgpu_reset.h"
> #include "aldebaran.h"
> #include "sienna_cichlid.h"
> @@ -167,5 +170,78 @@ void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain)
> up_write(&reset_domain->sem);
> }
>
> +#ifndef CONFIG_DEV_COREDUMP
> +void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
> + struct amdgpu_reset_context *reset_context)
> +{
> +}
> +#else
> +static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
> + size_t count, void *data, size_t datalen)
> +{
> + struct drm_printer p;
> + struct amdgpu_coredump_info *coredump = data;
> + struct drm_print_iterator iter;
> + int i;
> +
> + iter.data = buffer;
> + iter.offset = 0;
> + iter.start = offset;
> + iter.remain = count;
> +
> + p = drm_coredump_printer(&iter);
> +
> + drm_printf(&p, "**** AMDGPU Device Coredump ****\n");
> + drm_printf(&p, "kernel: " UTS_RELEASE "\n");
> + drm_printf(&p, "module: " KBUILD_MODNAME "\n");
> + drm_printf(&p, "time: %lld.%09ld\n", coredump->reset_time.tv_sec, coredump->reset_time.tv_nsec);
> + if (coredump->reset_task_info.pid)
> + drm_printf(&p, "process_name: %s PID: %d\n",
> + coredump->reset_task_info.process_name,
> + coredump->reset_task_info.pid);
> +
> + if (coredump->reset_vram_lost)
> + drm_printf(&p, "VRAM is lost due to GPU reset!\n");
> + if (coredump->adev->reset_info.num_regs) {
> + drm_printf(&p, "AMDGPU register dumps:\nOffset: Value:\n");
> +
> + for (i = 0; i < coredump->adev->reset_info.num_regs; i++)
> + drm_printf(&p, "0x%08x: 0x%08x\n",
> + coredump->adev->reset_info.reset_dump_reg_list[i],
> + coredump->adev->reset_info.reset_dump_reg_value[i]);
> + }
> +
> + return count - iter.remain;
> +}
>
> +static void amdgpu_devcoredump_free(void *data)
> +{
> + kfree(data);
> +}
>
> +void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
> + struct amdgpu_reset_context *reset_context)
> +{
> + struct amdgpu_coredump_info *coredump;
> + struct drm_device *dev = adev_to_drm(adev);
> +
> + coredump = kzalloc(sizeof(*coredump), GFP_NOWAIT);
> +
> + if (!coredump) {
> + DRM_ERROR("%s: failed to allocate memory for coredump\n", __func__);
> + return;
> + }
> +
> + coredump->reset_vram_lost = vram_lost;
> +
> + if (reset_context->job && reset_context->job->vm)
> + coredump->reset_task_info = reset_context->job->vm->task_info;
> +
> + coredump->adev = adev;
> +
> + ktime_get_ts64(&coredump->reset_time);
> +
> + dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT,
> + amdgpu_devcoredump_read, amdgpu_devcoredump_free);
> +}
> +#endif
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> index f4a501ff87d9..01e8183ade4b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
> @@ -87,6 +87,14 @@ struct amdgpu_reset_domain {
> atomic_t reset_res;
> };
>
> +#ifdef CONFIG_DEV_COREDUMP
> +struct amdgpu_coredump_info {
> + struct amdgpu_device *adev;
> + struct amdgpu_task_info reset_task_info;
> + struct timespec64 reset_time;
> + bool reset_vram_lost;
> +};
> +#endif
>
> int amdgpu_reset_init(struct amdgpu_device *adev);
> int amdgpu_reset_fini(struct amdgpu_device *adev);
> @@ -126,4 +134,6 @@ void amdgpu_device_lock_reset_domain(struct amdgpu_reset_domain *reset_domain);
>
> void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain);
>
> +void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
> + struct amdgpu_reset_context *reset_context);
> #endif
Reviewed-by: Shashank Sharma <shashank.sharma@amd.com>
- Shashank
next prev parent reply other threads:[~2023-08-21 14:23 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-17 18:20 [PATCH v5 0/5] drm/amdgpu: Rework coredump memory allocation André Almeida
2023-08-17 18:20 ` [PATCH v5 1/5] drm/amdgpu: Allocate coredump memory in a nonblocking way André Almeida
2023-08-17 18:20 ` [PATCH v5 2/5] drm/amdgpu: Rework coredump to use memory dynamically André Almeida
2023-08-21 14:20 ` Shashank Sharma
2023-08-17 18:20 ` [PATCH v5 3/5] drm/amdgpu: Encapsulate all device reset info André Almeida
2023-08-21 14:21 ` Shashank Sharma
2023-08-17 18:20 ` [PATCH v5 4/5] drm/amdgpu: Move coredump code to amdgpu_reset file André Almeida
2023-08-21 14:22 ` Shashank Sharma [this message]
2023-08-17 18:20 ` [PATCH v5 5/5] drm/amdgpu: Create version number for coredumps André Almeida
2023-08-21 14:24 ` Shashank Sharma
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=7e785b0a-aa1e-b733-2521-694941b7593f@amd.com \
--to=shashank.sharma@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=andrealmeid@igalia.com \
--cc=bas@basnieuwenhuizen.nl \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=kernel-dev@igalia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=maraeo@gmail.com \
--cc=pierre-eric.pelloux-prayer@amd.com \
--cc=samuel.pitoiset@gmail.com \
--cc=timur.kristof@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®