[PATCH] drm/amdgpu: Add autodump debugfs node for gpu reset v4

Zhao, Jiange Jiange.Zhao at amd.com
Thu May 14 07:14:48 UTC 2020


[AMD Official Use Only - Internal Distribution Only]

Hi Christian,

wait_for_completion_interruptible_timeout() would decrease autodump.dumping.done to UINT_MAX-1.

complete_all() here would restore autodump.dumping to the state as in amdgpu_debugfs_autodump_init().

I want to make sure every open() deals with the same situation.

Jiange
________________________________
From: Christian K?nig <ckoenig.leichtzumerken at gmail.com>
Sent: Thursday, May 14, 2020 3:01 PM
To: Zhao, Jiange <Jiange.Zhao at amd.com>; amd-gfx at lists.freedesktop.org <amd-gfx at lists.freedesktop.org>
Cc: Pelloux-prayer, Pierre-eric <Pierre-eric.Pelloux-prayer at amd.com>; Zhao, Jiange <Jiange.Zhao at amd.com>; Kuehling, Felix <Felix.Kuehling at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>; Koenig, Christian <Christian.Koenig at amd.com>; Liu, Monk <Monk.Liu at amd.com>; Zhang, Hawking <Hawking.Zhang at amd.com>
Subject: Re: [PATCH] drm/amdgpu: Add autodump debugfs node for gpu reset v4

Am 14.05.20 um 07:29 schrieb jianzh at amd.com:
> From: Jiange Zhao <Jiange.Zhao at amd.com>
>
> When GPU got timeout, it would notify an interested part
> of an opportunity to dump info before actual GPU reset.
>
> A usermode app would open 'autodump' node under debugfs system
> and poll() for readable/writable. When a GPU reset is due,
> amdgpu would notify usermode app through wait_queue_head and give
> it 10 minutes to dump info.
>
> After usermode app has done its work, this 'autodump' node is closed.
> On node closure, amdgpu gets to know the dump is done through
> the completion that is triggered in release().
>
> There is no write or read callback because necessary info can be
> obtained through dmesg and umr. Messages back and forth between
> usermode app and amdgpu are unnecessary.
>
> v2: (1) changed 'registered' to 'app_listening'
>      (2) add a mutex in open() to prevent race condition
>
> v3 (chk): grab the reset lock to avoid race in autodump_open,
>            rename debugfs file to amdgpu_autodump,
>            provide autodump_read as well,
>            style and code cleanups
>
> v4: add 'bool app_listening' to differentiate situations, so that
>      the node can be reopened; also, there is no need to wait for
>      completion when no app is waiting for a dump.
>
> v5: change 'bool app_listening' to 'enum amdgpu_autodump_state'
>      add 'app_state_mutex' for race conditions:
>        (1)Only 1 user can open this file node
>        (2)wait_dump() can only take effect after poll() executed.
>        (3)eliminated the race condition between release() and
>           wait_dump()
>
> v6: removed 'enum amdgpu_autodump_state' and 'app_state_mutex'
>      removed state checking in amdgpu_debugfs_wait_dump
>      Improve on top of version 3 so that the node can be reopened.
>
> v7: move reinit_completion into open() so that only one user
>      can open it.
>
> Signed-off-by: Jiange Zhao <Jiange.Zhao at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h         |  2 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 79 ++++++++++++++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h |  6 ++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +
>   4 files changed, 88 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 2a806cb55b78..9e8eeddfe7ce 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -992,6 +992,8 @@ struct amdgpu_device {
>        char                            product_number[16];
>        char                            product_name[32];
>        char                            serial[16];
> +
> +     struct amdgpu_autodump          autodump;
>   };
>
>   static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> index 1a4894fa3693..efee3f1adecf 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -27,7 +27,7 @@
>   #include <linux/pci.h>
>   #include <linux/uaccess.h>
>   #include <linux/pm_runtime.h>
> -
> +#include <linux/poll.h>
>   #include <drm/drm_debugfs.h>
>
>   #include "amdgpu.h"
> @@ -74,8 +74,83 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
>        return 0;
>   }
>
> +int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)
> +{
> +#if defined(CONFIG_DEBUG_FS)
> +     unsigned long timeout = 600 * HZ;
> +     int ret;
> +
> +     wake_up_interruptible(&adev->autodump.gpu_hang);
> +
> +     ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout);
> +     complete_all(&adev->autodump.dumping);

Sorry that I'm mentioning this only now. But what is this complete_all()
here good for?

I mean we already waited for completion, didn't we?

Christian.

> +     if (ret == 0) {
> +             pr_err("autodump: timeout, move on to gpu recovery\n");
> +             return -ETIMEDOUT;
> +     }
> +#endif
> +     return 0;
> +}
> +
>   #if defined(CONFIG_DEBUG_FS)
>
> +static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
> +{
> +     struct amdgpu_device *adev = inode->i_private;
> +     int ret;
> +
> +     file->private_data = adev;
> +
> +     mutex_lock(&adev->lock_reset);
> +     if (adev->autodump.dumping.done) {
> +             reinit_completion(&adev->autodump.dumping);
> +             ret = 0;
> +     } else {
> +             ret = -EBUSY;
> +     }
> +     mutex_unlock(&adev->lock_reset);
> +
> +     return ret;
> +}
> +
> +static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)
> +{
> +     struct amdgpu_device *adev = file->private_data;
> +
> +     complete_all(&adev->autodump.dumping);
> +     return 0;
> +}
> +
> +static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table)
> +{
> +     struct amdgpu_device *adev = file->private_data;
> +
> +     poll_wait(file, &adev->autodump.gpu_hang, poll_table);
> +
> +     if (adev->in_gpu_reset)
> +             return POLLIN | POLLRDNORM | POLLWRNORM;
> +
> +     return 0;
> +}
> +
> +static const struct file_operations autodump_debug_fops = {
> +     .owner = THIS_MODULE,
> +     .open = amdgpu_debugfs_autodump_open,
> +     .poll = amdgpu_debugfs_autodump_poll,
> +     .release = amdgpu_debugfs_autodump_release,
> +};
> +
> +static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
> +{
> +     init_completion(&adev->autodump.dumping);
> +     complete_all(&adev->autodump.dumping);
> +     init_waitqueue_head(&adev->autodump.gpu_hang);
> +
> +     debugfs_create_file("amdgpu_autodump", 0600,
> +             adev->ddev->primary->debugfs_root,
> +             adev, &autodump_debug_fops);
> +}
> +
>   /**
>    * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
>    *
> @@ -1434,6 +1509,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
>
>        amdgpu_ras_debugfs_create_all(adev);
>
> +     amdgpu_debugfs_autodump_init(adev);
> +
>        return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list,
>                                        ARRAY_SIZE(amdgpu_debugfs_list));
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
> index de12d1101526..2803884d338d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
> @@ -31,6 +31,11 @@ struct amdgpu_debugfs {
>        unsigned                num_files;
>   };
>
> +struct amdgpu_autodump {
> +     struct completion               dumping;
> +     struct wait_queue_head          gpu_hang;
> +};
> +
>   int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
>   int amdgpu_debugfs_init(struct amdgpu_device *adev);
>   void amdgpu_debugfs_fini(struct amdgpu_device *adev);
> @@ -40,3 +45,4 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev,
>   int amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
>   int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
>   int amdgpu_debugfs_gem_init(struct amdgpu_device *adev);
> +int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index cc41e8f5ad14..545beebcf43e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3927,6 +3927,8 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
>        int i, r = 0;
>        bool need_full_reset  = *need_full_reset_arg;
>
> +     amdgpu_debugfs_wait_dump(adev);
> +
>        /* block all schedulers and reset given job's ring */
>        for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
>                struct amdgpu_ring *ring = adev->rings[i];

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20200514/eeddc9a2/attachment-0001.htm>


More information about the amd-gfx mailing list