Re: [RFC PATCH V7 10/10] drm/xe/cri: Add sysfs interface for bad gpu vram pages

[Matthew Auld <matthew.auld@intel.com>]

On 04/05/2026 10:02, Upadhyay, Tejas wrote:
> 
> 
>> -----Original Message-----
>> From: Auld, Matthew <matthew.auld@intel.com>
>> Sent: 30 April 2026 19:23
>> To: Upadhyay, Tejas <tejas.upadhyay@intel.com>; intel-
>> xe@lists.freedesktop.org
>> Cc: Brost, Matthew <matthew.brost@intel.com>;
>> thomas.hellstrom@linux.intel.com; Ghimiray, Himal Prasad
>> <himal.prasad.ghimiray@intel.com>
>> Subject: Re: [RFC PATCH V7 10/10] drm/xe/cri: Add sysfs interface for bad gpu
>> vram pages
>>
>> On 16/04/2026 08:49, Tejas Upadhyay wrote:
>>> Starting CRI, Include a sysfs interface designed to expose information
>>> about bad VRAM pages—those identified as having hardware faults (e.g.,
>>> ECC errors). This interface allows userspace tools and administrators
>>> to monitor the health of the GPU's local memory and track the status
>>> of page retirement.To get details on bad gpu vram pages can be found
>>> under /sys/bus/pci/devices/bdf/vram_bad_pages.
>>>
>>> Where The format is, pfn : gpu page size : flags
>>
>> With "gpu page size" this is really just the min block size?
>> gpu-page-size is normally interpreted as GTT page size, which is a different
>> thing. But is that not always 4K here? Since that is the granularity of the addr
>> reservation? Is it useful to print that? Is knowing that pfn x is offlined not
>> enough?
> 
> I think you are right, its always 4K. But I will check with Aravind as for what reason design doc is saying format to be  "pfn : gpu page size : flags". Adding him in cc.
> 
>>
>> Also what is the story if you have multiple VRAM instances here? There is only
>> one vram_bad_pages file? Would this treat VRAM as one giant unified thing?
> 
> This is targeted for CRI, thus single VRAM is in reference right now. We can extend in future if need be or may be it will single huge thing only in future for multiple vram.

Since this is uapi, I think would be good to be forward looking and make 
sure we don't need to complety re-design if now asked to support 
multiple VRAM instances. I think one flat unfied thing listing all the 
pfns, should work, but I guess depends on the consumer of this and how 
they are going to use this.

> 
> Tejas
>>
>>>
>>> flags:
>>> R: reserved, this gpu page is reserved.
>>> P: pending for reserve, this gpu page is marked as bad, will be reserved
>>>      in next window of page_reserve.
>>> F: unable to reserve. this gpu page can’t be reserved due to some reasons.
>>>
>>> For example if you read using cat
>>> /sys/bus/pci/devices/bdf/vram_bad_pages,
>>> max_pages : 10000
>>> 0x00000000 : 0x00001000 : R
>>> 0x00001234 : 0x00001000 : P
>>>
>>> v3:
>>> - Move FW communication in RAS code
>>> v2:
>>> - Add max_pages info as per updated design doc
>>> - Rebase
>>>
>>> Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
>>> ---
>>>    drivers/gpu/drm/xe/xe_device_sysfs.c       |  7 ++
>>>    drivers/gpu/drm/xe/xe_ttm_vram_mgr.c       | 79
>> ++++++++++++++++++++++
>>>    drivers/gpu/drm/xe/xe_ttm_vram_mgr.h       |  1 +
>>>    drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h |  2 +
>>>    4 files changed, 89 insertions(+)
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c
>>> b/drivers/gpu/drm/xe/xe_device_sysfs.c
>>> index a73e0e957cb0..47c5be4180fe 100644
>>> --- a/drivers/gpu/drm/xe/xe_device_sysfs.c
>>> +++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
>>> @@ -8,12 +8,14 @@
>>>    #include <linux/pci.h>
>>>    #include <linux/sysfs.h>
>>>
>>> +#include "xe_configfs.h"
>>>    #include "xe_device.h"
>>>    #include "xe_device_sysfs.h"
>>>    #include "xe_mmio.h"
>>>    #include "xe_pcode_api.h"
>>>    #include "xe_pcode.h"
>>>    #include "xe_pm.h"
>>> +#include "xe_ttm_vram_mgr.h"
>>>
>>>    /**
>>>     * DOC: Xe device sysfs
>>> @@ -267,6 +269,7 @@ static const struct attribute_group
>> auto_link_downgrade_attr_group = {
>>>    int xe_device_sysfs_init(struct xe_device *xe)
>>>    {
>>>    	struct device *dev = xe->drm.dev;
>>> +	bool policy;
>>>    	int ret;
>>>
>>>    	if (xe->d3cold.capable) {
>>> @@ -285,5 +288,9 @@ int xe_device_sysfs_init(struct xe_device *xe)
>>>    			return ret;
>>>    	}
>>>
>>> +	policy = xe_configfs_get_bad_page_reservation(to_pci_dev(dev));
>>> +	if (xe->info.platform == XE_CRESCENTISLAND && policy)
>>> +		xe_ttm_vram_sysfs_init(xe);
>>> +
>>>    	return 0;
>>>    }
>>> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>>> b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>>> index 7f58e7e8c3e1..611d945c9eb4 100644
>>> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>>> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
>>> @@ -760,3 +760,82 @@ int xe_ttm_vram_handle_addr_fault(struct
>> xe_device *xe, unsigned long addr)
>>>    	return ret;
>>>    }
>>>    EXPORT_SYMBOL(xe_ttm_vram_handle_addr_fault);
>>> +
>>> +static void xe_ttm_vram_dump_bad_pages_info(char *buf, struct
>>> +xe_ttm_vram_mgr *mgr) {
>>> +	const unsigned int element_size = sizeof("0xabcdabcd : 0x12345678 :
>> R\n") - 1;
>>> +	const unsigned int maxpage_size = sizeof("max_pages: 10000\n") - 1;
>>> +	struct xe_ttm_vram_offline_resource *pos, *n;
>>> +	struct gpu_buddy_block *block;
>>> +	ssize_t s = 0;
>>> +
>>> +	mutex_lock(&mgr->lock);
>>> +	s += scnprintf(&buf[s], maxpage_size + 1, "max_pages: %d\n", mgr-
>>> max_pages);
>>> +	list_for_each_entry_safe(pos, n, &mgr->offlined_pages, offlined_link)
>> {
>>> +		block = list_first_entry(&pos->blocks,
>>> +					 struct gpu_buddy_block,
>>> +					 link);
>>> +		s += scnprintf(&buf[s], element_size + 1,
>>> +			       "0x%08llx : 0x%08llx : %1s\n",
>>> +			       gpu_buddy_block_offset(block) >> PAGE_SHIFT,
>>> +			       gpu_buddy_block_size(&mgr->mm, block),
>>> +			       "R");
>>> +	}
>>> +	list_for_each_entry_safe(pos, n, &mgr->queued_pages, queued_link)
>> {
>>> +		block = list_first_entry(&pos->blocks,
>>> +					 struct gpu_buddy_block,
>>> +					 link);
>>> +		s += scnprintf(&buf[s], element_size + 1,
>>> +			       "0x%08llx : 0x%08llx : %1s\n",
>>> +			       gpu_buddy_block_offset(block) >> PAGE_SHIFT,
>>> +			       gpu_buddy_block_size(&mgr->mm, block),
>>> +			       pos->status ? "P" : "F");
>>> +	}
>>> +	mutex_unlock(&mgr->lock);
>>> +}
>>> +
>>> +static ssize_t vram_bad_pages_show(struct device *dev, struct
>>> +device_attribute *attr, char *buf) {
>>> +	struct pci_dev *pdev = to_pci_dev(dev);
>>> +	struct xe_device *xe = pdev_to_xe_device(pdev);
>>> +	struct ttm_resource_manager *man;
>>> +	struct xe_ttm_vram_mgr *mgr;
>>> +
>>> +	man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0);
>>> +	if (man) {
>>> +		mgr = to_xe_ttm_vram_mgr(man);
>>> +		xe_ttm_vram_dump_bad_pages_info(buf, mgr);
>>> +	}
>>> +
>>> +	return sysfs_emit(buf, "%s\n", buf); } static
>>> +DEVICE_ATTR_RO(vram_bad_pages);
>>> +
>>> +static void xe_ttm_vram_sysfs_fini(void *arg) {
>>> +	struct xe_device *xe = arg;
>>> +
>>> +	device_remove_file(xe->drm.dev, &dev_attr_vram_bad_pages); }
>>> +
>>> +/**
>>> + * xe_ttm_vram_sysfs_init - Initialize vram sysfs component
>>> + * @tile: Xe Tile object
>>> + *
>>> + * It needs to be initialized after the main tile component is ready
>>> + *
>>> + * Returns: 0 on success, negative error code on error.
>>> + */
>>> +int xe_ttm_vram_sysfs_init(struct xe_device *xe) {
>>> +	int err;
>>> +
>>> +	err = device_create_file(xe->drm.dev, &dev_attr_vram_bad_pages);
>>> +	if (err) {
>>> +		dev_err(xe->drm.dev, "Failed to create vram_bad_pages sysfs
>> file: %d\n", err);
>>> +		return 0;
>>> +	}
>>> +
>>> +	return devm_add_action_or_reset(xe->drm.dev,
>> xe_ttm_vram_sysfs_fini,
>>> +xe); } EXPORT_SYMBOL(xe_ttm_vram_sysfs_init);
>>> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>>> b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>>> index 8ef06d9d44f7..c33e1a8d9217 100644
>>> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>>> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
>>> @@ -32,6 +32,7 @@ void xe_ttm_vram_get_used(struct
>> ttm_resource_manager *man,
>>>    			  u64 *used, u64 *used_visible);
>>>
>>>    int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, unsigned
>>> long addr);
>>> +int xe_ttm_vram_sysfs_init(struct xe_device *xe);
>>>    static inline struct xe_ttm_vram_mgr_resource *
>>>    to_xe_ttm_vram_mgr_resource(struct ttm_resource *res)
>>>    {
>>> diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>>> b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>>> index 07ed88b47e04..b23796066a1a 100644
>>> --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>>> +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
>>> @@ -39,6 +39,8 @@ struct xe_ttm_vram_mgr {
>>>    	u32 mem_type;
>>>    	/** @offline_mode: debugfs hook for setting page offline mode */
>>>    	u64 offline_mode;
>>> +	/** @max_pages: max pages that can be in offline queue retrieved
>> from FW */
>>> +	u16 max_pages;
>>>    };
>>>
>>>    /**
>