[PATCH V14 7/9] drm/xe/cri: Add sysfs interface for bad gpu vram pages

[Tejas Upadhyay <tejas.upadhyay@intel.com>]

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

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

v5(Sashiko):
- Add capacity of 10000(=max_pages) entries dump
v4:
- Use sysfs_emit_at() instead of scnprintf() to respect PAGE_SIZE
- Use list_first_entry_or_null() with continue to handle empty lists
- Use %016llx for full 64-bit address width
- Fix inverted P/F ternary (status ? F : P)
- Return err instead of 0 on device_create_file failure
- Remove redundant element_size/maxpage_size constants

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       | 144 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.h       |   1 +
 drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h |   2 +
 4 files changed, 154 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 b884f876f55d..ef9b7128f28a 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -824,3 +824,147 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
 	return xe_ttm_vram_reserve_page_at_addr(xe, addr, vram_mgr, mm);
 }
 EXPORT_SYMBOL(xe_ttm_vram_handle_addr_fault);
+
+static size_t serialize_bad_pages(struct xe_ttm_vram_mgr *mgr, char *buf, size_t max_len)
+{
+	struct xe_ttm_vram_offline_resource *pos;
+	struct gpu_buddy_block *block;
+	size_t s = 0;
+	int printed;
+	int count = 0;
+
+	lockdep_assert_held(&mgr->lock);
+
+	printed = scnprintf(buf + s, max_len - s, "max_pages: %d\n", mgr->max_pages);
+	s += printed;
+
+	list_for_each_entry(pos, &mgr->offlined_pages, offlined_link) {
+		if (count >= 10000 || s >= max_len)
+			break;
+
+		block = list_first_entry_or_null(&pos->blocks, struct gpu_buddy_block, link);
+		if (!block)
+			continue;
+
+		printed = scnprintf(buf + s, max_len - s, "0x%016llx : 0x%016llx : %c\n",
+				    gpu_buddy_block_offset(block) >> PAGE_SHIFT,
+				    gpu_buddy_block_size(&mgr->mm, block), 'R');
+		s += printed;
+		count++;
+	}
+	list_for_each_entry(pos, &mgr->queued_pages, queued_link) {
+		u64 pfn, blk_size;
+
+		if (count >= 10000 || s >= max_len)
+			break;
+
+		block = list_first_entry_or_null(&pos->blocks, struct gpu_buddy_block, link);
+		if (block) {
+			pfn = gpu_buddy_block_offset(block) >> PAGE_SHIFT;
+			blk_size = gpu_buddy_block_size(&mgr->mm, block);
+		} else {
+			pfn = pos->addr >> PAGE_SHIFT;
+			blk_size = PAGE_SIZE;
+		}
+
+		printed = scnprintf(buf + s, max_len - s, "0x%016llx : 0x%016llx : %c\n",
+				    pfn, blk_size, pos->status ? 'F' : 'P');
+		s += printed;
+		count++;
+	}
+
+	return s;
+}
+
+static ssize_t vram_bad_pages_bin_read(struct file *filp, struct kobject *kobj,
+				       const struct bin_attribute *attr, char *buf,
+				       loff_t off, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct ttm_resource_manager *man;
+	struct xe_ttm_vram_mgr *mgr;
+	size_t allocation_size;
+	struct xe_device *xe;
+	size_t full_data_len;
+	int active_entries;
+	char *temp_buf;
+
+	xe = pdev_to_xe_device(pdev);
+	man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0);
+	if (!man)
+		return -ENODEV;
+	mgr = to_xe_ttm_vram_mgr(man);
+
+	/* Snapshot entry count under lock, then allocate outside to avoid deadlock */
+	mutex_lock(&mgr->lock);
+	active_entries = mgr->n_offlined_pages + mgr->n_queued_pages;
+	mutex_unlock(&mgr->lock);
+
+	if (active_entries > 10000)
+		active_entries = 10000;
+
+	allocation_size = 64 + (active_entries * 48);
+
+	temp_buf = kvmalloc(allocation_size, GFP_KERNEL);
+	if (!temp_buf)
+		return -ENOMEM;
+
+	mutex_lock(&mgr->lock);
+	full_data_len = serialize_bad_pages(mgr, temp_buf, allocation_size);
+	mutex_unlock(&mgr->lock);
+
+	if (off >= full_data_len) {
+		kvfree(temp_buf);
+		return 0;
+	}
+
+	if (off + count > full_data_len)
+		count = full_data_len - off;
+
+	memcpy(buf, temp_buf + off, count);
+
+	kvfree(temp_buf);
+	return count;
+}
+
+static const struct bin_attribute bin_attr_vram_bad_pages = {
+	.attr = { .name = "vram_bad_pages", .mode = 0444 },
+	.read = vram_bad_pages_bin_read,
+	.size = 0,
+};
+
+static void xe_ttm_vram_sysfs_fini(void *arg)
+{
+	struct xe_device *xe = arg;
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+
+	sysfs_remove_bin_file(&pdev->dev.kobj, &bin_attr_vram_bad_pages);
+}
+
+/**
+ * xe_ttm_vram_sysfs_init - Initialize vram bad pages sysfs binary file
+ * @xe: Xe Device object
+ *
+ * Creates a binary sysfs file under the PCI device for reading
+ * offlined and queued VRAM pages. Supports large entry counts
+ * via offset/count pagination.
+ *
+ * Returns: 0 on success, negative error code on error.
+ */
+int xe_ttm_vram_sysfs_init(struct xe_device *xe)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	int err;
+
+	err = sysfs_create_bin_file(&pdev->dev.kobj, &bin_attr_vram_bad_pages);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Failed to create vram_bad_pages sysfs: %d\n",
+			err);
+		return err;
+	}
+
+	return devm_add_action_or_reset(&pdev->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 d5392beff30c..eb55b0f74ef3 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, u64 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 815a601504d5..5f7c53d3a753 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
@@ -37,6 +37,8 @@ struct xe_ttm_vram_mgr {
 	struct mutex lock;
 	/** @mem_type: The TTM memory type */
 	u32 mem_type;
+	/** @max_pages: max pages that can be in offline queue retrieved from FW */
+	u16 max_pages;
 };
 
 /**
-- 
2.52.0