Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Tejas Upadhyay <tejas.upadhyay@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: himal.prasad.ghimiray@intel.com, rodrigo.vivi@intel.com,
	Matthew Brost <matthew.brost@intel.com>,
	Tejas Upadhyay <tejas.upadhyay@intel.com>,
	Michal Wajdeczko <michal.wajdeczko@intel.com>
Subject: [PATCH V21 13/15] drm/xe: Expose bad VRAM pages via debugfs
Date: Thu,  3 Sep 2026 21:46:06 +0530	[thread overview]
Message-ID: <20260903161553.528932-30-tejas.upadhyay@intel.com> (raw)
In-Reply-To: <20260903161553.528932-17-tejas.upadhyay@intel.com>

Add a debugfs file "vram_bad_pages" that shows offlined and queued
VRAM pages across all tiles. Each entry displays the page frame number,
GPU page size, and status flag (R=reserved, P=pending, F=failed).

example,
cat /sys/kernel/debug/dri/0/vram_bad_pages

max_pages: 10000
0x0000000000000000 : 0x0000000000001000 : R
0x0000000000001234 : 0x0000000000001000 : P
0x0000000000080000 : 0x0000000000001000 : R   ← tile 1 addr

v3(Michal):
-add kernel doc
v2(Sashikoi/Michal/Himal):
-Remove block iteration, use offline and queue list only
-Move platform check inside api

Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/xe/xe_debugfs.c            |  3 +
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.c       | 71 ++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.h       |  1 +
 drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h |  2 +
 4 files changed, 77 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 28135f84e286..cb24e001b142 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -32,6 +32,7 @@
 #include "xe_sriov_vf.h"
 #include "xe_step.h"
 #include "xe_tile_debugfs.h"
+#include "xe_ttm_vram_mgr.h"
 #include "xe_vsec.h"
 #include "xe_wa.h"
 
@@ -773,6 +774,8 @@ void xe_debugfs_register(struct xe_device *xe)
 	if (man)
 		ttm_resource_manager_create_debugfs(man, root, "stolen_mm");
 
+	xe_ttm_vram_debugfs_init(xe, root);
+
 	for_each_tile(tile, xe, tile_id)
 		xe_tile_debugfs_register(tile);
 
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index f4810cb961df..3dcee4590126 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/cgroup_dmem.h>
+#include <linux/debugfs.h>
 
 #include <drm/drm_managed.h>
 #include <drm/drm_drv.h>
@@ -915,3 +916,73 @@ int xe_ttm_vram_handle_addr_fault(struct xe_device *xe, u64 addr)
 	return xe_ttm_vram_reserve_page_at_addr(xe, addr - vr->dpa_base, vram_mgr, mm);
 }
 EXPORT_SYMBOL(xe_ttm_vram_handle_addr_fault);
+
+static int vram_bad_pages_show(struct seq_file *m, void *unused)
+{
+	struct xe_device *xe = m->private;
+	struct xe_ttm_vram_offline_resource *pos;
+	struct ttm_resource_manager *man;
+	struct xe_ttm_vram_mgr *mgr;
+	struct xe_tile *tile;
+	u8 id;
+
+	man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0);
+	if (man)
+		/* TODO Hook with RAS to show max_pages fetched from FW */
+		seq_printf(m, "max_pages: %d\n",
+			   to_xe_ttm_vram_mgr(man)->max_pages);
+
+	for_each_tile(tile, xe, id) {
+		struct xe_vram_region *vr = tile->mem.vram;
+
+		man = ttm_manager_type(&xe->ttm, XE_PL_VRAM0 + id);
+		if (!man || !vr)
+			continue;
+		mgr = to_xe_ttm_vram_mgr(man);
+
+		rcu_read_lock();
+
+		list_for_each_entry_rcu(pos, &mgr->offlined_pages, offlined_link) {
+			u64 pfn;
+
+			pfn = (pos->addr + vr->dpa_base) >> PAGE_SHIFT;
+			seq_printf(m, "0x%016llx : 0x%016lx : R\n", pfn, PAGE_SIZE);
+		}
+
+		list_for_each_entry_rcu(pos, &mgr->queued_pages, queued_link) {
+			u64 pfn;
+
+			pfn = (pos->addr + vr->dpa_base) >> PAGE_SHIFT;
+			seq_printf(m, "0x%016llx : 0x%016lx : %c\n",
+				   pfn, PAGE_SIZE, pos->status ? 'F' : 'P');
+		}
+
+		rcu_read_unlock();
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(vram_bad_pages);
+
+/**
+ * xe_ttm_vram_debugfs_init - Initialize VRAM debugfs interfaces
+ * @xe: The xe device structure pointer
+ * @root: The root dentry of the debugfs directory
+ *
+ * This function registers platform-specific VRAM debugfs files used for
+ * testing and debugging. Currently, it exposes the "vram_bad_pages" interface
+ * to inspect marked faulty memory pages, restricted specifically to the
+ * %XE_CRESCENTISLAND platform.
+ *
+ * Return: Void.
+ */
+void xe_ttm_vram_debugfs_init(struct xe_device *xe, struct dentry *root)
+{
+	/*
+	 * TODO: Replace platform check with xe->info
+	 * once the feature flag is plumbed through device info.
+	 */
+	if (xe->info.platform != XE_CRESCENTISLAND)
+		return;
+	debugfs_create_file("vram_bad_pages", 0444, root, xe, &vram_bad_pages_fops);
+}
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
index 764d493b4d50..48f39fd20e44 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
@@ -17,6 +17,7 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
 			   u32 mem_type, u64 size, u64 io_size,
 			   u64 default_page_size);
 int xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_vram_region *vram);
+void xe_ttm_vram_debugfs_init(struct xe_device *xe, struct dentry *root);
 int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
 			      struct ttm_resource *res,
 			      u64 offset, u64 length,
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 dc97b0ad0e51..efcf3e1d4e80 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


  parent reply	other threads:[~2026-09-03 16:16 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-03 16:15 [PATCH V21 00/15] Add memory page offlining support Tejas Upadhyay
2026-09-03 16:15 ` [PATCH V21 01/15] drm/xe: Link VRAM resource allocation with gpu buddy Tejas Upadhyay
2026-09-03 16:15 ` [PATCH V21 02/15] drm/xe: Link LRC BO and its execution queue with safe lifetime rules Tejas Upadhyay
2026-09-03 16:15 ` [PATCH V21 03/15] drm/xe: Export xe_ttm_bo_purge() Tejas Upadhyay
2026-09-03 16:15 ` [PATCH V21 04/15] drm/xe: Handle NULL resource and allow purging of VRAM pages Tejas Upadhyay
2026-09-03 17:08   ` sashiko-bot
2026-09-03 16:15 ` [PATCH V21 05/15] drm/xe/bo: Make xe_bo_is_user() public Tejas Upadhyay
2026-09-03 16:15 ` [PATCH V21 06/15] drm/xe: Guard teardown paths against purged BOs Tejas Upadhyay
2026-09-03 16:55   ` sashiko-bot
2026-09-03 16:16 ` [PATCH V21 07/15] drm/xe/vram: Extract buddy allocation and free helpers Tejas Upadhyay
2026-09-03 16:16 ` [PATCH V21 08/15] drm/xe/vram: Add page offline data structures and lifecycle Tejas Upadhyay
2026-09-03 16:16 ` [PATCH V21 09/15] drm/xe/vram: Add VRAM page offline fault handler Tejas Upadhyay
2026-09-03 17:23   ` sashiko-bot
2026-09-03 16:16 ` [PATCH V21 10/15] drm/xe/configfs: Add disable_vram_page_offline attribute Tejas Upadhyay
2026-09-03 16:16 ` [PATCH V21 11/15] drm/xe/ras: Cache disable_vram_page_offline policy at init Tejas Upadhyay
2026-09-03 16:16 ` [PATCH V21 12/15] drm/xe/vram: Check disable_vram_page_offline policy in fault handler Tejas Upadhyay
2026-09-03 16:16 ` Tejas Upadhyay [this message]
2026-09-03 16:16 ` [PATCH V21 14/15] drm/xe/uapi: Expose ban reason in EXEC_QUEUE_GET_PROPERTY_BAN Tejas Upadhyay
2026-09-03 17:46   ` sashiko-bot
2026-09-03 16:16 ` [PATCH V21 15/15] drm/xe: Add fault-inject based VRAM page offline injection Tejas Upadhyay
2026-09-03 16:23 ` ✗ CI.checkpatch: warning for Add memory page offlining support (rev25) Patchwork
2026-09-03 16:25 ` ✓ CI.KUnit: success " Patchwork
2026-09-03 17:46 ` ✗ Xe.CI.BAT: failure " Patchwork
2026-09-04  4:33 ` [PATCH V21 00/15] Add memory page offlining support Matthew Brost
2026-09-04  5:18 ` ✗ Xe.CI.FULL: failure for Add memory page offlining support (rev25) Patchwork

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=20260903161553.528932-30-tejas.upadhyay@intel.com \
    --to=tejas.upadhyay@intel.com \
    --cc=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=michal.wajdeczko@intel.com \
    --cc=rodrigo.vivi@intel.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