From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: simona.vetter@ffwll.ch, matthew.brost@intel.com,
christian.koenig@amd.com, thomas.hellstrom@linux.intel.com,
joonas.lahtinen@linux.intel.com, christoph.manszewski@intel.com,
rodrigo.vivi@intel.com, lucas.demarchi@intel.com,
andrzej.hajda@intel.com, matthew.auld@intel.com,
maciej.patelczyk@intel.com, gwan-gyeong.mun@intel.com,
Mika Kuoppala <mika.kuoppala@linux.intel.com>,
Simona Vetter <simona@ffwll.ch>,
Dominik Grzegorzek <dominik.grzegorzek@intel.com>
Subject: [PATCH 09/20] drm/xe/eudebug: userptr vm pread/pwrite
Date: Mon, 6 Oct 2025 14:16:59 +0300 [thread overview]
Message-ID: <20251006111711.201906-10-mika.kuoppala@linux.intel.com> (raw)
In-Reply-To: <20251006111711.201906-1-mika.kuoppala@linux.intel.com>
Implement debugger vm access for userptrs.
When bind is done, take ref to current task so that
we know from which vm the address was bound. Then during
debugger pread/pwrite we use this target task as
parameter to access the debuggee vm with access_process_vm().
This is based on suggestions from Simona, Thomas and Joonas.
v2: need to add offset into vma (Dominik)
v3: move code into xe_userptr.c (Mika)
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Dominik Grzegorzek <dominik.grzegorzek@intel.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
drivers/gpu/drm/xe/xe_eudebug_vm.c | 16 +++++++++++++++
drivers/gpu/drm/xe/xe_userptr.c | 4 ++++
drivers/gpu/drm/xe/xe_userptr.h | 32 ++++++++++++++++++++++++++++++
drivers/gpu/drm/xe/xe_vm.c | 1 +
4 files changed, 53 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_eudebug_vm.c b/drivers/gpu/drm/xe/xe_eudebug_vm.c
index 4dd747680a9c..6d341bae4ffc 100644
--- a/drivers/gpu/drm/xe/xe_eudebug_vm.c
+++ b/drivers/gpu/drm/xe/xe_eudebug_vm.c
@@ -51,6 +51,22 @@ static int xe_eudebug_vma_access(struct xe_vma *vma,
xe_bo_put(bo);
return ret;
+ } else if (xe_vma_is_userptr(vma)) {
+ struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
+
+ if (XE_WARN_ON(!userptr->eudebug.task))
+ return -EINVAL;
+
+ /*
+ * access_remote_vm() would fit as userptr notifier has
+ * mm ref so we would not need to carry task ref at all.
+ * But access_remote_vm is not exported. access_process_vm()
+ * is exported so use it instead.
+ */
+ return access_process_vm(userptr->eudebug.task,
+ xe_vma_userptr(vma) + offset_in_vma,
+ buf, bytes,
+ write ? FOLL_WRITE : 0);
}
return -EINVAL;
diff --git a/drivers/gpu/drm/xe/xe_userptr.c b/drivers/gpu/drm/xe/xe_userptr.c
index f16e92cd8090..6cf9158f9e79 100644
--- a/drivers/gpu/drm/xe/xe_userptr.c
+++ b/drivers/gpu/drm/xe/xe_userptr.c
@@ -290,6 +290,8 @@ int xe_userptr_setup(struct xe_userptr_vma *uvma, unsigned long start,
userptr->pages.notifier_seq = LONG_MAX;
+ xe_eudebug_track_userptr_task(userptr);
+
return 0;
}
@@ -298,6 +300,8 @@ void xe_userptr_remove(struct xe_userptr_vma *uvma)
struct xe_vm *vm = xe_vma_vm(&uvma->vma);
struct xe_userptr *userptr = &uvma->userptr;
+ xe_eudebug_untrack_userptr_task(userptr);
+
drm_gpusvm_free_pages(&vm->svm.gpusvm, &uvma->userptr.pages,
xe_vma_size(&uvma->vma) >> PAGE_SHIFT);
diff --git a/drivers/gpu/drm/xe/xe_userptr.h b/drivers/gpu/drm/xe/xe_userptr.h
index ef801234991e..4af2569f1fa1 100644
--- a/drivers/gpu/drm/xe/xe_userptr.h
+++ b/drivers/gpu/drm/xe/xe_userptr.h
@@ -66,6 +66,12 @@ struct xe_userptr {
#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
u32 divisor;
#endif
+
+#if IS_ENABLED(CONFIG_DRM_XE_EUDEBUG)
+ struct {
+ struct task_struct *task;
+ } eudebug;
+#endif
};
#if IS_ENABLED(CONFIG_DRM_GPUSVM)
@@ -104,4 +110,30 @@ static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
{
}
#endif
+
+#if IS_ENABLED(CONFIG_DRM_XE_EUDEBUG)
+static inline void xe_eudebug_track_userptr_task(struct xe_userptr *userptr)
+{
+ /*
+ * We could use the mm which is on notifier. But
+ * the access_remote_vm() is not exported. Thus
+ * we get reference to task for access_process_vm()
+ */
+ userptr->eudebug.task = get_task_struct(current);
+}
+
+static inline void xe_eudebug_untrack_userptr_task(struct xe_userptr *userptr)
+{
+ put_task_struct(userptr->eudebug.task);
+}
+#else
+static inline void xe_eudebug_track_userptr_task(struct xe_userptr *userptr)
+{
+}
+
+static inline void xe_eudebug_untrack_userptr_task(struct xe_userptr *userptr)
+{
+}
+#endif /* CONFIG_DRM_XE_EUDEBUG */
+
#endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 5f86e87d8458..5a05563009b2 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1053,6 +1053,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
struct xe_userptr_vma *uvma = to_userptr_vma(vma);
xe_userptr_remove(uvma);
+
xe_vm_put(vm);
} else if (xe_vma_is_null(vma) || xe_vma_is_cpu_addr_mirror(vma)) {
xe_vm_put(vm);
--
2.43.0
next prev parent reply other threads:[~2025-10-06 11:18 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-06 11:16 [PATCH 00/20] Intel Xe GPU Debug Support (eudebug) v5 Mika Kuoppala
2025-10-06 11:16 ` [PATCH 01/20] drm/xe/eudebug: Introduce eudebug interface Mika Kuoppala
2025-10-06 11:16 ` [PATCH 02/20] drm/xe/eudebug: Introduce discovery for resources Mika Kuoppala
2025-10-06 11:16 ` [PATCH 03/20] drm/xe/eudebug: Introduce exec_queue events Mika Kuoppala
2025-10-06 11:16 ` [PATCH 04/20] drm/xe: Add EUDEBUG_ENABLE exec queue property Mika Kuoppala
2025-10-06 11:16 ` [PATCH 05/20] drm/xe: Introduce ADD_DEBUG_DATA and REMOVE_DEBUG_DATA vm bind ops Mika Kuoppala
2025-10-06 11:16 ` [PATCH 06/20] drm/xe/eudebug: Introduce vm bind and vm bind debug data events Mika Kuoppala
2025-10-06 11:16 ` [PATCH 07/20] drm/xe/eudebug: Add UFENCE events with acks Mika Kuoppala
2025-10-06 11:16 ` [PATCH 08/20] drm/xe/eudebug: vm open/pread/pwrite Mika Kuoppala
2025-10-06 11:16 ` Mika Kuoppala [this message]
2025-10-06 11:17 ` [PATCH 10/20] drm/xe/eudebug: hw enablement for eudebug Mika Kuoppala
2025-10-06 11:17 ` [PATCH 11/20] drm/xe/eudebug: Introduce EU control interface Mika Kuoppala
2025-10-06 11:17 ` [PATCH 12/20] drm/xe/eudebug: Introduce per device attention scan worker Mika Kuoppala
2025-10-06 11:17 ` [PATCH 13/20] drm/xe/eudebug_test: Introduce xe_eudebug wa kunit test Mika Kuoppala
2025-10-06 11:17 ` [PATCH 14/20] drm/xe: Implement SR-IOV and eudebug exclusivity Mika Kuoppala
2025-10-06 11:17 ` [PATCH 15/20] drm/xe: Add xe_client_debugfs and introduce debug_data file Mika Kuoppala
2025-10-06 11:17 ` [PATCH 16/20] drm/xe/eudebug: Mark guc contexts as debuggable Mika Kuoppala
2025-10-06 18:35 ` Matthew Brost
2025-10-20 12:56 ` Mika Kuoppala
2025-10-20 12:53 ` Mika Kuoppala
2025-11-18 14:48 ` Mika Kuoppala
2025-11-19 21:33 ` Daniele Ceraolo Spurio
2025-10-06 11:17 ` [PATCH 17/20] drm/xe/eudebug: Add read/count/compare helper for eu attention Mika Kuoppala
2025-10-06 11:17 ` [PATCH 18/20] drm/xe/eudebug: Introduce EU pagefault handling interface Mika Kuoppala
2025-10-06 11:17 ` [PATCH 19/20] drm/xe/vm: Support for adding null page VMA to VM on request Mika Kuoppala
2025-10-06 11:17 ` [PATCH 20/20] drm/xe/eudebug: Enable EU pagefault handling Mika Kuoppala
2025-10-06 18:43 ` Matthew Brost
2025-10-06 12:30 ` ✗ CI.checkpatch: warning for Intel Xe GPU Debug Support (eudebug) v5 Patchwork
2025-10-06 12:31 ` ✓ CI.KUnit: success " Patchwork
2025-10-06 13:14 ` ✓ Xe.CI.BAT: " Patchwork
2025-10-06 15:53 ` ✗ Xe.CI.Full: failure " 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=20251006111711.201906-10-mika.kuoppala@linux.intel.com \
--to=mika.kuoppala@linux.intel.com \
--cc=andrzej.hajda@intel.com \
--cc=christian.koenig@amd.com \
--cc=christoph.manszewski@intel.com \
--cc=dominik.grzegorzek@intel.com \
--cc=gwan-gyeong.mun@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=joonas.lahtinen@linux.intel.com \
--cc=lucas.demarchi@intel.com \
--cc=maciej.patelczyk@intel.com \
--cc=matthew.auld@intel.com \
--cc=matthew.brost@intel.com \
--cc=rodrigo.vivi@intel.com \
--cc=simona.vetter@ffwll.ch \
--cc=simona@ffwll.ch \
--cc=thomas.hellstrom@linux.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