[Intel-gfx] [PATCH 01/15] drm/i915: Copy user requested buffers into the error state
Introduce a new execobject.flag (EXEC_OBJECT_CAPTURE) that userspace may
use to indicate that it wants the contents of this buffer preserved in
the error state (/sys/class/drm/cardN/error) following a GPU hang
involving this batch.
Use this at your discretion, the contents of the error state. although
compressed, are allocated with GFP_ATOMIC (i.e. limited) and kept for all
eternity (until the error state is destroyed).
Based on an earlier patch by Ben Widawsky
Signed-off-by: Chris Wilson
Cc: Ben Widawsky
Cc: Matt Turner
Acked-by: Ben Widawsky
Reviewed-by: Joonas Lahtinen
---
drivers/gpu/drm/i915/i915_drv.c| 1 +
drivers/gpu/drm/i915/i915_drv.h| 3 +++
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 12 +
drivers/gpu/drm/i915/i915_gem_request.c| 16
drivers/gpu/drm/i915/i915_gem_request.h| 11
drivers/gpu/drm/i915/i915_gpu_error.c | 40 +-
include/uapi/drm/i915_drm.h| 15 ++-
7 files changed, 96 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9164167cd147..9d8c8b928aab 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -350,6 +350,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_HAS_EXEC_SOFTPIN:
case I915_PARAM_HAS_EXEC_ASYNC:
case I915_PARAM_HAS_EXEC_FENCE:
+ case I915_PARAM_HAS_EXEC_CAPTURE:
/* For the time being all of these are always true;
* if some supported hardware does not have one of these
* features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6e14c7d089b8..3c9551147e28 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1035,6 +1035,9 @@ struct i915_gpu_state {
u32 *pages[0];
} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
+ struct drm_i915_error_object **user_bo;
+ long user_bo_count;
+
struct drm_i915_error_object *wa_ctx;
struct drm_i915_error_request {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index dd7181ed5eca..cc6082a80d2d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1112,6 +1112,18 @@ i915_gem_execbuffer_move_to_gpu(struct
drm_i915_gem_request *req,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
+ if (vma->exec_entry->flags & EXEC_OBJECT_CAPTURE) {
+ struct i915_gem_capture_list *capture;
+
+ capture = kmalloc(sizeof(*capture), GFP_KERNEL);
+ if (unlikely(!capture))
+ return -ENOMEM;
+
+ capture->next = req->capture_list;
+ capture->vma = vma;
+ req->capture_list = capture;
+ }
+
if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC)
continue;
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c
b/drivers/gpu/drm/i915/i915_gem_request.c
index 1e1d9f2072cd..73e34cdc67c4 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -270,6 +270,19 @@ void i915_gem_retire_noop(struct i915_gem_active *active,
/* Space left intentionally blank */
}
+static void request_free_capture_list(struct drm_i915_gem_request *request)
+{
+ struct i915_gem_capture_list *capture;
+
+ capture = request->capture_list;
+ while (capture) {
+ struct i915_gem_capture_list *next = capture->next;
+
+ kfree(capture);
+ capture = next;
+ }
+}
+
static void i915_gem_request_retire(struct drm_i915_gem_request *request)
{
struct intel_engine_cs *engine = request->engine;
@@ -304,6 +317,8 @@ static void i915_gem_request_retire(struct
drm_i915_gem_request *request)
}
unreserve_seqno(request->engine);
+ request_free_capture_list(request);
+
/* Walk through the active list, calling retire on each. This allows
* objects to track their GPU activity and mark themselves as idle
* when their *last* active request is completed (updating state
@@ -602,6 +617,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
req->global_seqno = 0;
req->file_priv = NULL;
req->batch = NULL;
+ req->capture_list = NULL;
/*
* Reserve space in the ring buffer for all the commands required to
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h
b/drivers/gpu/drm/i915/i915_gem_request.h
index 0cef887b0de4..4eb642960393 100644
--- a/drivers/gpu/drm
Re: [Intel-gfx] [PATCH 01/15] drm/i915: Copy user requested buffers into the error state
On to, 2017-02-23 at 16:18 +, Chris Wilson wrote: > Introduce a new execobject.flag (EXEC_OBJECT_CAPTURE) that userspace may > use to indicate that it wants the contents of this buffer preserved in > the error state (/sys/class/drm/cardN/error) following a GPU hang > involving this batch. > > Use this at your discretion, the contents of the error state. although > compressed, are allocated with GFP_ATOMIC (i.e. limited) and kept for all > eternity (until the error state is destroyed). > > Based on an earlier patch by Ben Widawsky > Signed-off-by: Chris Wilson > Cc: Ben Widawsky > Cc: Matt Turner Reviewed-by: Joonas Lahtinen Regards, Joonas -- Joonas Lahtinen Open Source Technology Center Intel Corporation ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [Intel-gfx] [PATCH 01/15] drm/i915: Copy user requested buffers into the error state
On 17-02-23 16:18:16, Chris Wilson wrote:
Introduce a new execobject.flag (EXEC_OBJECT_CAPTURE) that userspace may
use to indicate that it wants the contents of this buffer preserved in
the error state (/sys/class/drm/cardN/error) following a GPU hang
involving this batch.
Use this at your discretion, the contents of the error state. although
compressed, are allocated with GFP_ATOMIC (i.e. limited) and kept for all
eternity (until the error state is destroyed).
Based on an earlier patch by Ben Widawsky
Signed-off-by: Chris Wilson
Cc: Ben Widawsky
Cc: Matt Turner
Haven't tested it or used it, but I wanted it.
Acked-by: Ben Widawsky
---
drivers/gpu/drm/i915/i915_drv.c| 1 +
drivers/gpu/drm/i915/i915_drv.h| 3 +++
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 12 +
drivers/gpu/drm/i915/i915_gem_request.c| 16
drivers/gpu/drm/i915/i915_gem_request.h| 11
drivers/gpu/drm/i915/i915_gpu_error.c | 40 +-
include/uapi/drm/i915_drm.h| 15 ++-
7 files changed, 96 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 409fc32ce2bd..842c62b96a83 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -353,6 +353,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_HAS_EXEC_ASYNC:
case I915_PARAM_HAS_EXEC_FENCE:
case I915_PARAM_HAS_EXEC_FENCE_DMABUF:
+ case I915_PARAM_HAS_EXEC_CAPTURE:
/* For the time being all of these are always true;
* if some supported hardware does not have one of these
* features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 440a4725b87f..2cc0253d6ef7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1018,6 +1018,9 @@ struct i915_gpu_state {
u32 *pages[0];
} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
+ struct drm_i915_error_object **user_bo;
+ long user_bo_count;
+
struct drm_i915_error_object *wa_ctx;
struct drm_i915_error_request {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3f2796131410..e8ffe0c9a20e 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1113,6 +1113,18 @@ i915_gem_execbuffer_move_to_gpu(struct
drm_i915_gem_request *req,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
+ if (vma->exec_entry->flags & EXEC_OBJECT_CAPTURE) {
+ struct i915_gem_capture_list *capture;
+
+ capture = kmalloc(sizeof(*capture), GFP_KERNEL);
+ if (unlikely(!capture))
+ return -ENOMEM;
+
+ capture->next = req->capture_list;
+ capture->vma = vma;
+ req->capture_list = capture;
+ }
+
if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC)
continue;
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c
b/drivers/gpu/drm/i915/i915_gem_request.c
index ad9d4ce07fb6..3a159cac2172 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -286,6 +286,19 @@ void i915_gem_retire_noop(struct i915_gem_active *active,
/* Space left intentionally blank */
}
+static void request_free_capture_list(struct drm_i915_gem_request *request)
+{
+ struct i915_gem_capture_list *capture;
+
+ capture = request->capture_list;
+ while (capture) {
+ struct i915_gem_capture_list *next = capture->next;
+
+ kfree(capture);
+ capture = next;
+ }
+}
+
static void i915_gem_request_retire(struct drm_i915_gem_request *request)
{
struct intel_engine_cs *engine = request->engine;
@@ -320,6 +333,8 @@ static void i915_gem_request_retire(struct
drm_i915_gem_request *request)
}
unreserve_seqno(request->engine);
+ request_free_capture_list(request);
+
/* Walk through the active list, calling retire on each. This allows
* objects to track their GPU activity and mark themselves as idle
* when their *last* active request is completed (updating state
@@ -615,6 +630,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
req->global_seqno = 0;
req->file_priv = NULL;
req->batch = NULL;
+ req->capture_list = NULL;
/*
* Reserve space in the ring buffer for all the commands required to
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h
b/drivers/gpu/drm/i915/i915_gem_request.h
index 0ef
[Intel-gfx] [PATCH 01/15] drm/i915: Copy user requested buffers into the error state
Introduce a new execobject.flag (EXEC_OBJECT_CAPTURE) that userspace may
use to indicate that it wants the contents of this buffer preserved in
the error state (/sys/class/drm/cardN/error) following a GPU hang
involving this batch.
Use this at your discretion, the contents of the error state. although
compressed, are allocated with GFP_ATOMIC (i.e. limited) and kept for all
eternity (until the error state is destroyed).
Based on an earlier patch by Ben Widawsky
Signed-off-by: Chris Wilson
Cc: Ben Widawsky
Cc: Matt Turner
---
drivers/gpu/drm/i915/i915_drv.c| 1 +
drivers/gpu/drm/i915/i915_drv.h| 3 +++
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 12 +
drivers/gpu/drm/i915/i915_gem_request.c| 16
drivers/gpu/drm/i915/i915_gem_request.h| 11
drivers/gpu/drm/i915/i915_gpu_error.c | 40 +-
include/uapi/drm/i915_drm.h| 15 ++-
7 files changed, 96 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 409fc32ce2bd..842c62b96a83 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -353,6 +353,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
case I915_PARAM_HAS_EXEC_ASYNC:
case I915_PARAM_HAS_EXEC_FENCE:
case I915_PARAM_HAS_EXEC_FENCE_DMABUF:
+ case I915_PARAM_HAS_EXEC_CAPTURE:
/* For the time being all of these are always true;
* if some supported hardware does not have one of these
* features this value needs to be provided from
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 440a4725b87f..2cc0253d6ef7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1018,6 +1018,9 @@ struct i915_gpu_state {
u32 *pages[0];
} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
+ struct drm_i915_error_object **user_bo;
+ long user_bo_count;
+
struct drm_i915_error_object *wa_ctx;
struct drm_i915_error_request {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3f2796131410..e8ffe0c9a20e 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1113,6 +1113,18 @@ i915_gem_execbuffer_move_to_gpu(struct
drm_i915_gem_request *req,
list_for_each_entry(vma, vmas, exec_list) {
struct drm_i915_gem_object *obj = vma->obj;
+ if (vma->exec_entry->flags & EXEC_OBJECT_CAPTURE) {
+ struct i915_gem_capture_list *capture;
+
+ capture = kmalloc(sizeof(*capture), GFP_KERNEL);
+ if (unlikely(!capture))
+ return -ENOMEM;
+
+ capture->next = req->capture_list;
+ capture->vma = vma;
+ req->capture_list = capture;
+ }
+
if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC)
continue;
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c
b/drivers/gpu/drm/i915/i915_gem_request.c
index ad9d4ce07fb6..3a159cac2172 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -286,6 +286,19 @@ void i915_gem_retire_noop(struct i915_gem_active *active,
/* Space left intentionally blank */
}
+static void request_free_capture_list(struct drm_i915_gem_request *request)
+{
+ struct i915_gem_capture_list *capture;
+
+ capture = request->capture_list;
+ while (capture) {
+ struct i915_gem_capture_list *next = capture->next;
+
+ kfree(capture);
+ capture = next;
+ }
+}
+
static void i915_gem_request_retire(struct drm_i915_gem_request *request)
{
struct intel_engine_cs *engine = request->engine;
@@ -320,6 +333,8 @@ static void i915_gem_request_retire(struct
drm_i915_gem_request *request)
}
unreserve_seqno(request->engine);
+ request_free_capture_list(request);
+
/* Walk through the active list, calling retire on each. This allows
* objects to track their GPU activity and mark themselves as idle
* when their *last* active request is completed (updating state
@@ -615,6 +630,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
req->global_seqno = 0;
req->file_priv = NULL;
req->batch = NULL;
+ req->capture_list = NULL;
/*
* Reserve space in the ring buffer for all the commands required to
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h
b/drivers/gpu/drm/i915/i915_gem_request.h
index 0efee879df23..cc24a6c72748 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i9
