Once upon a time before we had automated GPU state capture upon hangs,
we had intel_gpu_dump. Now we come almost full circle and reinstate that
view of the current GPU queues and registers by using the error capture
facility to snapshot the GPU state when debugfs/.../i915_gpu_info is
opened - which should provided useful debugging to both the error
capture routines (without having to cause a hang and avoid the error
state being eaten by igt) and generally.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_debugfs.c | 123 +++++++++++++++++++---------------
drivers/gpu/drm/i915/i915_drv.h | 26 ++++---
drivers/gpu/drm/i915/i915_gpu_error.c | 71 ++++++++------------
drivers/gpu/drm/i915/i915_sysfs.c | 31 +++++----
4 files changed, 132 insertions(+), 119 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3ae06568df7b..124a184389a8 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -954,89 +954,103 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
}
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
-
-static ssize_t
-i915_error_state_write(struct file *filp,
- const char __user *ubuf,
- size_t cnt,
- loff_t *ppos)
+static ssize_t error_state_read(struct file *file, char __user *ubuf,
+ size_t count, loff_t *pos)
{
- struct i915_error_state_file_priv *error_priv = filp->private_data;
-
- DRM_DEBUG_DRIVER("Resetting error state\n");
- i915_destroy_error_state(error_priv->i915);
-
- return cnt;
-}
+ struct drm_i915_error_state *error = file->private_data;
+ struct drm_i915_error_state_buf str;
+ ssize_t ret;
+ loff_t tmp;
-static int i915_error_state_open(struct inode *inode, struct file *file)
-{
- struct drm_i915_private *dev_priv = inode->i_private;
- struct i915_error_state_file_priv *error_priv;
+ if (!error)
+ return 0;
- error_priv = kzalloc(sizeof(*error_priv), GFP_KERNEL);
- if (!error_priv)
- return -ENOMEM;
+ ret = i915_error_state_buf_init(&str, error->i915, count, *pos);
+ if (ret)
+ return ret;
- error_priv->i915 = dev_priv;
+ ret = i915_error_state_to_str(&str, error);
+ if (ret)
+ goto out;
- i915_error_state_get(&dev_priv->drm, error_priv);
+ tmp = 0;
+ ret = simple_read_from_buffer(ubuf, count, &tmp, str.buf, str.bytes);
+ if (ret < 0)
+ goto out;
- file->private_data = error_priv;
+ *pos = str.start + ret;
+out:
+ i915_error_state_buf_release(&str);
+ return ret;
+}
+static int error_state_release(struct inode *inode, struct file *file)
+{
+ i915_error_state_put(file->private_data);
return 0;
}
-static int i915_error_state_release(struct inode *inode, struct file *file)
+static int i915_gpu_info_open(struct inode *inode, struct file *file)
{
- struct i915_error_state_file_priv *error_priv = file->private_data;
+ struct drm_i915_error_state *error;
- i915_error_state_put(error_priv);
- kfree(error_priv);
+ error = i915_error_state(inode->i_private);
+ if (!error)
+ return -ENOMEM;
+ file->private_data = error;
return 0;
}
-static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
- size_t count, loff_t *pos)
+static const struct file_operations i915_gpu_info_fops = {
+ .owner = THIS_MODULE,
+ .open = i915_gpu_info_open,
+ .read = error_state_read,
+ .llseek = default_llseek,
+ .release = error_state_release,
+};
+
+static ssize_t
+i915_error_state_write(struct file *filp,
+ const char __user *ubuf,
+ size_t cnt,
+ loff_t *ppos)
{
- struct i915_error_state_file_priv *error_priv = file->private_data;
- struct drm_i915_error_state_buf error_str;
- loff_t tmp_pos = 0;
- ssize_t ret_count = 0;
- int ret;
+ struct drm_i915_error_state *error = filp->private_data;
- ret = i915_error_state_buf_init(&error_str, error_priv->i915,
- count, *pos);
- if (ret)
- return ret;
+ if (!error)
+ return 0;
- ret = i915_error_state_to_str(&error_str, error_priv);
- if (ret)
- goto out;
+ DRM_DEBUG_DRIVER("Resetting error state\n");
+ i915_destroy_error_state(error->i915);
- ret_count = simple_read_from_buffer(userbuf, count, &tmp_pos,
- error_str.buf,
- error_str.bytes);
+ return cnt;
+}
- if (ret_count < 0)
- ret = ret_count;
- else
- *pos = error_str.start + ret_count;
-out:
- i915_error_state_buf_release(&error_str);
- return ret ?: ret_count;
+static int i915_error_state_open(struct inode *inode, struct file *file)
+{
+ struct drm_i915_private *i915 = inode->i_private;
+ struct drm_i915_error_state *error;
+
+ spin_lock_irq(&i915->gpu_error.lock);
+ error = i915->gpu_error.first_error;
+ if (error)
+ i915_error_state_get(error);
+ spin_unlock_irq(&i915->gpu_error.lock);
+
+ file->private_data = error;
+
+ return 0;
}
static const struct file_operations i915_error_state_fops = {
.owner = THIS_MODULE,
.open = i915_error_state_open,
- .read = i915_error_state_read,
+ .read = error_state_read,
.write = i915_error_state_write,
.llseek = default_llseek,
- .release = i915_error_state_release,
+ .release = error_state_release,
};
-
#endif
static int
@@ -4707,6 +4721,7 @@ static const struct i915_debugfs_files {
{"i915_gem_drop_caches", &i915_drop_caches_fops},
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
{"i915_error_state", &i915_error_state_fops},
+ {"i915_gpu_info", &i915_gpu_info_fops},
#endif
{"i915_next_seqno", &i915_next_seqno_fops},
{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 27e74322ca70..cb688918a913 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1504,11 +1504,6 @@ struct drm_i915_error_state_buf {
loff_t pos;
};
-struct i915_error_state_file_priv {
- struct drm_i915_private *i915;
- struct drm_i915_error_state *error;
-};
-
#define I915_RESET_TIMEOUT (10 * HZ) /* 10s */
#define I915_FENCE_TIMEOUT (10 * HZ) /* 10s */
@@ -3557,7 +3552,7 @@ static inline void intel_display_crc_init(struct drm_i915_private *dev_priv) {}
__printf(2, 3)
void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
- const struct i915_error_state_file_priv *error);
+ const struct drm_i915_error_state *error);
int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
struct drm_i915_private *i915,
size_t count, loff_t pos);
@@ -3566,12 +3561,25 @@ static inline void i915_error_state_buf_release(
{
kfree(eb->buf);
}
+struct drm_i915_error_state *i915_error_state(struct drm_i915_private *i915);
void i915_capture_error_state(struct drm_i915_private *dev_priv,
u32 engine_mask,
const char *error_msg);
-void i915_error_state_get(struct drm_device *dev,
- struct i915_error_state_file_priv *error_priv);
-void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
+
+static inline struct drm_i915_error_state *
+i915_error_state_get(struct drm_i915_error_state *error)
+{
+ kref_get(&error->ref);
+ return error;
+}
+
+void __i915_error_state_free(struct kref *error_ref);
+static inline void i915_error_state_put(struct drm_i915_error_state *error)
+{
+ if (error)
+ kref_put(&error->ref, __i915_error_state_free);
+}
+
void i915_destroy_error_state(struct drm_i915_private *dev_priv);
#else
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 5283fe815a4d..f8f6dad00d14 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -342,7 +342,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
}
static void error_print_instdone(struct drm_i915_error_state_buf *m,
- struct drm_i915_error_engine *ee)
+ const struct drm_i915_error_engine *ee)
{
int slice;
int subslice;
@@ -372,7 +372,7 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
static void error_print_request(struct drm_i915_error_state_buf *m,
const char *prefix,
- struct drm_i915_error_request *erq)
+ const struct drm_i915_error_request *erq)
{
if (!erq->seqno)
return;
@@ -386,7 +386,7 @@ static void error_print_request(struct drm_i915_error_state_buf *m,
static void error_print_context(struct drm_i915_error_state_buf *m,
const char *header,
- struct drm_i915_error_context *ctx)
+ const struct drm_i915_error_context *ctx)
{
err_printf(m, "%s%s[%d] user_handle %d hw_id %d, ban score %d guilty %d active %d\n",
header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
@@ -394,7 +394,7 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
}
static void error_print_engine(struct drm_i915_error_state_buf *m,
- struct drm_i915_error_engine *ee)
+ const struct drm_i915_error_engine *ee)
{
err_printf(m, "%s command stream:\n", engine_str(ee->engine_id));
err_printf(m, " START: 0x%08x\n", ee->start);
@@ -547,19 +547,13 @@ static void err_print_capabilities(struct drm_i915_error_state_buf *m,
}
int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
- const struct i915_error_state_file_priv *error_priv)
+ const struct drm_i915_error_state *error)
{
- struct drm_i915_private *dev_priv = error_priv->i915;
+ struct drm_i915_private *dev_priv = error->i915;
struct pci_dev *pdev = dev_priv->drm.pdev;
- struct drm_i915_error_state *error = error_priv->error;
struct drm_i915_error_object *obj;
int i, j;
- if (!error) {
- err_printf(m, "no error state collected\n");
- goto out;
- }
-
err_printf(m, "%s\n", error->error_msg);
err_printf(m, "Kernel: " UTS_RELEASE "\n");
err_printf(m, "Time: %ld s %ld us\n",
@@ -663,7 +657,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
error->pinned_bo_count);
for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
- struct drm_i915_error_engine *ee = &error->engine[i];
+ const struct drm_i915_error_engine *ee = &error->engine[i];
obj = ee->batchbuffer;
if (obj) {
@@ -730,7 +724,6 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
if (error->display)
intel_display_print_error_state(m, dev_priv, error->display);
-out:
if (m->bytes == 0 && m->err)
return m->err;
@@ -782,7 +775,7 @@ static void i915_error_object_free(struct drm_i915_error_object *obj)
kfree(obj);
}
-static void i915_error_state_free(struct kref *error_ref)
+void __i915_error_state_free(struct kref *error_ref)
{
struct drm_i915_error_state *error = container_of(error_ref,
typeof(*error), ref);
@@ -1609,6 +1602,23 @@ static int capture(void *data)
#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
+struct drm_i915_error_state *
+i915_error_state(struct drm_i915_private *i915)
+{
+ struct drm_i915_error_state *error;
+
+ error = kzalloc(sizeof(*error), GFP_ATOMIC);
+ if (!error)
+ return NULL;
+
+ kref_init(&error->ref);
+ error->i915 = i915;
+
+ stop_machine(capture, error, NULL);
+
+ return error;
+}
+
/**
* i915_capture_error_state - capture an error record for later analysis
* @dev: drm device
@@ -1632,18 +1642,12 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
if (READ_ONCE(dev_priv->gpu_error.first_error))
return;
- /* Account for pipe specific data like PIPE*STAT */
- error = kzalloc(sizeof(*error), GFP_ATOMIC);
+ error = i915_error_state(dev_priv);
if (!error) {
DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
return;
}
- kref_init(&error->ref);
- error->i915 = dev_priv;
-
- stop_machine(capture, error, NULL);
-
i915_error_capture_msg(dev_priv, error, engine_mask, error_msg);
DRM_INFO("%s\n", error->error_msg);
@@ -1657,7 +1661,7 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
}
if (error) {
- i915_error_state_free(&error->ref);
+ __i915_error_state_free(&error->ref);
return;
}
@@ -1673,24 +1677,6 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
}
}
-void i915_error_state_get(struct drm_device *dev,
- struct i915_error_state_file_priv *error_priv)
-{
- struct drm_i915_private *dev_priv = to_i915(dev);
-
- spin_lock_irq(&dev_priv->gpu_error.lock);
- error_priv->error = dev_priv->gpu_error.first_error;
- if (error_priv->error)
- kref_get(&error_priv->error->ref);
- spin_unlock_irq(&dev_priv->gpu_error.lock);
-}
-
-void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
-{
- if (error_priv->error)
- kref_put(&error_priv->error->ref, i915_error_state_free);
-}
-
void i915_destroy_error_state(struct drm_i915_private *dev_priv)
{
struct drm_i915_error_state *error;
@@ -1700,6 +1686,5 @@ void i915_destroy_error_state(struct drm_i915_private *dev_priv)
dev_priv->gpu_error.first_error = NULL;
spin_unlock_irq(&dev_priv->gpu_error.lock);
- if (error)
- kref_put(&error->ref, i915_error_state_free);
+ i915_error_state_put(error);
}
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index a721ff116101..3f1a825a9f24 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -522,30 +522,35 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
struct device *kdev = kobj_to_dev(kobj);
struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
- struct drm_device *dev = &dev_priv->drm;
- struct i915_error_state_file_priv error_priv;
struct drm_i915_error_state_buf error_str;
- ssize_t ret_count = 0;
+ struct drm_i915_error_state *error;
+ ssize_t ret_count;
int ret;
- memset(&error_priv, 0, sizeof(error_priv));
-
- ret = i915_error_state_buf_init(&error_str, to_i915(dev), count, off);
+ ret = i915_error_state_buf_init(&error_str, dev_priv, count, off);
if (ret)
return ret;
- error_priv.i915 = dev_priv;
- i915_error_state_get(dev, &error_priv);
+ spin_lock_irq(&dev_priv->gpu_error.lock);
+ error = dev_priv->gpu_error.first_error;
+ if (error)
+ i915_error_state_get(error);
+ spin_unlock_irq(&dev_priv->gpu_error.lock);
- ret = i915_error_state_to_str(&error_str, &error_priv);
- if (ret)
- goto out;
+ if (error) {
+ ret = i915_error_state_to_str(&error_str, error);
+ if (ret)
+ goto out;
+ } else {
+ error_str.bytes = strlen("No error state collected\n");
+ strcpy(error_str.buf, "No error state collected\n");
+ }
ret_count = count < error_str.bytes ? count : error_str.bytes;
-
memcpy(buf, error_str.buf, ret_count);
+
out:
- i915_error_state_put(&error_priv);
+ i915_error_state_put(error);
i915_error_state_buf_release(&error_str);
return ret ?: ret_count;
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
