linux_dsm_epyc7002/drivers/gpu/drm/i915/i915_reset.h
Chris Wilson c41166f9a1 drm/i915: Beware temporary wedging when determining -EIO
At a few points in our uABI, we check to see if the driver is wedged and
report -EIO back to the user in that case. However, as we perform the
check and reset asynchronously (where once before they were both
serialised by the struct_mutex), we may instead see the temporary wedging
used to cancel inflight rendering to avoid a deadlock during reset
(caused by either us timing out in our reset handler,
i915_wedge_on_timeout or with malice aforethought in intel_reset_prepare
for a stuck modeset). If we suspect this is the case, that is we see a
wedged driver *and* reset in progress, then wait until the reset is
resolved before reporting upon the wedged status.

v2: might_sleep() (Mika)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109580
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190220145637.23503-1-chris@chris-wilson.co.uk
2019-02-20 16:31:08 +00:00

66 lines
1.7 KiB
C

/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2008-2018 Intel Corporation
*/
#ifndef I915_RESET_H
#define I915_RESET_H
#include <linux/compiler.h>
#include <linux/types.h>
#include <linux/srcu.h>
struct drm_i915_private;
struct intel_engine_cs;
struct intel_guc;
__printf(4, 5)
void i915_handle_error(struct drm_i915_private *i915,
u32 engine_mask,
unsigned long flags,
const char *fmt, ...);
#define I915_ERROR_CAPTURE BIT(0)
void i915_clear_error_registers(struct drm_i915_private *i915);
void i915_reset(struct drm_i915_private *i915,
unsigned int stalled_mask,
const char *reason);
int i915_reset_engine(struct intel_engine_cs *engine,
const char *reason);
void i915_reset_request(struct i915_request *rq, bool guilty);
bool i915_reset_flush(struct drm_i915_private *i915);
int __must_check i915_reset_trylock(struct drm_i915_private *i915);
void i915_reset_unlock(struct drm_i915_private *i915, int tag);
int i915_terminally_wedged(struct drm_i915_private *i915);
bool intel_has_gpu_reset(struct drm_i915_private *i915);
bool intel_has_reset_engine(struct drm_i915_private *i915);
int intel_gpu_reset(struct drm_i915_private *i915, u32 engine_mask);
int intel_reset_guc(struct drm_i915_private *i915);
struct i915_wedge_me {
struct delayed_work work;
struct drm_i915_private *i915;
const char *name;
};
void __i915_init_wedge(struct i915_wedge_me *w,
struct drm_i915_private *i915,
long timeout,
const char *name);
void __i915_fini_wedge(struct i915_wedge_me *w);
#define i915_wedge_on_timeout(W, DEV, TIMEOUT) \
for (__i915_init_wedge((W), (DEV), (TIMEOUT), __func__); \
(W)->i915; \
__i915_fini_wedge((W)))
#endif /* I915_RESET_H */