Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
提交 9f58892e 编写于 作者: C Chris Wilson
浏览文件
操作

drm/i915: Pull all the reset functionality together into i915_reset.c 

Currently the code to reset the GPU and our state is spread widely
across a few files. Pull the logic together into a common file.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Acked-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190116153304.787-1-chris@chris-wilson.co.uk
上级 18bb2bcc
展开全部 隐藏空白更改
内联 并排
Showing with 1483 addition and 1472 deletion
drivers/gpu/drm/i915/Makefile
浏览文件 @ 9f58892e
......@@ -40,9 +40,10 @@ i915-y := i915_drv.o \
i915_mm.o \
i915_params.o \
i915_pci.o \
i915_reset.o \
i915_suspend.o \
i915_syncmap.o \
i915_sw_fence.o \
i915_syncmap.o \
i915_sysfs.o \
intel_csr.o \
intel_device_info.o \
......
drivers/gpu/drm/i915/i915_debugfs.c
浏览文件 @ 9f58892e
......@@ -32,6 +32,8 @@
#include "intel_drv.h"
#include "intel_guc_submission.h"
#include "i915_reset.h"
static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
{
return to_i915(node->minor->dev);
......
drivers/gpu/drm/i915/i915_drv.c
浏览文件 @ 9f58892e
......@@ -48,6 +48,7 @@
#include "i915_drv.h"
#include "i915_trace.h"
#include "i915_pmu.h"
#include "i915_reset.h"
#include "i915_query.h"
#include "i915_vgpu.h"
#include "intel_drv.h"
......@@ -2205,211 +2206,6 @@ static int i915_resume_switcheroo(struct drm_device *dev)
return i915_drm_resume(dev);
}
/**
* i915_reset - reset chip after a hang
* @i915: #drm_i915_private to reset
* @stalled_mask: mask of the stalled engines with the guilty requests
* @reason: user error message for why we are resetting
*
* Reset the chip. Useful if a hang is detected. Marks the device as wedged
* on failure.
*
* Caller must hold the struct_mutex.
*
* Procedure is fairly simple:
* - reset the chip using the reset reg
* - re-init context state
* - re-init hardware status page
* - re-init ring buffer
* - re-init interrupt state
* - re-init display
*/
void i915_reset(struct drm_i915_private *i915,
unsigned int stalled_mask,
const char *reason)
{
struct i915_gpu_error *error = &i915->gpu_error;
int ret;
int i;
GEM_TRACE("flags=%lx\n", error->flags);
might_sleep();
lockdep_assert_held(&i915->drm.struct_mutex);
assert_rpm_wakelock_held(i915);
GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
if (!test_bit(I915_RESET_HANDOFF, &error->flags))
return;
/* Clear any previous failed attempts at recovery. Time to try again. */
if (!i915_gem_unset_wedged(i915))
goto wakeup;
if (reason)
dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason);
error->reset_count++;
ret = i915_gem_reset_prepare(i915);
if (ret) {
dev_err(i915->drm.dev, "GPU recovery failed\n");
goto taint;
}
if (!intel_has_gpu_reset(i915)) {
if (i915_modparams.reset)
dev_err(i915->drm.dev, "GPU reset not supported\n");
else
DRM_DEBUG_DRIVER("GPU reset disabled\n");
goto error;
}
for (i = 0; i < 3; i++) {
ret = intel_gpu_reset(i915, ALL_ENGINES);
if (ret == 0)
break;
msleep(100);
}
if (ret) {
dev_err(i915->drm.dev, "Failed to reset chip\n");
goto taint;
}
/* Ok, now get things going again... */
/*
* Everything depends on having the GTT running, so we need to start
* there.
*/
ret = i915_ggtt_enable_hw(i915);
if (ret) {
DRM_ERROR("Failed to re-enable GGTT following reset (%d)\n",
ret);
goto error;
}
i915_gem_reset(i915, stalled_mask);
intel_overlay_reset(i915);
/*
* Next we need to restore the context, but we don't use those
* yet either...
*
* Ring buffer needs to be re-initialized in the KMS case, or if X
* was running at the time of the reset (i.e. we weren't VT
* switched away).
*/
ret = i915_gem_init_hw(i915);
if (ret) {
DRM_ERROR("Failed to initialise HW following reset (%d)\n",
ret);
goto error;
}
i915_queue_hangcheck(i915);
finish:
i915_gem_reset_finish(i915);
wakeup:
clear_bit(I915_RESET_HANDOFF, &error->flags);
wake_up_bit(&error->flags, I915_RESET_HANDOFF);
return;
taint:
/*
* History tells us that if we cannot reset the GPU now, we
* never will. This then impacts everything that is run
* subsequently. On failing the reset, we mark the driver
* as wedged, preventing further execution on the GPU.
* We also want to go one step further and add a taint to the
* kernel so that any subsequent faults can be traced back to
* this failure. This is important for CI, where if the
* GPU/driver fails we would like to reboot and restart testing
* rather than continue on into oblivion. For everyone else,
* the system should still plod along, but they have been warned!
*/
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
error:
i915_gem_set_wedged(i915);
i915_retire_requests(i915);
goto finish;
}
static inline int intel_gt_reset_engine(struct drm_i915_private *dev_priv,
struct intel_engine_cs *engine)
{
return intel_gpu_reset(dev_priv, intel_engine_flag(engine));
}
/**
* i915_reset_engine - reset GPU engine to recover from a hang
* @engine: engine to reset
* @msg: reason for GPU reset; or NULL for no dev_notice()
*
* Reset a specific GPU engine. Useful if a hang is detected.
* Returns zero on successful reset or otherwise an error code.
*
* Procedure is:
* - identifies the request that caused the hang and it is dropped
* - reset engine (which will force the engine to idle)
* - re-init/configure engine
*/
int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
{
struct i915_gpu_error *error = &engine->i915->gpu_error;
struct i915_request *active_request;
int ret;
GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
active_request = i915_gem_reset_prepare_engine(engine);
if (IS_ERR_OR_NULL(active_request)) {
/* Either the previous reset failed, or we pardon the reset. */
ret = PTR_ERR(active_request);
goto out;
}
if (msg)
dev_notice(engine->i915->drm.dev,
"Resetting %s for %s\n", engine->name, msg);
error->reset_engine_count[engine->id]++;
if (!engine->i915->guc.execbuf_client)
ret = intel_gt_reset_engine(engine->i915, engine);
else
ret = intel_guc_reset_engine(&engine->i915->guc, engine);
if (ret) {
/* If we fail here, we expect to fallback to a global reset */
DRM_DEBUG_DRIVER("%sFailed to reset %s, ret=%d\n",
engine->i915->guc.execbuf_client ? "GuC " : "",
engine->name, ret);
goto out;
}
/*
* The request that caused the hang is stuck on elsp, we know the
* active request and can drop it, adjust head to skip the offending
* request to resume executing remaining requests in the queue.
*/
i915_gem_reset_engine(engine, active_request, true);
/*
* The engine and its registers (and workarounds in case of render)
* have been reset to their default values. Follow the init_ring
* process to program RING_MODE, HWSP and re-enable submission.
*/
ret = engine->init_hw(engine);
if (ret)
goto out;
out:
intel_engine_cancel_stop_cs(engine);
i915_gem_reset_finish_engine(engine);
return ret;
}
static int i915_pm_prepare(struct device *kdev)
{
struct pci_dev *pdev = to_pci_dev(kdev);
......
drivers/gpu/drm/i915/i915_drv.h
浏览文件 @ 9f58892e
......@@ -2615,19 +2615,7 @@ extern const struct dev_pm_ops i915_pm_ops;
extern int i915_driver_load(struct pci_dev *pdev,
const struct pci_device_id *ent);
extern void i915_driver_unload(struct drm_device *dev);
extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
extern void i915_reset(struct drm_i915_private *i915,
unsigned int stalled_mask,
const char *reason);
extern int i915_reset_engine(struct intel_engine_cs *engine,
const char *reason);
extern bool intel_has_reset_engine(struct drm_i915_private *dev_priv);
extern int intel_reset_guc(struct drm_i915_private *dev_priv);
extern int intel_guc_reset_engine(struct intel_guc *guc,
struct intel_engine_cs *engine);
extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
extern void intel_hangcheck_init(struct drm_i915_private *dev_priv);
extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
......@@ -2670,20 +2658,11 @@ static inline void i915_queue_hangcheck(struct drm_i915_private *dev_priv)
&dev_priv->gpu_error.hangcheck_work, delay);
}
__printf(4, 5)
void i915_handle_error(struct drm_i915_private *dev_priv,
u32 engine_mask,
unsigned long flags,
const char *fmt, ...);
#define I915_ERROR_CAPTURE BIT(0)
extern void intel_irq_init(struct drm_i915_private *dev_priv);
extern void intel_irq_fini(struct drm_i915_private *dev_priv);
int intel_irq_install(struct drm_i915_private *dev_priv);
void intel_irq_uninstall(struct drm_i915_private *dev_priv);
void i915_clear_error_registers(struct drm_i915_private *dev_priv);
static inline bool intel_gvt_active(struct drm_i915_private *dev_priv)
{
return dev_priv->gvt;
......@@ -3048,18 +3027,8 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
return READ_ONCE(error->reset_engine_count[engine->id]);
}
struct i915_request *
i915_gem_reset_prepare_engine(struct intel_engine_cs *engine);
int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);
void i915_gem_reset(struct drm_i915_private *dev_priv,
unsigned int stalled_mask);
void i915_gem_reset_finish_engine(struct intel_engine_cs *engine);
void i915_gem_reset_finish(struct drm_i915_private *dev_priv);
void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
bool i915_gem_unset_wedged(struct drm_i915_private *dev_priv);
void i915_gem_reset_engine(struct intel_engine_cs *engine,
struct i915_request *request,
bool stalled);
void i915_gem_init_mmio(struct drm_i915_private *i915);
int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
......
drivers/gpu/drm/i915/i915_gem.c
浏览文件 @ 9f58892e
......@@ -27,15 +27,6 @@
#include <drm/drm_vma_manager.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "i915_vgpu.h"
#include "i915_trace.h"
#include "intel_drv.h"
#include "intel_frontbuffer.h"
#include "intel_mocs.h"
#include "intel_workarounds.h"
#include "i915_gemfs.h"
#include <linux/dma-fence-array.h>
#include <linux/kthread.h>
#include <linux/reservation.h>
......@@ -46,6 +37,18 @@
#include <linux/pci.h>
#include <linux/dma-buf.h>
#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "i915_gemfs.h"
#include "i915_reset.h"
#include "i915_trace.h"
#include "i915_vgpu.h"
#include "intel_drv.h"
#include "intel_frontbuffer.h"
#include "intel_mocs.h"
#include "intel_workarounds.h"
static void i915_gem_flush_free_objects(struct drm_i915_private *i915);
static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
......@@ -2873,61 +2876,6 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
return 0;
}
static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
const struct i915_gem_context *ctx)
{
unsigned int score;
unsigned long prev_hang;
if (i915_gem_context_is_banned(ctx))
score = I915_CLIENT_SCORE_CONTEXT_BAN;
else
score = 0;
prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
score += I915_CLIENT_SCORE_HANG_FAST;
if (score) {
atomic_add(score, &file_priv->ban_score);
DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
ctx->name, score,
atomic_read(&file_priv->ban_score));
}
}
static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
{
unsigned int score;
bool banned, bannable;
atomic_inc(&ctx->guilty_count);
bannable = i915_gem_context_is_bannable(ctx);
score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
/* Cool contexts don't accumulate client ban score */
if (!bannable)
return;
if (banned) {
DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, banned\n",
ctx->name, atomic_read(&ctx->guilty_count),
score);
i915_gem_context_set_banned(ctx);
}
if (!IS_ERR_OR_NULL(ctx->file_priv))
i915_gem_client_mark_guilty(ctx->file_priv, ctx);
}
static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
{
atomic_inc(&ctx->active_count);
}
struct i915_request *
i915_gem_find_active_request(struct intel_engine_cs *engine)
{
......@@ -2958,376 +2906,6 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
return active;
}
/*
* Ensure irq handler finishes, and not run again.
* Also return the active request so that we only search for it once.
*/
struct i915_request *
i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
{
struct i915_request *request;
/*
* During the reset sequence, we must prevent the engine from
* entering RC6. As the context state is undefined until we restart
* the engine, if it does enter RC6 during the reset, the state
* written to the powercontext is undefined and so we may lose
* GPU state upon resume, i.e. fail to restart after a reset.
*/
intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
request = engine->reset.prepare(engine);
if (request && request->fence.error == -EIO)
request = ERR_PTR(-EIO); /* Previous reset failed! */
return request;
}
int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
struct i915_request *request;
enum intel_engine_id id;
int err = 0;
for_each_engine(engine, dev_priv, id) {
request = i915_gem_reset_prepare_engine(engine);
if (IS_ERR(request)) {
err = PTR_ERR(request);
continue;
}
engine->hangcheck.active_request = request;
}
i915_gem_revoke_fences(dev_priv);
intel_uc_sanitize(dev_priv);
return err;
}
static void engine_skip_context(struct i915_request *request)
{
struct intel_engine_cs *engine = request->engine;
struct i915_gem_context *hung_ctx = request->gem_context;
struct i915_timeline *timeline = request->timeline;
unsigned long flags;
GEM_BUG_ON(timeline == &engine->timeline);
spin_lock_irqsave(&engine->timeline.lock, flags);
spin_lock(&timeline->lock);
list_for_each_entry_continue(request, &engine->timeline.requests, link)
if (request->gem_context == hung_ctx)
i915_request_skip(request, -EIO);
list_for_each_entry(request, &timeline->requests, link)
i915_request_skip(request, -EIO);
spin_unlock(&timeline->lock);
spin_unlock_irqrestore(&engine->timeline.lock, flags);
}
/* Returns the request if it was guilty of the hang */
static struct i915_request *
i915_gem_reset_request(struct intel_engine_cs *engine,
struct i915_request *request,
bool stalled)
{
/* The guilty request will get skipped on a hung engine.
*
* Users of client default contexts do not rely on logical
* state preserved between batches so it is safe to execute
* queued requests following the hang. Non default contexts
* rely on preserved state, so skipping a batch loses the
* evolution of the state and it needs to be considered corrupted.
* Executing more queued batches on top of corrupted state is
* risky. But we take the risk by trying to advance through
* the queued requests in order to make the client behaviour
* more predictable around resets, by not throwing away random
* amount of batches it has prepared for execution. Sophisticated
* clients can use gem_reset_stats_ioctl and dma fence status
* (exported via sync_file info ioctl on explicit fences) to observe
* when it loses the context state and should rebuild accordingly.
*
* The context ban, and ultimately the client ban, mechanism are safety
* valves if client submission ends up resulting in nothing more than
* subsequent hangs.
*/
if (i915_request_completed(request)) {
GEM_TRACE("%s pardoned global=%d (fence %llx:%d), current %d\n",
engine->name, request->global_seqno,
request->fence.context, request->fence.seqno,
intel_engine_get_seqno(engine));
stalled = false;
}
if (stalled) {
i915_gem_context_mark_guilty(request->gem_context);
i915_request_skip(request, -EIO);
/* If this context is now banned, skip all pending requests. */
if (i915_gem_context_is_banned(request->gem_context))
engine_skip_context(request);
} else {
/*
* Since this is not the hung engine, it may have advanced
* since the hang declaration. Double check by refinding
* the active request at the time of the reset.
*/
request = i915_gem_find_active_request(engine);
if (request) {
unsigned long flags;
i915_gem_context_mark_innocent(request->gem_context);
dma_fence_set_error(&request->fence, -EAGAIN);
/* Rewind the engine to replay the incomplete rq */
spin_lock_irqsave(&engine->timeline.lock, flags);
request = list_prev_entry(request, link);
if (&request->link == &engine->timeline.requests)
request = NULL;
spin_unlock_irqrestore(&engine->timeline.lock, flags);
}
}
return request;
}
void i915_gem_reset_engine(struct intel_engine_cs *engine,
struct i915_request *request,
bool stalled)
{
if (request)
request = i915_gem_reset_request(engine, request, stalled);
/* Setup the CS to resume from the breadcrumb of the hung request */
engine->reset.reset(engine, request);
}
void i915_gem_reset(struct drm_i915_private *dev_priv,
unsigned int stalled_mask)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
lockdep_assert_held(&dev_priv->drm.struct_mutex);
i915_retire_requests(dev_priv);
for_each_engine(engine, dev_priv, id) {
struct intel_context *ce;
i915_gem_reset_engine(engine,
engine->hangcheck.active_request,
stalled_mask & ENGINE_MASK(id));
ce = fetch_and_zero(&engine->last_retired_context);
if (ce)
intel_context_unpin(ce);
/*
* Ostensibily, we always want a context loaded for powersaving,
* so if the engine is idle after the reset, send a request
* to load our scratch kernel_context.
*
* More mysteriously, if we leave the engine idle after a reset,
* the next userspace batch may hang, with what appears to be
* an incoherent read by the CS (presumably stale TLB). An
* empty request appears sufficient to paper over the glitch.
*/
if (intel_engine_is_idle(engine)) {
struct i915_request *rq;
rq = i915_request_alloc(engine,
dev_priv->kernel_context);
if (!IS_ERR(rq))
i915_request_add(rq);
}
}
i915_gem_restore_fences(dev_priv);
}
void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
{
engine->reset.finish(engine);
intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
}
void i915_gem_reset_finish(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
lockdep_assert_held(&dev_priv->drm.struct_mutex);
for_each_engine(engine, dev_priv, id) {
engine->hangcheck.active_request = NULL;
i915_gem_reset_finish_engine(engine);
}
}
static void nop_submit_request(struct i915_request *request)
{
unsigned long flags;
GEM_TRACE("%s fence %llx:%d -> -EIO\n",
request->engine->name,
request->fence.context, request->fence.seqno);
dma_fence_set_error(&request->fence, -EIO);
spin_lock_irqsave(&request->engine->timeline.lock, flags);
__i915_request_submit(request);
intel_engine_write_global_seqno(request->engine, request->global_seqno);
spin_unlock_irqrestore(&request->engine->timeline.lock, flags);
}
void i915_gem_set_wedged(struct drm_i915_private *i915)
{
struct i915_gpu_error *error = &i915->gpu_error;
struct intel_engine_cs *engine;
enum intel_engine_id id;
mutex_lock(&error->wedge_mutex);
if (test_bit(I915_WEDGED, &error->flags)) {
mutex_unlock(&error->wedge_mutex);
return;
}
if (GEM_SHOW_DEBUG() && !intel_engines_are_idle(i915)) {
struct drm_printer p = drm_debug_printer(__func__);
for_each_engine(engine, i915, id)
intel_engine_dump(engine, &p, "%s\n", engine->name);
}
GEM_TRACE("start\n");
/*
* First, stop submission to hw, but do not yet complete requests by
* rolling the global seqno forward (since this would complete requests
* for which we haven't set the fence error to EIO yet).
*/
for_each_engine(engine, i915, id)
i915_gem_reset_prepare_engine(engine);
/* Even if the GPU reset fails, it should still stop the engines */
if (INTEL_GEN(i915) >= 5)
intel_gpu_reset(i915, ALL_ENGINES);
for_each_engine(engine, i915, id) {
engine->submit_request = nop_submit_request;
engine->schedule = NULL;
}
i915->caps.scheduler = 0;
/*
* Make sure no request can slip through without getting completed by
* either this call here to intel_engine_write_global_seqno, or the one
* in nop_submit_request.
*/
synchronize_rcu();
/* Mark all executing requests as skipped */
for_each_engine(engine, i915, id)
engine->cancel_requests(engine);
for_each_engine(engine, i915, id) {
i915_gem_reset_finish_engine(engine);
intel_engine_wakeup(engine);
}
smp_mb__before_atomic();
set_bit(I915_WEDGED, &error->flags);
GEM_TRACE("end\n");
mutex_unlock(&error->wedge_mutex);
wake_up_all(&error->reset_queue);
}
bool i915_gem_unset_wedged(struct drm_i915_private *i915)
{
struct i915_gpu_error *error = &i915->gpu_error;
struct i915_timeline *tl;
bool ret = false;
lockdep_assert_held(&i915->drm.struct_mutex);
if (!test_bit(I915_WEDGED, &error->flags))
return true;
if (!i915->gt.scratch) /* Never full initialised, recovery impossible */
return false;
mutex_lock(&error->wedge_mutex);
GEM_TRACE("start\n");
/*
* Before unwedging, make sure that all pending operations
* are flushed and errored out - we may have requests waiting upon
* third party fences. We marked all inflight requests as EIO, and
* every execbuf since returned EIO, for consistency we want all
* the currently pending requests to also be marked as EIO, which
* is done inside our nop_submit_request - and so we must wait.
*
* No more can be submitted until we reset the wedged bit.
*/
list_for_each_entry(tl, &i915->gt.timelines, link) {
struct i915_request *rq;
rq = i915_gem_active_peek(&tl->last_request,
&i915->drm.struct_mutex);
if (!rq)
continue;
/*
* We can't use our normal waiter as we want to
* avoid recursively trying to handle the current
* reset. The basic dma_fence_default_wait() installs
* a callback for dma_fence_signal(), which is
* triggered by our nop handler (indirectly, the
* callback enables the signaler thread which is
* woken by the nop_submit_request() advancing the seqno
* and when the seqno passes the fence, the signaler
* then signals the fence waking us up).
*/
if (dma_fence_default_wait(&rq->fence, true,
MAX_SCHEDULE_TIMEOUT) < 0)
goto unlock;
}
i915_retire_requests(i915);
GEM_BUG_ON(i915->gt.active_requests);
intel_engines_sanitize(i915, false);
/*
* Undo nop_submit_request. We prevent all new i915 requests from
* being queued (by disallowing execbuf whilst wedged) so having
* waited for all active requests above, we know the system is idle
* and do not have to worry about a thread being inside
* engine->submit_request() as we swap over. So unlike installing
* the nop_submit_request on reset, we can do this from normal
* context and do not require stop_machine().
*/
intel_engines_reset_default_submission(i915);
i915_gem_contexts_lost(i915);
GEM_TRACE("end\n");
smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
clear_bit(I915_WEDGED, &i915->gpu_error.flags);
ret = true;
unlock:
mutex_unlock(&i915->gpu_error.wedge_mutex);
return ret;
}
static void
i915_gem_retire_work_handler(struct work_struct *work)
{
......
drivers/gpu/drm/i915/i915_gem_gtt.c
浏览文件 @ 9f58892e
......@@ -37,6 +37,7 @@
#include "i915_drv.h"
#include "i915_vgpu.h"
#include "i915_reset.h"
#include "i915_trace.h"
#include "intel_drv.h"
#include "intel_frontbuffer.h"
......
drivers/gpu/drm/i915/i915_irq.c
浏览文件 @ 9f58892e
......@@ -2930,46 +2930,6 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
return IRQ_HANDLED;
}
struct wedge_me {
struct delayed_work work;
struct drm_i915_private *i915;
const char *name;
};
static void wedge_me(struct work_struct *work)
{
struct wedge_me *w = container_of(work, typeof(*w), work.work);
dev_err(w->i915->drm.dev,
"%s timed out, cancelling all in-flight rendering.\n",
w->name);
i915_gem_set_wedged(w->i915);
}
static void __init_wedge(struct wedge_me *w,
struct drm_i915_private *i915,
long timeout,
const char *name)
{
w->i915 = i915;
w->name = name;
INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
schedule_delayed_work(&w->work, timeout);
}
static void __fini_wedge(struct wedge_me *w)
{
cancel_delayed_work_sync(&w->work);
destroy_delayed_work_on_stack(&w->work);
w->i915 = NULL;
}
#define i915_wedge_on_timeout(W, DEV, TIMEOUT) \
for (__init_wedge((W), (DEV), (TIMEOUT), __func__); \
(W)->i915; \
__fini_wedge((W)))
static u32
gen11_gt_engine_identity(struct drm_i915_private * const i915,
const unsigned int bank, const unsigned int bit)
......@@ -3180,204 +3140,6 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
return IRQ_HANDLED;
}
static void i915_reset_device(struct drm_i915_private *dev_priv,
u32 engine_mask,
const char *reason)
{
struct i915_gpu_error *error = &dev_priv->gpu_error;
struct kobject *kobj = &dev_priv->drm.primary->kdev->kobj;
char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
char *reset_event[] = { I915_RESET_UEVENT "=1", NULL };
char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL };
struct wedge_me w;
kobject_uevent_env(kobj, KOBJ_CHANGE, error_event);
DRM_DEBUG_DRIVER("resetting chip\n");
kobject_uevent_env(kobj, KOBJ_CHANGE, reset_event);
/* Use a watchdog to ensure that our reset completes */
i915_wedge_on_timeout(&w, dev_priv, 5*HZ) {
intel_prepare_reset(dev_priv);
error->reason = reason;
error->stalled_mask = engine_mask;
/* Signal that locked waiters should reset the GPU */
smp_mb__before_atomic();
set_bit(I915_RESET_HANDOFF, &error->flags);
wake_up_all(&error->wait_queue);
/* Wait for anyone holding the lock to wakeup, without
* blocking indefinitely on struct_mutex.
*/
do {
if (mutex_trylock(&dev_priv->drm.struct_mutex)) {
i915_reset(dev_priv, engine_mask, reason);
mutex_unlock(&dev_priv->drm.struct_mutex);
}
} while (wait_on_bit_timeout(&error->flags,
I915_RESET_HANDOFF,
TASK_UNINTERRUPTIBLE,
1));
error->stalled_mask = 0;
error->reason = NULL;
intel_finish_reset(dev_priv);
}
if (!test_bit(I915_WEDGED, &error->flags))
kobject_uevent_env(kobj, KOBJ_CHANGE, reset_done_event);
}
void i915_clear_error_registers(struct drm_i915_private *dev_priv)
{
u32 eir;
if (!IS_GEN(dev_priv, 2))
I915_WRITE(PGTBL_ER, I915_READ(PGTBL_ER));
if (INTEL_GEN(dev_priv) < 4)
I915_WRITE(IPEIR, I915_READ(IPEIR));
else
I915_WRITE(IPEIR_I965, I915_READ(IPEIR_I965));
I915_WRITE(EIR, I915_READ(EIR));
eir = I915_READ(EIR);
if (eir) {
/*
* some errors might have become stuck,
* mask them.
*/
DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir);
I915_WRITE(EMR, I915_READ(EMR) | eir);
I915_WRITE(IIR, I915_MASTER_ERROR_INTERRUPT);
}
if (INTEL_GEN(dev_priv) >= 8) {
I915_WRITE(GEN8_RING_FAULT_REG,
I915_READ(GEN8_RING_FAULT_REG) & ~RING_FAULT_VALID);
POSTING_READ(GEN8_RING_FAULT_REG);
} else if (INTEL_GEN(dev_priv) >= 6) {
struct intel_engine_cs *engine;
enum intel_engine_id id;
for_each_engine(engine, dev_priv, id) {
I915_WRITE(RING_FAULT_REG(engine),
I915_READ(RING_FAULT_REG(engine)) &
~RING_FAULT_VALID);
}
POSTING_READ(RING_FAULT_REG(dev_priv->engine[RCS]));
}
}
/**
* i915_handle_error - handle a gpu error
* @dev_priv: i915 device private
* @engine_mask: mask representing engines that are hung
* @flags: control flags
* @fmt: Error message format string
*
* Do some basic checking of register state at error time and
* dump it to the syslog. Also call i915_capture_error_state() to make
* sure we get a record and make it available in debugfs. Fire a uevent
* so userspace knows something bad happened (should trigger collection
* of a ring dump etc.).
*/
void i915_handle_error(struct drm_i915_private *dev_priv,
u32 engine_mask,
unsigned long flags,
const char *fmt, ...)
{
struct intel_engine_cs *engine;
intel_wakeref_t wakeref;
unsigned int tmp;
char error_msg[80];
char *msg = NULL;
if (fmt) {
va_list args;
va_start(args, fmt);
vscnprintf(error_msg, sizeof(error_msg), fmt, args);
va_end(args);
msg = error_msg;
}
/*
* In most cases it's guaranteed that we get here with an RPM
* reference held, for example because there is a pending GPU
* request that won't finish until the reset is done. This
* isn't the case at least when we get here by doing a
* simulated reset via debugfs, so get an RPM reference.
*/
wakeref = intel_runtime_pm_get(dev_priv);
engine_mask &= INTEL_INFO(dev_priv)->ring_mask;
if (flags & I915_ERROR_CAPTURE) {
i915_capture_error_state(dev_priv, engine_mask, msg);
i915_clear_error_registers(dev_priv);
}
/*
* Try engine reset when available. We fall back to full reset if
* single reset fails.
*/
if (intel_has_reset_engine(dev_priv) &&
!i915_terminally_wedged(&dev_priv->gpu_error)) {
for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
&dev_priv->gpu_error.flags))
continue;
if (i915_reset_engine(engine, msg) == 0)
engine_mask &= ~intel_engine_flag(engine);
clear_bit(I915_RESET_ENGINE + engine->id,
&dev_priv->gpu_error.flags);
wake_up_bit(&dev_priv->gpu_error.flags,
I915_RESET_ENGINE + engine->id);
}
}
if (!engine_mask)
goto out;
/* Full reset needs the mutex, stop any other user trying to do so. */
if (test_and_set_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags)) {
wait_event(dev_priv->gpu_error.reset_queue,
!test_bit(I915_RESET_BACKOFF,
&dev_priv->gpu_error.flags));
goto out;
}
/* Prevent any other reset-engine attempt. */
for_each_engine(engine, dev_priv, tmp) {
while (test_and_set_bit(I915_RESET_ENGINE + engine->id,
&dev_priv->gpu_error.flags))
wait_on_bit(&dev_priv->gpu_error.flags,
I915_RESET_ENGINE + engine->id,
TASK_UNINTERRUPTIBLE);
}
i915_reset_device(dev_priv, engine_mask, msg);
for_each_engine(engine, dev_priv, tmp) {
clear_bit(I915_RESET_ENGINE + engine->id,
&dev_priv->gpu_error.flags);
}
clear_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags);
wake_up_all(&dev_priv->gpu_error.reset_queue);
out:
intel_runtime_pm_put(dev_priv, wakeref);
}
/* Called from drm generic code, passed 'crtc' which
* we use as a pipe index
*/
......
drivers/gpu/drm/i915/i915_request.c
浏览文件 @ 9f58892e
......@@ -29,6 +29,7 @@
#include <linux/sched/signal.h>
#include "i915_drv.h"
#include "i915_reset.h"
static const char *i915_fence_get_driver_name(struct dma_fence *fence)
{
......
drivers/gpu/drm/i915/i915_reset.c 0 → 100644
浏览文件 @ 9f58892e
此差异已折叠。
drivers/gpu/drm/i915/i915_reset.h 0 → 100644
浏览文件 @ 9f58892e
/*
* 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>
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);
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 */
drivers/gpu/drm/i915/intel_display.c
浏览文件 @ 9f58892e
......@@ -31,13 +31,7 @@
#include <linux/slab.h>
#include <linux/vgaarb.h>
#include <drm/drm_edid.h>
#include "intel_drv.h"
#include "intel_frontbuffer.h"
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "intel_dsi.h"
#include "i915_trace.h"
#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_dp_helper.h>
......@@ -48,6 +42,15 @@
#include <linux/intel-iommu.h>
#include <linux/reservation.h>
#include "intel_drv.h"
#include "intel_dsi.h"
#include "intel_frontbuffer.h"
#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "i915_reset.h"
#include "i915_trace.h"
/* Primary plane formats for gen <= 3 */
static const uint32_t i8xx_primary_formats[] = {
DRM_FORMAT_C8,
......
drivers/gpu/drm/i915/intel_engine_cs.c
浏览文件 @ 9f58892e
......@@ -25,6 +25,7 @@
#include <drm/drm_print.h>
#include "i915_drv.h"
#include "i915_reset.h"
#include "intel_ringbuffer.h"
#include "intel_lrc.h"
......
drivers/gpu/drm/i915/intel_guc.h
浏览文件 @ 9f58892e
......@@ -192,4 +192,7 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask)
spin_unlock_irq(&guc->irq_lock);
}
int intel_guc_reset_engine(struct intel_guc *guc,
struct intel_engine_cs *engine);
#endif
drivers/gpu/drm/i915/intel_hangcheck.c
浏览文件 @ 9f58892e
......@@ -23,6 +23,7 @@
*/
#include "i915_drv.h"
#include "i915_reset.h"
static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone)
{
......
drivers/gpu/drm/i915/intel_uc.c
浏览文件 @ 9f58892e
......@@ -26,6 +26,7 @@
#include "intel_guc_submission.h"
#include "intel_guc.h"
#include "i915_drv.h"
#include "i915_reset.h"
static void guc_free_load_err_log(struct intel_guc *guc);
......
drivers/gpu/drm/i915/intel_uncore.c
浏览文件 @ 9f58892e
......@@ -1715,372 +1715,6 @@ int i915_reg_read_ioctl(struct drm_device *dev,
return ret;
}
static void gen3_stop_engine(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
const u32 base = engine->mmio_base;
if (intel_engine_stop_cs(engine))
DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", engine->name);
I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
POSTING_READ_FW(RING_HEAD(base)); /* paranoia */
I915_WRITE_FW(RING_HEAD(base), 0);
I915_WRITE_FW(RING_TAIL(base), 0);
POSTING_READ_FW(RING_TAIL(base));
/* The ring must be empty before it is disabled */
I915_WRITE_FW(RING_CTL(base), 0);
/* Check acts as a post */
if (I915_READ_FW(RING_HEAD(base)) != 0)
DRM_DEBUG_DRIVER("%s: ring head not parked\n",
engine->name);
}
static void i915_stop_engines(struct drm_i915_private *dev_priv,
unsigned int engine_mask)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
if (INTEL_GEN(dev_priv) < 3)
return;
for_each_engine_masked(engine, dev_priv, engine_mask, id)
gen3_stop_engine(engine);
}
static bool i915_in_reset(struct pci_dev *pdev)
{
u8 gdrst;
pci_read_config_byte(pdev, I915_GDRST, &gdrst);
return gdrst & GRDOM_RESET_STATUS;
}
static int i915_do_reset(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
struct pci_dev *pdev = dev_priv->drm.pdev;
int err;
/* Assert reset for at least 20 usec, and wait for acknowledgement. */
pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
usleep_range(50, 200);
err = wait_for(i915_in_reset(pdev), 500);
/* Clear the reset request. */
pci_write_config_byte(pdev, I915_GDRST, 0);
usleep_range(50, 200);
if (!err)
err = wait_for(!i915_in_reset(pdev), 500);
return err;
}
static bool g4x_reset_complete(struct pci_dev *pdev)
{
u8 gdrst;
pci_read_config_byte(pdev, I915_GDRST, &gdrst);
return (gdrst & GRDOM_RESET_ENABLE) == 0;
}
static int g33_do_reset(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
struct pci_dev *pdev = dev_priv->drm.pdev;
pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
return wait_for(g4x_reset_complete(pdev), 500);
}
static int g4x_do_reset(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
struct pci_dev *pdev = dev_priv->drm.pdev;
int ret;
/* WaVcpClkGateDisableForMediaReset:ctg,elk */
I915_WRITE(VDECCLK_GATE_D,
I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE);
POSTING_READ(VDECCLK_GATE_D);
pci_write_config_byte(pdev, I915_GDRST,
GRDOM_MEDIA | GRDOM_RESET_ENABLE);
ret = wait_for(g4x_reset_complete(pdev), 500);
if (ret) {
DRM_DEBUG_DRIVER("Wait for media reset failed\n");
goto out;
}
pci_write_config_byte(pdev, I915_GDRST,
GRDOM_RENDER | GRDOM_RESET_ENABLE);
ret = wait_for(g4x_reset_complete(pdev), 500);
if (ret) {
DRM_DEBUG_DRIVER("Wait for render reset failed\n");
goto out;
}
out:
pci_write_config_byte(pdev, I915_GDRST, 0);
I915_WRITE(VDECCLK_GATE_D,
I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE);
POSTING_READ(VDECCLK_GATE_D);
return ret;
}
static int ironlake_do_reset(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
int ret;
I915_WRITE(ILK_GDSR, ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE);
ret = intel_wait_for_register(dev_priv,
ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
500);
if (ret) {
DRM_DEBUG_DRIVER("Wait for render reset failed\n");
goto out;
}
I915_WRITE(ILK_GDSR, ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE);
ret = intel_wait_for_register(dev_priv,
ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
500);
if (ret) {
DRM_DEBUG_DRIVER("Wait for media reset failed\n");
goto out;
}
out:
I915_WRITE(ILK_GDSR, 0);
POSTING_READ(ILK_GDSR);
return ret;
}
/* Reset the hardware domains (GENX_GRDOM_*) specified by mask */
static int gen6_hw_domain_reset(struct drm_i915_private *dev_priv,
u32 hw_domain_mask)
{
int err;
/* GEN6_GDRST is not in the gt power well, no need to check
* for fifo space for the write or forcewake the chip for
* the read
*/
__raw_i915_write32(dev_priv, GEN6_GDRST, hw_domain_mask);
/* Wait for the device to ack the reset requests */
err = __intel_wait_for_register_fw(dev_priv,
GEN6_GDRST, hw_domain_mask, 0,
500, 0,
NULL);
if (err)
DRM_DEBUG_DRIVER("Wait for 0x%08x engines reset failed\n",
hw_domain_mask);
return err;
}
/**
* gen6_reset_engines - reset individual engines
* @dev_priv: i915 device
* @engine_mask: mask of intel_ring_flag() engines or ALL_ENGINES for full reset
* @retry: the count of of previous attempts to reset.
*
* This function will reset the individual engines that are set in engine_mask.
* If you provide ALL_ENGINES as mask, full global domain reset will be issued.
*
* Note: It is responsibility of the caller to handle the difference between
* asking full domain reset versus reset for all available individual engines.
*
* Returns 0 on success, nonzero on error.
*/
static int gen6_reset_engines(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
struct intel_engine_cs *engine;
const u32 hw_engine_mask[I915_NUM_ENGINES] = {
[RCS] = GEN6_GRDOM_RENDER,
[BCS] = GEN6_GRDOM_BLT,
[VCS] = GEN6_GRDOM_MEDIA,
[VCS2] = GEN8_GRDOM_MEDIA2,
[VECS] = GEN6_GRDOM_VECS,
};
u32 hw_mask;
if (engine_mask == ALL_ENGINES) {
hw_mask = GEN6_GRDOM_FULL;
} else {
unsigned int tmp;
hw_mask = 0;
for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
hw_mask |= hw_engine_mask[engine->id];
}
return gen6_hw_domain_reset(dev_priv, hw_mask);
}
static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
struct intel_engine_cs *engine)
{
u8 vdbox_sfc_access = RUNTIME_INFO(dev_priv)->vdbox_sfc_access;
i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
i915_reg_t sfc_usage;
u32 sfc_usage_bit;
u32 sfc_reset_bit;
switch (engine->class) {
case VIDEO_DECODE_CLASS:
if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
return 0;
sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
sfc_forced_lock_ack_bit = GEN11_VCS_SFC_LOCK_ACK_BIT;
sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
break;
case VIDEO_ENHANCEMENT_CLASS:
sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
sfc_forced_lock_ack_bit = GEN11_VECS_SFC_LOCK_ACK_BIT;
sfc_usage = GEN11_VECS_SFC_USAGE(engine);
sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
break;
default:
return 0;
}
/*
* Tell the engine that a software reset is going to happen. The engine
* will then try to force lock the SFC (if currently locked, it will
* remain so until we tell the engine it is safe to unlock; if currently
* unlocked, it will ignore this and all new lock requests). If SFC
* ends up being locked to the engine we want to reset, we have to reset
* it as well (we will unlock it once the reset sequence is completed).
*/
I915_WRITE_FW(sfc_forced_lock,
I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
if (__intel_wait_for_register_fw(dev_priv,
sfc_forced_lock_ack,
sfc_forced_lock_ack_bit,
sfc_forced_lock_ack_bit,
1000, 0, NULL)) {
DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
return 0;
}
if (I915_READ_FW(sfc_usage) & sfc_usage_bit)
return sfc_reset_bit;
return 0;
}
static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
struct intel_engine_cs *engine)
{
u8 vdbox_sfc_access = RUNTIME_INFO(dev_priv)->vdbox_sfc_access;
i915_reg_t sfc_forced_lock;
u32 sfc_forced_lock_bit;
switch (engine->class) {
case VIDEO_DECODE_CLASS:
if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
return;
sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
break;
case VIDEO_ENHANCEMENT_CLASS:
sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
break;
default:
return;
}
I915_WRITE_FW(sfc_forced_lock,
I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
}
/**
* gen11_reset_engines - reset individual engines
* @dev_priv: i915 device
* @engine_mask: mask of intel_ring_flag() engines or ALL_ENGINES for full reset
*
* This function will reset the individual engines that are set in engine_mask.
* If you provide ALL_ENGINES as mask, full global domain reset will be issued.
*
* Note: It is responsibility of the caller to handle the difference between
* asking full domain reset versus reset for all available individual engines.
*
* Returns 0 on success, nonzero on error.
*/
static int gen11_reset_engines(struct drm_i915_private *dev_priv,
unsigned int engine_mask)
{
const u32 hw_engine_mask[I915_NUM_ENGINES] = {
[RCS] = GEN11_GRDOM_RENDER,
[BCS] = GEN11_GRDOM_BLT,
[VCS] = GEN11_GRDOM_MEDIA,
[VCS2] = GEN11_GRDOM_MEDIA2,
[VCS3] = GEN11_GRDOM_MEDIA3,
[VCS4] = GEN11_GRDOM_MEDIA4,
[VECS] = GEN11_GRDOM_VECS,
[VECS2] = GEN11_GRDOM_VECS2,
};
struct intel_engine_cs *engine;
unsigned int tmp;
u32 hw_mask;
int ret;
BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
if (engine_mask == ALL_ENGINES) {
hw_mask = GEN11_GRDOM_FULL;
} else {
hw_mask = 0;
for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
hw_mask |= hw_engine_mask[engine->id];
hw_mask |= gen11_lock_sfc(dev_priv, engine);
}
}
ret = gen6_hw_domain_reset(dev_priv, hw_mask);
if (engine_mask != ALL_ENGINES)
for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
gen11_unlock_sfc(dev_priv, engine);
return ret;
}
/**
* __intel_wait_for_register_fw - wait until register matches expected state
* @dev_priv: the i915 device
......@@ -2191,196 +1825,6 @@ int __intel_wait_for_register(struct drm_i915_private *dev_priv,
return ret;
}
static int gen8_engine_reset_prepare(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
int ret;
I915_WRITE_FW(RING_RESET_CTL(engine->mmio_base),
_MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET));
ret = __intel_wait_for_register_fw(dev_priv,
RING_RESET_CTL(engine->mmio_base),
RESET_CTL_READY_TO_RESET,
RESET_CTL_READY_TO_RESET,
700, 0,
NULL);
if (ret)
DRM_ERROR("%s: reset request timeout\n", engine->name);
return ret;
}
static void gen8_engine_reset_cancel(struct intel_engine_cs *engine)
{
struct drm_i915_private *dev_priv = engine->i915;
I915_WRITE_FW(RING_RESET_CTL(engine->mmio_base),
_MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET));
}
static int reset_engines(struct drm_i915_private *i915,
unsigned int engine_mask,
unsigned int retry)
{
if (INTEL_GEN(i915) >= 11)
return gen11_reset_engines(i915, engine_mask);
else
return gen6_reset_engines(i915, engine_mask, retry);
}
static int gen8_reset_engines(struct drm_i915_private *dev_priv,
unsigned int engine_mask,
unsigned int retry)
{
struct intel_engine_cs *engine;
const bool reset_non_ready = retry >= 1;
unsigned int tmp;
int ret;
for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
ret = gen8_engine_reset_prepare(engine);
if (ret && !reset_non_ready)
goto skip_reset;
/*
* If this is not the first failed attempt to prepare,
* we decide to proceed anyway.
*
* By doing so we risk context corruption and with
* some gens (kbl), possible system hang if reset
* happens during active bb execution.
*
* We rather take context corruption instead of
* failed reset with a wedged driver/gpu. And
* active bb execution case should be covered by
* i915_stop_engines we have before the reset.
*/
}
ret = reset_engines(dev_priv, engine_mask, retry);
skip_reset:
for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
gen8_engine_reset_cancel(engine);
return ret;
}
typedef int (*reset_func)(struct drm_i915_private *,
unsigned int engine_mask, unsigned int retry);
static reset_func intel_get_gpu_reset(struct drm_i915_private *dev_priv)
{
if (!i915_modparams.reset)
return NULL;
if (INTEL_GEN(dev_priv) >= 8)
return gen8_reset_engines;
else if (INTEL_GEN(dev_priv) >= 6)
return gen6_reset_engines;
else if (IS_GEN(dev_priv, 5))
return ironlake_do_reset;
else if (IS_G4X(dev_priv))
return g4x_do_reset;
else if (IS_G33(dev_priv) || IS_PINEVIEW(dev_priv))
return g33_do_reset;
else if (INTEL_GEN(dev_priv) >= 3)
return i915_do_reset;
else
return NULL;
}
int intel_gpu_reset(struct drm_i915_private *dev_priv,
const unsigned int engine_mask)
{
reset_func reset = intel_get_gpu_reset(dev_priv);
unsigned int retry;
int ret;
GEM_BUG_ON(!engine_mask);
/*
* We want to perform per-engine reset from atomic context (e.g.
* softirq), which imposes the constraint that we cannot sleep.
* However, experience suggests that spending a bit of time waiting
* for a reset helps in various cases, so for a full-device reset
* we apply the opposite rule and wait if we want to. As we should
* always follow up a failed per-engine reset with a full device reset,
* being a little faster, stricter and more error prone for the
* atomic case seems an acceptable compromise.
*
* Unfortunately this leads to a bimodal routine, when the goal was
* to have a single reset function that worked for resetting any
* number of engines simultaneously.
*/
might_sleep_if(engine_mask == ALL_ENGINES);
/*
* If the power well sleeps during the reset, the reset
* request may be dropped and never completes (causing -EIO).
*/
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
for (retry = 0; retry < 3; retry++) {
/*
* We stop engines, otherwise we might get failed reset and a
* dead gpu (on elk). Also as modern gpu as kbl can suffer
* from system hang if batchbuffer is progressing when
* the reset is issued, regardless of READY_TO_RESET ack.
* Thus assume it is best to stop engines on all gens
* where we have a gpu reset.
*
* WaKBLVECSSemaphoreWaitPoll:kbl (on ALL_ENGINES)
*
* WaMediaResetMainRingCleanup:ctg,elk (presumably)
*
* FIXME: Wa for more modern gens needs to be validated
*/
i915_stop_engines(dev_priv, engine_mask);
ret = -ENODEV;
if (reset) {
ret = reset(dev_priv, engine_mask, retry);
GEM_TRACE("engine_mask=%x, ret=%d, retry=%d\n",
engine_mask, ret, retry);
}
if (ret != -ETIMEDOUT || engine_mask != ALL_ENGINES)
break;
cond_resched();
}
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
return ret;
}
bool intel_has_gpu_reset(struct drm_i915_private *dev_priv)
{
return intel_get_gpu_reset(dev_priv) != NULL;
}
bool intel_has_reset_engine(struct drm_i915_private *dev_priv)
{
return (INTEL_INFO(dev_priv)->has_reset_engine &&
i915_modparams.reset >= 2);
}
int intel_reset_guc(struct drm_i915_private *dev_priv)
{
u32 guc_domain = INTEL_GEN(dev_priv) >= 11 ? GEN11_GRDOM_GUC :
GEN9_GRDOM_GUC;
int ret;
GEM_BUG_ON(!HAS_GUC(dev_priv));
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
ret = gen6_hw_domain_reset(dev_priv, guc_domain);
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
return ret;
}
bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv)
{
return check_for_unclaimed_mmio(dev_priv);
......
drivers/gpu/drm/i915/selftests/intel_lrc.c
浏览文件 @ 9f58892e
......@@ -4,6 +4,8 @@
* Copyright © 2018 Intel Corporation
*/
#include "../i915_reset.h"
#include "../i915_selftest.h"
#include "igt_flush_test.h"
#include "igt_spinner.h"
......
drivers/gpu/drm/i915/selftests/intel_workarounds.c
浏览文件 @ 9f58892e
......@@ -5,6 +5,7 @@
*/
#include "../i915_selftest.h"
#include "../i915_reset.h"
#include "igt_flush_test.h"
#include "igt_reset.h"
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或