AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-02 02:46:43 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity

drm/i915: Add engine reset count to error state

Browse Source 
Driver maintains count of how many times a given engine is reset, useful to
capture this in error state also. It gives an idea of how engine is coping
up with the workloads it is executing before this error state.

A follow-up patch will provide this information in debugfs.

v2: s/engine_reset/reset_engine/ (Chris)
    Define count as unsigned int (Tvrtko)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170615201828.23144-7-michel.thierry@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620095751.13127-7-chris@chris-wilson.co.uk
This commit is contained in:
Michel Thierry 2017-06-20 10:57:48 +01:00 committed by Chris Wilson
parent a1ef70e144
commit 702c8f8e5d
3 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
drivers/gpu/drm/i915/i915_drv.c
View File

@ -1971,7 +1971,10 @@ int i915_reset_engine(struct intel_engine_cs *engine)
* process to program RING_MODE, HWSP and re-enable submission. * process to program RING_MODE, HWSP and re-enable submission.
*/ */
ret = engine->init_hw(engine); ret = engine->init_hw(engine);
if (ret)
goto out;
error->reset_engine_count[engine->id]++;
out: out:
return ret; return ret;
} }

10
drivers/gpu/drm/i915/i915_drv.h
View File

@ -917,6 +917,7 @@ struct i915_gpu_state {
enum intel_engine_hangcheck_action hangcheck_action; enum intel_engine_hangcheck_action hangcheck_action;
struct i915_address_space *vm; struct i915_address_space *vm;
int num_requests; int num_requests;
u32 reset_count;
/* position of active request inside the ring */ /* position of active request inside the ring */
u32 rq_head, rq_post, rq_tail; u32 rq_head, rq_post, rq_tail;
@ -1567,6 +1568,9 @@ struct i915_gpu_error {
#define I915_WEDGED (BITS_PER_LONG - 1) #define I915_WEDGED (BITS_PER_LONG - 1)
#define I915_RESET_ENGINE (I915_WEDGED - I915_NUM_ENGINES) #define I915_RESET_ENGINE (I915_WEDGED - I915_NUM_ENGINES)
/** Number of times an engine has been reset */
u32 reset_engine_count[I915_NUM_ENGINES];
/** /**
* Waitqueue to signal when a hang is detected. Used to for waiters * Waitqueue to signal when a hang is detected. Used to for waiters
* to release the struct_mutex for the reset to procede. * to release the struct_mutex for the reset to procede.
@ -3474,6 +3478,12 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
return READ_ONCE(error->reset_count); return READ_ONCE(error->reset_count);
} }
static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
struct intel_engine_cs *engine)
{
return READ_ONCE(error->reset_engine_count[engine->id]);
}
struct drm_i915_gem_request * struct drm_i915_gem_request *
i915_gem_reset_prepare_engine(struct intel_engine_cs *engine); i915_gem_reset_prepare_engine(struct intel_engine_cs *engine);
int i915_gem_reset_prepare(struct drm_i915_private *dev_priv); int i915_gem_reset_prepare(struct drm_i915_private *dev_priv);

3
drivers/gpu/drm/i915/i915_gpu_error.c
View File

@ -463,6 +463,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
err_printf(m, " hangcheck action timestamp: %lu, %u ms ago\n", err_printf(m, " hangcheck action timestamp: %lu, %u ms ago\n",
ee->hangcheck_timestamp, ee->hangcheck_timestamp,
jiffies_to_msecs(jiffies - ee->hangcheck_timestamp)); jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
err_printf(m, " engine reset count: %u\n", ee->reset_count);
error_print_request(m, " ELSP[0]: ", &ee->execlist[0]); error_print_request(m, " ELSP[0]: ", &ee->execlist[0]);
error_print_request(m, " ELSP[1]: ", &ee->execlist[1]); error_print_request(m, " ELSP[1]: ", &ee->execlist[1]);
@ -1236,6 +1237,8 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
ee->hangcheck_timestamp = engine->hangcheck.action_timestamp; ee->hangcheck_timestamp = engine->hangcheck.action_timestamp;
ee->hangcheck_action = engine->hangcheck.action; ee->hangcheck_action = engine->hangcheck.action;
ee->hangcheck_stalled = engine->hangcheck.stalled; ee->hangcheck_stalled = engine->hangcheck.stalled;
ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error,
engine);
if (USES_PPGTT(dev_priv)) { if (USES_PPGTT(dev_priv)) {
int i; int i;