* [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno
@ 2019-02-26 9:49 Chris Wilson
2019-02-26 9:49 ` [CI 2/4] drm/i915: Remove access to global seqno in the HWSP Chris Wilson
` (3 more replies)
0 siblings, 4 replies; 5+ messages in thread
From: Chris Wilson @ 2019-02-26 9:49 UTC (permalink / raw)
To: intel-gfx
To determine whether an engine has 'stuck', we simply check whether or
not is still on the same seqno for several seconds. To keep this simple
mechanism intact over the loss of a global seqno, we can simply add a
new global heartbeat seqno instead. As we cannot know the sequence in
which requests will then be completed, we use a primitive random number
generator instead (with a cycle long enough to not matter over an
interval of a few thousand requests between hangcheck samples).
The alternative to using a dedicated seqno on every request is to issue
a heartbeat request and query its progress through the system. Sadly
this requires us to reduce struct_mutex so that we can issue requests
without requiring that bkl.
v2: And without the extra CS_STALL for the hangcheck seqno -- we don't
need strict serialisation with what comes later, we just need to be sure
we don't write the hangcheck seqno before our batch is flushed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/i915_debugfs.c | 7 ++---
drivers/gpu/drm/i915/intel_engine_cs.c | 5 ++--
drivers/gpu/drm/i915/intel_hangcheck.c | 6 ++---
drivers/gpu/drm/i915/intel_lrc.c | 15 +++++++++++
drivers/gpu/drm/i915/intel_ringbuffer.c | 36 +++++++++++++++++++++++--
drivers/gpu/drm/i915/intel_ringbuffer.h | 19 ++++++++++++-
6 files changed, 77 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 37175414ce89..545091a5180b 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1295,7 +1295,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
with_intel_runtime_pm(dev_priv, wakeref) {
for_each_engine(engine, dev_priv, id) {
acthd[id] = intel_engine_get_active_head(engine);
- seqno[id] = intel_engine_get_seqno(engine);
+ seqno[id] = intel_engine_get_hangcheck_seqno(engine);
}
intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
@@ -1315,8 +1315,9 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
for_each_engine(engine, dev_priv, id) {
seq_printf(m, "%s:\n", engine->name);
seq_printf(m, "\tseqno = %x [current %x, last %x], %dms ago\n",
- engine->hangcheck.seqno, seqno[id],
- intel_engine_last_submit(engine),
+ engine->hangcheck.last_seqno,
+ seqno[id],
+ engine->hangcheck.next_seqno,
jiffies_to_msecs(jiffies -
engine->hangcheck.action_timestamp));
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 81b80f8fd9ea..57bc5c4fb3ff 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1497,10 +1497,11 @@ void intel_engine_dump(struct intel_engine_cs *engine,
if (i915_reset_failed(engine->i915))
drm_printf(m, "*** WEDGED ***\n");
- drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
+ drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x/%x [%d ms]\n",
intel_engine_get_seqno(engine),
intel_engine_last_submit(engine),
- engine->hangcheck.seqno,
+ engine->hangcheck.last_seqno,
+ engine->hangcheck.next_seqno,
jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
drm_printf(m, "\tReset count: %d (global %d)\n",
i915_reset_engine_count(error, engine),
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index 9be033b6f4d2..f1d8dfc58049 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -133,21 +133,21 @@ static void hangcheck_load_sample(struct intel_engine_cs *engine,
struct hangcheck *hc)
{
hc->acthd = intel_engine_get_active_head(engine);
- hc->seqno = intel_engine_get_seqno(engine);
+ hc->seqno = intel_engine_get_hangcheck_seqno(engine);
}
static void hangcheck_store_sample(struct intel_engine_cs *engine,
const struct hangcheck *hc)
{
engine->hangcheck.acthd = hc->acthd;
- engine->hangcheck.seqno = hc->seqno;
+ engine->hangcheck.last_seqno = hc->seqno;
}
static enum intel_engine_hangcheck_action
hangcheck_get_action(struct intel_engine_cs *engine,
const struct hangcheck *hc)
{
- if (engine->hangcheck.seqno != hc->seqno)
+ if (engine->hangcheck.last_seqno != hc->seqno)
return ENGINE_ACTIVE_SEQNO;
if (intel_engine_is_idle(engine))
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 34a0866959c5..0516fc6b9652 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -178,6 +178,12 @@ static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
I915_GEM_HWS_INDEX_ADDR);
}
+static inline u32 intel_hws_hangcheck_address(struct intel_engine_cs *engine)
+{
+ return (i915_ggtt_offset(engine->status_page.vma) +
+ I915_GEM_HWS_HANGCHECK_ADDR);
+}
+
static inline struct i915_priolist *to_priolist(struct rb_node *rb)
{
return rb_entry(rb, struct i915_priolist, node);
@@ -2206,6 +2212,10 @@ static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
request->fence.seqno,
request->timeline->hwsp_offset);
+ cs = gen8_emit_ggtt_write(cs,
+ intel_engine_next_hangcheck_seqno(request->engine),
+ intel_hws_hangcheck_address(request->engine));
+
cs = gen8_emit_ggtt_write(cs,
request->global_seqno,
intel_hws_seqno_address(request->engine));
@@ -2230,6 +2240,11 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
PIPE_CONTROL_FLUSH_ENABLE |
PIPE_CONTROL_CS_STALL);
+ cs = gen8_emit_ggtt_write_rcs(cs,
+ intel_engine_next_hangcheck_seqno(request->engine),
+ intel_hws_hangcheck_address(request->engine),
+ 0);
+
cs = gen8_emit_ggtt_write_rcs(cs,
request->global_seqno,
intel_hws_seqno_address(request->engine),
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 7f841dba87b3..870184bbd169 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -43,6 +43,12 @@
*/
#define LEGACY_REQUEST_SIZE 200
+static inline u32 hws_hangcheck_address(struct intel_engine_cs *engine)
+{
+ return (i915_ggtt_offset(engine->status_page.vma) +
+ I915_GEM_HWS_HANGCHECK_ADDR);
+}
+
static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
{
return (i915_ggtt_offset(engine->status_page.vma) +
@@ -316,6 +322,11 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = rq->timeline->hwsp_offset | PIPE_CONTROL_GLOBAL_GTT;
*cs++ = rq->fence.seqno;
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_QW_WRITE;
+ *cs++ = hws_hangcheck_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT;
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
*cs++ = GFX_OP_PIPE_CONTROL(4);
*cs++ = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
*cs++ = intel_hws_seqno_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT;
@@ -422,6 +433,11 @@ static u32 *gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = rq->timeline->hwsp_offset;
*cs++ = rq->fence.seqno;
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
+ *cs++ = hws_hangcheck_address(rq->engine);
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
*cs++ = GFX_OP_PIPE_CONTROL(4);
*cs++ = (PIPE_CONTROL_QW_WRITE |
PIPE_CONTROL_GLOBAL_GTT_IVB |
@@ -447,12 +463,15 @@ static u32 *gen6_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = rq->fence.seqno;
+ *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+ *cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
*cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = rq->global_seqno;
*cs++ = MI_USER_INTERRUPT;
- *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -472,6 +491,10 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = rq->fence.seqno;
+ *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+ *cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
*cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = rq->global_seqno;
@@ -487,6 +510,7 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = 0;
*cs++ = MI_USER_INTERRUPT;
+ *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -930,11 +954,16 @@ static u32 *i9xx_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_SEQNO_ADDR;
*cs++ = rq->fence.seqno;
+ *cs++ = MI_STORE_DWORD_INDEX;
+ *cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
*cs++ = MI_STORE_DWORD_INDEX;
*cs++ = I915_GEM_HWS_INDEX_ADDR;
*cs++ = rq->global_seqno;
*cs++ = MI_USER_INTERRUPT;
+ *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -956,6 +985,10 @@ static u32 *gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_SEQNO_ADDR;
*cs++ = rq->fence.seqno;
+ *cs++ = MI_STORE_DWORD_INDEX;
+ *cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
+ *cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
BUILD_BUG_ON(GEN5_WA_STORES < 1);
for (i = 0; i < GEN5_WA_STORES; i++) {
*cs++ = MI_STORE_DWORD_INDEX;
@@ -964,7 +997,6 @@ static u32 *gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
}
*cs++ = MI_USER_INTERRUPT;
- *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 5d45ad4ecca9..2869aaa9d225 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -6,6 +6,7 @@
#include <linux/hashtable.h>
#include <linux/irq_work.h>
+#include <linux/random.h>
#include <linux/seqlock.h>
#include "i915_gem_batch_pool.h"
@@ -119,7 +120,8 @@ struct intel_instdone {
struct intel_engine_hangcheck {
u64 acthd;
- u32 seqno;
+ u32 last_seqno;
+ u32 next_seqno;
unsigned long action_timestamp;
struct intel_instdone instdone;
};
@@ -726,6 +728,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
#define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX * sizeof(u32))
#define I915_GEM_HWS_PREEMPT 0x32
#define I915_GEM_HWS_PREEMPT_ADDR (I915_GEM_HWS_PREEMPT * sizeof(u32))
+#define I915_GEM_HWS_HANGCHECK 0x34
+#define I915_GEM_HWS_HANGCHECK_ADDR (I915_GEM_HWS_HANGCHECK * sizeof(u32))
#define I915_GEM_HWS_SEQNO 0x40
#define I915_GEM_HWS_SEQNO_ADDR (I915_GEM_HWS_SEQNO * sizeof(u32))
#define I915_GEM_HWS_SCRATCH 0x80
@@ -1086,4 +1090,17 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
#endif
+static inline u32
+intel_engine_next_hangcheck_seqno(struct intel_engine_cs *engine)
+{
+ return engine->hangcheck.next_seqno =
+ next_pseudo_random32(engine->hangcheck.next_seqno);
+}
+
+static inline u32
+intel_engine_get_hangcheck_seqno(struct intel_engine_cs *engine)
+{
+ return intel_read_status_page(engine, I915_GEM_HWS_HANGCHECK);
+}
+
#endif /* _INTEL_RINGBUFFER_H_ */
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [CI 2/4] drm/i915: Remove access to global seqno in the HWSP
2019-02-26 9:49 [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Chris Wilson
@ 2019-02-26 9:49 ` Chris Wilson
2019-02-26 9:49 ` [CI 3/4] drm/i915: Remove i915_request.global_seqno Chris Wilson
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Chris Wilson @ 2019-02-26 9:49 UTC (permalink / raw)
To: intel-gfx
Stop accessing the HWSP to read the global seqno, and stop tracking the
mirror in the engine's execution timeline -- it is unused.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/i915_gpu_error.c | 4 --
drivers/gpu/drm/i915/i915_gpu_error.h | 3 --
drivers/gpu/drm/i915/i915_request.c | 27 +++++--------
drivers/gpu/drm/i915/i915_reset.c | 1 -
drivers/gpu/drm/i915/intel_engine_cs.c | 14 +------
drivers/gpu/drm/i915/intel_lrc.c | 21 +++-------
drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +---
drivers/gpu/drm/i915/intel_ringbuffer.h | 40 -------------------
drivers/gpu/drm/i915/selftests/i915_request.c | 3 +-
drivers/gpu/drm/i915/selftests/mock_engine.c | 3 --
10 files changed, 19 insertions(+), 104 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 3f6eddb6f6de..061a767e3bed 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -526,8 +526,6 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
ee->vm_info.pp_dir_base);
}
}
- err_printf(m, " seqno: 0x%08x\n", ee->seqno);
- err_printf(m, " last_seqno: 0x%08x\n", ee->last_seqno);
err_printf(m, " ring->head: 0x%08x\n", ee->cpu_ring_head);
err_printf(m, " ring->tail: 0x%08x\n", ee->cpu_ring_tail);
err_printf(m, " hangcheck timestamp: %dms (%lu%s)\n",
@@ -1216,8 +1214,6 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
ee->instpm = I915_READ(RING_INSTPM(engine->mmio_base));
ee->acthd = intel_engine_get_active_head(engine);
- ee->seqno = intel_engine_get_seqno(engine);
- ee->last_seqno = intel_engine_last_submit(engine);
ee->start = I915_READ_START(engine);
ee->head = I915_READ_HEAD(engine);
ee->tail = I915_READ_TAIL(engine);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 94eaf8ab9051..19ac102afaff 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -94,8 +94,6 @@ struct i915_gpu_state {
u32 cpu_ring_head;
u32 cpu_ring_tail;
- u32 last_seqno;
-
/* Register state */
u32 start;
u32 tail;
@@ -108,7 +106,6 @@ struct i915_gpu_state {
u32 bbstate;
u32 instpm;
u32 instps;
- u32 seqno;
u64 bbaddr;
u64 acthd;
u32 fault_reg;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 124b3e279c88..596183f35b78 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -179,12 +179,11 @@ static void free_capture_list(struct i915_request *request)
static void __retire_engine_request(struct intel_engine_cs *engine,
struct i915_request *rq)
{
- GEM_TRACE("%s(%s) fence %llx:%lld, global=%d, current %d:%d\n",
+ GEM_TRACE("%s(%s) fence %llx:%lld, global=%d, current %d\n",
__func__, engine->name,
rq->fence.context, rq->fence.seqno,
rq->global_seqno,
- hwsp_seqno(rq),
- intel_engine_get_seqno(engine));
+ hwsp_seqno(rq));
GEM_BUG_ON(!i915_request_completed(rq));
@@ -243,12 +242,11 @@ static void i915_request_retire(struct i915_request *request)
{
struct i915_active_request *active, *next;
- GEM_TRACE("%s fence %llx:%lld, global=%d, current %d:%d\n",
+ GEM_TRACE("%s fence %llx:%lld, global=%d, current %d\n",
request->engine->name,
request->fence.context, request->fence.seqno,
request->global_seqno,
- hwsp_seqno(request),
- intel_engine_get_seqno(request->engine));
+ hwsp_seqno(request));
lockdep_assert_held(&request->i915->drm.struct_mutex);
GEM_BUG_ON(!i915_sw_fence_signaled(&request->submit));
@@ -305,12 +303,11 @@ void i915_request_retire_upto(struct i915_request *rq)
struct intel_ring *ring = rq->ring;
struct i915_request *tmp;
- GEM_TRACE("%s fence %llx:%lld, global=%d, current %d:%d\n",
+ GEM_TRACE("%s fence %llx:%lld, global=%d, current %d\n",
rq->engine->name,
rq->fence.context, rq->fence.seqno,
rq->global_seqno,
- hwsp_seqno(rq),
- intel_engine_get_seqno(rq->engine));
+ hwsp_seqno(rq));
lockdep_assert_held(&rq->i915->drm.struct_mutex);
GEM_BUG_ON(!i915_request_completed(rq));
@@ -354,12 +351,11 @@ void __i915_request_submit(struct i915_request *request)
struct intel_engine_cs *engine = request->engine;
u32 seqno;
- GEM_TRACE("%s fence %llx:%lld -> global=%d, current %d:%d\n",
+ GEM_TRACE("%s fence %llx:%lld -> global=%d, current %d\n",
engine->name,
request->fence.context, request->fence.seqno,
engine->timeline.seqno + 1,
- hwsp_seqno(request),
- intel_engine_get_seqno(engine));
+ hwsp_seqno(request));
GEM_BUG_ON(!irqs_disabled());
lockdep_assert_held(&engine->timeline.lock);
@@ -371,7 +367,6 @@ void __i915_request_submit(struct i915_request *request)
seqno = next_global_seqno(&engine->timeline);
GEM_BUG_ON(!seqno);
- GEM_BUG_ON(intel_engine_signaled(engine, seqno));
/* We may be recursing from the signal callback of another i915 fence */
spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
@@ -409,12 +404,11 @@ void __i915_request_unsubmit(struct i915_request *request)
{
struct intel_engine_cs *engine = request->engine;
- GEM_TRACE("%s fence %llx:%lld <- global=%d, current %d:%d\n",
+ GEM_TRACE("%s fence %llx:%lld <- global=%d, current %d\n",
engine->name,
request->fence.context, request->fence.seqno,
request->global_seqno,
- hwsp_seqno(request),
- intel_engine_get_seqno(engine));
+ hwsp_seqno(request));
GEM_BUG_ON(!irqs_disabled());
lockdep_assert_held(&engine->timeline.lock);
@@ -425,7 +419,6 @@ void __i915_request_unsubmit(struct i915_request *request)
*/
GEM_BUG_ON(!request->global_seqno);
GEM_BUG_ON(request->global_seqno != engine->timeline.seqno);
- GEM_BUG_ON(intel_engine_has_completed(engine, request->global_seqno));
engine->timeline.seqno--;
/* We may be recursing from the signal callback of another i915 fence */
diff --git a/drivers/gpu/drm/i915/i915_reset.c b/drivers/gpu/drm/i915/i915_reset.c
index 39a08932a95a..55d6123dbba4 100644
--- a/drivers/gpu/drm/i915/i915_reset.c
+++ b/drivers/gpu/drm/i915/i915_reset.c
@@ -788,7 +788,6 @@ static void nop_submit_request(struct i915_request *request)
spin_lock_irqsave(&engine->timeline.lock, flags);
__i915_request_submit(request);
i915_request_mark_complete(request);
- intel_engine_write_global_seqno(engine, request->global_seqno);
spin_unlock_irqrestore(&engine->timeline.lock, flags);
intel_engine_queue_breadcrumbs(engine);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 57bc5c4fb3ff..ec859c7b8c7c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -455,12 +455,6 @@ int intel_engines_init(struct drm_i915_private *dev_priv)
return err;
}
-void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
- intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
- GEM_BUG_ON(intel_engine_get_seqno(engine) != seqno);
-}
-
static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
{
i915_gem_batch_pool_init(&engine->batch_pool, engine);
@@ -1011,10 +1005,6 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
if (i915_reset_failed(engine->i915))
return true;
- /* Any inflight/incomplete requests? */
- if (!intel_engine_signaled(engine, intel_engine_last_submit(engine)))
- return false;
-
/* Waiting to drain ELSP? */
if (READ_ONCE(engine->execlists.active)) {
struct tasklet_struct *t = &engine->execlists.tasklet;
@@ -1497,9 +1487,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
if (i915_reset_failed(engine->i915))
drm_printf(m, "*** WEDGED ***\n");
- drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x/%x [%d ms]\n",
- intel_engine_get_seqno(engine),
- intel_engine_last_submit(engine),
+ drm_printf(m, "\tHangcheck %x:%x [%d ms]\n",
engine->hangcheck.last_seqno,
engine->hangcheck.next_seqno,
jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0516fc6b9652..09b56b84e007 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -528,13 +528,12 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
desc = execlists_update_context(rq);
GEM_DEBUG_EXEC(port[n].context_id = upper_32_bits(desc));
- GEM_TRACE("%s in[%d]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d:%d), prio=%d\n",
+ GEM_TRACE("%s in[%d]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d), prio=%d\n",
engine->name, n,
port[n].context_id, count,
rq->global_seqno,
rq->fence.context, rq->fence.seqno,
hwsp_seqno(rq),
- intel_engine_get_seqno(engine),
rq_prio(rq));
} else {
GEM_BUG_ON(!n);
@@ -840,13 +839,12 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
while (num_ports-- && port_isset(port)) {
struct i915_request *rq = port_request(port);
- GEM_TRACE("%s:port%u global=%d (fence %llx:%lld), (current %d:%d)\n",
+ GEM_TRACE("%s:port%u global=%d (fence %llx:%lld), (current %d)\n",
rq->engine->name,
(unsigned int)(port - execlists->port),
rq->global_seqno,
rq->fence.context, rq->fence.seqno,
- hwsp_seqno(rq),
- intel_engine_get_seqno(rq->engine));
+ hwsp_seqno(rq));
GEM_BUG_ON(!execlists->active);
execlists_context_schedule_out(rq,
@@ -902,8 +900,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
struct rb_node *rb;
unsigned long flags;
- GEM_TRACE("%s current %d\n",
- engine->name, intel_engine_get_seqno(engine));
+ GEM_TRACE("%s\n", engine->name);
/*
* Before we call engine->cancel_requests(), we should have exclusive
@@ -952,10 +949,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
kmem_cache_free(engine->i915->priorities, p);
}
- intel_write_status_page(engine,
- I915_GEM_HWS_INDEX,
- intel_engine_last_submit(engine));
-
/* Remaining _unready_ requests will be nop'ed when submitted */
execlists->queue_priority_hint = INT_MIN;
@@ -1071,14 +1064,13 @@ static void process_csb(struct intel_engine_cs *engine)
EXECLISTS_ACTIVE_USER));
rq = port_unpack(port, &count);
- GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d:%d), prio=%d\n",
+ GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d), prio=%d\n",
engine->name,
port->context_id, count,
rq ? rq->global_seqno : 0,
rq ? rq->fence.context : 0,
rq ? rq->fence.seqno : 0,
rq ? hwsp_seqno(rq) : 0,
- intel_engine_get_seqno(engine),
rq ? rq_prio(rq) : 0);
/* Check the context/desc id for this event matches */
@@ -1946,10 +1938,9 @@ static void execlists_reset(struct intel_engine_cs *engine, bool stalled)
/* Following the reset, we need to reload the CSB read/write pointers */
reset_csb_pointers(&engine->execlists);
- GEM_TRACE("%s seqno=%d, current=%d, stalled? %s\n",
+ GEM_TRACE("%s seqno=%d, stalled? %s\n",
engine->name,
rq ? rq->global_seqno : 0,
- intel_engine_get_seqno(engine),
yesno(stalled));
if (!rq)
goto out_unlock;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 870184bbd169..2d59e2990448 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -782,10 +782,9 @@ static void reset_ring(struct intel_engine_cs *engine, bool stalled)
}
}
- GEM_TRACE("%s seqno=%d, current=%d, stalled? %s\n",
+ GEM_TRACE("%s seqno=%d, stalled? %s\n",
engine->name,
rq ? rq->global_seqno : 0,
- intel_engine_get_seqno(engine),
yesno(stalled));
/*
* The guilty request will get skipped on a hung engine.
@@ -924,10 +923,6 @@ static void cancel_requests(struct intel_engine_cs *engine)
i915_request_mark_complete(request);
}
- intel_write_status_page(engine,
- I915_GEM_HWS_INDEX,
- intel_engine_last_submit(engine));
-
/* Remaining _unready_ requests will be nop'ed when submitted */
spin_unlock_irqrestore(&engine->timeline.lock, flags);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2869aaa9d225..551b3daa741c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -848,8 +848,6 @@ __intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
return (head - tail - CACHELINE_BYTES) & (size - 1);
}
-void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno);
-
int intel_engine_setup_common(struct intel_engine_cs *engine);
int intel_engine_init_common(struct intel_engine_cs *engine);
void intel_engine_cleanup_common(struct intel_engine_cs *engine);
@@ -867,44 +865,6 @@ void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
-static inline u32 intel_engine_last_submit(struct intel_engine_cs *engine)
-{
- /*
- * We are only peeking at the tail of the submit queue (and not the
- * queue itself) in order to gain a hint as to the current active
- * state of the engine. Callers are not expected to be taking
- * engine->timeline->lock, nor are they expected to be concerned
- * wtih serialising this hint with anything, so document it as
- * a hint and nothing more.
- */
- return READ_ONCE(engine->timeline.seqno);
-}
-
-static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine)
-{
- return intel_read_status_page(engine, I915_GEM_HWS_INDEX);
-}
-
-static inline bool intel_engine_signaled(struct intel_engine_cs *engine,
- u32 seqno)
-{
- return i915_seqno_passed(intel_engine_get_seqno(engine), seqno);
-}
-
-static inline bool intel_engine_has_completed(struct intel_engine_cs *engine,
- u32 seqno)
-{
- GEM_BUG_ON(!seqno);
- return intel_engine_signaled(engine, seqno);
-}
-
-static inline bool intel_engine_has_started(struct intel_engine_cs *engine,
- u32 seqno)
-{
- GEM_BUG_ON(!seqno);
- return intel_engine_signaled(engine, seqno - 1);
-}
-
void intel_engine_get_instdone(struct intel_engine_cs *engine,
struct intel_instdone *instdone);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 03cc8ab6a620..7da52e3d67af 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -226,8 +226,7 @@ static int igt_request_rewind(void *arg)
mutex_unlock(&i915->drm.struct_mutex);
if (i915_request_wait(vip, 0, HZ) == -ETIME) {
- pr_err("timed out waiting for high priority request, vip.seqno=%d, current seqno=%d\n",
- vip->global_seqno, intel_engine_get_seqno(i915->engine[RCS]));
+ pr_err("timed out waiting for high priority request\n");
goto err;
}
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 08f0cab02e0f..79bf27606ab8 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -86,8 +86,6 @@ static struct mock_request *first_request(struct mock_engine *engine)
static void advance(struct mock_request *request)
{
list_del_init(&request->link);
- intel_engine_write_global_seqno(request->base.engine,
- request->base.global_seqno);
i915_request_mark_complete(&request->base);
GEM_BUG_ON(!i915_request_completed(&request->base));
@@ -278,7 +276,6 @@ void mock_engine_flush(struct intel_engine_cs *engine)
void mock_engine_reset(struct intel_engine_cs *engine)
{
- intel_engine_write_global_seqno(engine, 0);
}
void mock_engine_free(struct intel_engine_cs *engine)
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [CI 3/4] drm/i915: Remove i915_request.global_seqno
2019-02-26 9:49 [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Chris Wilson
2019-02-26 9:49 ` [CI 2/4] drm/i915: Remove access to global seqno in the HWSP Chris Wilson
@ 2019-02-26 9:49 ` Chris Wilson
2019-02-26 9:49 ` [CI 4/4] drm/i915/selftests: Exercise resetting during non-user payloads Chris Wilson
2019-02-26 10:52 ` ✗ Fi.CI.BAT: failure for series starting with [CI,1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Patchwork
3 siblings, 0 replies; 5+ messages in thread
From: Chris Wilson @ 2019-02-26 9:49 UTC (permalink / raw)
To: intel-gfx
Having weaned the interrupt handling off using a single global execution
queue, we no longer need to emit a global_seqno. Note that we still have
a few assumptions about execution order along engine timelines, but this
removes the most obvious artefact!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
drivers/gpu/drm/i915/i915_gpu_error.c | 34 ++-----------
drivers/gpu/drm/i915/i915_gpu_error.h | 2 -
drivers/gpu/drm/i915/i915_request.c | 34 ++-----------
drivers/gpu/drm/i915/i915_request.h | 32 ------------
drivers/gpu/drm/i915/i915_trace.h | 25 +++-------
drivers/gpu/drm/i915/intel_engine_cs.c | 5 +-
drivers/gpu/drm/i915/intel_guc_submission.c | 2 +-
drivers/gpu/drm/i915/intel_lrc.c | 34 ++-----------
drivers/gpu/drm/i915/intel_ringbuffer.c | 50 +++----------------
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 -
.../gpu/drm/i915/selftests/intel_hangcheck.c | 5 +-
drivers/gpu/drm/i915/selftests/mock_engine.c | 1 -
12 files changed, 32 insertions(+), 194 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 061a767e3bed..fa86c60fb56c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -380,19 +380,16 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
err_printf(m, "%s [%d]:\n", name, count);
while (count--) {
- err_printf(m, " %08x_%08x %8u %02x %02x %02x",
+ err_printf(m, " %08x_%08x %8u %02x %02x",
upper_32_bits(err->gtt_offset),
lower_32_bits(err->gtt_offset),
err->size,
err->read_domains,
- err->write_domain,
- err->wseqno);
+ err->write_domain);
err_puts(m, tiling_flag(err->tiling));
err_puts(m, dirty_flag(err->dirty));
err_puts(m, purgeable_flag(err->purgeable));
err_puts(m, err->userptr ? " userptr" : "");
- err_puts(m, err->engine != -1 ? " " : "");
- err_puts(m, engine_name(m->i915, err->engine));
err_puts(m, i915_cache_level_str(m->i915, err->cache_level));
if (err->name)
@@ -1048,27 +1045,6 @@ i915_error_object_create(struct drm_i915_private *i915,
return dst;
}
-/* The error capture is special as tries to run underneath the normal
- * locking rules - so we use the raw version of the i915_active_request lookup.
- */
-static inline u32
-__active_get_seqno(struct i915_active_request *active)
-{
- struct i915_request *request;
-
- request = __i915_active_request_peek(active);
- return request ? request->global_seqno : 0;
-}
-
-static inline int
-__active_get_engine_id(struct i915_active_request *active)
-{
- struct i915_request *request;
-
- request = __i915_active_request_peek(active);
- return request ? request->engine->id : -1;
-}
-
static void capture_bo(struct drm_i915_error_buffer *err,
struct i915_vma *vma)
{
@@ -1077,9 +1053,6 @@ static void capture_bo(struct drm_i915_error_buffer *err,
err->size = obj->base.size;
err->name = obj->base.name;
- err->wseqno = __active_get_seqno(&obj->frontbuffer_write);
- err->engine = __active_get_engine_id(&obj->frontbuffer_write);
-
err->gtt_offset = vma->node.start;
err->read_domains = obj->read_domains;
err->write_domain = obj->write_domain;
@@ -1284,7 +1257,8 @@ static void record_request(struct i915_request *request,
struct i915_gem_context *ctx = request->gem_context;
erq->flags = request->fence.flags;
- erq->context = ctx->hw_id;
+ erq->context = request->fence.context;
+ erq->seqno = request->fence.seqno;
erq->sched_attr = request->sched.attr;
erq->jiffies = request->emitted_jiffies;
erq->start = i915_ggtt_offset(request->ring->vma);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 19ac102afaff..8c1569c1830d 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -164,7 +164,6 @@ struct i915_gpu_state {
struct drm_i915_error_buffer {
u32 size;
u32 name;
- u32 wseqno;
u64 gtt_offset;
u32 read_domains;
u32 write_domain;
@@ -173,7 +172,6 @@ struct i915_gpu_state {
u32 dirty:1;
u32 purgeable:1;
u32 userptr:1;
- s32 engine:4;
u32 cache_level:3;
} *active_bo[I915_NUM_ENGINES], *pinned_bo;
u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 596183f35b78..935db5548f80 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -179,10 +179,9 @@ static void free_capture_list(struct i915_request *request)
static void __retire_engine_request(struct intel_engine_cs *engine,
struct i915_request *rq)
{
- GEM_TRACE("%s(%s) fence %llx:%lld, global=%d, current %d\n",
+ GEM_TRACE("%s(%s) fence %llx:%lld, current %d\n",
__func__, engine->name,
rq->fence.context, rq->fence.seqno,
- rq->global_seqno,
hwsp_seqno(rq));
GEM_BUG_ON(!i915_request_completed(rq));
@@ -242,10 +241,9 @@ static void i915_request_retire(struct i915_request *request)
{
struct i915_active_request *active, *next;
- GEM_TRACE("%s fence %llx:%lld, global=%d, current %d\n",
+ GEM_TRACE("%s fence %llx:%lld, current %d\n",
request->engine->name,
request->fence.context, request->fence.seqno,
- request->global_seqno,
hwsp_seqno(request));
lockdep_assert_held(&request->i915->drm.struct_mutex);
@@ -303,10 +301,9 @@ void i915_request_retire_upto(struct i915_request *rq)
struct intel_ring *ring = rq->ring;
struct i915_request *tmp;
- GEM_TRACE("%s fence %llx:%lld, global=%d, current %d\n",
+ GEM_TRACE("%s fence %llx:%lld, current %d\n",
rq->engine->name,
rq->fence.context, rq->fence.seqno,
- rq->global_seqno,
hwsp_seqno(rq));
lockdep_assert_held(&rq->i915->drm.struct_mutex);
@@ -339,22 +336,13 @@ static void move_to_timeline(struct i915_request *request,
spin_unlock(&request->timeline->lock);
}
-static u32 next_global_seqno(struct i915_timeline *tl)
-{
- if (!++tl->seqno)
- ++tl->seqno;
- return tl->seqno;
-}
-
void __i915_request_submit(struct i915_request *request)
{
struct intel_engine_cs *engine = request->engine;
- u32 seqno;
- GEM_TRACE("%s fence %llx:%lld -> global=%d, current %d\n",
+ GEM_TRACE("%s fence %llx:%lld -> current %d\n",
engine->name,
request->fence.context, request->fence.seqno,
- engine->timeline.seqno + 1,
hwsp_seqno(request));
GEM_BUG_ON(!irqs_disabled());
@@ -363,16 +351,10 @@ void __i915_request_submit(struct i915_request *request)
if (i915_gem_context_is_banned(request->gem_context))
i915_request_skip(request, -EIO);
- GEM_BUG_ON(request->global_seqno);
-
- seqno = next_global_seqno(&engine->timeline);
- GEM_BUG_ON(!seqno);
-
/* We may be recursing from the signal callback of another i915 fence */
spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
- request->global_seqno = seqno;
if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
!i915_request_enable_breadcrumb(request))
intel_engine_queue_breadcrumbs(engine);
@@ -404,10 +386,9 @@ void __i915_request_unsubmit(struct i915_request *request)
{
struct intel_engine_cs *engine = request->engine;
- GEM_TRACE("%s fence %llx:%lld <- global=%d, current %d\n",
+ GEM_TRACE("%s fence %llx:%lld, current %d\n",
engine->name,
request->fence.context, request->fence.seqno,
- request->global_seqno,
hwsp_seqno(request));
GEM_BUG_ON(!irqs_disabled());
@@ -417,13 +398,9 @@ void __i915_request_unsubmit(struct i915_request *request)
* Only unwind in reverse order, required so that the per-context list
* is kept in seqno/ring order.
*/
- GEM_BUG_ON(!request->global_seqno);
- GEM_BUG_ON(request->global_seqno != engine->timeline.seqno);
- engine->timeline.seqno--;
/* We may be recursing from the signal callback of another i915 fence */
spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
- request->global_seqno = 0;
if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
i915_request_cancel_breadcrumb(request);
GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
@@ -637,7 +614,6 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
i915_sched_node_init(&rq->sched);
/* No zalloc, must clear what we need by hand */
- rq->global_seqno = 0;
rq->file_priv = NULL;
rq->batch = NULL;
rq->capture_list = NULL;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 40f3e8dcbdd5..1e127c1c53fa 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -147,14 +147,6 @@ struct i915_request {
*/
const u32 *hwsp_seqno;
- /**
- * GEM sequence number associated with this request on the
- * global execution timeline. It is zero when the request is not
- * on the HW queue (i.e. not on the engine timeline list).
- * Its value is guarded by the timeline spinlock.
- */
- u32 global_seqno;
-
/** Position in the ring of the start of the request */
u32 head;
@@ -247,30 +239,6 @@ i915_request_put(struct i915_request *rq)
dma_fence_put(&rq->fence);
}
-/**
- * i915_request_global_seqno - report the current global seqno
- * @request - the request
- *
- * A request is assigned a global seqno only when it is on the hardware
- * execution queue. The global seqno can be used to maintain a list of
- * requests on the same engine in retirement order, for example for
- * constructing a priority queue for waiting. Prior to its execution, or
- * if it is subsequently removed in the event of preemption, its global
- * seqno is zero. As both insertion and removal from the execution queue
- * may operate in IRQ context, it is not guarded by the usual struct_mutex
- * BKL. Instead those relying on the global seqno must be prepared for its
- * value to change between reads. Only when the request is complete can
- * the global seqno be stable (due to the memory barriers on submitting
- * the commands to the hardware to write the breadcrumb, if the HWS shows
- * that it has passed the global seqno and the global seqno is unchanged
- * after the read, it is indeed complete).
- */
-static inline u32
-i915_request_global_seqno(const struct i915_request *request)
-{
- return READ_ONCE(request->global_seqno);
-}
-
int i915_request_await_object(struct i915_request *to,
struct drm_i915_gem_object *obj,
bool write);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 0d9cedb892b0..12893304c8f8 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -708,7 +708,6 @@ DECLARE_EVENT_CLASS(i915_request,
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
- __field(u32, global)
),
TP_fast_assign(
@@ -718,13 +717,11 @@ DECLARE_EVENT_CLASS(i915_request,
__entry->instance = rq->engine->instance;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
- __entry->global = rq->global_seqno;
),
- TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u",
+ TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u",
__entry->dev, __entry->class, __entry->instance,
- __entry->hw_id, __entry->ctx, __entry->seqno,
- __entry->global)
+ __entry->hw_id, __entry->ctx, __entry->seqno)
);
DEFINE_EVENT(i915_request, i915_request_add,
@@ -754,7 +751,6 @@ TRACE_EVENT(i915_request_in,
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
- __field(u32, global_seqno)
__field(u32, port)
__field(u32, prio)
),
@@ -766,15 +762,14 @@ TRACE_EVENT(i915_request_in,
__entry->instance = rq->engine->instance;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
- __entry->global_seqno = rq->global_seqno;
__entry->prio = rq->sched.attr.priority;
__entry->port = port;
),
- TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, global=%u, port=%u",
+ TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, port=%u",
__entry->dev, __entry->class, __entry->instance,
__entry->hw_id, __entry->ctx, __entry->seqno,
- __entry->prio, __entry->global_seqno, __entry->port)
+ __entry->prio, __entry->port)
);
TRACE_EVENT(i915_request_out,
@@ -788,7 +783,6 @@ TRACE_EVENT(i915_request_out,
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
- __field(u32, global_seqno)
__field(u32, completed)
),
@@ -799,14 +793,13 @@ TRACE_EVENT(i915_request_out,
__entry->instance = rq->engine->instance;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
- __entry->global_seqno = rq->global_seqno;
__entry->completed = i915_request_completed(rq);
),
- TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, completed?=%u",
+ TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, completed?=%u",
__entry->dev, __entry->class, __entry->instance,
__entry->hw_id, __entry->ctx, __entry->seqno,
- __entry->global_seqno, __entry->completed)
+ __entry->completed)
);
#else
@@ -849,7 +842,6 @@ TRACE_EVENT(i915_request_wait_begin,
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
- __field(u32, global)
__field(unsigned int, flags)
),
@@ -866,14 +858,13 @@ TRACE_EVENT(i915_request_wait_begin,
__entry->instance = rq->engine->instance;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
- __entry->global = rq->global_seqno;
__entry->flags = flags;
),
- TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, blocking=%u, flags=0x%x",
+ TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, blocking=%u, flags=0x%x",
__entry->dev, __entry->class, __entry->instance,
__entry->hw_id, __entry->ctx, __entry->seqno,
- __entry->global, !!(__entry->flags & I915_WAIT_LOCKED),
+ !!(__entry->flags & I915_WAIT_LOCKED),
__entry->flags)
);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index ec859c7b8c7c..b7b626195eda 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1271,15 +1271,14 @@ static void print_request(struct drm_printer *m,
x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
- drm_printf(m, "%s%x%s%s [%llx:%llx]%s @ %dms: %s\n",
+ drm_printf(m, "%s %llx:%llx%s%s %s @ %dms: %s\n",
prefix,
- rq->global_seqno,
+ rq->fence.context, rq->fence.seqno,
i915_request_completed(rq) ? "!" :
i915_request_started(rq) ? "*" :
"",
test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
&rq->fence.flags) ? "+" : "",
- rq->fence.context, rq->fence.seqno,
buf,
jiffies_to_msecs(jiffies - rq->emitted_jiffies),
name);
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 8bc8aa54aa35..20cbceeabeae 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -535,7 +535,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
spin_lock(&client->wq_lock);
guc_wq_item_append(client, engine->guc_id, ctx_desc,
- ring_tail, rq->global_seqno);
+ ring_tail, rq->fence.seqno);
guc_ring_doorbell(client);
client->submissions[engine->id] += 1;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 09b56b84e007..c4f4966b0f4f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -172,12 +172,6 @@ static void execlists_init_reg_state(u32 *reg_state,
struct intel_engine_cs *engine,
struct intel_ring *ring);
-static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
-{
- return (i915_ggtt_offset(engine->status_page.vma) +
- I915_GEM_HWS_INDEX_ADDR);
-}
-
static inline u32 intel_hws_hangcheck_address(struct intel_engine_cs *engine)
{
return (i915_ggtt_offset(engine->status_page.vma) +
@@ -528,10 +522,9 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
desc = execlists_update_context(rq);
GEM_DEBUG_EXEC(port[n].context_id = upper_32_bits(desc));
- GEM_TRACE("%s in[%d]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d), prio=%d\n",
+ GEM_TRACE("%s in[%d]: ctx=%d.%d, fence %llx:%lld (current %d), prio=%d\n",
engine->name, n,
port[n].context_id, count,
- rq->global_seqno,
rq->fence.context, rq->fence.seqno,
hwsp_seqno(rq),
rq_prio(rq));
@@ -839,10 +832,9 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
while (num_ports-- && port_isset(port)) {
struct i915_request *rq = port_request(port);
- GEM_TRACE("%s:port%u global=%d (fence %llx:%lld), (current %d)\n",
+ GEM_TRACE("%s:port%u fence %llx:%lld, (current %d)\n",
rq->engine->name,
(unsigned int)(port - execlists->port),
- rq->global_seqno,
rq->fence.context, rq->fence.seqno,
hwsp_seqno(rq));
@@ -924,8 +916,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
/* Mark all executing requests as skipped. */
list_for_each_entry(rq, &engine->timeline.requests, link) {
- GEM_BUG_ON(!rq->global_seqno);
-
if (!i915_request_signaled(rq))
dma_fence_set_error(&rq->fence, -EIO);
@@ -1064,10 +1054,9 @@ static void process_csb(struct intel_engine_cs *engine)
EXECLISTS_ACTIVE_USER));
rq = port_unpack(port, &count);
- GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%lld) (current %d), prio=%d\n",
+ GEM_TRACE("%s out[0]: ctx=%d.%d, fence %llx:%lld (current %d), prio=%d\n",
engine->name,
port->context_id, count,
- rq ? rq->global_seqno : 0,
rq ? rq->fence.context : 0,
rq ? rq->fence.seqno : 0,
rq ? hwsp_seqno(rq) : 0,
@@ -1938,10 +1927,7 @@ static void execlists_reset(struct intel_engine_cs *engine, bool stalled)
/* Following the reset, we need to reload the CSB read/write pointers */
reset_csb_pointers(&engine->execlists);
- GEM_TRACE("%s seqno=%d, stalled? %s\n",
- engine->name,
- rq ? rq->global_seqno : 0,
- yesno(stalled));
+ GEM_TRACE("%s stalled? %s\n", engine->name, yesno(stalled));
if (!rq)
goto out_unlock;
@@ -2196,9 +2182,6 @@ static u32 *gen8_emit_wa_tail(struct i915_request *request, u32 *cs)
static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
{
- /* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */
- BUILD_BUG_ON(I915_GEM_HWS_INDEX_ADDR & (1 << 5));
-
cs = gen8_emit_ggtt_write(cs,
request->fence.seqno,
request->timeline->hwsp_offset);
@@ -2207,10 +2190,6 @@ static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
intel_engine_next_hangcheck_seqno(request->engine),
intel_hws_hangcheck_address(request->engine));
- cs = gen8_emit_ggtt_write(cs,
- request->global_seqno,
- intel_hws_seqno_address(request->engine));
-
*cs++ = MI_USER_INTERRUPT;
*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
@@ -2236,11 +2215,6 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
intel_hws_hangcheck_address(request->engine),
0);
- cs = gen8_emit_ggtt_write_rcs(cs,
- request->global_seqno,
- intel_hws_seqno_address(request->engine),
- PIPE_CONTROL_CS_STALL);
-
*cs++ = MI_USER_INTERRUPT;
*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 2d59e2990448..1b96b0960adc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -49,12 +49,6 @@ static inline u32 hws_hangcheck_address(struct intel_engine_cs *engine)
I915_GEM_HWS_HANGCHECK_ADDR);
}
-static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
-{
- return (i915_ggtt_offset(engine->status_page.vma) +
- I915_GEM_HWS_INDEX_ADDR);
-}
-
unsigned int intel_ring_update_space(struct intel_ring *ring)
{
unsigned int space;
@@ -327,11 +321,6 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = hws_hangcheck_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT;
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
- *cs++ = GFX_OP_PIPE_CONTROL(4);
- *cs++ = PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
- *cs++ = intel_hws_seqno_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT;
- *cs++ = rq->global_seqno;
-
*cs++ = MI_USER_INTERRUPT;
*cs++ = MI_NOOP;
@@ -438,13 +427,6 @@ static u32 *gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = hws_hangcheck_address(rq->engine);
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
- *cs++ = GFX_OP_PIPE_CONTROL(4);
- *cs++ = (PIPE_CONTROL_QW_WRITE |
- PIPE_CONTROL_GLOBAL_GTT_IVB |
- PIPE_CONTROL_CS_STALL);
- *cs++ = intel_hws_seqno_address(rq->engine);
- *cs++ = rq->global_seqno;
-
*cs++ = MI_USER_INTERRUPT;
*cs++ = MI_NOOP;
@@ -467,11 +449,8 @@ static u32 *gen6_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
- *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
- *cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
- *cs++ = rq->global_seqno;
-
*cs++ = MI_USER_INTERRUPT;
+ *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -495,10 +474,6 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
- *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
- *cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
- *cs++ = rq->global_seqno;
-
for (i = 0; i < GEN7_XCS_WA; i++) {
*cs++ = MI_STORE_DWORD_INDEX;
*cs++ = I915_GEM_HWS_SEQNO_ADDR;
@@ -510,7 +485,6 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = 0;
*cs++ = MI_USER_INTERRUPT;
- *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -782,10 +756,8 @@ static void reset_ring(struct intel_engine_cs *engine, bool stalled)
}
}
- GEM_TRACE("%s seqno=%d, stalled? %s\n",
- engine->name,
- rq ? rq->global_seqno : 0,
- yesno(stalled));
+ GEM_TRACE("%s stalled? %s\n", engine->name, yesno(stalled));
+
/*
* The guilty request will get skipped on a hung engine.
*
@@ -915,8 +887,6 @@ static void cancel_requests(struct intel_engine_cs *engine)
/* Mark all submitted requests as skipped. */
list_for_each_entry(request, &engine->timeline.requests, link) {
- GEM_BUG_ON(!request->global_seqno);
-
if (!i915_request_signaled(request))
dma_fence_set_error(&request->fence, -EIO);
@@ -953,12 +923,7 @@ static u32 *i9xx_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
- *cs++ = MI_STORE_DWORD_INDEX;
- *cs++ = I915_GEM_HWS_INDEX_ADDR;
- *cs++ = rq->global_seqno;
-
*cs++ = MI_USER_INTERRUPT;
- *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
@@ -976,10 +941,6 @@ static u32 *gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
*cs++ = MI_FLUSH;
- *cs++ = MI_STORE_DWORD_INDEX;
- *cs++ = I915_GEM_HWS_SEQNO_ADDR;
- *cs++ = rq->fence.seqno;
-
*cs++ = MI_STORE_DWORD_INDEX;
*cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
@@ -987,11 +948,12 @@ static u32 *gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
BUILD_BUG_ON(GEN5_WA_STORES < 1);
for (i = 0; i < GEN5_WA_STORES; i++) {
*cs++ = MI_STORE_DWORD_INDEX;
- *cs++ = I915_GEM_HWS_INDEX_ADDR;
- *cs++ = rq->global_seqno;
+ *cs++ = I915_GEM_HWS_SEQNO_ADDR;
+ *cs++ = rq->fence.seqno;
}
*cs++ = MI_USER_INTERRUPT;
+ *cs++ = MI_NOOP;
rq->tail = intel_ring_offset(rq, cs);
assert_ring_tail_valid(rq->ring, rq->tail);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 551b3daa741c..de8dba7565b0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -724,8 +724,6 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
*
* The area from dword 0x30 to 0x3ff is available for driver usage.
*/
-#define I915_GEM_HWS_INDEX 0x30
-#define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX * sizeof(u32))
#define I915_GEM_HWS_PREEMPT 0x32
#define I915_GEM_HWS_PREEMPT_ADDR (I915_GEM_HWS_PREEMPT * sizeof(u32))
#define I915_GEM_HWS_HANGCHECK 0x34
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index a77e4bf1ab55..fa02cf9ce0cf 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -571,11 +571,10 @@ static int active_request_put(struct i915_request *rq)
return 0;
if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
- GEM_TRACE("%s timed out waiting for completion of fence %llx:%lld, seqno %d.\n",
+ GEM_TRACE("%s timed out waiting for completion of fence %llx:%lld\n",
rq->engine->name,
rq->fence.context,
- rq->fence.seqno,
- i915_request_global_seqno(rq));
+ rq->fence.seqno);
GEM_TRACE_DUMP();
i915_gem_set_wedged(rq->i915);
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 79bf27606ab8..6f3fb803c747 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -196,7 +196,6 @@ static void mock_submit_request(struct i915_request *request)
unsigned long flags;
i915_request_submit(request);
- GEM_BUG_ON(!request->global_seqno);
spin_lock_irqsave(&engine->hw_lock, flags);
list_add_tail(&mock->link, &engine->hw_queue);
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [CI 4/4] drm/i915/selftests: Exercise resetting during non-user payloads
2019-02-26 9:49 [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Chris Wilson
2019-02-26 9:49 ` [CI 2/4] drm/i915: Remove access to global seqno in the HWSP Chris Wilson
2019-02-26 9:49 ` [CI 3/4] drm/i915: Remove i915_request.global_seqno Chris Wilson
@ 2019-02-26 9:49 ` Chris Wilson
2019-02-26 10:52 ` ✗ Fi.CI.BAT: failure for series starting with [CI,1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Patchwork
3 siblings, 0 replies; 5+ messages in thread
From: Chris Wilson @ 2019-02-26 9:49 UTC (permalink / raw)
To: intel-gfx
In selftests/live_hangcheck, we have a lot of tests for resetting simple
spinners, but nothing quite prepared us for how the GPU reacted to
triggering a reset outside of the safe spinner. These two subtests fill
the ring with plain old empty, non-spinning requests, and then triggers
a reset. Without a user-payload to blame, these requests will exercise
the 'non-started' paths and mostly be replayed verbatim.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
.../gpu/drm/i915/selftests/intel_hangcheck.c | 218 ++++++++++++++++++
1 file changed, 218 insertions(+)
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index fa02cf9ce0cf..12e047328ab8 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -415,6 +415,222 @@ static bool wait_for_idle(struct intel_engine_cs *engine)
return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
}
+static int igt_reset_nop(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_engine_cs *engine;
+ struct i915_gem_context *ctx;
+ unsigned int reset_count, count;
+ enum intel_engine_id id;
+ intel_wakeref_t wakeref;
+ struct drm_file *file;
+ IGT_TIMEOUT(end_time);
+ int err = 0;
+
+ /* Check that we can reset during non-user portions of requests */
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ mutex_lock(&i915->drm.struct_mutex);
+ ctx = live_context(i915, file);
+ mutex_unlock(&i915->drm.struct_mutex);
+ if (IS_ERR(ctx)) {
+ err = PTR_ERR(ctx);
+ goto out;
+ }
+
+ i915_gem_context_clear_bannable(ctx);
+ wakeref = intel_runtime_pm_get(i915);
+ reset_count = i915_reset_count(&i915->gpu_error);
+ count = 0;
+ do {
+ mutex_lock(&i915->drm.struct_mutex);
+ for_each_engine(engine, i915, id) {
+ int i;
+
+ for (i = 0; i < 16; i++) {
+ struct i915_request *rq;
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ break;
+ }
+
+ i915_request_add(rq);
+ }
+ }
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ igt_global_reset_lock(i915);
+ i915_reset(i915, ALL_ENGINES, NULL);
+ igt_global_reset_unlock(i915);
+ if (i915_reset_failed(i915)) {
+ err = -EIO;
+ break;
+ }
+
+ if (i915_reset_count(&i915->gpu_error) !=
+ reset_count + ++count) {
+ pr_err("Full GPU reset not recorded!\n");
+ err = -EINVAL;
+ break;
+ }
+
+ if (!i915_reset_flush(i915)) {
+ struct drm_printer p =
+ drm_info_printer(i915->drm.dev);
+
+ pr_err("%s failed to idle after reset\n",
+ engine->name);
+ intel_engine_dump(engine, &p,
+ "%s\n", engine->name);
+
+ err = -EIO;
+ break;
+ }
+
+ err = igt_flush_test(i915, 0);
+ if (err)
+ break;
+ } while (time_before(jiffies, end_time));
+ pr_info("%s: %d resets\n", __func__, count);
+
+ mutex_lock(&i915->drm.struct_mutex);
+ err = igt_flush_test(i915, I915_WAIT_LOCKED);
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ intel_runtime_pm_put(i915, wakeref);
+
+out:
+ mock_file_free(i915, file);
+ if (i915_reset_failed(i915))
+ err = -EIO;
+ return err;
+}
+
+static int igt_reset_nop_engine(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_engine_cs *engine;
+ struct i915_gem_context *ctx;
+ enum intel_engine_id id;
+ intel_wakeref_t wakeref;
+ struct drm_file *file;
+ int err = 0;
+
+ /* Check that we can engine-reset during non-user portions */
+
+ if (!intel_has_reset_engine(i915))
+ return 0;
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ mutex_lock(&i915->drm.struct_mutex);
+ ctx = live_context(i915, file);
+ mutex_unlock(&i915->drm.struct_mutex);
+ if (IS_ERR(ctx)) {
+ err = PTR_ERR(ctx);
+ goto out;
+ }
+
+ i915_gem_context_clear_bannable(ctx);
+ wakeref = intel_runtime_pm_get(i915);
+ for_each_engine(engine, i915, id) {
+ unsigned int reset_count, reset_engine_count;
+ unsigned int count;
+ IGT_TIMEOUT(end_time);
+
+ reset_count = i915_reset_count(&i915->gpu_error);
+ reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
+ engine);
+ count = 0;
+
+ set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+ do {
+ int i;
+
+ if (!wait_for_idle(engine)) {
+ pr_err("%s failed to idle before reset\n",
+ engine->name);
+ err = -EIO;
+ break;
+ }
+
+ mutex_lock(&i915->drm.struct_mutex);
+ for (i = 0; i < 16; i++) {
+ struct i915_request *rq;
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ break;
+ }
+
+ i915_request_add(rq);
+ }
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ err = i915_reset_engine(engine, NULL);
+ if (err) {
+ pr_err("i915_reset_engine failed\n");
+ break;
+ }
+
+ if (i915_reset_count(&i915->gpu_error) != reset_count) {
+ pr_err("Full GPU reset recorded! (engine reset expected)\n");
+ err = -EINVAL;
+ break;
+ }
+
+ if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+ reset_engine_count + ++count) {
+ pr_err("%s engine reset not recorded!\n",
+ engine->name);
+ err = -EINVAL;
+ break;
+ }
+
+ if (!i915_reset_flush(i915)) {
+ struct drm_printer p =
+ drm_info_printer(i915->drm.dev);
+
+ pr_err("%s failed to idle after reset\n",
+ engine->name);
+ intel_engine_dump(engine, &p,
+ "%s\n", engine->name);
+
+ err = -EIO;
+ break;
+ }
+ } while (time_before(jiffies, end_time));
+ clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+ pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
+
+ if (err)
+ break;
+
+ err = igt_flush_test(i915, 0);
+ if (err)
+ break;
+ }
+
+ mutex_lock(&i915->drm.struct_mutex);
+ err = igt_flush_test(i915, I915_WAIT_LOCKED);
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ intel_runtime_pm_put(i915, wakeref);
+out:
+ mock_file_free(i915, file);
+ if (i915_reset_failed(i915))
+ err = -EIO;
+ return err;
+}
+
static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
{
struct intel_engine_cs *engine;
@@ -1646,6 +1862,8 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
SUBTEST(igt_global_reset), /* attempt to recover GPU first */
SUBTEST(igt_wedged_reset),
SUBTEST(igt_hang_sanitycheck),
+ SUBTEST(igt_reset_nop),
+ SUBTEST(igt_reset_nop_engine),
SUBTEST(igt_reset_idle_engine),
SUBTEST(igt_reset_active_engine),
SUBTEST(igt_reset_engines),
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 5+ messages in thread
* ✗ Fi.CI.BAT: failure for series starting with [CI,1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno
2019-02-26 9:49 [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Chris Wilson
` (2 preceding siblings ...)
2019-02-26 9:49 ` [CI 4/4] drm/i915/selftests: Exercise resetting during non-user payloads Chris Wilson
@ 2019-02-26 10:52 ` Patchwork
3 siblings, 0 replies; 5+ messages in thread
From: Patchwork @ 2019-02-26 10:52 UTC (permalink / raw)
To: intel-gfx
== Series Details ==
Series: series starting with [CI,1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno
URL : https://patchwork.freedesktop.org/series/57242/
State : failure
== Summary ==
Applying: drm/i915: Replace global_seqno with a hangcheck heartbeat seqno
Using index info to reconstruct a base tree...
M drivers/gpu/drm/i915/i915_debugfs.c
M drivers/gpu/drm/i915/intel_engine_cs.c
M drivers/gpu/drm/i915/intel_hangcheck.c
M drivers/gpu/drm/i915/intel_lrc.c
M drivers/gpu/drm/i915/intel_ringbuffer.c
M drivers/gpu/drm/i915/intel_ringbuffer.h
Falling back to patching base and 3-way merge...
Auto-merging drivers/gpu/drm/i915/intel_ringbuffer.h
Auto-merging drivers/gpu/drm/i915/intel_ringbuffer.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/intel_ringbuffer.c
Auto-merging drivers/gpu/drm/i915/intel_lrc.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/intel_lrc.c
Auto-merging drivers/gpu/drm/i915/intel_engine_cs.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/intel_engine_cs.c
error: Failed to merge in the changes.
hint: Use 'git am --show-current-patch' to see the failed patch
Patch failed at 0001 drm/i915: Replace global_seqno with a hangcheck heartbeat seqno
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2019-02-26 10:52 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-02-26 9:49 [CI 1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Chris Wilson
2019-02-26 9:49 ` [CI 2/4] drm/i915: Remove access to global seqno in the HWSP Chris Wilson
2019-02-26 9:49 ` [CI 3/4] drm/i915: Remove i915_request.global_seqno Chris Wilson
2019-02-26 9:49 ` [CI 4/4] drm/i915/selftests: Exercise resetting during non-user payloads Chris Wilson
2019-02-26 10:52 ` ✗ Fi.CI.BAT: failure for series starting with [CI,1/4] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno Patchwork
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.