[Intel-gfx] [PATCH v2 1/5] drm/i915: Make i915_engine_info pretty printer to standalone
Mika Kuoppala
mika.kuoppala at linux.intel.com
Mon Oct 9 11:48:30 UTC 2017
Chris Wilson <chris at chris-wilson.co.uk> writes:
> We can use drm_printer to hide the differences between printk and
> seq_printf, and so make the i915_engine_info pretty printer able to be
> called from different contexts and not just debugfs. For instance, I
> want to use the pretty printer to debug kselftests.
>
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala at intel.com>
With this, triaging all kinds of engine problems is easier
and perhaps GEM_ENGINE_BUG_ON or similar might also emerge.
Reviewed-by: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_debugfs.c | 148 +----------------------------
> drivers/gpu/drm/i915/intel_engine_cs.c | 160 ++++++++++++++++++++++++++++++++
> drivers/gpu/drm/i915/intel_ringbuffer.h | 4 +
> 3 files changed, 168 insertions(+), 144 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index f7817c667958..9ec2bcd9a695 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -3292,9 +3292,9 @@ static int i915_display_info(struct seq_file *m, void *unused)
> static int i915_engine_info(struct seq_file *m, void *unused)
> {
> struct drm_i915_private *dev_priv = node_to_i915(m->private);
> - struct i915_gpu_error *error = &dev_priv->gpu_error;
> struct intel_engine_cs *engine;
> enum intel_engine_id id;
> + struct drm_printer p;
>
> intel_runtime_pm_get(dev_priv);
>
> @@ -3303,149 +3303,9 @@ static int i915_engine_info(struct seq_file *m, void *unused)
> seq_printf(m, "Global active requests: %d\n",
> dev_priv->gt.active_requests);
>
> - for_each_engine(engine, dev_priv, id) {
> - struct intel_breadcrumbs *b = &engine->breadcrumbs;
> - struct drm_i915_gem_request *rq;
> - struct rb_node *rb;
> - u64 addr;
> -
> - seq_printf(m, "%s\n", engine->name);
> - seq_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
> - intel_engine_get_seqno(engine),
> - intel_engine_last_submit(engine),
> - engine->hangcheck.seqno,
> - jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
> - engine->timeline->inflight_seqnos);
> - seq_printf(m, "\tReset count: %d\n",
> - i915_reset_engine_count(error, engine));
> -
> - rcu_read_lock();
> -
> - seq_printf(m, "\tRequests:\n");
> -
> - rq = list_first_entry(&engine->timeline->requests,
> - struct drm_i915_gem_request, link);
> - if (&rq->link != &engine->timeline->requests)
> - print_request(m, rq, "\t\tfirst ");
> -
> - rq = list_last_entry(&engine->timeline->requests,
> - struct drm_i915_gem_request, link);
> - if (&rq->link != &engine->timeline->requests)
> - print_request(m, rq, "\t\tlast ");
> -
> - rq = i915_gem_find_active_request(engine);
> - if (rq) {
> - print_request(m, rq, "\t\tactive ");
> - seq_printf(m,
> - "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
> - rq->head, rq->postfix, rq->tail,
> - rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
> - rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
> - }
> -
> - seq_printf(m, "\tRING_START: 0x%08x [0x%08x]\n",
> - I915_READ(RING_START(engine->mmio_base)),
> - rq ? i915_ggtt_offset(rq->ring->vma) : 0);
> - seq_printf(m, "\tRING_HEAD: 0x%08x [0x%08x]\n",
> - I915_READ(RING_HEAD(engine->mmio_base)) & HEAD_ADDR,
> - rq ? rq->ring->head : 0);
> - seq_printf(m, "\tRING_TAIL: 0x%08x [0x%08x]\n",
> - I915_READ(RING_TAIL(engine->mmio_base)) & TAIL_ADDR,
> - rq ? rq->ring->tail : 0);
> - seq_printf(m, "\tRING_CTL: 0x%08x [%s]\n",
> - I915_READ(RING_CTL(engine->mmio_base)),
> - I915_READ(RING_CTL(engine->mmio_base)) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? "waiting" : "");
> -
> - rcu_read_unlock();
> -
> - addr = intel_engine_get_active_head(engine);
> - seq_printf(m, "\tACTHD: 0x%08x_%08x\n",
> - upper_32_bits(addr), lower_32_bits(addr));
> - addr = intel_engine_get_last_batch_head(engine);
> - seq_printf(m, "\tBBADDR: 0x%08x_%08x\n",
> - upper_32_bits(addr), lower_32_bits(addr));
> -
> - if (i915_modparams.enable_execlists) {
> - const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
> - struct intel_engine_execlists * const execlists = &engine->execlists;
> - u32 ptr, read, write;
> - unsigned int idx;
> -
> - seq_printf(m, "\tExeclist status: 0x%08x %08x\n",
> - I915_READ(RING_EXECLIST_STATUS_LO(engine)),
> - I915_READ(RING_EXECLIST_STATUS_HI(engine)));
> -
> - ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
> - read = GEN8_CSB_READ_PTR(ptr);
> - write = GEN8_CSB_WRITE_PTR(ptr);
> - seq_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
> - read, execlists->csb_head,
> - write,
> - intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
> - yesno(test_bit(ENGINE_IRQ_EXECLIST,
> - &engine->irq_posted)));
> - if (read >= GEN8_CSB_ENTRIES)
> - read = 0;
> - if (write >= GEN8_CSB_ENTRIES)
> - write = 0;
> - if (read > write)
> - write += GEN8_CSB_ENTRIES;
> - while (read < write) {
> - idx = ++read % GEN8_CSB_ENTRIES;
> - seq_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n",
> - idx,
> - I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
> - hws[idx * 2],
> - I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)),
> - hws[idx * 2 + 1]);
> - }
> -
> - rcu_read_lock();
> - for (idx = 0; idx < execlists_num_ports(execlists); idx++) {
> - unsigned int count;
> -
> - rq = port_unpack(&execlists->port[idx], &count);
> - if (rq) {
> - seq_printf(m, "\t\tELSP[%d] count=%d, ",
> - idx, count);
> - print_request(m, rq, "rq: ");
> - } else {
> - seq_printf(m, "\t\tELSP[%d] idle\n",
> - idx);
> - }
> - }
> - rcu_read_unlock();
> -
> - spin_lock_irq(&engine->timeline->lock);
> - for (rb = execlists->first; rb; rb = rb_next(rb)) {
> - struct i915_priolist *p =
> - rb_entry(rb, typeof(*p), node);
> -
> - list_for_each_entry(rq, &p->requests,
> - priotree.link)
> - print_request(m, rq, "\t\tQ ");
> - }
> - spin_unlock_irq(&engine->timeline->lock);
> - } else if (INTEL_GEN(dev_priv) > 6) {
> - seq_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
> - I915_READ(RING_PP_DIR_BASE(engine)));
> - seq_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n",
> - I915_READ(RING_PP_DIR_BASE_READ(engine)));
> - seq_printf(m, "\tPP_DIR_DCLV: 0x%08x\n",
> - I915_READ(RING_PP_DIR_DCLV(engine)));
> - }
> -
> - spin_lock_irq(&b->rb_lock);
> - for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
> - struct intel_wait *w = rb_entry(rb, typeof(*w), node);
> -
> - seq_printf(m, "\t%s [%d] waiting for %x\n",
> - w->tsk->comm, w->tsk->pid, w->seqno);
> - }
> - spin_unlock_irq(&b->rb_lock);
> -
> - seq_puts(m, "\n");
> - }
> + p = drm_seq_file_printer(m);
> + for_each_engine(engine, dev_priv, id)
> + intel_engine_dump(engine, &p);
>
> intel_runtime_pm_put(dev_priv);
>
> diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
> index 807a7aafc089..a59b2a30ff5a 100644
> --- a/drivers/gpu/drm/i915/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
> @@ -22,6 +22,8 @@
> *
> */
>
> +#include <drm/drm_print.h>
> +
> #include "i915_drv.h"
> #include "intel_ringbuffer.h"
> #include "intel_lrc.h"
> @@ -1616,6 +1618,164 @@ bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
> }
> }
>
> +static void print_request(struct drm_printer *m,
> + struct drm_i915_gem_request *rq,
> + const char *prefix)
> +{
> + drm_printf(m, "%s%x [%x:%x] prio=%d @ %dms: %s\n", prefix,
> + rq->global_seqno, rq->ctx->hw_id, rq->fence.seqno,
> + rq->priotree.priority,
> + jiffies_to_msecs(jiffies - rq->emitted_jiffies),
> + rq->timeline->common->name);
> +}
> +
> +void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
> +{
> + struct intel_breadcrumbs *b = &engine->breadcrumbs;
> + struct i915_gpu_error *error = &engine->i915->gpu_error;
> + struct drm_i915_private *dev_priv = engine->i915;
> + struct drm_i915_gem_request *rq;
> + struct rb_node *rb;
> + u64 addr;
> +
> + drm_printf(m, "%s\n", engine->name);
> + drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
> + intel_engine_get_seqno(engine),
> + intel_engine_last_submit(engine),
> + engine->hangcheck.seqno,
> + jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
> + engine->timeline->inflight_seqnos);
> + drm_printf(m, "\tReset count: %d\n",
> + i915_reset_engine_count(error, engine));
> +
> + rcu_read_lock();
> +
> + drm_printf(m, "\tRequests:\n");
> +
> + rq = list_first_entry(&engine->timeline->requests,
> + struct drm_i915_gem_request, link);
> + if (&rq->link != &engine->timeline->requests)
> + print_request(m, rq, "\t\tfirst ");
> +
> + rq = list_last_entry(&engine->timeline->requests,
> + struct drm_i915_gem_request, link);
> + if (&rq->link != &engine->timeline->requests)
> + print_request(m, rq, "\t\tlast ");
> +
> + rq = i915_gem_find_active_request(engine);
> + if (rq) {
> + print_request(m, rq, "\t\tactive ");
> + drm_printf(m,
> + "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
> + rq->head, rq->postfix, rq->tail,
> + rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
> + rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
> + }
> +
> + drm_printf(m, "\tRING_START: 0x%08x [0x%08x]\n",
> + I915_READ(RING_START(engine->mmio_base)),
> + rq ? i915_ggtt_offset(rq->ring->vma) : 0);
> + drm_printf(m, "\tRING_HEAD: 0x%08x [0x%08x]\n",
> + I915_READ(RING_HEAD(engine->mmio_base)) & HEAD_ADDR,
> + rq ? rq->ring->head : 0);
> + drm_printf(m, "\tRING_TAIL: 0x%08x [0x%08x]\n",
> + I915_READ(RING_TAIL(engine->mmio_base)) & TAIL_ADDR,
> + rq ? rq->ring->tail : 0);
> + drm_printf(m, "\tRING_CTL: 0x%08x [%s]\n",
> + I915_READ(RING_CTL(engine->mmio_base)),
> + I915_READ(RING_CTL(engine->mmio_base)) & (RING_WAIT | RING_WAIT_SEMAPHORE) ? "waiting" : "");
> +
> + rcu_read_unlock();
> +
> + addr = intel_engine_get_active_head(engine);
> + drm_printf(m, "\tACTHD: 0x%08x_%08x\n",
> + upper_32_bits(addr), lower_32_bits(addr));
> + addr = intel_engine_get_last_batch_head(engine);
> + drm_printf(m, "\tBBADDR: 0x%08x_%08x\n",
> + upper_32_bits(addr), lower_32_bits(addr));
> +
> + if (i915_modparams.enable_execlists) {
> + const u32 *hws = &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
> + struct intel_engine_execlists * const execlists = &engine->execlists;
> + u32 ptr, read, write;
> + unsigned int idx;
> +
> + drm_printf(m, "\tExeclist status: 0x%08x %08x\n",
> + I915_READ(RING_EXECLIST_STATUS_LO(engine)),
> + I915_READ(RING_EXECLIST_STATUS_HI(engine)));
> +
> + ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
> + read = GEN8_CSB_READ_PTR(ptr);
> + write = GEN8_CSB_WRITE_PTR(ptr);
> + drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s\n",
> + read, execlists->csb_head,
> + write,
> + intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
> + yesno(test_bit(ENGINE_IRQ_EXECLIST,
> + &engine->irq_posted)));
> + if (read >= GEN8_CSB_ENTRIES)
> + read = 0;
> + if (write >= GEN8_CSB_ENTRIES)
> + write = 0;
> + if (read > write)
> + write += GEN8_CSB_ENTRIES;
> + while (read < write) {
> + idx = ++read % GEN8_CSB_ENTRIES;
> + drm_printf(m, "\tExeclist CSB[%d]: 0x%08x [0x%08x in hwsp], context: %d [%d in hwsp]\n",
> + idx,
> + I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)),
> + hws[idx * 2],
> + I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx)),
> + hws[idx * 2 + 1]);
> + }
> +
> + rcu_read_lock();
> + for (idx = 0; idx < execlists_num_ports(execlists); idx++) {
> + unsigned int count;
> +
> + rq = port_unpack(&execlists->port[idx], &count);
> + if (rq) {
> + drm_printf(m, "\t\tELSP[%d] count=%d, ",
> + idx, count);
> + print_request(m, rq, "rq: ");
> + } else {
> + drm_printf(m, "\t\tELSP[%d] idle\n",
> + idx);
> + }
> + }
> + rcu_read_unlock();
> +
> + spin_lock_irq(&engine->timeline->lock);
> + for (rb = execlists->first; rb; rb = rb_next(rb)) {
> + struct i915_priolist *p =
> + rb_entry(rb, typeof(*p), node);
> +
> + list_for_each_entry(rq, &p->requests,
> + priotree.link)
> + print_request(m, rq, "\t\tQ ");
> + }
> + spin_unlock_irq(&engine->timeline->lock);
> + } else if (INTEL_GEN(dev_priv) > 6) {
> + drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
> + I915_READ(RING_PP_DIR_BASE(engine)));
> + drm_printf(m, "\tPP_DIR_BASE_READ: 0x%08x\n",
> + I915_READ(RING_PP_DIR_BASE_READ(engine)));
> + drm_printf(m, "\tPP_DIR_DCLV: 0x%08x\n",
> + I915_READ(RING_PP_DIR_DCLV(engine)));
> + }
> +
> + spin_lock_irq(&b->rb_lock);
> + for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
> + struct intel_wait *w = rb_entry(rb, typeof(*w), node);
> +
> + drm_printf(m, "\t%s [%d] waiting for %x\n",
> + w->tsk->comm, w->tsk->pid, w->seqno);
> + }
> + spin_unlock_irq(&b->rb_lock);
> +
> + drm_printf(m, "\n");
> +}
> +
> #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
> #include "selftests/mock_engine.c"
> #endif
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 0fedda17488c..17186f067408 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -7,6 +7,8 @@
> #include "i915_gem_timeline.h"
> #include "i915_selftest.h"
>
> +struct drm_printer;
> +
> #define I915_CMD_HASH_ORDER 9
>
> /* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
> @@ -839,4 +841,6 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915);
>
> bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
>
> +void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *p);
> +
> #endif /* _INTEL_RINGBUFFER_H_ */
> --
> 2.14.2
More information about the Intel-gfx
mailing list