diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gpu_error.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gpu_error.c | 34 |
1 files changed, 26 insertions, 8 deletions
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 594341e27a47..2a4cd0ba5464 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -37,6 +37,7 @@ #include <drm/drm_print.h> #include "display/intel_atomic.h" +#include "display/intel_csr.h" #include "display/intel_overlay.h" #include "gem/i915_gem_context.h" @@ -47,7 +48,6 @@ #include "i915_gpu_error.h" #include "i915_memcpy.h" #include "i915_scatterlist.h" -#include "intel_csr.h" #define ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN) #define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN) @@ -450,6 +450,14 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m, err_printf(m, " ROW_INSTDONE[%d][%d]: 0x%08x\n", slice, subslice, ee->instdone.row[slice][subslice]); + + if (INTEL_GEN(m->i915) < 12) + return; + + err_printf(m, " SC_INSTDONE_EXTRA: 0x%08x\n", + ee->instdone.slice_common_extra[0]); + err_printf(m, " SC_INSTDONE_EXTRA2: 0x%08x\n", + ee->instdone.slice_common_extra[1]); } static void error_print_request(struct drm_i915_error_state_buf *m, @@ -473,9 +481,13 @@ static void error_print_context(struct drm_i915_error_state_buf *m, const char *header, const struct i915_gem_context_coredump *ctx) { - err_printf(m, "%s%s[%d] prio %d, guilty %d active %d\n", + const u32 period = RUNTIME_INFO(m->i915)->cs_timestamp_period_ns; + + err_printf(m, "%s%s[%d] prio %d, guilty %d active %d, runtime total %lluns, avg %lluns\n", header, ctx->comm, ctx->pid, ctx->sched_attr.priority, - ctx->guilty, ctx->active); + ctx->guilty, ctx->active, + ctx->total_runtime * period, + mul_u32_u32(ctx->avg_runtime, period)); } static struct i915_vma_coredump * @@ -515,6 +527,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m, (u32)(ee->acthd>>32), (u32)ee->acthd); err_printf(m, " IPEIR: 0x%08x\n", ee->ipeir); err_printf(m, " IPEHR: 0x%08x\n", ee->ipehr); + err_printf(m, " ESR: 0x%08x\n", ee->esr); error_print_instdone(m, ee); @@ -1102,6 +1115,7 @@ static void engine_record_registers(struct intel_engine_coredump *ee) } if (INTEL_GEN(i915) >= 4) { + ee->esr = ENGINE_READ(engine, RING_ESR); ee->faddr = ENGINE_READ(engine, RING_DMA_FADD); ee->ipeir = ENGINE_READ(engine, RING_IPEIR); ee->ipehr = ENGINE_READ(engine, RING_IPEHR); @@ -1228,7 +1242,7 @@ static bool record_context(struct i915_gem_context_coredump *e, { struct i915_gem_context *ctx; struct task_struct *task; - bool capture; + bool simulated; rcu_read_lock(); ctx = rcu_dereference(rq->context->gem_context); @@ -1236,7 +1250,7 @@ static bool record_context(struct i915_gem_context_coredump *e, ctx = NULL; rcu_read_unlock(); if (!ctx) - return false; + return true; rcu_read_lock(); task = pid_task(ctx->pid, PIDTYPE_PID); @@ -1250,10 +1264,13 @@ static bool record_context(struct i915_gem_context_coredump *e, e->guilty = atomic_read(&ctx->guilty_count); e->active = atomic_read(&ctx->active_count); - capture = i915_gem_context_no_error_capture(ctx); + e->total_runtime = rq->context->runtime.total; + e->avg_runtime = ewma_runtime_read(&rq->context->runtime.avg); + + simulated = i915_gem_context_no_error_capture(ctx); i915_gem_context_put(ctx); - return capture; + return simulated; } struct intel_engine_capture_vma { @@ -1852,7 +1869,8 @@ void i915_error_state_store(struct i915_gpu_coredump *error) if (!xchg(&warned, true) && ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) { pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n"); - pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n"); + pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n"); + pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n"); pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n"); pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n"); pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n", |