diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gpu_error.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gpu_error.c | 153 |
1 files changed, 147 insertions, 6 deletions
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index f020c0086fbc..ec368e700235 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -808,10 +808,15 @@ static void err_print_gt_engines(struct drm_i915_error_state_buf *m, for (ee = gt->engine; ee; ee = ee->next) { const struct i915_vma_coredump *vma; - if (ee->guc_capture_node) - intel_guc_capture_print_engine_node(m, ee); - else + if (gt->uc && gt->uc->guc.is_guc_capture) { + if (ee->guc_capture_node) + intel_guc_capture_print_engine_node(m, ee); + else + err_printf(m, " Missing GuC capture node for %s\n", + ee->engine->name); + } else { error_print_engine(m, ee); + } err_printf(m, " hung: %u\n", ee->hung); err_printf(m, " engine reset count: %u\n", ee->reset_count); @@ -1117,10 +1122,14 @@ i915_vma_coredump_create(const struct intel_gt *gt, mutex_lock(&ggtt->error_mutex); if (ggtt->vm.raw_insert_page) ggtt->vm.raw_insert_page(&ggtt->vm, dma, slot, - I915_CACHE_NONE, 0); + i915_gem_get_pat_index(gt->i915, + I915_CACHE_NONE), + 0); else ggtt->vm.insert_page(&ggtt->vm, dma, slot, - I915_CACHE_NONE, 0); + i915_gem_get_pat_index(gt->i915, + I915_CACHE_NONE), + 0); mb(); s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE); @@ -2162,7 +2171,7 @@ void i915_error_state_store(struct i915_gpu_coredump *error) * i915_capture_error_state - capture an error record for later analysis * @gt: intel_gt which originated the hang * @engine_mask: hung engines - * + * @dump_flags: dump flags * * Should be called when an error is detected (either a hang or an error * interrupt) to capture error state from the time of the error. Fills @@ -2219,3 +2228,135 @@ void i915_disable_error_state(struct drm_i915_private *i915, int err) i915->gpu_error.first_error = ERR_PTR(err); spin_unlock_irq(&i915->gpu_error.lock); } + +#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) +void intel_klog_error_capture(struct intel_gt *gt, + intel_engine_mask_t engine_mask) +{ + static int g_count; + struct drm_i915_private *i915 = gt->i915; + struct i915_gpu_coredump *error; + intel_wakeref_t wakeref; + size_t buf_size = PAGE_SIZE * 128; + size_t pos_err; + char *buf, *ptr, *next; + int l_count = g_count++; + int line = 0; + + /* Can't allocate memory during a reset */ + if (test_bit(I915_RESET_BACKOFF, >->reset.flags)) { + drm_err(>->i915->drm, "[Capture/%d.%d] Inside GT reset, skipping error capture :(\n", + l_count, line++); + return; + } + + error = READ_ONCE(i915->gpu_error.first_error); + if (error) { + drm_err(&i915->drm, "[Capture/%d.%d] Clearing existing error capture first...\n", + l_count, line++); + i915_reset_error_state(i915); + } + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) + error = i915_gpu_coredump(gt, engine_mask, CORE_DUMP_FLAG_NONE); + + if (IS_ERR(error)) { + drm_err(&i915->drm, "[Capture/%d.%d] Failed to capture error capture: %ld!\n", + l_count, line++, PTR_ERR(error)); + return; + } + + buf = kvmalloc(buf_size, GFP_KERNEL); + if (!buf) { + drm_err(&i915->drm, "[Capture/%d.%d] Failed to allocate buffer for error capture!\n", + l_count, line++); + i915_gpu_coredump_put(error); + return; + } + + drm_info(&i915->drm, "[Capture/%d.%d] Dumping i915 error capture for %ps...\n", + l_count, line++, __builtin_return_address(0)); + + /* Largest string length safe to print via dmesg */ +# define MAX_CHUNK 800 + + pos_err = 0; + while (1) { + ssize_t got = i915_gpu_coredump_copy_to_buffer(error, buf, pos_err, buf_size - 1); + + if (got <= 0) + break; + + buf[got] = 0; + pos_err += got; + + ptr = buf; + while (got > 0) { + size_t count; + char tag[2]; + + next = strnchr(ptr, got, '\n'); + if (next) { + count = next - ptr; + *next = 0; + tag[0] = '>'; + tag[1] = '<'; + } else { + count = got; + tag[0] = '}'; + tag[1] = '{'; + } + + if (count > MAX_CHUNK) { + size_t pos; + char *ptr2 = ptr; + + for (pos = MAX_CHUNK; pos < count; pos += MAX_CHUNK) { + char chr = ptr[pos]; + + ptr[pos] = 0; + drm_info(&i915->drm, "[Capture/%d.%d] }%s{\n", + l_count, line++, ptr2); + ptr[pos] = chr; + ptr2 = ptr + pos; + + /* + * If spewing large amounts of data via a serial console, + * this can be a very slow process. So be friendly and try + * not to cause 'softlockup on CPU' problems. + */ + cond_resched(); + } + + if (ptr2 < (ptr + count)) + drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n", + l_count, line++, tag[0], ptr2, tag[1]); + else if (tag[0] == '>') + drm_info(&i915->drm, "[Capture/%d.%d] ><\n", + l_count, line++); + } else { + drm_info(&i915->drm, "[Capture/%d.%d] %c%s%c\n", + l_count, line++, tag[0], ptr, tag[1]); + } + + ptr = next; + got -= count; + if (next) { + ptr++; + got--; + } + + /* As above. */ + cond_resched(); + } + + if (got) + drm_info(&i915->drm, "[Capture/%d.%d] Got %zd bytes remaining!\n", + l_count, line++, got); + } + + kvfree(buf); + + drm_info(&i915->drm, "[Capture/%d.%d] Dumped %zd bytes\n", l_count, line++, pos_err); +} +#endif |