diff options
Diffstat (limited to 'drivers/gpu')
35 files changed, 1287 insertions, 930 deletions
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 27b0e34..20689f1 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -79,10 +79,8 @@ static int i915_capabilities(struct seq_file *m, void *data) seq_printf(m, "gen: %d\n", INTEL_GEN(dev_priv)); seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev_priv)); #define PRINT_FLAG(x) seq_printf(m, #x ": %s\n", yesno(info->x)) -#define SEP_SEMICOLON ; - DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_SEMICOLON); + DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG -#undef SEP_SEMICOLON return 0; } @@ -645,6 +643,23 @@ static int i915_gem_batch_pool_info(struct seq_file *m, void *data) return 0; } +static void print_request(struct seq_file *m, + struct drm_i915_gem_request *rq, + const char *prefix) +{ + struct pid *pid = rq->ctx->pid; + struct task_struct *task; + + rcu_read_lock(); + task = pid ? pid_task(pid, PIDTYPE_PID) : NULL; + seq_printf(m, "%s%x [%x:%x] @ %d: %s [%d]\n", prefix, + rq->fence.seqno, rq->ctx->hw_id, rq->fence.seqno, + jiffies_to_msecs(jiffies - rq->emitted_jiffies), + task ? task->comm : "<unknown>", + task ? task->pid : -1); + rcu_read_unlock(); +} + static int i915_gem_request_info(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -668,19 +683,8 @@ static int i915_gem_request_info(struct seq_file *m, void *data) continue; seq_printf(m, "%s requests: %d\n", engine->name, count); - list_for_each_entry(req, &engine->request_list, link) { - struct pid *pid = req->ctx->pid; - struct task_struct *task; - - rcu_read_lock(); - task = pid ? pid_task(pid, PIDTYPE_PID) : NULL; - seq_printf(m, " %x @ %d: %s [%d]\n", - req->fence.seqno, - (int) (jiffies - req->emitted_jiffies), - task ? task->comm : "<unknown>", - task ? task->pid : -1); - rcu_read_unlock(); - } + list_for_each_entry(req, &engine->request_list, link) + print_request(m, req, " "); any++; } @@ -1277,15 +1281,42 @@ out: return ret; } +static void i915_instdone_info(struct drm_i915_private *dev_priv, + struct seq_file *m, + struct intel_instdone *instdone) +{ + int slice; + int subslice; + + seq_printf(m, "\t\tINSTDONE: 0x%08x\n", + instdone->instdone); + + if (INTEL_GEN(dev_priv) <= 3) + return; + + seq_printf(m, "\t\tSC_INSTDONE: 0x%08x\n", + instdone->slice_common); + + if (INTEL_GEN(dev_priv) <= 6) + return; + + for_each_instdone_slice_subslice(dev_priv, slice, subslice) + seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, instdone->sampler[slice][subslice]); + + for_each_instdone_slice_subslice(dev_priv, slice, subslice) + seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, instdone->row[slice][subslice]); +} + static int i915_hangcheck_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); struct intel_engine_cs *engine; u64 acthd[I915_NUM_ENGINES]; u32 seqno[I915_NUM_ENGINES]; - u32 instdone[I915_NUM_INSTDONE_REG]; + struct intel_instdone instdone; enum intel_engine_id id; - int j; if (test_bit(I915_WEDGED, &dev_priv->gpu_error.flags)) seq_printf(m, "Wedged\n"); @@ -1308,7 +1339,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) seqno[id] = intel_engine_get_seqno(engine); } - i915_get_extra_instdone(dev_priv, instdone); + i915_get_engine_instdone(dev_priv, RCS, &instdone); intel_runtime_pm_put(dev_priv); @@ -1320,6 +1351,9 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) seq_printf(m, "Hangcheck inactive\n"); for_each_engine_id(engine, dev_priv, id) { + struct intel_breadcrumbs *b = &engine->breadcrumbs; + struct rb_node *rb; + seq_printf(m, "%s:\n", engine->name); seq_printf(m, "\tseqno = %x [current %x, last %x]\n", engine->hangcheck.seqno, @@ -1329,6 +1363,15 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) yesno(intel_engine_has_waiter(engine)), yesno(test_bit(engine->id, &dev_priv->gpu_error.missed_irq_rings))); + spin_lock(&b->lock); + for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) { + struct intel_wait *w = container_of(rb, typeof(*w), node); + + seq_printf(m, "\t%s [%d] waiting for %x\n", + w->tsk->comm, w->tsk->pid, w->seqno); + } + spin_unlock(&b->lock); + seq_printf(m, "\tACTHD = 0x%08llx [current 0x%08llx]\n", (long long)engine->hangcheck.acthd, (long long)acthd[id]); @@ -1336,18 +1379,14 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) seq_printf(m, "\taction = %d\n", engine->hangcheck.action); if (engine->id == RCS) { - seq_puts(m, "\tinstdone read ="); + seq_puts(m, "\tinstdone read =\n"); - for (j = 0; j < I915_NUM_INSTDONE_REG; j++) - seq_printf(m, " 0x%08x", instdone[j]); + i915_instdone_info(dev_priv, m, &instdone); - seq_puts(m, "\n\tinstdone accu ="); + seq_puts(m, "\tinstdone accu =\n"); - for (j = 0; j < I915_NUM_INSTDONE_REG; j++) - seq_printf(m, " 0x%08x", - engine->hangcheck.instdone[j]); - - seq_puts(m, "\n"); + i915_instdone_info(dev_priv, m, + &engine->hangcheck.instdone); } } @@ -1635,7 +1674,8 @@ static int i915_fbc_status(struct seq_file *m, void *unused) seq_printf(m, "FBC disabled: %s\n", dev_priv->fbc.no_fbc_reason); - if (INTEL_GEN(dev_priv) >= 7) + if (intel_fbc_is_active(dev_priv) && + INTEL_GEN(dev_priv) >= 7) seq_printf(m, "Compressing: %s\n", yesno(I915_READ(FBC_STATUS2) & FBC_COMPRESSION_MASK)); @@ -2022,84 +2062,6 @@ static int i915_dump_lrc(struct seq_file *m, void *unused) return 0; } -static int i915_execlists(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; - struct intel_engine_cs *engine; - u32 status_pointer; - u8 read_pointer; - u8 write_pointer; - u32 status; - u32 ctx_id; - struct list_head *cursor; - int i, ret; - - if (!i915.enable_execlists) { - seq_puts(m, "Logical Ring Contexts are disabled\n"); - return 0; - } - - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; - - intel_runtime_pm_get(dev_priv); - - for_each_engine(engine, dev_priv) { - struct drm_i915_gem_request *head_req = NULL; - int count = 0; - - seq_printf(m, "%s\n", engine->name); - - status = I915_READ(RING_EXECLIST_STATUS_LO(engine)); - ctx_id = I915_READ(RING_EXECLIST_STATUS_HI(engine)); - seq_printf(m, "\tExeclist status: 0x%08X, context: %u\n", - status, ctx_id); - - status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(engine)); - seq_printf(m, "\tStatus pointer: 0x%08X\n", status_pointer); - - read_pointer = GEN8_CSB_READ_PTR(status_pointer); - write_pointer = GEN8_CSB_WRITE_PTR(status_pointer); - if (read_pointer > write_pointer) - write_pointer += GEN8_CSB_ENTRIES; - seq_printf(m, "\tRead pointer: 0x%08X, write pointer 0x%08X\n", - read_pointer, write_pointer); - - for (i = 0; i < GEN8_CSB_ENTRIES; i++) { - status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, i)); - ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, i)); - - seq_printf(m, "\tStatus buffer %d: 0x%08X, context: %u\n", - i, status, ctx_id); - } - - spin_lock_bh(&engine->execlist_lock); - list_for_each(cursor, &engine->execlist_queue) - count++; - head_req = list_first_entry_or_null(&engine->execlist_queue, - struct drm_i915_gem_request, - execlist_link); - spin_unlock_bh(&engine->execlist_lock); - - seq_printf(m, "\t%d requests in queue\n", count); - if (head_req) { - seq_printf(m, "\tHead request context: %u\n", - head_req->ctx->hw_id); - seq_printf(m, "\tHead request tail: %u\n", - head_req->tail); - } - - seq_putc(m, '\n'); - } - - intel_runtime_pm_put(dev_priv); - mutex_unlock(&dev->struct_mutex); - - return 0; -} - static const char *swizzle_string(unsigned swizzle) { switch (swizzle) { @@ -3121,6 +3083,133 @@ static int i915_display_info(struct seq_file *m, void *unused) return 0; } +static int i915_engine_info(struct seq_file *m, void *unused) +{ + struct drm_i915_private *dev_priv = node_to_i915(m->private); + struct intel_engine_cs *engine; + + for_each_engine(engine, dev_priv) { + 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 [score %d]\n", + intel_engine_get_seqno(engine), + engine->last_submitted_seqno, + engine->hangcheck.seqno, + engine->hangcheck.score); + + rcu_read_lock(); + + seq_printf(m, "\tRequests:\n"); + + rq = list_first_entry(&engine->request_list, + struct drm_i915_gem_request, link); + if (&rq->link != &engine->request_list) + print_request(m, rq, "\t\tfirst "); + + rq = list_last_entry(&engine->request_list, + struct drm_i915_gem_request, link); + if (&rq->link != &engine->request_list) + 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.enable_execlists) { + u32 ptr, read, write; + + 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, write %d\n", + read, write); + if (read >= GEN8_CSB_ENTRIES) + read = 0; + if (write >= GEN8_CSB_ENTRIES) + write = 0; + if (read > write) + write += GEN8_CSB_ENTRIES; + while (read < write) { + unsigned int idx = ++read % GEN8_CSB_ENTRIES; + + seq_printf(m, "\tExeclist CSB[%d]: 0x%08x, context: %d\n", + idx, + I915_READ(RING_CONTEXT_STATUS_BUF_LO(engine, idx)), + I915_READ(RING_CONTEXT_STATUS_BUF_HI(engine, idx))); + } + + rcu_read_lock(); + rq = READ_ONCE(engine->execlist_port[0].request); + if (rq) + print_request(m, rq, "\t\tELSP[0] "); + else + seq_printf(m, "\t\tELSP[0] idle\n"); + rq = READ_ONCE(engine->execlist_port[1].request); + if (rq) + print_request(m, rq, "\t\tELSP[1] "); + else + seq_printf(m, "\t\tELSP[1] idle\n"); + rcu_read_unlock(); + } 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(&b->lock); + for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) { + struct intel_wait *w = container_of(rb, typeof(*w), node); + + seq_printf(m, "\t%s [%d] waiting for %x\n", + w->tsk->comm, w->tsk->pid, w->seqno); + } + spin_unlock(&b->lock); + + seq_puts(m, "\n"); + } + + return 0; +} + static int i915_semaphore_status(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -5275,7 +5364,6 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_framebuffer", i915_gem_framebuffer_info, 0}, {"i915_context_status", i915_context_status, 0}, {"i915_dump_lrc", i915_dump_lrc, 0}, - {"i915_execlists", i915_execlists, 0}, {"i915_forcewake_domains", i915_forcewake_domains, 0}, {"i915_swizzle_info", i915_swizzle_info, 0}, {"i915_ppgtt_info", i915_ppgtt_info, 0}, @@ -5287,6 +5375,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_power_domain_info", i915_power_domain_info, 0}, {"i915_dmc_info", i915_dmc_info, 0}, {"i915_display_info", i915_display_info, 0}, + {"i915_engine_info", i915_engine_info, 0}, {"i915_semaphore_status", i915_semaphore_status, 0}, {"i915_shared_dplls_info", i915_shared_dplls_info, 0}, {"i915_dp_mst_info", i915_dp_mst_info, 0}, diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index bfb2efd..89d3222 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -771,6 +771,19 @@ static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv) destroy_workqueue(dev_priv->wq); } +/* + * We don't keep the workarounds for pre-production hardware, so we expect our + * driver to fail on these machines in one way or another. A little warning on + * dmesg may help both the user and the bug triagers. + */ +static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) +{ + if (IS_HSW_EARLY_SDV(dev_priv) || + IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0)) + DRM_ERROR("This is a pre-production stepping. " + "It may not be fully functional.\n"); +} + /** * i915_driver_init_early - setup state not requiring device access * @dev_priv: device private @@ -838,13 +851,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, intel_device_info_dump(dev_priv); - /* Not all pre-production machines fall into this category, only the - * very first ones. Almost everything should work, except for maybe - * suspend/resume. And we don't implement workarounds that affect only - * pre-production machines. */ - if (IS_HSW_EARLY_SDV(dev_priv)) - DRM_INFO("This is an early pre-production Haswell machine. " - "It may not be fully functional.\n"); + intel_detect_preproduction_hw(dev_priv); return 0; @@ -1721,6 +1728,21 @@ int i915_resume_switcheroo(struct drm_device *dev) return i915_drm_resume(dev); } +static void disable_engines_irq(struct drm_i915_private *dev_priv) +{ + struct intel_engine_cs *engine; + + /* Ensure irq handler finishes, and not run again. */ + disable_irq(dev_priv->drm.irq); + for_each_engine(engine, dev_priv) + tasklet_kill(&engine->irq_tasklet); +} + +static void enable_engines_irq(struct drm_i915_private *dev_priv) +{ + enable_irq(dev_priv->drm.irq); +} + /** * i915_reset - reset chip after a hang * @dev: drm device to reset @@ -1754,7 +1776,11 @@ void i915_reset(struct drm_i915_private *dev_priv) error->reset_count++; pr_notice("drm/i915: Resetting chip after gpu hang\n"); + + disable_engines_irq(dev_priv); ret = intel_gpu_reset(dev_priv, ALL_ENGINES); + enable_engines_irq(dev_priv); + if (ret) { if (ret != -ENODEV) DRM_ERROR("Failed to reset chip: %i\n", ret); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8b9ee4e..54d860e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -70,7 +70,7 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20160919" +#define DRIVER_DATE "20161010" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@ -185,6 +185,7 @@ enum plane { #define sprite_name(p, s) ((p) * INTEL_INFO(dev)->num_sprites[(p)] + (s) + 'A') enum port { + PORT_NONE = -1, PORT_A = 0, PORT_B, PORT_C, @@ -581,13 +582,25 @@ struct intel_uncore_funcs { uint32_t val, bool trace); }; +struct intel_forcewake_range { + u32 start; + u32 end; + + enum forcewake_domains domains; +}; + struct intel_uncore { spinlock_t lock; /** lock is also taken in irq contexts. */ + const struct intel_forcewake_range *fw_domains_table; + unsigned int fw_domains_table_entries; + struct intel_uncore_funcs funcs; unsigned fifo_count; + enum forcewake_domains fw_domains; + enum forcewake_domains fw_domains_active; struct intel_uncore_forcewake_domain { struct drm_i915_private *i915; @@ -633,54 +646,53 @@ struct intel_csr { uint32_t allowed_dc_mask; }; -#define DEV_INFO_FOR_EACH_FLAG(func, sep) \ - func(is_mobile) sep \ - func(is_i85x) sep \ - func(is_i915g) sep \ - func(is_i945gm) sep \ - func(is_g33) sep \ - func(hws_needs_physical) sep \ - func(is_g4x) sep \ - func(is_pineview) sep \ - func(is_broadwater) sep \ - func(is_crestline) sep \ - func(is_ivybridge) sep \ - func(is_valleyview) sep \ - func(is_cherryview) sep \ - func(is_haswell) sep \ - func(is_broadwell) sep \ - func(is_skylake) sep \ - func(is_broxton) sep \ - func(is_kabylake) sep \ - func(is_preliminary) sep \ - func(has_fbc) sep \ - func(has_psr) sep \ - func(has_runtime_pm) sep \ - func(has_csr) sep \ - func(has_resource_streamer) sep \ - func(has_rc6) sep \ - func(has_rc6p) sep \ - func(has_dp_mst) sep \ - func(has_gmbus_irq) sep \ - func(has_hw_contexts) sep \ - func(has_logical_ring_contexts) sep \ - func(has_l3_dpf) sep \ - func(has_gmch_display) sep \ - func(has_guc) sep \ - func(has_pipe_cxsr) sep \ - func(has_hotplug) sep \ - func(cursor_needs_physical) sep \ - func(has_overlay) sep \ - func(overlay_needs_physical) sep \ - func(supports_tv) sep \ - func(has_llc) sep \ - func(has_snoop) sep \ - func(has_ddi) sep \ - func(has_fpga_dbg) sep \ - func(has_pooled_eu) - -#define DEFINE_FLAG(name) u8 name:1 -#define SEP_SEMICOLON ; +#define DEV_INFO_FOR_EACH_FLAG(func) \ + /* Keep is_* in chronological order */ \ + func(is_mobile); \ + func(is_i85x); \ + func(is_i915g); \ + func(is_i945gm); \ + func(is_g33); \ + func(is_g4x); \ + func(is_pineview); \ + func(is_broadwater); \ + func(is_crestline); \ + func(is_ivybridge); \ + func(is_valleyview); \ + func(is_cherryview); \ + func(is_haswell); \ + func(is_broadwell); \ + func(is_skylake); \ + func(is_broxton); \ + func(is_kabylake); \ + func(is_preliminary); \ + /* Keep has_* in alphabetical order */ \ + func(has_csr); \ + func(has_ddi); \ + func(has_dp_mst); \ + func(has_fbc); \ + func(has_fpga_dbg); \ + func(has_gmbus_irq); \ + func(has_gmch_display); \ + func(has_guc); \ + func(has_hotplug); \ + func(has_hw_contexts); \ + func(has_l3_dpf); \ + func(has_llc); \ + func(has_logical_ring_contexts); \ + func(has_overlay); \ + func(has_pipe_cxsr); \ + func(has_pooled_eu); \ + func(has_psr); \ + func(has_rc6); \ + func(has_rc6p); \ + func(has_resource_streamer); \ + func(has_runtime_pm); \ + func(has_snoop); \ + func(cursor_needs_physical); \ + func(hws_needs_physical); \ + func(overlay_needs_physical); \ + func(supports_tv) struct sseu_dev_info { u8 slice_mask; @@ -709,7 +721,9 @@ struct intel_device_info { u16 gen_mask; u8 ring_mask; /* Rings supported by the HW */ u8 num_rings; - DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON); +#define DEFINE_FLAG(name) u8 name:1 + DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG); +#undef DEFINE_FLAG u16 ddb_size; /* in blocks */ /* Register offsets for the various display pipes and transcoders */ int pipe_offsets[I915_MAX_TRANSCODERS]; @@ -726,9 +740,6 @@ struct intel_device_info { } color; }; -#undef DEFINE_FLAG -#undef SEP_SEMICOLON - struct intel_display_error_state; struct drm_i915_error_state { @@ -759,7 +770,7 @@ struct drm_i915_error_state { u32 gam_ecochk; u32 gab_ctl; u32 gfx_mode; - u32 extra_instdone[I915_NUM_INSTDONE_REG]; + u64 fence[I915_MAX_NUM_FENCES]; struct intel_overlay_error_state *overlay; struct intel_display_error_state *display; @@ -775,6 +786,9 @@ struct drm_i915_error_state { struct i915_address_space *vm; int num_requests; + /* position of active request inside the ring */ + u32 rq_head, rq_post, rq_tail; + /* our own tracking of ring head and tail */ u32 cpu_ring_head; u32 cpu_ring_tail; @@ -791,7 +805,6 @@ struct drm_i915_error_state { u32 hws; u32 ipeir; u32 ipehr; - u32 instdone; u32 bbstate; u32 instpm; u32 instps; @@ -802,6 +815,7 @@ struct drm_i915_error_state { u64 faddr; u32 rc_psmi; /* sleep state */ u32 semaphore_mboxes[I915_NUM_ENGINES - 1]; + struct intel_instdone instdone; struct drm_i915_error_object { int page_count; @@ -972,6 +986,9 @@ struct intel_fbc { bool enabled; bool active; + bool underrun_detected; + struct work_struct underrun_work; + struct intel_fbc_state_cache { struct { unsigned int mode_flags; @@ -2079,7 +2096,8 @@ struct drm_i915_private { /* perform PHY state sanity checks? */ bool chv_phy_assert[2]; - struct intel_encoder *dig_port_map[I915_MAX_PORTS]; + /* Used to save the pipe-to-encoder mapping for audio */ + struct intel_encoder *av_enc_map[I915_MAX_PIPES]; /* * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch @@ -2883,6 +2901,11 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level, extern long i915_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); #endif +extern const struct dev_pm_ops i915_pm_ops; + +extern int i915_driver_load(struct pci_dev *pdev, + const struct pci_device_id *ent); +extern void i915_driver_unload(struct drm_device *dev); extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask); extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv); extern void i915_reset(struct drm_i915_private *dev_priv); @@ -3541,7 +3564,9 @@ void i915_error_state_get(struct drm_device *dev, void i915_error_state_put(struct i915_error_state_file_priv *error_priv); void i915_destroy_error_state(struct drm_device *dev); -void i915_get_extra_instdone(struct drm_i915_private *dev_priv, uint32_t *instdone); +void i915_get_engine_instdone(struct drm_i915_private *dev_priv, + enum intel_engine_id engine_id, + struct intel_instdone *instdone); const char *i915_cache_level_str(struct drm_i915_private *i915, int type); /* i915_cmd_parser.c */ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 1418c1c..fdd496e 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1813,8 +1813,7 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf) view.params.partial.offset = rounddown(page_offset, chunk_size); view.params.partial.size = min_t(unsigned int, chunk_size, - (area->vm_end - area->vm_start) / PAGE_SIZE - - view.params.partial.offset); + vma_pages(area) - view.params.partial.offset); /* If the partial covers the entire object, just create a * normal VMA. @@ -2208,6 +2207,15 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) return 0; } +static unsigned long swiotlb_max_size(void) +{ +#if IS_ENABLED(CONFIG_SWIOTLB) + return rounddown(swiotlb_nr_tbl() << IO_TLB_SHIFT, PAGE_SIZE); +#else + return 0; +#endif +} + static int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) { @@ -2219,6 +2227,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) struct sgt_iter sgt_iter; struct page *page; unsigned long last_pfn = 0; /* suppress gcc warning */ + unsigned long max_segment; int ret; gfp_t gfp; @@ -2229,6 +2238,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS); BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS); + max_segment = swiotlb_max_size(); + if (!max_segment) + max_segment = obj->base.size; + st = kmalloc(sizeof(*st), GFP_KERNEL); if (st == NULL) return -ENOMEM; @@ -2264,22 +2277,15 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) * our own buffer, now let the real VM do its job and * go down in flames if truly OOM. */ - i915_gem_shrink_all(dev_priv); page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) { ret = PTR_ERR(page); goto err_pages; } } -#ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl()) { - st->nents++; - sg_set_page(sg, page, PAGE_SIZE, 0); - sg = sg_next(sg); - continue; - } -#endif - if (!i || page_to_pfn(page) != last_pfn + 1) { + if (!i || + sg->length >= max_segment || + page_to_pfn(page) != last_pfn + 1) { if (i) sg = sg_next(sg); st->nents++; @@ -2292,9 +2298,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) /* Check that the i965g/gm workaround works. */ WARN_ON((gfp & __GFP_DMA32) && (last_pfn >= 0x00100000UL)); } -#ifdef CONFIG_SWIOTLB - if (!swiotlb_nr_tbl()) -#endif + if (sg) /* loop terminated early; short sg table */ sg_mark_end(sg); obj->pages = st; @@ -2581,8 +2585,6 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine) struct i915_gem_context *incomplete_ctx; bool ring_hung; - /* Ensure irq handler finishes, and not run again. */ - tasklet_kill(&engine->irq_tasklet); if (engine->irq_seqno_barrier) engine->irq_seqno_barrier(engine); @@ -2591,6 +2593,9 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine) return; ring_hung = engine->hangcheck.score >= HANGCHECK_SCORE_RING_HUNG; + if (engine->hangcheck.seqno != intel_engine_get_seqno(engine)) + ring_hung = false; + i915_set_reset_status(request->ctx, ring_hung); if (!ring_hung) return; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 222796f..72c7c18 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -429,7 +429,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, } if (cache->vaddr) { - io_mapping_unmap_atomic(unmask_page(cache->vaddr)); + io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); } else { struct i915_vma *vma; int ret; @@ -474,7 +474,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, offset += page << PAGE_SHIFT; } - vaddr = io_mapping_map_atomic_wc(&cache->i915->ggtt.mappable, offset); + vaddr = (void __force *) io_mapping_map_atomic_wc(&cache->i915->ggtt.mappable, offset); cache->page = page; cache->vaddr = (unsigned long)vaddr; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 334f15d..b5b5869 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -228,13 +228,43 @@ static const char *hangcheck_action_to_str(enum intel_engine_hangcheck_action a) return "unknown"; } +static void error_print_instdone(struct drm_i915_error_state_buf *m, + struct drm_i915_error_engine *ee) +{ + int slice; + int subslice; + + err_printf(m, " INSTDONE: 0x%08x\n", + ee->instdone.instdone); + + if (ee->engine_id != RCS || INTEL_GEN(m->i915) <= 3) + return; + + err_printf(m, " SC_INSTDONE: 0x%08x\n", + ee->instdone.slice_common); + + if (INTEL_GEN(m->i915) <= 6) + return; + + for_each_instdone_slice_subslice(m->i915, slice, subslice) + err_printf(m, " SAMPLER_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, + ee->instdone.sampler[slice][subslice]); + + for_each_instdone_slice_subslice(m->i915, slice, subslice) + err_printf(m, " ROW_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, + ee->instdone.row[slice][subslice]); +} + static void error_print_engine(struct drm_i915_error_state_buf *m, struct drm_i915_error_engine *ee) { err_printf(m, "%s command stream:\n", engine_str(ee->engine_id)); err_printf(m, " START: 0x%08x\n", ee->start); - err_printf(m, " HEAD: 0x%08x\n", ee->head); - err_printf(m, " TAIL: 0x%08x\n", ee->tail); + err_printf(m, " HEAD: 0x%08x\n [0x%08x]", ee->head, ee->rq_head); + err_printf(m, " TAIL: 0x%08x [0x%08x, 0x%08x]\n", + ee->tail, ee->rq_post, ee->rq_tail); err_printf(m, " CTL: 0x%08x\n", ee->ctl); err_printf(m, " MODE: 0x%08x\n", ee->mode); err_printf(m, " HWS: 0x%08x\n", ee->hws); @@ -242,7 +272,9 @@ 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, " INSTDONE: 0x%08x\n", ee->instdone); + + error_print_instdone(m, ee); + if (ee->batchbuffer) { u64 start = ee->batchbuffer->gtt_offset; u64 end = start + ee->batchbuffer->gtt_size; @@ -325,10 +357,8 @@ static void err_print_capabilities(struct drm_i915_error_state_buf *m, const struct intel_device_info *info) { #define PRINT_FLAG(x) err_printf(m, #x ": %s\n", yesno(info->x)) -#define SEP_SEMICOLON ; - DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_SEMICOLON); + DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG -#undef SEP_SEMICOLON } int i915_error_state_to_str(struct drm_i915_error_state_buf *m, @@ -402,10 +432,6 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, for (i = 0; i < dev_priv->num_fence_regs; i++) err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); - for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++) - err_printf(m, " INSTDONE_%d: 0x%08x\n", i, - error->extra_instdone[i]); - if (INTEL_INFO(dev)->gen >= 6) { err_printf(m, "ERROR: 0x%08x\n", error->error); @@ -855,7 +881,8 @@ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv, if (engine_id) *engine_id = i; - return error->engine[i].ipehr ^ error->engine[i].instdone; + return error->engine[i].ipehr ^ + error->engine[i].instdone.instdone; } } @@ -998,7 +1025,6 @@ static void error_record_engine_registers(struct drm_i915_error_state *error, ee->faddr = I915_READ(RING_DMA_FADD(engine->mmio_base)); ee->ipeir = I915_READ(RING_IPEIR(engine->mmio_base)); ee->ipehr = I915_READ(RING_IPEHR(engine->mmio_base)); - ee->instdone = I915_READ(RING_INSTDONE(engine->mmio_base)); ee->instps = I915_READ(RING_INSTPS(engine->mmio_base)); ee->bbaddr = I915_READ(RING_BBADDR(engine->mmio_base)); if (INTEL_GEN(dev_priv) >= 8) { @@ -1010,9 +1036,10 @@ static void error_record_engine_registers(struct drm_i915_error_state *error, ee->faddr = I915_READ(DMA_FADD_I8XX); ee->ipeir = I915_READ(IPEIR); ee->ipehr = I915_READ(IPEHR); - ee->instdone = I915_READ(GEN2_INSTDONE); } + i915_get_engine_instdone(dev_priv, engine->id, &ee->instdone); + ee->waiting = intel_engine_has_waiter(engine); ee->instpm = I915_READ(RING_INSTPM(engine->mmio_base)); ee->acthd = intel_engine_get_active_head(engine); @@ -1202,6 +1229,10 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, error->simulated |= request->ctx->flags & CONTEXT_NO_ERROR_CAPTURE; + ee->rq_head = request->head; + ee->rq_post = request->postfix; + ee->rq_tail = request->tail; + ring = request->ring; ee->cpu_ring_head = ring->head; ee->cpu_ring_tail = ring->tail; @@ -1372,8 +1403,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, } error->eir = I915_READ(EIR); error->pgtbl_er = I915_READ(PGTBL_ER); - - i915_get_extra_instdone(dev_priv, error->extra_instdone); } static void i915_error_capture_msg(struct drm_i915_private *dev_priv, @@ -1531,21 +1560,95 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type) } } +static inline uint32_t +read_subslice_reg(struct drm_i915_private *dev_priv, int slice, + int subslice, i915_reg_t reg) +{ + uint32_t mcr; + uint32_t ret; + enum forcewake_domains fw_domains; + + fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, + FW_REG_READ); + fw_domains |= intel_uncore_forcewake_for_reg(dev_priv, + GEN8_MCR_SELECTOR, + FW_REG_READ | FW_REG_WRITE); + + spin_lock_irq(&dev_priv->uncore.lock); + intel_uncore_forcewake_get__locked(dev_priv, fw_domains); + + mcr = I915_READ_FW(GEN8_MCR_SELECTOR); + /* + * The HW expects the slice and sublice selectors to be reset to 0 + * after reading out the registers. + */ + WARN_ON_ONCE(mcr & (GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK)); + mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK); + mcr |= GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice); + I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); + + ret = I915_READ_FW(reg); + + mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK); + I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr); + + intel_uncore_forcewake_put__locked(dev_priv, fw_domains); + spin_unlock_irq(&dev_priv->uncore.lock); + + return ret; +} + /* NB: please notice the memset */ -void i915_get_extra_instdone(struct drm_i915_private *dev_priv, - uint32_t *instdone) +void i915_get_engine_instdone(struct drm_i915_private *dev_priv, + enum intel_engine_id engine_id, + struct intel_instdone *instdone) { - memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG); - - if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv)) - instdone[0] = I915_READ(GEN2_INSTDONE); - else if (IS_GEN4(dev_priv) || IS_GEN5(dev_priv) || IS_GEN6(dev_priv)) { - instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE)); - instdone[1] = I915_READ(GEN4_INSTDONE1); - } else if (INTEL_GEN(dev_priv) >= 7) { - instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE)); - instdone[1] = I915_READ(GEN7_SC_INSTDONE); - instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE); - instdone[3] = I915_READ(GEN7_ROW_INSTDONE); + u32 mmio_base = dev_priv->engine[engine_id].mmio_base; + int slice; + int subslice; + + memset(instdone, 0, sizeof(*instdone)); + + switch (INTEL_GEN(dev_priv)) { + default: + instdone->instdone = I915_READ(RING_INSTDONE(mmio_base)); + + if (engine_id != RCS) + break; + + instdone->slice_common = I915_READ(GEN7_SC_INSTDONE); + for_each_instdone_slice_subslice(dev_priv, slice, subslice) { + instdone->sampler[slice][subslice] = + read_subslice_reg(dev_priv, slice, subslice, + GEN7_SAMPLER_INSTDONE); + instdone->row[slice][subslice] = + read_subslice_reg(dev_priv, slice, subslice, + GEN7_ROW_INSTDONE); + } + break; + case 7: + instdone->instdone = I915_READ(RING_INSTDONE(mmio_base)); + + if (engine_id != RCS) + break; + + instdone->slice_common = I915_READ(GEN7_SC_INSTDONE); + instdone->sampler[0][0] = I915_READ(GEN7_SAMPLER_INSTDONE); + instdone->row[0][0] = I915_READ(GEN7_ROW_INSTDONE); + + break; + case 6: + case 5: + case 4: + instdone->instdone = I915_READ(RING_INSTDONE(mmio_base)); + + if (engine_id == RCS) + /* HACK: Using the wrong struct member */ + instdone->slice_common = I915_READ(GEN4_INSTDONE1); + break; + case 3: + case 2: + instdone->instdone = I915_READ(GEN2_INSTDONE); + break; } } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 3fc286cd..bd6c8b0 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2551,18 +2551,44 @@ static void i915_reset_and_wakeup(struct drm_i915_private *dev_priv) wake_up_all(&dev_priv->gpu_error.reset_queue); } +static inline void +i915_err_print_instdone(struct drm_i915_private *dev_priv, + struct intel_instdone *instdone) +{ + int slice; + int subslice; + + pr_err(" INSTDONE: 0x%08x\n", instdone->instdone); + + if (INTEL_GEN(dev_priv) <= 3) + return; + + pr_err(" SC_INSTDONE: 0x%08x\n", instdone->slice_common); + + if (INTEL_GEN(dev_priv) <= 6) + return; + + for_each_instdone_slice_subslice(dev_priv, slice, subslice) + pr_err(" SAMPLER_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, instdone->sampler[slice][subslice]); + + for_each_instdone_slice_subslice(dev_priv, slice, subslice) + pr_err(" ROW_INSTDONE[%d][%d]: 0x%08x\n", + slice, subslice, instdone->row[slice][subslice]); +} + static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv) { - uint32_t instdone[I915_NUM_INSTDONE_REG]; + struct intel_instdone instdone; u32 eir = I915_READ(EIR); - int pipe, i; + int pipe; if (!eir) return; pr_err("render error detected, EIR: 0x%08x\n", eir); - i915_get_extra_instdone(dev_priv, instdone); + i915_get_engine_instdone(dev_priv, RCS, &instdone); if (IS_G4X(dev_priv)) { if (eir & (GM45_ERROR_MEM_PRIV | GM45_ERROR_CP_PRIV)) { @@ -2570,8 +2596,7 @@ static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv) pr_err(" IPEIR: 0x%08x\n", I915_READ(IPEIR_I965)); pr_err(" IPEHR: 0x%08x\n", I915_READ(IPEHR_I965)); - for (i = 0; i < ARRAY_SIZE(instdone); i++) - pr_err(" INSTDONE_%d: 0x%08x\n", i, instdone[i]); + i915_err_print_instdone(dev_priv, &instdone); pr_err(" INSTPS: 0x%08x\n", I915_READ(INSTPS)); pr_err(" ACTHD: 0x%08x\n", I915_READ(ACTHD_I965)); I915_WRITE(IPEIR_I965, ipeir); @@ -2606,8 +2631,7 @@ static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv) if (eir & I915_ERROR_INSTRUCTION) { pr_err("instruction error\n"); pr_err(" INSTPM: 0x%08x\n", I915_READ(INSTPM)); - for (i = 0; i < ARRAY_SIZE(instdone); i++) - pr_err(" INSTDONE_%d: 0x%08x\n", i, instdone[i]); + i915_err_print_instdone(dev_priv, &instdone); if (INTEL_GEN(dev_priv) < 4) { u32 ipeir = I915_READ(IPEIR); @@ -2954,30 +2978,46 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) engine->hangcheck.deadlock = 0; } +static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone) +{ + u32 tmp = current_instdone | *old_instdone; + bool unchanged; + + unchanged = tmp == *old_instdone; + *old_instdone |= tmp; + + return unchanged; +} + static bool subunits_stuck(struct intel_engine_cs *engine) { - u32 instdone[I915_NUM_INSTDONE_REG]; + struct drm_i915_private *dev_priv = engine->i915; + struct intel_instdone instdone; + struct intel_instdone *accu_instdone = &engine->hangcheck.instdone; bool stuck; - int i; + int slice; + int subslice; if (engine->id != RCS) return true; - i915_get_extra_instdone(engine->i915, instdone); + i915_get_engine_instdone(dev_priv, RCS, &instdone); /* There might be unstable subunit states even when * actual head is not moving. Filter out the unstable ones by * accumulating the undone -> done transitions and only * consider those as progress. */ - stuck = true; - for (i = 0; i < I915_NUM_INSTDONE_REG; i++) { - const u32 tmp = instdone[i] | engine->hangcheck.instdone[i]; - - if (tmp != engine->hangcheck.instdone[i]) - stuck = false; - - engine->hangcheck.instdone[i] |= tmp; + stuck = instdone_unchanged(instdone.instdone, + &accu_instdone->instdone); + stuck &= instdone_unchanged(instdone.slice_common, + &accu_instdone->slice_common); + + for_each_instdone_slice_subslice(dev_priv, slice, subslice) { + stuck &= instdone_unchanged(instdone.sampler[slice][subslice], + &accu_instdone->sampler[slice][subslice]); + stuck &= instdone_unchanged(instdone.row[slice][subslice], + &accu_instdone->row[slice][subslice]); } return stuck; @@ -2989,7 +3029,7 @@ head_stuck(struct intel_engine_cs *engine, u64 acthd) if (acthd != engine->hangcheck.acthd) { /* Clear subunit states on head movement */ - memset(engine->hangcheck.instdone, 0, + memset(&engine->hangcheck.instdone, 0, sizeof(engine->hangcheck.instdone)); return HANGCHECK_ACTIVE; @@ -3159,7 +3199,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work) /* Clear head and subunit states on seqno movement */ acthd = 0; - memset(engine->hangcheck.instdone, 0, + memset(&engine->hangcheck.instdone, 0, sizeof(engine->hangcheck.instdone)); } diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 687c768..31e6edd 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -431,9 +431,6 @@ static const struct pci_device_id pciidlist[] = { }; MODULE_DEVICE_TABLE(pci, pciidlist); -extern int i915_driver_load(struct pci_dev *pdev, - const struct pci_device_id *ent); - static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct intel_device_info *intel_info = @@ -463,8 +460,6 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return i915_driver_load(pdev, ent); } -extern void i915_driver_unload(struct drm_device *dev); - static void i915_pci_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); @@ -473,8 +468,6 @@ static void i915_pci_remove(struct pci_dev *pdev) drm_dev_unref(dev); } -extern const struct dev_pm_ops i915_pm_ops; - static struct pci_driver i915_pci_driver = { .name = DRIVER_NAME, .id_table = pciidlist, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 70d9616..595d196 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1605,6 +1605,7 @@ enum skl_disp_power_wells { #define RING_HEAD(base) _MMIO((base)+0x34) #define RING_START(base) _MMIO((base)+0x38) #define RING_CTL(base) _MMIO((base)+0x3c) +#define RING_CTL_SIZE(size) ((size) - PAGE_SIZE) /* in bytes -> pages */ #define RING_SYNC_0(base) _MMIO((base)+0x40) #define RING_SYNC_1(base) _MMIO((base)+0x44) #define RING_SYNC_2(base) _MMIO((base)+0x48) @@ -1708,7 +1709,11 @@ enum skl_disp_power_wells { #define GEN7_SC_INSTDONE _MMIO(0x7100) #define GEN7_SAMPLER_INSTDONE _MMIO(0xe160) #define GEN7_ROW_INSTDONE _MMIO(0xe164) -#define I915_NUM_INSTDONE_REG 4 +#define GEN8_MCR_SELECTOR _MMIO(0xfdc) +#define GEN8_MCR_SLICE(slice) (((slice) & 3) << 26) +#define GEN8_MCR_SLICE_MASK GEN8_MCR_SLICE(3) +#define GEN8_MCR_SUBSLICE(subslice) (((subslice) & 3) << 24) +#define GEN8_MCR_SUBSLICE_MASK GEN8_MCR_SUBSLICE(3) #define RING_IPEIR(base) _MMIO((base)+0x64) #define RING_IPEHR(base) _MMIO((base)+0x68) /* @@ -7327,6 +7332,10 @@ enum { #define AUD_CONFIG_UPPER_N_MASK (0xff << 20) #define AUD_CONFIG_LOWER_N_SHIFT 4 #define AUD_CONFIG_LOWER_N_MASK (0xfff << 4) +#define AUD_CONFIG_N_MASK (AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK) +#define AUD_CONFIG_N(n) \ + (((((n) >> 12) & 0xff) << AUD_CONFIG_UPPER_N_SHIFT) | \ + (((n) & 0xfff) << AUD_CONFIG_LOWER_N_SHIFT)) #define AUD_CONFIG_PIXEL_CLOCK_HDMI_SHIFT 16 #define AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK (0xf << 16) #define AUD_CONFIG_PIXEL_CLOCK_HDMI_25175 (0 << 16) diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 6c70a5b..81df29c 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -81,7 +81,7 @@ static const struct { int clock; int n; int cts; -} aud_ncts[] = { +} hdmi_aud_ncts[] = { { 44100, TMDS_296M, 4459, 234375 }, { 44100, TMDS_297M, 4704, 247500 }, { 48000, TMDS_296M, 5824, 281250 }, @@ -121,45 +121,20 @@ static u32 audio_config_hdmi_pixel_clock(const struct drm_display_mode *adjusted return hdmi_audio_clock[i].config; } -static int audio_config_get_n(const struct drm_display_mode *mode, int rate) +static int audio_config_hdmi_get_n(const struct drm_display_mode *adjusted_mode, + int rate) { int i; - for (i = 0; i < ARRAY_SIZE(aud_ncts); i++) { - if ((rate == aud_ncts[i].sample_rate) && - (mode->clock == aud_ncts[i].clock)) { - return aud_ncts[i].n; + for (i = 0; i < ARRAY_SIZE(hdmi_aud_ncts); i++) { + if (rate == hdmi_aud_ncts[i].sample_rate && + adjusted_mode->crtc_clock == hdmi_aud_ncts[i].clock) { + return hdmi_aud_ncts[i].n; } } return 0; } -static uint32_t audio_config_setup_n_reg(int n, uint32_t val) -{ - int n_low, n_up; - uint32_t tmp = val; - - n_low = n & 0xfff; - n_up = (n >> 12) & 0xff; - tmp &= ~(AUD_CONFIG_UPPER_N_MASK | AUD_CONFIG_LOWER_N_MASK); - tmp |= ((n_up << AUD_CONFIG_UPPER_N_SHIFT) | - (n_low << AUD_CONFIG_LOWER_N_SHIFT) | - AUD_CONFIG_N_PROG_ENABLE); - return tmp; -} - -/* check whether N/CTS/M need be set manually */ -static bool audio_rate_need_prog(struct intel_crtc *crtc, - const struct drm_display_mode *mode) -{ - if (((mode->clock == TMDS_297M) || - (mode->clock == TMDS_296M)) && - intel_crtc_has_type(crtc->config, INTEL_OUTPUT_HDMI)) - return true; - else - return false; -} - static bool intel_eld_uptodate(struct drm_connector *connector, i915_reg_t reg_eldv, uint32_t bits_eldv, i915_reg_t reg_elda, uint32_t bits_elda, @@ -245,6 +220,65 @@ static void g4x_audio_codec_enable(struct drm_connector *connector, I915_WRITE(G4X_AUD_CNTL_ST, tmp); } +static void +hsw_dp_audio_config_update(struct intel_crtc *intel_crtc, enum port port, + const struct drm_display_mode *adjusted_mode) +{ + struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); + enum pipe pipe = intel_crtc->pipe; + u32 tmp; + + tmp = I915_READ(HSW_AUD_CFG(pipe)); + tmp &= ~AUD_CONFIG_N_VALUE_INDEX; + tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; + tmp &= ~AUD_CONFIG_N_PROG_ENABLE; + tmp |= AUD_CONFIG_N_VALUE_INDEX; + + I915_WRITE(HSW_AUD_CFG(pipe), tmp); +} + +static void +hsw_hdmi_audio_config_update(struct intel_crtc *intel_crtc, enum port port, + const struct drm_display_mode *adjusted_mode) +{ + struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); + struct i915_audio_component *acomp = dev_priv->audio_component; + int rate = acomp ? acomp->aud_sample_rate[port] : 0; + enum pipe pipe = intel_crtc->pipe; + int n; + u32 tmp; + + tmp = I915_READ(HSW_AUD_CFG(pipe)); + tmp &= ~AUD_CONFIG_N_VALUE_INDEX; + tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; + tmp &= ~AUD_CONFIG_N_PROG_ENABLE; + tmp |= audio_config_hdmi_pixel_clock(adjusted_mode); + + if (adjusted_mode->crtc_clock == TMDS_296M || + adjusted_mode->crtc_clock == TMDS_297M) { + n = audio_config_hdmi_get_n(adjusted_mode, rate); + if (n != 0) { + tmp &= ~AUD_CONFIG_N_MASK; + tmp |= AUD_CONFIG_N(n); + tmp |= AUD_CONFIG_N_PROG_ENABLE; + } else { + DRM_DEBUG_KMS("no suitable N value is found\n"); + } + } + + I915_WRITE(HSW_AUD_CFG(pipe), tmp); +} + +static void +hsw_audio_config_update(struct intel_crtc *intel_crtc, enum port port, + const struct drm_display_mode *adjusted_mode) +{ + if (intel_crtc_has_dp_encoder(intel_crtc->config)) + hsw_dp_audio_config_update(intel_crtc, port, adjusted_mode); + else + hsw_hdmi_audio_config_update(intel_crtc, port, adjusted_mode); +} + static void hsw_audio_codec_disable(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); @@ -276,20 +310,16 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder) } static void hsw_audio_codec_enable(struct drm_connector *connector, - struct intel_encoder *encoder, + struct intel_encoder *intel_encoder, const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = to_i915(connector->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + struct intel_crtc *intel_crtc = to_intel_crtc(intel_encoder->base.crtc); enum pipe pipe = intel_crtc->pipe; - struct i915_audio_component *acomp = dev_priv->audio_component; + enum port port = intel_encoder->port; const uint8_t *eld = connector->eld; - struct intel_digital_port *intel_dig_port = - enc_to_dig_port(&encoder->base); - enum port port = intel_dig_port->port; uint32_t tmp; int len, i; - int n, rate; DRM_DEBUG_KMS("Enable audio codec on pipe %c, %u bytes ELD\n", pipe_name(pipe), drm_eld_size(eld)); @@ -325,42 +355,17 @@ static void hsw_audio_codec_enable(struct drm_connector *connector, I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); /* Enable timestamps */ - tmp = I915_READ(HSW_AUD_CFG(pipe)); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; - if (intel_crtc_has_dp_encoder(intel_crtc->config)) - tmp |= AUD_CONFIG_N_VALUE_INDEX; - else - tmp |= audio_config_hdmi_pixel_clock(adjusted_mode); - - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - if (audio_rate_need_prog(intel_crtc, adjusted_mode)) { - if (!acomp) - rate = 0; - else if (port >= PORT_A && port <= PORT_E) - rate = acomp->aud_sample_rate[port]; - else { - DRM_ERROR("invalid port: %d\n", port); - rate = 0; - } - n = audio_config_get_n(adjusted_mode, rate); - if (n != 0) - tmp = audio_config_setup_n_reg(n, tmp); - else - DRM_DEBUG_KMS("no suitable N value is found\n"); - } - - I915_WRITE(HSW_AUD_CFG(pipe), tmp); + hsw_audio_config_update(intel_crtc, port, adjusted_mode); mutex_unlock(&dev_priv->av_mutex); } -static void ilk_audio_codec_disable(struct intel_encoder *encoder) +static void ilk_audio_codec_disable(struct intel_encoder *intel_encoder) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); - enum port port = enc_to_dig_port(&encoder->base)->port; + struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev); + struct intel_crtc *intel_crtc = to_intel_crtc(intel_encoder->base.crtc); enum pipe pipe = intel_crtc->pipe; + enum port port = intel_encoder->port; uint32_t tmp, eldv; i915_reg_t aud_config, aud_cntrl_st2; @@ -400,13 +405,13 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder) } static void ilk_audio_codec_enable(struct drm_connector *connector, - struct intel_encoder *encoder, + struct intel_encoder *intel_encoder, const struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = to_i915(connector->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); - enum port port = enc_to_dig_port(&encoder->base)->port; + struct intel_crtc *intel_crtc = to_intel_crtc(intel_encoder->base.crtc); enum pipe pipe = intel_crtc->pipe; + enum port port = intel_encoder->port; uint8_t *eld = connector->eld; uint32_t tmp, eldv; int len, i; @@ -490,11 +495,10 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode; struct drm_connector *connector; - struct drm_device *dev = encoder->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->dev); struct i915_audio_component *acomp = dev_priv->audio_component; - struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); - enum port port = intel_dig_port->port; + enum port port = intel_encoder->port; + enum pipe pipe = crtc->pipe; connector = drm_select_eld(encoder); if (!connector) @@ -518,13 +522,19 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) adjusted_mode); mutex_lock(&dev_priv->av_mutex); - intel_dig_port->audio_connector = connector; + intel_encoder->audio_connector = connector; + /* referred in audio callbacks */ - dev_priv->dig_port_map[port] = intel_encoder; + dev_priv->av_enc_map[pipe] = intel_encoder; mutex_unlock(&dev_priv->av_mutex); + /* audio drivers expect pipe = -1 to indicate Non-MST cases */ + if (intel_encoder->type != INTEL_OUTPUT_DP_MST) + pipe = -1; + if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) - acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, (int) port); + acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, + (int) port, (int) pipe); } /** @@ -537,22 +547,27 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) void intel_audio_codec_disable(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; - struct drm_device *dev = encoder->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(encoder->dev); struct i915_audio_component *acomp = dev_priv->audio_component; - struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); - enum port port = intel_dig_port->port; + enum port port = intel_encoder->port; + struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); + enum pipe pipe = crtc->pipe; if (dev_priv->display.audio_codec_disable) dev_priv->display.audio_codec_disable(intel_encoder); mutex_lock(&dev_priv->av_mutex); - intel_dig_port->audio_connector = NULL; - dev_priv->dig_port_map[port] = NULL; + intel_encoder->audio_connector = NULL; + dev_priv->av_enc_map[pipe] = NULL; mutex_unlock(&dev_priv->av_mutex); + /* audio drivers expect pipe = -1 to indicate Non-MST cases */ + if (intel_encoder->type != INTEL_OUTPUT_DP_MST) + pipe = -1; + if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) - acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, (int) port); + acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr, + (int) port, (int) pipe); } /** @@ -627,74 +642,67 @@ static int i915_audio_component_get_cdclk_freq(struct device *kdev) return dev_priv->cdclk_freq; } -static int i915_audio_component_sync_audio_rate(struct device *kdev, - int port, int rate) +static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, + int port, int pipe) +{ + + if (WARN_ON(pipe >= I915_MAX_PIPES)) + return NULL; + + /* MST */ + if (pipe >= 0) + return dev_priv->av_enc_map[pipe]; + + /* Non-MST */ + for_each_pipe(dev_priv, pipe) { + struct intel_encoder *encoder; + + encoder = dev_priv->av_enc_map[pipe]; + if (encoder == NULL) + continue; + + if (port == encoder->port) + return encoder; + } + + return NULL; +} + +static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, + int pipe, int rate) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_encoder *intel_encoder; struct intel_crtc *crtc; - struct drm_display_mode *mode; + struct drm_display_mode *adjusted_mode; struct i915_audio_component *acomp = dev_priv->audio_component; - enum pipe pipe = INVALID_PIPE; - u32 tmp; - int n; int err = 0; - /* HSW, BDW, SKL, KBL need this fix */ - if (!IS_SKYLAKE(dev_priv) && - !IS_KABYLAKE(dev_priv) && - !IS_BROADWELL(dev_priv) && - !IS_HASWELL(dev_priv)) + if (!HAS_DDI(dev_priv)) return 0; i915_audio_component_get_power(kdev); mutex_lock(&dev_priv->av_mutex); + /* 1. get the pipe */ - intel_encoder = dev_priv->dig_port_map[port]; - /* intel_encoder might be NULL for DP MST */ + intel_encoder = get_saved_enc(dev_priv, port, pipe); if (!intel_encoder || !intel_encoder->base.crtc || intel_encoder->type != INTEL_OUTPUT_HDMI) { - DRM_DEBUG_KMS("no valid port %c\n", port_name(port)); + DRM_DEBUG_KMS("Not valid for port %c\n", port_name(port)); err = -ENODEV; goto unlock; } + + /* pipe passed from the audio driver will be -1 for Non-MST case */ crtc = to_intel_crtc(intel_encoder->base.crtc); pipe = crtc->pipe; - if (pipe == INVALID_PIPE) { - DRM_DEBUG_KMS("no pipe for the port %c\n", port_name(port)); - err = -ENODEV; - goto unlock; - } - DRM_DEBUG_KMS("pipe %c connects port %c\n", - pipe_name(pipe), port_name(port)); - mode = &crtc->config->base.adjusted_mode; + adjusted_mode = &crtc->config->base.adjusted_mode; /* port must be valid now, otherwise the pipe will be invalid */ acomp->aud_sample_rate[port] = rate; - /* 2. check whether to set the N/CTS/M manually or not */ - if (!audio_rate_need_prog(crtc, mode)) { - tmp = I915_READ(HSW_AUD_CFG(pipe)); - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - I915_WRITE(HSW_AUD_CFG(pipe), tmp); - goto unlock; - } - - n = audio_config_get_n(mode, rate); - if (n == 0) { - DRM_DEBUG_KMS("Using automatic mode for N value on port %c\n", - port_name(port)); - tmp = I915_READ(HSW_AUD_CFG(pipe)); - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - I915_WRITE(HSW_AUD_CFG(pipe), tmp); - goto unlock; - } - - /* 3. set the N/CTS/M */ - tmp = I915_READ(HSW_AUD_CFG(pipe)); - tmp = audio_config_setup_n_reg(n, tmp); - I915_WRITE(HSW_AUD_CFG(pipe), tmp); + hsw_audio_config_update(crtc, port, adjusted_mode); unlock: mutex_unlock(&dev_priv->av_mutex); @@ -703,27 +711,29 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, } static int i915_audio_component_get_eld(struct device *kdev, int port, - bool *enabled, + int pipe, bool *enabled, unsigned char *buf, int max_bytes) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_encoder *intel_encoder; - struct intel_digital_port *intel_dig_port; const u8 *eld; int ret = -EINVAL; mutex_lock(&dev_priv->av_mutex); - intel_encoder = dev_priv->dig_port_map[port]; - /* intel_encoder might be NULL for DP MST */ - if (intel_encoder) { - ret = 0; - intel_dig_port = enc_to_dig_port(&intel_encoder->base); - *enabled = intel_dig_port->audio_connector != NULL; - if (*enabled) { - eld = intel_dig_port->audio_connector->eld; - ret = drm_eld_size(eld); - memcpy(buf, eld, min(max_bytes, ret)); - } + + intel_encoder = get_saved_enc(dev_priv, port, pipe); + if (!intel_encoder) { + DRM_DEBUG_KMS("Not valid for port %c\n", port_name(port)); + mutex_unlock(&dev_priv->av_mutex); + return ret; + } + + ret = 0; + *enabled = intel_encoder->audio_connector != NULL; + if (*enabled) { + eld = intel_encoder->audio_connector->eld; + ret = drm_eld_size(eld); + memcpy(buf, eld, min(max_bytes, ret)); } mutex_unlock(&dev_priv->av_mutex); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index c6e69e4..83667e8 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -996,6 +996,10 @@ parse_mipi_sequence(struct drm_i915_private *dev_priv, goto err; } + /* Log about presence of sequences we won't run. */ + if (seq_id == MIPI_SEQ_TEAR_ON || seq_id == MIPI_SEQ_TEAR_OFF) + DRM_DEBUG_KMS("Unsupported sequence %u\n", seq_id); + dev_priv->vbt.dsi.sequence[seq_id] = data + index; if (sequence->version >= 3) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index dfbcf16..4a7b6c5 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -643,6 +643,32 @@ intel_crt_load_detect(struct intel_crt *crt, uint32_t pipe) return status; } +static int intel_spurious_crt_detect_dmi_callback(const struct dmi_system_id *id) +{ + DRM_DEBUG_DRIVER("Skipping CRT detection for %s\n", id->ident); + return 1; +} + +static const struct dmi_system_id intel_spurious_crt_detect[] = { + { + .callback = intel_spurious_crt_detect_dmi_callback, + .ident = "ACER ZGB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ACER"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"), + }, + }, + { + .callback = intel_spurious_crt_detect_dmi_callback, + .ident = "Intel DZ77BH-55K", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "DZ77BH-55K"), + }, + }, + { } +}; + static enum drm_connector_status intel_crt_detect(struct drm_connector *connector, bool force) { @@ -659,6 +685,10 @@ intel_crt_detect(struct drm_connector *connector, bool force) connector->base.id, connector->name, force); + /* Skip machines without VGA that falsely report hotplug events */ + if (dmi_check_system(intel_spurious_crt_detect)) + return connector_status_disconnected; + power_domain = intel_display_port_power_domain(intel_encoder); intel_display_power_get(dev_priv, power_domain); @@ -808,32 +838,6 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = { .destroy = intel_encoder_destroy, }; -static int intel_no_crt_dmi_callback(const struct dmi_system_id *id) -{ - DRM_INFO("Skipping CRT initialization for %s\n", id->ident); - return 1; -} - -static const struct dmi_system_id intel_no_crt[] = { - { - .callback = intel_no_crt_dmi_callback, - .ident = "ACER ZGB", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ACER"), - DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"), - }, - }, - { - .callback = intel_no_crt_dmi_callback, - .ident = "DELL XPS 8700", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"), - }, - }, - { } -}; - void intel_crt_init(struct drm_device *dev) { struct drm_connector *connector; @@ -843,10 +847,6 @@ void intel_crt_init(struct drm_device *dev) i915_reg_t adpa_reg; u32 adpa; - /* Skip machines without VGA that falsely report hotplug events */ - if (dmi_check_system(intel_no_crt)) - return; - if (HAS_PCH_SPLIT(dev)) adpa_reg = PCH_ADPA; else if (IS_VALLEYVIEW(dev)) @@ -914,13 +914,16 @@ void intel_crt_init(struct drm_device *dev) crt->base.disable = intel_disable_crt; } crt->base.enable = intel_enable_crt; - if (I915_HAS_HOTPLUG(dev)) + if (I915_HAS_HOTPLUG(dev) && + !dmi_check_system(intel_spurious_crt_detect)) crt->base.hpd_pin = HPD_CRT; if (HAS_DDI(dev)) { + crt->base.port = PORT_E; crt->base.get_config = hsw_crt_get_config; crt->base.get_hw_state = intel_ddi_get_hw_state; crt->base.post_disable = hsw_post_disable_crt; } else { + crt->base.port = PORT_NONE; crt->base.get_config = intel_crt_get_config; crt->base.get_hw_state = intel_crt_get_hw_state; } diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 15d47c8..35f0b7c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2520,6 +2520,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_dig_port->max_lanes = max_lanes; intel_encoder->type = INTEL_OUTPUT_UNKNOWN; + intel_encoder->port = port; intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); intel_encoder->cloneable = 0; diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 73b6858..d6a8f11 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -28,20 +28,14 @@ void intel_device_info_dump(struct drm_i915_private *dev_priv) { const struct intel_device_info *info = &dev_priv->info; -#define PRINT_S(name) "%s" -#define SEP_EMPTY -#define PRINT_FLAG(name) info->name ? #name "," : "" -#define SEP_COMMA , - DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x flags=" - DEV_INFO_FOR_EACH_FLAG(PRINT_S, SEP_EMPTY), + DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x", info->gen, dev_priv->drm.pdev->device, - dev_priv->drm.pdev->revision, - DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_COMMA)); -#undef PRINT_S -#undef SEP_EMPTY + dev_priv->drm.pdev->revision); +#define PRINT_FLAG(name) \ + DRM_DEBUG_DRIVER("i915 device info: " #name ": %s", yesno(info->name)) + DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG -#undef SEP_COMMA } static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv) @@ -192,7 +186,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv) struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu; const int s_max = 3, ss_max = 3, eu_max = 8; int s, ss; - u32 fuse2, eu_disable[s_max]; + u32 fuse2, eu_disable[3]; /* s_max */ fuse2 = I915_READ(GEN8_FUSE2); sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index fbcfed6..e4bdd3a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3603,8 +3603,6 @@ void intel_finish_reset(struct drm_i915_private *dev_priv) dev_priv->modeset_restore_state = NULL; - dev_priv->modeset_restore_state = NULL; - /* reset doesn't touch the display */ if (!gpu_reset_clobbers_display(dev_priv)) { if (!state) { @@ -12288,7 +12286,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, work->flip_queued_req = i915_gem_active_get(&obj->last_write, &obj->base.dev->struct_mutex); - schedule_work(&work->mmio_work); + queue_work(system_unbound_wq, &work->mmio_work); } else { request = i915_gem_request_alloc(engine, engine->last_context); if (IS_ERR(request)) { @@ -15840,12 +15838,6 @@ intel_user_framebuffer_create(struct drm_device *dev, return fb; } -#ifndef CONFIG_DRM_FBDEV_EMULATION -static inline void intel_fbdev_output_poll_changed(struct drm_device *dev) -{ -} -#endif - static const struct drm_mode_config_funcs intel_mode_funcs = { .fb_create = intel_user_framebuffer_create, .output_poll_changed = intel_fbdev_output_poll_changed, diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 14a3cf0..5992093 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1297,14 +1297,10 @@ intel_dp_sink_rates(struct intel_dp *intel_dp, const int **sink_rates) bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = dig_port->base.base.dev; - - /* WaDisableHBR2:skl */ - if (IS_SKL_REVID(dev, 0, SKL_REVID_B0)) - return false; + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - if ((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) || IS_BROADWELL(dev) || - (INTEL_INFO(dev)->gen >= 9)) + if ((IS_HASWELL(dev_priv) && !IS_HSW_ULX(dev_priv)) || + IS_BROADWELL(dev_priv) || (INTEL_GEN(dev_priv) >= 9)) return true; else return false; @@ -1314,13 +1310,13 @@ static int intel_dp_source_rates(struct intel_dp *intel_dp, const int **source_rates) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = dig_port->base.base.dev; + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); int size; - if (IS_BROXTON(dev)) { + if (IS_BROXTON(dev_priv)) { *source_rates = bxt_rates; size = ARRAY_SIZE(bxt_rates); - } else if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) { + } else if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { *source_rates = skl_rates; size = ARRAY_SIZE(skl_rates); } else { @@ -5826,6 +5822,7 @@ bool intel_dp_init(struct drm_device *dev, intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); } intel_encoder->cloneable = 0; + intel_encoder->port = port; intel_dig_port->hpd_pulse = intel_dp_hpd_pulse; dev_priv->hotplug.irq_port[port] = intel_dig_port; diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c index c438b02..0048b52 100644 --- a/drivers/gpu/drm/i915/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/intel_dp_link_training.c @@ -225,9 +225,6 @@ static u32 intel_dp_training_pattern(struct intel_dp *intel_dp) * Intel platforms that support HBR2 also support TPS3. TPS3 support is * also mandatory for downstream devices that support HBR2. However, not * all sinks follow the spec. - * - * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is - * supported in source but still not enabled. */ source_tps3 = intel_dp_source_supports_hbr2(intel_dp); sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd); diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 54a9d76..3ffbd69 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -523,6 +523,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum DRM_MODE_ENCODER_DPMST, "DP-MST %c", pipe_name(pipe)); intel_encoder->type = INTEL_OUTPUT_DP_MST; + intel_encoder->port = intel_dig_port->port; intel_encoder->crtc_mask = 0x7; intel_encoder->cloneable = 0; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a19ec06..f48e79a 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -206,6 +206,7 @@ struct intel_encoder { struct drm_encoder base; enum intel_output_type type; + enum port port; unsigned int cloneable; void (*hot_plug)(struct intel_encoder *); bool (*compute_config)(struct intel_encoder *, @@ -247,6 +248,8 @@ struct intel_encoder { void (*suspend)(struct intel_encoder *); int crtc_mask; enum hpd_pin hpd_pin; + /* for communication with audio component; protected by av_mutex */ + const struct drm_connector *audio_connector; }; struct intel_panel { @@ -959,8 +962,6 @@ struct intel_digital_port { enum irqreturn (*hpd_pulse)(struct intel_digital_port *, bool); bool release_cl2_override; uint8_t max_lanes; - /* for communication with audio component; protected by av_mutex */ - const struct drm_connector *audio_connector; }; struct intel_dp_mst_encoder { @@ -1487,6 +1488,10 @@ static inline void intel_fbdev_set_suspend(struct drm_device *dev, int state, bo { } +static inline void intel_fbdev_output_poll_changed(struct drm_device *dev) +{ +} + static inline void intel_fbdev_restore_mode(struct drm_device *dev) { } @@ -1513,6 +1518,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, void intel_fbc_flush(struct drm_i915_private *dev_priv, unsigned int frontbuffer_bits, enum fb_op_origin origin); void intel_fbc_cleanup_cfb(struct drm_i915_private *dev_priv); +void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv); /* intel_hdmi.c */ void intel_hdmi_init(struct drm_device *dev, i915_reg_t hdmi_reg, enum port port); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index b2e3d3a..727adaa 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -1488,6 +1488,7 @@ void intel_dsi_init(struct drm_device *dev) intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_encoder->port = port; /* * On BYT/CHV, pipe A maps to MIPI DSI port A, pipe B maps to MIPI DSI * port C. BXT isn't limited like this. diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index cd154ce..9f279a3 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -126,6 +126,8 @@ static const u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi, u16 len; enum port port; + DRM_DEBUG_KMS("\n"); + flags = *data++; type = *data++; @@ -199,6 +201,8 @@ static const u8 *mipi_exec_delay(struct intel_dsi *intel_dsi, const u8 *data) { u32 delay = *((const u32 *) data); + DRM_DEBUG_KMS("\n"); + usleep_range(delay, delay + 10); data += 4; @@ -307,6 +311,8 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) u8 gpio_source, gpio_index; bool value; + DRM_DEBUG_KMS("\n"); + if (dev_priv->vbt.dsi.seq_version >= 3) data++; @@ -331,18 +337,36 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) return data; } -static const u8 *mipi_exec_i2c_skip(struct intel_dsi *intel_dsi, const u8 *data) +static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data) { + DRM_DEBUG_KMS("Skipping I2C element execution\n"); + return data + *(data + 6) + 7; } +static const u8 *mipi_exec_spi(struct intel_dsi *intel_dsi, const u8 *data) +{ + DRM_DEBUG_KMS("Skipping SPI element execution\n"); + + return data + *(data + 5) + 6; +} + +static const u8 *mipi_exec_pmic(struct intel_dsi *intel_dsi, const u8 *data) +{ + DRM_DEBUG_KMS("Skipping PMIC element execution\n"); + + return data + 15; +} + typedef const u8 * (*fn_mipi_elem_exec)(struct intel_dsi *intel_dsi, const u8 *data); static const fn_mipi_elem_exec exec_elem[] = { [MIPI_SEQ_ELEM_SEND_PKT] = mipi_exec_send_packet, [MIPI_SEQ_ELEM_DELAY] = mipi_exec_delay, [MIPI_SEQ_ELEM_GPIO] = mipi_exec_gpio, - [MIPI_SEQ_ELEM_I2C] = mipi_exec_i2c_skip, + [MIPI_SEQ_ELEM_I2C] = mipi_exec_i2c, + [MIPI_SEQ_ELEM_SPI] = mipi_exec_spi, + [MIPI_SEQ_ELEM_PMIC] = mipi_exec_pmic, }; /* @@ -385,11 +409,8 @@ static void generic_exec_sequence(struct drm_panel *panel, enum mipi_seq seq_id) return; data = dev_priv->vbt.dsi.sequence[seq_id]; - if (!data) { - DRM_DEBUG_KMS("MIPI sequence %d - %s not available\n", - seq_id, sequence_name(seq_id)); + if (!data) return; - } WARN_ON(*data != seq_id); @@ -420,7 +441,15 @@ static void generic_exec_sequence(struct drm_panel *panel, enum mipi_seq seq_id) operation_size = *data++; if (mipi_elem_exec) { + const u8 *next = data + operation_size; + data = mipi_elem_exec(intel_dsi, data); + + /* Consistency check if we have size. */ + if (operation_size && data != next) { + DRM_ERROR("Inconsistent operation size\n"); + return; + } } else if (operation_size) { /* We have size, skip. */ DRM_DEBUG_KMS("Unsupported MIPI operation byte %u\n", @@ -438,6 +467,8 @@ static void generic_exec_sequence(struct drm_panel *panel, enum mipi_seq seq_id) static int vbt_panel_prepare(struct drm_panel *panel) { generic_exec_sequence(panel, MIPI_SEQ_ASSERT_RESET); + generic_exec_sequence(panel, MIPI_SEQ_POWER_ON); + generic_exec_sequence(panel, MIPI_SEQ_DEASSERT_RESET); generic_exec_sequence(panel, MIPI_SEQ_INIT_OTP); return 0; @@ -445,7 +476,8 @@ static int vbt_panel_prepare(struct drm_panel *panel) static int vbt_panel_unprepare(struct drm_panel *panel) { - generic_exec_sequence(panel, MIPI_SEQ_DEASSERT_RESET); + generic_exec_sequence(panel, MIPI_SEQ_ASSERT_RESET); + generic_exec_sequence(panel, MIPI_SEQ_POWER_OFF); return 0; } @@ -453,12 +485,14 @@ static int vbt_panel_unprepare(struct drm_panel *panel) static int vbt_panel_enable(struct drm_panel *panel) { generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_ON); + generic_exec_sequence(panel, MIPI_SEQ_BACKLIGHT_ON); return 0; } static int vbt_panel_disable(struct drm_panel *panel) { + generic_exec_sequence(panel, MIPI_SEQ_BACKLIGHT_OFF); generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_OFF); return 0; diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 2e452c5..cd57490 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -412,16 +412,14 @@ intel_dvo_get_current_mode(struct drm_connector *connector) return mode; } -static char intel_dvo_port_name(i915_reg_t dvo_reg) +static enum port intel_dvo_port(i915_reg_t dvo_reg) { if (i915_mmio_reg_equal(dvo_reg, DVOA)) - return 'A'; + return PORT_A; else if (i915_mmio_reg_equal(dvo_reg, DVOB)) - return 'B'; - else if (i915_mmio_reg_equal(dvo_reg, DVOC)) - return 'C'; + return PORT_B; else - return '?'; + return PORT_C; } void intel_dvo_init(struct drm_device *dev) @@ -464,6 +462,7 @@ void intel_dvo_init(struct drm_device *dev) bool dvoinit; enum pipe pipe; uint32_t dpll[I915_MAX_PIPES]; + enum port port; /* Allow the I2C driver info to specify the GPIO to be used in * special cases, but otherwise default to what's defined @@ -511,12 +510,15 @@ void intel_dvo_init(struct drm_device *dev) if (!dvoinit) continue; + port = intel_dvo_port(dvo->dvo_reg); drm_encoder_init(dev, &intel_encoder->base, &intel_dvo_enc_funcs, encoder_type, - "DVO %c", intel_dvo_port_name(dvo->dvo_reg)); + "DVO %c", port_name(port)); intel_encoder->type = INTEL_OUTPUT_DVO; + intel_encoder->port = port; intel_encoder->crtc_mask = (1 << 0) | (1 << 1); + switch (dvo->type) { case INTEL_DVO_CHIP_TMDS: intel_encoder->cloneable = (1 << INTEL_OUTPUT_ANALOG) | diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 025e232..480584c 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -319,3 +319,33 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) intel_engine_cleanup_cmd_parser(engine); i915_gem_batch_pool_fini(&engine->batch_pool); } + +u64 intel_engine_get_active_head(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + u64 acthd; + + if (INTEL_GEN(dev_priv) >= 8) + acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base), + RING_ACTHD_UDW(engine->mmio_base)); + else if (INTEL_GEN(dev_priv) >= 4) + acthd = I915_READ(RING_ACTHD(engine->mmio_base)); + else + acthd = I915_READ(ACTHD); + + return acthd; +} + +u64 intel_engine_get_last_batch_head(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + u64 bbaddr; + + if (INTEL_GEN(dev_priv) >= 8) + bbaddr = I915_READ64_2x32(RING_BBADDR(engine->mmio_base), + RING_BBADDR_UDW(engine->mmio_base)); + else + bbaddr = I915_READ(RING_BBADDR(engine->mmio_base)); + + return bbaddr; +} diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index faa6762..617189a 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -774,6 +774,14 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) struct intel_fbc *fbc = &dev_priv->fbc; struct intel_fbc_state_cache *cache = &fbc->state_cache; + /* We don't need to use a state cache here since this information is + * global for all CRTC. + */ + if (fbc->underrun_detected) { + fbc->no_fbc_reason = "underrun detected"; + return false; + } + if (!cache->plane.visible) { fbc->no_fbc_reason = "primary plane not visible"; return false; @@ -859,6 +867,11 @@ static bool intel_fbc_can_choose(struct intel_crtc *crtc) return false; } + if (fbc->underrun_detected) { + fbc->no_fbc_reason = "underrun detected"; + return false; + } + if (fbc_on_pipe_a_only(dev_priv) && crtc->pipe != PIPE_A) { fbc->no_fbc_reason = "no enabled pipes can have FBC"; return false; @@ -1221,6 +1234,59 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv) cancel_work_sync(&fbc->work.work); } +static void intel_fbc_underrun_work_fn(struct work_struct *work) +{ + struct drm_i915_private *dev_priv = + container_of(work, struct drm_i915_private, fbc.underrun_work); + struct intel_fbc *fbc = &dev_priv->fbc; + + mutex_lock(&fbc->lock); + + /* Maybe we were scheduled twice. */ + if (fbc->underrun_detected) + goto out; + + DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n"); + fbc->underrun_detected = true; + + intel_fbc_deactivate(dev_priv); +out: + mutex_unlock(&fbc->lock); +} + +/** + * intel_fbc_handle_fifo_underrun_irq - disable FBC when we get a FIFO underrun + * @dev_priv: i915 device instance + * + * Without FBC, most underruns are harmless and don't really cause too many + * problems, except for an annoying message on dmesg. With FBC, underruns can + * become black screens or even worse, especially when paired with bad + * watermarks. So in order for us to be on the safe side, completely disable FBC + * in case we ever detect a FIFO underrun on any pipe. An underrun on any pipe + * already suggests that watermarks may be bad, so try to be as safe as + * possible. + * + * This function is called from the IRQ handler. + */ +void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv) +{ + struct intel_fbc *fbc = &dev_priv->fbc; + + if (!fbc_supported(dev_priv)) + return; + + /* There's no guarantee that underrun_detected won't be set to true + * right after this check and before the work is scheduled, but that's + * not a problem since we'll check it again under the work function + * while FBC is locked. This check here is just to prevent us from + * unnecessarily scheduling the work, and it relies on the fact that we + * never switch underrun_detect back to false after it's true. */ + if (READ_ONCE(fbc->underrun_detected)) + return; + + schedule_work(&fbc->underrun_work); +} + /** * intel_fbc_init_pipe_state - initialize FBC's CRTC visibility tracking * @dev_priv: i915 device instance @@ -1292,6 +1358,7 @@ void intel_fbc_init(struct drm_i915_private *dev_priv) enum pipe pipe; INIT_WORK(&fbc->work.work, intel_fbc_work_fn); + INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn); mutex_init(&fbc->lock); fbc->enabled = false; fbc->active = false; diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c index 2aa7440..ebb4fed 100644 --- a/drivers/gpu/drm/i915/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c @@ -372,6 +372,8 @@ void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, if (intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false)) DRM_ERROR("CPU pipe %c FIFO underrun\n", pipe_name(pipe)); + + intel_fbc_handle_fifo_underrun_irq(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c index 6fd39ef..7ace96b 100644 --- a/drivers/gpu/drm/i915/intel_guc_loader.c +++ b/drivers/gpu/drm/i915/intel_guc_loader.c @@ -375,16 +375,14 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv) /* Enable MIA caching. GuC clock gating is disabled. */ I915_WRITE(GUC_SHIM_CONTROL, GUC_SHIM_CONTROL_VALUE); - /* WaDisableMinuteIaClockGating:skl,bxt */ - if (IS_SKL_REVID(dev, 0, SKL_REVID_B0) || - IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { + /* WaDisableMinuteIaClockGating:bxt */ + if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { I915_WRITE(GUC_SHIM_CONTROL, (I915_READ(GUC_SHIM_CONTROL) & ~GUC_ENABLE_MIA_CLOCK_GATING)); } - /* WaC6DisallowByGfxPause*/ - if (IS_SKL_REVID(dev, 0, SKL_REVID_C0) || - IS_BXT_REVID(dev, 0, BXT_REVID_B0)) + /* WaC6DisallowByGfxPause:bxt */ + if (IS_BXT_REVID(dev, 0, BXT_REVID_B0)) I915_WRITE(GEN6_GFXPAUSE, 0x30FFF); if (IS_BROXTON(dev)) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index f40a35f..8d46f58 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1979,6 +1979,7 @@ void intel_hdmi_init(struct drm_device *dev, } intel_encoder->type = INTEL_OUTPUT_HDMI; + intel_encoder->port = port; if (IS_CHERRYVIEW(dev)) { if (port == PORT_D) intel_encoder->crtc_mask = 1 << 2; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 0adb879..10fcea57 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -275,8 +275,7 @@ logical_ring_init_platform_invariants(struct intel_engine_cs *engine) struct drm_i915_private *dev_priv = engine->i915; engine->disable_lite_restore_wa = - (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) && + IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1) && (engine->id == VCS || engine->id == VCS2); engine->ctx_desc_template = GEN8_CTX_VALID; @@ -853,13 +852,12 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); /* - * WaDisableLSQCROPERFforOCL:skl,kbl + * WaDisableLSQCROPERFforOCL:kbl * This WA is implemented in skl_init_clock_gating() but since * this batch updates GEN8_L3SQCREG4 with default value we need to * set this bit here to retain the WA during flush. */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) || - IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1002,9 +1000,8 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, struct drm_i915_private *dev_priv = engine->i915; uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); - /* WaDisableCtxRestoreArbitration:skl,bxt */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) + /* WaDisableCtxRestoreArbitration:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE); /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt */ @@ -1075,9 +1072,8 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine, { uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); - /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */ - if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_B0) || - IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) { + /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:bxt */ + if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) { wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1)); wa_ctx_emit_reg(batch, index, GEN9_SLICE_COMMON_ECO_CHICKEN0); wa_ctx_emit(batch, index, @@ -1104,9 +1100,8 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine, wa_ctx_emit(batch, index, MI_NOOP); } - /* WaDisableCtxRestoreArbitration:skl,bxt */ - if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_D0) || - IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) + /* WaDisableCtxRestoreArbitration:bxt */ + if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE); wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END); @@ -1250,8 +1245,12 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) intel_engine_init_hangcheck(engine); - if (!execlists_elsp_idle(engine)) + /* After a GPU reset, we may have requests to replay */ + if (!execlists_elsp_idle(engine)) { + engine->execlist_port[0].count = 0; + engine->execlist_port[1].count = 0; execlists_submit_ports(engine); + } return 0; } @@ -1326,10 +1325,7 @@ static void reset_common_ring(struct intel_engine_cs *engine, memset(&port[1], 0, sizeof(port[1])); } - /* CS is stopped, and we will resubmit both ports on resume */ GEM_BUG_ON(request->ctx != port[0].request->ctx); - port[0].count = 0; - port[1].count = 0; /* Reset WaIdleLiteRestore:bdw,skl as well */ request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32); @@ -1945,7 +1941,7 @@ static void execlists_init_reg_state(u32 *reg_state, RING_START(engine->mmio_base), 0); ASSIGN_CTX_REG(reg_state, CTX_RING_BUFFER_CONTROL, RING_CTL(engine->mmio_base), - ((ring->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID); + RING_CTL_SIZE(ring->size) | RING_VALID); ASSIGN_CTX_REG(reg_state, CTX_BB_HEAD_U, RING_BBADDR_UDW(engine->mmio_base), 0); ASSIGN_CTX_REG(reg_state, CTX_BB_HEAD_L, @@ -2153,30 +2149,42 @@ error_deref_obj: void intel_lr_context_resume(struct drm_i915_private *dev_priv) { - struct i915_gem_context *ctx = dev_priv->kernel_context; struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + + /* Because we emit WA_TAIL_DWORDS there may be a disparity + * between our bookkeeping in ce->ring->head and ce->ring->tail and + * that stored in context. As we only write new commands from + * ce->ring->tail onwards, everything before that is junk. If the GPU + * starts reading from its RING_HEAD from the context, it may try to + * execute that junk and die. + * + * So to avoid that we reset the context images upon resume. For + * simplicity, we just zero everything out. + */ + list_for_each_entry(ctx, &dev_priv->context_list, link) { + for_each_engine(engine, dev_priv) { + struct intel_context *ce = &ctx->engine[engine->id]; + u32 *reg; - for_each_engine(engine, dev_priv) { - struct intel_context *ce = &ctx->engine[engine->id]; - void *vaddr; - uint32_t *reg_state; - - if (!ce->state) - continue; - - vaddr = i915_gem_object_pin_map(ce->state->obj, I915_MAP_WB); - if (WARN_ON(IS_ERR(vaddr))) - continue; + if (!ce->state) + continue; - reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; + reg = i915_gem_object_pin_map(ce->state->obj, + I915_MAP_WB); + if (WARN_ON(IS_ERR(reg))) + continue; - reg_state[CTX_RING_HEAD+1] = 0; - reg_state[CTX_RING_TAIL+1] = 0; + reg += LRC_STATE_PN * PAGE_SIZE / sizeof(*reg); + reg[CTX_RING_HEAD+1] = 0; + reg[CTX_RING_TAIL+1] = 0; - ce->state->obj->dirty = true; - i915_gem_object_unpin_map(ce->state->obj); + ce->state->obj->dirty = true; + i915_gem_object_unpin_map(ce->state->obj); - ce->ring->head = 0; - ce->ring->tail = 0; + ce->ring->head = ce->ring->tail = 0; + ce->ring->last_retired_head = -1; + intel_ring_update_space(ce->ring); + } } } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index e1d47d5..2e943bd 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -1064,8 +1064,9 @@ void intel_lvds_init(struct drm_device *dev) intel_connector->get_hw_state = intel_connector_get_hw_state; intel_connector_attach_encoder(intel_connector, intel_encoder); - intel_encoder->type = INTEL_OUTPUT_LVDS; + intel_encoder->type = INTEL_OUTPUT_LVDS; + intel_encoder->port = PORT_NONE; intel_encoder->cloneable = 0; if (HAS_PCH_SPLIT(dev)) intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a2f751c..fe6c1c6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3362,13 +3362,15 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, int num_active; int id, i; + /* Clear the partitioning for disabled planes. */ + memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); + memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe])); + if (WARN_ON(!state)) return 0; if (!cstate->base.active) { ddb->pipe[pipe].start = ddb->pipe[pipe].end = 0; - memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); - memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe])); return 0; } @@ -3580,11 +3582,12 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, case 2: y_min_scanlines = 8; break; - default: - WARN(1, "Unsupported pixel depth for rotation"); case 4: y_min_scanlines = 4; break; + default: + MISSING_CASE(cpp); + return -EINVAL; } } else { y_min_scanlines = 4; @@ -3615,7 +3618,10 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) { selected_result = max(method2, y_tile_minimum); } else { - if ((ddb_allocation / plane_blocks_per_line) >= 1) + if ((cpp * cstate->base.adjusted_mode.crtc_htotal / 512 < 1) && + (plane_bytes_per_line / 512 < 1)) + selected_result = method2; + else if ((ddb_allocation / plane_blocks_per_line) >= 1) selected_result = min(method1, method2); else selected_result = method1; @@ -3962,7 +3968,7 @@ pipes_modified(struct drm_atomic_state *state) return ret; } -int +static int skl_ddb_add_affected_planes(struct intel_crtc_state *cstate) { struct drm_atomic_state *state = cstate->base.state; @@ -4050,6 +4056,12 @@ skl_compute_ddb(struct drm_atomic_state *state) intel_state->wm_results.dirty_pipes = ~0; } + /* + * We're not recomputing for the pipes not included in the commit, so + * make sure we start with the current state. + */ + memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb)); + for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) { struct intel_crtc_state *cstate; @@ -5392,9 +5404,8 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv) if (intel_enable_rc6() & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE)); - /* WaRsUseTimeoutMode */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) { + /* WaRsUseTimeoutMode:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) { I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us */ I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE | GEN7_RC_CTL_TO_MODE | diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index ed9955d..729f373 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -405,22 +405,6 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req, u32 mode) return gen8_emit_pipe_control(req, flags, scratch_addr); } -u64 intel_engine_get_active_head(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - u64 acthd; - - if (INTEL_GEN(dev_priv) >= 8) - acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base), - RING_ACTHD_UDW(engine->mmio_base)); - else if (INTEL_GEN(dev_priv) >= 4) - acthd = I915_READ(RING_ACTHD(engine->mmio_base)); - else - acthd = I915_READ(ACTHD); - - return acthd; -} - static void ring_setup_phys_status_page(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; @@ -585,9 +569,7 @@ static int init_ring_common(struct intel_engine_cs *engine) I915_WRITE_TAIL(engine, ring->tail); (void)I915_READ_TAIL(engine); - I915_WRITE_CTL(engine, - ((ring->size - PAGE_SIZE) & RING_NR_PAGES) - | RING_VALID); + I915_WRITE_CTL(engine, RING_CTL_SIZE(ring->size) | RING_VALID); /* If the head is still not zero, the ring is dead */ if (intel_wait_for_register_fw(dev_priv, RING_CTL(engine->mmio_base), @@ -851,15 +833,13 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); - /* WaDisableDgMirrorFixInHalfSliceChicken5:skl,bxt */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) + /* WaDisableDgMirrorFixInHalfSliceChicken5:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_DG_MIRROR_FIX_ENABLE); - /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) { + /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) { WA_SET_BIT_MASKED(GEN7_COMMON_SLICE_CHICKEN1, GEN9_RHWO_OPTIMIZATION_DISABLE); /* @@ -884,9 +864,8 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_CCS_TLB_PREFETCH_ENABLE); - /* WaDisableMaskBasedCammingInRCC:skl,bxt */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, SKL_REVID_C0) || - IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) + /* WaDisableMaskBasedCammingInRCC:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0, PIXEL_MASK_CAMMING_DISABLE); @@ -1003,47 +982,12 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) * until D0 which is the default case so this is equivalent to * !WaDisablePerCtxtPreemptionGranularityControl:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_E0, REVID_FOREVER)) { - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); - } - - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0)) { - /* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */ - I915_WRITE(FF_SLICE_CS_CHICKEN2, - _MASKED_BIT_ENABLE(GEN9_TSG_BARRIER_ACK_DISABLE)); - } - - /* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes - * involving this register should also be added to WA batch as required. - */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0)) - /* WaDisableLSQCROPERFforOCL:skl */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN8_LQSC_RO_PERF_DIS); + I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, + _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); /* WaEnableGapsTsvCreditFix:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, REVID_FOREVER)) { - I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | - GEN9_GAPS_TSV_CREDIT_DISABLE)); - } - - /* WaDisablePowerCompilerClockGating:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_B0, SKL_REVID_B0)) - WA_SET_BIT_MASKED(HIZ_CHICKEN, - BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - - /* WaBarrierPerformanceFixDisable:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, SKL_REVID_D0)) - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FENCE_DEST_SLM_DISABLE | - HDC_BARRIER_PERFORMANCE_DISABLE); - - /* WaDisableSbeCacheDispatchPortSharing:skl */ - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0)) - WA_SET_BIT_MASKED( - GEN7_HALF_SLICE_CHICKEN1, - GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | + GEN9_GAPS_TSV_CREDIT_DISABLE)); /* WaDisableGafsUnitClkGating:skl */ WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); @@ -1989,6 +1933,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size) struct i915_vma *vma; GEM_BUG_ON(!is_power_of_2(size)); + GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES); ring = kzalloc(sizeof(*ring), GFP_KERNEL); if (!ring) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index ec0b4a0..124f464 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -73,13 +73,40 @@ enum intel_engine_hangcheck_action { #define HANGCHECK_SCORE_RING_HUNG 31 +#define I915_MAX_SLICES 3 +#define I915_MAX_SUBSLICES 3 + +#define instdone_slice_mask(dev_priv__) \ + (INTEL_GEN(dev_priv__) == 7 ? \ + 1 : INTEL_INFO(dev_priv__)->sseu.slice_mask) + +#define instdone_subslice_mask(dev_priv__) \ + (INTEL_GEN(dev_priv__) == 7 ? \ + 1 : INTEL_INFO(dev_priv__)->sseu.subslice_mask) + +#define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \ + for ((slice__) = 0, (subslice__) = 0; \ + (slice__) < I915_MAX_SLICES; \ + (subslice__) = ((subslice__) + 1) < I915_MAX_SUBSLICES ? (subslice__) + 1 : 0, \ + (slice__) += ((subslice__) == 0)) \ + for_each_if((BIT(slice__) & instdone_slice_mask(dev_priv__)) && \ + (BIT(subslice__) & instdone_subslice_mask(dev_priv__))) + +struct intel_instdone { + u32 instdone; + /* The following exist only in the RCS engine */ + u32 slice_common; + u32 sampler[I915_MAX_SLICES][I915_MAX_SUBSLICES]; + u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES]; +}; + struct intel_engine_hangcheck { u64 acthd; u32 seqno; int score; enum intel_engine_hangcheck_action action; int deadlock; - u32 instdone[I915_NUM_INSTDONE_REG]; + struct intel_instdone instdone; }; struct intel_ring { @@ -514,6 +541,8 @@ int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine); u64 intel_engine_get_active_head(struct intel_engine_cs *engine); +u64 intel_engine_get_last_batch_head(struct intel_engine_cs *engine); + static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine) { return intel_read_status_page(engine, I915_GEM_HWS_INDEX); diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index c551024..a061b00 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -2981,6 +2981,7 @@ bool intel_sdvo_init(struct drm_device *dev, /* encoder type will be decided later */ intel_encoder = &intel_sdvo->base; intel_encoder->type = INTEL_OUTPUT_SDVO; + intel_encoder->port = port; drm_encoder_init(dev, &intel_encoder->base, &intel_sdvo_enc_funcs, 0, "SDVO %c", port_name(port)); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index d960e48..3988c45 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1610,7 +1610,9 @@ intel_tv_init(struct drm_device *dev) intel_connector->get_hw_state = intel_connector_get_hw_state; intel_connector_attach_encoder(intel_connector, intel_encoder); + intel_encoder->type = INTEL_OUTPUT_TVOUT; + intel_encoder->port = PORT_NONE; intel_encoder->crtc_mask = (1 << 0) | (1 << 1); intel_encoder->cloneable = 0; intel_encoder->base.possible_crtcs = ((1 << 0) | (1 << 1)); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index ee2306a..e2b188d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -231,19 +231,21 @@ intel_uncore_fw_release_timer(struct hrtimer *timer) { struct intel_uncore_forcewake_domain *domain = container_of(timer, struct intel_uncore_forcewake_domain, timer); + struct drm_i915_private *dev_priv = domain->i915; unsigned long irqflags; - assert_rpm_device_not_suspended(domain->i915); + assert_rpm_device_not_suspended(dev_priv); - spin_lock_irqsave(&domain->i915->uncore.lock, irqflags); + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); if (WARN_ON(domain->wake_count == 0)) domain->wake_count++; - if (--domain->wake_count == 0) - domain->i915->uncore.funcs.force_wake_put(domain->i915, - 1 << domain->id); + if (--domain->wake_count == 0) { + dev_priv->uncore.funcs.force_wake_put(dev_priv, domain->mask); + dev_priv->uncore.fw_domains_active &= ~domain->mask; + } - spin_unlock_irqrestore(&domain->i915->uncore.lock, irqflags); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); return HRTIMER_NORESTART; } @@ -254,7 +256,7 @@ void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, unsigned long irqflags; struct intel_uncore_forcewake_domain *domain; int retry_count = 100; - enum forcewake_domains fw = 0, active_domains; + enum forcewake_domains fw, active_domains; /* Hold uncore.lock across reset to prevent any register access * with forcewake not set correctly. Wait until all pending @@ -291,10 +293,7 @@ void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, WARN_ON(active_domains); - for_each_fw_domain(domain, dev_priv) - if (domain->wake_count) - fw |= domain->mask; - + fw = dev_priv->uncore.fw_domains_active; if (fw) dev_priv->uncore.funcs.force_wake_put(dev_priv, fw); @@ -443,9 +442,6 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, { struct intel_uncore_forcewake_domain *domain; - if (!dev_priv->uncore.funcs.force_wake_get) - return; - fw_domains &= dev_priv->uncore.fw_domains; for_each_fw_domain_masked(domain, fw_domains, dev_priv) { @@ -453,8 +449,10 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv, fw_domains &= ~domain->mask; } - if (fw_domains) + if (fw_domains) { dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); + dev_priv->uncore.fw_domains_active |= fw_domains; + } } /** @@ -509,9 +507,6 @@ static void __intel_uncore_forcewake_put(struct drm_i915_private *dev_priv, { struct intel_uncore_forcewake_domain *domain; - if (!dev_priv->uncore.funcs.force_wake_put) - return; - fw_domains &= dev_priv->uncore.fw_domains; for_each_fw_domain_masked(domain, fw_domains, dev_priv) { @@ -567,13 +562,10 @@ void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv, void assert_forcewakes_inactive(struct drm_i915_private *dev_priv) { - struct intel_uncore_forcewake_domain *domain; - if (!dev_priv->uncore.funcs.force_wake_get) return; - for_each_fw_domain(domain, dev_priv) - WARN_ON(domain->wake_count); + WARN_ON(dev_priv->uncore.fw_domains_active); } /* We give fast paths for the really cool registers */ @@ -589,49 +581,146 @@ void assert_forcewakes_inactive(struct drm_i915_private *dev_priv) __fwd; \ }) -#define REG_RANGE(reg, start, end) ((reg) >= (start) && (reg) < (end)) +static int fw_range_cmp(u32 offset, const struct intel_forcewake_range *entry) +{ + if (offset < entry->start) + return -1; + else if (offset > entry->end) + return 1; + else + return 0; +} + +/* Copied and "macroized" from lib/bsearch.c */ +#define BSEARCH(key, base, num, cmp) ({ \ + unsigned int start__ = 0, end__ = (num); \ + typeof(base) result__ = NULL; \ + while (start__ < end__) { \ + unsigned int mid__ = start__ + (end__ - start__) / 2; \ + int ret__ = (cmp)((key), (base) + mid__); \ + if (ret__ < 0) { \ + end__ = mid__; \ + } else if (ret__ > 0) { \ + start__ = mid__ + 1; \ + } else { \ + result__ = (base) + mid__; \ + break; \ + } \ + } \ + result__; \ +}) + +static enum forcewake_domains +find_fw_domain(struct drm_i915_private *dev_priv, u32 offset) +{ + const struct intel_forcewake_range *entry; + + entry = BSEARCH(offset, + dev_priv->uncore.fw_domains_table, + dev_priv->uncore.fw_domains_table_entries, + fw_range_cmp); -#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x2000, 0x4000) || \ - REG_RANGE((reg), 0x5000, 0x8000) || \ - REG_RANGE((reg), 0xB000, 0x12000) || \ - REG_RANGE((reg), 0x2E000, 0x30000)) + return entry ? entry->domains : 0; +} + +static void +intel_fw_table_check(struct drm_i915_private *dev_priv) +{ + const struct intel_forcewake_range *ranges; + unsigned int num_ranges; + s32 prev; + unsigned int i; + + if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG)) + return; + + ranges = dev_priv->uncore.fw_domains_table; + if (!ranges) + return; + + num_ranges = dev_priv->uncore.fw_domains_table_entries; + + for (i = 0, prev = -1; i < num_ranges; i++, ranges++) { + WARN_ON_ONCE(prev >= (s32)ranges->start); + prev = ranges->start; + WARN_ON_ONCE(prev >= (s32)ranges->end); + prev = ranges->end; + } +} -#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x12000, 0x14000) || \ - REG_RANGE((reg), 0x22000, 0x24000) || \ - REG_RANGE((reg), 0x30000, 0x40000)) +#define GEN_FW_RANGE(s, e, d) \ + { .start = (s), .end = (e), .domains = (d) } -#define __vlv_reg_read_fw_domains(offset) \ +#define HAS_FWTABLE(dev_priv) \ + (IS_GEN9(dev_priv) || \ + IS_CHERRYVIEW(dev_priv) || \ + IS_VALLEYVIEW(dev_priv)) + +/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */ +static const struct intel_forcewake_range __vlv_fw_ranges[] = { + GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x5000, 0x7fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xb000, 0x11fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x12000, 0x13fff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x22000, 0x23fff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x2e000, 0x2ffff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_MEDIA), +}; + +#define __fwtable_reg_read_fw_domains(offset) \ ({ \ enum forcewake_domains __fwd = 0; \ - if (!NEEDS_FORCE_WAKE(offset)) \ - __fwd = 0; \ - else if (FORCEWAKE_VLV_RENDER_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else if (FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_MEDIA; \ + if (NEEDS_FORCE_WAKE((offset))) \ + __fwd = find_fw_domain(dev_priv, offset); \ __fwd; \ }) +/* *Must* be sorted by offset! See intel_shadow_table_check(). */ static const i915_reg_t gen8_shadowed_regs[] = { - GEN6_RPNSWREQ, - GEN6_RC_VIDEO_FREQ, - RING_TAIL(RENDER_RING_BASE), - RING_TAIL(GEN6_BSD_RING_BASE), - RING_TAIL(VEBOX_RING_BASE), - RING_TAIL(BLT_RING_BASE), + RING_TAIL(RENDER_RING_BASE), /* 0x2000 (base) */ + GEN6_RPNSWREQ, /* 0xA008 */ + GEN6_RC_VIDEO_FREQ, /* 0xA00C */ + RING_TAIL(GEN6_BSD_RING_BASE), /* 0x12000 (base) */ + RING_TAIL(VEBOX_RING_BASE), /* 0x1a000 (base) */ + RING_TAIL(BLT_RING_BASE), /* 0x22000 (base) */ /* TODO: Other registers are not yet used */ }; +static void intel_shadow_table_check(void) +{ + const i915_reg_t *reg = gen8_shadowed_regs; + s32 prev; + u32 offset; + unsigned int i; + + if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG)) + return; + + for (i = 0, prev = -1; i < ARRAY_SIZE(gen8_shadowed_regs); i++, reg++) { + offset = i915_mmio_reg_offset(*reg); + WARN_ON_ONCE(prev >= (s32)offset); + prev = offset; + } +} + +static int mmio_reg_cmp(u32 key, const i915_reg_t *reg) +{ + u32 offset = i915_mmio_reg_offset(*reg); + + if (key < offset) + return -1; + else if (key > offset) + return 1; + else + return 0; +} + static bool is_gen8_shadowed(u32 offset) { - int i; - for (i = 0; i < ARRAY_SIZE(gen8_shadowed_regs); i++) - if (offset == gen8_shadowed_regs[i].reg) - return true; + const i915_reg_t *regs = gen8_shadowed_regs; - return false; + return BSEARCH(offset, regs, ARRAY_SIZE(gen8_shadowed_regs), + mmio_reg_cmp); } #define __gen8_reg_write_fw_domains(offset) \ @@ -644,143 +733,70 @@ static bool is_gen8_shadowed(u32 offset) __fwd; \ }) -#define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x2000, 0x4000) || \ - REG_RANGE((reg), 0x5200, 0x8000) || \ - REG_RANGE((reg), 0x8300, 0x8500) || \ - REG_RANGE((reg), 0xB000, 0xB480) || \ - REG_RANGE((reg), 0xE000, 0xE800)) - -#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x8800, 0x8900) || \ - REG_RANGE((reg), 0xD000, 0xD800) || \ - REG_RANGE((reg), 0x12000, 0x14000) || \ - REG_RANGE((reg), 0x1A000, 0x1C000) || \ - REG_RANGE((reg), 0x1E800, 0x1EA00) || \ - REG_RANGE((reg), 0x30000, 0x38000)) - -#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x4000, 0x5000) || \ - REG_RANGE((reg), 0x8000, 0x8300) || \ - REG_RANGE((reg), 0x8500, 0x8600) || \ - REG_RANGE((reg), 0x9000, 0xB000) || \ - REG_RANGE((reg), 0xF000, 0x10000)) - -#define __chv_reg_read_fw_domains(offset) \ -({ \ - enum forcewake_domains __fwd = 0; \ - if (!NEEDS_FORCE_WAKE(offset)) \ - __fwd = 0; \ - else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_MEDIA; \ - else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \ - __fwd; \ -}) +/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */ +static const struct intel_forcewake_range __chv_fw_ranges[] = { + GEN_FW_RANGE(0x2000, 0x3fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x4000, 0x4fff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8000, 0x82ff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x8300, 0x84ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8500, 0x85ff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x8800, 0x88ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x9000, 0xafff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0xb000, 0xb47f, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xd000, 0xd7ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0xe000, 0xe7ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xf000, 0xffff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x12000, 0x13fff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x1a000, 0x1bfff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x1e800, 0x1e9ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x30000, 0x37fff, FORCEWAKE_MEDIA), +}; -#define __chv_reg_write_fw_domains(offset) \ +#define __fwtable_reg_write_fw_domains(offset) \ ({ \ enum forcewake_domains __fwd = 0; \ - if (!NEEDS_FORCE_WAKE(offset) || is_gen8_shadowed(offset)) \ - __fwd = 0; \ - else if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_MEDIA; \ - else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \ - __fwd; \ -}) - -#define FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg) \ - REG_RANGE((reg), 0xB00, 0x2000) - -#define FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x2000, 0x2700) || \ - REG_RANGE((reg), 0x3000, 0x4000) || \ - REG_RANGE((reg), 0x5200, 0x8000) || \ - REG_RANGE((reg), 0x8140, 0x8160) || \ - REG_RANGE((reg), 0x8300, 0x8500) || \ - REG_RANGE((reg), 0x8C00, 0x8D00) || \ - REG_RANGE((reg), 0xB000, 0xB480) || \ - REG_RANGE((reg), 0xE000, 0xE900) || \ - REG_RANGE((reg), 0x24400, 0x24800)) - -#define FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg) \ - (REG_RANGE((reg), 0x8130, 0x8140) || \ - REG_RANGE((reg), 0x8800, 0x8A00) || \ - REG_RANGE((reg), 0xD000, 0xD800) || \ - REG_RANGE((reg), 0x12000, 0x14000) || \ - REG_RANGE((reg), 0x1A000, 0x1EA00) || \ - REG_RANGE((reg), 0x30000, 0x40000)) - -#define FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg) \ - REG_RANGE((reg), 0x9400, 0x9800) - -#define FORCEWAKE_GEN9_BLITTER_RANGE_OFFSET(reg) \ - ((reg) < 0x40000 && \ - !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg) && \ - !FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(reg) && \ - !FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(reg) && \ - !FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(reg)) - -#define SKL_NEEDS_FORCE_WAKE(reg) \ - ((reg) < 0x40000 && !FORCEWAKE_GEN9_UNCORE_RANGE_OFFSET(reg)) - -#define __gen9_reg_read_fw_domains(offset) \ -({ \ - enum forcewake_domains __fwd; \ - if (!SKL_NEEDS_FORCE_WAKE(offset)) \ - __fwd = 0; \ - else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_MEDIA; \ - else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \ - else \ - __fwd = FORCEWAKE_BLITTER; \ + if (NEEDS_FORCE_WAKE((offset)) && !is_gen8_shadowed(offset)) \ + __fwd = find_fw_domain(dev_priv, offset); \ __fwd; \ }) -static const i915_reg_t gen9_shadowed_regs[] = { - RING_TAIL(RENDER_RING_BASE), - RING_TAIL(GEN6_BSD_RING_BASE), - RING_TAIL(VEBOX_RING_BASE), - RING_TAIL(BLT_RING_BASE), - GEN6_RPNSWREQ, - GEN6_RC_VIDEO_FREQ, - /* TODO: Other registers are not yet used */ +/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */ +static const struct intel_forcewake_range __gen9_fw_ranges[] = { + GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0xb00, 0x1fff, 0), /* uncore range */ + GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x2700, 0x2fff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x3000, 0x3fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x4000, 0x51ff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8000, 0x812f, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x8130, 0x813f, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x8140, 0x815f, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8160, 0x82ff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x8300, 0x84ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8500, 0x87ff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x8800, 0x89ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x8a00, 0x8bff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x8c00, 0x8cff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x8d00, 0x93ff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x9400, 0x97ff, FORCEWAKE_RENDER | FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x9800, 0xafff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0xb000, 0xb47f, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xb480, 0xbfff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0xd000, 0xd7ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0xd800, 0xdfff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0xe000, 0xe8ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0xe900, 0x11fff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x12000, 0x13fff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x14000, 0x19fff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x1a000, 0x1e9ff, FORCEWAKE_MEDIA), + GEN_FW_RANGE(0x1ea00, 0x243ff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x24400, 0x247ff, FORCEWAKE_RENDER), + GEN_FW_RANGE(0x24800, 0x2ffff, FORCEWAKE_BLITTER), + GEN_FW_RANGE(0x30000, 0x3ffff, FORCEWAKE_MEDIA), }; -static bool is_gen9_shadowed(u32 offset) -{ - int i; - for (i = 0; i < ARRAY_SIZE(gen9_shadowed_regs); i++) - if (offset == gen9_shadowed_regs[i].reg) - return true; - - return false; -} - -#define __gen9_reg_write_fw_domains(offset) \ -({ \ - enum forcewake_domains __fwd; \ - if (!SKL_NEEDS_FORCE_WAKE(offset) || is_gen9_shadowed(offset)) \ - __fwd = 0; \ - else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else if (FORCEWAKE_GEN9_MEDIA_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_MEDIA; \ - else if (FORCEWAKE_GEN9_COMMON_RANGE_OFFSET(offset)) \ - __fwd = FORCEWAKE_RENDER | FORCEWAKE_MEDIA; \ - else \ - __fwd = FORCEWAKE_BLITTER; \ - __fwd; \ -}) - static void ilk_dummy_write(struct drm_i915_private *dev_priv) { @@ -869,26 +885,30 @@ __gen2_read(64) trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ return val -static inline void __force_wake_auto(struct drm_i915_private *dev_priv, - enum forcewake_domains fw_domains) +static noinline void ___force_wake_auto(struct drm_i915_private *dev_priv, + enum forcewake_domains fw_domains) { struct intel_uncore_forcewake_domain *domain; + for_each_fw_domain_masked(domain, fw_domains, dev_priv) + fw_domain_arm_timer(domain); + + dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); + dev_priv->uncore.fw_domains_active |= fw_domains; +} + +static inline void __force_wake_auto(struct drm_i915_private *dev_priv, + enum forcewake_domains fw_domains) +{ if (WARN_ON(!fw_domains)) return; - /* Ideally GCC would be constant-fold and eliminate this loop */ - for_each_fw_domain_masked(domain, fw_domains, dev_priv) { - if (domain->wake_count) { - fw_domains &= ~domain->mask; - continue; - } - - fw_domain_arm_timer(domain); - } + /* Turn on all requested but inactive supported forcewake domains. */ + fw_domains &= dev_priv->uncore.fw_domains; + fw_domains &= ~dev_priv->uncore.fw_domains_active; if (fw_domains) - dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains); + ___force_wake_auto(dev_priv, fw_domains); } #define __gen6_read(x) \ @@ -903,62 +923,28 @@ gen6_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ GEN6_READ_FOOTER; \ } -#define __vlv_read(x) \ -static u##x \ -vlv_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ - enum forcewake_domains fw_engine; \ - GEN6_READ_HEADER(x); \ - fw_engine = __vlv_reg_read_fw_domains(offset); \ - if (fw_engine) \ - __force_wake_auto(dev_priv, fw_engine); \ - val = __raw_i915_read##x(dev_priv, reg); \ - GEN6_READ_FOOTER; \ -} - -#define __chv_read(x) \ +#define __fwtable_read(x) \ static u##x \ -chv_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ +fwtable_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_READ_HEADER(x); \ - fw_engine = __chv_reg_read_fw_domains(offset); \ + fw_engine = __fwtable_reg_read_fw_domains(offset); \ if (fw_engine) \ __force_wake_auto(dev_priv, fw_engine); \ val = __raw_i915_read##x(dev_priv, reg); \ GEN6_READ_FOOTER; \ } -#define __gen9_read(x) \ -static u##x \ -gen9_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ - enum forcewake_domains fw_engine; \ - GEN6_READ_HEADER(x); \ - fw_engine = __gen9_reg_read_fw_domains(offset); \ - if (fw_engine) \ - __force_wake_auto(dev_priv, fw_engine); \ - val = __raw_i915_read##x(dev_priv, reg); \ - GEN6_READ_FOOTER; \ -} - -__gen9_read(8) -__gen9_read(16) -__gen9_read(32) -__gen9_read(64) -__chv_read(8) -__chv_read(16) -__chv_read(32) -__chv_read(64) -__vlv_read(8) -__vlv_read(16) -__vlv_read(32) -__vlv_read(64) +__fwtable_read(8) +__fwtable_read(16) +__fwtable_read(32) +__fwtable_read(64) __gen6_read(8) __gen6_read(16) __gen6_read(32) __gen6_read(64) -#undef __gen9_read -#undef __chv_read -#undef __vlv_read +#undef __fwtable_read #undef __gen6_read #undef GEN6_READ_FOOTER #undef GEN6_READ_HEADER @@ -1054,21 +1040,6 @@ gen6_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool GEN6_WRITE_FOOTER; \ } -#define __hsw_write(x) \ -static void \ -hsw_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ - u32 __fifo_ret = 0; \ - GEN6_WRITE_HEADER; \ - if (NEEDS_FORCE_WAKE(offset)) { \ - __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ - } \ - __raw_i915_write##x(dev_priv, reg, val); \ - if (unlikely(__fifo_ret)) { \ - gen6_gt_check_fifodbg(dev_priv); \ - } \ - GEN6_WRITE_FOOTER; \ -} - #define __gen8_write(x) \ static void \ gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ @@ -1081,51 +1052,30 @@ gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool GEN6_WRITE_FOOTER; \ } -#define __chv_write(x) \ -static void \ -chv_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ - enum forcewake_domains fw_engine; \ - GEN6_WRITE_HEADER; \ - fw_engine = __chv_reg_write_fw_domains(offset); \ - if (fw_engine) \ - __force_wake_auto(dev_priv, fw_engine); \ - __raw_i915_write##x(dev_priv, reg, val); \ - GEN6_WRITE_FOOTER; \ -} - -#define __gen9_write(x) \ +#define __fwtable_write(x) \ static void \ -gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \ - bool trace) { \ +fwtable_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_WRITE_HEADER; \ - fw_engine = __gen9_reg_write_fw_domains(offset); \ + fw_engine = __fwtable_reg_write_fw_domains(offset); \ if (fw_engine) \ __force_wake_auto(dev_priv, fw_engine); \ __raw_i915_write##x(dev_priv, reg, val); \ GEN6_WRITE_FOOTER; \ } -__gen9_write(8) -__gen9_write(16) -__gen9_write(32) -__chv_write(8) -__chv_write(16) -__chv_write(32) +__fwtable_write(8) +__fwtable_write(16) +__fwtable_write(32) __gen8_write(8) __gen8_write(16) __gen8_write(32) -__hsw_write(8) -__hsw_write(16) -__hsw_write(32) __gen6_write(8) __gen6_write(16) __gen6_write(32) -#undef __gen9_write -#undef __chv_write +#undef __fwtable_write #undef __gen8_write -#undef __hsw_write #undef __gen6_write #undef GEN6_WRITE_FOOTER #undef GEN6_WRITE_HEADER @@ -1314,6 +1264,13 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) WARN_ON(dev_priv->uncore.fw_domains == 0); } +#define ASSIGN_FW_DOMAINS_TABLE(d) \ +{ \ + dev_priv->uncore.fw_domains_table = \ + (struct intel_forcewake_range *)(d); \ + dev_priv->uncore.fw_domains_table_entries = ARRAY_SIZE((d)); \ +} + void intel_uncore_init(struct drm_i915_private *dev_priv) { i915_check_vgpu(dev_priv); @@ -1327,13 +1284,15 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) switch (INTEL_INFO(dev_priv)->gen) { default: case 9: - ASSIGN_WRITE_MMIO_VFUNCS(gen9); - ASSIGN_READ_MMIO_VFUNCS(gen9); + ASSIGN_FW_DOMAINS_TABLE(__gen9_fw_ranges); + ASSIGN_WRITE_MMIO_VFUNCS(fwtable); + ASSIGN_READ_MMIO_VFUNCS(fwtable); break; case 8: if (IS_CHERRYVIEW(dev_priv)) { - ASSIGN_WRITE_MMIO_VFUNCS(chv); - ASSIGN_READ_MMIO_VFUNCS(chv); + ASSIGN_FW_DOMAINS_TABLE(__chv_fw_ranges); + ASSIGN_WRITE_MMIO_VFUNCS(fwtable); + ASSIGN_READ_MMIO_VFUNCS(fwtable); } else { ASSIGN_WRITE_MMIO_VFUNCS(gen8); @@ -1342,14 +1301,11 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) break; case 7: case 6: - if (IS_HASWELL(dev_priv)) { - ASSIGN_WRITE_MMIO_VFUNCS(hsw); - } else { - ASSIGN_WRITE_MMIO_VFUNCS(gen6); - } + ASSIGN_WRITE_MMIO_VFUNCS(gen6); if (IS_VALLEYVIEW(dev_priv)) { - ASSIGN_READ_MMIO_VFUNCS(vlv); + ASSIGN_FW_DOMAINS_TABLE(__vlv_fw_ranges); + ASSIGN_READ_MMIO_VFUNCS(fwtable); } else { ASSIGN_READ_MMIO_VFUNCS(gen6); } @@ -1366,6 +1322,10 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) break; } + intel_fw_table_check(dev_priv); + if (INTEL_GEN(dev_priv) >= 8) + intel_shadow_table_check(); + if (intel_vgpu_active(dev_priv)) { ASSIGN_WRITE_MMIO_VFUNCS(vgpu); ASSIGN_READ_MMIO_VFUNCS(vgpu); @@ -1815,35 +1775,16 @@ static enum forcewake_domains intel_uncore_forcewake_for_read(struct drm_i915_private *dev_priv, i915_reg_t reg) { + u32 offset = i915_mmio_reg_offset(reg); enum forcewake_domains fw_domains; - if (intel_vgpu_active(dev_priv)) - return 0; - - switch (INTEL_GEN(dev_priv)) { - case 9: - fw_domains = __gen9_reg_read_fw_domains(i915_mmio_reg_offset(reg)); - break; - case 8: - if (IS_CHERRYVIEW(dev_priv)) - fw_domains = __chv_reg_read_fw_domains(i915_mmio_reg_offset(reg)); - else - fw_domains = __gen6_reg_read_fw_domains(i915_mmio_reg_offset(reg)); - break; - case 7: - case 6: - if (IS_VALLEYVIEW(dev_priv)) - fw_domains = __vlv_reg_read_fw_domains(i915_mmio_reg_offset(reg)); - else - fw_domains = __gen6_reg_read_fw_domains(i915_mmio_reg_offset(reg)); - break; - default: - MISSING_CASE(INTEL_INFO(dev_priv)->gen); - case 5: /* forcewake was introduced with gen6 */ - case 4: - case 3: - case 2: - return 0; + if (HAS_FWTABLE(dev_priv)) { + fw_domains = __fwtable_reg_read_fw_domains(offset); + } else if (INTEL_GEN(dev_priv) >= 6) { + fw_domains = __gen6_reg_read_fw_domains(offset); + } else { + WARN_ON(!IS_GEN(dev_priv, 2, 5)); + fw_domains = 0; } WARN_ON(fw_domains & ~dev_priv->uncore.fw_domains); @@ -1855,32 +1796,18 @@ static enum forcewake_domains intel_uncore_forcewake_for_write(struct drm_i915_private *dev_priv, i915_reg_t reg) { + u32 offset = i915_mmio_reg_offset(reg); enum forcewake_domains fw_domains; - if (intel_vgpu_active(dev_priv)) - return 0; - - switch (INTEL_GEN(dev_priv)) { - case 9: - fw_domains = __gen9_reg_write_fw_domains(i915_mmio_reg_offset(reg)); - break; - case 8: - if (IS_CHERRYVIEW(dev_priv)) - fw_domains = __chv_reg_write_fw_domains(i915_mmio_reg_offset(reg)); - else - fw_domains = __gen8_reg_write_fw_domains(i915_mmio_reg_offset(reg)); - break; - case 7: - case 6: + if (HAS_FWTABLE(dev_priv) && !IS_VALLEYVIEW(dev_priv)) { + fw_domains = __fwtable_reg_write_fw_domains(offset); + } else if (IS_GEN8(dev_priv)) { + fw_domains = __gen8_reg_write_fw_domains(offset); + } else if (IS_GEN(dev_priv, 6, 7)) { fw_domains = FORCEWAKE_RENDER; - break; - default: - MISSING_CASE(INTEL_INFO(dev_priv)->gen); - case 5: - case 4: - case 3: - case 2: - return 0; + } else { + WARN_ON(!IS_GEN(dev_priv, 2, 5)); + fw_domains = 0; } WARN_ON(fw_domains & ~dev_priv->uncore.fw_domains); @@ -1910,6 +1837,9 @@ intel_uncore_forcewake_for_reg(struct drm_i915_private *dev_priv, WARN_ON(!op); + if (intel_vgpu_active(dev_priv)) + return 0; + if (op & FW_REG_READ) fw_domains = intel_uncore_forcewake_for_read(dev_priv, reg); |
