diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
22 files changed, 204 insertions, 184 deletions
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index eea79125b3ea..438040ff0179 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -7,7 +7,6 @@ config DRM_I915_WERROR # We use the dependency on !COMPILE_TEST to not be enabled in # allmodconfig or allyesconfig configurations depends on !COMPILE_TEST - select HEADER_TEST default n help Add -Werror to the build flags for (and only for) i915.ko. @@ -22,7 +21,6 @@ config DRM_I915_DEBUG depends on DRM_I915 select DEBUG_FS select PREEMPT_COUNT - select REFCOUNT_FULL select I2C_CHARDEV select STACKDEPOT select DRM_DP_AUX_CHARDEV diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index c7c2b349858d..2a27fb5d7dc6 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3986,6 +3986,7 @@ static void intel_enable_ddi(struct intel_encoder *encoder, if (conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) intel_hdcp_enable(to_intel_connector(conn_state->connector), + crtc_state->cpu_transcoder, (u8)conn_state->hdcp_content_type); } @@ -4089,7 +4090,9 @@ static void intel_ddi_update_pipe(struct intel_encoder *encoder, if (conn_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED || content_protection_type_changed) - intel_hdcp_enable(connector, (u8)conn_state->hdcp_content_type); + intel_hdcp_enable(connector, + crtc_state->cpu_transcoder, + (u8)conn_state->hdcp_content_type); } static void diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 707ac110e271..ce1b64f4dd44 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -5015,6 +5015,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) power_domains->initializing = true; + /* Must happen before power domain init on VLV/CHV */ + intel_update_rawclk(i915); + if (INTEL_GEN(i915) >= 11) { icl_display_core_init(i915, resume); } else if (IS_CANNONLAKE(i915)) { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index c61ac0c3acb5..b05b2191b919 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2414,9 +2414,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_psr_compute_config(intel_dp, pipe_config); - intel_hdcp_transcoder_config(intel_connector, - pipe_config->cpu_transcoder); - return 0; } @@ -5476,15 +5473,13 @@ static bool bxt_digital_port_connected(struct intel_encoder *encoder) return I915_READ(GEN8_DE_PORT_ISR) & bit; } -static bool icl_combo_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *intel_dig_port) +static bool intel_combo_phy_connected(struct drm_i915_private *dev_priv, + enum phy phy) { - enum port port = intel_dig_port->base.port; - - if (HAS_PCH_MCC(dev_priv) && port == PORT_C) + if (HAS_PCH_MCC(dev_priv) && phy == PHY_C) return I915_READ(SDEISR) & SDE_TC_HOTPLUG_ICP(PORT_TC1); - return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(port); + return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(phy); } static bool icl_digital_port_connected(struct intel_encoder *encoder) @@ -5494,7 +5489,7 @@ static bool icl_digital_port_connected(struct intel_encoder *encoder) enum phy phy = intel_port_to_phy(dev_priv, encoder->port); if (intel_phy_is_combo(dev_priv, phy)) - return icl_combo_port_connected(dev_priv, dig_port); + return intel_combo_phy_connected(dev_priv, phy); else if (intel_phy_is_tc(dev_priv, phy)) return intel_tc_port_connected(dig_port); else diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 3111ecaeabd0..20616639b8ab 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1284,7 +1284,7 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) return 0; /* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */ - if (IS_GEMINILAKE(dev_priv)) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 0; if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index f1f41ca8402b..a448815d8fc2 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1821,23 +1821,6 @@ enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder) } } -void intel_hdcp_transcoder_config(struct intel_connector *connector, - enum transcoder cpu_transcoder) -{ - struct drm_i915_private *dev_priv = to_i915(connector->base.dev); - struct intel_hdcp *hdcp = &connector->hdcp; - - if (!hdcp->shim) - return; - - if (INTEL_GEN(dev_priv) >= 12) { - mutex_lock(&hdcp->mutex); - hdcp->cpu_transcoder = cpu_transcoder; - hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder); - mutex_unlock(&hdcp->mutex); - } -} - static inline int initialize_hdcp_port_data(struct intel_connector *connector, const struct intel_hdcp_shim *shim) { @@ -1959,8 +1942,10 @@ int intel_hdcp_init(struct intel_connector *connector, return 0; } -int intel_hdcp_enable(struct intel_connector *connector, u8 content_type) +int intel_hdcp_enable(struct intel_connector *connector, + enum transcoder cpu_transcoder, u8 content_type) { + struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; unsigned long check_link_interval = DRM_HDCP_CHECK_PERIOD_MS; int ret = -EINVAL; @@ -1972,6 +1957,11 @@ int intel_hdcp_enable(struct intel_connector *connector, u8 content_type) WARN_ON(hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED); hdcp->content_type = content_type; + if (INTEL_GEN(dev_priv) >= 12) { + hdcp->cpu_transcoder = cpu_transcoder; + hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder); + } + /* * Considering that HDCP2.2 is more secure than HDCP1.4, If the setup * is capable of HDCP2.2, it is preferred to use HDCP2.2. diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h index 41c1053d9e38..f3c3272e712a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp.h @@ -21,11 +21,10 @@ enum transcoder; void intel_hdcp_atomic_check(struct drm_connector *connector, struct drm_connector_state *old_state, struct drm_connector_state *new_state); -void intel_hdcp_transcoder_config(struct intel_connector *connector, - enum transcoder cpu_transcoder); int intel_hdcp_init(struct intel_connector *connector, const struct intel_hdcp_shim *hdcp_shim); -int intel_hdcp_enable(struct intel_connector *connector, u8 content_type); +int intel_hdcp_enable(struct intel_connector *connector, + enum transcoder cpu_transcoder, u8 content_type); int intel_hdcp_disable(struct intel_connector *connector); bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port); bool intel_hdcp_capable(struct intel_connector *connector); diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index f6f5312205c4..f56fffc474fa 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2489,9 +2489,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder, return -EINVAL; } - intel_hdcp_transcoder_config(intel_hdmi->attached_connector, - pipe_config->cpu_transcoder); - return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 255ab040022e..337ba17b1e0e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -368,7 +368,7 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (!ce->timeline) return NULL; - rcu_read_lock(); + mutex_lock(&ce->timeline->mutex); list_for_each_entry_reverse(rq, &ce->timeline->requests, link) { if (i915_request_completed(rq)) break; @@ -378,7 +378,7 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (engine) break; } - rcu_read_unlock(); + mutex_unlock(&ce->timeline->mutex); return engine; } @@ -1687,7 +1687,7 @@ replace: i915_gem_context_set_user_engines(ctx); else i915_gem_context_clear_user_engines(ctx); - rcu_swap_protected(ctx->engines, set.engines, 1); + set.engines = rcu_replace_pointer(ctx->engines, set.engines, 1); mutex_unlock(&ctx->engines_mutex); call_rcu(&set.engines->rcu, free_engines_rcu); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index fd3ce6da8497..f2418a1cfe68 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -437,12 +437,12 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915, fs_reclaim_acquire(GFP_KERNEL); mutex_acquire(&mutex->dep_map, 0, 0, _RET_IP_); - mutex_release(&mutex->dep_map, 0, _RET_IP_); + mutex_release(&mutex->dep_map, _RET_IP_); fs_reclaim_release(GFP_KERNEL); if (unlock) - mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_); + mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_); } #define obj_to_i915(obj__) to_i915((obj__)->base.dev) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 0e1ad4a4bd97..c1dd0cd3efc7 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -55,7 +55,7 @@ static inline unsigned long __timeline_mark_lock(struct intel_context *ce) static inline void __timeline_mark_unlock(struct intel_context *ce, unsigned long flags) { - mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_); + mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_); local_irq_restore(flags); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c index 3cdbd5f8b5be..397186818305 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c @@ -104,6 +104,8 @@ node_create(struct intel_engine_pool *pool, size_t sz) return ERR_CAST(obj); } + i915_gem_object_set_readonly(obj); + node->obj = obj; return node; } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 9fdefbdc3546..75dd0e0367b7 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -845,12 +845,6 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) } } -static void unwind_wa_tail(struct i915_request *rq) -{ - rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES); - assert_ring_tail_valid(rq->ring, rq->tail); -} - static struct i915_request * __unwind_incomplete_requests(struct intel_engine_cs *engine) { @@ -863,12 +857,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) list_for_each_entry_safe_reverse(rq, rn, &engine->active.requests, sched.link) { - if (i915_request_completed(rq)) continue; /* XXX */ __i915_request_unsubmit(rq); - unwind_wa_tail(rq); /* * Push the request back into the queue for later resubmission. @@ -1161,13 +1153,29 @@ execlists_schedule_out(struct i915_request *rq) i915_request_put(rq); } -static u64 execlists_update_context(const struct i915_request *rq) +static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->hw_context; - u64 desc; + u64 desc = ce->lrc_desc; + u32 tail; - ce->lrc_reg_state[CTX_RING_TAIL] = - intel_ring_set_tail(rq->ring, rq->tail); + /* + * WaIdleLiteRestore:bdw,skl + * + * We should never submit the context with the same RING_TAIL twice + * just in case we submit an empty ring, which confuses the HW. + * + * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of + * the normal request to be able to always advance the RING_TAIL on + * subsequent resubmissions (for lite restore). Should that fail us, + * and we try and submit the same tail again, force the context + * reload. + */ + tail = intel_ring_set_tail(rq->ring, rq->tail); + if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) + desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_reg_state[CTX_RING_TAIL] = tail; + rq->tail = rq->wa_tail; /* * Make sure the context image is complete before we submit it to HW. @@ -1186,13 +1194,11 @@ static u64 execlists_update_context(const struct i915_request *rq) */ mb(); - desc = ce->lrc_desc; - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; - /* Wa_1607138340:tgl */ if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0)) desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1703,16 +1709,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) return; } - - /* - * WaIdleLiteRestore:bdw,skl - * Apply the wa NOOPs to prevent - * ring:HEAD == rq:TAIL as we resubmit the - * request. See gen8_emit_fini_breadcrumb() for - * where we prepare the padding after the - * end of the request. - */ - last->tail = last->wa_tail; } } @@ -4120,17 +4116,18 @@ static void virtual_context_destroy(struct kref *kref) for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; + unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irq(&sibling->active.lock); + spin_lock_irqsave(&sibling->active.lock, flags); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irq(&sibling->active.lock); + spin_unlock_irqrestore(&sibling->active.lock, flags); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 6e881c735b20..2b977991b785 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -200,14 +200,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { MOCS_ENTRY(15, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \ L3_3_WB), \ - /* Bypass LLC - Uncached (EHL+) */ \ - MOCS_ENTRY(16, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_1_UC), \ - /* Bypass LLC - L3 (Read-Only) (EHL+) */ \ - MOCS_ENTRY(17, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_3_WB), \ /* Self-Snoop - L3 + LLC */ \ MOCS_ENTRY(18, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \ @@ -271,7 +263,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = { L3_1_UC), /* HW Special Case (Displayable) */ MOCS_ENTRY(61, - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), + LE_1_UC | LE_TC_1_LLC, L3_3_WB), }; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 6a3ac8cde95d..21a176cd8acc 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1599,9 +1599,9 @@ static int cmd_handler_mi_op_2f(struct parser_exec_state *s) if (!(cmd_val(s, 0) & (1 << 22))) return ret; - /* check if QWORD */ - if (DWORD_FIELD(0, 20, 19) == 1) - valid_len += 8; + /* check inline data */ + if (cmd_val(s, 0) & BIT(18)) + valid_len = CMD_LEN(9); ret = gvt_check_valid_cmd_length(cmd_length(s), valid_len); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index a816aef6142b..e451298d11c3 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -499,8 +499,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) goto out_free_gem; } - i915_gem_object_put(obj); - ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR); if (ret < 0) { gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret); @@ -525,6 +523,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) file_count(dmabuf->file), kref_read(&obj->base.refcount)); + i915_gem_object_put(obj); + return dmabuf_fd; out_free_dmabuf: diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index bd12af349123..bb9fe6bf5275 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -460,6 +460,7 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, static i915_reg_t force_nonpriv_white_list[] = { GEN9_CS_DEBUG_MODE1, //_MMIO(0x20ec) GEN9_CTX_PREEMPT_REG,//_MMIO(0x2248) + PS_INVOCATION_COUNT,//_MMIO(0x2348) GEN8_CS_CHICKEN1,//_MMIO(0x2580) _MMIO(0x2690), _MMIO(0x2694), @@ -508,7 +509,7 @@ static inline bool in_whitelist(unsigned int reg) static int force_nonpriv_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - u32 reg_nonpriv = *(u32 *)p_data; + u32 reg_nonpriv = (*(u32 *)p_data) & REG_GENMASK(25, 2); int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset); u32 ring_base; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; @@ -528,7 +529,7 @@ static int force_nonpriv_write(struct intel_vgpu *vgpu, bytes); } else gvt_err("vgpu(%d) Invalid FORCE_NONPRIV write %x at offset %x\n", - vgpu->id, reg_nonpriv, offset); + vgpu->id, *(u32 *)p_data, offset); return 0; } diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index dca15ace88f6..a19e7d89bc8a 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -384,7 +384,7 @@ void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f) mutex_acquire(&ref->mutex.dep_map, 0, 0, _THIS_IP_); if (!__i915_active_fence_set(&ref->excl, f)) atomic_inc(&ref->count); - mutex_release(&ref->mutex.dep_map, 0, _THIS_IP_); + mutex_release(&ref->mutex.dep_map, _THIS_IP_); } bool i915_active_acquire_if_busy(struct i915_active *ref) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 87e05ca3646a..3c512c571e60 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -297,9 +297,6 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915) if (ret) goto cleanup_vga_client; - /* must happen before intel_power_domains_init_hw() on VLV/CHV */ - intel_update_rawclk(i915); - intel_power_domains_init_hw(i915, false); intel_csr_ucode_init(i915); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b9eb6b3149b7..d034fa413164 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -45,6 +45,7 @@ #include "gem/i915_gem_context.h" #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_pm.h" +#include "gt/intel_context.h" #include "gt/intel_engine_user.h" #include "gt/intel_gt.h" #include "gt/intel_gt_pm.h" @@ -1053,6 +1054,18 @@ out: return err; } +static int __intel_context_flush_retire(struct intel_context *ce) +{ + struct intel_timeline *tl; + + tl = intel_context_timeline_lock(ce); + if (IS_ERR(tl)) + return PTR_ERR(tl); + + intel_context_timeline_unlock(tl); + return 0; +} + static int __intel_engines_record_defaults(struct intel_gt *gt) { struct i915_request *requests[I915_NUM_ENGINES] = {}; @@ -1121,13 +1134,20 @@ err_rq: if (!rq) continue; - /* We want to be able to unbind the state from the GGTT */ - GEM_BUG_ON(intel_context_is_pinned(rq->hw_context)); - + GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT, + &rq->hw_context->flags)); state = rq->hw_context->state; if (!state) continue; + /* Serialise with retirement on another CPU */ + err = __intel_context_flush_retire(rq->hw_context); + if (err) + goto out; + + /* We want to be able to unbind the state from the GGTT */ + GEM_BUG_ON(intel_context_is_pinned(rq->hw_context)); + /* * As we will hold a reference to the logical state, it will * not be torn down with the context, and importantly the diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 65d7c2e599de..2ae14bc14931 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce, u32 *reg_state = ce->lrc_reg_state; int i; - if (IS_GEN(stream->perf->i915, 12)) { - u32 format = stream->oa_buffer.format; + reg_state[ctx_oactxctrl + 1] = + (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | + (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | + GEN8_OA_COUNTER_RESUME; - reg_state[ctx_oactxctrl + 1] = - (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | - (stream->oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0); - } else { - reg_state[ctx_oactxctrl + 1] = - (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | - (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | - GEN8_OA_COUNTER_RESUME; - } - - for (i = 0; !!ctx_flexeu0 && i < ARRAY_SIZE(flex_regs); i++) + for (i = 0; i < ARRAY_SIZE(flex_regs); i++) reg_state[ctx_flexeu0 + i * 2 + 1] = oa_config_flex_reg(stream->oa_config, flex_regs[i]); @@ -2224,34 +2216,51 @@ static int gen8_configure_context(struct i915_gem_context *ctx, return err; } -static int gen12_emit_oar_config(struct intel_context *ce, bool enable) +static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable) { - struct i915_request *rq; - u32 *cs; - int err = 0; - - rq = i915_request_create(ce); - if (IS_ERR(rq)) - return PTR_ERR(rq); - - cs = intel_ring_begin(rq, 4); - if (IS_ERR(cs)) { - err = PTR_ERR(cs); - goto out; - } - - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base)); - *cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE, - enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0); - *cs++ = MI_NOOP; + int err; + struct intel_context *ce = stream->pinned_ctx; + u32 format = stream->oa_buffer.format; + struct flex regs_context[] = { + { + GEN8_OACTXCONTROL, + stream->perf->ctx_oactxctrl_offset + 1, + enable ? GEN8_OA_COUNTER_RESUME : 0, + }, + }; + /* Offsets in regs_lri are not used since this configuration is only + * applied using LRI. Initialize the correct offsets for posterity. + */ +#define GEN12_OAR_OACONTROL_OFFSET 0x5B0 + struct flex regs_lri[] = { + { + GEN12_OAR_OACONTROL, + GEN12_OAR_OACONTROL_OFFSET + 1, + (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | + (enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0) + }, + { + RING_CONTEXT_CONTROL(ce->engine->mmio_base), + CTX_CONTEXT_CONTROL, + _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE, + enable ? + GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : + 0) + }, + }; - intel_ring_advance(rq, cs); + /* Modify the context image of pinned context with regs_context*/ + err = intel_context_lock_pinned(ce); + if (err) + return err; -out: - i915_request_add(rq); + err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context)); + intel_context_unlock_pinned(ce); + if (err) + return err; - return err; + /* Apply regs_lri using LRI with pinned context */ + return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri)); } /* @@ -2277,53 +2286,16 @@ out: * per-context OA state. * * Note: it's only the RCS/Render context that has any OA state. + * Note: the first flex register passed must always be R_PWR_CLK_STATE */ -static int lrc_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config) +static int oa_configure_all_contexts(struct i915_perf_stream *stream, + struct flex *regs, + size_t num_regs) { struct drm_i915_private *i915 = stream->perf->i915; - /* The MMIO offsets for Flex EU registers aren't contiguous */ - const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; -#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1) - struct flex regs[] = { - { - GEN8_R_PWR_CLK_STATE, - CTX_R_PWR_CLK_STATE, - }, - { - IS_GEN(i915, 12) ? - GEN12_OAR_OACONTROL : GEN8_OACTXCONTROL, - stream->perf->ctx_oactxctrl_offset + 1, - }, - { EU_PERF_CNTL0, ctx_flexeuN(0) }, - { EU_PERF_CNTL1, ctx_flexeuN(1) }, - { EU_PERF_CNTL2, ctx_flexeuN(2) }, - { EU_PERF_CNTL3, ctx_flexeuN(3) }, - { EU_PERF_CNTL4, ctx_flexeuN(4) }, - { EU_PERF_CNTL5, ctx_flexeuN(5) }, - { EU_PERF_CNTL6, ctx_flexeuN(6) }, - }; -#undef ctx_flexeuN struct intel_engine_cs *engine; struct i915_gem_context *ctx, *cn; - size_t array_size = IS_GEN(i915, 12) ? 2 : ARRAY_SIZE(regs); - int i, err; - - if (IS_GEN(i915, 12)) { - u32 format = stream->oa_buffer.format; - - regs[1].value = - (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) | - (oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0); - } else { - regs[1].value = - (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | - (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | - GEN8_OA_COUNTER_RESUME; - } - - for (i = 2; !!ctx_flexeu0 && i < array_size; i++) - regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg); + int err; lockdep_assert_held(&stream->perf->lock); @@ -2353,7 +2325,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, spin_unlock(&i915->gem.contexts.lock); - err = gen8_configure_context(ctx, regs, array_size); + err = gen8_configure_context(ctx, regs, num_regs); if (err) { i915_gem_context_put(ctx); return err; @@ -2378,7 +2350,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu); - err = gen8_modify_self(ce, regs, array_size); + err = gen8_modify_self(ce, regs, num_regs); if (err) return err; } @@ -2386,6 +2358,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, return 0; } +static int gen12_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config) +{ + struct flex regs[] = { + { + GEN8_R_PWR_CLK_STATE, + CTX_R_PWR_CLK_STATE, + }, + }; + + return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); +} + +static int lrc_configure_all_contexts(struct i915_perf_stream *stream, + const struct i915_oa_config *oa_config) +{ + /* The MMIO offsets for Flex EU registers aren't contiguous */ + const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset; +#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1) + struct flex regs[] = { + { + GEN8_R_PWR_CLK_STATE, + CTX_R_PWR_CLK_STATE, + }, + { + GEN8_OACTXCONTROL, + stream->perf->ctx_oactxctrl_offset + 1, + }, + { EU_PERF_CNTL0, ctx_flexeuN(0) }, + { EU_PERF_CNTL1, ctx_flexeuN(1) }, + { EU_PERF_CNTL2, ctx_flexeuN(2) }, + { EU_PERF_CNTL3, ctx_flexeuN(3) }, + { EU_PERF_CNTL4, ctx_flexeuN(4) }, + { EU_PERF_CNTL5, ctx_flexeuN(5) }, + { EU_PERF_CNTL6, ctx_flexeuN(6) }, + }; +#undef ctx_flexeuN + int i; + + regs[1].value = + (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) | + (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) | + GEN8_OA_COUNTER_RESUME; + + for (i = 2; i < ARRAY_SIZE(regs); i++) + regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg); + + return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); +} + static int gen8_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; @@ -2464,7 +2486,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = lrc_configure_all_contexts(stream, oa_config); + ret = gen12_configure_all_contexts(stream, oa_config); if (ret) return ret; @@ -2474,8 +2496,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) * requested this. */ if (stream->ctx) { - ret = gen12_emit_oar_config(stream->pinned_ctx, - oa_config != NULL); + ret = gen12_configure_oar_context(stream, true); if (ret) return ret; } @@ -2509,11 +2530,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) struct intel_uncore *uncore = stream->uncore; /* Reset all contexts' slices/subslices configurations. */ - lrc_configure_all_contexts(stream, NULL); + gen12_configure_all_contexts(stream, NULL); /* disable the context save/restore or OAR counters */ if (stream->ctx) - gen12_emit_oar_config(stream->pinned_ctx, false); + gen12_configure_oar_context(stream, false); /* Make sure we disable noa to save power. */ intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0); @@ -2713,7 +2734,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return -EINVAL; } - if (!(props->sample_flags & SAMPLE_OA_REPORT)) { + if (!(props->sample_flags & SAMPLE_OA_REPORT) && + (INTEL_GEN(perf->i915) < 12 || !stream->ctx)) { DRM_DEBUG("Only OA report sampling supported\n"); return -EINVAL; } @@ -2745,7 +2767,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, format_size = perf->oa_formats[props->oa_format].size; - stream->sample_flags |= SAMPLE_OA_REPORT; + stream->sample_flags = props->sample_flags; stream->sample_size += format_size; stream->oa_buffer.format_size = format_size; @@ -2854,7 +2876,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce, return; stream = engine->i915->perf.exclusive_stream; - if (stream) + /* + * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller + * is already doing that, so nothing to be done for gen12 here. + */ + if (stream && INTEL_GEN(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 00011f9533b6..bbd71af00a91 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1502,7 +1502,7 @@ long i915_request_wait(struct i915_request *rq, dma_fence_remove_callback(&rq->fence, &wait.cb); out: - mutex_release(&rq->engine->gt->reset.mutex.dep_map, 0, _THIS_IP_); + mutex_release(&rq->engine->gt->reset.mutex.dep_map, _THIS_IP_); trace_i915_request_wait_end(rq); return timeout; } |
