diff options
31 files changed, 1378 insertions, 470 deletions
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index aef87fdbd187..44311296ec02 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -840,6 +840,14 @@ static bool i830_check_flags(unsigned int flags) return false; } +void intel_gtt_insert_page(dma_addr_t addr, + unsigned int pg, + unsigned int flags) +{ + intel_private.driver->write_entry(addr, pg, flags); +} +EXPORT_SYMBOL(intel_gtt_insert_page); + void intel_gtt_insert_sg_entries(struct sg_table *st, unsigned int pg_start, unsigned int flags) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index d97f28bfa9db..b0fd6a7b0603 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -737,7 +737,7 @@ static void fini_hash_table(struct intel_engine_cs *engine) /** * i915_cmd_parser_init_ring() - set cmd parser related fields for a ringbuffer - * @ring: the ringbuffer to initialize + * @engine: the engine to initialize * * Optionally initializes fields related to batch buffer command parsing in the * struct intel_engine_cs based on whether the platform requires software @@ -830,7 +830,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine) /** * i915_cmd_parser_fini_ring() - clean up cmd parser related fields - * @ring: the ringbuffer to clean up + * @engine: the engine to clean up * * Releases any resources related to command parsing that may have been * initialized for the specified ring. @@ -1024,7 +1024,7 @@ unpin_src: /** * i915_needs_cmd_parser() - should a given ring use software command parsing? - * @ring: the ring in question + * @engine: the engine in question * * Only certain platforms require software batch buffer command parsing, and * only when enabled via module parameter. @@ -1176,7 +1176,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, /** * i915_parse_cmds() - parse a submitted batch buffer for privilege violations - * @ring: the ring on which the batch is to execute + * @engine: the engine on which the batch is to execute * @batch_obj: the batch buffer in question * @shadow_batch_obj: copy of the batch buffer in question * @batch_start_offset: byte offset in the batch at which execution starts @@ -1281,6 +1281,7 @@ int i915_parse_cmds(struct intel_engine_cs *engine, /** * i915_cmd_parser_get_version() - get the cmd parser version number + * @dev_priv: i915 device private * * The cmd parser maintains a simple increasing integer version number suitable * for passing to userspace clients to determine what operations are permitted. diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 614ac085e51f..5b7526697838 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -2574,6 +2574,10 @@ static int i915_guc_info(struct seq_file *m, void *data) mutex_unlock(&dev->struct_mutex); + seq_printf(m, "Doorbell map:\n"); + seq_printf(m, "\t%*pb\n", GUC_MAX_DOORBELLS, guc.doorbell_bitmap); + seq_printf(m, "Doorbell next cacheline: 0x%x\n\n", guc.db_cacheline); + seq_printf(m, "GuC total action count: %llu\n", guc.action_count); seq_printf(m, "GuC action failure count: %u\n", guc.action_fail); seq_printf(m, "GuC last action command: 0x%x\n", guc.action_cmd); @@ -5306,6 +5310,10 @@ static int i915_sseu_status(struct seq_file *m, void *unused) INTEL_INFO(dev)->eu_total); seq_printf(m, " Available EU Per Subslice: %u\n", INTEL_INFO(dev)->eu_per_subslice); + seq_printf(m, " Has Pooled EU: %s\n", yesno(HAS_POOLED_EU(dev))); + if (HAS_POOLED_EU(dev)) + seq_printf(m, " Min EU in pool: %u\n", + INTEL_INFO(dev)->min_eu_in_pool); seq_printf(m, " Has Slice Power Gating: %s\n", yesno(INTEL_INFO(dev)->has_slice_pg)); seq_printf(m, " Has Subslice Power Gating: %s\n", diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 07edaed9d5a2..24b670f72ed4 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -764,6 +764,32 @@ static void gen9_sseu_info_init(struct drm_device *dev) (info->slice_total > 1)); info->has_subslice_pg = (IS_BROXTON(dev) && (info->subslice_total > 1)); info->has_eu_pg = (info->eu_per_subslice > 2); + + if (IS_BROXTON(dev)) { +#define IS_SS_DISABLED(_ss_disable, ss) (_ss_disable & (0x1 << ss)) + /* + * There is a HW issue in 2x6 fused down parts that requires + * Pooled EU to be enabled as a WA. The pool configuration + * changes depending upon which subslice is fused down. This + * doesn't affect if the device has all 3 subslices enabled. + */ + /* WaEnablePooledEuFor2x6:bxt */ + info->has_pooled_eu = ((info->subslice_per_slice == 3) || + (info->subslice_per_slice == 2 && + INTEL_REVID(dev) < BXT_REVID_C0)); + + info->min_eu_in_pool = 0; + if (info->has_pooled_eu) { + if (IS_SS_DISABLED(ss_disable, 0) || + IS_SS_DISABLED(ss_disable, 2)) + info->min_eu_in_pool = 3; + else if (IS_SS_DISABLED(ss_disable, 1)) + info->min_eu_in_pool = 6; + else + info->min_eu_in_pool = 9; + } +#undef IS_SS_DISABLED + } } static void broadwell_sseu_info_init(struct drm_device *dev) @@ -962,6 +988,9 @@ static void intel_device_info_runtime_init(struct drm_device *dev) DRM_DEBUG_DRIVER("subslice per slice: %u\n", info->subslice_per_slice); DRM_DEBUG_DRIVER("EU total: %u\n", info->eu_total); DRM_DEBUG_DRIVER("EU per subslice: %u\n", info->eu_per_subslice); + DRM_DEBUG_DRIVER("Has Pooled EU: %s\n", HAS_POOLED_EU(dev) ? "y" : "n"); + if (HAS_POOLED_EU(dev)) + DRM_DEBUG_DRIVER("Min EU in pool: %u\n", info->min_eu_in_pool); DRM_DEBUG_DRIVER("has slice power gating: %s\n", info->has_slice_pg ? "y" : "n"); DRM_DEBUG_DRIVER("has subslice power gating: %s\n", diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 872c60608dbd..3eb47fbcea73 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -355,6 +355,7 @@ static const struct intel_device_info intel_broxton_info = { .has_ddi = 1, .has_fpga_dbg = 1, .has_fbc = 1, + .has_pooled_eu = 0, GEN_DEFAULT_PIPEOFFSETS, IVB_CURSOR_OFFSETS, BDW_COLORS, @@ -517,8 +518,10 @@ void intel_detect_pch(struct drm_device *dev) } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) || ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && - pch->subsystem_vendor == 0x1af4 && - pch->subsystem_device == 0x1100)) { + pch->subsystem_vendor == + PCI_SUBVENDOR_ID_REDHAT_QUMRANET && + pch->subsystem_device == + PCI_SUBDEVICE_ID_QEMU)) { dev_priv->pch_type = intel_virt_detect_pch(dev); } else continue; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0113207967d9..9fa9698fe247 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -761,7 +761,8 @@ struct intel_csr { func(has_llc) sep \ func(has_snoop) sep \ func(has_ddi) sep \ - func(has_fpga_dbg) + func(has_fpga_dbg) sep \ + func(has_pooled_eu) #define DEFINE_FLAG(name) u8 name:1 #define SEP_SEMICOLON ; @@ -787,6 +788,7 @@ struct intel_device_info { u8 subslice_per_slice; u8 eu_total; u8 eu_per_subslice; + u8 min_eu_in_pool; /* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */ u8 subslice_7eu[3]; u8 has_slice_pg:1; @@ -2717,6 +2719,15 @@ struct drm_i915_cmd_table { #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until)) +#define KBL_REVID_A0 0x0 +#define KBL_REVID_B0 0x1 +#define KBL_REVID_C0 0x2 +#define KBL_REVID_D0 0x3 +#define KBL_REVID_E0 0x4 + +#define IS_KBL_REVID(p, since, until) \ + (IS_KABYLAKE(p) && IS_REVID(p, since, until)) + /* * The genX designation typically refers to the render engine, so render * capability related checks should use IS_GEN, while display and other checks @@ -2823,6 +2834,8 @@ struct drm_i915_cmd_table { !IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) && \ !IS_BROXTON(dev)) +#define HAS_POOLED_EU(dev) (INTEL_INFO(dev)->has_pooled_eu) + #define INTEL_PCH_DEVICE_ID_MASK 0xff00 #define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00 #define INTEL_PCH_CPT_DEVICE_ID_TYPE 0x1c00 @@ -3109,6 +3122,23 @@ static inline int __sg_page_count(struct scatterlist *sg) struct page * i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n); +static inline dma_addr_t +i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, int n) +{ + if (n < obj->get_page.last) { + obj->get_page.sg = obj->pages->sgl; + obj->get_page.last = 0; + } + + while (obj->get_page.last + __sg_page_count(obj->get_page.sg) <= n) { + obj->get_page.last += __sg_page_count(obj->get_page.sg++); + if (unlikely(sg_is_chain(obj->get_page.sg))) + obj->get_page.sg = sg_chain_ptr(obj->get_page.sg); + } + + return sg_dma_address(obj->get_page.sg) + ((n - obj->get_page.last) << PAGE_SHIFT); +} + static inline struct page * i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n) { @@ -3619,6 +3649,7 @@ int intel_bios_init(struct drm_i915_private *dev_priv); bool intel_bios_is_valid_vbt(const void *buf, size_t size); bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv); bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin); +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port); bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv, enum port *port); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 343d88114f3b..21d0dea57312 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -54,12 +54,33 @@ static bool cpu_cache_is_coherent(struct drm_device *dev, static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj) { + if (obj->base.write_domain == I915_GEM_DOMAIN_CPU) + return false; + if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level)) return true; return obj->pin_display; } +static int +insert_mappable_node(struct drm_i915_private *i915, + struct drm_mm_node *node, u32 size) +{ + memset(node, 0, sizeof(*node)); + return drm_mm_insert_node_in_range_generic(&i915->ggtt.base.mm, node, + size, 0, 0, 0, + i915->ggtt.mappable_end, + DRM_MM_SEARCH_DEFAULT, + DRM_MM_CREATE_DEFAULT); +} + +static void +remove_mappable_node(struct drm_mm_node *node) +{ + drm_mm_remove_node(node); +} + /* some bookkeeping */ static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv, size_t size) @@ -409,6 +430,9 @@ i915_gem_dumb_create(struct drm_file *file, /** * Creates a new mm object and returns a handle to it. + * @dev: drm device pointer + * @data: ioctl data blob + * @file: drm file pointer */ int i915_gem_create_ioctl(struct drm_device *dev, void *data, @@ -585,6 +609,142 @@ shmem_pread_slow(struct page *page, int shmem_page_offset, int page_length, return ret ? - EFAULT : 0; } +static inline unsigned long +slow_user_access(struct io_mapping *mapping, + uint64_t page_base, int page_offset, + char __user *user_data, + unsigned long length, bool pwrite) +{ + void __iomem *ioaddr; + void *vaddr; + uint64_t unwritten; + + ioaddr = io_mapping_map_wc(mapping, page_base, PAGE_SIZE); + /* We can use the cpu mem copy function because this is X86. */ + vaddr = (void __force *)ioaddr + page_offset; + if (pwrite) + unwritten = __copy_from_user(vaddr, user_data, length); + else + unwritten = __copy_to_user(user_data, vaddr, length); + + io_mapping_unmap(ioaddr); + return unwritten; +} + +static int +i915_gem_gtt_pread(struct drm_device *dev, + struct drm_i915_gem_object *obj, uint64_t size, + uint64_t data_offset, uint64_t data_ptr) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_ggtt *ggtt = &dev_priv->ggtt; + struct drm_mm_node node; + char __user *user_data; + uint64_t remain; + uint64_t offset; + int ret; + + ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE); + if (ret) { + ret = insert_mappable_node(dev_priv, &node, PAGE_SIZE); + if (ret) + goto out; + + ret = i915_gem_object_get_pages(obj); + if (ret) { + remove_mappable_node(&node); + goto out; + } + + i915_gem_object_pin_pages(obj); + } else { + node.start = i915_gem_obj_ggtt_offset(obj); + node.allocated = false; + ret = i915_gem_object_put_fence(obj); + if (ret) + goto out_unpin; + } + + ret = i915_gem_object_set_to_gtt_domain(obj, false); + if (ret) + goto out_unpin; + + user_data = u64_to_user_ptr(data_ptr); + remain = size; + offset = data_offset; + + mutex_unlock(&dev->struct_mutex); + if (likely(!i915.prefault_disable)) { + ret = fault_in_multipages_writeable(user_data, remain); + if (ret) { + mutex_lock(&dev->struct_mutex); + goto out_unpin; + } + } + + while (remain > 0) { + /* Operation in this page + * + * page_base = page offset within aperture + * page_offset = offset within page + * page_length = bytes to copy for this page + */ + u32 page_base = node.start; + unsigned page_offset = offset_in_page(offset); + unsigned page_length = PAGE_SIZE - page_offset; + page_length = remain < page_length ? remain : page_length; + if (node.allocated) { + wmb(); + ggtt->base.insert_page(&ggtt->base, + i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), + node.start, + I915_CACHE_NONE, 0); + wmb(); + } else { + page_base += offset & PAGE_MASK; + } + /* This is a slow read/write as it tries to read from + * and write to user memory which may result into page + * faults, and so we cannot perform this under struct_mutex. + */ + if (slow_user_access(ggtt->mappable, page_base, + page_offset, user_data, + page_length, false)) { + ret = -EFAULT; + break; + } + + remain -= page_length; + user_data += page_length; + offset += page_length; + } + + mutex_lock(&dev->struct_mutex); + if (ret == 0 && (obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) { + /* The user has modified the object whilst we tried + * reading from it, and we now have no idea what domain + * the pages should be in. As we have just been touching + * them directly, flush everything back to the GTT + * domain. + */ + ret = i915_gem_object_set_to_gtt_domain(obj, false); + } + +out_unpin: + if (node.allocated) { + wmb(); + ggtt->base.clear_range(&ggtt->base, + node.start, node.size, + true); + i915_gem_object_unpin_pages(obj); + remove_mappable_node(&node); + } else { + i915_gem_object_ggtt_unpin(obj); + } +out: + return ret; +} + static int i915_gem_shmem_pread(struct drm_device *dev, struct drm_i915_gem_object *obj, @@ -600,6 +760,9 @@ i915_gem_shmem_pread(struct drm_device *dev, int needs_clflush = 0; struct sg_page_iter sg_iter; + if (!obj->base.filp) + return -ENODEV; + user_data = u64_to_user_ptr(args->data_ptr); remain = args->size; @@ -672,6 +835,9 @@ out: /** * Reads data from the object referenced by handle. + * @dev: drm device pointer + * @data: ioctl data blob + * @file: drm file pointer * * On error, the contents of *data are undefined. */ @@ -708,18 +874,15 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, goto out; } - /* prime objects have no backing filp to GEM pread/pwrite - * pages from. - */ - if (!obj->base.filp) { - ret = -EINVAL; - goto out; - } - trace_i915_gem_object_pread(obj, args->offset, args->size); ret = i915_gem_shmem_pread(dev, obj, args, file); + /* pread for non shmem backed objects */ + if (ret == -EFAULT || ret == -ENODEV) + ret = i915_gem_gtt_pread(dev, obj, args->size, + args->offset, args->data_ptr); + out: drm_gem_object_unreference(&obj->base); unlock: @@ -753,60 +916,99 @@ fast_user_write(struct io_mapping *mapping, /** * This is the fast pwrite path, where we copy the data directly from the * user into the GTT, uncached. + * @dev: drm device pointer + * @obj: i915 gem object + * @args: pwrite arguments structure + * @file: drm file pointer */ static int -i915_gem_gtt_pwrite_fast(struct drm_device *dev, +i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915, struct drm_i915_gem_object *obj, struct drm_i915_gem_pwrite *args, struct drm_file *file) { - struct drm_i915_private *dev_priv = to_i915(dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; - ssize_t remain; - loff_t offset, page_base; + struct i915_ggtt *ggtt = &i915->ggtt; + struct drm_device *dev = obj->base.dev; + struct drm_mm_node node; + uint64_t remain, offset; char __user *user_data; - int page_offset, page_length, ret; + int ret; + bool hit_slow_path = false; + + if (obj->tiling_mode != I915_TILING_NONE) + return -EFAULT; ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK); - if (ret) - goto out; + if (ret) { + ret = insert_mappable_node(i915, &node, PAGE_SIZE); + if (ret) + goto out; + + ret = i915_gem_object_get_pages(obj); + if (ret) { + remove_mappable_node(&node); + goto out; + } + + i915_gem_object_pin_pages(obj); + } else { + node.start = i915_gem_obj_ggtt_offset(obj); + node.allocated = false; + ret = i915_gem_object_put_fence(obj); + if (ret) + goto out_unpin; + } ret = i915_gem_object_set_to_gtt_domain(obj, true); if (ret) goto out_unpin; - ret = i915_gem_object_put_fence(obj); - if (ret) - goto out_unpin; + intel_fb_obj_invalidate(obj, ORIGIN_GTT); + obj->dirty = true; user_data = u64_to_user_ptr(args->data_ptr); + offset = args->offset; remain = args->size; - - offset = i915_gem_obj_ggtt_offset(obj) + args->offset; - - intel_fb_obj_invalidate(obj, ORIGIN_GTT); - - while (remain > 0) { + while (remain) { /* Operation in this page * * page_base = page offset within aperture * page_offset = offset within page * page_length = bytes to copy for this page */ - page_base = offset & PAGE_MASK; - page_offset = offset_in_page(offset); - page_length = remain; - if ((page_offset + remain) > PAGE_SIZE) - page_length = PAGE_SIZE - page_offset; - + u32 page_base = node.start; + unsigned page_offset = offset_in_page(offset); + unsigned page_length = PAGE_SIZE - page_offset; + page_length = remain < page_length ? remain : page_length; + if (node.allocated) { + wmb(); /* flush the write before we modify the GGTT */ + ggtt->base.insert_page(&ggtt->base, + i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT), + node.start, I915_CACHE_NONE, 0); + wmb(); /* flush modifications to the GGTT (insert_page) */ + } else { + page_base += offset & PAGE_MASK; + } /* If we get a fault while copying data, then (presumably) our * source page isn't available. Return the error and we'll * retry in the slow path. + * If the object is non-shmem backed, we retry again with the + * path that handles page fault. */ if (fast_user_write(ggtt->mappable, page_base, page_offset, user_data, page_length)) { - ret = -EFAULT; - goto out_flush; + hit_slow_path = true; + mutex_unlock(&dev->struct_mutex); + if (slow_user_access(ggtt->mappable, + page_base, + page_offset, user_data, + page_length, true)) { + ret = -EFAULT; + mutex_lock(&dev->struct_mutex); + goto out_flush; + } + + mutex_lock(&dev->struct_mutex); } remain -= page_length; @@ -815,9 +1017,31 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, } out_flush: + if (hit_slow_path) { + if (ret == 0 && + (obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) { + /* The user has modified the object whilst we tried + * reading from it, and we now have no idea what domain + * the pages should be in. As we have just been touching + * them directly, flush everything back to the GTT + * domain. + */ + ret = i915_gem_object_set_to_gtt_domain(obj, false); + } + } + intel_fb_obj_flush(obj, false, ORIGIN_GTT); out_unpin: - i915_gem_object_ggtt_unpin(obj); + if (node.allocated) { + wmb(); + ggtt->base.clear_range(&ggtt->base, + node.start, node.size, + true); + i915_gem_object_unpin_pages(obj); + remove_mappable_node(&node); + } else { + i915_gem_object_ggtt_unpin(obj); + } out: return ret; } @@ -1016,6 +1240,9 @@ out: /** * Writes data to the object referenced by handle. + * @dev: drm device + * @data: ioctl data blob + * @file: drm file * * On error, the contents of the buffer that were to be modified are undefined. */ @@ -1062,14 +1289,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, goto out; } - /* prime objects have no backing filp to GEM pread/pwrite - * pages from. - */ - if (!obj->base.filp) { - ret = -EINVAL; - goto out; - } - trace_i915_gem_object_pwrite(obj, args->offset, args->size); ret = -EFAULT; @@ -1079,20 +1298,20 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, * pread/pwrite currently are reading and writing from the CPU * perspective, requiring manual detiling by the client. */ - if (obj->tiling_mode == I915_TILING_NONE && - obj->base.write_domain != I915_GEM_DOMAIN_CPU && - cpu_write_needs_clflush(obj)) { - ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file); + if (!obj->base.filp || cpu_write_needs_clflush(obj)) { + ret = i915_gem_gtt_pwrite_fast(dev_priv, obj, args, file); /* Note that the gtt paths might fail with non-page-backed user * pointers (e.g. gtt mappings when moving data between * textures). Fallback to the shmem path in that case. */ } - if (ret == -EFAULT || ret == -ENOSPC) { + if (ret == -EFAULT) { if (obj->phys_handle) ret = i915_gem_phys_pwrite(obj, args, file); - else + else if (obj->base.filp) ret = i915_gem_shmem_pwrite(dev, obj, args, file); + else + ret = -ENODEV; } out: @@ -1213,6 +1432,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state) * @req: duh! * @interruptible: do an interruptible wait (normally yes) * @timeout: in - how long to wait (NULL forever); out - how much time remaining + * @rps: RPS client * * Note: It is of utmost importance that the passed in seqno and reset_counter * values have been read by the caller in an smp safe manner. Where read-side @@ -1446,6 +1666,7 @@ __i915_gem_request_retire__upto(struct drm_i915_gem_request *req) /** * Waits for a request to be signaled, and cleans up the * request and object lists appropriately for that event. + * @req: request to wait on */ int i915_wait_request(struct drm_i915_gem_request *req) @@ -1472,6 +1693,8 @@ i915_wait_request(struct drm_i915_gem_request *req) /** * Ensures that all rendering to the object has completed and the object is * safe to unbind from the GTT or access from the CPU. + * @obj: i915 gem object + * @readonly: waiting for read access or write */ int i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj, @@ -1589,6 +1812,9 @@ static struct intel_rps_client *to_rps_client(struct drm_file *file) /** * Called when user space prepares to use an object with the CPU, either * through the mmap ioctl's mapping or a GTT mapping. + * @dev: drm device + * @data: ioctl data blob + * @file: drm file */ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, @@ -1652,6 +1878,9 @@ unlock: /** * Called when user space has done writes to this buffer + * @dev: drm device + * @data: ioctl data blob + * @file: drm file */ int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, @@ -1682,8 +1911,11 @@ unlock: } /** - * Maps the contents of an object, returning the address it is mapped - * into. + * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address + * it is mapped to. + * @dev: drm device + * @data: ioctl data blob + * @file: drm file * * While the mapping holds a reference on the contents of the object, it doesn't * imply a ref on the object itself. @@ -2001,7 +2233,10 @@ i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode) /** * i915_gem_get_gtt_alignment - return required GTT alignment for an object - * @obj: object to check + * @dev: drm device + * @size: object size + * @tiling_mode: tiling mode + * @fenced: is fenced alignemned required or not * * Return the required GTT alignment for an object, taking into account * potential fence register mapping. @@ -2951,6 +3186,7 @@ void i915_gem_reset(struct drm_device *dev) /** * This function clears the request list as sequence numbers are passed. + * @engine: engine to retire requests on */ void i915_gem_retire_requests_ring(struct intel_engine_cs *engine) @@ -3074,6 +3310,7 @@ i915_gem_idle_work_handler(struct work_struct *work) * Ensures that an object will eventually get non-busy by flushing any required * write domains, emitting any outstanding lazy request and retiring and * completed requests. + * @obj: object to flush */ static int i915_gem_object_flush_active(struct drm_i915_gem_object *obj) @@ -3099,7 +3336,9 @@ i915_gem_object_flush_active(struct drm_i915_gem_object *obj) /** * i915_gem_wait_ioctl - implements DRM_IOCTL_I915_GEM_WAIT - * @DRM_IOCTL_ARGS: standard ioctl arguments + * @dev: drm device pointer + * @data: ioctl data blob + * @file: drm file pointer * * Returns 0 if successful, else an error is returned with the remaining time in * the timeout parameter. @@ -3489,6 +3728,11 @@ static bool i915_gem_valid_gtt_space(struct i915_vma *vma, /** * Finds free space in the GTT aperture and binds the object or a view of it * there. + * @obj: object to bind + * @vm: address space to bind into + * @ggtt_view: global gtt view if applicable + * @alignment: requested alignment + * @flags: mask of PIN_* flags to use */ static struct i915_vma * i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj, @@ -3746,6 +3990,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj) /** * Moves a single object to the GTT read, and possibly write domain. + * @obj: object to act on + * @write: ask for write access or read only * * This function returns when the move is complete, including waiting on * flushes to occur. @@ -3817,6 +4063,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) /** * Changes the cache-level of an object across all VMA. + * @obj: object to act on + * @cache_level: new cache level to set for the object * * After this function returns, the object will be in the new cache-level * across all GTT and the contents of the backing storage will be coherent, @@ -3926,9 +4174,7 @@ out: * object is now coherent at its new cache level (with respect * to the access domain). */ - if (obj->cache_dirty && - obj->base.write_domain != I915_GEM_DOMAIN_CPU && - cpu_write_needs_clflush(obj)) { + if (obj->cache_dirty && cpu_write_needs_clflush(obj)) { if (i915_gem_clflush_object(obj, true)) i915_gem_chipset_flush(to_i915(obj->base.dev)); } @@ -4098,6 +4344,8 @@ i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj, /** * Moves a single object to the CPU read, and possibly write domain. + * @obj: object to act on + * @write: requesting write or read-only access * * This function returns when the move is complete, including waiting on * flushes to occur. @@ -4886,11 +5134,9 @@ i915_gem_init_hw(struct drm_device *dev) intel_mocs_init_l3cc_table(dev); /* We can't enable contexts until all firmware is loaded */ - if (HAS_GUC(dev)) { - ret = intel_guc_setup(dev); - if (ret) - goto out; - } + ret = intel_guc_setup(dev); + if (ret) + goto out; /* * Increment the next seqno by 0x100 so we have a visible break diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 46684779d4d6..7a139a6d4487 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2355,6 +2355,28 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte) #endif } +static void gen8_ggtt_insert_page(struct i915_address_space *vm, + dma_addr_t addr, + uint64_t offset, + enum i915_cache_level level, + u32 unused) +{ + struct drm_i915_private *dev_priv = to_i915(vm->dev); + gen8_pte_t __iomem *pte = + (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + + (offset >> PAGE_SHIFT); + int rpm_atomic_seq; + + rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); + + gen8_set_pte(pte, gen8_pte_encode(addr, level, true)); + + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + POSTING_READ(GFX_FLSH_CNTL_GEN6); + + assert_rpm_atomic_end(dev_priv, rpm_atomic_seq); +} + static void gen8_ggtt_insert_entries(struct i915_address_space *vm, struct sg_table *st, uint64_t start, @@ -2424,6 +2446,28 @@ static void gen8_ggtt_insert_entries__BKL(struct i915_address_space *vm, stop_machine(gen8_ggtt_insert_entries__cb, &arg, NULL); } +static void gen6_ggtt_insert_page(struct i915_address_space *vm, + dma_addr_t addr, + uint64_t offset, + enum i915_cache_level level, + u32 flags) +{ + struct drm_i915_private *dev_priv = to_i915(vm->dev); + gen6_pte_t __iomem *pte = + (gen6_pte_t __iomem *)dev_priv->ggtt.gsm + + (offset >> PAGE_SHIFT); + int rpm_atomic_seq; + + rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); + + iowrite32(vm->pte_encode(addr, level, true, flags), pte); + + I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + POSTING_READ(GFX_FLSH_CNTL_GEN6); + + assert_rpm_atomic_end(dev_priv, rpm_atomic_seq); +} + /* * Binds an object into the global gtt with the specified cache level. The object * will be accessible to the GPU via commands whose operands reference offsets @@ -2543,6 +2587,24 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm, assert_rpm_atomic_end(dev_priv, rpm_atomic_seq); } +static void i915_ggtt_insert_page(struct i915_address_space *vm, + dma_addr_t addr, + uint64_t offset, + enum i915_cache_level cache_level, + u32 unused) +{ + struct drm_i915_private *dev_priv = to_i915(vm->dev); + unsigned int flags = (cache_level == I915_CACHE_NONE) ? + AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY; + int rpm_atomic_seq; + + rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv); + + intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags); + + assert_rpm_atomic_end(dev_priv, rpm_atomic_seq); +} + static void i915_ggtt_insert_entries(struct i915_address_space *vm, struct sg_table *pages, uint64_t start, @@ -3076,7 +3138,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->base.bind_vma = ggtt_bind_vma; ggtt->base.unbind_vma = ggtt_unbind_vma; - + ggtt->base.insert_page = gen8_ggtt_insert_page; ggtt->base.clear_range = nop_clear_range; if (!USES_FULL_PPGTT(dev_priv)) ggtt->base.clear_range = gen8_ggtt_clear_range; @@ -3116,6 +3178,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) ret = ggtt_probe_common(dev, ggtt->size); ggtt->base.clear_range = gen6_ggtt_clear_range; + ggtt->base.insert_page = gen6_ggtt_insert_page; ggtt->base.insert_entries = gen6_ggtt_insert_entries; ggtt->base.bind_vma = ggtt_bind_vma; ggtt->base.unbind_vma = ggtt_unbind_vma; @@ -3147,6 +3210,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) &ggtt->mappable_base, &ggtt->mappable_end); ggtt->do_idle_maps = needs_idle_maps(dev_priv->dev); + ggtt->base.insert_page = i915_ggtt_insert_page; ggtt->base.insert_entries = i915_ggtt_insert_entries; ggtt->base.clear_range = i915_ggtt_clear_range; ggtt->base.bind_vma = ggtt_bind_vma; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 62be77cac5cd..163b564fb87d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -319,6 +319,11 @@ struct i915_address_space { uint64_t start, uint64_t length, bool use_scratch); + void (*insert_page)(struct i915_address_space *vm, + dma_addr_t addr, + uint64_t offset, + enum i915_cache_level cache_level, + u32 flags); void (*insert_entries)(struct i915_address_space *vm, struct sg_table *st, uint64_t start, diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c index 7c93327b70fe..b7c1b5fb61ea 100644 --- a/drivers/gpu/drm/i915/i915_gem_render_state.c +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c @@ -94,6 +94,7 @@ free_gem: static int render_state_setup(struct render_state *so) { + struct drm_device *dev = so->obj->base.dev; const struct intel_renderstate_rodata *rodata = so->rodata; unsigned int i = 0, reloc_index = 0; struct page *page; @@ -135,6 +136,33 @@ static int render_state_setup(struct render_state *so) so->aux_batch_offset = i * sizeof(u32); + if (HAS_POOLED_EU(dev)) { + /* + * We always program 3x6 pool config but depending upon which + * subslice is disabled HW drops down to appropriate config + * shown below. + * + * In the below table 2x6 config always refers to + * fused-down version, native 2x6 is not available and can + * be ignored + * + * SNo subslices config eu pool configuration + * ----------------------------------------------------------- + * 1 3 subslices enabled (3x6) - 0x00777000 (9+9) + * 2 ss0 disabled (2x6) - 0x00777000 (3+9) + * 3 ss1 disabled (2x6) - 0x00770000 (6+6) + * 4 ss2 disabled (2x6) - 0x00007000 (9+3) + */ + u32 eu_pool_config = 0x00777000; + + OUT_BATCH(d, i, GEN9_MEDIA_POOL_STATE); + OUT_BATCH(d, i, GEN9_MEDIA_POOL_ENABLE); + OUT_BATCH(d, i, eu_pool_config); + OUT_BATCH(d, i, 0); + OUT_BATCH(d, i, 0); + OUT_BATCH(d, i, 0); + } + OUT_BATCH(d, i, MI_BATCH_BUFFER_END); so->aux_batch_size = (i * sizeof(u32)) - so->aux_batch_offset; diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index f9253f2b7ba0..e9cd82290408 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -55,8 +55,10 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, return -ENODEV; /* See the comment at the drm_mm_init() call for more about this check. - * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */ - if (IS_GEN8(dev_priv) && start < 4096) + * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete) + */ + if (start < 4096 && (IS_GEN8(dev_priv) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0))) start = 4096; mutex_lock(&dev_priv->mm.stolen_lock); diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c index ac72451c571c..22a55ac4e51c 100644 --- a/drivers/gpu/drm/i915/i915_guc_submission.c +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -174,94 +174,88 @@ static int host2guc_sample_forcewake(struct intel_guc *guc, * client object which contains the page being used for the doorbell */ -static void guc_init_doorbell(struct intel_guc *guc, - struct i915_guc_client *client) +static int guc_update_doorbell_id(struct intel_guc *guc, + struct i915_guc_client *client, + u16 new_id) { + struct sg_table *sg = guc->ctx_pool_obj->pages; + void *doorbell_bitmap = guc->doorbell_bitmap; struct guc_doorbell_info *doorbell; + struct guc_context_desc desc; + size_t len; doorbell = client->client_base + client->doorbell_offset; - doorbell->db_status = GUC_DOORBELL_ENABLED; - doorbell->cookie = 0; -} - -static int guc_ring_doorbell(struct i915_guc_client *gc) -{ - struct guc_process_desc *desc; - union guc_doorbell_qw db_cmp, db_exc, db_ret; - union guc_doorbell_qw *db; - int attempt = 2, ret = -EAGAIN; - - desc = gc->client_base + gc->proc_desc_offset; - - /* Update the tail so it is visible to GuC */ - desc->tail = gc->wq_tail; - - /* current cookie */ - db_cmp.db_status = GUC_DOORBELL_ENABLED; - db_cmp.cookie = gc->cookie; - - /* cookie to be updated */ - db_exc.db_status = GUC_DOORBELL_ENABLED; - db_exc.cookie = gc->cookie + 1; - if (db_exc.cookie == 0) - db_exc.cookie = 1; - - /* pointer of current doorbell cacheline */ - db = gc->client_base + gc->doorbell_offset; - - while (attempt--) { - /* lets ring the doorbell */ - db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db, - db_cmp.value_qw, db_exc.value_qw); - - /* if the exchange was successfully executed */ - if (db_ret.value_qw == db_cmp.value_qw) { - /* db was successfully rung */ - gc->cookie = db_exc.cookie; - ret = 0; - break; - } + if (client->doorbell_id != GUC_INVALID_DOORBELL_ID && + test_bit(client->doorbell_id, doorbell_bitmap)) { + /* Deactivate the old doorbell */ + doorbell->db_status = GUC_DOORBELL_DISABLED; + (void)host2guc_release_doorbell(guc, client); + __clear_bit(client->doorbell_id, doorbell_bitmap); + } - /* XXX: doorbell was lost and need to acquire it again */ - if (db_ret.db_status == GUC_DOORBELL_DISABLED) - break; + /* Update the GuC's idea of the doorbell ID */ + len = sg_pcopy_to_buffer(sg->sgl, sg->nents, &desc, sizeof(desc), + sizeof(desc) * client->ctx_index); + if (len != sizeof(desc)) + return -EFAULT; + desc.db_id = new_id; + len = sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc), + sizeof(desc) * client->ctx_index); + if (len != sizeof(desc)) + return -EFAULT; - DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n", - db_cmp.cookie, db_ret.cookie); + client->doorbell_id = new_id; + if (new_id == GUC_INVALID_DOORBELL_ID) + return 0; - /* update the cookie to newly read cookie from GuC */ - db_cmp.cookie = db_ret.cookie; - db_exc.cookie = db_ret.cookie + 1; - if (db_exc.cookie == 0) - db_exc.cookie = 1; - } + /* Activate the new doorbell */ + __set_bit(new_id, doorbell_bitmap); + doorbell->cookie = 0; + doorbell->db_status = GUC_DOORBELL_ENABLED; + return host2guc_allocate_doorbell(guc, client); +} - return ret; +static int guc_init_doorbell(struct intel_guc *guc, + struct i915_guc_client *client, + uint16_t db_id) +{ + return guc_update_doorbell_id(guc, client, db_id); } static void guc_disable_doorbell(struct intel_guc *guc, struct i915_guc_client *client) { - struct drm_i915_private *dev_priv = guc_to_i915(guc); - struct guc_doorbell_info *doorbell; - i915_reg_t drbreg = GEN8_DRBREGL(client->doorbell_id); - int value; + (void)guc_update_doorbell_id(guc, client, GUC_INVALID_DOORBELL_ID); - doorbell = client->client_base + client->doorbell_offset; - - doorbell->db_status = GUC_DOORBELL_DISABLED; + /* XXX: wait for any interrupts */ + /* XXX: wait for workqueue to drain */ +} - I915_WRITE(drbreg, I915_READ(drbreg) & ~GEN8_DRB_VALID); +static uint16_t +select_doorbell_register(struct intel_guc *guc, uint32_t priority) +{ + /* + * The bitmap tracks which doorbell registers are currently in use. + * It is split into two halves; the first half is used for normal + * priority contexts, the second half for high-priority ones. + * Note that logically higher priorities are numerically less than + * normal ones, so the test below means "is it high-priority?" + */ + const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH); + const uint16_t half = GUC_MAX_DOORBELLS / 2; + const uint16_t start = hi_pri ? half : 0; + const uint16_t end = start + half; + uint16_t id; - value = I915_READ(drbreg); - WARN_ON((value & GEN8_DRB_VALID) != 0); + id = find_next_zero_bit(guc->doorbell_bitmap, end, start); + if (id == end) + id = GUC_INVALID_DOORBELL_ID; - I915_WRITE(GEN8_DRBREGU(client->doorbell_id), 0); - I915_WRITE(drbreg, 0); + DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n", + hi_pri ? "high" : "normal", id); - /* XXX: wait for any interrupts */ - /* XXX: wait for workqueue to drain */ + return id; } /* @@ -288,37 +282,6 @@ static uint32_t select_doorbell_cacheline(struct intel_guc *guc) return offset; } -static uint16_t assign_doorbell(struct intel_guc *guc, uint32_t priority) -{ - /* - * The bitmap is split into two halves; the first half is used for - * normal priority contexts, the second half for high-priority ones. - * Note that logically higher priorities are numerically less than - * normal ones, so the test below means "is it high-priority?" - */ - const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH); - const uint16_t half = GUC_MAX_DOORBELLS / 2; - const uint16_t start = hi_pri ? half : 0; - const uint16_t end = start + half; - uint16_t id; - - id = find_next_zero_bit(guc->doorbell_bitmap, end, start); - if (id == end) - id = GUC_INVALID_DOORBELL_ID; - else - bitmap_set(guc->doorbell_bitmap, id, 1); - - DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n", - hi_pri ? "high" : "normal", id); - - return id; -} - -static void release_doorbell(struct intel_guc *guc, uint16_t id) -{ - bitmap_clear(guc->doorbell_bitmap, id, 1); -} - /* * Initialise the process descriptor shared with the GuC firmware. */ @@ -543,6 +506,61 @@ static void guc_add_workqueue_item(struct i915_guc_client *gc, kunmap_atomic(base); } +static int guc_ring_doorbell(struct i915_guc_client *gc) +{ + struct guc_process_desc *desc; + union guc_doorbell_qw db_cmp, db_exc, db_ret; + union guc_doorbell_qw *db; + int attempt = 2, ret = -EAGAIN; + + desc = gc->client_base + gc->proc_desc_offset; + + /* Update the tail so it is visible to GuC */ + desc->tail = gc->wq_tail; + + /* current cookie */ + db_cmp.db_status = GUC_DOORBELL_ENABLED; + db_cmp.cookie = gc->cookie; + + /* cookie to be updated */ + db_exc.db_status = GUC_DOORBELL_ENABLED; + db_exc.cookie = gc->cookie + 1; + if (db_exc.cookie == 0) + db_exc.cookie = 1; + + /* pointer of current doorbell cacheline */ + db = gc->client_base + gc->doorbell_offset; + + while (attempt--) { + /* lets ring the doorbell */ + db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db, + db_cmp.value_qw, db_exc.value_qw); + + /* if the exchange was successfully executed */ + if (db_ret.value_qw == db_cmp.value_qw) { + /* db was successfully rung */ + gc->cookie = db_exc.cookie; + ret = 0; + break; + } + + /* XXX: doorbell was lost and need to acquire it again */ + if (db_ret.db_status == GUC_DOORBELL_DISABLED) + break; + + DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n", + db_cmp.cookie, db_ret.cookie); + + /* update the cookie to newly read cookie from GuC */ + db_cmp.cookie = db_ret.cookie; + db_exc.cookie = db_ret.cookie + 1; + if (db_exc.cookie == 0) + db_exc.cookie = 1; + } + + return ret; +} + /** * i915_guc_submit() - Submit commands through GuC * @rq: request associated with the commands @@ -591,7 +609,7 @@ int i915_guc_submit(struct drm_i915_gem_request *rq) /** * gem_allocate_guc_obj() - Allocate gem object for GuC usage - * @dev: drm device + * @dev_priv: driver private data structure * @size: size of object * * This is a wrapper to create a gem obj. In order to use it inside GuC, the @@ -600,13 +618,12 @@ int i915_guc_submit(struct drm_i915_gem_request *rq) * * Return: A drm_i915_gem_object if successful, otherwise NULL. */ -static struct drm_i915_gem_object *gem_allocate_guc_obj(struct drm_device *dev, - u32 size) +static struct drm_i915_gem_object * +gem_allocate_guc_obj(struct drm_i915_private *dev_priv, u32 size) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; - obj = i915_gem_object_create(dev, size); + obj = i915_gem_object_create(dev_priv->dev, size); if (IS_ERR(obj)) return NULL; @@ -642,10 +659,10 @@ static void gem_release_guc_obj(struct drm_i915_gem_object *obj) drm_gem_object_unreference(&obj->base); } -static void guc_client_free(struct drm_device *dev, - struct i915_guc_client *client) +static void +guc_client_free(struct drm_i915_private *dev_priv, + struct i915_guc_client *client) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; if (!client) @@ -658,17 +675,10 @@ static void guc_client_free(struct drm_device *dev, if (client->client_base) { /* - * If we got as far as setting up a doorbell, make sure - * we shut it down before unmapping & deallocating the - * memory. So first disable the doorbell, then tell the - * GuC that we've finished with it, finally deallocate - * it in our bitmap + * If we got as far as setting up a doorbell, make sure we + * shut it down before unmapping & deallocating the memory. */ - if (client->doorbell_id != GUC_INVALID_DOORBELL_ID) { - guc_disable_doorbell(guc, client); - host2guc_release_doorbell(guc, client); - release_doorbell(guc, client->doorbell_id); - } + guc_disable_doorbell(guc, client); kunmap(kmap_to_page(client->client_base)); } @@ -683,9 +693,51 @@ static void guc_client_free(struct drm_device *dev, kfree(client); } +/* + * Borrow the first client to set up & tear down every doorbell + * in turn, to ensure that all doorbell h/w is (re)initialised. + */ +static void guc_init_doorbell_hw(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct i915_guc_client *client = guc->execbuf_client; + uint16_t db_id, i; + int err; + + db_id = client->doorbell_id; + + for (i = 0; i < GUC_MAX_DOORBELLS; ++i) { + i915_reg_t drbreg = GEN8_DRBREGL(i); + u32 value = I915_READ(drbreg); + + err = guc_update_doorbell_id(guc, client, i); + + /* Report update failure or unexpectedly active doorbell */ + if (err || (i != db_id && (value & GUC_DOORBELL_ENABLED))) + DRM_DEBUG_DRIVER("Doorbell %d (reg 0x%x) was 0x%x, err %d\n", + i, drbreg.reg, value, err); + } + + /* Restore to original value */ + err = guc_update_doorbell_id(guc, client, db_id); + if (err) + DRM_ERROR("Failed to restore doorbell to %d, err %d\n", + db_id, err); + + for (i = 0; i < GUC_MAX_DOORBELLS; ++i) { + i915_reg_t drbreg = GEN8_DRBREGL(i); + u32 value = I915_READ(drbreg); + + if (i != db_id && (value & GUC_DOORBELL_ENABLED)) + DRM_DEBUG_DRIVER("Doorbell %d (reg 0x%x) finally 0x%x\n", + i, drbreg.reg, value); + + } +} + /** * guc_client_alloc() - Allocate an i915_guc_client - * @dev: drm device + * @dev_priv: driver private data structure * @priority: four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW * The kernel client to replace ExecList submission is created with * NORMAL priority. Priority of a client for scheduler can be HIGH, @@ -695,14 +747,15 @@ static void guc_client_free(struct drm_device *dev, * * Return: An i915_guc_client object if success, else NULL. */ -static struct i915_guc_client *guc_client_alloc(struct drm_device *dev, - uint32_t priority, - struct i915_gem_context *ctx) +static struct i915_guc_client * +guc_client_alloc(struct drm_i915_private *dev_priv, + uint32_t priority, + struct i915_gem_context *ctx) { struct i915_guc_client *client; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; struct drm_i915_gem_object *obj; + uint16_t db_id; client = kzalloc(sizeof(*client), GFP_KERNEL); if (!client) @@ -721,7 +774,7 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev, } /* The first page is doorbell/proc_desc. Two followed pages are wq. */ - obj = gem_allocate_guc_obj(dev, GUC_DB_SIZE + GUC_WQ_SIZE); + obj = gem_allocate_guc_obj(dev_priv, GUC_DB_SIZE + GUC_WQ_SIZE); if (!obj) goto err; @@ -731,6 +784,11 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev, client->wq_offset = GUC_DB_SIZE; client->wq_size = GUC_WQ_SIZE; + db_id = select_doorbell_register(guc, client->priority); + if (db_id == GUC_INVALID_DOORBELL_ID) + /* XXX: evict a doorbell instead? */ + goto err; + client->doorbell_offset = select_doorbell_cacheline(guc); /* @@ -743,29 +801,22 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev, else client->proc_desc_offset = (GUC_DB_SIZE / 2); - client->doorbell_id = assign_doorbell(guc, client->priority); - if (client->doorbell_id == GUC_INVALID_DOORBELL_ID) - /* XXX: evict a doorbell instead */ - goto err; - guc_init_proc_desc(guc, client); guc_init_ctx_desc(guc, client); - guc_init_doorbell(guc, client); - - /* XXX: Any cache flushes needed? General domain mgmt calls? */ - - if (host2guc_allocate_doorbell(guc, client)) + if (guc_init_doorbell(guc, client, db_id)) goto err; - DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u db_id %u\n", - priority, client, client->ctx_index, client->doorbell_id); + DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u\n", + priority, client, client->ctx_index); + DRM_DEBUG_DRIVER("doorbell id %u, cacheline offset 0x%x\n", + client->doorbell_id, client->doorbell_offset); return client; err: DRM_ERROR("FAILED to create priority %u GuC client!\n", priority); - guc_client_free(dev, client); + guc_client_free(dev_priv, client); return NULL; } @@ -790,7 +841,7 @@ static void guc_create_log(struct intel_guc *guc) obj = guc->log_obj; if (!obj) { - obj = gem_allocate_guc_obj(dev_priv->dev, size); + obj = gem_allocate_guc_obj(dev_priv, size); if (!obj) { /* logging will be off */ i915.guc_log_level = -1; @@ -850,7 +901,7 @@ static void guc_create_ads(struct intel_guc *guc) obj = guc->ads_obj; if (!obj) { - obj = gem_allocate_guc_obj(dev_priv->dev, PAGE_ALIGN(size)); + obj = gem_allocate_guc_obj(dev_priv, PAGE_ALIGN(size)); if (!obj) return; @@ -904,41 +955,41 @@ static void guc_create_ads(struct intel_guc *guc) * Set up the memory resources to be shared with the GuC. At this point, * we require just one object that can be mapped through the GGTT. */ -int i915_guc_submission_init(struct drm_device *dev) +int i915_guc_submission_init(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; const size_t ctxsize = sizeof(struct guc_context_desc); const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize; const size_t gemsize = round_up(poolsize, PAGE_SIZE); struct intel_guc *guc = &dev_priv->guc; + /* Wipe bitmap & delete client in case of reinitialisation */ + bitmap_clear(guc->doorbell_bitmap, 0, GUC_MAX_DOORBELLS); + i915_guc_submission_disable(dev_priv); + if (!i915.enable_guc_submission) return 0; /* not enabled */ if (guc->ctx_pool_obj) return 0; /* already allocated */ - guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv->dev, gemsize); + guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv, gemsize); if (!guc->ctx_pool_obj) return -ENOMEM; ida_init(&guc->ctx_ids); - guc_create_log(guc); - guc_create_ads(guc); return 0; } -int i915_guc_submission_enable(struct drm_device *dev) +int i915_guc_submission_enable(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; struct i915_guc_client *client; /* client for execbuf submission */ - client = guc_client_alloc(dev, + client = guc_client_alloc(dev_priv, GUC_CTX_PRIORITY_KMD_NORMAL, dev_priv->kernel_context); if (!client) { @@ -947,24 +998,22 @@ int i915_guc_submission_enable(struct drm_device *dev) } guc->execbuf_client = client; - host2guc_sample_forcewake(guc, client); + guc_init_doorbell_hw(guc); return 0; } -void i915_guc_submission_disable(struct drm_device *dev) +void i915_guc_submission_disable(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; - guc_client_free(dev, guc->execbuf_client); + guc_client_free(dev_priv, guc->execbuf_client); guc->execbuf_client = NULL; } -void i915_guc_submission_fini(struct drm_device *dev) +void i915_guc_submission_fini(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; gem_release_guc_obj(dev_priv->guc.ads_obj); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 5c7378374ae6..4378a659d962 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -588,7 +588,7 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe, /** * i915_enable_asle_pipestat - enable ASLE pipestat for OpRegion - * @dev: drm device + * @dev_priv: i915 device private */ static void i915_enable_asle_pipestat(struct drm_i915_private *dev_priv) { @@ -2517,7 +2517,7 @@ static void i915_error_wake_up(struct drm_i915_private *dev_priv, /** * i915_reset_and_wakeup - do process context error handling work - * @dev: drm device + * @dev_priv: i915 device private * * Fire an error uevent so userspace can see that a hang or error * was detected. @@ -2674,13 +2674,14 @@ static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv) /** * i915_handle_error - handle a gpu error - * @dev: drm device + * @dev_priv: i915 device private * @engine_mask: mask representing engines that are hung * Do some basic checking of register state at error time and * dump it to the syslog. Also call i915_capture_error_state() to make * sure we get a record and make it available in debugfs. Fire a uevent * so userspace knows something bad happened (should trigger collection * of a ring dump etc.). + * @fmt: Error message format string */ void i915_handle_error(struct drm_i915_private *dev_priv, u32 engine_mask, diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 5e18cf9f754d..573e78723fc5 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -54,8 +54,8 @@ struct i915_params i915 __read_mostly = { .verbose_state_checks = 1, .nuclear_pageflip = 0, .edp_vswing = 0, - .enable_guc_loading = 0, - .enable_guc_submission = 0, + .enable_guc_loading = -1, + .enable_guc_submission = -1, .guc_log_level = -1, .enable_dp_mst = true, .inject_load_failure = 0, @@ -202,12 +202,12 @@ MODULE_PARM_DESC(edp_vswing, module_param_named_unsafe(enable_guc_loading, i915.enable_guc_loading, int, 0400); MODULE_PARM_DESC(enable_guc_loading, "Enable GuC firmware loading " - "(-1=auto, 0=never [default], 1=if available, 2=required)"); + "(-1=auto [default], 0=never, 1=if available, 2=required)"); module_param_named_unsafe(enable_guc_submission, i915.enable_guc_submission, int, 0400); MODULE_PARM_DESC(enable_guc_submission, "Enable GuC submission " - "(-1=auto, 0=never [default], 1=if available, 2=required)"); + "(-1=auto [default], 0=never, 1=if available, 2=required)"); module_param_named(guc_log_level, i915.guc_log_level, int, 0400); MODULE_PARM_DESC(guc_log_level, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index dfb4c7a88de3..d229a83ad70a 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -220,6 +220,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2<<3) #define ECOCHK_PPGTT_WB_HSW (0x3<<3) +#define GEN8_CONFIG0 _MMIO(0xD00) +#define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) @@ -442,6 +445,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) */ #define GFX_INSTR(opcode, flags) ((0x3 << 29) | ((opcode) << 24) | (flags)) +#define GEN9_MEDIA_POOL_STATE ((0x3 << 29) | (0x2 << 27) | (0x5 << 16) | 4) +#define GEN9_MEDIA_POOL_ENABLE (1 << 31) #define GFX_OP_RASTER_RULES ((0x3<<29)|(0x7<<24)) #define GFX_OP_SCISSOR ((0x3<<29)|(0x1c<<24)|(0x10<<19)) #define SC_UPDATE_SCISSOR (0x1<<1) @@ -713,6 +718,9 @@ enum skl_disp_power_wells { /* Not actual bit groups. Used as IDs for lookup_power_well() */ SKL_DISP_PW_ALWAYS_ON, SKL_DISP_PW_DC_OFF, + + BXT_DPIO_CMN_A, + BXT_DPIO_CMN_BC, }; #define SKL_POWER_WELL_STATE(pw) (1 << ((pw) * 2)) @@ -1273,6 +1281,15 @@ enum skl_disp_power_wells { #define BXT_P_CR_GT_DISP_PWRON _MMIO(0x138090) #define GT_DISPLAY_POWER_ON(phy) (1 << (phy)) +#define _BXT_PHY_CTL_DDI_A 0x64C00 +#define _BXT_PHY_CTL_DDI_B 0x64C10 +#define _BXT_PHY_CTL_DDI_C 0x64C20 +#define BXT_PHY_CMNLANE_POWERDOWN_ACK (1 << 10) +#define BXT_PHY_LANE_POWERDOWN_ACK (1 << 9) +#define BXT_PHY_LANE_ENABLED (1 << 8) +#define BXT_PHY_CTL(port) _MMIO_PORT(port, _BXT_PHY_CTL_DDI_A, \ + _BXT_PHY_CTL_DDI_B) + #define _PHY_CTL_FAMILY_EDP 0x64C80 #define _PHY_CTL_FAMILY_DDI 0x64C90 #define COMMON_RESET_DIS (1 << 31) @@ -1669,6 +1686,9 @@ enum skl_disp_power_wells { #define GEN7_TLB_RD_ADDR _MMIO(0x4700) +#define GAMT_CHKN_BIT_REG _MMIO(0x4ab8) +#define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1<<28) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -1804,6 +1824,10 @@ enum skl_disp_power_wells { #define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2)) #define GEN9_IZ_HASHING(slice, val) ((val) << ((slice) * 2)) +/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */ +#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4) +#define GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2) + /* WaClearTdlStateAckDirtyBits */ #define GEN8_STATE_ACK _MMIO(0x20F0) #define GEN9_STATE_ACK_SLICE1 _MMIO(0x20F8) @@ -2161,6 +2185,9 @@ enum skl_disp_power_wells { #define FBC_LL_SIZE (1536) +#define FBC_LLC_READ_CTRL _MMIO(0x9044) +#define FBC_LLC_FULLY_OPEN (1<<30) + /* Framebuffer compression for GM45+ */ #define DPFC_CB_BASE _MMIO(0x3200) #define DPFC_CONTROL _MMIO(0x3208) @@ -2200,6 +2227,8 @@ enum skl_disp_power_wells { #define ILK_DPFC_STATUS _MMIO(0x43210) #define ILK_DPFC_FENCE_YOFF _MMIO(0x43218) #define ILK_DPFC_CHICKEN _MMIO(0x43224) +#define ILK_DPFC_DISABLE_DUMMY0 (1<<8) +#define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1<<23) #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID (1<<0) #define SNB_FBC_FRONT_BUFFER (1<<1) @@ -6035,6 +6064,9 @@ enum skl_disp_power_wells { #define FORCE_ARB_IDLE_PLANES (1 << 14) #define SKL_EDP_PSR_FIX_RDWRAP (1 << 3) +#define CHICKEN_PAR2_1 _MMIO(0x42090) +#define KVM_CONFIG_CHANGE_NOTIFICATION_SELECT (1 << 14) + #define _CHICKEN_PIPESL_1_A 0x420b0 #define _CHICKEN_PIPESL_1_B 0x420b4 #define HSW_FBCQ_DIS (1 << 22) @@ -6042,6 +6074,7 @@ enum skl_disp_power_wells { #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) #define DISP_ARB_CTL _MMIO(0x45000) +#define DISP_FBC_MEMORY_WAKE (1<<31) #define DISP_TILE_SURFACE_SWIZZLING (1<<13) #define DISP_FBC_WM_DIS (1<<15) #define DISP_ARB_CTL2 _MMIO(0x45004) @@ -6055,6 +6088,9 @@ enum skl_disp_power_wells { #define HSW_NDE_RSTWRN_OPT _MMIO(0x46408) #define RESET_PCH_HANDSHAKE_ENABLE (1<<4) +#define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) +#define MASK_WAKEMEM (1<<13) + #define SKL_DFSM _MMIO(0x51000) #define SKL_DFSM_CDCLK_LIMIT_MASK (3 << 23) #define SKL_DFSM_CDCLK_LIMIT_675 (0 << 23) @@ -6070,8 +6106,10 @@ enum skl_disp_power_wells { #define FF_SLICE_CS_CHICKEN2 _MMIO(0x20e4) #define GEN9_TSG_BARRIER_ACK_DISABLE (1<<8) +#define GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE (1<<10) #define GEN9_CS_DEBUG_MODE1 _MMIO(0x20ec) +#define GEN9_CTX_PREEMPT_REG _MMIO(0x2248) #define GEN8_CS_CHICKEN1 _MMIO(0x2580) /* GEN7 chicken */ @@ -6079,6 +6117,7 @@ enum skl_disp_power_wells { # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1<<10) | (1<<26)) # define GEN9_RHWO_OPTIMIZATION_DISABLE (1<<14) #define COMMON_SLICE_CHICKEN2 _MMIO(0x7014) +# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8) # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE (1<<0) #define HIZ_CHICKEN _MMIO(0x7018) @@ -6931,6 +6970,7 @@ enum skl_disp_power_wells { #define EDRAM_SETS_IDX(cap) (((cap) >> 8) & 0x3) #define GEN6_UCGCTL1 _MMIO(0x9400) +# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE (1 << 22) # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -6947,6 +6987,7 @@ enum skl_disp_power_wells { #define GEN7_UCGCTL4 _MMIO(0x940c) #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE (1<<14) #define GEN6_RCGCTL1 _MMIO(0x9410) #define GEN6_RCGCTL2 _MMIO(0x9414) @@ -8151,6 +8192,8 @@ enum skl_disp_power_wells { #define _MIPIA_EOT_DISABLE (dev_priv->mipi_mmio_base + 0xb05c) #define _MIPIC_EOT_DISABLE (dev_priv->mipi_mmio_base + 0xb85c) #define MIPI_EOT_DISABLE(port) _MMIO_MIPI(port, _MIPIA_EOT_DISABLE, _MIPIC_EOT_DISABLE) +#define BXT_DEFEATURE_DPI_FIFO_CTR (1 << 9) +#define BXT_DPHY_DEFEATURE_EN (1 << 8) #define LP_RX_TIMEOUT_ERROR_RECOVERY_DISABLE (1 << 7) #define HS_RX_TIMEOUT_ERROR_RECOVERY_DISABLE (1 << 6) #define LOW_CONTENTION_RECOVERY_DISABLE (1 << 5) diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c index 004326291854..c3c6c64e5f5e 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.c +++ b/drivers/gpu/drm/i915/i915_vgpu.c @@ -53,7 +53,7 @@ /** * i915_check_vgpu - detect virtual GPU - * @dev: drm device * + * @dev_priv: i915 device private * * This function is called at the initialization stage, to detect whether * running on a vGPU. @@ -135,7 +135,7 @@ static int vgt_balloon_space(struct drm_mm *mm, /** * intel_vgt_balloon - balloon out reserved graphics address trunks - * @dev_priv: i915 device + * @dev: drm device * * This function is called at the initialization stage, to balloon out the * graphic address space allocated to other vGPUs, by marking these spaces as diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 713a02db378a..da5ed4a850b9 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1570,6 +1570,45 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin) } /** + * intel_bios_is_port_present - is the specified digital port present + * @dev_priv: i915 device instance + * @port: port to check + * + * Return true if the device in %port is present. + */ +bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port) +{ + static const struct { + u16 dp, hdmi; + } port_mapping[] = { + [PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, }, + [PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, }, + [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, + [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, + }; + int i; + + /* FIXME maybe deal with port A as well? */ + if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping)) + return false; + + if (!dev_priv->vbt.child_dev_num) + return false; + + for (i = 0; i < dev_priv->vbt.child_dev_num; i++) { + const union child_device_config *p_child = + &dev_priv->vbt.child_dev[i]; + if ((p_child->common.dvo_port == port_mapping[port].dp || + p_child->common.dvo_port == port_mapping[port].hdmi) && + (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING | + DEVICE_TYPE_DISPLAYPORT_OUTPUT))) + return true; + } + + return false; +} + +/** * intel_bios_is_port_edp - is the device in given port eDP * @dev_priv: i915 device instance * @port: port to check diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 022b41d422dc..ad3b0ee5e55b 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1342,6 +1342,14 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port)); out: + if (ret && IS_BROXTON(dev_priv)) { + tmp = I915_READ(BXT_PHY_CTL(port)); + if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK | + BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) + DRM_ERROR("Port %c enabled but PHY powered down? " + "(PHY_CTL %08x)\n", port_name(port), tmp); + } + intel_display_power_put(dev_priv, power_domain); return ret; @@ -1742,9 +1750,11 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder) } } -static bool broxton_phy_is_enabled(struct drm_i915_private *dev_priv, - enum dpio_phy phy) +bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, + enum dpio_phy phy) { + enum port port; + if (!(I915_READ(BXT_P_CR_GT_DISP_PWRON) & GT_DISPLAY_POWER_ON(phy))) return false; @@ -1770,38 +1780,48 @@ static bool broxton_phy_is_enabled(struct drm_i915_private *dev_priv, return false; } + for_each_port_masked(port, + phy == DPIO_PHY0 ? BIT(PORT_B) | BIT(PORT_C) : + BIT(PORT_A)) { + u32 tmp = I915_READ(BXT_PHY_CTL(port)); + + if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) { + DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane " + "for port %c powered down " + "(PHY_CTL %08x)\n", + phy, port_name(port), tmp); + + return false; + } + } + return true; } -static u32 broxton_get_grc(struct drm_i915_private *dev_priv, enum dpio_phy phy) +static u32 bxt_get_grc(struct drm_i915_private *dev_priv, enum dpio_phy phy) { u32 val = I915_READ(BXT_PORT_REF_DW6(phy)); return (val & GRC_CODE_MASK) >> GRC_CODE_SHIFT; } -static void broxton_phy_wait_grc_done(struct drm_i915_private *dev_priv, - enum dpio_phy phy) +static void bxt_phy_wait_grc_done(struct drm_i915_private *dev_priv, + enum dpio_phy phy) { if (wait_for(I915_READ(BXT_PORT_REF_DW3(phy)) & GRC_DONE, 10)) DRM_ERROR("timeout waiting for PHY%d GRC\n", phy); } -static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv, - enum dpio_phy phy); - -static void broxton_phy_init(struct drm_i915_private *dev_priv, - enum dpio_phy phy) +void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy) { - enum port port; - u32 ports, val; + u32 val; - if (broxton_phy_is_enabled(dev_priv, phy)) { + if (bxt_ddi_phy_is_enabled(dev_priv, phy)) { /* Still read out the GRC value for state verification */ if (phy == DPIO_PHY0) - dev_priv->bxt_phy_grc = broxton_get_grc(dev_priv, phy); + dev_priv->bxt_phy_grc = bxt_get_grc(dev_priv, phy); - if (broxton_phy_verify_state(dev_priv, phy)) { + if (bxt_ddi_phy_verify_state(dev_priv, phy)) { DRM_DEBUG_DRIVER("DDI PHY %d already enabled, " "won't reprogram it\n", phy); @@ -1810,8 +1830,6 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv, DRM_DEBUG_DRIVER("DDI PHY %d enabled with invalid state, " "force reprogramming it\n", phy); - } else { - DRM_DEBUG_DRIVER("DDI PHY %d not enabled, enabling it\n", phy); } val = I915_READ(BXT_P_CR_GT_DISP_PWRON); @@ -1831,28 +1849,6 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv, DRM_ERROR("timeout during PHY%d power on\n", phy); } - if (phy == DPIO_PHY0) - ports = BIT(PORT_B) | BIT(PORT_C); - else - ports = BIT(PORT_A); - - for_each_port_masked(port, ports) { - int lane; - - for (lane = 0; lane < 4; lane++) { - val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane)); - /* - * Note that on CHV this flag is called UPAR, but has - * the same function. - */ - val &= ~LATENCY_OPTIM; - if (lane != 1) - val |= LATENCY_OPTIM; - - I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val); - } - } - /* Program PLL Rcomp code offset */ val = I915_READ(BXT_PORT_CL1CM_DW9(phy)); val &= ~IREF0RC_OFFSET_MASK; @@ -1899,10 +1895,7 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv, * the corresponding calibrated value from PHY1, and disable * the automatic calibration on PHY0. */ - broxton_phy_wait_grc_done(dev_priv, DPIO_PHY1); - - val = dev_priv->bxt_phy_grc = broxton_get_grc(dev_priv, - DPIO_PHY1); + val = dev_priv->bxt_phy_grc = bxt_get_grc(dev_priv, DPIO_PHY1); grc_code = val << GRC_CODE_FAST_SHIFT | val << GRC_CODE_SLOW_SHIFT | val; @@ -1912,31 +1905,16 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv, val |= GRC_DIS | GRC_RDY_OVRD; I915_WRITE(BXT_PORT_REF_DW8(DPIO_PHY0), val); } - /* - * During PHY1 init delay waiting for GRC calibration to finish, since - * it can happen in parallel with the subsequent PHY0 init. - */ val = I915_READ(BXT_PHY_CTL_FAMILY(phy)); val |= COMMON_RESET_DIS; I915_WRITE(BXT_PHY_CTL_FAMILY(phy), val); -} -void broxton_ddi_phy_init(struct drm_i915_private *dev_priv) -{ - /* Enable PHY1 first since it provides Rcomp for PHY0 */ - broxton_phy_init(dev_priv, DPIO_PHY1); - broxton_phy_init(dev_priv, DPIO_PHY0); - - /* - * If BIOS enabled only PHY0 and not PHY1, we skipped waiting for the - * PHY1 GRC calibration to finish, so wait for it here. - */ - broxton_phy_wait_grc_done(dev_priv, DPIO_PHY1); + if (phy == DPIO_PHY1) + bxt_phy_wait_grc_done(dev_priv, DPIO_PHY1); } -static void broxton_phy_uninit(struct drm_i915_private *dev_priv, - enum dpio_phy phy) +void bxt_ddi_phy_uninit(struct drm_i915_private *dev_priv, enum dpio_phy phy) { uint32_t val; @@ -1949,12 +1927,6 @@ static void broxton_phy_uninit(struct drm_i915_private *dev_priv, I915_WRITE(BXT_P_CR_GT_DISP_PWRON, val); } -void broxton_ddi_phy_uninit(struct drm_i915_private *dev_priv) -{ - broxton_phy_uninit(dev_priv, DPIO_PHY1); - broxton_phy_uninit(dev_priv, DPIO_PHY0); -} - static bool __printf(6, 7) __phy_reg_verify_state(struct drm_i915_private *dev_priv, enum dpio_phy phy, i915_reg_t reg, u32 mask, u32 expected, @@ -1982,11 +1954,9 @@ __phy_reg_verify_state(struct drm_i915_private *dev_priv, enum dpio_phy phy, return false; } -static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv, - enum dpio_phy phy) +bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv, + enum dpio_phy phy) { - enum port port; - u32 ports; uint32_t mask; bool ok; @@ -1994,27 +1964,11 @@ static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv, __phy_reg_verify_state(dev_priv, phy, reg, mask, exp, fmt, \ ## __VA_ARGS__) - /* We expect the PHY to be always enabled */ - if (!broxton_phy_is_enabled(dev_priv, phy)) + if (!bxt_ddi_phy_is_enabled(dev_priv, phy)) return false; ok = true; - if (phy == DPIO_PHY0) - ports = BIT(PORT_B) | BIT(PORT_C); - else - ports = BIT(PORT_A); - - for_each_port_masked(port, ports) { - int lane; - - for (lane = 0; lane < 4; lane++) - ok &= _CHK(BXT_PORT_TX_DW14_LN(port, lane), - LATENCY_OPTIM, - lane != 1 ? LATENCY_OPTIM : 0, - "BXT_PORT_TX_DW14_LN(%d, %d)", port, lane); - } - /* PLL Rcomp code offset */ ok &= _CHK(BXT_PORT_CL1CM_DW9(phy), IREF0RC_OFFSET_MASK, 0xe4 << IREF0RC_OFFSET_SHIFT, @@ -2058,11 +2012,65 @@ static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv, #undef _CHK } -void broxton_ddi_phy_verify_state(struct drm_i915_private *dev_priv) +static uint8_t +bxt_ddi_phy_calc_lane_lat_optim_mask(struct intel_encoder *encoder, + struct intel_crtc_state *pipe_config) { - if (!broxton_phy_verify_state(dev_priv, DPIO_PHY0) || - !broxton_phy_verify_state(dev_priv, DPIO_PHY1)) - i915_report_error(dev_priv, "DDI PHY state mismatch\n"); + switch (pipe_config->lane_count) { + case 1: + return 0; + case 2: + return BIT(2) | BIT(0); + case 4: + return BIT(3) | BIT(2) | BIT(0); + default: + MISSING_CASE(pipe_config->lane_count); + + return 0; + } +} + +static void bxt_ddi_pre_pll_enable(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev); + enum port port = dport->port; + struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); + int lane; + + for (lane = 0; lane < 4; lane++) { + u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane)); + + /* + * Note that on CHV this flag is called UPAR, but has + * the same function. + */ + val &= ~LATENCY_OPTIM; + if (intel_crtc->config->lane_lat_optim_mask & BIT(lane)) + val |= LATENCY_OPTIM; + + I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val); + } +} + +static uint8_t +bxt_ddi_phy_get_lane_lat_optim_mask(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev); + enum port port = dport->port; + int lane; + uint8_t mask; + + mask = 0; + for (lane = 0; lane < 4; lane++) { + u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane)); + + if (val & LATENCY_OPTIM) + mask |= BIT(lane); + } + + return mask; } void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp) @@ -2236,13 +2244,19 @@ void intel_ddi_get_config(struct intel_encoder *encoder, } intel_ddi_clock_get(encoder, pipe_config); + + if (IS_BROXTON(dev_priv)) + pipe_config->lane_lat_optim_mask = + bxt_ddi_phy_get_lane_lat_optim_mask(encoder); } static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { + struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; int type = encoder->type; int port = intel_ddi_get_encoder_port(encoder); + int ret; WARN(type == INTEL_OUTPUT_UNKNOWN, "compute_config() on unknown output!\n"); @@ -2250,9 +2264,17 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, pipe_config->cpu_transcoder = TRANSCODER_EDP; if (type == INTEL_OUTPUT_HDMI) - return intel_hdmi_compute_config(encoder, pipe_config); + ret = intel_hdmi_compute_config(encoder, pipe_config); else - return intel_dp_compute_config(encoder, pipe_config); + ret = intel_dp_compute_config(encoder, pipe_config); + + if (IS_BROXTON(dev_priv) && ret) + pipe_config->lane_lat_optim_mask = + bxt_ddi_phy_calc_lane_lat_optim_mask(encoder, + pipe_config); + + return ret; + } static const struct drm_encoder_funcs intel_ddi_funcs = { @@ -2351,6 +2373,8 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->compute_config = intel_ddi_compute_config; intel_encoder->enable = intel_enable_ddi; + if (IS_BROXTON(dev_priv)) + intel_encoder->pre_pll_enable = bxt_ddi_pre_pll_enable; intel_encoder->pre_enable = intel_ddi_pre_enable; intel_encoder->disable = intel_disable_ddi; intel_encoder->post_disable = intel_ddi_post_disable; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 49322f6cfa2b..095f83e22392 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -123,7 +123,7 @@ static void ironlake_pfit_enable(struct intel_crtc *crtc); static void intel_modeset_setup_hw_state(struct drm_device *dev); static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc); static int ilk_max_pixel_rate(struct drm_atomic_state *state); -static int broxton_calc_cdclk(int max_pixclk); +static int bxt_calc_cdclk(int max_pixclk); struct intel_limit { struct { @@ -4648,7 +4648,7 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state) intel_pre_disable_primary(&crtc->base); } - if (pipe_config->disable_cxsr) { + if (pipe_config->disable_cxsr && HAS_GMCH_DISPLAY(dev)) { crtc->wm.cxsr_allowed = false; /* @@ -4841,6 +4841,10 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A, false); + for_each_encoder_on_crtc(dev, crtc, encoder) + if (encoder->pre_pll_enable) + encoder->pre_pll_enable(encoder); + if (intel_crtc->config->shared_dpll) intel_enable_shared_dpll(intel_crtc); @@ -5416,7 +5420,7 @@ static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco) dev_priv->cdclk_pll.vco = vco; } -static void broxton_set_cdclk(struct drm_i915_private *dev_priv, int cdclk) +static void bxt_set_cdclk(struct drm_i915_private *dev_priv, int cdclk) { u32 val, divider; int vco, ret; @@ -5541,7 +5545,7 @@ sanitize: dev_priv->cdclk_pll.vco = -1; } -void broxton_init_cdclk(struct drm_i915_private *dev_priv) +void bxt_init_cdclk(struct drm_i915_private *dev_priv) { bxt_sanitize_cdclk(dev_priv); @@ -5553,12 +5557,12 @@ void broxton_init_cdclk(struct drm_i915_private *dev_priv) * - The initial CDCLK needs to be read from VBT. * Need to make this change after VBT has changes for BXT. */ - broxton_set_cdclk(dev_priv, broxton_calc_cdclk(0)); + bxt_set_cdclk(dev_priv, bxt_calc_cdclk(0)); } -void broxton_uninit_cdclk(struct drm_i915_private *dev_priv) +void bxt_uninit_cdclk(struct drm_i915_private *dev_priv) { - broxton_set_cdclk(dev_priv, dev_priv->cdclk_pll.ref); + bxt_set_cdclk(dev_priv, dev_priv->cdclk_pll.ref); } static int skl_calc_cdclk(int max_pixclk, int vco) @@ -5984,7 +5988,7 @@ static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv, return 200000; } -static int broxton_calc_cdclk(int max_pixclk) +static int bxt_calc_cdclk(int max_pixclk) { if (max_pixclk > 576000) return 624000; @@ -6044,17 +6048,17 @@ static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state) return 0; } -static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state) +static int bxt_modeset_calc_cdclk(struct drm_atomic_state *state) { int max_pixclk = ilk_max_pixel_rate(state); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); intel_state->cdclk = intel_state->dev_cdclk = - broxton_calc_cdclk(max_pixclk); + bxt_calc_cdclk(max_pixclk); if (!intel_state->active_crtcs) - intel_state->dev_cdclk = broxton_calc_cdclk(0); + intel_state->dev_cdclk = bxt_calc_cdclk(0); return 0; } @@ -8430,12 +8434,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) else final |= DREF_NONSPREAD_SOURCE_ENABLE; + final &= ~DREF_SSC_SOURCE_MASK; final &= ~DREF_CPU_SOURCE_OUTPUT_MASK; - - if (!using_ssc_source) { - final &= ~DREF_SSC_SOURCE_MASK; - final &= ~DREF_SSC1_ENABLE; - } + final &= ~DREF_SSC1_ENABLE; if (has_panel) { final |= DREF_SSC_SOURCE_ENABLE; @@ -8450,9 +8451,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - } else { - final |= DREF_SSC_SOURCE_DISABLE; - final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } else if (using_ssc_source) { + final |= DREF_SSC_SOURCE_ENABLE; + final |= DREF_SSC1_ENABLE; } if (final == val) @@ -9673,14 +9674,14 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) } } -static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state) +static void bxt_modeset_commit_cdclk(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; struct intel_atomic_state *old_intel_state = to_intel_atomic_state(old_state); unsigned int req_cdclk = old_intel_state->dev_cdclk; - broxton_set_cdclk(to_i915(dev), req_cdclk); + bxt_set_cdclk(to_i915(dev), req_cdclk); } /* compute the max rate for new configuration */ @@ -12816,6 +12817,7 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(has_dp_encoder); PIPE_CONF_CHECK_I(lane_count); + PIPE_CONF_CHECK_X(lane_lat_optim_mask); if (INTEL_INFO(dev)->gen < 8) { PIPE_CONF_CHECK_M_N(dp_m_n); @@ -14702,7 +14704,7 @@ static void intel_setup_outputs(struct drm_device *dev) if (I915_READ(PCH_DP_D) & DP_DETECTED) intel_dp_init(dev, PCH_DP_D, PORT_D); } else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { - bool has_edp; + bool has_edp, has_port; /* * The DP_DETECTED bit is the latched state of the DDC @@ -14712,25 +14714,37 @@ static void intel_setup_outputs(struct drm_device *dev) * Thus we can't rely on the DP_DETECTED bit alone to detect * eDP ports. Consult the VBT as well as DP_DETECTED to * detect eDP ports. + * + * Sadly the straps seem to be missing sometimes even for HDMI + * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap + * and VBT for the presence of the port. Additionally we can't + * trust the port type the VBT declares as we've seen at least + * HDMI ports that the VBT claim are DP or eDP. */ has_edp = intel_dp_is_edp(dev, PORT_B); - if (I915_READ(VLV_DP_B) & DP_DETECTED || has_edp) + has_port = intel_bios_is_port_present(dev_priv, PORT_B); + if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port) has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B); - if (I915_READ(VLV_HDMIB) & SDVO_DETECTED && !has_edp) + if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIB, PORT_B); has_edp = intel_dp_is_edp(dev, PORT_C); - if (I915_READ(VLV_DP_C) & DP_DETECTED || has_edp) + has_port = intel_bios_is_port_present(dev_priv, PORT_C); + if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port) has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C); - if (I915_READ(VLV_HDMIC) & SDVO_DETECTED && !has_edp) + if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp) intel_hdmi_init(dev, VLV_HDMIC, PORT_C); if (IS_CHERRYVIEW(dev)) { - /* eDP not supported on port D, so don't check VBT */ - if (I915_READ(CHV_HDMID) & SDVO_DETECTED) - intel_hdmi_init(dev, CHV_HDMID, PORT_D); - if (I915_READ(CHV_DP_D) & DP_DETECTED) + /* + * eDP not supported on port D, + * so no need to worry about it + */ + has_port = intel_bios_is_port_present(dev_priv, PORT_D); + if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port) intel_dp_init(dev, CHV_DP_D, PORT_D); + if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port) + intel_hdmi_init(dev, CHV_HDMID, PORT_D); } intel_dsi_init(dev); @@ -15212,9 +15226,9 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) valleyview_modeset_calc_cdclk; } else if (IS_BROXTON(dev_priv)) { dev_priv->display.modeset_commit_cdclk = - broxton_modeset_commit_cdclk; + bxt_modeset_commit_cdclk; dev_priv->display.modeset_calc_cdclk = - broxton_modeset_calc_cdclk; + bxt_modeset_calc_cdclk; } else if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { dev_priv->display.modeset_commit_cdclk = skl_modeset_commit_cdclk; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 270da8de0acf..8dc67adace6b 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -579,6 +579,12 @@ struct intel_crtc_state { uint8_t lane_count; + /* + * Used by platforms having DP/HDMI PHY with programmable lane + * latency optimization. + */ + uint8_t lane_lat_optim_mask; + /* Panel fitter controls for gen2-gen4 + VLV */ struct { u32 control; @@ -1260,11 +1266,14 @@ void intel_prepare_reset(struct drm_i915_private *dev_priv); void intel_finish_reset(struct drm_i915_private *dev_priv); void hsw_enable_pc8(struct drm_i915_private *dev_priv); void hsw_disable_pc8(struct drm_i915_private *dev_priv); -void broxton_init_cdclk(struct drm_i915_private *dev_priv); -void broxton_uninit_cdclk(struct drm_i915_private *dev_priv); -void broxton_ddi_phy_init(struct drm_i915_private *dev_priv); -void broxton_ddi_phy_uninit(struct drm_i915_private *dev_priv); -void broxton_ddi_phy_verify_state(struct drm_i915_private *dev_priv); +void bxt_init_cdclk(struct drm_i915_private *dev_priv); +void bxt_uninit_cdclk(struct drm_i915_private *dev_priv); +void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy); +void bxt_ddi_phy_uninit(struct drm_i915_private *dev_priv, enum dpio_phy phy); +bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, + enum dpio_phy phy); +bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv, + enum dpio_phy phy); void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv); void bxt_enable_dc9(struct drm_i915_private *dev_priv); void bxt_disable_dc9(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index a2ead5eac336..10e12829b13f 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -1172,6 +1172,12 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder) if (intel_dsi->clock_stop) tmp |= CLOCKSTOP; + if (IS_BROXTON(dev_priv)) { + tmp |= BXT_DPHY_DEFEATURE_EN; + if (!is_cmd_mode(intel_dsi)) + tmp |= BXT_DEFEATURE_DPI_FIFO_CTR; + } + for_each_dsi_port(port, intel_dsi->ports) { I915_WRITE(MIPI_DSI_FUNC_PRG(port), val); diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 4c725ad6fb54..4babefc51eb2 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -552,8 +552,6 @@ static void intel_fbdev_destroy(struct drm_device *dev, drm_fb_helper_fini(&ifbdev->helper); if (ifbdev->fb) { - drm_framebuffer_unregister_private(&ifbdev->fb->base); - mutex_lock(&dev->struct_mutex); intel_unpin_fb_obj(&ifbdev->fb->base, BIT(DRM_ROTATE_0)); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h index 41601c71f529..4df80cc9a291 100644 --- a/drivers/gpu/drm/i915/intel_guc.h +++ b/drivers/gpu/drm/i915/intel_guc.h @@ -156,11 +156,11 @@ extern int intel_guc_suspend(struct drm_device *dev); extern int intel_guc_resume(struct drm_device *dev); /* i915_guc_submission.c */ -int i915_guc_submission_init(struct drm_device *dev); -int i915_guc_submission_enable(struct drm_device *dev); +int i915_guc_submission_init(struct drm_i915_private *dev_priv); +int i915_guc_submission_enable(struct drm_i915_private *dev_priv); int i915_guc_wq_check_space(struct drm_i915_gem_request *rq); int i915_guc_submit(struct drm_i915_gem_request *rq); -void i915_guc_submission_disable(struct drm_device *dev); -void i915_guc_submission_fini(struct drm_device *dev); +void i915_guc_submission_disable(struct drm_i915_private *dev_priv); +void i915_guc_submission_fini(struct drm_i915_private *dev_priv); #endif diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c index f2b88c7209cb..8fe96a2d989e 100644 --- a/drivers/gpu/drm/i915/intel_guc_loader.c +++ b/drivers/gpu/drm/i915/intel_guc_loader.c @@ -425,9 +425,13 @@ int intel_guc_setup(struct drm_device *dev) if (!i915.enable_guc_loading) { err = 0; goto fail; - } else if (fw_path == NULL || *fw_path == '\0') { - if (*fw_path == '\0') - DRM_INFO("No GuC firmware known for this platform\n"); + } else if (fw_path == NULL) { + /* Device is known to have no uCode (e.g. no GuC) */ + err = -ENXIO; + goto fail; + } else if (*fw_path == '\0') { + /* Device has a GuC but we don't know what f/w to load? */ + DRM_INFO("No GuC firmware known for this platform\n"); err = -ENODEV; goto fail; } @@ -449,7 +453,7 @@ int intel_guc_setup(struct drm_device *dev) intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status), intel_guc_fw_status_repr(guc_fw->guc_fw_load_status)); - err = i915_guc_submission_init(dev); + err = i915_guc_submission_init(dev_priv); if (err) goto fail; @@ -488,10 +492,7 @@ int intel_guc_setup(struct drm_device *dev) intel_guc_fw_status_repr(guc_fw->guc_fw_load_status)); if (i915.enable_guc_submission) { - /* The execbuf_client will be recreated. Release it first. */ - i915_guc_submission_disable(dev); - - err = i915_guc_submission_enable(dev); + err = i915_guc_submission_enable(dev_priv); if (err) goto fail; direct_interrupts_to_guc(dev_priv); @@ -504,8 +505,8 @@ fail: guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL; direct_interrupts_to_host(dev_priv); - i915_guc_submission_disable(dev); - i915_guc_submission_fini(dev); + i915_guc_submission_disable(dev_priv); + i915_guc_submission_fini(dev_priv); /* * We've failed to load the firmware :( @@ -524,18 +525,20 @@ fail: ret = 0; } - if (err == 0) + if (err == 0 && !HAS_GUC_UCODE(dev)) + ; /* Don't mention the GuC! */ + else if (err == 0) DRM_INFO("GuC firmware load skipped\n"); - else if (ret == -EIO) - DRM_ERROR("GuC firmware load failed: %d\n", err); - else + else if (ret != -EIO) DRM_INFO("GuC firmware load failed: %d\n", err); + else + DRM_ERROR("GuC firmware load failed: %d\n", err); if (i915.enable_guc_submission) { if (fw_path == NULL) DRM_INFO("GuC submission without firmware not supported\n"); if (ret == 0) - DRM_INFO("Falling back to execlist mode\n"); + DRM_INFO("Falling back from GuC submission to execlist mode\n"); else DRM_ERROR("GuC init failed: %d\n", ret); } @@ -730,8 +733,8 @@ void intel_guc_fini(struct drm_device *dev) mutex_lock(&dev->struct_mutex); direct_interrupts_to_host(dev_priv); - i915_guc_submission_disable(dev); - i915_guc_submission_fini(dev); + i915_guc_submission_disable(dev_priv); + i915_guc_submission_fini(dev_priv); if (guc_fw->guc_fw_obj) drm_gem_object_unreference(&guc_fw->guc_fw_obj->base); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 6b29da9bba38..ad0c71b3e242 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1809,6 +1809,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; uint8_t alternate_ddc_pin; + DRM_DEBUG_KMS("Adding HDMI connector on port %c\n", + port_name(port)); + if (WARN(intel_dig_port->max_lanes < 4, "Not enough lanes (%d) for HDMI on port %c\n", intel_dig_port->max_lanes, port_name(port))) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 5c191a1afaaf..4fad8303648e 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -238,7 +238,7 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx, /** * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists - * @dev: DRM device. + * @dev_priv: i915 device private * @enable_execlists: value of i915.enable_execlists module parameter. * * Only certain platforms support Execlists (the prerequisites being @@ -516,7 +516,7 @@ get_context_status(struct intel_engine_cs *engine, unsigned int read_pointer, /** * intel_lrc_irq_handler() - handle Context Switch interrupts - * @engine: Engine Command Streamer to handle. + * @data: tasklet handler passed in unsigned long * * Check the unread Context Status Buffers and manage the submission of new * contexts to the ELSP accordingly. @@ -786,15 +786,9 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request) /** * execlists_submission() - submit a batchbuffer for execution, Execlists style - * @dev: DRM device. - * @file: DRM file. - * @ring: Engine Command Streamer to submit to. - * @ctx: Context to employ for this submission. + * @params: execbuffer call parameters. * @args: execbuffer call arguments. * @vmas: list of vmas. - * @batch_obj: the batchbuffer to submit. - * @exec_start: batchbuffer start virtual address pointer. - * @dispatch_flags: translated execbuffer call flags. * * This is the evil twin version of i915_gem_ringbuffer_submission. It abstracts * away the submission details of the execbuffer ioctl call. @@ -1081,12 +1075,13 @@ 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 + * WaDisableLSQCROPERFforOCL:skl,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(engine->i915, 0, SKL_REVID_E0)) + if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_E0) || + IS_KBL_REVID(engine->i915, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1138,7 +1133,7 @@ static inline int wa_ctx_end(struct i915_wa_ctx_bb *wa_ctx, /** * gen8_init_indirectctx_bb() - initialize indirect ctx batch with WA * - * @ring: only applicable for RCS + * @engine: only applicable for RCS * @wa_ctx: structure representing wa_ctx * offset: specifies start of the batch, should be cache-aligned. This is updated * with the offset value received as input. @@ -1212,7 +1207,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine, /** * gen8_init_perctx_bb() - initialize per ctx batch with WA * - * @ring: only applicable for RCS + * @engine: only applicable for RCS * @wa_ctx: structure representing wa_ctx * offset: specifies start of the batch, should be cache-aligned. * size: size of the batch in DWORDS but HW expects in terms of cachelines @@ -1260,6 +1255,22 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, return ret; index = ret; + /* WaClearSlmSpaceAtContextSwitch:kbl */ + /* Actual scratch location is at 128 bytes offset */ + if (IS_KBL_REVID(engine->i915, 0, KBL_REVID_A0)) { + uint32_t scratch_addr + = engine->scratch.gtt_offset + 2*CACHELINE_BYTES; + + wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6)); + wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE)); + wa_ctx_emit(batch, index, scratch_addr); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + wa_ctx_emit(batch, index, 0); + } /* Pad to end of cacheline */ while (index % CACHELINE_DWORDS) wa_ctx_emit(batch, index, MI_NOOP); @@ -1657,9 +1668,10 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, struct intel_ringbuffer *ringbuf = request->ringbuf; struct intel_engine_cs *engine = ringbuf->engine; u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES; - bool vf_flush_wa = false; + bool vf_flush_wa = false, dc_flush_wa = false; u32 flags = 0; int ret; + int len; flags |= PIPE_CONTROL_CS_STALL; @@ -1686,9 +1698,21 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, */ if (IS_GEN9(request->i915)) vf_flush_wa = true; + + /* WaForGAMHang:kbl */ + if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0)) + dc_flush_wa = true; } - ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6); + len = 6; + + if (vf_flush_wa) + len += 6; + + if (dc_flush_wa) + len += 12; + + ret = intel_ring_begin(request, len); if (ret) return ret; @@ -1701,12 +1725,31 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, intel_logical_ring_emit(ringbuf, 0); } + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); intel_logical_ring_emit(ringbuf, flags); intel_logical_ring_emit(ringbuf, scratch_addr); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, 0); + + if (dc_flush_wa) { + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6)); + intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, 0); + } + intel_logical_ring_advance(ringbuf); return 0; @@ -1860,7 +1903,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req) /** * intel_logical_ring_cleanup() - deallocate the Engine Command Streamer * - * @ring: Engine Command Streamer. + * @engine: Engine Command Streamer. * */ void intel_logical_ring_cleanup(struct intel_engine_cs *engine) @@ -2413,7 +2456,7 @@ populate_lr_context(struct i915_gem_context *ctx, /** * intel_lr_context_size() - return the size of the context for an engine - * @ring: which engine to find the context size for + * @engine: which engine to find the context size for * * Each engine may require a different amount of space for a context image, * so when allocating (or copying) an image, this function can be used to diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c index b765c75f3fcd..3c1482b8f2f4 100644 --- a/drivers/gpu/drm/i915/intel_mocs.c +++ b/drivers/gpu/drm/i915/intel_mocs.c @@ -156,6 +156,16 @@ static bool get_mocs_settings(struct drm_i915_private *dev_priv, "Platform that should have a MOCS table does not.\n"); } + /* WaDisableSkipCaching:skl,bxt,kbl */ + if (IS_GEN9(dev_priv)) { + int i; + + for (i = 0; i < table->size; i++) + if (WARN_ON(table->table[i].l3cc_value & + (L3_ESC(1) | L3_SCC(0x7)))) + return false; + } + return result; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 08274591db7e..658a75659657 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -55,14 +55,38 @@ #define INTEL_RC6p_ENABLE (1<<1) #define INTEL_RC6pp_ENABLE (1<<2) -static void bxt_init_clock_gating(struct drm_device *dev) +static void gen9_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - /* See Bspec note for PSR2_CTL bit 31, Wa#828:bxt */ + /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */ I915_WRITE(CHICKEN_PAR1_1, I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + I915_WRITE(GEN8_CONFIG0, + I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES); + + /* WaEnableChickenDCPR:skl,bxt,kbl */ + I915_WRITE(GEN8_CHICKEN_DCPR_1, + I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM); + + /* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */ + /* WaFbcWakeMemOn:skl,bxt,kbl */ + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_FBC_WM_DIS | + DISP_FBC_MEMORY_WAKE); + + /* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_DISABLE_DUMMY0); +} + +static void bxt_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + /* WaDisableSDEUnitClockGating:bxt */ I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | GEN8_SDEUNIT_CLOCK_GATE_DISABLE); @@ -6963,13 +6987,40 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, I915_WRITE(GEN7_MISCCPCTL, misccpctl); } +static void kabylake_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + gen9_init_clock_gating(dev); + + /* WaDisableSDEUnitClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableGamClockGating:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_GAMUNIT_CLOCK_GATE_DISABLE); + + /* WaFbcNukeOnHostModify:kbl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); +} + static void skylake_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,kbl */ - I915_WRITE(CHICKEN_PAR1_1, - I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); + gen9_init_clock_gating(dev); + + /* WAC6entrylatency:skl */ + I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) | + FBC_LLC_FULLY_OPEN); + + /* WaFbcNukeOnHostModify:skl */ + I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) | + ILK_DPFC_NUKE_ON_ANY_MODIFICATION); } static void broadwell_init_clock_gating(struct drm_device *dev) @@ -7016,6 +7067,10 @@ static void broadwell_init_clock_gating(struct drm_device *dev) */ I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL); + /* WaKVMNotificationOnConfigChange:bdw */ + I915_WRITE(CHICKEN_PAR2_1, I915_READ(CHICKEN_PAR2_1) + | KVM_CONFIG_CHANGE_NOTIFICATION_SELECT); + lpt_init_clock_gating(dev); } @@ -7433,7 +7488,7 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) if (IS_SKYLAKE(dev_priv)) dev_priv->display.init_clock_gating = skylake_init_clock_gating; else if (IS_KABYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = skylake_init_clock_gating; + dev_priv->display.init_clock_gating = kabylake_init_clock_gating; else if (IS_BROXTON(dev_priv)) dev_priv->display.init_clock_gating = bxt_init_clock_gating; else if (IS_BROADWELL(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 8d35a3978f9b..fedd27049814 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -908,24 +908,26 @@ static int chv_init_workarounds(struct intel_engine_cs *engine) static int gen9_init_workarounds(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; - uint32_t tmp; int ret; - /* WaEnableLbsSlaRetryTimerDecrement:skl */ + /* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */ + I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */ I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl */ + /* WaDisableKillLogic:bxt,skl,kbl */ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | ECOCHK_DIS_TLB); - /* WaClearFlowControlGpgpuContextSave:skl,bxt */ - /* WaDisablePartialInstShootdown:skl,bxt */ + /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */ + /* WaDisablePartialInstShootdown:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, FLOW_CONTROL_ENABLE | PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); - /* Syncing dependencies between camera and graphics:skl,bxt */ + /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); @@ -947,18 +949,18 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) */ } - /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */ - /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */ + /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */ + /* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */ WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7, GEN9_ENABLE_YV12_BUGFIX | GEN9_ENABLE_GPGPU_PREEMPTION); - /* Wa4x4STCOptimizationDisable:skl,bxt */ - /* WaDisablePartialResolveInVc:skl,bxt */ + /* Wa4x4STCOptimizationDisable:skl,bxt,kbl */ + /* WaDisablePartialResolveInVc:skl,bxt,kbl */ WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE | GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE)); - /* WaCcsTlbPrefetchDisable:skl,bxt */ + /* WaCcsTlbPrefetchDisable:skl,bxt,kbl */ WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5, GEN9_CCS_TLB_PREFETCH_ENABLE); @@ -968,31 +970,57 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0, PIXEL_MASK_CAMMING_DISABLE); - /* WaForceContextSaveRestoreNonCoherent:skl,bxt */ - tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT; - if (IS_SKL_REVID(dev_priv, SKL_REVID_F0, REVID_FOREVER) || - IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) - tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE; - WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp); + /* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | + HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE); + + /* WaForceEnableNonCoherent and WaDisableHDCInvalidation are + * both tied to WaForceContextSaveRestoreNonCoherent + * in some hsds for skl. We keep the tie for all gen9. The + * documentation is a bit hazy and so we want to get common behaviour, + * even though there is no clear evidence we would need both on kbl/bxt. + * This area has been source of system hangs so we play it safe + * and mimic the skl regardless of what bspec says. + * + * Use Force Non-Coherent whenever executing a 3D context. This + * is a workaround for a possible hang in the unlikely event + * a TLB invalidation occurs during a PSD flush. + */ - /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */ - if (IS_SKYLAKE(dev_priv) || IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + /* WaForceEnableNonCoherent:skl,bxt,kbl */ + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FORCE_NON_COHERENT); + + /* WaDisableHDCInvalidation:skl,bxt,kbl */ + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + BDW_DISABLE_HDC_INVALIDATION); + + /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */ + if (IS_SKYLAKE(dev_priv) || + IS_KABYLAKE(dev_priv) || + IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN8_SAMPLER_POWER_BYPASS_DIS); - /* WaDisableSTUnitPowerOptimization:skl,bxt */ + /* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE); - /* WaOCLCoherentLineFlush:skl,bxt */ + /* WaOCLCoherentLineFlush:skl,bxt,kbl */ I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES)); - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt */ + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */ + ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); + if (ret) + return ret; + + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */ ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1); if (ret) return ret; - /* WaAllowUMDToModifyHDCChicken1:skl,bxt */ + /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */ ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1); if (ret) return ret; @@ -1060,7 +1088,7 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); } - if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0)) { + 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)); @@ -1085,22 +1113,6 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HIZ_CHICKEN, BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE); - /* This is tied to WaForceContextSaveRestoreNonCoherent */ - if (IS_SKL_REVID(dev_priv, 0, REVID_FOREVER)) { - /* - *Use Force Non-Coherent whenever executing a 3D context. This - * is a workaround for a possible hang in the unlikely event - * a TLB invalidation occurs during a PSD flush. - */ - /* WaForceEnableNonCoherent:skl */ - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FORCE_NON_COHERENT); - - /* WaDisableHDCInvalidation:skl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - } - /* WaBarrierPerformanceFixDisable:skl */ if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, SKL_REVID_D0)) WA_SET_BIT_MASKED(HDC_CHICKEN0, @@ -1113,6 +1125,9 @@ static int skl_init_workarounds(struct intel_engine_cs *engine) GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + /* WaDisableGafsUnitClkGating:skl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + /* WaDisableLSQCROPERFforOCL:skl */ ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); if (ret) @@ -1145,6 +1160,12 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); + /* WaDisablePooledEuLoadBalancingFix:bxt */ + if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) { + WA_SET_BIT_MASKED(FF_SLICE_CS_CHICKEN2, + GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); + } + /* WaDisableSbeCacheDispatchPortSharing:bxt */ if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) { WA_SET_BIT_MASKED( @@ -1171,6 +1192,63 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2)); + /* WaInsertDummyPushConstPs:bxt */ + if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + return 0; +} + +static int kbl_init_workarounds(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + int ret; + + ret = gen9_init_workarounds(engine); + if (ret) + return ret; + + /* WaEnableGapsTsvCreditFix:kbl */ + I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) | + GEN9_GAPS_TSV_CREDIT_DISABLE)); + + /* WaDisableDynamicCreditSharing:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT(GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + + /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) + WA_SET_BIT_MASKED(HDC_CHICKEN0, + HDC_FENCE_DEST_SLM_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_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) + /* WaDisableLSQCROPERFforOCL:kbl */ + I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | + GEN8_LQSC_RO_PERF_DIS); + + /* WaInsertDummyPushConstPs:kbl */ + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, + GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); + + /* WaDisableGafsUnitClkGating:kbl */ + WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSbeCacheDispatchPortSharing:kbl */ + WA_SET_BIT_MASKED( + GEN7_HALF_SLICE_CHICKEN1, + GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); + + /* WaDisableLSQCROPERFforOCL:kbl */ + ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4); + if (ret) + return ret; + return 0; } @@ -1195,6 +1273,9 @@ int init_workarounds_ring(struct intel_engine_cs *engine) if (IS_BROXTON(dev_priv)) return bxt_init_workarounds(engine); + if (IS_KABYLAKE(dev_priv)) + return kbl_init_workarounds(engine); + return 0; } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index fe8faf30bda7..e856d49d6dc3 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -65,6 +65,9 @@ bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv, int power_well_id); +static struct i915_power_well * +lookup_power_well(struct drm_i915_private *dev_priv, int power_well_id); + const char * intel_display_power_domain_str(enum intel_display_power_domain domain) { @@ -151,6 +154,23 @@ static void intel_power_well_disable(struct drm_i915_private *dev_priv, power_well->ops->disable(dev_priv, power_well); } +static void intel_power_well_get(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + if (!power_well->count++) + intel_power_well_enable(dev_priv, power_well); +} + +static void intel_power_well_put(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + WARN(!power_well->count, "Use count on power well %s is already zero", + power_well->name); + + if (!--power_well->count) + intel_power_well_disable(dev_priv, power_well); +} + /* * We should only use the power well if we explicitly asked the hardware to * enable it, so check if it's enabled and also check if we've requested it to @@ -419,6 +439,16 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv, BIT(POWER_DOMAIN_MODESET) | \ BIT(POWER_DOMAIN_AUX_A) | \ BIT(POWER_DOMAIN_INIT)) +#define BXT_DPIO_CMN_A_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_A_LANES) | \ + BIT(POWER_DOMAIN_AUX_A) | \ + BIT(POWER_DOMAIN_INIT)) +#define BXT_DPIO_CMN_BC_POWER_DOMAINS ( \ + BIT(POWER_DOMAIN_PORT_DDI_B_LANES) | \ + BIT(POWER_DOMAIN_PORT_DDI_C_LANES) | \ + BIT(POWER_DOMAIN_AUX_B) | \ + BIT(POWER_DOMAIN_AUX_C) | \ + BIT(POWER_DOMAIN_INIT)) static void assert_can_enable_dc9(struct drm_i915_private *dev_priv) { @@ -800,6 +830,72 @@ static void skl_power_well_disable(struct drm_i915_private *dev_priv, skl_set_power_well(dev_priv, power_well, false); } +static enum dpio_phy bxt_power_well_to_phy(struct i915_power_well *power_well) +{ + enum skl_disp_power_wells power_well_id = power_well->data; + + return power_well_id == BXT_DPIO_CMN_A ? DPIO_PHY1 : DPIO_PHY0; +} + +static void bxt_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + enum skl_disp_power_wells power_well_id = power_well->data; + struct i915_power_well *cmn_a_well; + + if (power_well_id == BXT_DPIO_CMN_BC) { + /* + * We need to copy the GRC calibration value from the eDP PHY, + * so make sure it's powered up. + */ + cmn_a_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_A); + intel_power_well_get(dev_priv, cmn_a_well); + } + + bxt_ddi_phy_init(dev_priv, bxt_power_well_to_phy(power_well)); + + if (power_well_id == BXT_DPIO_CMN_BC) + intel_power_well_put(dev_priv, cmn_a_well); +} + +static void bxt_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + bxt_ddi_phy_uninit(dev_priv, bxt_power_well_to_phy(power_well)); +} + +static bool bxt_dpio_cmn_power_well_enabled(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + return bxt_ddi_phy_is_enabled(dev_priv, + bxt_power_well_to_phy(power_well)); +} + +static void bxt_dpio_cmn_power_well_sync_hw(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + if (power_well->count > 0) + bxt_dpio_cmn_power_well_enable(dev_priv, power_well); + else + bxt_dpio_cmn_power_well_disable(dev_priv, power_well); +} + + +static void bxt_verify_ddi_phy_power_wells(struct drm_i915_private *dev_priv) +{ + struct i915_power_well *power_well; + + power_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_A); + if (power_well->count > 0) + bxt_ddi_phy_verify_state(dev_priv, + bxt_power_well_to_phy(power_well)); + + power_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_BC); + if (power_well->count > 0) + bxt_ddi_phy_verify_state(dev_priv, + bxt_power_well_to_phy(power_well)); +} + static bool gen9_dc_off_power_well_enabled(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { @@ -826,7 +922,7 @@ static void gen9_dc_off_power_well_enable(struct drm_i915_private *dev_priv, gen9_assert_dbuf_enabled(dev_priv); if (IS_BROXTON(dev_priv)) - broxton_ddi_phy_verify_state(dev_priv); + bxt_verify_ddi_phy_power_wells(dev_priv); } static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv, @@ -1518,10 +1614,8 @@ __intel_display_power_get_domain(struct drm_i915_private *dev_priv, struct i915_power_well *power_well; int i; - for_each_power_well(i, power_well, BIT(domain), power_domains) { - if (!power_well->count++) - intel_power_well_enable(dev_priv, power_well); - } + for_each_power_well(i, power_well, BIT(domain), power_domains) + intel_power_well_get(dev_priv, power_well); power_domains->domain_use_count[domain]++; } @@ -1615,14 +1709,8 @@ void intel_display_power_put(struct drm_i915_private *dev_priv, intel_display_power_domain_str(domain)); power_domains->domain_use_count[domain]--; - for_each_power_well_rev(i, power_well, BIT(domain), power_domains) { - WARN(!power_well->count, - "Use count on power well %s is already zero", - power_well->name); - - if (!--power_well->count) - intel_power_well_disable(dev_priv, power_well); - } + for_each_power_well_rev(i, power_well, BIT(domain), power_domains) + intel_power_well_put(dev_priv, power_well); mutex_unlock(&power_domains->lock); @@ -1793,6 +1881,13 @@ static const struct i915_power_well_ops gen9_dc_off_power_well_ops = { .is_enabled = gen9_dc_off_power_well_enabled, }; +static const struct i915_power_well_ops bxt_dpio_cmn_power_well_ops = { + .sync_hw = bxt_dpio_cmn_power_well_sync_hw, + .enable = bxt_dpio_cmn_power_well_enable, + .disable = bxt_dpio_cmn_power_well_disable, + .is_enabled = bxt_dpio_cmn_power_well_enabled, +}; + static struct i915_power_well hsw_power_wells[] = { { .name = "always-on", @@ -2029,6 +2124,18 @@ static struct i915_power_well bxt_power_wells[] = { .ops = &skl_power_well_ops, .data = SKL_DISP_PW_2, }, + { + .name = "dpio-common-a", + .domains = BXT_DPIO_CMN_A_POWER_DOMAINS, + .ops = &bxt_dpio_cmn_power_well_ops, + .data = BXT_DPIO_CMN_A, + }, + { + .name = "dpio-common-bc", + .domains = BXT_DPIO_CMN_BC_POWER_DOMAINS, + .ops = &bxt_dpio_cmn_power_well_ops, + .data = BXT_DPIO_CMN_BC, + }, }; static int @@ -2294,14 +2401,10 @@ void bxt_display_core_init(struct drm_i915_private *dev_priv, mutex_unlock(&power_domains->lock); - broxton_init_cdclk(dev_priv); + bxt_init_cdclk(dev_priv); gen9_dbuf_enable(dev_priv); - broxton_ddi_phy_init(dev_priv); - - broxton_ddi_phy_verify_state(dev_priv); - if (resume && dev_priv->csr.dmc_payload) intel_csr_load_program(dev_priv); } @@ -2313,11 +2416,9 @@ void bxt_display_core_uninit(struct drm_i915_private *dev_priv) gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); - broxton_ddi_phy_uninit(dev_priv); - gen9_dbuf_disable(dev_priv); - broxton_uninit_cdclk(dev_priv); + bxt_uninit_cdclk(dev_priv); /* The spec doesn't call for removing the reset handshake flag */ @@ -2448,6 +2549,7 @@ static void vlv_cmnlane_wa(struct drm_i915_private *dev_priv) /** * intel_power_domains_init_hw - initialize hardware power domain state * @dev_priv: i915 device instance + * @resume: Called from resume code paths or not * * This function initializes the hardware power domain state and enables all * power domains using intel_display_set_init_power(). diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index 9e9bddaa58a5..f49edecd66a3 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -13,6 +13,9 @@ void intel_gmch_remove(void); bool intel_enable_gtt(void); void intel_gtt_chipset_flush(void); +void intel_gtt_insert_page(dma_addr_t addr, + unsigned int pg, + unsigned int flags); void intel_gtt_insert_sg_entries(struct sg_table *st, unsigned int pg_start, unsigned int flags); |