diff options
28 files changed, 1044 insertions, 230 deletions
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index c92424ca1a5..5cf47ac2d40 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -76,7 +76,6 @@ static struct _intel_private { struct resource ifp_resource; int resource_valid; struct page *scratch_page; - dma_addr_t scratch_page_dma; } intel_private; #define INTEL_GTT_GEN intel_private.driver->gen @@ -306,9 +305,9 @@ static int intel_gtt_setup_scratch_page(void) if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) return -EINVAL; - intel_private.scratch_page_dma = dma_addr; + intel_private.base.scratch_page_dma = dma_addr; } else - intel_private.scratch_page_dma = page_to_phys(page); + intel_private.base.scratch_page_dma = page_to_phys(page); intel_private.scratch_page = page; @@ -631,7 +630,7 @@ static unsigned int intel_gtt_mappable_entries(void) static void intel_gtt_teardown_scratch_page(void) { set_pages_wb(intel_private.scratch_page, 1); - pci_unmap_page(intel_private.pcidev, intel_private.scratch_page_dma, + pci_unmap_page(intel_private.pcidev, intel_private.base.scratch_page_dma, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); put_page(intel_private.scratch_page); __free_page(intel_private.scratch_page); @@ -681,6 +680,7 @@ static int intel_gtt_init(void) iounmap(intel_private.registers); return -ENOMEM; } + intel_private.base.gtt = intel_private.gtt; global_cache_flush(); /* FIXME: ? */ @@ -975,7 +975,7 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries) unsigned int i; for (i = first_entry; i < (first_entry + num_entries); i++) { - intel_private.driver->write_entry(intel_private.scratch_page_dma, + intel_private.driver->write_entry(intel_private.base.scratch_page_dma, i, 0); } readl(intel_private.gtt+i-1); diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c index ddd70db45f7..637fcc3766c 100644 --- a/drivers/gpu/drm/drm_ioc32.c +++ b/drivers/gpu/drm/drm_ioc32.c @@ -315,7 +315,8 @@ static int compat_drm_getclient(struct file *file, unsigned int cmd, if (err) return err; - if (__get_user(c32.auth, &client->auth) + if (__get_user(c32.idx, &client->idx) + || __get_user(c32.auth, &client->auth) || __get_user(c32.pid, &client->pid) || __get_user(c32.uid, &client->uid) || __get_user(c32.magic, &client->magic) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 11ae06aac1f..fdb7ccefffb 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -721,8 +721,14 @@ static void i915_ring_error_state(struct seq_file *m, if (INTEL_INFO(dev)->gen >= 6) { seq_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]); seq_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]); + seq_printf(m, " SYNC_0: 0x%08x\n", + error->semaphore_mboxes[ring][0]); + seq_printf(m, " SYNC_1: 0x%08x\n", + error->semaphore_mboxes[ring][1]); } seq_printf(m, " seqno: 0x%08x\n", error->seqno[ring]); + seq_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]); + seq_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]); } static int i915_error_state(struct seq_file *m, void *unused) @@ -732,7 +738,7 @@ static int i915_error_state(struct seq_file *m, void *unused) drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_error_state *error; unsigned long flags; - int i, page, offset, elt; + int i, j, page, offset, elt; spin_lock_irqsave(&dev_priv->error_lock, flags); if (!dev_priv->first_error) { @@ -772,10 +778,10 @@ static int i915_error_state(struct seq_file *m, void *unused) error->pinned_bo, error->pinned_bo_count); - for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) { - if (error->batchbuffer[i]) { - struct drm_i915_error_object *obj = error->batchbuffer[i]; + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + struct drm_i915_error_object *obj; + if ((obj = error->ring[i].batchbuffer)) { seq_printf(m, "%s --- gtt_offset = 0x%08x\n", dev_priv->ring[i].name, obj->gtt_offset); @@ -787,11 +793,20 @@ static int i915_error_state(struct seq_file *m, void *unused) } } } - } - for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) { - if (error->ringbuffer[i]) { - struct drm_i915_error_object *obj = error->ringbuffer[i]; + if (error->ring[i].num_requests) { + seq_printf(m, "%s --- %d requests\n", + dev_priv->ring[i].name, + error->ring[i].num_requests); + for (j = 0; j < error->ring[i].num_requests; j++) { + seq_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n", + error->ring[i].requests[j].seqno, + error->ring[i].requests[j].jiffies, + error->ring[i].requests[j].tail); + } + } + + if ((obj = error->ring[i].ringbuffer)) { seq_printf(m, "%s --- ringbuffer = 0x%08x\n", dev_priv->ring[i].name, obj->gtt_offset); @@ -1431,7 +1446,57 @@ static int i915_swizzle_info(struct seq_file *m, void *data) I915_READ16(C0DRB3)); seq_printf(m, "C1DRB3 = 0x%04x\n", I915_READ16(C1DRB3)); + } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + seq_printf(m, "MAD_DIMM_C0 = 0x%08x\n", + I915_READ(MAD_DIMM_C0)); + seq_printf(m, "MAD_DIMM_C1 = 0x%08x\n", + I915_READ(MAD_DIMM_C1)); + seq_printf(m, "MAD_DIMM_C2 = 0x%08x\n", + I915_READ(MAD_DIMM_C2)); + seq_printf(m, "TILECTL = 0x%08x\n", + I915_READ(TILECTL)); + seq_printf(m, "ARB_MODE = 0x%08x\n", + I915_READ(ARB_MODE)); + seq_printf(m, "DISP_ARB_CTL = 0x%08x\n", + I915_READ(DISP_ARB_CTL)); + } + mutex_unlock(&dev->struct_mutex); + + return 0; +} + +static int i915_ppgtt_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *ring; + int i, ret; + + + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; + if (INTEL_INFO(dev)->gen == 6) + seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE)); + + for (i = 0; i < I915_NUM_RINGS; i++) { + ring = &dev_priv->ring[i]; + + seq_printf(m, "%s\n", ring->name); + if (INTEL_INFO(dev)->gen == 7) + seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(RING_MODE_GEN7(ring))); + seq_printf(m, "PP_DIR_BASE: 0x%08x\n", I915_READ(RING_PP_DIR_BASE(ring))); + seq_printf(m, "PP_DIR_BASE_READ: 0x%08x\n", I915_READ(RING_PP_DIR_BASE_READ(ring))); + seq_printf(m, "PP_DIR_DCLV: 0x%08x\n", I915_READ(RING_PP_DIR_DCLV(ring))); + } + if (dev_priv->mm.aliasing_ppgtt) { + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; + + seq_printf(m, "aliasing PPGTT:\n"); + seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd_offset); } + seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); mutex_unlock(&dev->struct_mutex); return 0; @@ -1778,6 +1843,7 @@ static struct drm_info_list i915_debugfs_list[] = { {"i915_context_status", i915_context_status, 0}, {"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0}, {"i915_swizzle_info", i915_swizzle_info, 0}, + {"i915_ppgtt_info", i915_ppgtt_info, 0}, }; #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index a8081f2efae..9341eb8ce93 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1196,22 +1196,39 @@ static int i915_load_gem_init(struct drm_device *dev) /* Basic memrange allocator for stolen space */ drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size); - /* Let GEM Manage all of the aperture. - * - * However, leave one page at the end still bound to the scratch page. - * There are a number of places where the hardware apparently - * prefetches past the end of the object, and we've seen multiple - * hangs with the GPU head pointer stuck in a batchbuffer bound - * at the last page of the aperture. One page should be enough to - * keep any prefetching inside of the aperture. - */ - i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE); - mutex_lock(&dev->struct_mutex); - ret = i915_gem_init_ringbuffer(dev); + if (i915_enable_ppgtt && HAS_ALIASING_PPGTT(dev)) { + /* PPGTT pdes are stolen from global gtt ptes, so shrink the + * aperture accordingly when using aliasing ppgtt. */ + gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE; + /* For paranoia keep the guard page in between. */ + gtt_size -= PAGE_SIZE; + + i915_gem_do_init(dev, 0, mappable_size, gtt_size); + + ret = i915_gem_init_aliasing_ppgtt(dev); + if (ret) + return ret; + } else { + /* Let GEM Manage all of the aperture. + * + * However, leave one page at the end still bound to the scratch + * page. There are a number of places where the hardware + * apparently prefetches past the end of the object, and we've + * seen multiple hangs with the GPU head pointer stuck in a + * batchbuffer bound at the last page of the aperture. One page + * should be enough to keep any prefetching inside of the + * aperture. + */ + i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE); + } + + ret = i915_gem_init_hw(dev); mutex_unlock(&dev->struct_mutex); - if (ret) + if (ret) { + i915_gem_cleanup_aliasing_ppgtt(dev); return ret; + } /* Try to set up FBC with a reasonable compressed buffer size */ if (I915_HAS_FBC(dev) && i915_powersave) { @@ -1298,6 +1315,7 @@ cleanup_gem: mutex_lock(&dev->struct_mutex); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + i915_gem_cleanup_aliasing_ppgtt(dev); cleanup_vga_switcheroo: vga_switcheroo_unregister_client(dev->pdev); cleanup_vga_client: @@ -2187,6 +2205,7 @@ int i915_driver_unload(struct drm_device *dev) i915_gem_free_all_phys_object(dev); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + i915_gem_cleanup_aliasing_ppgtt(dev); if (I915_HAS_FBC(dev) && i915_powersave) i915_cleanup_compression(dev); drm_mm_takedown(&dev_priv->mm.stolen); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 3d92d822c39..0694e170a33 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -103,6 +103,11 @@ MODULE_PARM_DESC(enable_hangcheck, "WARNING: Disabling this can cause system wide hangs. " "(default: true)"); +bool i915_enable_ppgtt __read_mostly = 1; +module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, bool, 0600); +MODULE_PARM_DESC(i915_enable_ppgtt, + "Enable PPGTT (default: true)"); + static struct drm_driver driver; extern int intel_agp_enabled; @@ -380,16 +385,27 @@ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv) spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); } +static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv) +{ + u32 gtfifodbg; + gtfifodbg = I915_READ_NOTRACE(GTFIFODBG); + if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK, + "MMIO read or write has been dropped %x\n", gtfifodbg)) + I915_WRITE_NOTRACE(GTFIFODBG, GT_FIFO_CPU_ERROR_MASK); +} + void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv) { I915_WRITE_NOTRACE(FORCEWAKE, 0); - POSTING_READ(FORCEWAKE); + /* The below doubles as a POSTING_READ */ + gen6_gt_check_fifodbg(dev_priv); } void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv) { I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 0); - POSTING_READ(FORCEWAKE_MT); + /* The below doubles as a POSTING_READ */ + gen6_gt_check_fifodbg(dev_priv); } /* @@ -405,8 +421,10 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv) spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); } -void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) +int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) { + int ret = 0; + if (dev_priv->gt_fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) { int loop = 500; u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); @@ -414,10 +432,13 @@ void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) udelay(10); fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); } - WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES); + if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES)) + ++ret; dev_priv->gt_fifo_count = fifo; } dev_priv->gt_fifo_count--; + + return ret; } static int i915_drm_freeze(struct drm_device *dev) @@ -498,7 +519,7 @@ static int i915_drm_thaw(struct drm_device *dev) mutex_lock(&dev->struct_mutex); dev_priv->mm.suspended = 0; - error = i915_gem_init_ringbuffer(dev); + error = i915_gem_init_hw(dev); mutex_unlock(&dev->struct_mutex); if (HAS_PCH_SPLIT(dev)) @@ -713,12 +734,16 @@ int i915_reset(struct drm_device *dev, u8 flags) !dev_priv->mm.suspended) { dev_priv->mm.suspended = 0; + i915_gem_init_swizzling(dev); + dev_priv->ring[RCS].init(&dev_priv->ring[RCS]); if (HAS_BSD(dev)) dev_priv->ring[VCS].init(&dev_priv->ring[VCS]); if (HAS_BLT(dev)) dev_priv->ring[BCS].init(&dev_priv->ring[BCS]); + i915_gem_init_ppgtt(dev); + mutex_unlock(&dev->struct_mutex); drm_irq_uninstall(dev); drm_mode_config_reset(dev); @@ -981,11 +1006,15 @@ __i915_read(64, q) #define __i915_write(x, y) \ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \ + u32 __fifo_ret = 0; \ trace_i915_reg_rw(true, reg, val, sizeof(val)); \ if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \ - __gen6_gt_wait_for_fifo(dev_priv); \ + __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ } \ write##y(val, dev_priv->regs + reg); \ + if (unlikely(__fifo_ret)) { \ + gen6_gt_check_fifodbg(dev_priv); \ + } \ } __i915_write(8, b) __i915_write(16, w) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 68a5338ea86..b8397282153 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -159,6 +159,10 @@ struct drm_i915_error_state { u32 ipehr[I915_NUM_RINGS]; u32 instdone[I915_NUM_RINGS]; u32 acthd[I915_NUM_RINGS]; + u32 semaphore_mboxes[I915_NUM_RINGS][I915_NUM_RINGS - 1]; + /* our own tracking of ring head and tail */ + u32 cpu_ring_head[I915_NUM_RINGS]; + u32 cpu_ring_tail[I915_NUM_RINGS]; u32 error; /* gen6+ */ u32 instpm[I915_NUM_RINGS]; u32 instps[I915_NUM_RINGS]; @@ -170,11 +174,19 @@ struct drm_i915_error_state { u32 faddr[I915_NUM_RINGS]; u64 fence[I915_MAX_NUM_FENCES]; struct timeval time; - struct drm_i915_error_object { - int page_count; - u32 gtt_offset; - u32 *pages[0]; - } *ringbuffer[I915_NUM_RINGS], *batchbuffer[I915_NUM_RINGS]; + struct drm_i915_error_ring { + struct drm_i915_error_object { + int page_count; + u32 gtt_offset; + u32 *pages[0]; + } *ringbuffer, *batchbuffer; + struct drm_i915_error_request { + long jiffies; + u32 seqno; + u32 tail; + } *requests; + int num_requests; + } ring[I915_NUM_RINGS]; struct drm_i915_error_buffer { u32 size; u32 name; @@ -254,6 +266,16 @@ struct intel_device_info { u8 has_llc:1; }; +#define I915_PPGTT_PD_ENTRIES 512 +#define I915_PPGTT_PT_ENTRIES 1024 +struct i915_hw_ppgtt { + unsigned num_pd_entries; + struct page **pt_pages; + uint32_t pd_offset; + dma_addr_t *pt_dma_addr; + dma_addr_t scratch_page_dma_addr; +}; + enum no_fbc_reason { FBC_NO_OUTPUT, /* no outputs enabled to compress */ FBC_STOLEN_TOO_SMALL, /* not enough space to hold compressed buffers */ @@ -299,6 +321,10 @@ typedef struct drm_i915_private { u32 reg0; } *gmbus; + /** gmbus_mutex protects against concurrent usage of the single hw gmbus + * controller on different i2c buses. */ + struct mutex gmbus_mutex; + struct pci_dev *bridge_dev; struct intel_ring_buffer ring[I915_NUM_RINGS]; uint32_t next_seqno; @@ -580,6 +606,9 @@ typedef struct drm_i915_private { struct io_mapping *gtt_mapping; int gtt_mtrr; + /** PPGTT used for aliasing the PPGTT with the GTT */ + struct i915_hw_ppgtt *aliasing_ppgtt; + struct shrinker inactive_shrinker; /** @@ -745,6 +774,13 @@ typedef struct drm_i915_private { struct drm_property *force_audio_property; } drm_i915_private_t; +enum hdmi_force_audio { + HDMI_AUDIO_OFF_DVI = -2, /* no aux data for HDMI-DVI converter */ + HDMI_AUDIO_OFF, /* force turn off HDMI audio */ + HDMI_AUDIO_AUTO, /* trust EDID */ + HDMI_AUDIO_ON, /* force turn on HDMI audio */ +}; + enum i915_cache_level { I915_CACHE_NONE, I915_CACHE_LLC, @@ -837,6 +873,8 @@ struct drm_i915_gem_object { unsigned int cache_level:2; + unsigned int has_aliasing_ppgtt_mapping:1; + struct page **pages; /** @@ -914,6 +952,9 @@ struct drm_i915_gem_request { /** GEM sequence number associated with this request. */ uint32_t seqno; + /** Postion in the ringbuffer of the end of the request */ + u32 tail; + /** Time at which this request was emitted, in jiffies. */ unsigned long emitted_jiffies; @@ -973,6 +1014,8 @@ struct drm_i915_file_private { #define HAS_LLC(dev) (INTEL_INFO(dev)->has_llc) #define I915_NEED_GFX_HWS(dev) (INTEL_INFO(dev)->need_gfx_hws) +#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >=6) + #define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->overlay_needs_physical) @@ -1015,6 +1058,7 @@ extern int i915_vbt_sdvo_panel_type __read_mostly; extern int i915_enable_rc6 __read_mostly; extern int i915_enable_fbc __read_mostly; extern bool i915_enable_hangcheck __read_mostly; +extern bool i915_enable_ppgtt __read_mostly; extern int i915_suspend(struct drm_device *dev, pm_message_t state); extern int i915_resume(struct drm_device *dev); @@ -1155,12 +1199,7 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } -static inline u32 -i915_gem_next_request_seqno(struct intel_ring_buffer *ring) -{ - drm_i915_private_t *dev_priv = ring->dev->dev_private; - return ring->outstanding_lazy_request = dev_priv->next_seqno; -} +u32 i915_gem_next_request_seqno(struct intel_ring_buffer *ring); int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj, struct intel_ring_buffer *pipelined); @@ -1185,13 +1224,17 @@ i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) } void i915_gem_retire_requests(struct drm_device *dev); +void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring); + void i915_gem_reset(struct drm_device *dev); void i915_gem_clflush_object(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_set_domain(struct drm_i915_gem_object *obj, uint32_t read_domains, uint32_t write_domain); int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj); -int __must_check i915_gem_init_ringbuffer(struct drm_device *dev); +int __must_check i915_gem_init_hw(struct drm_device *dev); +void i915_gem_init_swizzling(struct drm_device *dev); +void i915_gem_init_ppgtt(struct drm_device *dev); void i915_gem_cleanup_ringbuffer(struct drm_device *dev); void i915_gem_do_init(struct drm_device *dev, unsigned long start, @@ -1231,6 +1274,14 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); /* i915_gem_gtt.c */ +int __must_check i915_gem_init_aliasing_ppgtt(struct drm_device *dev); +void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev); +void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj, + enum i915_cache_level cache_level); +void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj); + void i915_gem_restore_gtt_mappings(struct drm_device *dev); int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj); void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj, @@ -1369,7 +1420,7 @@ extern void intel_display_print_error_state(struct seq_file *m, */ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv); void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv); -void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); +int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); /* We give fast paths for the really cool registers */ #define NEEDS_FORCE_WAKE(dev_priv, reg) \ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 51a2b0c2a30..19a06c280b1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1576,6 +1576,28 @@ i915_gem_process_flushing_list(struct intel_ring_buffer *ring, } } +static u32 +i915_gem_get_seqno(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + u32 seqno = dev_priv->next_seqno; + + /* reserve 0 for non-seqno */ + if (++dev_priv->next_seqno == 0) + dev_priv->next_seqno = 1; + + return seqno; +} + +u32 +i915_gem_next_request_seqno(struct intel_ring_buffer *ring) +{ + if (ring->outstanding_lazy_request == 0) + ring->outstanding_lazy_request = i915_gem_get_seqno(ring->dev); + + return ring->outstanding_lazy_request; +} + int i915_add_request(struct intel_ring_buffer *ring, struct drm_file *file, @@ -1583,10 +1605,19 @@ i915_add_request(struct intel_ring_buffer *ring, { drm_i915_private_t *dev_priv = ring->dev->dev_private; uint32_t seqno; + u32 request_ring_position; int was_empty; int ret; BUG_ON(request == NULL); + seqno = i915_gem_next_request_seqno(ring); + + /* Record the position of the start of the request so that + * should we detect the updated seqno part-way through the + * GPU processing the request, we never over-estimate the + * position of the head. + */ + request_ring_position = intel_ring_get_tail(ring); ret = ring->add_request(ring, &seqno); if (ret) @@ -1596,6 +1627,7 @@ i915_add_request(struct intel_ring_buffer *ring, request->seqno = seqno; request->ring = ring; + request->tail = request_ring_position; request->emitted_jiffies = jiffies; was_empty = list_empty(&ring->request_list); list_add_tail(&request->list, &ring->request_list); @@ -1610,7 +1642,7 @@ i915_add_request(struct intel_ring_buffer *ring, spin_unlock(&file_priv->mm.lock); } - ring->outstanding_lazy_request = false; + ring->outstanding_lazy_request = 0; if (!dev_priv->mm.suspended) { if (i915_enable_hangcheck) { @@ -1732,7 +1764,7 @@ void i915_gem_reset(struct drm_device *dev) /** * This function clears the request list as sequence numbers are passed. */ -static void +void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) { uint32_t seqno; @@ -1760,6 +1792,12 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) break; trace_i915_gem_request_retire(ring, request->seqno); + /* We know the GPU must have read the request to have + * sent us the seqno + interrupt, so use the position + * of tail of the request to update the last known position + * of the GPU head. + */ + ring->last_retired_head = request->tail; list_del(&request->list); i915_gem_request_remove_from_client(request); @@ -2020,6 +2058,7 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj) int i915_gem_object_unbind(struct drm_i915_gem_object *obj) { + drm_i915_private_t *dev_priv = obj->base.dev->dev_private; int ret = 0; if (obj->gtt_space == NULL) @@ -2064,6 +2103,11 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj) trace_i915_gem_object_unbind(obj); i915_gem_gtt_unbind_object(obj); + if (obj->has_aliasing_ppgtt_mapping) { + i915_ppgtt_unbind_object(dev_priv->mm.aliasing_ppgtt, obj); + obj->has_aliasing_ppgtt_mapping = 0; + } + i915_gem_object_put_pages_gtt(obj); list_del_init(&obj->gtt_list); @@ -2882,6 +2926,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { + struct drm_device *dev = obj->base.dev; + drm_i915_private_t *dev_priv = dev->dev_private; int ret; if (obj->cache_level == cache_level) @@ -2910,6 +2956,9 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, } i915_gem_gtt_rebind_object(obj, cache_level); + if (obj->has_aliasing_ppgtt_mapping) + i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, + obj, cache_level); } if (cache_level == I915_CACHE_NONE) { @@ -3681,12 +3730,71 @@ i915_gem_idle(struct drm_device *dev) return 0; } +void i915_gem_init_swizzling(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen < 5 || + dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE) + return; + + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_TILE_SURFACE_SWIZZLING); + + if (IS_GEN5(dev)) + return; + + I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_SWZCTL); + if (IS_GEN6(dev)) + I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_SNB)); + else + I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_IVB)); +} + +void i915_gem_init_ppgtt(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + uint32_t pd_offset; + struct intel_ring_buffer *ring; + int i; + + if (!dev_priv->mm.aliasing_ppgtt) + return; + + pd_offset = dev_priv->mm.aliasing_ppgtt->pd_offset; + pd_offset /= 64; /* in cachelines, */ + pd_offset <<= 16; + + if (INTEL_INFO(dev)->gen == 6) { + uint32_t ecochk = I915_READ(GAM_ECOCHK); + I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT | + ECOCHK_PPGTT_CACHE64B); + I915_WRITE(GFX_MODE, GFX_MODE_ENABLE(GFX_PPGTT_ENABLE)); + } else if (INTEL_INFO(dev)->gen >= 7) { + I915_WRITE(GAM_ECOCHK, ECOCHK_PPGTT_CACHE64B); + /* GFX_MODE is per-ring on gen7+ */ + } + + for (i = 0; i < I915_NUM_RINGS; i++) { + ring = &dev_priv->ring[i]; + + if (INTEL_INFO(dev)->gen >= 7) + I915_WRITE(RING_MODE_GEN7(ring), + GFX_MODE_ENABLE(GFX_PPGTT_ENABLE)); + + I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G); + I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset); + } +} + int -i915_gem_init_ringbuffer(struct drm_device *dev) +i915_gem_init_hw(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; int ret; + i915_gem_init_swizzling(dev); + ret = intel_init_render_ring_buffer(dev); if (ret) return ret; @@ -3705,6 +3813,8 @@ i915_gem_init_ringbuffer(struct drm_device *dev) dev_priv->next_seqno = 1; + i915_gem_init_ppgtt(dev); + return 0; cleanup_bsd_ring: @@ -3742,7 +3852,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); dev_priv->mm.suspended = 0; - ret = i915_gem_init_ringbuffer(dev); + ret = i915_gem_init_hw(dev); if (ret != 0) { mutex_unlock(&dev->struct_mutex); return ret; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index c719df19b3d..81687af0089 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -287,14 +287,14 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, * exec_object list, so it should have a GTT space bound by now. */ if (unlikely(target_offset == 0)) { - DRM_ERROR("No GTT space found for object %d\n", + DRM_DEBUG("No GTT space found for object %d\n", reloc->target_handle); return ret; } /* Validate that the target is in a valid r/w GPU domain */ if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) { - DRM_ERROR("reloc with multiple write domains: " + DRM_DEBUG("reloc with multiple write domains: " "obj %p target %d offset %d " "read %08x write %08x", obj, reloc->target_handle, @@ -305,7 +305,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, } if (unlikely((reloc->write_domain | reloc->read_domains) & ~I915_GEM_GPU_DOMAINS)) { - DRM_ERROR("reloc with read/write non-GPU domains: " + DRM_DEBUG("reloc with read/write non-GPU domains: " "obj %p target %d offset %d " "read %08x write %08x", obj, reloc->target_handle, @@ -316,7 +316,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, } if (unlikely(reloc->write_domain && target_obj->pending_write_domain && reloc->write_domain != target_obj->pending_write_domain)) { - DRM_ERROR("Write domain conflict: " + DRM_DEBUG("Write domain conflict: " "obj %p target %d offset %d " "new %08x old %08x\n", obj, reloc->target_handle, @@ -337,7 +337,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, /* Check that the relocation address is valid... */ if (unlikely(reloc->offset > obj->base.size - 4)) { - DRM_ERROR("Relocation beyond object bounds: " + DRM_DEBUG("Relocation beyond object bounds: " "obj %p target %d offset %d size %d.\n", obj, reloc->target_handle, (int) reloc->offset, @@ -345,7 +345,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return ret; } if (unlikely(reloc->offset & 3)) { - DRM_ERROR("Relocation not 4-byte aligned: " + DRM_DEBUG("Relocation not 4-byte aligned: " "obj %p target %d offset %d.\n", obj, reloc->target_handle, (int) reloc->offset); @@ -515,6 +515,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct drm_file *file, struct list_head *objects) { + drm_i915_private_t *dev_priv = ring->dev->dev_private; struct drm_i915_gem_object *obj; int ret, retry; bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; @@ -623,6 +624,14 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, } i915_gem_object_unpin(obj); + + /* ... and ensure ppgtt mapping exist if needed. */ + if (dev_priv->mm.aliasing_ppgtt && !obj->has_aliasing_ppgtt_mapping) { + i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, + obj, obj->cache_level); + + obj->has_aliasing_ppgtt_mapping = 1; + } } if (ret != -ENOSPC || retry > 1) @@ -724,7 +733,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, obj = to_intel_bo(drm_gem_object_lookup(dev, file, exec[i].handle)); if (&obj->base == NULL) { - DRM_ERROR("Invalid object handle %d at index %d\n", + DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); ret = -ENOENT; goto err; @@ -1055,7 +1064,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, int ret, mode, i; if (!i915_gem_check_execbuffer(args)) { - DRM_ERROR("execbuf with invalid offset/length\n"); + DRM_DEBUG("execbuf with invalid offset/length\n"); return -EINVAL; } @@ -1070,20 +1079,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, break; case I915_EXEC_BSD: if (!HAS_BSD(dev)) { - DRM_ERROR("execbuf with invalid ring (BSD)\n"); + DRM_DEBUG("execbuf with invalid ring (BSD)\n"); return -EINVAL; } ring = &dev_priv->ring[VCS]; break; case I915_EXEC_BLT: if (!HAS_BLT(dev)) { - DRM_ERROR("execbuf with invalid ring (BLT)\n"); + DRM_DEBUG("execbuf with invalid ring (BLT)\n"); return -EINVAL; } ring = &dev_priv->ring[BCS]; break; default: - DRM_ERROR("execbuf with unknown ring: %d\n", + DRM_DEBUG("execbuf with unknown ring: %d\n", (int)(args->flags & I915_EXEC_RING_MASK)); return -EINVAL; } @@ -1109,18 +1118,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } break; default: - DRM_ERROR("execbuf with unknown constants: %d\n", mode); + DRM_DEBUG("execbuf with unknown constants: %d\n", mode); return -EINVAL; } if (args->buffer_count < 1) { - DRM_ERROR("execbuf with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); return -EINVAL; } if (args->num_cliprects != 0) { if (ring != &dev_priv->ring[RCS]) { - DRM_ERROR("clip rectangles are only valid with the render ring\n"); + DRM_DEBUG("clip rectangles are only valid with the render ring\n"); return -EINVAL; } @@ -1165,7 +1174,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, obj = to_intel_bo(drm_gem_object_lookup(dev, file, exec[i].handle)); if (&obj->base == NULL) { - DRM_ERROR("Invalid object handle %d at index %d\n", + DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); /* prevent error path from reading uninitialized data */ ret = -ENOENT; @@ -1173,7 +1182,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } if (!list_empty(&obj->exec_list)) { - DRM_ERROR("Object %p [handle %d, index %d] appears more than once in object list\n", + DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", obj, exec[i].handle, i); ret = -EINVAL; goto err; @@ -1211,7 +1220,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, /* Set the pending read domains for the batch buffer to COMMAND */ if (batch_obj->base.pending_write_domain) { - DRM_ERROR("Attempting to use self-modifying batch buffer\n"); + DRM_DEBUG("Attempting to use self-modifying batch buffer\n"); ret = -EINVAL; goto err; } @@ -1316,7 +1325,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, int ret, i; if (args->buffer_count < 1) { - DRM_ERROR("execbuf with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); return -EINVAL; } @@ -1324,7 +1333,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count); exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); if (exec_list == NULL || exec2_list == NULL) { - DRM_ERROR("Failed to allocate exec list for %d buffers\n", + DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); drm_free_large(exec_list); drm_free_large(exec2_list); @@ -1335,7 +1344,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, (uintptr_t) args->buffers_ptr, sizeof(*exec_list) * args->buffer_count); if (ret != 0) { - DRM_ERROR("copy %d exec entries failed %d\n", + DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); drm_free_large(exec_list); drm_free_large(exec2_list); @@ -1376,7 +1385,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, sizeof(*exec_list) * args->buffer_count); if (ret) { ret = -EFAULT; - DRM_ERROR("failed to copy %d exec entries " + DRM_DEBUG("failed to copy %d exec entries " "back to user (%d)\n", args->buffer_count, ret); } @@ -1396,7 +1405,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, int ret; if (args->buffer_count < 1) { - DRM_ERROR("execbuf2 with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf2 with %d buffers\n", args->buffer_count); return -EINVAL; } @@ -1406,7 +1415,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); if (exec2_list == NULL) { - DRM_ERROR("Failed to allocate exec list for %d buffers\n", + DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); return -ENOMEM; } @@ -1415,7 +1424,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, (uintptr_t) args->buffers_ptr, sizeof(*exec2_list) * args->buffer_count); if (ret != 0) { - DRM_ERROR("copy %d exec entries failed %d\n", + DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); drm_free_large(exec2_list); return -EFAULT; @@ -1430,7 +1439,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, sizeof(*exec2_list) * args->buffer_count); if (ret) { ret = -EFAULT; - DRM_ERROR("failed to copy %d exec entries " + DRM_DEBUG("failed to copy %d exec entries " "back to user (%d)\n", args->buffer_count, ret); } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 11bddd5a5a6..2eacd78bb93 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -29,6 +29,279 @@ #include "i915_trace.h" #include "intel_drv.h" +/* PPGTT support for Sandybdrige/Gen6 and later */ +static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, + unsigned first_entry, + unsigned num_entries) +{ + uint32_t *pt_vaddr; + uint32_t scratch_pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned last_pte, i; + + scratch_pte = GEN6_PTE_ADDR_ENCODE(ppgtt->scratch_page_dma_addr); + scratch_pte |= GEN6_PTE_VALID | GEN6_PTE_CACHE_LLC; + + while (num_entries) { + last_pte = first_pte + num_entries; + if (last_pte > I915_PPGTT_PT_ENTRIES) + last_pte = I915_PPGTT_PT_ENTRIES; + + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (i = first_pte; i < last_pte; i++) + pt_vaddr[i] = scratch_pte; + + kunmap_atomic(pt_vaddr); + + num_entries -= last_pte - first_pte; + first_pte = 0; + act_pd++; + } +} + +int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_hw_ppgtt *ppgtt; + uint32_t pd_entry; + unsigned first_pd_entry_in_global_pt; + uint32_t __iomem *pd_addr; + int i; + int ret = -ENOMEM; + + /* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024 + * entries. For aliasing ppgtt support we just steal them at the end for + * now. */ + first_pd_entry_in_global_pt = 512*1024 - I915_PPGTT_PD_ENTRIES; + + ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL); + if (!ppgtt) + return ret; + + ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES; + ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries, + GFP_KERNEL); + if (!ppgtt->pt_pages) + goto err_ppgtt; + + for (i = 0; i < ppgtt->num_pd_entries; i++) { + ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL); + if (!ppgtt->pt_pages[i]) + goto err_pt_alloc; + } + + if (dev_priv->mm.gtt->needs_dmar) { + ppgtt->pt_dma_addr = kzalloc(sizeof(dma_addr_t) + *ppgtt->num_pd_entries, + GFP_KERNEL); + if (!ppgtt->pt_dma_addr) + goto err_pt_alloc; + } + + pd_addr = dev_priv->mm.gtt->gtt + first_pd_entry_in_global_pt; + for (i = 0; i < ppgtt->num_pd_entries; i++) { + dma_addr_t pt_addr; + if (dev_priv->mm.gtt->needs_dmar) { + pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], + 0, 4096, + PCI_DMA_BIDIRECTIONAL); + + if (pci_dma_mapping_error(dev->pdev, + pt_addr)) { + ret = -EIO; + goto err_pd_pin; + + } + ppgtt->pt_dma_addr[i] = pt_addr; + } else + pt_addr = page_to_phys(ppgtt->pt_pages[i]); + + pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr); + pd_entry |= GEN6_PDE_VALID; + + writel(pd_entry, pd_addr + i); + } + readl(pd_addr); + + ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma; + + i915_ppgtt_clear_range(ppgtt, 0, + ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES); + + ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(uint32_t); + + dev_priv->mm.aliasing_ppgtt = ppgtt; + + return 0; + +err_pd_pin: + if (ppgtt->pt_dma_addr) { + for (i--; i >= 0; i--) + pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i], + 4096, PCI_DMA_BIDIRECTIONAL); + } +err_pt_alloc: + kfree(ppgtt->pt_dma_addr); + for (i = 0; i < ppgtt->num_pd_entries; i++) { + if (ppgtt->pt_pages[i]) + __free_page(ppgtt->pt_pages[i]); + } + kfree(ppgtt->pt_pages); +err_ppgtt: + kfree(ppgtt); + + return ret; +} + +void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; + int i; + + if (!ppgtt) + return; + + if (ppgtt->pt_dma_addr) { + for (i = 0; i < ppgtt->num_pd_entries; i++) + pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i], + 4096, PCI_DMA_BIDIRECTIONAL); + } + + kfree(ppgtt->pt_dma_addr); + for (i = 0; i < ppgtt->num_pd_entries; i++) + __free_page(ppgtt->pt_pages[i]); + kfree(ppgtt->pt_pages); + kfree(ppgtt); +} + +static void i915_ppgtt_insert_sg_entries(struct i915_hw_ppgtt *ppgtt, + struct scatterlist *sg_list, + unsigned sg_len, + unsigned first_entry, + uint32_t pte_flags) +{ + uint32_t *pt_vaddr, pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned i, j, m, segment_len; + dma_addr_t page_addr; + struct scatterlist *sg; + + /* init sg walking */ + sg = sg_list; + i = 0; + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + + while (i < sg_len) { + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (j = first_pte; j < I915_PPGTT_PT_ENTRIES; j++) { + page_addr = sg_dma_address(sg) + (m << PAGE_SHIFT); + pte = GEN6_PTE_ADDR_ENCODE(page_addr); + pt_vaddr[j] = pte | pte_flags; + + /* grab the next page */ + m++; + if (m == segment_len) { + sg = sg_next(sg); + i++; + if (i == sg_len) + break; + + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + } + } + + kunmap_atomic(pt_vaddr); + + first_pte = 0; + act_pd++; + } +} + +static void i915_ppgtt_insert_pages(struct i915_hw_ppgtt *ppgtt, + unsigned first_entry, unsigned num_entries, + struct page **pages, uint32_t pte_flags) +{ + uint32_t *pt_vaddr, pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned last_pte, i; + dma_addr_t page_addr; + + while (num_entries) { + last_pte = first_pte + num_entries; + last_pte = min_t(unsigned, last_pte, I915_PPGTT_PT_ENTRIES); + + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (i = first_pte; i < last_pte; i++) { + page_addr = page_to_phys(*pages); + pte = GEN6_PTE_ADDR_ENCODE(page_addr); + pt_vaddr[i] = pte | pte_flags; + + pages++; + } + + kunmap_atomic(pt_vaddr); + + num_entries -= last_pte - first_pte; + first_pte = 0; + act_pd++; + } +} + +void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj, + enum i915_cache_level cache_level) +{ + struct drm_device *dev = obj->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t pte_flags = GEN6_PTE_VALID; + + switch (cache_level) { + case I915_CACHE_LLC_MLC: + pte_flags |= GEN6_PTE_CACHE_LLC_MLC; + break; + case I915_CACHE_LLC: + pte_flags |= GEN6_PTE_CACHE_LLC; + break; + case I915_CACHE_NONE: + pte_flags |= GEN6_PTE_UNCACHED; + break; + default: + BUG(); + } + + if (dev_priv->mm.gtt->needs_dmar) { + BUG_ON(!obj->sg_list); + + i915_ppgtt_insert_sg_entries(ppgtt, + obj->sg_list, + obj->num_sg, + obj->gtt_space->start >> PAGE_SHIFT, + pte_flags); + } else + i915_ppgtt_insert_pages(ppgtt, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT, + obj->pages, + pte_flags); +} + +void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj) +{ + i915_ppgtt_clear_range(ppgtt, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); +} + /* XXX kill agp_type! */ static unsigned int cache_level_to_agp_type(struct drm_device *dev, enum i915_cache_level cache_level) diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 861223bf394..1a930666598 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -93,8 +93,23 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN; if (INTEL_INFO(dev)->gen >= 6) { - swizzle_x = I915_BIT_6_SWIZZLE_NONE; - swizzle_y = I915_BIT_6_SWIZZLE_NONE; + uint32_t dimm_c0, dimm_c1; + dimm_c0 = I915_READ(MAD_DIMM_C0); + dimm_c1 = I915_READ(MAD_DIMM_C1); + dimm_c0 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK; + dimm_c1 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK; + /* Enable swizzling when the channels are populated with + * identically sized dimms. We don't need to check the 3rd + * channel because no cpu with gpu attached ships in that + * configuration. Also, swizzling only makes sense for 2 + * channels anyway. */ + if (dimm_c0 == dimm_c1) { + swizzle_x = I915_BIT_6_SWIZZLE_9_10; + swizzle_y = I915_BIT_6_SWIZZLE_9; + } else { + swizzle_x = I915_BIT_6_SWIZZLE_NONE; + swizzle_y = I915_BIT_6_SWIZZLE_NONE; + } } else if (IS_GEN5(dev)) { /* On Ironlake whatever DRAM config, GPU always do * same swizzling setup. diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 6442ff26964..afd4e03e337 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -788,11 +788,11 @@ i915_error_state_free(struct drm_device *dev, { int i; - for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) - i915_error_object_free(error->batchbuffer[i]); - - for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) - i915_error_object_free(error->ringbuffer[i]); + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + i915_error_object_free(error->ring[i].batchbuffer); + i915_error_object_free(error->ring[i].ringbuffer); + kfree(error->ring[i].requests); + } kfree(error->active_bo); kfree(error->overlay); @@ -903,6 +903,10 @@ static void i915_record_ring_state(struct drm_device *dev, if (INTEL_INFO(dev)->gen >= 6) { error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); + error->semaphore_mboxes[ring->id][0] + = I915_READ(RING_SYNC_0(ring->mmio_base)); + error->semaphore_mboxes[ring->id][1] + = I915_READ(RING_SYNC_1(ring->mmio_base)); } if (INTEL_INFO(dev)->gen >= 4) { @@ -925,6 +929,55 @@ static void i915_record_ring_state(struct drm_device *dev, error->acthd[ring->id] = intel_ring_get_active_head(ring); error->head[ring->id] = I915_READ_HEAD(ring); error->tail[ring->id] = I915_READ_TAIL(ring); + + error->cpu_ring_head[ring->id] = ring->head; + error->cpu_ring_tail[ring->id] = ring->tail; +} + +static void i915_gem_record_rings(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_request *request; + int i, count; + + for (i = 0; i < I915_NUM_RINGS; i++) { + struct intel_ring_buffer *ring = &dev_priv->ring[i]; + + if (ring->obj == NULL) + continue; + + i915_record_ring_state(dev, error, ring); + + error->ring[i].batchbuffer = + i915_error_first_batchbuffer(dev_priv, ring); + + error->ring[i].ringbuffer = + i915_error_object_create(dev_priv, ring->obj); + + count = 0; + list_for_each_entry(request, &ring->request_list, list) + count++; + + error->ring[i].num_requests = count; + error->ring[i].requests = + kmalloc(count*sizeof(struct drm_i915_error_request), + GFP_ATOMIC); + if (error->ring[i].requests == NULL) { + error->ring[i].num_requests = 0; + continue; + } + + count = 0; + list_for_each_entry(request, &ring->request_list, list) { + struct drm_i915_error_request *erq; + + erq = &error->ring[i].requests[count++]; + erq->seqno = request->seqno; + erq->jiffies = request->emitted_jiffies; + erq->tail = request->tail; + } + } } /** @@ -970,24 +1023,8 @@ static void i915_capture_error_state(struct drm_device *dev) error->done_reg = I915_READ(DONE_REG); } - i915_record_ring_state(dev, error, &dev_priv->ring[RCS]); - if (HAS_BLT(dev)) - i915_record_ring_state(dev, error, &dev_priv->ring[BCS]); - if (HAS_BSD(dev)) - i915_record_ring_state(dev, error, &dev_priv->ring[VCS]); - i915_gem_record_fences(dev, error); - - /* Record the active batch and ring buffers */ - for (i = 0; i < I915_NUM_RINGS; i++) { - error->batchbuffer[i] = - i915_error_first_batchbuffer(dev_priv, - &dev_priv->ring[i]); - - error->ringbuffer[i] = - i915_error_object_create(dev_priv, - dev_priv->ring[i].obj); - } + i915_gem_record_rings(dev, error); /* Record buffers on the active and pinned lists. */ error->active_bo = NULL; @@ -1778,18 +1815,6 @@ static void ironlake_irq_preinstall(struct drm_device *dev) I915_WRITE(HWSTAM, 0xeffe); - if (IS_GEN6(dev)) { - /* Workaround stalls observed on Sandy Bridge GPUs by - * making the blitter command streamer generate a - * write to the Hardware Status Page for - * MI_USER_INTERRUPT. This appears to serialize the - * previous seqno write out before the interrupt - * happens. - */ - I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT); - I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT); - } - /* XXX hotplug from PCH */ I915_WRITE(DEIMR, 0xffffffff); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f9607387c00..52a06be1d98 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -86,12 +86,45 @@ #define GEN6_MBC_SNPCR_LOW (2<<21) #define GEN6_MBC_SNPCR_MIN (3<<21) /* only 1/16th of the cache is shared */ +#define GEN6_MBCTL 0x0907c +#define GEN6_MBCTL_ENABLE_BOOT_FETCH (1 << 4) +#define GEN6_MBCTL_CTX_FETCH_NEEDED (1 << 3) +#define GEN6_MBCTL_BME_UPDATE_ENABLE (1 << 2) +#define GEN6_MBCTL_MAE_UPDATE_ENABLE (1 << 1) +#define GEN6_MBCTL_BOOT_FETCH_MECH (1 << 0) + #define GEN6_GDRST 0x941c #define GEN6_GRDOM_FULL (1 << 0) #define GEN6_GRDOM_RENDER (1 << 1) #define GEN6_GRDOM_MEDIA (1 << 2) #define GEN6_GRDOM_BLT (1 << 3) +/* PPGTT stuff */ +#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) + +#define GEN6_PDE_VALID (1 << 0) +#define GEN6_PDE_LARGE_PAGE (2 << 0) /* use 32kb pages */ +/* gen6+ has bit 11-4 for physical addr bit 39-32 */ +#define GEN6_PDE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) + +#define GEN6_PTE_VALID (1 << 0) +#define GEN6_PTE_UNCACHED (1 << 1) +#define GEN6_PTE_CACHE_LLC (2 << 1) +#define GEN6_PTE_CACHE_LLC_MLC (3 << 1) +#define GEN6_PTE_CACHE_BITS (3 << 1) +#define GEN6_PTE_GFDT (1 << 3) +#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) + +#define RING_PP_DIR_BASE(ring) ((ring)->mmio_base+0x228) +#define RING_PP_DIR_BASE_READ(ring) ((ring)->mmio_base+0x518) +#define RING_PP_DIR_DCLV(ring) ((ring)->mmio_base+0x220) +#define PP_DIR_DCLV_2G 0xffffffff + +#define GAM_ECOCHK 0x4090 +#define ECOCHK_SNB_BIT (1<<10) +#define ECOCHK_PPGTT_CACHE64B (0x3<<3) +#define ECOCHK_PPGTT_CACHE4B (0x0<<3) + /* VGA stuff */ #define VGA_ST01_MDA 0x3ba @@ -295,6 +328,12 @@ #define FENCE_REG_SANDYBRIDGE_0 0x100000 #define SANDYBRIDGE_FENCE_PITCH_SHIFT 32 +/* control register for cpu gtt access */ +#define TILECTL 0x101000 +#define TILECTL_SWZCTL (1 << 0) +#define TILECTL_TLB_PREFETCH_DIS (1 << 2) +#define TILECTL_BACKSNOOP_DIS (1 << 3) + /* * Instruction and interrupt control regs */ @@ -318,6 +357,11 @@ #define RING_MAX_IDLE(base) ((base)+0x54) #define RING_HWS_PGA(base) ((base)+0x80) #define RING_HWS_PGA_GEN6(base) ((base)+0x2080) +#define ARB_MODE 0x04030 +#define ARB_MODE_SWIZZLE_SNB (1<<4) +#define ARB_MODE_SWIZZLE_IVB (1<<5) +#define ARB_MODE_ENABLE(x) GFX_MODE_ENABLE(x) +#define ARB_MODE_DISABLE(x) GFX_MODE_DISABLE(x) #define RENDER_HWS_PGA_GEN7 (0x04080) #define RING_FAULT_REG(ring) (0x4094 + 0x100*(ring)->id) #define DONE_REG 0x40b0 @@ -395,6 +439,7 @@ #define GFX_MODE 0x02520 #define GFX_MODE_GEN7 0x0229c +#define RING_MODE_GEN7(ring) ((ring)->mmio_base+0x29c) #define GFX_RUN_LIST_ENABLE (1<<15) #define GFX_TLB_INVALIDATE_ALWAYS (1<<13) #define GFX_SURFACE_FAULT_ENABLE (1<<12) @@ -1037,6 +1082,29 @@ #define C0DRB3 0x10206 #define C1DRB3 0x10606 +/** snb MCH registers for reading the DRAM channel configuration */ +#define MAD_DIMM_C0 (MCHBAR_MIRROR_BASE_SNB + 0x5004) +#define MAD_DIMM_C1 (MCHBAR_MIRROR_BASE_SNB + 0x5008) +#define MAD_DIMM_C2 (MCHBAR_MIRROR_BASE_SNB + 0x500C) +#define MAD_DIMM_ECC_MASK (0x3 << 24) +#define MAD_DIMM_ECC_OFF (0x0 << 24) +#define MAD_DIMM_ECC_IO_ON_LOGIC_OFF (0x1 << 24) +#define MAD_DIMM_ECC_IO_OFF_LOGIC_ON (0x2 << 24) +#define MAD_DIMM_ECC_ON (0x3 << 24) +#define MAD_DIMM_ENH_INTERLEAVE (0x1 << 22) +#define MAD_DIMM_RANK_INTERLEAVE (0x1 << 21) +#define MAD_DIMM_B_WIDTH_X16 (0x1 << 20) /* X8 chips if unset */ +#define MAD_DIMM_A_WIDTH_X16 (0x1 << 19) /* X8 chips if unset */ +#define MAD_DIMM_B_DUAL_RANK (0x1 << 18) +#define MAD_DIMM_A_DUAL_RANK (0x1 << 17) +#define MAD_DIMM_A_SELECT (0x1 << 16) +/* DIMM sizes are in multiples of 256mb. */ +#define MAD_DIMM_B_SIZE_SHIFT 8 +#define MAD_DIMM_B_SIZE_MASK (0xff << MAD_DIMM_B_SIZE_SHIFT) +#define MAD_DIMM_A_SIZE_SHIFT 0 +#define MAD_DIMM_A_SIZE_MASK (0xff << MAD_DIMM_A_SIZE_SHIFT) + + /* Clocking configuration register */ #define CLKCFG 0x10c00 #define CLKCFG_FSB_400 (5 << 0) /* hrawclk 100 */ @@ -1316,6 +1384,7 @@ #define _VSYNC_A 0x60014 #define _PIPEASRC 0x6001c #define _BCLRPAT_A 0x60020 +#define _VSYNCSHIFT_A 0x60028 /* Pipe B timing regs */ #define _HTOTAL_B 0x61000 @@ -1326,6 +1395,8 @@ #define _VSYNC_B 0x61014 #define _PIPEBSRC 0x6101c #define _BCLRPAT_B 0x61020 +#define _VSYNCSHIFT_B 0x61028 + #define HTOTAL(pipe) _PIPE(pipe, _HTOTAL_A, _HTOTAL_B) #define HBLANK(pipe) _PIPE(pipe, _HBLANK_A, _HBLANK_B) @@ -1334,6 +1405,7 @@ #define VBLANK(pipe) _PIPE(pipe, _VBLANK_A, _VBLANK_B) #define VSYNC(pipe) _PIPE(pipe, _VSYNC_A, _VSYNC_B) #define BCLRPAT(pipe) _PIPE(pipe, _BCLRPAT_A, _BCLRPAT_B) +#define VSYNCSHIFT(pipe) _PIPE(pipe, _VSYNCSHIFT_A, _VSYNCSHIFT_B) /* VGA port control */ #define ADPA 0x61100 @@ -2319,10 +2391,21 @@ #define PIPECONF_PALETTE 0 #define PIPECONF_GAMMA (1<<24) #define PIPECONF_FORCE_BORDER (1<<25) -#define PIPECONF_PROGRESSIVE (0 << 21) -#define PIPECONF_INTERLACE_W_FIELD_INDICATION (6 << 21) -#define PIPECONF_INTERLACE_FIELD_0_ONLY (7 << 21) #define PIPECONF_INTERLACE_MASK (7 << 21) +/* Note that pre-gen3 does not support interlaced display directly. Panel + * fitting must be disabled on pre-ilk for interlaced. */ +#define PIPECONF_PROGRESSIVE (0 << 21) +#define PIPECONF_INTERLACE_W_SYNC_SHIFT_PANEL (4 << 21) /* gen4 only */ +#define PIPECONF_INTERLACE_W_SYNC_SHIFT (5 << 21) /* gen4 only */ +#define PIPECONF_INTERLACE_W_FIELD_INDICATION (6 << 21) +#define PIPECONF_INTERLACE_FIELD_0_ONLY (7 << 21) /* gen3 only */ +/* Ironlake and later have a complete new set of values for interlaced. PFIT + * means panel fitter required, PF means progressive fetch, DBL means power + * saving pixel doubling. */ +#define PIPECONF_PFIT_PF_INTERLACED_ILK (1 << 21) +#define PIPECONF_INTERLACED_ILK (3 << 21) +#define PIPECONF_INTERLACED_DBL_ILK (4 << 21) /* ilk/snb only */ +#define PIPECONF_PFIT_PF_INTERLACED_DBL_ILK (5 << 21) /* ilk/snb only */ #define PIPECONF_CXSR_DOWNCLOCK (1<<16) #define PIPECONF_BPP_MASK (0x000000e0) #define PIPECONF_BPP_8 (0<<5) @@ -3205,6 +3288,7 @@ #define _TRANS_VSYNC_A 0xe0014 #define TRANS_VSYNC_END_SHIFT 16 #define TRANS_VSYNC_START_SHIFT 0 +#define _TRANS_VSYNCSHIFT_A 0xe0028 #define _TRANSA_DATA_M1 0xe0030 #define _TRANSA_DATA_N1 0xe0034 @@ -3235,6 +3319,7 @@ #define _TRANS_VTOTAL_B 0xe100c #define _TRANS_VBLANK_B 0xe1010 #define _TRANS_VSYNC_B 0xe1014 +#define _TRANS_VSYNCSHIFT_B 0xe1028 #define TRANS_HTOTAL(pipe) _PIPE(pipe, _TRANS_HTOTAL_A, _TRANS_HTOTAL_B) #define TRANS_HBLANK(pipe) _PIPE(pipe, _TRANS_HBLANK_A, _TRANS_HBLANK_B) @@ -3242,6 +3327,8 @@ #define TRANS_VTOTAL(pipe) _PIPE(pipe, _TRANS_VTOTAL_A, _TRANS_VTOTAL_B) #define TRANS_VBLANK(pipe) _PIPE(pipe, _TRANS_VBLANK_A, _TRANS_VBLANK_B) #define TRANS_VSYNC(pipe) _PIPE(pipe, _TRANS_VSYNC_A, _TRANS_VSYNC_B) +#define TRANS_VSYNCSHIFT(pipe) _PIPE(pipe, _TRANS_VSYNCSHIFT_A, \ + _TRANS_VSYNCSHIFT_B) #define _TRANSB_DATA_M1 0xe1030 #define _TRANSB_DATA_N1 0xe1034 @@ -3275,7 +3362,10 @@ #define TRANS_FSYNC_DELAY_HB4 (3<<27) #define TRANS_DP_AUDIO_ONLY (1<<26) #define TRANS_DP_VIDEO_AUDIO (0<<26) +#define TRANS_INTERLACE_MASK (7<<21) #define TRANS_PROGRESSIVE (0<<21) +#define TRANS_INTERLACED (3<<21) +#define TRANS_LEGACY_INTERLACED_ILK (2<<21) #define TRANS_8BPC (0<<5) #define TRANS_10BPC (1<<5) #define TRANS_6BPC (2<<5) @@ -3614,6 +3704,12 @@ #define ECOBUS 0xa180 #define FORCEWAKE_MT_ENABLE (1<<5) +#define GTFIFODBG 0x120000 +#define GT_FIFO_CPU_ERROR_MASK 7 +#define GT_FIFO_OVFERR (1<<2) +#define GT_FIFO_IAWRERR (1<<1) +#define GT_FIFO_IARDERR (1<<0) + #define GT_FIFO_FREE_ENTRIES 0x120008 #define GT_FIFO_NUM_RESERVED_ENTRIES 20 diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index dd729d46a61..4d3d736a4f5 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -594,7 +594,10 @@ void intel_crt_init(struct drm_device *dev) 1 << INTEL_ANALOG_CLONE_BIT | 1 << INTEL_SDVO_LVDS_CLONE_BIT); crt->base.crtc_mask = (1 << 0) | (1 << 1); - connector->interlace_allowed = 1; + if (IS_GEN2(dev)) + connector->interlace_allowed = 0; + else + connector->interlace_allowed = 1; connector->doublescan_allowed = 0; drm_encoder_helper_add(&crt->base.base, &intel_crt_helper_funcs); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0a8a640d36e..b65dc04f128 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1266,7 +1266,8 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, enum pipe pipe) { int reg; - u32 val; + u32 val, pipeconf_val; + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; /* PCH only available on ILK+ */ BUG_ON(dev_priv->info->gen < 5); @@ -1280,6 +1281,7 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, reg = TRANSCONF(pipe); val = I915_READ(reg); + pipeconf_val = I915_READ(PIPECONF(pipe)); if (HAS_PCH_IBX(dev_priv->dev)) { /* @@ -1287,8 +1289,19 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, * that in pipeconf reg. */ val &= ~PIPE_BPC_MASK; - val |= I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK; + val |= pipeconf_val & PIPE_BPC_MASK; } + + val &= ~TRANS_INTERLACE_MASK; + if ((pipeconf_val & PIPECONF_INTERLACE_MASK) == PIPECONF_INTERLACED_ILK) + if (HAS_PCH_IBX(dev_priv->dev) && + intel_pipe_has_type(crtc, INTEL_OUTPUT_SDVO)) + val |= TRANS_LEGACY_INTERLACED_ILK; + else + val |= TRANS_INTERLACED; + else + val |= TRANS_PROGRESSIVE; + I915_WRITE(reg, val | TRANS_ENABLE); if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100)) DRM_ERROR("failed to enable transcoder %d\n", pipe); @@ -1901,7 +1914,7 @@ static void intel_update_fbc(struct drm_device *dev) if (enable_fbc < 0) { DRM_DEBUG_KMS("fbc set to per-chip default\n"); enable_fbc = 1; - if (INTEL_INFO(dev)->gen <= 5) + if (INTEL_INFO(dev)->gen <= 6) enable_fbc = 0; } if (!enable_fbc) { @@ -2973,6 +2986,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) I915_WRITE(TRANS_VTOTAL(pipe), I915_READ(VTOTAL(pipe))); I915_WRITE(TRANS_VBLANK(pipe), I915_READ(VBLANK(pipe))); I915_WRITE(TRANS_VSYNC(pipe), I915_READ(VSYNC(pipe))); + I915_WRITE(TRANS_VSYNCSHIFT(pipe), I915_READ(VSYNCSHIFT(pipe))); intel_fdi_normal_train(crtc); @@ -3437,11 +3451,8 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc, return false; } - /* XXX some encoders set the crtcinfo, others don't. - * Obviously we need some form of conflict resolution here... - */ - if (adjusted_mode->crtc_htotal == 0) - drm_mode_set_crtcinfo(adjusted_mode, 0); + /* All interlaced capable intel hw wants timings in frames. */ + drm_mode_set_crtcinfo(adjusted_mode, 0); return true; } @@ -5106,7 +5117,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, int plane = intel_crtc->plane; int refclk, num_connectors = 0; intel_clock_t clock, reduced_clock; - u32 dpll, dspcntr, pipeconf; + u32 dpll, dspcntr, pipeconf, vsyncshift; bool ok, has_reduced_clock = false, is_sdvo = false, is_dvo = false; bool is_crt = false, is_lvds = false, is_tv = false, is_dp = false; struct drm_mode_config *mode_config = &dev->mode_config; @@ -5387,17 +5398,22 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, } } - if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { + pipeconf &= ~PIPECONF_INTERLACE_MASK; + if (!IS_GEN2(dev) && + adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION; /* the chip adds 2 halflines automatically */ - adjusted_mode->crtc_vdisplay -= 1; adjusted_mode->crtc_vtotal -= 1; - adjusted_mode->crtc_vblank_start -= 1; adjusted_mode->crtc_vblank_end -= 1; - adjusted_mode->crtc_vsync_end -= 1; - adjusted_mode->crtc_vsync_start -= 1; - } else - pipeconf &= ~PIPECONF_INTERLACE_MASK; /* progressive */ + vsyncshift = adjusted_mode->crtc_hsync_start + - adjusted_mode->crtc_htotal/2; + } else { + pipeconf |= PIPECONF_PROGRESSIVE; + vsyncshift = 0; + } + + if (!IS_GEN3(dev)) + I915_WRITE(VSYNCSHIFT(pipe), vsyncshift); I915_WRITE(HTOTAL(pipe), (adjusted_mode->crtc_hdisplay - 1) | @@ -5979,17 +5995,19 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, } } + pipeconf &= ~PIPECONF_INTERLACE_MASK; if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { - pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION; + pipeconf |= PIPECONF_INTERLACED_ILK; /* the chip adds 2 halflines automatically */ - adjusted_mode->crtc_vdisplay -= 1; adjusted_mode->crtc_vtotal -= 1; - adjusted_mode->crtc_vblank_start -= 1; adjusted_mode->crtc_vblank_end -= 1; - adjusted_mode->crtc_vsync_end -= 1; - adjusted_mode->crtc_vsync_start -= 1; - } else - pipeconf &= ~PIPECONF_INTERLACE_W_FIELD_INDICATION; /* progressive */ + I915_WRITE(VSYNCSHIFT(pipe), + adjusted_mode->crtc_hsync_start + - adjusted_mode->crtc_htotal/2); + } else { + pipeconf |= PIPECONF_PROGRESSIVE; + I915_WRITE(VSYNCSHIFT(pipe), 0); + } I915_WRITE(HTOTAL(pipe), (adjusted_mode->crtc_hdisplay - 1) | @@ -6032,12 +6050,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, intel_wait_for_vblank(dev, pipe); - if (IS_GEN5(dev)) { - /* enable address swizzle for tiling buffer */ - temp = I915_READ(DISP_ARB_CTL); - I915_WRITE(DISP_ARB_CTL, temp | DISP_TILE_SURFACE_SWIZZLING); - } - I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); @@ -6999,9 +7011,7 @@ static void intel_increase_pllclock(struct drm_crtc *crtc) if (!HAS_PIPE_CXSR(dev) && (dpll & DISPLAY_RATE_SELECT_FPA1)) { DRM_DEBUG_DRIVER("upclocking LVDS\n"); - /* Unlock panel regs */ - I915_WRITE(PP_CONTROL, - I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); + assert_panel_unlocked(dev_priv, pipe); dpll &= ~DISPLAY_RATE_SELECT_FPA1; I915_WRITE(dpll_reg, dpll); @@ -7010,9 +7020,6 @@ static void intel_increase_pllclock(struct drm_crtc *crtc) dpll = I915_READ(dpll_reg); if (dpll & DISPLAY_RATE_SELECT_FPA1) DRM_DEBUG_DRIVER("failed to upclock LVDS!\n"); - - /* ...and lock them again */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) & 0x3); } /* Schedule downclock */ @@ -7042,9 +7049,7 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc) if (!HAS_PIPE_CXSR(dev) && intel_crtc->lowfreq_avail) { DRM_DEBUG_DRIVER("downclocking LVDS\n"); - /* Unlock panel regs */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) | - PANEL_UNLOCK_REGS); + assert_panel_unlocked(dev_priv, pipe); dpll |= DISPLAY_RATE_SELECT_FPA1; I915_WRITE(dpll_reg, dpll); @@ -7052,9 +7057,6 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc) dpll = I915_READ(dpll_reg); if (!(dpll & DISPLAY_RATE_SELECT_FPA1)) DRM_DEBUG_DRIVER("failed to downclock LVDS!\n"); - - /* ...and lock them again */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) & 0x3); } } @@ -7753,10 +7755,9 @@ static void intel_setup_outputs(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *encoder; bool dpd_is_edp = false; - bool has_lvds = false; + bool has_lvds; - if (IS_MOBILE(dev) && !IS_I830(dev)) - has_lvds = intel_lvds_init(dev); + has_lvds = intel_lvds_init(dev); if (!has_lvds && !HAS_PCH_SPLIT(dev)) { /* disable the panel fitter on everything but LVDS */ I915_WRITE(PFIT_CONTROL, 0); @@ -8234,6 +8235,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); u32 pcu_mbox, rc6_mask = 0; + u32 gtfifodbg; int cur_freq, min_freq, max_freq; int i; @@ -8245,6 +8247,13 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) */ I915_WRITE(GEN6_RC_STATE, 0); mutex_lock(&dev_priv->dev->struct_mutex); + + /* Clear the DBG now so we don't confuse earlier errors */ + if ((gtfifodbg = I915_READ(GTFIFODBG))) { + DRM_ERROR("GT fifo had a previous error %x\n", gtfifodbg); + I915_WRITE(GTFIFODBG, gtfifodbg); + } + gen6_gt_force_wake_get(dev_priv); /* disable the counters and set deterministic thresholds */ diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 8f1148c0410..39eccf908a6 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -208,17 +208,8 @@ intel_dp_link_clock(uint8_t link_bw) */ static int -intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock, int check_bpp) +intel_dp_link_required(int pixel_clock, int bpp) { - struct drm_crtc *crtc = intel_dp->base.base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int bpp = 24; - - if (check_bpp) - bpp = check_bpp; - else if (intel_crtc) - bpp = intel_crtc->bpp; - return (pixel_clock * bpp + 9) / 10; } @@ -245,12 +236,11 @@ intel_dp_mode_valid(struct drm_connector *connector, return MODE_PANEL; } - mode_rate = intel_dp_link_required(intel_dp, mode->clock, 0); + mode_rate = intel_dp_link_required(mode->clock, 24); max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes); if (mode_rate > max_rate) { - mode_rate = intel_dp_link_required(intel_dp, - mode->clock, 18); + mode_rate = intel_dp_link_required(mode->clock, 18); if (mode_rate > max_rate) return MODE_CLOCK_HIGH; else @@ -682,7 +672,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, int lane_count, clock; int max_lane_count = intel_dp_max_lane_count(intel_dp); int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0; - int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 0; + int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 24; static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 }; if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) { @@ -700,7 +690,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, for (clock = 0; clock <= max_clock; clock++) { int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count); - if (intel_dp_link_required(intel_dp, mode->clock, bpp) + if (intel_dp_link_required(mode->clock, bpp) <= link_avail) { intel_dp->link_bw = bws[clock]; intel_dp->lane_count = lane_count; diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 6eda1b51c63..020a7d7f744 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -157,7 +157,6 @@ static bool intel_dvo_mode_fixup(struct drm_encoder *encoder, C(vsync_end); C(vtotal); C(clock); - drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); #undef C } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 64541f7ef90..cae3e5f17a4 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -44,7 +44,7 @@ struct intel_hdmi { uint32_t color_range; bool has_hdmi_sink; bool has_audio; - int force_audio; + enum hdmi_force_audio force_audio; void (*write_infoframe)(struct drm_encoder *encoder, struct dip_infoframe *frame); }; @@ -339,7 +339,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) if (edid) { if (edid->input & DRM_EDID_INPUT_DIGITAL) { status = connector_status_connected; - intel_hdmi->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + if (intel_hdmi->force_audio != HDMI_AUDIO_OFF_DVI) + intel_hdmi->has_hdmi_sink = + drm_detect_hdmi_monitor(edid); intel_hdmi->has_audio = drm_detect_monitor_audio(edid); } connector->display_info.raw_edid = NULL; @@ -347,8 +349,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) } if (status == connector_status_connected) { - if (intel_hdmi->force_audio) - intel_hdmi->has_audio = intel_hdmi->force_audio > 0; + if (intel_hdmi->force_audio != HDMI_AUDIO_AUTO) + intel_hdmi->has_audio = + (intel_hdmi->force_audio == HDMI_AUDIO_ON); } return status; @@ -402,7 +405,7 @@ intel_hdmi_set_property(struct drm_connector *connector, return ret; if (property == dev_priv->force_audio_property) { - int i = val; + enum hdmi_force_audio i = val; bool has_audio; if (i == intel_hdmi->force_audio) @@ -410,13 +413,13 @@ intel_hdmi_set_property(struct drm_connector *connector, intel_hdmi->force_audio = i; - if (i == 0) + if (i == HDMI_AUDIO_AUTO) has_audio = intel_hdmi_detect_audio(connector); else - has_audio = i > 0; + has_audio = (i == HDMI_AUDIO_ON); - if (has_audio == intel_hdmi->has_audio) - return 0; + if (i == HDMI_AUDIO_OFF_DVI) + intel_hdmi->has_hdmi_sink = 0; intel_hdmi->has_audio = has_audio; goto done; @@ -514,7 +517,7 @@ void intel_hdmi_init(struct drm_device *dev, int sdvox_reg) intel_encoder->type = INTEL_OUTPUT_HDMI; connector->polled = DRM_CONNECTOR_POLL_HPD; - connector->interlace_allowed = 0; + connector->interlace_allowed = 1; connector->doublescan_allowed = 0; intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 03573e00471..068617f7256 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -233,11 +233,15 @@ gmbus_xfer(struct i2c_adapter *adapter, struct intel_gmbus, adapter); struct drm_i915_private *dev_priv = adapter->algo_data; - int i, reg_offset; + int i, reg_offset, ret; - if (bus->force_bit) - return intel_i2c_quirk_xfer(dev_priv, + mutex_lock(&dev_priv->gmbus_mutex); + + if (bus->force_bit) { + ret = intel_i2c_quirk_xfer(dev_priv, bus->force_bit, msgs, num); + goto out; + } reg_offset = HAS_PCH_SPLIT(dev_priv->dev) ? PCH_GMBUS0 - GMBUS0 : 0; @@ -321,7 +325,8 @@ done: * start of the next xfer, till then let it sleep. */ I915_WRITE(GMBUS0 + reg_offset, 0); - return i; + ret = i; + goto out; timeout: DRM_INFO("GMBUS timed out, falling back to bit banging on pin %d [%s]\n", @@ -331,9 +336,12 @@ timeout: /* Hardware may not support GMBUS over these pins? Try GPIO bitbanging instead. */ bus->force_bit = intel_gpio_create(dev_priv, bus->reg0 & 0xff); if (!bus->force_bit) - return -ENOMEM; - - return intel_i2c_quirk_xfer(dev_priv, bus->force_bit, msgs, num); + ret = -ENOMEM; + else + ret = intel_i2c_quirk_xfer(dev_priv, bus->force_bit, msgs, num); +out: + mutex_unlock(&dev_priv->gmbus_mutex); + return ret; } static u32 gmbus_func(struct i2c_adapter *adapter) @@ -380,6 +388,8 @@ int intel_setup_gmbus(struct drm_device *dev) if (dev_priv->gmbus == NULL) return -ENOMEM; + mutex_init(&dev_priv->gmbus_mutex); + for (i = 0; i < GMBUS_NUM_PORTS; i++) { struct intel_gmbus *bus = &dev_priv->gmbus[i]; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 798f6e1aa54..b103c3b2bfe 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -694,6 +694,14 @@ static const struct dmi_system_id intel_no_lvds[] = { }, { .callback = intel_no_lvds_dmi_callback, + .ident = "AOpen i45GMx-I", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"), + DMI_MATCH(DMI_BOARD_NAME, "i45GMx-I"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, .ident = "Aopen i945GTt-VFA", .matches = { DMI_MATCH(DMI_PRODUCT_VERSION, "AO00001JW"), @@ -836,6 +844,18 @@ static bool lvds_is_present_in_vbt(struct drm_device *dev, return false; } +static bool intel_lvds_supported(struct drm_device *dev) +{ + /* With the introduction of the PCH we gained a dedicated + * LVDS presence pin, use it. */ + if (HAS_PCH_SPLIT(dev)) + return true; + + /* Otherwise LVDS was only attached to mobile products, + * except for the inglorious 830gm */ + return IS_MOBILE(dev) && !IS_I830(dev); +} + /** * intel_lvds_init - setup LVDS connectors on this device * @dev: drm device @@ -857,6 +877,9 @@ bool intel_lvds_init(struct drm_device *dev) int pipe; u8 pin; + if (!intel_lvds_supported(dev)) + return false; + /* Skip init on machines we know falsely report LVDS */ if (dmi_check_system(intel_no_lvds)) return false; diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 961f75dbeae..2978a3f61b5 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -84,9 +84,10 @@ int intel_ddc_get_modes(struct drm_connector *connector, } static const struct drm_prop_enum_list force_audio_names[] = { - { -1, "off" }, - { 0, "auto" }, - { 1, "on" }, + { HDMI_AUDIO_OFF_DVI, "force-dvi" }, + { HDMI_AUDIO_OFF, "off" }, + { HDMI_AUDIO_AUTO, "auto" }, + { HDMI_AUDIO_ON, "on" }, }; void diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 23a543cdfa9..80b331c322f 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -25,8 +25,6 @@ * * Derived from Xorg ddx, xf86-video-intel, src/i830_video.c */ - -#include <linux/seq_file.h> #include "drmP.h" #include "drm.h" #include "i915_drm.h" @@ -264,7 +262,7 @@ i830_activate_pipe_a(struct drm_device *dev) DRM_DEBUG_DRIVER("Enabling pipe A in order to enable overlay\n"); mode = drm_mode_duplicate(dev, &vesa_640x480); - drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(mode, 0); if (!drm_crtc_helper_set_mode(&crtc->base, mode, crtc->base.x, crtc->base.y, crtc->base.fb)) @@ -937,10 +935,10 @@ static int check_overlay_dst(struct intel_overlay *overlay, { struct drm_display_mode *mode = &overlay->crtc->base.mode; - if (rec->dst_x < mode->crtc_hdisplay && - rec->dst_x + rec->dst_width <= mode->crtc_hdisplay && - rec->dst_y < mode->crtc_vdisplay && - rec->dst_y + rec->dst_height <= mode->crtc_vdisplay) + if (rec->dst_x < mode->hdisplay && + rec->dst_x + rec->dst_width <= mode->hdisplay && + rec->dst_y < mode->vdisplay && + rec->dst_y + rec->dst_height <= mode->vdisplay) return 0; else return -EINVAL; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index c935cdaa215..230a141dbea 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -48,7 +48,7 @@ intel_fixed_panel_mode(struct drm_display_mode *fixed_mode, adjusted_mode->clock = fixed_mode->clock; - drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(adjusted_mode, 0); } /* adjusted_mode has been preset to be the panel's fixed mode */ diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 4956f1bff52..ca3972f2c6f 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -52,20 +52,6 @@ static inline int ring_space(struct intel_ring_buffer *ring) return space; } -static u32 i915_gem_get_seqno(struct drm_device *dev) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - u32 seqno; - - seqno = dev_priv->next_seqno; - - /* reserve 0 for non-seqno */ - if (++dev_priv->next_seqno == 0) - dev_priv->next_seqno = 1; - - return seqno; -} - static int render_ring_flush(struct intel_ring_buffer *ring, u32 invalidate_domains, @@ -465,7 +451,7 @@ gen6_add_request(struct intel_ring_buffer *ring, mbox1_reg = ring->signal_mbox[0]; mbox2_reg = ring->signal_mbox[1]; - *seqno = i915_gem_get_seqno(ring->dev); + *seqno = i915_gem_next_request_seqno(ring); update_mboxes(ring, *seqno, mbox1_reg); update_mboxes(ring, *seqno, mbox2_reg); @@ -563,8 +549,7 @@ static int pc_render_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); struct pipe_control *pc = ring->private; u32 scratch_addr = pc->gtt_offset + 128; int ret; @@ -598,6 +583,7 @@ pc_render_add_request(struct intel_ring_buffer *ring, PIPE_CONTROL_FLUSH(ring, scratch_addr); scratch_addr += 128; PIPE_CONTROL_FLUSH(ring, scratch_addr); + intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_WRITE_FLUSH | PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE | @@ -615,8 +601,7 @@ static int render_ring_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); int ret; ret = intel_ring_begin(ring, 4); @@ -790,7 +775,7 @@ ring_add_request(struct intel_ring_buffer *ring, if (ret) return ret; - seqno = i915_gem_get_seqno(ring->dev); + seqno = i915_gem_next_request_seqno(ring); intel_ring_emit(ring, MI_STORE_DWORD_INDEX); intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT); @@ -814,8 +799,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag) /* It looks like we need to prevent the gt from suspending while waiting * for an notifiy irq, otherwise irqs seem to get lost on at least the * blt/bsd rings on ivb. */ - if (IS_GEN7(dev)) - gen6_gt_force_wake_get(dev_priv); + gen6_gt_force_wake_get(dev_priv); spin_lock(&ring->irq_lock); if (ring->irq_refcount++ == 0) { @@ -842,8 +826,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag) } spin_unlock(&ring->irq_lock); - if (IS_GEN7(dev)) - gen6_gt_force_wake_put(dev_priv); + gen6_gt_force_wake_put(dev_priv); } static bool @@ -1125,11 +1108,89 @@ static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring) return 0; } +static int intel_ring_wait_seqno(struct intel_ring_buffer *ring, u32 seqno) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + bool was_interruptible; + int ret; + + /* XXX As we have not yet audited all the paths to check that + * they are ready for ERESTARTSYS from intel_ring_begin, do not + * allow us to be interruptible by a signal. + */ + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + ret = i915_wait_request(ring, seqno, true); + + dev_priv->mm.interruptible = was_interruptible; + + return ret; +} + +static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) +{ + struct drm_i915_gem_request *request; + u32 seqno = 0; + int ret; + + i915_gem_retire_requests_ring(ring); + + if (ring->last_retired_head != -1) { + ring->head = ring->last_retired_head; + ring->last_retired_head = -1; + ring->space = ring_space(ring); + if (ring->space >= n) + return 0; + } + + list_for_each_entry(request, &ring->request_list, list) { + int space; + + if (request->tail == -1) + continue; + + space = request->tail - (ring->tail + 8); + if (space < 0) + space += ring->size; + if (space >= n) { + seqno = request->seqno; + break; + } + + /* Consume this request in case we need more space than + * is available and so need to prevent a race between + * updating last_retired_head and direct reads of + * I915_RING_HEAD. It also provides a nice sanity check. + */ + request->tail = -1; + } + + if (seqno == 0) + return -ENOSPC; + + ret = intel_ring_wait_seqno(ring, seqno); + if (ret) + return ret; + + if (WARN_ON(ring->last_retired_head == -1)) + return -ENOSPC; + + ring->head = ring->last_retired_head; + ring->last_retired_head = -1; + ring->space = ring_space(ring); + if (WARN_ON(ring->space < n)) + return -ENOSPC; + + return 0; +} + int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned long end; + int ret; u32 head; /* If the reported head position has wrapped or hasn't advanced, @@ -1143,6 +1204,10 @@ int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n) return 0; } + ret = intel_ring_wait_request(ring, n); + if (ret != -ENOSPC) + return ret; + trace_i915_ring_wait_begin(ring); if (drm_core_check_feature(dev, DRIVER_GEM)) /* With GEM the hangcheck timer should kick us out of the loop, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index c8b9cc0cd0d..bc0365b8fa4 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -46,6 +46,16 @@ struct intel_ring_buffer { int effective_size; struct intel_hw_status_page status_page; + /** We track the position of the requests in the ring buffer, and + * when each is retired we increment last_retired_head as the GPU + * must have finished processing the request and so we know we + * can advance the ringbuffer up to that position. + * + * last_retired_head is set to -1 after the value is consumed so + * we can detect new retirements. + */ + u32 last_retired_head; + spinlock_t irq_lock; u32 irq_refcount; u32 irq_mask; @@ -193,6 +203,11 @@ int intel_init_blt_ring_buffer(struct drm_device *dev); u32 intel_ring_get_active_head(struct intel_ring_buffer *ring); void intel_ring_setup_status_page(struct intel_ring_buffer *ring); +static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring) +{ + return ring->tail; +} + static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno) { if (ring->trace_irq_seqno == 0 && ring->irq_get(ring)) diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 80acc3f241e..724190ec496 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -944,7 +944,6 @@ intel_sdvo_set_input_timings_for_mode(struct intel_sdvo *intel_sdvo, intel_sdvo_get_mode_from_dtd(adjusted_mode, &intel_sdvo->input_dtd); - drm_mode_set_crtcinfo(adjusted_mode, 0); return true; } @@ -1985,7 +1984,7 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector, drm_connector_helper_add(&connector->base.base, &intel_sdvo_connector_helper_funcs); - connector->base.base.interlace_allowed = 0; + connector->base.base.interlace_allowed = 1; connector->base.base.doublescan_allowed = 0; connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB; diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 1571be37ce3..05f765ef546 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1240,7 +1240,7 @@ intel_tv_detect(struct drm_connector *connector, bool force) int type; mode = reported_modes[0]; - drm_mode_set_crtcinfo(&mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(&mode, 0); if (intel_tv->base.base.crtc && intel_tv->base.base.crtc->enabled) { type = intel_tv_detect_type(intel_tv, connector); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index b7a7102e965..1a816ea5122 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -3222,6 +3222,7 @@ static int evergreen_startup(struct radeon_device *rdev) if (r) { DRM_ERROR("radeon: failed testing IB (%d).\n", r); rdev->accel_working = false; + return r; } r = r600_audio_init(rdev); diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index b174620cc9b..0a0001b9dc7 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -15,6 +15,10 @@ const struct intel_gtt { unsigned int needs_dmar : 1; /* Whether we idle the gpu before mapping/unmapping */ unsigned int do_idle_maps : 1; + /* Share the scratch page dma with ppgtts. */ + dma_addr_t scratch_page_dma; + /* for ppgtt PDE access */ + u32 __iomem *gtt; } *intel_gtt_get(void); void intel_gtt_chipset_flush(void); |